Automatically merging tracking-igloo_kernel-other into merging-stable-linaro-ux500-3.1stable-linaro-ux500-3.1

Conflicting files:

994 files changed, 18726 insertions, 4828 deletions

diff --git a/Documentation/devicetree/bindings/arm/freescale.txt b/Documentation/devicetree/bindings/arm/freescale.txt
new file mode 100644
index 00000000000..8c52102b225
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/freescale.txt
@@ -0,0 +1,7 @@
+mx51 "Babbage" evalutation board
+Required root node properties:
+    - compatible = "fsl,mx51-babbage", "fsl,mx51";
+
+mx53 "Loco" evaluation board
+Required root node properties:
+    - compatible = "fsl,mx53-loco", "fsl,mx53";
diff --git a/Documentation/devicetree/bindings/arm/genesi.txt b/Documentation/devicetree/bindings/arm/genesi.txt
new file mode 100644
index 00000000000..b353489acd4
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/genesi.txt
@@ -0,0 +1,8 @@
+Genesi EfikaMX based on Freescale mx51
+Required root node properties:
+    - compatible = "genesi,efikamx", "fsl,mx51";
+
+Genesi EfikaMX Smartbook based on Freescale mx51
+Required root node properties:
+    - compatible = "genesi,efikasb", "fsl,mx51";
+
diff --git a/Documentation/devicetree/bindings/arm/l2cc.txt b/Documentation/devicetree/bindings/arm/l2cc.txt
new file mode 100644
index 00000000000..7ca52161e7a
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/l2cc.txt
@@ -0,0 +1,44 @@
+* ARM L2 Cache Controller
+
+ARM cores often have a separate level 2 cache controller. There are various
+implementations of the L2 cache controller with compatible programming models.
+The ARM L2 cache representation in the device tree should be done as follows:
+
+Required properties:
+
+- compatible : should be one of:
+	"arm,pl310-cache"
+	"arm,l220-cache"
+	"arm,l210-cache"
+- cache-unified : Specifies the cache is a unified cache.
+- cache-level : Should be set to 2 for a level 2 cache.
+- reg : Physical base address and size of cache controller's memory mapped
+  registers.
+
+Optional properties:
+
+- arm,data-latency : Cycles of latency for Data RAM accesses. Specifies 3 cells of
+  read, write and setup latencies. Minimum valid values are 1. Controllers
+  without setup latency control should use a value of 0.
+- arm,tag-latency : Cycles of latency for Tag RAM accesses. Specifies 3 cells of
+  read, write and setup latencies. Controllers without setup latency control
+  should use 0. Controllers without separate read and write Tag RAM latency
+  values should only use the first cell.
+- arm,dirty-latency : Cycles of latency for Dirty RAMs. This is a single cell.
+- arm,filter-ranges : <start length> Starting address and length of window to
+  filter. Addresses in the filter window are directed to the M1 port. Other
+  addresses will go to the M0 port.
+- interrupts : 1 combined interrupt.
+
+Example:
+
+L2: cache-controller {
+        compatible = "arm,pl310-cache";
+        reg = <0xfff12000 0x1000>;
+        arm,data-latency = <1 1 1>;
+        arm,tag-latency = <2 2 2>;
+        arm,filter-latency = <0x80000000 0x8000000>;
+        cache-unified;
+        cache-level = <2>;
+	interrupts = <45>;
+};
diff --git a/Documentation/devicetree/bindings/arm/primecell.txt b/Documentation/devicetree/bindings/arm/primecell.txt
index 1d5d7a870ec..951ca46789d 100644
--- a/Documentation/devicetree/bindings/arm/primecell.txt
+++ b/Documentation/devicetree/bindings/arm/primecell.txt
@@ -6,7 +6,9 @@ driver matching.
 
 Required properties:
 
-- compatible : should be a specific value for peripheral and "arm,primecell"
+- compatible : should be a specific name for the peripheral and
+               "arm,primecell".  The specific name will match the ARM
+               engineering name for the logic block in the form: "arm,pl???"
 
 Optional properties:
 
diff --git a/Documentation/devicetree/bindings/arm/samsung.txt b/Documentation/devicetree/bindings/arm/samsung.txt
new file mode 100644
index 00000000000..594cb97e3d8
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/samsung.txt
@@ -0,0 +1,9 @@
+Samsung Exynos4 S5PV310 SoC based SMDKV310 eval board
+
+    SMDKV310 eval board is based on S5PV310 SoC which belongs to
+    Samsung's Exynos4 family of application processors.
+
+Required root node properties:
+    - compatible = "samsung,smdkv310","samsung,s5pv310"
+        (a) "samsung,smdkv310" - for Samsung's SMDKV310 eval board.
+        (b) "samsung,s5pv310"  - for boards based on S5PV310 SoC.
diff --git a/Documentation/devicetree/bindings/gpio/pl061-gpio.txt b/Documentation/devicetree/bindings/gpio/pl061-gpio.txt
new file mode 100644
index 00000000000..a2c416bcbcc
--- /dev/null
+++ b/Documentation/devicetree/bindings/gpio/pl061-gpio.txt
@@ -0,0 +1,10 @@
+ARM PL061 GPIO controller
+
+Required properties:
+- compatible : "arm,pl061", "arm,primecell"
+- #gpio-cells : Should be two. The first cell is the pin number and the
+  second cell is used to specify optional parameters:
+  - bit 0 specifies polarity (0 for normal, 1 for inverted)
+- gpio-controller : Marks the device node as a GPIO controller.
+- interrupts : Interrupt mapping for GPIO IRQ.
+
diff --git a/Documentation/devicetree/bindings/spi/spi_pl022.txt b/Documentation/devicetree/bindings/spi/spi_pl022.txt
new file mode 100644
index 00000000000..306ec3ff3c0
--- /dev/null
+++ b/Documentation/devicetree/bindings/spi/spi_pl022.txt
@@ -0,0 +1,12 @@
+ARM PL022 SPI controller
+
+Required properties:
+- compatible : "arm,pl022", "arm,primecell"
+- reg : Offset and length of the register set for the device
+- interrupts : Should contain SPI controller interrupt
+
+Optional properties:
+- cs-gpios : should specify GPIOs used for chipselects.
+  The gpios will be referred to as reg = <index> in the SPI child nodes.
+  If unspecified, a single SPI device without a chip select can be used.
+
diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt
new file mode 100644
index 00000000000..e8552782b44
--- /dev/null
+++ b/Documentation/devicetree/bindings/vendor-prefixes.txt
@@ -0,0 +1,40 @@
+Device tree binding vendor prefix registry.  Keep list in alphabetical order.
+
+This isn't an exhaustive list, but you should add new prefixes to it before
+using them to avoid name-space collisions.
+
+adi	Analog Devices, Inc.
+amcc	Applied Micro Circuits Corporation (APM, formally AMCC)
+apm	Applied Micro Circuits Corporation (APM)
+arm	ARM Ltd.
+atmel	Atmel Corporation
+chrp	Common Hardware Reference Platform
+dallas	Maxim Integrated Products (formerly Dallas Semiconductor)
+denx	Denx Software Engineering
+epson	Seiko Epson Corp.
+est	ESTeem Wireless Modems
+fsl	Freescale Semiconductor
+GEFanuc	GE Fanuc Intelligent Platforms Embedded Systems, Inc.
+gef	GE Fanuc Intelligent Platforms Embedded Systems, Inc.
+hp	Hewlett Packard
+ibm	International Business Machines (IBM)
+idt	Integrated Device Technologies, Inc.
+intercontrol	Inter Control Group
+linux	Linux-specific binding
+marvell	Marvell Technology Group Ltd.
+maxim	Maxim Integrated Products
+mosaixtech	Mosaix Technologies, Inc.
+national	National Semiconductor
+nintendo	Nintendo
+nvidia	NVIDIA
+nxp	NXP Semiconductors
+powervr	Imagination Technologies
+qcom	Qualcomm, Inc.
+ramtron	Ramtron International
+samsung	Samsung Semiconductor
+schindler	Schindler
+simtek
+sirf	SiRF Technology, Inc.
+stericsson	ST-Ericsson
+ti	Texas Instruments
+xlnx	Xilinx
diff --git a/Documentation/devicetree/usage-model b/Documentation/devicetree/usage-model
new file mode 100644
index 00000000000..45e03b8dd04
--- /dev/null
+++ b/Documentation/devicetree/usage-model
@@ -0,0 +1,403 @@
+Linux and the Device Tree
+The Linux usage model for device tree data
+
+Author: Grant Likely <grant.likely@secretlab.ca>
+
+This article describes how Linux uses the device tree.  An overview of
+the device tree data format can be found at the <a
+href="http://devicetree.org/Device_Tree_Usage">Device Tree Usage</a>
+page on <a href="http://devicetree.org">devicetree.org</a>.
+
+
+	All the cool architectures are using device tree.  I want to
+	use device tree too!
+
+The "Open Firmware Device Tree", or simply Device Tree (DT), is a data
+structure and language for describing hardware.  More specifically, it
+is a description of hardware that is readable by an operating system
+so that the operating system doesn't need to hard code details of the
+machine.
+
+Structurally, the DT is a tree, or acyclic graph with named nodes, and
+nodes may have an arbitrary number of named properties encapsulating
+arbitrary data.  A mechanism also exists to create arbitrary
+links from one node to another outside of the natural tree structure.
+
+Conceptually, a common set of usage conventions, called 'bindings',
+is defined for how data should appear in the tree to describe typical
+hardware characteristics including data busses, interrupt lines, GPIO
+connections, and peripheral devices.
+
+As much as possible, hardware is described using existing bindings to
+maximize use of existing support code, but since property and node
+names are simply text strings, it is easy to extend existing bindings
+or create new ones by defining new nodes and properties.
+
+<h2>History</h2>
+The DT was originally created by Open Firmware as part of the
+communication method for passing data from Open Firmware to a client
+program (like to an operating system).  An operating system used the
+Device Tree to discover the topology of the hardware at runtime, and
+thereby support a majority of available hardware without hard coded
+information (assuming drivers were available for all devices).
+
+Since Open Firmware is commonly used on PowerPC and SPARC platforms,
+the Linux support for those architectures has for a long time used the
+Device Tree.
+
+In 2005, when PowerPC Linux began a major cleanup and to merge 32-bit
+and 64-bit support, the decision was made to require DT support on all
+powerpc platforms, regardless of whether or not they used Open
+Firmware.  To do this, a DT representation called the Flattened Device
+Tree (FDT) was created which could be passed to the kernel as a binary
+blob without requiring a real Open Firmware implementation.  U-Boot,
+kexec, and other bootloaders were modified to support both passing a
+Device Tree Binary (dtb) and to modify a dtb at boot time.
+
+Some time later, FDT infrastructure was generalized to be usable by
+all architectures.  At the time of this writing, 6 mainlined
+architectures (arm, microblaze, mips, powerpc, sparc, and x86) and 1
+out of mainline (nios) have some level of DT support.
+
+<h2>Data Model</h2>
+If you haven't already read the
+href="http://devicetree.org/Device_Tree_Usage">Device Tree Usage</a>
+page, then go read it now.  It's okay, I'll wait....
+
+<h3>High Level View</h3>
+The most important thing to understand is that the DT is simply a data
+structure that describes the hardware.  There is nothing magical about
+it, and it doesn't magically make all hardware configuration problems
+go away.  What it does do is provide a language for decoupling the
+hardware configuration from the board and device driver support in the
+Linux kernel (or any other operating system for that matter).  Using
+it allows board and device support to become data driven; to make
+setup decisions based on data passed into the kernel instead of on
+per-machine hard coded selections.
+
+Ideally, data driven platform setup should result in less code
+duplication and make it easier to support a wide range of hardware
+with a single kernel image.
+
+Linux uses DT data for three major purposes:
+1) platform identification,
+2) runtime configuration, and
+3) device population.
+
+<h4>Platform Identification</h4>
+First and foremost, the kernel will use data in the DT to identify the
+specific machine.  In a perfect world, the specific platform shouldn't
+matter to the kernel because all platform details would be described
+perfectly by the device tree in a consistent and reliable manner.
+Hardware is not perfect though, and so the kernel must identify the
+machine during early boot so that it has the opportunity to run
+machine-specific fixups.
+
+In the majority of cases, the machine identity is irrelevant, and the
+kernel will instead select setup code based on the machine's core
+CPU or SoC.  On ARM for example, setup_arch() in
+arch/arm/kernel/setup.c will call setup_machine_fdt() in
+arch/arm/kernel/devicetree.c which searches through the machine_desc
+table and selects the machine_desc which best matches the device tree
+data.  It determines the best match by looking at the 'compatible'
+property in the root device tree node, and comparing it with the
+dt_compat list in struct machine_desc.
+
+The 'compatible' property contains a sorted list of strings starting
+with the exact name of the machine, followed by an optional list of
+boards it is compatible with sorted from most compatible to least.  For
+example, the root compatible properties for the TI BeagleBoard and its
+successor, the BeagleBoard xM board might look like:
+
+	compatible = "ti,omap3-beagleboard", "ti,omap3450", "ti,omap3";
+	compatible = "ti,omap3-beagleboard-xm", "ti,omap3450", "ti,omap3";
+
+Where "ti,omap3-beagleboard-xm" specifies the exact model, it also
+claims that it compatible with the OMAP 3450 SoC, and the omap3 family
+of SoCs in general.  You'll notice that the list is sorted from most
+specific (exact board) to least specific (SoC family).
+
+Astute readers might point out that the Beagle xM could also claim
+compatibility with the original Beagle board.  However, one should be
+cautioned about doing so at the board level since there is typically a
+high level of change from one board to another, even within the same
+product line, and it is hard to nail down exactly what is meant when one
+board claims to be compatible with another.  For the top level, it is
+better to err on the side of caution and not claim one board is
+compatible with another.  The notable exception would be when one
+board is a carrier for another, such as a CPU module attached to a
+carrier board.
+
+One more note on compatible values.  Any string used in a compatible
+property must be documented as to what it indicates.  Add
+documentation for compatible strings in Documentation/devicetree/bindings.
+
+Again on ARM, for each machine_desc, the kernel looks to see if
+any of the dt_compat list entries appear in the compatible property.
+If one does, then that machine_desc is a candidate for driving the
+machine.  After searching the entire table of machine_descs,
+setup_machine_fdt() returns the 'most compatible' machine_desc based
+on which entry in the compatible property each machine_desc matches
+against.  If no matching machine_desc is found, then it returns NULL.
+
+The reasoning behind this scheme is the observation that in the majority
+of cases, a single machine_desc can support a large number of boards
+if they all use the same SoC, or same family of SoCs.  However,
+invariably there will be some exceptions where a specific board will
+require special setup code that is not useful in the generic case.
+Special cases could be handled by explicitly checking for the
+troublesome board(s) in generic setup code, but doing so very quickly
+becomes ugly and/or unmaintainable if it is more than just a couple of
+cases.
+
+Instead, the compatible list allows a generic machine_desc to provide
+support for a wide common set of boards by specifying "less
+compatible" value in the dt_compat list.  In the example above,
+generic board support can claim compatibility with "ti,omap3" or
+"ti,omap3450".  If a bug was discovered on the original beagleboard
+that required special workaround code during early boot, then a new
+machine_desc could be added which implements the workarounds and only
+matches on "ti,omap3-beagleboard".
+
+PowerPC uses a slightly different scheme where it calls the .probe()
+hook from each machine_desc, and the first one returning TRUE is used.
+However, this approach does not take into account the priority of the
+compatible list, and probably should be avoided for new architecture
+support.
+
+<h4>Runtime configuration</h4>
+In most cases, a DT will be the sole method of communicating data from
+firmware to the kernel, so also gets used to pass in runtime and
+configuration data like the kernel parameters string and the location
+of an initrd image.
+
+Most of this data is contained in the /chosen node, and when booting
+Linux it will look something like this:
+
+	chosen {
+		bootargs = "console=ttyS0,115200 loglevel=8";
+		initrd-start = &lt;0xc8000000&gt;;
+		initrd-end = &lt;0xc8200000&gt;;
+	};
+
+The bootargs property contains the kernel arguments, and the initrd-*
+properties define the address and size of an initrd blob.  The
+chosen node may also optionally contain an arbitrary number of
+additional properties for platform-specific configuration data.
+
+During early boot, the architecture setup code calls of_scan_flat_dt()
+several times with different helper callbacks to parse device tree
+data before paging is setup.  The of_scan_flat_dt() code scans through
+the device tree and uses the helpers to extract information required
+during early boot.  Typically the early_init_dt_scan_chosen() helper
+is used to parse the chosen node including kernel parameters,
+early_init_dt_scan_root() to initialize the DT address space model,
+and early_init_dt_scan_memory() to determine the size and
+location of usable RAM.
+
+On ARM, the function setup_machine_fdt() is responsible for early
+scanning of the device tree after selecting the correct machine_desc
+that supports the board.
+
+<h4>Device population</h4>
+After the board has been identified, and after the early configuration data
+has been parsed, then kernel initialization can proceed in the normal
+way.  At some point in this process, unflatten_device_tree() is called
+to convert the data into a more efficient runtime representation.
+This is also when machine-specific setup hooks will get called, like
+the machine_desc .init_early(), .init_irq() and .init_machine() hooks
+on ARM.  The remainder of this section uses examples from the ARM
+implementation, but all architectures will do pretty much the same
+thing when using a DT.
+
+As can be guessed by the names, .init_early() is used for any machine-
+specific setup that needs to be executed early in the boot process,
+and .init_irq() is used to set up interrupt handling.  Using a DT
+doesn't materially change the behaviour of either of these functions.
+If a DT is provided, then both .init_early() and .init_irq() are able
+to call any of the DT query functions (of_* in include/linux/of*.h) to
+get additional data about the platform.
+
+The most interesting hook in the DT context is .init_machine() which
+is primarily responsible for populating the Linux device model with
+data about the platform.  Historically this has been implemented on
+embedded platforms by defining a set of static clock structures,
+platform_devices, and other data in the board support .c file, and
+registering it en-masse in .init_machine().  When DT is used, then
+instead of hard coding static devices for each platform, the list of
+devices can be obtained by parsing the DT, and allocating device
+structures dynamically.
+
+The simplest case is when .init_machine() is only responsible for
+registering a block of platform_devices.  A platform_device is a concept
+used by Linux for memory or I/O mapped devices which cannot be detected
+by hardware, and for 'composite' or 'virtual' devices (more on those
+later).  While there is no 'platform device' terminology for the DT,
+platform devices roughly correspond to device nodes at the root of the
+tree and children of simple memory mapped bus nodes.
+
+About now is a good time to lay out an example.  Here is part of the
+device tree for the NVIDIA Tegra board.
+
+/{
+	compatible = "nvidia,harmony", "nvidia,tegra20";
+	#address-cells = <1>;
+	#size-cells = <1>;
+	interrupt-parent = <&intc>;
+
+	chosen { };
+	aliases { };
+
+	memory {
+		device_type = "memory";
+		reg = <0x00000000 0x40000000>;
+	};
+
+	soc {
+		compatible = "nvidia,tegra20-soc", "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges;
+
+		intc: interrupt-controller@50041000 {
+			compatible = "nvidia,tegra20-gic";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+			reg = <0x50041000 0x1000>, < 0x50040100 0x0100 >;
+		};
+
+		serial@70006300 {
+			compatible = "nvidia,tegra20-uart";
+			reg = <0x70006300 0x100>;
+			interrupts = <122>;
+		};
+
+		i2s-1: i2s@70002800 {
+			compatible = "nvidia,tegra20-i2s";
+			reg = <0x70002800 0x100>;
+			interrupts = <77>;
+			codec = <&wm8903>;
+		};
+
+		i2c@7000c000 {
+			compatible = "nvidia,tegra20-i2c";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			reg = <0x7000c000 0x100>;
+			interrupts = <70>;
+
+			wm8903: codec@1a {
+				compatible = "wlf,wm8903";
+				reg = <0x1a>;
+				interrupts = <347>;
+			};
+		};
+	};
+
+	sound {
+		compatible = "nvidia,harmony-sound";
+		i2s-controller = <&i2s-1>;
+		i2s-codec = <&wm8903>;
+	};
+};
+
+At .machine_init() time, Tegra board support code will need to look at
+this DT and decide which nodes to create platform_devices for.
+However, looking at the tree, it is not immediately obvious what kind
+of device each node represents, or even if a node represents a device
+at all.  The /chosen, /aliases, and /memory nodes are informational
+nodes that don't describe devices (although arguably memory could be
+considered a device).  The children of the /soc node are memory mapped
+devices, but the codec@1a is an i2c device, and the sound node
+represents not a device, but rather how other devices are connected
+together to create the audio subsystem.  I know what each device is
+because I'm familiar with the board design, but how does the kernel
+know what to do with each node?
+
+The trick is that the kernel starts at the root of the tree and looks
+for nodes that have a 'compatible' property.  First, it is generally
+assumed that any node with a 'compatible' property represents a device
+of some kind, and second, it can be assumed that any node at the root
+of the tree is either directly attached to the processor bus, or is a
+miscellaneous system device that cannot be described any other way.
+For each of these nodes, Linux allocates and registers a
+platform_device, which in turn may get bound to a platform_driver.
+
+Why is using a platform_device for these nodes a safe assumption?
+Well, for the way that Linux models devices, just about all bus_types
+assume that its devices are children of a bus controller.  For
+example, each i2c_client is a child of an i2c_master.  Each spi_device
+is a child of an SPI bus.  Similarly for USB, PCI, MDIO, etc.  The
+same hierarchy is also found in the DT, where I2C device nodes only
+ever appear as children of an I2C bus node.  Ditto for SPI, MDIO, USB,
+etc.  The only devices which do not require a specific type of parent
+device are platform_devices (and amba_devices, but more on that
+later), which will happily live at the base of the Linux /sys/devices
+tree.  Therefore, if a DT node is at the root of the tree, then it
+really probably is best registered as a platform_device.
+
+Linux board support code calls of_platform_populate(NULL, NULL, NULL)
+to kick off discovery of devices at the root of the tree.  The
+parameters are all NULL because when starting from the root of the
+tree, there is no need to provide a starting node (the first NULL), a
+parent struct device (the last NULL), and we're not using a match
+table (yet).  For a board that only needs to register devices,
+.init_machine() can be completely empty except for the
+of_platform_populate() call.
+
+In the Tegra example, this accounts for the /soc and /sound nodes, but
+what about the children of the SoC node?  Shouldn't they be registered
+as platform devices too?  For Linux DT support, the generic behaviour
+is for child devices to be registered by the parent's device driver at
+driver .probe() time.  So, an i2c bus device driver will register a
+i2c_client for each child node, an SPI bus driver will register
+its spi_device children, and similarly for other bus_types.
+According to that model, a driver could be written that binds to the
+SoC node and simply registers platform_devices for each of its
+children.  The board support code would allocate and register an SoC
+device, an SoC device driver would bind to the SoC device, and
+register platform_devices for /soc/interrupt-controller, /soc/serial,
+/soc/i2s, and /soc/i2c in its .probe() hook.  Easy, right?  Although
+it is a lot of mucking about for just registering platform devices.
+
+It turns out that registering children of certain platform_devices as
+more platform_devices is a common pattern, and the device tree support
+code reflects that.  The second argument to of_platform_populate() is
+an of_device_id table, and any node that matches an entry in that
+table will also get its child nodes registered.  In the tegra case,
+the code can look something like this:
+
+static struct of_device_id harmony_bus_ids[] __initdata = {
+	{ .compatible = "simple-bus", },
+	{}
+};
+
+static void __init harmony_init_machine(void)
+{
+	/* ... */
+	of_platform_populate(NULL, harmony_bus_ids, NULL);
+}
+
+"simple-bus" is defined in the ePAPR 1.0 specification as a property
+meaning a simple memory mapped bus, so the of_platform_populate() code
+could be written to just assume simple-bus compatible nodes will
+always be traversed.  However, we pass it in as an argument so that
+board support code can always override the default behaviour.
+
+<h2>Appendix A: AMBA devices</h2>
+
+ARM Primecells are a certain kind of device attached to the ARM AMBA
+bus which include some support for hardware detection and power
+management.  In Linux, struct amba_device and the amba_bus_type is
+used to represent Primecell devices.  However, the fiddly bit is that
+not all devices on an AMBA bus are Primecells, and for Linux it is
+typical for both amba_device and platform_device instances to be
+siblings of the same bus segment.
+
+When using the DT, this creates problems for of_platform_populate()
+because it must decide whether to register each node as either a
+platform_device or an amba_device.  This unfortunately complicates the
+device creation model a little bit, but the solution turns out not to
+be too invasive.  If a node is compatible with "arm,amba-primecell", then
+of_platform_populate() will register it as an amba_device instead of a
+platform_device.
diff --git a/Documentation/hwmon/exynos4_tmu b/Documentation/hwmon/exynos4_tmu
new file mode 100644
index 00000000000..c3c6b41db60
--- /dev/null
+++ b/Documentation/hwmon/exynos4_tmu
@@ -0,0 +1,81 @@
+Kernel driver exynos4_tmu
+=================
+
+Supported chips:
+* ARM SAMSUNG EXYNOS4 series of SoC
+  Prefix: 'exynos4-tmu'
+  Datasheet: Not publicly available
+
+Authors: Donggeun Kim <dg77.kim@samsung.com>
+
+Description
+-----------
+
+This driver allows to read temperature inside SAMSUNG EXYNOS4 series of SoC.
+
+The chip only exposes the measured 8-bit temperature code value
+through a register.
+Temperature can be taken from the temperature code.
+There are three equations converting from temperature to temperature code.
+
+The three equations are:
+  1. Two point trimming
+	Tc = (T - 25) * (TI2 - TI1) / (85 - 25) + TI1
+
+  2. One point trimming
+	Tc = T + TI1 - 25
+
+  3. No trimming
+	Tc = T + 50
+
+  Tc: Temperature code, T: Temperature,
+  TI1: Trimming info for 25 degree Celsius (stored at TRIMINFO register)
+       Temperature code measured at 25 degree Celsius which is unchanged
+  TI2: Trimming info for 85 degree Celsius (stored at TRIMINFO register)
+       Temperature code measured at 85 degree Celsius which is unchanged
+
+TMU(Thermal Management Unit) in EXYNOS4 generates interrupt
+when temperature exceeds pre-defined levels.
+The maximum number of configurable threshold is four.
+The threshold levels are defined as follows:
+  Level_0: current temperature > trigger_level_0 + threshold
+  Level_1: current temperature > trigger_level_1 + threshold
+  Level_2: current temperature > trigger_level_2 + threshold
+  Level_3: current temperature > trigger_level_3 + threshold
+
+  The threshold and each trigger_level are set
+  through the corresponding registers.
+
+When an interrupt occurs, this driver notify user space of
+one of four threshold levels for the interrupt
+through kobject_uevent_env and sysfs_notify functions.
+Although an interrupt condition for level_0 can be set,
+it is not notified to user space through sysfs_notify function.
+
+Sysfs Interface
+---------------
+name		name of the temperature sensor
+		RO
+
+temp1_input	temperature
+		RO
+
+temp1_max	temperature for level_1 interrupt
+		RO
+
+temp1_crit	temperature for level_2 interrupt
+		RO
+
+temp1_emergency	temperature for level_3 interrupt
+		RO
+
+temp1_max_alarm	alarm for level_1 interrupt
+		RO
+
+temp1_crit_alarm
+		alarm for level_2 interrupt
+		RO
+
+temp1_emergency_alarm
+		alarm for level_3 interrupt
+		RO
diff --git a/Documentation/hwspinlock.txt b/Documentation/hwspinlock.txt
index 7dcd1a4e726..69966813d59 100644
--- a/Documentation/hwspinlock.txt
+++ b/Documentation/hwspinlock.txt
@@ -39,23 +39,20 @@ independent, drivers.
      in case an unused hwspinlock isn't available. Users of this
      API will usually want to communicate the lock's id to the remote core
      before it can be used to achieve synchronization.
-     Can be called from an atomic context (this function will not sleep) but
-     not from within interrupt context.
+     Should be called from a process context (might sleep).
 
   struct hwspinlock *hwspin_lock_request_specific(unsigned int id);
    - assign a specific hwspinlock id and return its address, or NULL
      if that hwspinlock is already in use. Usually board code will
      be calling this function in order to reserve specific hwspinlock
      ids for predefined purposes.
-     Can be called from an atomic context (this function will not sleep) but
-     not from within interrupt context.
+     Should be called from a process context (might sleep).
 
   int hwspin_lock_free(struct hwspinlock *hwlock);
    - free a previously-assigned hwspinlock; returns 0 on success, or an
      appropriate error code on failure (e.g. -EINVAL if the hwspinlock
      is already free).
-     Can be called from an atomic context (this function will not sleep) but
-     not from within interrupt context.
+     Should be called from a process context (might sleep).
 
   int hwspin_lock_timeout(struct hwspinlock *hwlock, unsigned int timeout);
    - lock a previously-assigned hwspinlock with a timeout limit (specified in
@@ -232,15 +229,14 @@ int hwspinlock_example2(void)
 
   int hwspin_lock_register(struct hwspinlock *hwlock);
    - to be called from the underlying platform-specific implementation, in
-     order to register a new hwspinlock instance. Can be called from an atomic
-     context (this function will not sleep) but not from within interrupt
-     context. Returns 0 on success, or appropriate error code on failure.
+     order to register a new hwspinlock instance. Should be called from
+     a process context (this function might sleep).
+     Returns 0 on success, or appropriate error code on failure.
 
   struct hwspinlock *hwspin_lock_unregister(unsigned int id);
    - to be called from the underlying vendor-specific implementation, in order
      to unregister an existing (and unused) hwspinlock instance.
-     Can be called from an atomic context (will not sleep) but not from
-     within interrupt context.
+     Should be called from a process context (this function might sleep).
      Returns the address of hwspinlock on success, or NULL on error (e.g.
      if the hwspinlock is sill in use).
 
diff --git a/Documentation/power/runtime_pm.txt b/Documentation/power/runtime_pm.txt
index 6066e3a6b9a..d3710dc6d25 100644
--- a/Documentation/power/runtime_pm.txt
+++ b/Documentation/power/runtime_pm.txt
@@ -782,6 +782,16 @@ will behave normally, not taking the autosuspend delay into account.
 Similarly, if the power.use_autosuspend field isn't set then the autosuspend
 helper functions will behave just like the non-autosuspend counterparts.
 
+Under some circumstances a driver or subsystem may want to prevent a device
+from autosuspending immediately, even though the usage counter is zero and the
+autosuspend delay time has expired.  If the ->runtime_suspend() callback
+returns -EAGAIN or -EBUSY, and if the next autosuspend delay expiration time is
+in the future (as it normally would be if the callback invoked
+pm_runtime_mark_last_busy()), the PM core will automatically reschedule the
+autosuspend.  The ->runtime_suspend() callback can't do this rescheduling
+itself because no suspend requests of any kind are accepted while the device is
+suspending (i.e., while the callback is running).
+
 The implementation is well suited for asynchronous use in interrupt contexts.
 However such use inevitably involves races, because the PM core can't
 synchronize ->runtime_suspend() callbacks with the arrival of I/O requests.
diff --git a/Documentation/sound/alsa/HD-Audio-Models.txt b/Documentation/sound/alsa/HD-Audio-Models.txt
index d70c93bdcad..f8961402a85 100644
--- a/Documentation/sound/alsa/HD-Audio-Models.txt
+++ b/Documentation/sound/alsa/HD-Audio-Models.txt
@@ -408,6 +408,7 @@ STAC92HD83*
   ref		Reference board
   mic-ref	Reference board with power management for ports
   dell-s14	Dell laptop
+  dell-vostro-3500	Dell Vostro 3500 laptop
   hp		HP laptops with (inverted) mute-LED
   hp-dv7-4000	HP dv-7 4000
   auto		BIOS setup (default)
diff --git a/Documentation/stable_kernel_rules.txt b/Documentation/stable_kernel_rules.txt
index e213f45cf9d..21fd05c28e7 100644
--- a/Documentation/stable_kernel_rules.txt
+++ b/Documentation/stable_kernel_rules.txt
@@ -24,10 +24,10 @@ Rules on what kind of patches are accepted, and which ones are not, into the
 Procedure for submitting patches to the -stable tree:
 
  - Send the patch, after verifying that it follows the above rules, to
-   stable@kernel.org.  You must note the upstream commit ID in the changelog
-   of your submission.
+   stable@vger.kernel.org.  You must note the upstream commit ID in the
+   changelog of your submission.
  - To have the patch automatically included in the stable tree, add the tag
-     Cc: stable@kernel.org
+     Cc: stable@vger.kernel.org
    in the sign-off area. Once the patch is merged it will be applied to
    the stable tree without anything else needing to be done by the author
    or subsystem maintainer.
@@ -35,10 +35,10 @@ Procedure for submitting patches to the -stable tree:
    cherry-picked than this can be specified in the following format in
    the sign-off area:
 
-     Cc: <stable@kernel.org> # .32.x: a1f84a3: sched: Check for idle
-     Cc: <stable@kernel.org> # .32.x: 1b9508f: sched: Rate-limit newidle
-     Cc: <stable@kernel.org> # .32.x: fd21073: sched: Fix affinity logic
-     Cc: <stable@kernel.org> # .32.x
+     Cc: <stable@vger.kernel.org> # .32.x: a1f84a3: sched: Check for idle
+     Cc: <stable@vger.kernel.org> # .32.x: 1b9508f: sched: Rate-limit newidle
+     Cc: <stable@vger.kernel.org> # .32.x: fd21073: sched: Fix affinity logic
+     Cc: <stable@vger.kernel.org> # .32.x
     Signed-off-by: Ingo Molnar <mingo@elte.hu>
 
    The tag sequence has the meaning of:
diff --git a/Documentation/thermal/cpu-cooling-api.txt b/Documentation/thermal/cpu-cooling-api.txt
new file mode 100644
index 00000000000..d30b4f276a9
--- /dev/null
+++ b/Documentation/thermal/cpu-cooling-api.txt
@@ -0,0 +1,52 @@
+CPU cooling api's How To
+===================================
+
+Written by Amit Daniel Kachhap <amit.kachhap@linaro.org>
+
+Updated: 13 Dec 2011
+
+Copyright (c)  2011 Samsung Electronics Co., Ltd(http://www.samsung.com)
+
+0. Introduction
+
+The generic cpu cooling(freq clipping, cpuhotplug) provides
+registration/unregistration api's to the user. The binding of the cooling
+devices to the trip types is left for the user. The registration api's returns
+the cooling device pointer.
+
+1. cpufreq cooling api's
+
+1.1 cpufreq registration api's
+1.1.1 struct thermal_cooling_device *cpufreq_cooling_register(
+	struct freq_pctg_table *tab_ptr, unsigned int tab_size,
+	const struct cpumask *mask_val)
+
+    This interface function registers the cpufreq cooling device with the name
+	"thermal-cpufreq".
+
+    tab_ptr: The table containing the percentage of frequency to be clipped for
+    each cooling state.
+	.freq_clip_pctg[NR_CPUS]:Percentage of frequency to be clipped for each
+	 cpu.
+	.polling_interval: polling interval for this cooling state.
+    tab_size: the total number of cooling state.
+    mask_val: all the allowed cpu's where frequency clipping can happen.
+
+1.1.2 void cpufreq_cooling_unregister(void)
+
+    This interface function unregisters the "thermal-cpufreq" cooling device.
+
+
+1.2 cpuhotplug registration api's
+
+1.2.1 struct thermal_cooling_device *cpuhotplug_cooling_register(
+	const struct cpumask *mask_val)
+
+    This interface function registers the cpuhotplug cooling device with the name
+	"thermal-cpuhotplug".
+
+    mask_val: all the allowed cpu's which can be hotplugged out.
+
+1.1.2 void cpuhotplug_cooling_unregister(void)
+
+    This interface function unregisters the "thermal-cpuhotplug" cooling device.
diff --git a/Documentation/thermal/sysfs-api.txt b/Documentation/thermal/sysfs-api.txt
index b61e46f449a..5c1d44e0df5 100644
--- a/Documentation/thermal/sysfs-api.txt
+++ b/Documentation/thermal/sysfs-api.txt
@@ -184,8 +184,8 @@ trip_point_[0-*]_temp
 
 trip_point_[0-*]_type
 	Strings which indicate the type of the trip point.
-	E.g. it can be one of critical, hot, passive, active[0-*] for ACPI
-	thermal zone.
+	E.g. it can be one of critical, hot, passive, active[0-1],
+	state-active[0-*] for ACPI thermal zone.
 	RO, Optional
 
 cdev[0-*]
diff --git a/MAINTAINERS b/MAINTAINERS
index 6185d051358..48113e6815e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1230,7 +1230,7 @@ F:	Documentation/aoe/
 F:	drivers/block/aoe/
 
 ATHEROS ATH GENERIC UTILITIES
-M:	"Luis R. Rodriguez" <lrodriguez@atheros.com>
+M:	"Luis R. Rodriguez" <mcgrof@qca.qualcomm.com>
 L:	linux-wireless@vger.kernel.org
 S:	Supported
 F:	drivers/net/wireless/ath/*
@@ -1238,7 +1238,7 @@ F:	drivers/net/wireless/ath/*
 ATHEROS ATH5K WIRELESS DRIVER
 M:	Jiri Slaby <jirislaby@gmail.com>
 M:	Nick Kossifidis <mickflemm@gmail.com>
-M:	"Luis R. Rodriguez" <lrodriguez@atheros.com>
+M:	"Luis R. Rodriguez" <mcgrof@qca.qualcomm.com>
 M:	Bob Copeland <me@bobcopeland.com>
 L:	linux-wireless@vger.kernel.org
 L:	ath5k-devel@lists.ath5k.org
@@ -1247,10 +1247,10 @@ S:	Maintained
 F:	drivers/net/wireless/ath/ath5k/
 
 ATHEROS ATH9K WIRELESS DRIVER
-M:	"Luis R. Rodriguez" <lrodriguez@atheros.com>
-M:	Jouni Malinen <jmalinen@atheros.com>
-M:	Vasanthakumar Thiagarajan <vasanth@atheros.com>
-M:	Senthil Balasubramanian <senthilkumar@atheros.com>
+M:	"Luis R. Rodriguez" <mcgrof@qca.qualcomm.com>
+M:	Jouni Malinen <jouni@qca.qualcomm.com>
+M:	Vasanthakumar Thiagarajan <vthiagar@qca.qualcomm.com>
+M:	Senthil Balasubramanian <senthilb@qca.qualcomm.com>
 L:	linux-wireless@vger.kernel.org
 L:	ath9k-devel@lists.ath9k.org
 W:	http://wireless.kernel.org/en/users/Drivers/ath9k
@@ -4728,10 +4728,12 @@ F:	drivers/i2c/busses/i2c-ocores.c
 
 OPEN FIRMWARE AND FLATTENED DEVICE TREE
 M:	Grant Likely <grant.likely@secretlab.ca>
+M:	Rob Herring <rob.herring@calxeda.com>
 L:	devicetree-discuss@lists.ozlabs.org (moderated for non-subscribers)
 W:	http://fdt.secretlab.ca
 T:	git git://git.secretlab.ca/git/linux-2.6.git
 S:	Maintained
+F:	Documentation/devicetree
 F:	drivers/of
 F:	include/linux/of*.h
 K:	of_get_property
diff --git a/Makefile b/Makefile
index ae7cd870c7c..96a32106fc5 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
 VERSION = 3
 PATCHLEVEL = 1
-SUBLEVEL = 0
+SUBLEVEL = 5
 EXTRAVERSION =
 NAME = "Divemaster Edition"
 
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 0ec3f620d71..a1eafd50c55 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -29,6 +29,7 @@ config ARM
 	select HAVE_GENERIC_HARDIRQS
 	select HAVE_SPARSE_IRQ
 	select GENERIC_IRQ_SHOW
+	select CPU_PM if (SUSPEND || CPU_IDLE)
 	help
 	  The ARM series is a line of low-power-consumption RISC chip designs
 	  licensed by ARM Ltd and targeted at embedded applications and
@@ -1303,6 +1304,18 @@ config ARM_ERRATA_764369
 	  relevant cache maintenance functions and sets a specific bit
 	  in the diagnostic control register of the SCU.
 
+config PL310_ERRATA_769419
+	bool "PL310 errata: no automatic Store Buffer drain"
+	depends on CACHE_L2X0
+	help
+	  On revisions of the PL310 prior to r3p2, the Store Buffer does
+	  not automatically drain. This can cause normal, non-cacheable
+	  writes to be retained when the memory system is idle, leading
+	  to suboptimal I/O performance for drivers using coherent DMA.
+	  This option adds a write barrier to the cpu_idle loop so that,
+	  on systems with an outer cache, the store buffer is drained
+	  explicitly.
+
 endmenu
 
 source "arch/arm/common/Kconfig"
@@ -1413,6 +1426,31 @@ config SMP_ON_UP
 
 	  If you don't know what to do here, say Y.
 
+config ARM_CPU_TOPOLOGY
+	bool "Support cpu topology definition"
+	depends on SMP && CPU_V7
+	default y
+	help
+	  Support ARM cpu topology definition. The MPIDR register defines
+	  affinity between processors which is then used to describe the cpu
+	  topology of an ARM System.
+
+config SCHED_MC
+	bool "Multi-core scheduler support"
+	depends on ARM_CPU_TOPOLOGY
+	help
+	  Multi-core scheduler support improves the CPU scheduler's decision
+	  making when dealing with multi-core CPU chips at a cost of slightly
+	  increased overhead in some places. If unsure say N here.
+
+config SCHED_SMT
+	bool "SMT scheduler support"
+	depends on ARM_CPU_TOPOLOGY
+	help
+	  Improves the CPU scheduler's decision making when dealing with
+	  MultiThreading at a cost of slightly increased overhead in some
+	  places. If unsure say N here.
+
 config HAVE_ARM_SCU
 	bool
 	help
@@ -1815,6 +1853,38 @@ config ZBOOT_ROM_SH_MOBILE_SDHI
 
 endchoice
 
+config ARM_APPENDED_DTB
+	bool "Use appended device tree blob to zImage (EXPERIMENTAL)"
+	depends on OF && !ZBOOT_ROM && EXPERIMENTAL
+	help
+	  With this option, the boot code will look for a device tree binary
+	  (DTB) appended to zImage
+	  (e.g. cat zImage <filename>.dtb > zImage_w_dtb).
+
+	  This is meant as a backward compatibility convenience for those
+	  systems with a bootloader that can't be upgraded to accommodate
+	  the documented boot protocol using a device tree.
+
+	  Beware that there is very little in terms of protection against
+	  this option being confused by leftover garbage in memory that might
+	  look like a DTB header after a reboot if no actual DTB is appended
+	  to zImage.  Do not leave this option active in a production kernel
+	  if you don't intend to always append a DTB.  Proper passing of the
+	  location into r2 of a bootloader provided DTB is always preferable
+	  to this option.
+
+config ARM_ATAG_DTB_COMPAT
+	bool "Supplement the appended DTB with traditional ATAG information"
+	depends on ARM_APPENDED_DTB
+	help
+	  Some old bootloaders can't be updated to a DTB capable one, yet
+	  they provide ATAGs with memory configuration, the ramdisk address,
+	  the kernel cmdline string, etc.  Such information is dynamically
+	  provided by the bootloader and can't always be stored in a static
+	  DTB.  To allow a device tree enabled kernel to be used with such
+	  bootloaders, this option allows zImage to extract the information
+	  from the ATAG list and store it at run time into the appended DTB.
+
 config CMDLINE
 	string "Default kernel command string"
 	default ""
@@ -1853,7 +1923,7 @@ endchoice
 
 config XIP_KERNEL
 	bool "Kernel Execute-In-Place from ROM"
-	depends on !ZBOOT_ROM
+	depends on !ZBOOT_ROM && !ARM_LPAE
 	help
 	  Execute-In-Place allows the kernel to run from non-volatile storage
 	  directly addressable by the CPU, such as NOR flash. This saves RAM
diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug
index 5816849fa15..363b761b403 100644
--- a/arch/arm/Kconfig.debug
+++ b/arch/arm/Kconfig.debug
@@ -138,4 +138,10 @@ config DEBUG_S3C_UART
 	  The uncompressor code port configuration is now handled
 	  by CONFIG_S3C_LOWLEVEL_UART_PORT.
 
+config ARM_KPROBES_TEST
+	tristate "Kprobes test module"
+	depends on KPROBES && MODULES
+	help
+	  Perform tests of kprobes API and instruction set simulation.
+
 endmenu
diff --git a/arch/arm/boot/compressed/.gitignore b/arch/arm/boot/compressed/.gitignore
index c6028967d33..e0936a14851 100644
--- a/arch/arm/boot/compressed/.gitignore
+++ b/arch/arm/boot/compressed/.gitignore
@@ -5,3 +5,12 @@ piggy.lzo
 piggy.lzma
 vmlinux
 vmlinux.lds
+
+# borrowed libfdt files
+fdt.c
+fdt.h
+fdt_ro.c
+fdt_rw.c
+fdt_wip.c
+libfdt.h
+libfdt_internal.h
diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile
index 0c74a6fab95..e4f32a8e002 100644
--- a/arch/arm/boot/compressed/Makefile
+++ b/arch/arm/boot/compressed/Makefile
@@ -26,6 +26,10 @@ HEAD	= head.o
 OBJS	+= misc.o decompress.o
 FONTC	= $(srctree)/drivers/video/console/font_acorn_8x8.c
 
+# string library code (-Os is enforced to keep it much smaller)
+OBJS		+= string.o
+CFLAGS_string.o	:= -Os
+
 #
 # Architecture dependencies
 #
@@ -89,21 +93,41 @@ suffix_$(CONFIG_KERNEL_GZIP) = gzip
 suffix_$(CONFIG_KERNEL_LZO)  = lzo
 suffix_$(CONFIG_KERNEL_LZMA) = lzma
 
+# Borrowed libfdt files for the ATAG compatibility mode
+
+libfdt		:= fdt_rw.c fdt_ro.c fdt_wip.c fdt.c
+libfdt_hdrs	:= fdt.h libfdt.h libfdt_internal.h
+
+libfdt_objs	:= $(addsuffix .o, $(basename $(libfdt)))
+
+$(addprefix $(obj)/,$(libfdt) $(libfdt_hdrs)): $(obj)/%: $(srctree)/scripts/dtc/libfdt/%
+	$(call cmd,shipped)
+
+$(addprefix $(obj)/,$(libfdt_objs) atags_to_fdt.o): \
+	$(addprefix $(obj)/,$(libfdt_hdrs))
+
+ifeq ($(CONFIG_ARM_ATAG_DTB_COMPAT),y)
+OBJS	+= $(libfdt_objs) atags_to_fdt.o
+endif
+
 targets       := vmlinux vmlinux.lds \
 		 piggy.$(suffix_y) piggy.$(suffix_y).o \
-		 font.o font.c head.o misc.o $(OBJS)
+		 lib1funcs.o lib1funcs.S font.o font.c head.o misc.o $(OBJS)
 
 # Make sure files are removed during clean
-extra-y       += piggy.gzip piggy.lzo piggy.lzma lib1funcs.S
+extra-y       += piggy.gzip piggy.lzo piggy.lzma lib1funcs.S $(libfdt) $(libfdt_hdrs)
 
 ifeq ($(CONFIG_FUNCTION_TRACER),y)
 ORIG_CFLAGS := $(KBUILD_CFLAGS)
 KBUILD_CFLAGS = $(subst -pg, , $(ORIG_CFLAGS))
 endif
 
-ccflags-y := -fpic -fno-builtin
+ccflags-y := -fpic -fno-builtin -I$(obj)
 asflags-y := -Wa,-march=all
 
+# Supply kernel BSS size to the decompressor via a linker symbol.
+KBSS_SZ = $(shell size $(obj)/../../../../vmlinux | awk 'END{print $$3}')
+LDFLAGS_vmlinux = --defsym _kernel_bss_size=$(KBSS_SZ)
 # Supply ZRELADDR to the decompressor via a linker symbol.
 ifneq ($(CONFIG_AUTO_ZRELADDR),y)
 LDFLAGS_vmlinux += --defsym zreladdr=$(ZRELADDR)
@@ -123,7 +147,7 @@ LDFLAGS_vmlinux += -T
 # For __aeabi_uidivmod
 lib1funcs = $(obj)/lib1funcs.o
 
-$(obj)/lib1funcs.S: $(srctree)/arch/$(SRCARCH)/lib/lib1funcs.S FORCE
+$(obj)/lib1funcs.S: $(srctree)/arch/$(SRCARCH)/lib/lib1funcs.S
 	$(call cmd,shipped)
 
 # We need to prevent any GOTOFF relocs being used with references
diff --git a/arch/arm/boot/compressed/atags_to_fdt.c b/arch/arm/boot/compressed/atags_to_fdt.c
new file mode 100644
index 00000000000..6ce11c48117
--- /dev/null
+++ b/arch/arm/boot/compressed/atags_to_fdt.c
@@ -0,0 +1,97 @@
+#include <asm/setup.h>
+#include <libfdt.h>
+
+static int node_offset(void *fdt, const char *node_path)
+{
+	int offset = fdt_path_offset(fdt, node_path);
+	if (offset == -FDT_ERR_NOTFOUND)
+		offset = fdt_add_subnode(fdt, 0, node_path);
+	return offset;
+}
+
+static int setprop(void *fdt, const char *node_path, const char *property,
+		   uint32_t *val_array, int size)
+{
+	int offset = node_offset(fdt, node_path);
+	if (offset < 0)
+		return offset;
+	return fdt_setprop(fdt, offset, property, val_array, size);
+}
+
+static int setprop_string(void *fdt, const char *node_path,
+			  const char *property, const char *string)
+{
+	int offset = node_offset(fdt, node_path);
+	if (offset < 0)
+		return offset;
+	return fdt_setprop_string(fdt, offset, property, string);
+}
+
+static int setprop_cell(void *fdt, const char *node_path,
+			const char *property, uint32_t val)
+{
+	int offset = node_offset(fdt, node_path);
+	if (offset < 0)
+		return offset;
+	return fdt_setprop_cell(fdt, offset, property, val);
+}
+
+/*
+ * Convert and fold provided ATAGs into the provided FDT.
+ *
+ * REturn values:
+ *    = 0 -> pretend success
+ *    = 1 -> bad ATAG (may retry with another possible ATAG pointer)
+ *    < 0 -> error from libfdt
+ */
+int atags_to_fdt(void *atag_list, void *fdt, int total_space)
+{
+	struct tag *atag = atag_list;
+	uint32_t mem_reg_property[2 * NR_BANKS];
+	int memcount = 0;
+	int ret;
+
+	/* make sure we've got an aligned pointer */
+	if ((u32)atag_list & 0x3)
+		return 1;
+
+	/* if we get a DTB here we're done already */
+	if (*(u32 *)atag_list == fdt32_to_cpu(FDT_MAGIC))
+	       return 0;
+
+	/* validate the ATAG */
+	if (atag->hdr.tag != ATAG_CORE ||
+	    (atag->hdr.size != tag_size(tag_core) &&
+	     atag->hdr.size != 2))
+		return 1;
+
+	/* let's give it all the room it could need */
+	ret = fdt_open_into(fdt, fdt, total_space);
+	if (ret < 0)
+		return ret;
+
+	for_each_tag(atag, atag_list) {
+		if (atag->hdr.tag == ATAG_CMDLINE) {
+			setprop_string(fdt, "/chosen", "bootargs",
+					atag->u.cmdline.cmdline);
+		} else if (atag->hdr.tag == ATAG_MEM) {
+			if (memcount >= sizeof(mem_reg_property)/4)
+				continue;
+			mem_reg_property[memcount++] = cpu_to_fdt32(atag->u.mem.start);
+			mem_reg_property[memcount++] = cpu_to_fdt32(atag->u.mem.size);
+		} else if (atag->hdr.tag == ATAG_INITRD2) {
+			uint32_t initrd_start, initrd_size;
+			initrd_start = atag->u.initrd.start;
+			initrd_size = atag->u.initrd.size;
+			setprop_cell(fdt, "/chosen", "linux,initrd-start",
+					initrd_start);
+			setprop_cell(fdt, "/chosen", "linux,initrd-end",
+					initrd_start + initrd_size);
+		}
+	}
+
+	if (memcount)
+		setprop(fdt, "/memory", "reg", mem_reg_property, 4*memcount);
+
+	return fdt_pack(fdt);
+}
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index e95a5989602..7ffc0d85ac5 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -216,6 +216,103 @@ restart:	adr	r0, LC0
 		mov	r10, r6
 #endif
 
+		mov	r5, #0			@ init dtb size to 0
+#ifdef CONFIG_ARM_APPENDED_DTB
+/*
+ *   r0  = delta
+ *   r2  = BSS start
+ *   r3  = BSS end
+ *   r4  = final kernel address
+ *   r5  = appended dtb size (still unknown)
+ *   r6  = _edata
+ *   r7  = architecture ID
+ *   r8  = atags/device tree pointer
+ *   r9  = size of decompressed image
+ *   r10 = end of this image, including  bss/stack/malloc space if non XIP
+ *   r11 = GOT start
+ *   r12 = GOT end
+ *   sp  = stack pointer
+ *
+ * if there are device trees (dtb) appended to zImage, advance r10 so that the
+ * dtb data will get relocated along with the kernel if necessary.
+ */
+
+		ldr	lr, [r6, #0]
+#ifndef __ARMEB__
+		ldr	r1, =0xedfe0dd0		@ sig is 0xd00dfeed big endian
+#else
+		ldr	r1, =0xd00dfeed
+#endif
+		cmp	lr, r1
+		bne	dtb_check_done		@ not found
+
+#ifdef CONFIG_ARM_ATAG_DTB_COMPAT
+		/*
+		 * OK... Let's do some funky business here.
+		 * If we do have a DTB appended to zImage, and we do have
+		 * an ATAG list around, we want the later to be translated
+		 * and folded into the former here.  To be on the safe side,
+		 * let's temporarily move  the stack away into the malloc
+		 * area.  No GOT fixup has occurred yet, but none of the
+		 * code we're about to call uses any global variable.
+		*/
+		add	sp, sp, #0x10000
+		stmfd	sp!, {r0-r3, ip, lr}
+		mov	r0, r8
+		mov	r1, r6
+		sub	r2, sp, r6
+		bl	atags_to_fdt
+
+		/*
+		 * If returned value is 1, there is no ATAG at the location
+		 * pointed by r8.  Try the typical 0x100 offset from start
+		 * of RAM and hope for the best.
+		 */
+		cmp	r0, #1
+		sub	r0, r4, #(TEXT_OFFSET - 0x100)
+		mov	r1, r6
+		sub	r2, sp, r6
+		blne	atags_to_fdt
+
+		ldmfd	sp!, {r0-r3, ip, lr}
+		sub	sp, sp, #0x10000
+#endif
+
+		mov	r8, r6			@ use the appended device tree
+
+		/*
+		 * Make sure that the DTB doesn't end up in the final
+		 * kernel's .bss area. To do so, we adjust the decompressed
+		 * kernel size to compensate if that .bss size is larger
+		 * than the relocated code.
+		 */
+		ldr	r5, =_kernel_bss_size
+		adr	r1, wont_overwrite
+		sub	r1, r6, r1
+		subs	r1, r5, r1
+		addhi	r9, r9, r1
+
+		/* Get the dtb's size */
+		ldr	r5, [r6, #4]
+#ifndef __ARMEB__
+		/* convert r5 (dtb size) to little endian */
+		eor	r1, r5, r5, ror #16
+		bic	r1, r1, #0x00ff0000
+		mov	r5, r5, ror #8
+		eor	r5, r5, r1, lsr #8
+#endif
+
+		/* preserve 64-bit alignment */
+		add	r5, r5, #7
+		bic	r5, r5, #7
+
+		/* relocate some pointers past the appended dtb */
+		add	r6, r6, r5
+		add	r10, r10, r5
+		add	sp, sp, r5
+dtb_check_done:
+#endif
+
 /*
  * Check to see if we will overwrite ourselves.
  *   r4  = final kernel address
@@ -223,15 +320,14 @@ restart:	adr	r0, LC0
  *   r10 = end of this image, including  bss/stack/malloc space if non XIP
  * We basically want:
  *   r4 - 16k page directory >= r10 -> OK
- *   r4 + image length <= current position (pc) -> OK
+ *   r4 + image length <= address of wont_overwrite -> OK
  */
 		add	r10, r10, #16384
 		cmp	r4, r10
 		bhs	wont_overwrite
 		add	r10, r4, r9
-   ARM(		cmp	r10, pc		)
- THUMB(		mov	lr, pc		)
- THUMB(		cmp	r10, lr		)
+		adr	r9, wont_overwrite
+		cmp	r10, r9
 		bls	wont_overwrite
 
 /*
@@ -285,14 +381,16 @@ wont_overwrite:
  *   r2  = BSS start
  *   r3  = BSS end
  *   r4  = kernel execution address
+ *   r5  = appended dtb size (0 if not present)
  *   r7  = architecture ID
  *   r8  = atags pointer
  *   r11 = GOT start
  *   r12 = GOT end
  *   sp  = stack pointer
  */
-		teq	r0, #0
+		orrs	r1, r0, r5
 		beq	not_relocated
+
 		add	r11, r11, r0
 		add	r12, r12, r0
 
@@ -307,12 +405,21 @@ wont_overwrite:
 
 		/*
 		 * Relocate all entries in the GOT table.
+		 * Bump bss entries to _edata + dtb size
 		 */
 1:		ldr	r1, [r11, #0]		@ relocate entries in the GOT
-		add	r1, r1, r0		@ table.  This fixes up the
-		str	r1, [r11], #4		@ C references.
+		add	r1, r1, r0		@ This fixes up C references
+		cmp	r1, r2			@ if entry >= bss_start &&
+		cmphs	r3, r1			@       bss_end > entry
+		addhi	r1, r1, r5		@    entry += dtb size
+		str	r1, [r11], #4		@ next entry
 		cmp	r11, r12
 		blo	1b
+
+		/* bump our bss pointers too */
+		add	r2, r2, r5
+		add	r3, r3, r5
+
 #else
 
 		/*
@@ -551,6 +658,7 @@ __armv7_mmu_cache_on:
 		mcrne	p15, 0, r3, c2, c0, 0	@ load page table pointer
 		mcrne	p15, 0, r1, c3, c0, 0	@ load domain access control
 #endif
+		mcr	p15, 0, r0, c7, c5, 4	@ ISB
 		mcr	p15, 0, r0, c1, c0, 0	@ load control register
 		mrc	p15, 0, r0, c1, c0, 0	@ and read it back
 		mov	r0, #0
diff --git a/arch/arm/boot/compressed/libfdt_env.h b/arch/arm/boot/compressed/libfdt_env.h
new file mode 100644
index 00000000000..1f4e71876b0
--- /dev/null
+++ b/arch/arm/boot/compressed/libfdt_env.h
@@ -0,0 +1,15 @@
+#ifndef _ARM_LIBFDT_ENV_H
+#define _ARM_LIBFDT_ENV_H
+
+#include <linux/types.h>
+#include <linux/string.h>
+#include <asm/byteorder.h>
+
+#define fdt16_to_cpu(x)		be16_to_cpu(x)
+#define cpu_to_fdt16(x)		cpu_to_be16(x)
+#define fdt32_to_cpu(x)		be32_to_cpu(x)
+#define cpu_to_fdt32(x)		cpu_to_be32(x)
+#define fdt64_to_cpu(x)		be64_to_cpu(x)
+#define cpu_to_fdt64(x)		cpu_to_be64(x)
+
+#endif
diff --git a/arch/arm/boot/compressed/misc.c b/arch/arm/boot/compressed/misc.c
index 832d37236c5..8e2a8fca5ed 100644
--- a/arch/arm/boot/compressed/misc.c
+++ b/arch/arm/boot/compressed/misc.c
@@ -18,14 +18,9 @@
 
 unsigned int __machine_arch_type;
 
-#define _LINUX_STRING_H_
-
 #include <linux/compiler.h>	/* for inline */
-#include <linux/types.h>	/* for size_t */
-#include <linux/stddef.h>	/* for NULL */
+#include <linux/types.h>
 #include <linux/linkage.h>
-#include <asm/string.h>
-
 
 static void putstr(const char *ptr);
 extern void error(char *x);
@@ -101,41 +96,6 @@ static void putstr(const char *ptr)
 	flush();
 }
 
-
-void *memcpy(void *__dest, __const void *__src, size_t __n)
-{
-	int i = 0;
-	unsigned char *d = (unsigned char *)__dest, *s = (unsigned char *)__src;
-
-	for (i = __n >> 3; i > 0; i--) {
-		*d++ = *s++;
-		*d++ = *s++;
-		*d++ = *s++;
-		*d++ = *s++;
-		*d++ = *s++;
-		*d++ = *s++;
-		*d++ = *s++;
-		*d++ = *s++;
-	}
-
-	if (__n & 1 << 2) {
-		*d++ = *s++;
-		*d++ = *s++;
-		*d++ = *s++;
-		*d++ = *s++;
-	}
-
-	if (__n & 1 << 1) {
-		*d++ = *s++;
-		*d++ = *s++;
-	}
-
-	if (__n & 1)
-		*d++ = *s++;
-
-	return __dest;
-}
-
 /*
  * gzip declarations
  */
diff --git a/arch/arm/boot/compressed/string.c b/arch/arm/boot/compressed/string.c
new file mode 100644
index 00000000000..36e53ef9200
--- /dev/null
+++ b/arch/arm/boot/compressed/string.c
@@ -0,0 +1,127 @@
+/*
+ * arch/arm/boot/compressed/string.c
+ *
+ * Small subset of simple string routines
+ */
+
+#include <linux/string.h>
+
+void *memcpy(void *__dest, __const void *__src, size_t __n)
+{
+	int i = 0;
+	unsigned char *d = (unsigned char *)__dest, *s = (unsigned char *)__src;
+
+	for (i = __n >> 3; i > 0; i--) {
+		*d++ = *s++;
+		*d++ = *s++;
+		*d++ = *s++;
+		*d++ = *s++;
+		*d++ = *s++;
+		*d++ = *s++;
+		*d++ = *s++;
+		*d++ = *s++;
+	}
+
+	if (__n & 1 << 2) {
+		*d++ = *s++;
+		*d++ = *s++;
+		*d++ = *s++;
+		*d++ = *s++;
+	}
+
+	if (__n & 1 << 1) {
+		*d++ = *s++;
+		*d++ = *s++;
+	}
+
+	if (__n & 1)
+		*d++ = *s++;
+
+	return __dest;
+}
+
+void *memmove(void *__dest, __const void *__src, size_t count)
+{
+	unsigned char *d = __dest;
+	const unsigned char *s = __src;
+
+	if (__dest == __src)
+		return __dest;
+
+	if (__dest < __src)
+		return memcpy(__dest, __src, count);
+
+	while (count--)
+		d[count] = s[count];
+	return __dest;
+}
+
+size_t strlen(const char *s)
+{
+	const char *sc = s;
+
+	while (*sc != '\0')
+		sc++;
+	return sc - s;
+}
+
+int memcmp(const void *cs, const void *ct, size_t count)
+{
+	const unsigned char *su1 = cs, *su2 = ct, *end = su1 + count;
+	int res = 0;
+
+	while (su1 < end) {
+		res = *su1++ - *su2++;
+		if (res)
+			break;
+	}
+	return res;
+}
+
+int strcmp(const char *cs, const char *ct)
+{
+	unsigned char c1, c2;
+	int res = 0;
+
+	do {
+		c1 = *cs++;
+		c2 = *ct++;
+		res = c1 - c2;
+		if (res)
+			break;
+	} while (c1);
+	return res;
+}
+
+void *memchr(const void *s, int c, size_t count)
+{
+	const unsigned char *p = s;
+
+	while (count--)
+		if ((unsigned char)c == *p++)
+			return (void *)(p - 1);
+	return NULL;
+}
+
+char *strchr(const char *s, int c)
+{
+	while (*s != (char)c)
+		if (*s++ == '\0')
+			return NULL;
+	return (char *)s;
+}
+
+#undef memset
+
+void *memset(void *s, int c, size_t count)
+{
+	char *xs = s;
+	while (count--)
+		*xs++ = c;
+	return s;
+}
+
+void __memzero(void *s, size_t count)
+{
+	memset(s, 0, count);
+}
diff --git a/arch/arm/boot/compressed/vmlinux.lds.in b/arch/arm/boot/compressed/vmlinux.lds.in
index 4e728834a1b..4919f2ac8b8 100644
--- a/arch/arm/boot/compressed/vmlinux.lds.in
+++ b/arch/arm/boot/compressed/vmlinux.lds.in
@@ -51,6 +51,10 @@ SECTIONS
   _got_start = .;
   .got			: { *(.got) }
   _got_end = .;
+
+  /* ensure the zImage file size is always a multiple of 64 bits */
+  /* (without a dummy byte, ld just ignores the empty section) */
+  .pad			: { BYTE(0); . = ALIGN(8); }
   _edata = .;
 
   . = BSS_START;
diff --git a/arch/arm/boot/dts/exynos4-smdkv310.dts b/arch/arm/boot/dts/exynos4-smdkv310.dts
new file mode 100644
index 00000000000..dd6c80a7ffc
--- /dev/null
+++ b/arch/arm/boot/dts/exynos4-smdkv310.dts
@@ -0,0 +1,11 @@
+/dts-v1/;
+/include/ "skeleton.dtsi"
+
+/ {
+	model = "Samsung Exynos4 SMDKV310 eval board";
+	compatible = "samsung,smdkv310", "samsung,s5pv310";
+
+	memory {
+		reg = <0x40000000 0x08000000>;
+	};
+};
diff --git a/arch/arm/boot/dts/genesi-efikamx.dts b/arch/arm/boot/dts/genesi-efikamx.dts
new file mode 100644
index 00000000000..e81ffcc8443
--- /dev/null
+++ b/arch/arm/boot/dts/genesi-efikamx.dts
@@ -0,0 +1,22 @@
+/*
+ * Copyright 2011 Linaro Ltd.
+ *
+ * The code contained herein is licensed under the GNU General Public
+ * License. You may obtain a copy of the GNU General Public License
+ * Version 2 or later at the following locations:
+ *
+ * http://www.opensource.org/licenses/gpl-license.html
+ * http://www.gnu.org/copyleft/gpl.html
+ */
+
+/dts-v1/;
+/include/ "skeleton.dtsi"
+
+/ {
+	model = "Genesi EfikaMX nettop";
+	compatible = "genesi,efikamx", "fsl,mx51";
+
+	memory {
+		reg = <0x90000000 0x20000000>;
+	};
+};
diff --git a/arch/arm/boot/dts/genesi-efikasb.dts b/arch/arm/boot/dts/genesi-efikasb.dts
new file mode 100644
index 00000000000..9fda6ae314e
--- /dev/null
+++ b/arch/arm/boot/dts/genesi-efikasb.dts
@@ -0,0 +1,22 @@
+/*
+ * Copyright 2011 Linaro Ltd.
+ *
+ * The code contained herein is licensed under the GNU General Public
+ * License. You may obtain a copy of the GNU General Public License
+ * Version 2 or later at the following locations:
+ *
+ * http://www.opensource.org/licenses/gpl-license.html
+ * http://www.gnu.org/copyleft/gpl.html
+ */
+
+/dts-v1/;
+/include/ "skeleton.dtsi"
+
+/ {
+	model = "Genesi Efika Smartbook";
+	compatible = "genesi,efikasb", "fsl,mx51";
+
+	memory {
+		reg = <0x90000000 0x20000000>;
+	};
+};
diff --git a/arch/arm/boot/dts/isee-igep-v2.dts b/arch/arm/boot/dts/isee-igep-v2.dts
new file mode 100644
index 00000000000..72caabb85b7
--- /dev/null
+++ b/arch/arm/boot/dts/isee-igep-v2.dts
@@ -0,0 +1,7 @@
+/dts-v1/;
+/include/ "skeleton.dtsi"
+
+/ {
+	model = "ISSE IGEPv2 Board";
+	compatible = "ISEE,igep-v2";
+};
diff --git a/arch/arm/boot/dts/isee-igep-v3.dts b/arch/arm/boot/dts/isee-igep-v3.dts
new file mode 100644
index 00000000000..f40886fef69
--- /dev/null
+++ b/arch/arm/boot/dts/isee-igep-v3.dts
@@ -0,0 +1,7 @@
+/dts-v1/;
+/include/ "skeleton.dtsi"
+
+/ {
+	model = "ISSE IGEPv3 Module";
+	compatible = "ISEE,igep-v3";
+};
diff --git a/arch/arm/boot/dts/mx51-babbage.dts b/arch/arm/boot/dts/mx51-babbage.dts
new file mode 100644
index 00000000000..e5e9c8913d0
--- /dev/null
+++ b/arch/arm/boot/dts/mx51-babbage.dts
@@ -0,0 +1,22 @@
+/*
+ * Copyright 2011 Linaro Ltd.
+ *
+ * The code contained herein is licensed under the GNU General Public
+ * License. You may obtain a copy of the GNU General Public License
+ * Version 2 or later at the following locations:
+ *
+ * http://www.opensource.org/licenses/gpl-license.html
+ * http://www.gnu.org/copyleft/gpl.html
+ */
+
+/dts-v1/;
+/include/ "skeleton.dtsi"
+
+/ {
+	model = "Freescale i.MX51 Babbage";
+	compatible = "fsl,mx51-babbage", "fsl,mx51";
+
+	memory {
+		reg = <0x90000000 0x20000000>;
+	};
+};
diff --git a/arch/arm/boot/dts/mx53-loco.dts b/arch/arm/boot/dts/mx53-loco.dts
new file mode 100644
index 00000000000..8426c620614
--- /dev/null
+++ b/arch/arm/boot/dts/mx53-loco.dts
@@ -0,0 +1,22 @@
+/*
+ * Copyright 2011 Linaro Ltd.
+ *
+ * The code contained herein is licensed under the GNU General Public
+ * License. You may obtain a copy of the GNU General Public License
+ * Version 2 or later at the following locations:
+ *
+ * http://www.opensource.org/licenses/gpl-license.html
+ * http://www.gnu.org/copyleft/gpl.html
+ */
+
+/dts-v1/;
+/include/ "skeleton.dtsi"
+
+/ {
+	model = "Freescale i.MX53 LOCO";
+	compatible = "fsl,mx53-loco", "fsl,mx53";
+
+	memory {
+		reg = <0x70000000 0x40000000>;
+	};
+};
diff --git a/arch/arm/boot/dts/omap3-beagle.dts b/arch/arm/boot/dts/omap3-beagle.dts
new file mode 100644
index 00000000000..44394660006
--- /dev/null
+++ b/arch/arm/boot/dts/omap3-beagle.dts
@@ -0,0 +1,7 @@
+/dts-v1/;
+/include/ "skeleton.dtsi"
+
+/ {
+	model = "TI OMAP3 BeagleBoard";
+	compatible = "ti,omap3-beagle";
+};
diff --git a/arch/arm/boot/dts/omap3-overo.dts b/arch/arm/boot/dts/omap3-overo.dts
new file mode 100644
index 00000000000..c61f0112bf3
--- /dev/null
+++ b/arch/arm/boot/dts/omap3-overo.dts
@@ -0,0 +1,7 @@
+/dts-v1/;
+/include/ "skeleton.dtsi"
+
+/ {
+	model = "Gumstix Overo";
+	compatible = "gumstix,omap3-overo";
+};
diff --git a/arch/arm/boot/dts/omap4-panda.dts b/arch/arm/boot/dts/omap4-panda.dts
new file mode 100644
index 00000000000..58909e9b664
--- /dev/null
+++ b/arch/arm/boot/dts/omap4-panda.dts
@@ -0,0 +1,11 @@
+/dts-v1/;
+
+/memreserve/ 0x9D000000 0x03000000; /* Frame buffer */
+/memreserve/ 0xB0000000 0x10000000; /* Top 256MB is unaccessable */
+
+/include/ "skeleton.dtsi"
+
+/ {
+	model = "TI OMAP4 PandaBoard";
+	compatible = "ti,omap4-panda", "ti,omap4430";
+};
diff --git a/arch/arm/boot/dts/vexpress.dts b/arch/arm/boot/dts/vexpress.dts
new file mode 100644
index 00000000000..5f3bc1d1f1c
--- /dev/null
+++ b/arch/arm/boot/dts/vexpress.dts
@@ -0,0 +1,10 @@
+/dts-v1/;
+/include/ "skeleton.dtsi"
+
+/ {
+	model = "ARM Versatile Express";
+	compatible = "arm,vexpress";
+	memory {
+		reg = <0x60000000 0x40000000>;
+	};
+};
diff --git a/arch/arm/common/gic.c b/arch/arm/common/gic.c
index 3227ca952a1..734db99eaee 100644
--- a/arch/arm/common/gic.c
+++ b/arch/arm/common/gic.c
@@ -26,6 +26,7 @@
 #include <linux/kernel.h>
 #include <linux/list.h>
 #include <linux/smp.h>
+#include <linux/cpu_pm.h>
 #include <linux/cpumask.h>
 #include <linux/io.h>
 
@@ -276,6 +277,8 @@ static void __init gic_dist_init(struct gic_chip_data *gic,
 	if (gic_irqs > 1020)
 		gic_irqs = 1020;
 
+	gic->gic_irqs = gic_irqs;
+
 	/*
 	 * Set all global interrupts to be level triggered, active low.
 	 */
@@ -343,6 +346,189 @@ static void __cpuinit gic_cpu_init(struct gic_chip_data *gic)
 	writel_relaxed(1, base + GIC_CPU_CTRL);
 }
 
+#ifdef CONFIG_CPU_PM
+/*
+ * Saves the GIC distributor registers during suspend or idle.  Must be called
+ * with interrupts disabled but before powering down the GIC.  After calling
+ * this function, no interrupts will be delivered by the GIC, and another
+ * platform-specific wakeup source must be enabled.
+ */
+static void gic_dist_save(unsigned int gic_nr)
+{
+	unsigned int gic_irqs;
+	void __iomem *dist_base;
+	int i;
+
+	if (gic_nr >= MAX_GIC_NR)
+		BUG();
+
+	gic_irqs = gic_data[gic_nr].gic_irqs;
+	dist_base = gic_data[gic_nr].dist_base;
+
+	if (!dist_base)
+		return;
+
+	for (i = 0; i < DIV_ROUND_UP(gic_irqs, 16); i++)
+		gic_data[gic_nr].saved_spi_conf[i] =
+			readl_relaxed(dist_base + GIC_DIST_CONFIG + i * 4);
+
+	for (i = 0; i < DIV_ROUND_UP(gic_irqs, 4); i++)
+		gic_data[gic_nr].saved_spi_target[i] =
+			readl_relaxed(dist_base + GIC_DIST_TARGET + i * 4);
+
+	for (i = 0; i < DIV_ROUND_UP(gic_irqs, 32); i++)
+		gic_data[gic_nr].saved_spi_enable[i] =
+			readl_relaxed(dist_base + GIC_DIST_ENABLE_SET + i * 4);
+}
+
+/*
+ * Restores the GIC distributor registers during resume or when coming out of
+ * idle.  Must be called before enabling interrupts.  If a level interrupt
+ * that occured while the GIC was suspended is still present, it will be
+ * handled normally, but any edge interrupts that occured will not be seen by
+ * the GIC and need to be handled by the platform-specific wakeup source.
+ */
+static void gic_dist_restore(unsigned int gic_nr)
+{
+	unsigned int gic_irqs;
+	unsigned int i;
+	void __iomem *dist_base;
+
+	if (gic_nr >= MAX_GIC_NR)
+		BUG();
+
+	gic_irqs = gic_data[gic_nr].gic_irqs;
+	dist_base = gic_data[gic_nr].dist_base;
+
+	if (!dist_base)
+		return;
+
+	writel_relaxed(0, dist_base + GIC_DIST_CTRL);
+
+	for (i = 0; i < DIV_ROUND_UP(gic_irqs, 16); i++)
+		writel_relaxed(gic_data[gic_nr].saved_spi_conf[i],
+			dist_base + GIC_DIST_CONFIG + i * 4);
+
+	for (i = 0; i < DIV_ROUND_UP(gic_irqs, 4); i++)
+		writel_relaxed(0xa0a0a0a0,
+			dist_base + GIC_DIST_PRI + i * 4);
+
+	for (i = 0; i < DIV_ROUND_UP(gic_irqs, 4); i++)
+		writel_relaxed(gic_data[gic_nr].saved_spi_target[i],
+			dist_base + GIC_DIST_TARGET + i * 4);
+
+	for (i = 0; i < DIV_ROUND_UP(gic_irqs, 32); i++)
+		writel_relaxed(gic_data[gic_nr].saved_spi_enable[i],
+			dist_base + GIC_DIST_ENABLE_SET + i * 4);
+
+	writel_relaxed(1, dist_base + GIC_DIST_CTRL);
+}
+
+static void gic_cpu_save(unsigned int gic_nr)
+{
+	int i;
+	u32 *ptr;
+	void __iomem *dist_base;
+	void __iomem *cpu_base;
+
+	if (gic_nr >= MAX_GIC_NR)
+		BUG();
+
+	dist_base = gic_data[gic_nr].dist_base;
+	cpu_base = gic_data[gic_nr].cpu_base;
+
+	if (!dist_base || !cpu_base)
+		return;
+
+	ptr = __this_cpu_ptr(gic_data[gic_nr].saved_ppi_enable);
+	for (i = 0; i < DIV_ROUND_UP(32, 32); i++)
+		ptr[i] = readl_relaxed(dist_base + GIC_DIST_ENABLE_SET + i * 4);
+
+	ptr = __this_cpu_ptr(gic_data[gic_nr].saved_ppi_conf);
+	for (i = 0; i < DIV_ROUND_UP(32, 16); i++)
+		ptr[i] = readl_relaxed(dist_base + GIC_DIST_CONFIG + i * 4);
+
+}
+
+static void gic_cpu_restore(unsigned int gic_nr)
+{
+	int i;
+	u32 *ptr;
+	void __iomem *dist_base;
+	void __iomem *cpu_base;
+
+	if (gic_nr >= MAX_GIC_NR)
+		BUG();
+
+	dist_base = gic_data[gic_nr].dist_base;
+	cpu_base = gic_data[gic_nr].cpu_base;
+
+	if (!dist_base || !cpu_base)
+		return;
+
+	ptr = __this_cpu_ptr(gic_data[gic_nr].saved_ppi_enable);
+	for (i = 0; i < DIV_ROUND_UP(32, 32); i++)
+		writel_relaxed(ptr[i], dist_base + GIC_DIST_ENABLE_SET + i * 4);
+
+	ptr = __this_cpu_ptr(gic_data[gic_nr].saved_ppi_conf);
+	for (i = 0; i < DIV_ROUND_UP(32, 16); i++)
+		writel_relaxed(ptr[i], dist_base + GIC_DIST_CONFIG + i * 4);
+
+	for (i = 0; i < DIV_ROUND_UP(32, 4); i++)
+		writel_relaxed(0xa0a0a0a0, dist_base + GIC_DIST_PRI + i * 4);
+
+	writel_relaxed(0xf0, cpu_base + GIC_CPU_PRIMASK);
+	writel_relaxed(1, cpu_base + GIC_CPU_CTRL);
+}
+
+static int gic_notifier(struct notifier_block *self, unsigned long cmd,	void *v)
+{
+	int i;
+
+	for (i = 0; i < MAX_GIC_NR; i++) {
+		switch (cmd) {
+		case CPU_PM_ENTER:
+			gic_cpu_save(i);
+			break;
+		case CPU_PM_ENTER_FAILED:
+		case CPU_PM_EXIT:
+			gic_cpu_restore(i);
+			break;
+		case CPU_CLUSTER_PM_ENTER:
+			gic_dist_save(i);
+			break;
+		case CPU_CLUSTER_PM_ENTER_FAILED:
+		case CPU_CLUSTER_PM_EXIT:
+			gic_dist_restore(i);
+			break;
+		}
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block gic_notifier_block = {
+	.notifier_call = gic_notifier,
+};
+
+static void __init gic_pm_init(struct gic_chip_data *gic)
+{
+	gic->saved_ppi_enable = __alloc_percpu(DIV_ROUND_UP(32, 32) * 4,
+		sizeof(u32));
+	BUG_ON(!gic->saved_ppi_enable);
+
+	gic->saved_ppi_conf = __alloc_percpu(DIV_ROUND_UP(32, 16) * 4,
+		sizeof(u32));
+	BUG_ON(!gic->saved_ppi_conf);
+
+	cpu_pm_register_notifier(&gic_notifier_block);
+}
+#else
+static void __init gic_pm_init(struct gic_chip_data *gic)
+{
+}
+#endif
+
 void __init gic_init(unsigned int gic_nr, unsigned int irq_start,
 	void __iomem *dist_base, void __iomem *cpu_base)
 {
@@ -358,8 +544,10 @@ void __init gic_init(unsigned int gic_nr, unsigned int irq_start,
 	if (gic_nr == 0)
 		gic_cpu_base_addr = cpu_base;
 
+	gic_chip.flags |= gic_arch_extn.flags;
 	gic_dist_init(gic, irq_start);
 	gic_cpu_init(gic);
+	gic_pm_init(gic);
 }
 
 void __cpuinit gic_secondary_init(unsigned int gic_nr)
diff --git a/arch/arm/configs/exynos4_defconfig b/arch/arm/configs/exynos4_defconfig
index da53ff3b4d7..cd40bb56e56 100644
--- a/arch/arm/configs/exynos4_defconfig
+++ b/arch/arm/configs/exynos4_defconfig
@@ -11,6 +11,7 @@ CONFIG_MACH_SMDKV310=y
 CONFIG_MACH_ARMLEX4210=y
 CONFIG_MACH_UNIVERSAL_C210=y
 CONFIG_MACH_NURI=y
+CONFIG_MACH_ORIGEN=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_SMP=y
diff --git a/arch/arm/configs/ezx_defconfig b/arch/arm/configs/ezx_defconfig
index 227a477346e..d95763d5f0d 100644
--- a/arch/arm/configs/ezx_defconfig
+++ b/arch/arm/configs/ezx_defconfig
@@ -287,7 +287,7 @@ CONFIG_USB=y
 # CONFIG_USB_DEVICE_CLASS is not set
 CONFIG_USB_OHCI_HCD=y
 CONFIG_USB_GADGET=y
-CONFIG_USB_GADGET_PXA27X=y
+CONFIG_USB_PXA27X=y
 CONFIG_USB_ETH=m
 # CONFIG_USB_ETH_RNDIS is not set
 CONFIG_MMC=y
diff --git a/arch/arm/configs/imote2_defconfig b/arch/arm/configs/imote2_defconfig
index 176ec22af03..fd996bb1302 100644
--- a/arch/arm/configs/imote2_defconfig
+++ b/arch/arm/configs/imote2_defconfig
@@ -263,7 +263,7 @@ CONFIG_USB=y
 # CONFIG_USB_DEVICE_CLASS is not set
 CONFIG_USB_OHCI_HCD=y
 CONFIG_USB_GADGET=y
-CONFIG_USB_GADGET_PXA27X=y
+CONFIG_USB_PXA27X=y
 CONFIG_USB_ETH=m
 # CONFIG_USB_ETH_RNDIS is not set
 CONFIG_MMC=y
diff --git a/arch/arm/configs/magician_defconfig b/arch/arm/configs/magician_defconfig
index a88e64d4e9a..443675d317e 100644
--- a/arch/arm/configs/magician_defconfig
+++ b/arch/arm/configs/magician_defconfig
@@ -132,7 +132,7 @@ CONFIG_USB_MON=m
 CONFIG_USB_OHCI_HCD=y
 CONFIG_USB_GADGET=y
 CONFIG_USB_GADGET_VBUS_DRAW=500
-CONFIG_USB_GADGET_PXA27X=y
+CONFIG_USB_PXA27X=y
 CONFIG_USB_ETH=m
 # CONFIG_USB_ETH_RNDIS is not set
 CONFIG_USB_GADGETFS=m
diff --git a/arch/arm/configs/zeus_defconfig b/arch/arm/configs/zeus_defconfig
index 59577ad3f4e..547a3c1e59d 100644
--- a/arch/arm/configs/zeus_defconfig
+++ b/arch/arm/configs/zeus_defconfig
@@ -140,7 +140,7 @@ CONFIG_USB_SERIAL=m
 CONFIG_USB_SERIAL_GENERIC=y
 CONFIG_USB_SERIAL_MCT_U232=m
 CONFIG_USB_GADGET=m
-CONFIG_USB_GADGET_PXA27X=y
+CONFIG_USB_PXA27X=y
 CONFIG_USB_ETH=m
 CONFIG_USB_GADGETFS=m
 CONFIG_USB_FILE_STORAGE=m
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index 29035e86a59..b6e65dedfd7 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -187,6 +187,17 @@
 #endif
 
 /*
+ * Instruction barrier
+ */
+	.macro	instr_sync
+#if __LINUX_ARM_ARCH__ >= 7
+	isb
+#elif __LINUX_ARM_ARCH__ == 6
+	mcr	p15, 0, r0, c7, c5, 4
+#endif
+	.endm
+
+/*
  * SMP data memory barrier
  */
 	.macro	smp_dmb mode
diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h
index cd4458f6417..cb47d28cbe1 100644
--- a/arch/arm/include/asm/cputype.h
+++ b/arch/arm/include/asm/cputype.h
@@ -8,6 +8,7 @@
 #define CPUID_CACHETYPE	1
 #define CPUID_TCM	2
 #define CPUID_TLBTYPE	3
+#define CPUID_MPIDR	5
 
 #define CPUID_EXT_PFR0	"c1, 0"
 #define CPUID_EXT_PFR1	"c1, 1"
@@ -70,6 +71,11 @@ static inline unsigned int __attribute_const__ read_cpuid_tcmstatus(void)
 	return read_cpuid(CPUID_TCM);
 }
 
+static inline unsigned int __attribute_const__ read_cpuid_mpidr(void)
+{
+	return read_cpuid(CPUID_MPIDR);
+}
+
 /*
  * Intel's XScale3 core supports some v6 features (supersections, L2)
  * but advertises itself as v5 as it does not support the v6 ISA.  For
diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index 7a21d0bf713..cb3b7c981c4 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -32,7 +32,7 @@ static inline unsigned long dma_to_pfn(struct device *dev, dma_addr_t addr)
 
 static inline void *dma_to_virt(struct device *dev, dma_addr_t addr)
 {
-	return (void *)__bus_to_virt(addr);
+	return (void *)__bus_to_virt((unsigned long)addr);
 }
 
 static inline dma_addr_t virt_to_dma(struct device *dev, void *addr)
@@ -205,6 +205,13 @@ extern void *dma_alloc_writecombine(struct device *, size_t, dma_addr_t *,
 int dma_mmap_writecombine(struct device *, struct vm_area_struct *,
 		void *, dma_addr_t, size_t);
 
+/*
+ * This can be called during boot to increase the size of the consistent
+ * DMA region above it's default value of 2MB. It must be called before the
+ * memory allocator is initialised, i.e. before any core_initcall.
+ */
+extern void __init init_consistent_dma_size(unsigned long size);
+
 
 #ifdef CONFIG_DMABOUNCE
 /*
diff --git a/arch/arm/include/asm/hardware/cache-l2x0.h b/arch/arm/include/asm/hardware/cache-l2x0.h
index 99a6ed7e1bf..434edccdf7f 100644
--- a/arch/arm/include/asm/hardware/cache-l2x0.h
+++ b/arch/arm/include/asm/hardware/cache-l2x0.h
@@ -52,6 +52,8 @@
 #define L2X0_LOCKDOWN_WAY_D_BASE	0x900
 #define L2X0_LOCKDOWN_WAY_I_BASE	0x904
 #define L2X0_LOCKDOWN_STRIDE		0x08
+#define L2X0_ADDR_FILTER_START		0xC00
+#define L2X0_ADDR_FILTER_END		0xC04
 #define L2X0_TEST_OPERATION		0xF00
 #define L2X0_LINE_DATA			0xF10
 #define L2X0_LINE_TAG			0xF30
@@ -65,8 +67,23 @@
 #define L2X0_CACHE_ID_PART_MASK		(0xf << 6)
 #define L2X0_CACHE_ID_PART_L210		(1 << 6)
 #define L2X0_CACHE_ID_PART_L310		(3 << 6)
+#define L2X0_CACHE_ID_RTL_MASK          0x3f
+#define L2X0_CACHE_ID_RTL_R0P0          0x0
+#define L2X0_CACHE_ID_RTL_R1P0          0x2
+#define L2X0_CACHE_ID_RTL_R2P0          0x4
+#define L2X0_CACHE_ID_RTL_R3P0          0x5
+#define L2X0_CACHE_ID_RTL_R3P1          0x6
+#define L2X0_CACHE_ID_RTL_R3P2          0x8
 
 #define L2X0_AUX_CTRL_MASK			0xc0000fff
+#define L2X0_AUX_CTRL_DATA_RD_LATENCY_SHIFT	0
+#define L2X0_AUX_CTRL_DATA_RD_LATENCY_MASK	0x7
+#define L2X0_AUX_CTRL_DATA_WR_LATENCY_SHIFT	3
+#define L2X0_AUX_CTRL_DATA_WR_LATENCY_MASK	(0x7 << 3)
+#define L2X0_AUX_CTRL_TAG_LATENCY_SHIFT		6
+#define L2X0_AUX_CTRL_TAG_LATENCY_MASK		(0x7 << 6)
+#define L2X0_AUX_CTRL_DIRTY_LATENCY_SHIFT	9
+#define L2X0_AUX_CTRL_DIRTY_LATENCY_MASK	(0x7 << 9)
 #define L2X0_AUX_CTRL_ASSOCIATIVITY_SHIFT	16
 #define L2X0_AUX_CTRL_WAY_SIZE_SHIFT		17
 #define L2X0_AUX_CTRL_WAY_SIZE_MASK		(0x7 << 17)
@@ -77,8 +94,33 @@
 #define L2X0_AUX_CTRL_INSTR_PREFETCH_SHIFT	29
 #define L2X0_AUX_CTRL_EARLY_BRESP_SHIFT		30
 
+#define L2X0_LATENCY_CTRL_SETUP_SHIFT	0
+#define L2X0_LATENCY_CTRL_RD_SHIFT	4
+#define L2X0_LATENCY_CTRL_WR_SHIFT	8
+
+#define L2X0_ADDR_FILTER_EN		1
+
 #ifndef __ASSEMBLY__
 extern void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask);
+extern int l2x0_of_init(__u32 aux_val, __u32 aux_mask);
+
+struct l2x0_regs {
+	unsigned long phy_base;
+	unsigned long aux_ctrl;
+	/*
+	 * Whether the following registers need to be saved/restored
+	 * depends on platform
+	 */
+	unsigned long tag_latency;
+	unsigned long data_latency;
+	unsigned long filter_start;
+	unsigned long filter_end;
+	unsigned long prefetch_ctrl;
+	unsigned long pwr_ctrl;
+};
+
+extern struct l2x0_regs l2x0_saved_regs;
+
 #endif
 
 #endif
diff --git a/arch/arm/include/asm/hardware/gic.h b/arch/arm/include/asm/hardware/gic.h
index 435d3f86c70..c5627057b1c 100644
--- a/arch/arm/include/asm/hardware/gic.h
+++ b/arch/arm/include/asm/hardware/gic.h
@@ -46,6 +46,14 @@ struct gic_chip_data {
 	unsigned int irq_offset;
 	void __iomem *dist_base;
 	void __iomem *cpu_base;
+#ifdef CONFIG_CPU_PM
+	u32 saved_spi_enable[DIV_ROUND_UP(1020, 32)];
+	u32 saved_spi_conf[DIV_ROUND_UP(1020, 16)];
+	u32 saved_spi_target[DIV_ROUND_UP(1020, 4)];
+	u32 __percpu *saved_ppi_enable;
+	u32 __percpu *saved_ppi_conf;
+#endif
+	unsigned int gic_irqs;
 };
 #endif
 
diff --git a/arch/arm/include/asm/hw_breakpoint.h b/arch/arm/include/asm/hw_breakpoint.h
index f389b2704d8..c190bc992f0 100644
--- a/arch/arm/include/asm/hw_breakpoint.h
+++ b/arch/arm/include/asm/hw_breakpoint.h
@@ -50,6 +50,7 @@ static inline void decode_ctrl_reg(u32 reg,
 #define ARM_DEBUG_ARCH_V6_1	2
 #define ARM_DEBUG_ARCH_V7_ECP14	3
 #define ARM_DEBUG_ARCH_V7_MM	4
+#define ARM_DEBUG_ARCH_V7_1	5
 
 /* Breakpoint */
 #define ARM_BREAKPOINT_EXECUTE	0
@@ -57,6 +58,7 @@ static inline void decode_ctrl_reg(u32 reg,
 /* Watchpoints */
 #define ARM_BREAKPOINT_LOAD	1
 #define ARM_BREAKPOINT_STORE	2
+#define ARM_FSR_ACCESS_MASK	(1 << 11)
 
 /* Privilege Levels */
 #define ARM_BREAKPOINT_PRIV	1
diff --git a/arch/arm/include/asm/mach/arch.h b/arch/arm/include/asm/mach/arch.h
index 217aa1911dd..727da118bcc 100644
--- a/arch/arm/include/asm/mach/arch.h
+++ b/arch/arm/include/asm/mach/arch.h
@@ -17,7 +17,7 @@ struct sys_timer;
 struct machine_desc {
 	unsigned int		nr;		/* architecture number	*/
 	const char		*name;		/* architecture name	*/
-	unsigned long		boot_params;	/* tagged list		*/
+	unsigned long		atag_offset;	/* tagged list (relative) */
 	const char		**dt_compat;	/* array of device tree
 						 * 'compatible' strings	*/
 
diff --git a/arch/arm/include/asm/mach/map.h b/arch/arm/include/asm/mach/map.h
index d2fedb5aeb1..b36f3654bf5 100644
--- a/arch/arm/include/asm/mach/map.h
+++ b/arch/arm/include/asm/mach/map.h
@@ -29,6 +29,7 @@ struct map_desc {
 #define MT_MEMORY_NONCACHED	11
 #define MT_MEMORY_DTCM		12
 #define MT_MEMORY_ITCM		13
+#define MT_MEMORY_SO		14
 
 #ifdef CONFIG_MMU
 extern void iotable_init(struct map_desc *, int);
diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index b8de516e600..652fccca495 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -77,16 +77,7 @@
  */
 #define IOREMAP_MAX_ORDER	24
 
-/*
- * Size of DMA-consistent memory region.  Must be multiple of 2M,
- * between 2MB and 14MB inclusive.
- */
-#ifndef CONSISTENT_DMA_SIZE
-#define CONSISTENT_DMA_SIZE 	SZ_2M
-#endif
-
 #define CONSISTENT_END		(0xffe00000UL)
-#define CONSISTENT_BASE		(CONSISTENT_END - CONSISTENT_DMA_SIZE)
 
 #else /* CONFIG_MMU */
 
diff --git a/arch/arm/include/asm/outercache.h b/arch/arm/include/asm/outercache.h
index 7ed8f98b217..170e9037ff1 100644
--- a/arch/arm/include/asm/outercache.h
+++ b/arch/arm/include/asm/outercache.h
@@ -36,6 +36,7 @@ struct outer_cache_fns {
 	void (*prefetch_enable)(void);
 	void (*prefetch_disable)(void);
 	void (*set_debug)(unsigned long);
+	void (*resume)(void);
 };
 
 #ifdef CONFIG_OUTER_CACHE
@@ -86,6 +87,10 @@ static inline void outer_prefetch_disable(void)
 {
 	if (outer_cache.prefetch_disable)
 		outer_cache.prefetch_disable();
+static inline void outer_resume(void)
+{
+	if (outer_cache.resume)
+		outer_cache.resume();
 }
 
 #else
diff --git a/arch/arm/include/asm/page.h b/arch/arm/include/asm/page.h
index ac75d084888..97b440c25c5 100644
--- a/arch/arm/include/asm/page.h
+++ b/arch/arm/include/asm/page.h
@@ -151,47 +151,11 @@ extern void __cpu_copy_user_highpage(struct page *to, struct page *from,
 #define clear_page(page)	memset((void *)(page), 0, PAGE_SIZE)
 extern void copy_page(void *to, const void *from);
 
-typedef unsigned long pteval_t;
-
-#undef STRICT_MM_TYPECHECKS
-
-#ifdef STRICT_MM_TYPECHECKS
-/*
- * These are used to make use of C type-checking..
- */
-typedef struct { pteval_t pte; } pte_t;
-typedef struct { unsigned long pmd; } pmd_t;
-typedef struct { unsigned long pgd[2]; } pgd_t;
-typedef struct { unsigned long pgprot; } pgprot_t;
-
-#define pte_val(x)      ((x).pte)
-#define pmd_val(x)      ((x).pmd)
-#define pgd_val(x)	((x).pgd[0])
-#define pgprot_val(x)   ((x).pgprot)
-
-#define __pte(x)        ((pte_t) { (x) } )
-#define __pmd(x)        ((pmd_t) { (x) } )
-#define __pgprot(x)     ((pgprot_t) { (x) } )
-
+#ifdef CONFIG_ARM_LPAE
+#include <asm/pgtable-3level-types.h>
 #else
-/*
- * .. while these make it easier on the compiler
- */
-typedef pteval_t pte_t;
-typedef unsigned long pmd_t;
-typedef unsigned long pgd_t[2];
-typedef unsigned long pgprot_t;
-
-#define pte_val(x)      (x)
-#define pmd_val(x)      (x)
-#define pgd_val(x)	((x)[0])
-#define pgprot_val(x)   (x)
-
-#define __pte(x)        (x)
-#define __pmd(x)        (x)
-#define __pgprot(x)     (x)
-
-#endif /* STRICT_MM_TYPECHECKS */
+#include <asm/pgtable-2level-types.h>
+#endif
 
 #endif /* CONFIG_MMU */
 
diff --git a/arch/arm/include/asm/pgalloc.h b/arch/arm/include/asm/pgalloc.h
index 22de005f159..943504f53f5 100644
--- a/arch/arm/include/asm/pgalloc.h
+++ b/arch/arm/include/asm/pgalloc.h
@@ -25,12 +25,34 @@
 #define _PAGE_USER_TABLE	(PMD_TYPE_TABLE | PMD_BIT4 | PMD_DOMAIN(DOMAIN_USER))
 #define _PAGE_KERNEL_TABLE	(PMD_TYPE_TABLE | PMD_BIT4 | PMD_DOMAIN(DOMAIN_KERNEL))
 
+#ifdef CONFIG_ARM_LPAE
+
+static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
+{
+	return (pmd_t *)get_zeroed_page(GFP_KERNEL | __GFP_REPEAT);
+}
+
+static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
+{
+	BUG_ON((unsigned long)pmd & (PAGE_SIZE-1));
+	free_page((unsigned long)pmd);
+}
+
+static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
+{
+	set_pud(pud, __pud(__pa(pmd) | PMD_TYPE_TABLE));
+}
+
+#else	/* !CONFIG_ARM_LPAE */
+
 /*
  * Since we have only two-level page tables, these are trivial
  */
 #define pmd_alloc_one(mm,addr)		({ BUG(); ((pmd_t *)2); })
 #define pmd_free(mm, pmd)		do { } while (0)
-#define pgd_populate(mm,pmd,pte)	BUG()
+#define pud_populate(mm,pmd,pte)	BUG()
+
+#endif	/* CONFIG_ARM_LPAE */
 
 extern pgd_t *pgd_alloc(struct mm_struct *mm);
 extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
@@ -105,11 +127,13 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
 }
 
 static inline void __pmd_populate(pmd_t *pmdp, phys_addr_t pte,
-	unsigned long prot)
+				  pmdval_t prot)
 {
-	unsigned long pmdval = (pte + PTE_HWTABLE_OFF) | prot;
+	pmdval_t pmdval = (pte + PTE_HWTABLE_OFF) | prot;
 	pmdp[0] = __pmd(pmdval);
+#ifndef CONFIG_ARM_LPAE
 	pmdp[1] = __pmd(pmdval + 256 * sizeof(pte_t));
+#endif
 	flush_pmd_entry(pmdp);
 }
 
diff --git a/arch/arm/include/asm/pgtable-2level-hwdef.h b/arch/arm/include/asm/pgtable-2level-hwdef.h
new file mode 100644
index 00000000000..5cfba15cb40
--- /dev/null
+++ b/arch/arm/include/asm/pgtable-2level-hwdef.h
@@ -0,0 +1,93 @@
+/*
+ *  arch/arm/include/asm/pgtable-2level-hwdef.h
+ *
+ *  Copyright (C) 1995-2002 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef _ASM_PGTABLE_2LEVEL_HWDEF_H
+#define _ASM_PGTABLE_2LEVEL_HWDEF_H
+
+/*
+ * Hardware page table definitions.
+ *
+ * + Level 1 descriptor (PMD)
+ *   - common
+ */
+#define PMD_TYPE_MASK		(_AT(pmdval_t, 3) << 0)
+#define PMD_TYPE_FAULT		(_AT(pmdval_t, 0) << 0)
+#define PMD_TYPE_TABLE		(_AT(pmdval_t, 1) << 0)
+#define PMD_TYPE_SECT		(_AT(pmdval_t, 2) << 0)
+#define PMD_BIT4		(_AT(pmdval_t, 1) << 4)
+#define PMD_DOMAIN(x)		(_AT(pmdval_t, (x)) << 5)
+#define PMD_PROTECTION		(_AT(pmdval_t, 1) << 9)		/* v5 */
+/*
+ *   - section
+ */
+#define PMD_SECT_BUFFERABLE	(_AT(pmdval_t, 1) << 2)
+#define PMD_SECT_CACHEABLE	(_AT(pmdval_t, 1) << 3)
+#define PMD_SECT_XN		(_AT(pmdval_t, 1) << 4)		/* v6 */
+#define PMD_SECT_AP_WRITE	(_AT(pmdval_t, 1) << 10)
+#define PMD_SECT_AP_READ	(_AT(pmdval_t, 1) << 11)
+#define PMD_SECT_TEX(x)		(_AT(pmdval_t, (x)) << 12)	/* v5 */
+#define PMD_SECT_APX		(_AT(pmdval_t, 1) << 15)	/* v6 */
+#define PMD_SECT_S		(_AT(pmdval_t, 1) << 16)	/* v6 */
+#define PMD_SECT_nG		(_AT(pmdval_t, 1) << 17)	/* v6 */
+#define PMD_SECT_SUPER		(_AT(pmdval_t, 1) << 18)	/* v6 */
+#define PMD_SECT_AF		(_AT(pmdval_t, 0))
+
+#define PMD_SECT_UNCACHED	(_AT(pmdval_t, 0))
+#define PMD_SECT_BUFFERED	(PMD_SECT_BUFFERABLE)
+#define PMD_SECT_WT		(PMD_SECT_CACHEABLE)
+#define PMD_SECT_WB		(PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE)
+#define PMD_SECT_MINICACHE	(PMD_SECT_TEX(1) | PMD_SECT_CACHEABLE)
+#define PMD_SECT_WBWA		(PMD_SECT_TEX(1) | PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE)
+#define PMD_SECT_NONSHARED_DEV	(PMD_SECT_TEX(2))
+
+/*
+ *   - coarse table (not used)
+ */
+
+/*
+ * + Level 2 descriptor (PTE)
+ *   - common
+ */
+#define PTE_TYPE_MASK		(_AT(pteval_t, 3) << 0)
+#define PTE_TYPE_FAULT		(_AT(pteval_t, 0) << 0)
+#define PTE_TYPE_LARGE		(_AT(pteval_t, 1) << 0)
+#define PTE_TYPE_SMALL		(_AT(pteval_t, 2) << 0)
+#define PTE_TYPE_EXT		(_AT(pteval_t, 3) << 0)		/* v5 */
+#define PTE_BUFFERABLE		(_AT(pteval_t, 1) << 2)
+#define PTE_CACHEABLE		(_AT(pteval_t, 1) << 3)
+
+/*
+ *   - extended small page/tiny page
+ */
+#define PTE_EXT_XN		(_AT(pteval_t, 1) << 0)		/* v6 */
+#define PTE_EXT_AP_MASK		(_AT(pteval_t, 3) << 4)
+#define PTE_EXT_AP0		(_AT(pteval_t, 1) << 4)
+#define PTE_EXT_AP1		(_AT(pteval_t, 2) << 4)
+#define PTE_EXT_AP_UNO_SRO	(_AT(pteval_t, 0) << 4)
+#define PTE_EXT_AP_UNO_SRW	(PTE_EXT_AP0)
+#define PTE_EXT_AP_URO_SRW	(PTE_EXT_AP1)
+#define PTE_EXT_AP_URW_SRW	(PTE_EXT_AP1|PTE_EXT_AP0)
+#define PTE_EXT_TEX(x)		(_AT(pteval_t, (x)) << 6)	/* v5 */
+#define PTE_EXT_APX		(_AT(pteval_t, 1) << 9)		/* v6 */
+#define PTE_EXT_COHERENT	(_AT(pteval_t, 1) << 9)		/* XScale3 */
+#define PTE_EXT_SHARED		(_AT(pteval_t, 1) << 10)	/* v6 */
+#define PTE_EXT_NG		(_AT(pteval_t, 1) << 11)	/* v6 */
+
+/*
+ *   - small page
+ */
+#define PTE_SMALL_AP_MASK	(_AT(pteval_t, 0xff) << 4)
+#define PTE_SMALL_AP_UNO_SRO	(_AT(pteval_t, 0x00) << 4)
+#define PTE_SMALL_AP_UNO_SRW	(_AT(pteval_t, 0x55) << 4)
+#define PTE_SMALL_AP_URO_SRW	(_AT(pteval_t, 0xaa) << 4)
+#define PTE_SMALL_AP_URW_SRW	(_AT(pteval_t, 0xff) << 4)
+
+#define PHYS_MASK		(~0UL)
+
+#endif
diff --git a/arch/arm/include/asm/pgtable-2level-types.h b/arch/arm/include/asm/pgtable-2level-types.h
new file mode 100644
index 00000000000..66cb5b0e89c
--- /dev/null
+++ b/arch/arm/include/asm/pgtable-2level-types.h
@@ -0,0 +1,67 @@
+/*
+ * arch/arm/include/asm/pgtable-2level-types.h
+ *
+ * Copyright (C) 1995-2003 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+#ifndef _ASM_PGTABLE_2LEVEL_TYPES_H
+#define _ASM_PGTABLE_2LEVEL_TYPES_H
+
+#include <asm/types.h>
+
+typedef u32 pteval_t;
+typedef u32 pmdval_t;
+
+#undef STRICT_MM_TYPECHECKS
+
+#ifdef STRICT_MM_TYPECHECKS
+/*
+ * These are used to make use of C type-checking..
+ */
+typedef struct { pteval_t pte; } pte_t;
+typedef struct { pmdval_t pmd; } pmd_t;
+typedef struct { pmdval_t pgd[2]; } pgd_t;
+typedef struct { pteval_t pgprot; } pgprot_t;
+
+#define pte_val(x)      ((x).pte)
+#define pmd_val(x)      ((x).pmd)
+#define pgd_val(x)	((x).pgd[0])
+#define pgprot_val(x)   ((x).pgprot)
+
+#define __pte(x)        ((pte_t) { (x) } )
+#define __pmd(x)        ((pmd_t) { (x) } )
+#define __pgprot(x)     ((pgprot_t) { (x) } )
+
+#else
+/*
+ * .. while these make it easier on the compiler
+ */
+typedef pteval_t pte_t;
+typedef pmdval_t pmd_t;
+typedef pmdval_t pgd_t[2];
+typedef pteval_t pgprot_t;
+
+#define pte_val(x)      (x)
+#define pmd_val(x)      (x)
+#define pgd_val(x)	((x)[0])
+#define pgprot_val(x)   (x)
+
+#define __pte(x)        (x)
+#define __pmd(x)        (x)
+#define __pgprot(x)     (x)
+
+#endif /* STRICT_MM_TYPECHECKS */
+
+#endif	/* _ASM_PGTABLE_2LEVEL_TYPES_H */
diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h
new file mode 100644
index 00000000000..2317a71c8f8
--- /dev/null
+++ b/arch/arm/include/asm/pgtable-2level.h
@@ -0,0 +1,184 @@
+/*
+ *  arch/arm/include/asm/pgtable-2level.h
+ *
+ *  Copyright (C) 1995-2002 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef _ASM_PGTABLE_2LEVEL_H
+#define _ASM_PGTABLE_2LEVEL_H
+
+/*
+ * Hardware-wise, we have a two level page table structure, where the first
+ * level has 4096 entries, and the second level has 256 entries.  Each entry
+ * is one 32-bit word.  Most of the bits in the second level entry are used
+ * by hardware, and there aren't any "accessed" and "dirty" bits.
+ *
+ * Linux on the other hand has a three level page table structure, which can
+ * be wrapped to fit a two level page table structure easily - using the PGD
+ * and PTE only.  However, Linux also expects one "PTE" table per page, and
+ * at least a "dirty" bit.
+ *
+ * Therefore, we tweak the implementation slightly - we tell Linux that we
+ * have 2048 entries in the first level, each of which is 8 bytes (iow, two
+ * hardware pointers to the second level.)  The second level contains two
+ * hardware PTE tables arranged contiguously, preceded by Linux versions
+ * which contain the state information Linux needs.  We, therefore, end up
+ * with 512 entries in the "PTE" level.
+ *
+ * This leads to the page tables having the following layout:
+ *
+ *    pgd             pte
+ * |        |
+ * +--------+
+ * |        |       +------------+ +0
+ * +- - - - +       | Linux pt 0 |
+ * |        |       +------------+ +1024
+ * +--------+ +0    | Linux pt 1 |
+ * |        |-----> +------------+ +2048
+ * +- - - - + +4    |  h/w pt 0  |
+ * |        |-----> +------------+ +3072
+ * +--------+ +8    |  h/w pt 1  |
+ * |        |       +------------+ +4096
+ *
+ * See L_PTE_xxx below for definitions of bits in the "Linux pt", and
+ * PTE_xxx for definitions of bits appearing in the "h/w pt".
+ *
+ * PMD_xxx definitions refer to bits in the first level page table.
+ *
+ * The "dirty" bit is emulated by only granting hardware write permission
+ * iff the page is marked "writable" and "dirty" in the Linux PTE.  This
+ * means that a write to a clean page will cause a permission fault, and
+ * the Linux MM layer will mark the page dirty via handle_pte_fault().
+ * For the hardware to notice the permission change, the TLB entry must
+ * be flushed, and ptep_set_access_flags() does that for us.
+ *
+ * The "accessed" or "young" bit is emulated by a similar method; we only
+ * allow accesses to the page if the "young" bit is set.  Accesses to the
+ * page will cause a fault, and handle_pte_fault() will set the young bit
+ * for us as long as the page is marked present in the corresponding Linux
+ * PTE entry.  Again, ptep_set_access_flags() will ensure that the TLB is
+ * up to date.
+ *
+ * However, when the "young" bit is cleared, we deny access to the page
+ * by clearing the hardware PTE.  Currently Linux does not flush the TLB
+ * for us in this case, which means the TLB will retain the transation
+ * until either the TLB entry is evicted under pressure, or a context
+ * switch which changes the user space mapping occurs.
+ */
+#define PTRS_PER_PTE		512
+#define PTRS_PER_PMD		1
+#define PTRS_PER_PGD		2048
+
+#define PTE_HWTABLE_PTRS	(PTRS_PER_PTE)
+#define PTE_HWTABLE_OFF		(PTE_HWTABLE_PTRS * sizeof(pte_t))
+#define PTE_HWTABLE_SIZE	(PTRS_PER_PTE * sizeof(u32))
+
+/*
+ * PMD_SHIFT determines the size of the area a second-level page table can map
+ * PGDIR_SHIFT determines what a third-level page table entry can map
+ */
+#define PMD_SHIFT		21
+#define PGDIR_SHIFT		21
+
+#define PMD_SIZE		(1UL << PMD_SHIFT)
+#define PMD_MASK		(~(PMD_SIZE-1))
+#define PGDIR_SIZE		(1UL << PGDIR_SHIFT)
+#define PGDIR_MASK		(~(PGDIR_SIZE-1))
+
+/*
+ * section address mask and size definitions.
+ */
+#define SECTION_SHIFT		20
+#define SECTION_SIZE		(1UL << SECTION_SHIFT)
+#define SECTION_MASK		(~(SECTION_SIZE-1))
+
+/*
+ * ARMv6 supersection address mask and size definitions.
+ */
+#define SUPERSECTION_SHIFT	24
+#define SUPERSECTION_SIZE	(1UL << SUPERSECTION_SHIFT)
+#define SUPERSECTION_MASK	(~(SUPERSECTION_SIZE-1))
+
+#define USER_PTRS_PER_PGD	(TASK_SIZE / PGDIR_SIZE)
+
+/*
+ * "Linux" PTE definitions.
+ *
+ * We keep two sets of PTEs - the hardware and the linux version.
+ * This allows greater flexibility in the way we map the Linux bits
+ * onto the hardware tables, and allows us to have YOUNG and DIRTY
+ * bits.
+ *
+ * The PTE table pointer refers to the hardware entries; the "Linux"
+ * entries are stored 1024 bytes below.
+ */
+#define L_PTE_PRESENT		(_AT(pteval_t, 1) << 0)
+#define L_PTE_YOUNG		(_AT(pteval_t, 1) << 1)
+#define L_PTE_FILE		(_AT(pteval_t, 1) << 2)	/* only when !PRESENT */
+#define L_PTE_DIRTY		(_AT(pteval_t, 1) << 6)
+#define L_PTE_RDONLY		(_AT(pteval_t, 1) << 7)
+#define L_PTE_USER		(_AT(pteval_t, 1) << 8)
+#define L_PTE_XN		(_AT(pteval_t, 1) << 9)
+#define L_PTE_SHARED		(_AT(pteval_t, 1) << 10)	/* shared(v6), coherent(xsc3) */
+
+/*
+ * These are the memory types, defined to be compatible with
+ * pre-ARMv6 CPUs cacheable and bufferable bits:   XXCB
+ */
+#define L_PTE_MT_UNCACHED	(_AT(pteval_t, 0x00) << 2)	/* 0000 */
+#define L_PTE_MT_BUFFERABLE	(_AT(pteval_t, 0x01) << 2)	/* 0001 */
+#define L_PTE_MT_WRITETHROUGH	(_AT(pteval_t, 0x02) << 2)	/* 0010 */
+#define L_PTE_MT_WRITEBACK	(_AT(pteval_t, 0x03) << 2)	/* 0011 */
+#define L_PTE_MT_MINICACHE	(_AT(pteval_t, 0x06) << 2)	/* 0110 (sa1100, xscale) */
+#define L_PTE_MT_WRITEALLOC	(_AT(pteval_t, 0x07) << 2)	/* 0111 */
+#define L_PTE_MT_DEV_SHARED	(_AT(pteval_t, 0x04) << 2)	/* 0100 */
+#define L_PTE_MT_DEV_NONSHARED	(_AT(pteval_t, 0x0c) << 2)	/* 1100 */
+#define L_PTE_MT_DEV_WC		(_AT(pteval_t, 0x09) << 2)	/* 1001 */
+#define L_PTE_MT_DEV_CACHED	(_AT(pteval_t, 0x0b) << 2)	/* 1011 */
+#define L_PTE_MT_MASK		(_AT(pteval_t, 0x0f) << 2)
+
+#ifndef __ASSEMBLY__
+
+/*
+ * The "pud_xxx()" functions here are trivial when the pmd is folded into
+ * the pud: the pud entry is never bad, always exists, and can't be set or
+ * cleared.
+ */
+#define pud_none(pud)		(0)
+#define pud_bad(pud)		(0)
+#define pud_present(pud)	(1)
+#define pud_clear(pudp)		do { } while (0)
+#define set_pud(pud,pudp)	do { } while (0)
+
+static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
+{
+	return (pmd_t *)pud;
+}
+
+#define pmd_bad(pmd)		(pmd_val(pmd) & 2)
+
+#define copy_pmd(pmdpd,pmdps)		\
+	do {				\
+		pmdpd[0] = pmdps[0];	\
+		pmdpd[1] = pmdps[1];	\
+		flush_pmd_entry(pmdpd);	\
+	} while (0)
+
+#define pmd_clear(pmdp)			\
+	do {				\
+		pmdp[0] = __pmd(0);	\
+		pmdp[1] = __pmd(0);	\
+		clean_pmd_entry(pmdp);	\
+	} while (0)
+
+/* we don't need complex calculations here as the pmd is folded into the pgd */
+#define pmd_addr_end(addr,end) (end)
+
+#define set_pte_ext(ptep,pte,ext) cpu_set_pte_ext(ptep,pte,ext)
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_PGTABLE_2LEVEL_H */
diff --git a/arch/arm/include/asm/pgtable-3level-hwdef.h b/arch/arm/include/asm/pgtable-3level-hwdef.h
new file mode 100644
index 00000000000..7c238a3b48c
--- /dev/null
+++ b/arch/arm/include/asm/pgtable-3level-hwdef.h
@@ -0,0 +1,82 @@
+/*
+ * arch/arm/include/asm/pgtable-3level-hwdef.h
+ *
+ * Copyright (C) 2011 ARM Ltd.
+ * Author: Catalin Marinas <catalin.marinas@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+#ifndef _ASM_PGTABLE_3LEVEL_HWDEF_H
+#define _ASM_PGTABLE_3LEVEL_HWDEF_H
+
+/*
+ * Hardware page table definitions.
+ *
+ * + Level 1/2 descriptor
+ *   - common
+ */
+#define PMD_TYPE_MASK		(_AT(pmdval_t, 3) << 0)
+#define PMD_TYPE_FAULT		(_AT(pmdval_t, 0) << 0)
+#define PMD_TYPE_TABLE		(_AT(pmdval_t, 3) << 0)
+#define PMD_TYPE_SECT		(_AT(pmdval_t, 1) << 0)
+#define PMD_BIT4		(_AT(pmdval_t, 0))
+#define PMD_DOMAIN(x)		(_AT(pmdval_t, 0))
+
+/*
+ *   - section
+ */
+#define PMD_SECT_BUFFERABLE	(_AT(pmdval_t, 1) << 2)
+#define PMD_SECT_CACHEABLE	(_AT(pmdval_t, 1) << 3)
+#define PMD_SECT_S		(_AT(pmdval_t, 3) << 8)
+#define PMD_SECT_AF		(_AT(pmdval_t, 1) << 10)
+#define PMD_SECT_nG		(_AT(pmdval_t, 1) << 11)
+#ifdef __ASSEMBLY__
+/* avoid 'shift count out of range' warning */
+#define PMD_SECT_XN		(0)
+#else
+#define PMD_SECT_XN		((pmdval_t)1 << 54)
+#endif
+#define PMD_SECT_AP_WRITE	(_AT(pmdval_t, 0))
+#define PMD_SECT_AP_READ	(_AT(pmdval_t, 0))
+#define PMD_SECT_TEX(x)		(_AT(pmdval_t, 0))
+
+/*
+ * AttrIndx[2:0] encoding (mapping attributes defined in the MAIR* registers).
+ */
+#define PMD_SECT_UNCACHED	(_AT(pmdval_t, 0) << 2)	/* strongly ordered */
+#define PMD_SECT_BUFFERED	(_AT(pmdval_t, 1) << 2)	/* normal non-cacheable */
+#define PMD_SECT_WT		(_AT(pmdval_t, 2) << 2)	/* normal inner write-through */
+#define PMD_SECT_WB		(_AT(pmdval_t, 3) << 2)	/* normal inner write-back */
+#define PMD_SECT_WBWA		(_AT(pmdval_t, 7) << 2)	/* normal inner write-alloc */
+
+/*
+ * + Level 3 descriptor (PTE)
+ */
+#define PTE_TYPE_MASK		(_AT(pteval_t, 3) << 0)
+#define PTE_TYPE_FAULT		(_AT(pteval_t, 0) << 0)
+#define PTE_TYPE_PAGE		(_AT(pteval_t, 3) << 0)
+#define PTE_BUFFERABLE		(_AT(pteval_t, 1) << 2)		/* AttrIndx[0] */
+#define PTE_CACHEABLE		(_AT(pteval_t, 1) << 3)		/* AttrIndx[1] */
+#define PTE_EXT_SHARED		(_AT(pteval_t, 3) << 8)		/* SH[1:0], inner shareable */
+#define PTE_EXT_AF		(_AT(pteval_t, 1) << 10)	/* Access Flag */
+#define PTE_EXT_NG		(_AT(pteval_t, 1) << 11)	/* nG */
+#define PTE_EXT_XN		(_AT(pteval_t, 1) << 54)	/* XN */
+
+/*
+ * 40-bit physical address supported.
+ */
+#define PHYS_MASK_SHIFT		(40)
+#define PHYS_MASK		((1ULL << PHYS_MASK_SHIFT) - 1)
+
+#endif
diff --git a/arch/arm/include/asm/pgtable-3level-types.h b/arch/arm/include/asm/pgtable-3level-types.h
new file mode 100644
index 00000000000..921aa30259c
--- /dev/null
+++ b/arch/arm/include/asm/pgtable-3level-types.h
@@ -0,0 +1,70 @@
+/*
+ * arch/arm/include/asm/pgtable-3level-types.h
+ *
+ * Copyright (C) 2011 ARM Ltd.
+ * Author: Catalin Marinas <catalin.marinas@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+#ifndef _ASM_PGTABLE_3LEVEL_TYPES_H
+#define _ASM_PGTABLE_3LEVEL_TYPES_H
+
+#include <asm/types.h>
+
+typedef u64 pteval_t;
+typedef u64 pmdval_t;
+typedef u64 pgdval_t;
+
+#undef STRICT_MM_TYPECHECKS
+
+#ifdef STRICT_MM_TYPECHECKS
+
+/*
+ * These are used to make use of C type-checking..
+ */
+typedef struct { pteval_t pte; } pte_t;
+typedef struct { pmdval_t pmd; } pmd_t;
+typedef struct { pgdval_t pgd; } pgd_t;
+typedef struct { pteval_t pgprot; } pgprot_t;
+
+#define pte_val(x)      ((x).pte)
+#define pmd_val(x)      ((x).pmd)
+#define pgd_val(x)	((x).pgd)
+#define pgprot_val(x)   ((x).pgprot)
+
+#define __pte(x)        ((pte_t) { (x) } )
+#define __pmd(x)        ((pmd_t) { (x) } )
+#define __pgd(x)	((pgd_t) { (x) } )
+#define __pgprot(x)     ((pgprot_t) { (x) } )
+
+#else	/* !STRICT_MM_TYPECHECKS */
+
+typedef pteval_t pte_t;
+typedef pmdval_t pmd_t;
+typedef pgdval_t pgd_t;
+typedef pteval_t pgprot_t;
+
+#define pte_val(x)	(x)
+#define pmd_val(x)	(x)
+#define pgd_val(x)	(x)
+#define pgprot_val(x)	(x)
+
+#define __pte(x)	(x)
+#define __pmd(x)	(x)
+#define __pgd(x)	(x)
+#define __pgprot(x)	(x)
+
+#endif	/* STRICT_MM_TYPECHECKS */
+
+#endif	/* _ASM_PGTABLE_3LEVEL_TYPES_H */
diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h
new file mode 100644
index 00000000000..759af70f9a0
--- /dev/null
+++ b/arch/arm/include/asm/pgtable-3level.h
@@ -0,0 +1,155 @@
+/*
+ * arch/arm/include/asm/pgtable-3level.h
+ *
+ * Copyright (C) 2011 ARM Ltd.
+ * Author: Catalin Marinas <catalin.marinas@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+#ifndef _ASM_PGTABLE_3LEVEL_H
+#define _ASM_PGTABLE_3LEVEL_H
+
+/*
+ * With LPAE, there are 3 levels of page tables. Each level has 512 entries of
+ * 8 bytes each, occupying a 4K page. The first level table covers a range of
+ * 512GB, each entry representing 1GB. Since we are limited to 4GB input
+ * address range, only 4 entries in the PGD are used.
+ *
+ * There are enough spare bits in a page table entry for the kernel specific
+ * state.
+ */
+#define PTRS_PER_PTE		512
+#define PTRS_PER_PMD		512
+#define PTRS_PER_PGD		4
+
+#define PTE_HWTABLE_PTRS	(PTRS_PER_PTE)
+#define PTE_HWTABLE_OFF		(0)
+#define PTE_HWTABLE_SIZE	(PTRS_PER_PTE * sizeof(u64))
+
+/*
+ * PGDIR_SHIFT determines the size a top-level page table entry can map.
+ */
+#define PGDIR_SHIFT		30
+
+/*
+ * PMD_SHIFT determines the size a middle-level page table entry can map.
+ */
+#define PMD_SHIFT		21
+
+#define PMD_SIZE		(1UL << PMD_SHIFT)
+#define PMD_MASK		(~(PMD_SIZE-1))
+#define PGDIR_SIZE		(1UL << PGDIR_SHIFT)
+#define PGDIR_MASK		(~(PGDIR_SIZE-1))
+
+/*
+ * section address mask and size definitions.
+ */
+#define SECTION_SHIFT		21
+#define SECTION_SIZE		(1UL << SECTION_SHIFT)
+#define SECTION_MASK		(~(SECTION_SIZE-1))
+
+#define USER_PTRS_PER_PGD	(PAGE_OFFSET / PGDIR_SIZE)
+
+/*
+ * "Linux" PTE definitions for LPAE.
+ *
+ * These bits overlap with the hardware bits but the naming is preserved for
+ * consistency with the classic page table format.
+ */
+#define L_PTE_PRESENT		(_AT(pteval_t, 3) << 0)		/* Valid */
+#define L_PTE_FILE		(_AT(pteval_t, 1) << 2)		/* only when !PRESENT */
+#define L_PTE_BUFFERABLE	(_AT(pteval_t, 1) << 2)		/* AttrIndx[0] */
+#define L_PTE_CACHEABLE		(_AT(pteval_t, 1) << 3)		/* AttrIndx[1] */
+#define L_PTE_USER		(_AT(pteval_t, 1) << 6)		/* AP[1] */
+#define L_PTE_RDONLY		(_AT(pteval_t, 1) << 7)		/* AP[2] */
+#define L_PTE_SHARED		(_AT(pteval_t, 3) << 8)		/* SH[1:0], inner shareable */
+#define L_PTE_YOUNG		(_AT(pteval_t, 1) << 10)	/* AF */
+#define L_PTE_XN		(_AT(pteval_t, 1) << 54)	/* XN */
+#define L_PTE_DIRTY		(_AT(pteval_t, 1) << 55)	/* unused */
+#define L_PTE_SPECIAL		(_AT(pteval_t, 1) << 56)	/* unused */
+
+/*
+ * To be used in assembly code with the upper page attributes.
+ */
+#define L_PTE_XN_HIGH		(1 << (54 - 32))
+#define L_PTE_DIRTY_HIGH	(1 << (55 - 32))
+
+/*
+ * AttrIndx[2:0] encoding (mapping attributes defined in the MAIR* registers).
+ */
+#define L_PTE_MT_UNCACHED	(_AT(pteval_t, 0) << 2)	/* strongly ordered */
+#define L_PTE_MT_BUFFERABLE	(_AT(pteval_t, 1) << 2)	/* normal non-cacheable */
+#define L_PTE_MT_WRITETHROUGH	(_AT(pteval_t, 2) << 2)	/* normal inner write-through */
+#define L_PTE_MT_WRITEBACK	(_AT(pteval_t, 3) << 2)	/* normal inner write-back */
+#define L_PTE_MT_WRITEALLOC	(_AT(pteval_t, 7) << 2)	/* normal inner write-alloc */
+#define L_PTE_MT_DEV_SHARED	(_AT(pteval_t, 4) << 2)	/* device */
+#define L_PTE_MT_DEV_NONSHARED	(_AT(pteval_t, 4) << 2)	/* device */
+#define L_PTE_MT_DEV_WC		(_AT(pteval_t, 1) << 2)	/* normal non-cacheable */
+#define L_PTE_MT_DEV_CACHED	(_AT(pteval_t, 3) << 2)	/* normal inner write-back */
+#define L_PTE_MT_MASK		(_AT(pteval_t, 7) << 2)
+
+/*
+ * Software PGD flags.
+ */
+#define L_PGD_SWAPPER		(_AT(pgdval_t, 1) << 55)	/* swapper_pg_dir entry */
+
+#ifndef __ASSEMBLY__
+
+#define pud_none(pud)		(!pud_val(pud))
+#define pud_bad(pud)		(!(pud_val(pud) & 2))
+#define pud_present(pud)	(pud_val(pud))
+
+#define pud_clear(pudp)			\
+	do {				\
+		*pudp = __pud(0);	\
+		clean_pmd_entry(pudp);	\
+	} while (0)
+
+#define set_pud(pudp, pud)		\
+	do {				\
+		*pudp = pud;		\
+		flush_pmd_entry(pudp);	\
+	} while (0)
+
+static inline pmd_t *pud_page_vaddr(pud_t pud)
+{
+	return __va(pud_val(pud) & PHYS_MASK & (s32)PAGE_MASK);
+}
+
+/* Find an entry in the second-level page table.. */
+#define pmd_index(addr)		(((addr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1))
+static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
+{
+	return (pmd_t *)pud_page_vaddr(*pud) + pmd_index(addr);
+}
+
+#define pmd_bad(pmd)		(!(pmd_val(pmd) & 2))
+
+#define copy_pmd(pmdpd,pmdps)		\
+	do {				\
+		*pmdpd = *pmdps;	\
+		flush_pmd_entry(pmdpd);	\
+	} while (0)
+
+#define pmd_clear(pmdp)			\
+	do {				\
+		*pmdp = __pmd(0);	\
+		clean_pmd_entry(pmdp);	\
+	} while (0)
+
+#define set_pte_ext(ptep,pte,ext) cpu_set_pte_ext(ptep,__pte(pte_val(pte)|(ext)))
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_PGTABLE_3LEVEL_H */
diff --git a/arch/arm/include/asm/pgtable-hwdef.h b/arch/arm/include/asm/pgtable-hwdef.h
index fd1521d5cb9..8426229ba29 100644
--- a/arch/arm/include/asm/pgtable-hwdef.h
+++ b/arch/arm/include/asm/pgtable-hwdef.h
@@ -10,81 +10,10 @@
 #ifndef _ASMARM_PGTABLE_HWDEF_H
 #define _ASMARM_PGTABLE_HWDEF_H
 
-/*
- * Hardware page table definitions.
- *
- * + Level 1 descriptor (PMD)
- *   - common
- */
-#define PMD_TYPE_MASK		(3 << 0)
-#define PMD_TYPE_FAULT		(0 << 0)
-#define PMD_TYPE_TABLE		(1 << 0)
-#define PMD_TYPE_SECT		(2 << 0)
-#define PMD_BIT4		(1 << 4)
-#define PMD_DOMAIN(x)		((x) << 5)
-#define PMD_PROTECTION		(1 << 9)	/* v5 */
-/*
- *   - section
- */
-#define PMD_SECT_BUFFERABLE	(1 << 2)
-#define PMD_SECT_CACHEABLE	(1 << 3)
-#define PMD_SECT_XN		(1 << 4)	/* v6 */
-#define PMD_SECT_AP_WRITE	(1 << 10)
-#define PMD_SECT_AP_READ	(1 << 11)
-#define PMD_SECT_TEX(x)		((x) << 12)	/* v5 */
-#define PMD_SECT_APX		(1 << 15)	/* v6 */
-#define PMD_SECT_S		(1 << 16)	/* v6 */
-#define PMD_SECT_nG		(1 << 17)	/* v6 */
-#define PMD_SECT_SUPER		(1 << 18)	/* v6 */
-
-#define PMD_SECT_UNCACHED	(0)
-#define PMD_SECT_BUFFERED	(PMD_SECT_BUFFERABLE)
-#define PMD_SECT_WT		(PMD_SECT_CACHEABLE)
-#define PMD_SECT_WB		(PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE)
-#define PMD_SECT_MINICACHE	(PMD_SECT_TEX(1) | PMD_SECT_CACHEABLE)
-#define PMD_SECT_WBWA		(PMD_SECT_TEX(1) | PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE)
-#define PMD_SECT_NONSHARED_DEV	(PMD_SECT_TEX(2))
-
-/*
- *   - coarse table (not used)
- */
-
-/*
- * + Level 2 descriptor (PTE)
- *   - common
- */
-#define PTE_TYPE_MASK		(3 << 0)
-#define PTE_TYPE_FAULT		(0 << 0)
-#define PTE_TYPE_LARGE		(1 << 0)
-#define PTE_TYPE_SMALL		(2 << 0)
-#define PTE_TYPE_EXT		(3 << 0)	/* v5 */
-#define PTE_BUFFERABLE		(1 << 2)
-#define PTE_CACHEABLE		(1 << 3)
-
-/*
- *   - extended small page/tiny page
- */
-#define PTE_EXT_XN		(1 << 0)	/* v6 */
-#define PTE_EXT_AP_MASK		(3 << 4)
-#define PTE_EXT_AP0		(1 << 4)
-#define PTE_EXT_AP1		(2 << 4)
-#define PTE_EXT_AP_UNO_SRO	(0 << 4)
-#define PTE_EXT_AP_UNO_SRW	(PTE_EXT_AP0)
-#define PTE_EXT_AP_URO_SRW	(PTE_EXT_AP1)
-#define PTE_EXT_AP_URW_SRW	(PTE_EXT_AP1|PTE_EXT_AP0)
-#define PTE_EXT_TEX(x)		((x) << 6)	/* v5 */
-#define PTE_EXT_APX		(1 << 9)	/* v6 */
-#define PTE_EXT_COHERENT	(1 << 9)	/* XScale3 */
-#define PTE_EXT_SHARED		(1 << 10)	/* v6 */
-#define PTE_EXT_NG		(1 << 11)	/* v6 */
-
-/*
- *   - small page
- */
-#define PTE_SMALL_AP_MASK	(0xff << 4)
-#define PTE_SMALL_AP_UNO_SRO	(0x00 << 4)
-#define PTE_SMALL_AP_UNO_SRW	(0x55 << 4)
-#define PTE_SMALL_AP_URO_SRW	(0xaa << 4)
-#define PTE_SMALL_AP_URW_SRW	(0xff << 4)
+#ifdef CONFIG_ARM_LPAE
+#include <asm/pgtable-3level-hwdef.h>
+#else
+#include <asm/pgtable-2level-hwdef.h>
+#endif
 
 #endif
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index 5750704e027..9d5255ae784 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -11,19 +11,26 @@
 #define _ASMARM_PGTABLE_H
 
 #include <linux/const.h>
-#include <asm-generic/4level-fixup.h>
 #include <asm/proc-fns.h>
 
 #ifndef CONFIG_MMU
 
+#include <asm-generic/4level-fixup.h>
 #include "pgtable-nommu.h"
 
 #else
 
+#include <asm-generic/pgtable-nopud.h>
 #include <asm/memory.h>
 #include <mach/vmalloc.h>
 #include <asm/pgtable-hwdef.h>
 
+#ifdef CONFIG_ARM_LPAE
+#include <asm/pgtable-3level.h>
+#else
+#include <asm/pgtable-2level.h>
+#endif
+
 /*
  * Just any arbitrary offset to the start of the vmalloc VM area: the
  * current 8MB value just means that there will be a 8MB "hole" after the
@@ -41,79 +48,6 @@
 #define VMALLOC_START		(((unsigned long)high_memory + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1))
 #endif
 
-/*
- * Hardware-wise, we have a two level page table structure, where the first
- * level has 4096 entries, and the second level has 256 entries.  Each entry
- * is one 32-bit word.  Most of the bits in the second level entry are used
- * by hardware, and there aren't any "accessed" and "dirty" bits.
- *
- * Linux on the other hand has a three level page table structure, which can
- * be wrapped to fit a two level page table structure easily - using the PGD
- * and PTE only.  However, Linux also expects one "PTE" table per page, and
- * at least a "dirty" bit.
- *
- * Therefore, we tweak the implementation slightly - we tell Linux that we
- * have 2048 entries in the first level, each of which is 8 bytes (iow, two
- * hardware pointers to the second level.)  The second level contains two
- * hardware PTE tables arranged contiguously, preceded by Linux versions
- * which contain the state information Linux needs.  We, therefore, end up
- * with 512 entries in the "PTE" level.
- *
- * This leads to the page tables having the following layout:
- *
- *    pgd             pte
- * |        |
- * +--------+
- * |        |       +------------+ +0
- * +- - - - +       | Linux pt 0 |
- * |        |       +------------+ +1024
- * +--------+ +0    | Linux pt 1 |
- * |        |-----> +------------+ +2048
- * +- - - - + +4    |  h/w pt 0  |
- * |        |-----> +------------+ +3072
- * +--------+ +8    |  h/w pt 1  |
- * |        |       +------------+ +4096
- *
- * See L_PTE_xxx below for definitions of bits in the "Linux pt", and
- * PTE_xxx for definitions of bits appearing in the "h/w pt".
- *
- * PMD_xxx definitions refer to bits in the first level page table.
- *
- * The "dirty" bit is emulated by only granting hardware write permission
- * iff the page is marked "writable" and "dirty" in the Linux PTE.  This
- * means that a write to a clean page will cause a permission fault, and
- * the Linux MM layer will mark the page dirty via handle_pte_fault().
- * For the hardware to notice the permission change, the TLB entry must
- * be flushed, and ptep_set_access_flags() does that for us.
- *
- * The "accessed" or "young" bit is emulated by a similar method; we only
- * allow accesses to the page if the "young" bit is set.  Accesses to the
- * page will cause a fault, and handle_pte_fault() will set the young bit
- * for us as long as the page is marked present in the corresponding Linux
- * PTE entry.  Again, ptep_set_access_flags() will ensure that the TLB is
- * up to date.
- *
- * However, when the "young" bit is cleared, we deny access to the page
- * by clearing the hardware PTE.  Currently Linux does not flush the TLB
- * for us in this case, which means the TLB will retain the transation
- * until either the TLB entry is evicted under pressure, or a context
- * switch which changes the user space mapping occurs.
- */
-#define PTRS_PER_PTE		512
-#define PTRS_PER_PMD		1
-#define PTRS_PER_PGD		2048
-
-#define PTE_HWTABLE_PTRS	(PTRS_PER_PTE)
-#define PTE_HWTABLE_OFF		(PTE_HWTABLE_PTRS * sizeof(pte_t))
-#define PTE_HWTABLE_SIZE	(PTRS_PER_PTE * sizeof(u32))
-
-/*
- * PMD_SHIFT determines the size of the area a second-level page table can map
- * PGDIR_SHIFT determines what a third-level page table entry can map
- */
-#define PMD_SHIFT		21
-#define PGDIR_SHIFT		21
-
 #define LIBRARY_TEXT_START	0x0c000000
 
 #ifndef __ASSEMBLY__
@@ -124,12 +58,6 @@ extern void __pgd_error(const char *file, int line, pgd_t);
 #define pte_ERROR(pte)		__pte_error(__FILE__, __LINE__, pte)
 #define pmd_ERROR(pmd)		__pmd_error(__FILE__, __LINE__, pmd)
 #define pgd_ERROR(pgd)		__pgd_error(__FILE__, __LINE__, pgd)
-#endif /* !__ASSEMBLY__ */
-
-#define PMD_SIZE		(1UL << PMD_SHIFT)
-#define PMD_MASK		(~(PMD_SIZE-1))
-#define PGDIR_SIZE		(1UL << PGDIR_SHIFT)
-#define PGDIR_MASK		(~(PGDIR_SIZE-1))
 
 /*
  * This is the lowest virtual address we can permit any user space
@@ -138,60 +66,6 @@ extern void __pgd_error(const char *file, int line, pgd_t);
  */
 #define FIRST_USER_ADDRESS	PAGE_SIZE
 
-#define USER_PTRS_PER_PGD	(TASK_SIZE / PGDIR_SIZE)
-
-/*
- * section address mask and size definitions.
- */
-#define SECTION_SHIFT		20
-#define SECTION_SIZE		(1UL << SECTION_SHIFT)
-#define SECTION_MASK		(~(SECTION_SIZE-1))
-
-/*
- * ARMv6 supersection address mask and size definitions.
- */
-#define SUPERSECTION_SHIFT	24
-#define SUPERSECTION_SIZE	(1UL << SUPERSECTION_SHIFT)
-#define SUPERSECTION_MASK	(~(SUPERSECTION_SIZE-1))
-
-/*
- * "Linux" PTE definitions.
- *
- * We keep two sets of PTEs - the hardware and the linux version.
- * This allows greater flexibility in the way we map the Linux bits
- * onto the hardware tables, and allows us to have YOUNG and DIRTY
- * bits.
- *
- * The PTE table pointer refers to the hardware entries; the "Linux"
- * entries are stored 1024 bytes below.
- */
-#define L_PTE_PRESENT		(_AT(pteval_t, 1) << 0)
-#define L_PTE_YOUNG		(_AT(pteval_t, 1) << 1)
-#define L_PTE_FILE		(_AT(pteval_t, 1) << 2)	/* only when !PRESENT */
-#define L_PTE_DIRTY		(_AT(pteval_t, 1) << 6)
-#define L_PTE_RDONLY		(_AT(pteval_t, 1) << 7)
-#define L_PTE_USER		(_AT(pteval_t, 1) << 8)
-#define L_PTE_XN		(_AT(pteval_t, 1) << 9)
-#define L_PTE_SHARED		(_AT(pteval_t, 1) << 10)	/* shared(v6), coherent(xsc3) */
-
-/*
- * These are the memory types, defined to be compatible with
- * pre-ARMv6 CPUs cacheable and bufferable bits:   XXCB
- */
-#define L_PTE_MT_UNCACHED	(_AT(pteval_t, 0x00) << 2)	/* 0000 */
-#define L_PTE_MT_BUFFERABLE	(_AT(pteval_t, 0x01) << 2)	/* 0001 */
-#define L_PTE_MT_WRITETHROUGH	(_AT(pteval_t, 0x02) << 2)	/* 0010 */
-#define L_PTE_MT_WRITEBACK	(_AT(pteval_t, 0x03) << 2)	/* 0011 */
-#define L_PTE_MT_MINICACHE	(_AT(pteval_t, 0x06) << 2)	/* 0110 (sa1100, xscale) */
-#define L_PTE_MT_WRITEALLOC	(_AT(pteval_t, 0x07) << 2)	/* 0111 */
-#define L_PTE_MT_DEV_SHARED	(_AT(pteval_t, 0x04) << 2)	/* 0100 */
-#define L_PTE_MT_DEV_NONSHARED	(_AT(pteval_t, 0x0c) << 2)	/* 1100 */
-#define L_PTE_MT_DEV_WC		(_AT(pteval_t, 0x09) << 2)	/* 1001 */
-#define L_PTE_MT_DEV_CACHED	(_AT(pteval_t, 0x0b) << 2)	/* 1011 */
-#define L_PTE_MT_MASK		(_AT(pteval_t, 0x0f) << 2)
-
-#ifndef __ASSEMBLY__
-
 /*
  * The pgprot_* and protection_map entries will be fixed up in runtime
  * to include the cachable and bufferable bits based on memory policy,
@@ -232,6 +106,9 @@ extern pgprot_t		pgprot_kernel;
 #define pgprot_writecombine(prot) \
 	__pgprot_modify(prot, L_PTE_MT_MASK, L_PTE_MT_BUFFERABLE)
 
+#define pgprot_stronglyordered(prot) \
+	__pgprot_modify(prot, L_PTE_MT_MASK, L_PTE_MT_UNCACHED)
+
 #ifdef CONFIG_ARM_DMA_MEM_BUFFERABLE
 #define pgprot_dmacoherent(prot) \
 	__pgprot_modify(prot, L_PTE_MT_MASK, L_PTE_MT_BUFFERABLE | L_PTE_XN)
@@ -291,50 +168,15 @@ extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
 /* to find an entry in a kernel page-table-directory */
 #define pgd_offset_k(addr)	pgd_offset(&init_mm, addr)
 
-/*
- * The "pgd_xxx()" functions here are trivial for a folded two-level
- * setup: the pgd is never bad, and a pmd always exists (as it's folded
- * into the pgd entry)
- */
-#define pgd_none(pgd)		(0)
-#define pgd_bad(pgd)		(0)
-#define pgd_present(pgd)	(1)
-#define pgd_clear(pgdp)		do { } while (0)
-#define set_pgd(pgd,pgdp)	do { } while (0)
-#define set_pud(pud,pudp)	do { } while (0)
-
-
-/* Find an entry in the second-level page table.. */
-#define pmd_offset(dir, addr)	((pmd_t *)(dir))
-
 #define pmd_none(pmd)		(!pmd_val(pmd))
 #define pmd_present(pmd)	(pmd_val(pmd))
-#define pmd_bad(pmd)		(pmd_val(pmd) & 2)
-
-#define copy_pmd(pmdpd,pmdps)		\
-	do {				\
-		pmdpd[0] = pmdps[0];	\
-		pmdpd[1] = pmdps[1];	\
-		flush_pmd_entry(pmdpd);	\
-	} while (0)
-
-#define pmd_clear(pmdp)			\
-	do {				\
-		pmdp[0] = __pmd(0);	\
-		pmdp[1] = __pmd(0);	\
-		clean_pmd_entry(pmdp);	\
-	} while (0)
 
 static inline pte_t *pmd_page_vaddr(pmd_t pmd)
 {
-	return __va(pmd_val(pmd) & PAGE_MASK);
+	return __va(pmd_val(pmd) & PHYS_MASK & (s32)PAGE_MASK);
 }
 
-#define pmd_page(pmd)		pfn_to_page(__phys_to_pfn(pmd_val(pmd)))
-
-/* we don't need complex calculations here as the pmd is folded into the pgd */
-#define pmd_addr_end(addr,end)	(end)
-
+#define pmd_page(pmd)		pfn_to_page(__phys_to_pfn(pmd_val(pmd) & PHYS_MASK))
 
 #ifndef CONFIG_HIGHPTE
 #define __pte_map(pmd)		pmd_page_vaddr(*(pmd))
@@ -351,13 +193,12 @@ static inline pte_t *pmd_page_vaddr(pmd_t pmd)
 #define pte_offset_map(pmd,addr)	(__pte_map(pmd) + pte_index(addr))
 #define pte_unmap(pte)			__pte_unmap(pte)
 
-#define pte_pfn(pte)		(pte_val(pte) >> PAGE_SHIFT)
+#define pte_pfn(pte)		((pte_val(pte) & PHYS_MASK) >> PAGE_SHIFT)
 #define pfn_pte(pfn,prot)	__pte(__pfn_to_phys(pfn) | pgprot_val(prot))
 
 #define pte_page(pte)		pfn_to_page(pte_pfn(pte))
 #define mk_pte(page,prot)	pfn_pte(page_to_pfn(page), prot)
 
-#define set_pte_ext(ptep,pte,ext) cpu_set_pte_ext(ptep,pte,ext)
 #define pte_clear(mm,addr,ptep)	set_pte_ext(ptep, __pte(0), 0)
 
 #if __LINUX_ARM_ARCH__ < 6
@@ -464,6 +305,7 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
  * We provide our own arch_get_unmapped_area to cope with VIPT caches.
  */
 #define HAVE_ARCH_UNMAPPED_AREA
+#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
 
 /*
  * remap a physical page `pfn' of size `size' with page protection `prot'
diff --git a/arch/arm/include/asm/pmu.h b/arch/arm/include/asm/pmu.h
index b7e82c4aced..71d99b83cdb 100644
--- a/arch/arm/include/asm/pmu.h
+++ b/arch/arm/include/asm/pmu.h
@@ -13,7 +13,12 @@
 #define __ARM_PMU_H__
 
 #include <linux/interrupt.h>
+#include <linux/perf_event.h>
 
+/*
+ * Types of PMUs that can be accessed directly and require mutual
+ * exclusion between profiling tools.
+ */
 enum arm_pmu_type {
 	ARM_PMU_DEVICE_CPU	= 0,
 	ARM_NUM_PMU_DEVICES,
@@ -37,21 +42,17 @@ struct arm_pmu_platdata {
  * reserve_pmu() - reserve the hardware performance counters
  *
  * Reserve the hardware performance counters in the system for exclusive use.
- * The platform_device for the system is returned on success, ERR_PTR()
- * encoded error on failure.
+ * Returns 0 on success or -EBUSY if the lock is already held.
  */
-extern struct platform_device *
+extern int
 reserve_pmu(enum arm_pmu_type type);
 
 /**
  * release_pmu() - Relinquish control of the performance counters
  *
  * Release the performance counters and allow someone else to use them.
- * Callers must have disabled the counters and released IRQs before calling
- * this. The platform_device returned from reserve_pmu() must be passed as
- * a cookie.
  */
-extern int
+extern void
 release_pmu(enum arm_pmu_type type);
 
 /**
@@ -68,24 +69,78 @@ init_pmu(enum arm_pmu_type type);
 
 #include <linux/err.h>
 
-static inline struct platform_device *
-reserve_pmu(enum arm_pmu_type type)
-{
-	return ERR_PTR(-ENODEV);
-}
-
 static inline int
-release_pmu(enum arm_pmu_type type)
+reserve_pmu(enum arm_pmu_type type)
 {
 	return -ENODEV;
 }
 
-static inline int
-init_pmu(enum arm_pmu_type type)
-{
-	return -ENODEV;
-}
+static inline void
+release_pmu(enum arm_pmu_type type)	{ }
 
 #endif /* CONFIG_CPU_HAS_PMU */
 
+#ifdef CONFIG_HW_PERF_EVENTS
+
+/* The events for a given PMU register set. */
+struct pmu_hw_events {
+	/*
+	 * The events that are active on the PMU for the given index.
+	 */
+	struct perf_event	**events;
+
+	/*
+	 * A 1 bit for an index indicates that the counter is being used for
+	 * an event. A 0 means that the counter can be used.
+	 */
+	unsigned long           *used_mask;
+
+	/*
+	 * Hardware lock to serialize accesses to PMU registers. Needed for the
+	 * read/modify/write sequences.
+	 */
+	raw_spinlock_t		pmu_lock;
+};
+
+struct arm_pmu {
+	struct pmu	pmu;
+	enum arm_perf_pmu_ids id;
+	enum arm_pmu_type type;
+	cpumask_t	active_irqs;
+	const char	*name;
+	irqreturn_t	(*handle_irq)(int irq_num, void *dev);
+	void		(*enable)(struct hw_perf_event *evt, int idx);
+	void		(*disable)(struct hw_perf_event *evt, int idx);
+	int		(*get_event_idx)(struct pmu_hw_events *hw_events,
+					 struct hw_perf_event *hwc);
+	int		(*set_event_filter)(struct hw_perf_event *evt,
+					    struct perf_event_attr *attr);
+	u32		(*read_counter)(int idx);
+	void		(*write_counter)(int idx, u32 val);
+	void		(*start)(void);
+	void		(*stop)(void);
+	void		(*reset)(void *);
+	int		(*map_event)(struct perf_event *event);
+	int		num_events;
+	atomic_t	active_events;
+	struct mutex	reserve_mutex;
+	u64		max_period;
+	struct platform_device	*plat_device;
+	struct pmu_hw_events	*(*get_hw_events)(void);
+};
+
+#define to_arm_pmu(p) (container_of(p, struct arm_pmu, pmu))
+
+int __init armpmu_register(struct arm_pmu *armpmu, char *name, int type);
+
+u64 armpmu_event_update(struct perf_event *event,
+			struct hw_perf_event *hwc,
+			int idx, int overflow);
+
+int armpmu_event_set_period(struct perf_event *event,
+			    struct hw_perf_event *hwc,
+			    int idx);
+
+#endif /* CONFIG_HW_PERF_EVENTS */
+
 #endif /* __ARM_PMU_H__ */
diff --git a/arch/arm/include/asm/proc-fns.h b/arch/arm/include/asm/proc-fns.h
index 633d1cb84d8..f3628fb3d2b 100644
--- a/arch/arm/include/asm/proc-fns.h
+++ b/arch/arm/include/asm/proc-fns.h
@@ -65,7 +65,11 @@ extern struct processor {
 	 * Set a possibly extended PTE.  Non-extended PTEs should
 	 * ignore 'ext'.
 	 */
+#ifdef CONFIG_ARM_LPAE
+	void (*set_pte_ext)(pte_t *ptep, pte_t pte);
+#else
 	void (*set_pte_ext)(pte_t *ptep, pte_t pte, unsigned int ext);
+#endif
 
 	/* Suspend/resume */
 	unsigned int suspend_size;
@@ -79,8 +83,16 @@ extern void cpu_proc_fin(void);
 extern int cpu_do_idle(void);
 extern void cpu_dcache_clean_area(void *, int);
 extern void cpu_do_switch_mm(unsigned long pgd_phys, struct mm_struct *mm);
+#ifdef CONFIG_ARM_LPAE
+extern void cpu_set_pte_ext(pte_t *ptep, pte_t pte);
+#else
 extern void cpu_set_pte_ext(pte_t *ptep, pte_t pte, unsigned int ext);
+#endif
 extern void cpu_reset(unsigned long addr) __attribute__((noreturn));
+
+/* These three are private to arch/arm/kernel/suspend.c */
+extern void cpu_do_suspend(void *);
+extern void cpu_do_resume(void *);
 #else
 #define cpu_proc_init			processor._proc_init
 #define cpu_proc_fin			processor._proc_fin
@@ -89,6 +101,10 @@ extern void cpu_reset(unsigned long addr) __attribute__((noreturn));
 #define cpu_dcache_clean_area		processor.dcache_clean_area
 #define cpu_set_pte_ext			processor.set_pte_ext
 #define cpu_do_switch_mm		processor.switch_mm
+
+/* These three are private to arch/arm/kernel/suspend.c */
+#define cpu_do_suspend			processor.do_suspend
+#define cpu_do_resume			processor.do_resume
 #endif
 
 extern void cpu_resume(void);
@@ -99,6 +115,18 @@ extern void cpu_resume(void);
 
 #define cpu_switch_mm(pgd,mm) cpu_do_switch_mm(virt_to_phys(pgd),mm)
 
+#ifdef CONFIG_ARM_LPAE
+#define cpu_get_pgd()	\
+	({						\
+		unsigned long pg, pg2;			\
+		__asm__("mrrc	p15, 0, %0, %1, c2"	\
+			: "=r" (pg), "=r" (pg2)		\
+			:				\
+			: "cc");			\
+		pg &= ~(PTRS_PER_PGD*sizeof(pgd_t)-1);	\
+		(pgd_t *)phys_to_virt(pg);		\
+	})
+#else
 #define cpu_get_pgd()	\
 	({						\
 		unsigned long pg;			\
@@ -107,6 +135,7 @@ extern void cpu_resume(void);
 		pg &= ~0x3fff;				\
 		(pgd_t *)phys_to_virt(pg);		\
 	})
+#endif
 
 #endif
 
diff --git a/arch/arm/include/asm/processor.h b/arch/arm/include/asm/processor.h
index b2d9df5667a..ce280b8d613 100644
--- a/arch/arm/include/asm/processor.h
+++ b/arch/arm/include/asm/processor.h
@@ -123,6 +123,8 @@ static inline void prefetch(const void *ptr)
 
 #endif
 
+#define HAVE_ARCH_PICK_MMAP_LAYOUT
+
 #endif
 
 #endif /* __ASM_ARM_PROCESSOR_H */
diff --git a/arch/arm/include/asm/suspend.h b/arch/arm/include/asm/suspend.h
index b0e4e1a0231..1c0a551ae37 100644
--- a/arch/arm/include/asm/suspend.h
+++ b/arch/arm/include/asm/suspend.h
@@ -1,22 +1,7 @@
 #ifndef __ASM_ARM_SUSPEND_H
 #define __ASM_ARM_SUSPEND_H
 
-#include <asm/memory.h>
-#include <asm/tlbflush.h>
-
 extern void cpu_resume(void);
-
-/*
- * Hide the first two arguments to __cpu_suspend - these are an implementation
- * detail which platform code shouldn't have to know about.
- */
-static inline int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
-{
-	extern int __cpu_suspend(int, long, unsigned long,
-				 int (*)(unsigned long));
-	int ret = __cpu_suspend(0, PHYS_OFFSET - PAGE_OFFSET, arg, fn);
-	flush_tlb_all();
-	return ret;
-}
+extern int cpu_suspend(unsigned long, int (*)(unsigned long));
 
 #endif
diff --git a/arch/arm/include/asm/system.h b/arch/arm/include/asm/system.h
index 42d7d5c6594..c6b0f485795 100644
--- a/arch/arm/include/asm/system.h
+++ b/arch/arm/include/asm/system.h
@@ -57,6 +57,7 @@
 
 #ifndef __ASSEMBLY__
 
+#include <linux/compiler.h>
 #include <linux/linkage.h>
 #include <linux/irqflags.h>
 
@@ -86,6 +87,14 @@ struct siginfo;
 void arm_notify_die(const char *str, struct pt_regs *regs, struct siginfo *info,
 		unsigned long err, unsigned long trap);
 
+#ifdef CONFIG_ARM_LPAE
+#define FAULT_CODE_ALIGNMENT	33
+#define FAULT_CODE_DEBUG	34
+#else
+#define FAULT_CODE_ALIGNMENT	1
+#define FAULT_CODE_DEBUG	2
+#endif
+
 void hook_fault_code(int nr, int (*fn)(unsigned long, unsigned int,
 				       struct pt_regs *),
 		     int sig, int code, const char *name);
@@ -104,7 +113,7 @@ struct mm_struct;
 extern void show_pte(struct mm_struct *mm, unsigned long addr);
 extern void __show_regs(struct pt_regs *);
 
-extern int cpu_architecture(void);
+extern int __pure cpu_architecture(void);
 extern void cpu_init(void);
 
 void arm_machine_restart(char mode, const char *cmd);
diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h
index 265f908c4a6..5d3ed7e3856 100644
--- a/arch/arm/include/asm/tlb.h
+++ b/arch/arm/include/asm/tlb.h
@@ -202,8 +202,18 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 	tlb_remove_page(tlb, pte);
 }
 
+static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
+				  unsigned long addr)
+{
+#ifdef CONFIG_ARM_LPAE
+	tlb_add_flush(tlb, addr);
+	tlb_remove_page(tlb, virt_to_page(pmdp));
+#endif
+}
+
 #define pte_free_tlb(tlb, ptep, addr)	__pte_free_tlb(tlb, ptep, addr)
-#define pmd_free_tlb(tlb, pmdp, addr)	pmd_free((tlb)->mm, pmdp)
+#define pmd_free_tlb(tlb, pmdp, addr)	__pmd_free_tlb(tlb, pmdp, addr)
+#define pud_free_tlb(tlb, pudp, addr)	pud_free((tlb)->mm, pudp)
 
 #define tlb_migrate_finish(mm)		do { } while (0)
 
diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h
index 8077145698f..02b2f820398 100644
--- a/arch/arm/include/asm/tlbflush.h
+++ b/arch/arm/include/asm/tlbflush.h
@@ -471,7 +471,7 @@ static inline void local_flush_tlb_kernel_page(unsigned long kaddr)
  *	these operations.  This is typically used when we are removing
  *	PMD entries.
  */
-static inline void flush_pmd_entry(pmd_t *pmd)
+static inline void flush_pmd_entry(void *pmd)
 {
 	const unsigned int __tlb_flag = __cpu_tlb_flags;
 
@@ -487,7 +487,7 @@ static inline void flush_pmd_entry(pmd_t *pmd)
 		dsb();
 }
 
-static inline void clean_pmd_entry(pmd_t *pmd)
+static inline void clean_pmd_entry(void *pmd)
 {
 	const unsigned int __tlb_flag = __cpu_tlb_flags;
 
diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h
index accbd7cad9b..f7f02e392ef 100644
--- a/arch/arm/include/asm/topology.h
+++ b/arch/arm/include/asm/topology.h
@@ -1,6 +1,72 @@
 #ifndef _ASM_ARM_TOPOLOGY_H
 #define _ASM_ARM_TOPOLOGY_H
 
+#ifdef CONFIG_ARM_CPU_TOPOLOGY
+
+#include <linux/cpumask.h>
+
+struct cputopo_arm {
+	int thread_id;
+	int core_id;
+	int socket_id;
+	cpumask_t thread_sibling;
+	cpumask_t core_sibling;
+};
+
+extern struct cputopo_arm cpu_topology[NR_CPUS];
+
+#define topology_physical_package_id(cpu)	(cpu_topology[cpu].socket_id)
+#define topology_core_id(cpu)		(cpu_topology[cpu].core_id)
+#define topology_core_cpumask(cpu)	(&cpu_topology[cpu].core_sibling)
+#define topology_thread_cpumask(cpu)	(&cpu_topology[cpu].thread_sibling)
+
+#define mc_capable()	(cpu_topology[0].socket_id != -1)
+#define smt_capable()	(cpu_topology[0].thread_id != -1)
+
+void init_cpu_topology(void);
+void store_cpu_topology(unsigned int cpuid);
+const struct cpumask *cpu_coregroup_mask(int cpu);
+
+#else
+
+static inline void init_cpu_topology(void) { }
+static inline void store_cpu_topology(unsigned int cpuid) { }
+
+#endif
+
+/* Common values for CPUs */
+#ifndef SD_CPU_INIT
+#define SD_CPU_INIT (struct sched_domain) {				\
+	.min_interval		= 1,					\
+	.max_interval		= 4,					\
+	.busy_factor		= 64,					\
+	.imbalance_pct		= 125,					\
+	.cache_nice_tries	= 1,					\
+	.busy_idx		= 2,					\
+	.idle_idx		= 1,					\
+	.newidle_idx		= 0,					\
+	.wake_idx		= 0,					\
+	.forkexec_idx		= 0,					\
+									\
+	.flags			= 1*SD_LOAD_BALANCE			\
+				| 1*SD_BALANCE_NEWIDLE			\
+				| 1*SD_BALANCE_EXEC			\
+				| 1*SD_BALANCE_FORK			\
+				| 0*SD_BALANCE_WAKE			\
+				| 1*SD_WAKE_AFFINE			\
+				| 0*SD_PREFER_LOCAL			\
+				| 0*SD_SHARE_CPUPOWER			\
+				| 0*SD_SHARE_PKG_RESOURCES		\
+				| 0*SD_SERIALIZE			\
+				| arch_sd_sibling_asym_packing()	\
+				| sd_balance_for_package_power()	\
+				| sd_power_saving_flags()		\
+				,					\
+	.last_balance		= jiffies,				\
+	.balance_interval	= 1,					\
+}
+#endif
+
 #include <asm-generic/topology.h>
 
 #endif /* _ASM_ARM_TOPOLOGY_H */
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index f7887dc53c1..7cac26c5f50 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -29,7 +29,7 @@ obj-$(CONFIG_MODULES)		+= armksyms.o module.o
 obj-$(CONFIG_ARTHUR)		+= arthur.o
 obj-$(CONFIG_ISA_DMA)		+= dma-isa.o
 obj-$(CONFIG_PCI)		+= bios32.o isa.o
-obj-$(CONFIG_PM_SLEEP)		+= sleep.o
+obj-$(CONFIG_PM_SLEEP)		+= sleep.o suspend.o
 obj-$(CONFIG_HAVE_SCHED_CLOCK)	+= sched_clock.o
 obj-$(CONFIG_SMP)		+= smp.o smp_tlb.o
 obj-$(CONFIG_HAVE_ARM_SCU)	+= smp_scu.o
@@ -43,6 +43,13 @@ obj-$(CONFIG_KPROBES)		+= kprobes-thumb.o
 else
 obj-$(CONFIG_KPROBES)		+= kprobes-arm.o
 endif
+obj-$(CONFIG_ARM_KPROBES_TEST)	+= test-kprobes.o
+test-kprobes-objs		:= kprobes-test.o
+ifdef CONFIG_THUMB2_KERNEL
+test-kprobes-objs		+= kprobes-test-thumb.o
+else
+test-kprobes-objs		+= kprobes-test-arm.o
+endif
 obj-$(CONFIG_ATAGS_PROC)	+= atags.o
 obj-$(CONFIG_OABI_COMPAT)	+= sys_oabi-compat.o
 obj-$(CONFIG_ARM_THUMBEE)	+= thumbee.o
@@ -66,6 +73,7 @@ obj-$(CONFIG_IWMMXT)		+= iwmmxt.o
 obj-$(CONFIG_CPU_HAS_PMU)	+= pmu.o
 obj-$(CONFIG_HW_PERF_EVENTS)	+= perf_event.o
 AFLAGS_iwmmxt.o			:= -Wa,-mcpu=iwmmxt
+obj-$(CONFIG_ARM_CPU_TOPOLOGY)  += topology.o
 
 ifneq ($(CONFIG_ARCH_EBSA110),y)
   obj-y		+= io.o
diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index 16baba2e436..1429d8989fb 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -20,6 +20,7 @@
 #include <asm/thread_info.h>
 #include <asm/memory.h>
 #include <asm/procinfo.h>
+#include <asm/hardware/cache-l2x0.h>
 #include <linux/kbuild.h>
 
 /*
@@ -92,6 +93,17 @@ int main(void)
   DEFINE(S_OLD_R0,		offsetof(struct pt_regs, ARM_ORIG_r0));
   DEFINE(S_FRAME_SIZE,		sizeof(struct pt_regs));
   BLANK();
+#ifdef CONFIG_CACHE_L2X0
+  DEFINE(L2X0_R_PHY_BASE,	offsetof(struct l2x0_regs, phy_base));
+  DEFINE(L2X0_R_AUX_CTRL,	offsetof(struct l2x0_regs, aux_ctrl));
+  DEFINE(L2X0_R_TAG_LATENCY,	offsetof(struct l2x0_regs, tag_latency));
+  DEFINE(L2X0_R_DATA_LATENCY,	offsetof(struct l2x0_regs, data_latency));
+  DEFINE(L2X0_R_FILTER_START,	offsetof(struct l2x0_regs, filter_start));
+  DEFINE(L2X0_R_FILTER_END,	offsetof(struct l2x0_regs, filter_end));
+  DEFINE(L2X0_R_PREFETCH_CTRL,	offsetof(struct l2x0_regs, prefetch_ctrl));
+  DEFINE(L2X0_R_PWR_CTRL,	offsetof(struct l2x0_regs, pwr_ctrl));
+  BLANK();
+#endif
 #ifdef CONFIG_CPU_HAS_ASID
   DEFINE(MM_CONTEXT_ID,		offsetof(struct mm_struct, context.id));
   BLANK();
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index a87cbf889ff..9ad50c4208a 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -24,6 +24,7 @@
 #include <asm/unwind.h>
 #include <asm/unistd.h>
 #include <asm/tls.h>
+#include <asm/system.h>
 
 #include "entry-header.S"
 #include <asm/entry-macro-multi.S>
@@ -262,8 +263,7 @@ __und_svc:
 	ldr	r0, [r4, #-4]
 #else
 	ldrh	r0, [r4, #-2]			@ Thumb instruction at LR - 2
-	and	r9, r0, #0xf800
-	cmp	r9, #0xe800			@ 32-bit instruction if xx >= 0
+	cmp	r0, #0xe800			@ 32-bit instruction if xx >= 0
 	ldrhhs	r9, [r4]			@ bottom 16 bits
 	orrhs	r0, r9, r0, lsl #16
 #endif
@@ -440,18 +440,46 @@ __und_usr:
 #endif
 	beq	call_fpe
 	@ Thumb instruction
-#if __LINUX_ARM_ARCH__ >= 7
+#if CONFIG_ARM_THUMB && __LINUX_ARM_ARCH__ >= 6 && CONFIG_CPU_V7
+/*
+ * Thumb-2 instruction handling.  Note that because pre-v6 and >= v6 platforms
+ * can never be supported in a single kernel, this code is not applicable at
+ * all when __LINUX_ARM_ARCH__ < 6.  This allows simplifying assumptions to be
+ * made about .arch directives.
+ */
+#if __LINUX_ARM_ARCH__ < 7
+/* If the target CPU may not be Thumb-2-capable, a run-time check is needed: */
+#define NEED_CPU_ARCHITECTURE
+	ldr	r5, .LCcpu_architecture
+	ldr	r5, [r5]
+	cmp	r5, #CPU_ARCH_ARMv7
+	blo	__und_usr_unknown
+/*
+ * The following code won't get run unless the running CPU really is v7, so
+ * coding round the lack of ldrht on older arches is pointless.  Temporarily
+ * override the assembler target arch with the minimum required instead:
+ */
+	.arch	armv6t2
+#endif
 2:
  ARM(	ldrht	r5, [r4], #2	)
  THUMB(	ldrht	r5, [r4]	)
  THUMB(	add	r4, r4, #2	)
-	and	r0, r5, #0xf800			@ mask bits 111x x... .... ....
-	cmp	r0, #0xe800			@ 32bit instruction if xx != 0
+	cmp	r5, #0xe800			@ 32bit instruction if xx != 0
 	blo	__und_usr_unknown
 3:	ldrht	r0, [r4]
 	add	r2, r2, #2			@ r2 is PC + 2, make it PC + 4
 	orr	r0, r0, r5, lsl #16
+
+#if __LINUX_ARM_ARCH__ < 7
+/* If the target arch was overridden, change it back: */
+#ifdef CONFIG_CPU_32v6K
+	.arch	armv6k
 #else
+	.arch	armv6
+#endif
+#endif /* __LINUX_ARM_ARCH__ < 7 */
+#else /* !(CONFIG_ARM_THUMB && __LINUX_ARM_ARCH__ >= 6 && CONFIG_CPU_V7) */
 	b	__und_usr_unknown
 #endif
  UNWIND(.fnend		)
@@ -578,6 +606,12 @@ call_fpe:
 	movw_pc	lr				@ CP#14 (Debug)
 	movw_pc	lr				@ CP#15 (Control)
 
+#ifdef NEED_CPU_ARCHITECTURE
+	.align	2
+.LCcpu_architecture:
+	.word	__cpu_architecture
+#endif
+
 #ifdef CONFIG_NEON
 	.align	6
 
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 742b6108a00..1768db22d71 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -21,6 +21,7 @@
 #include <asm/memory.h>
 #include <asm/thread_info.h>
 #include <asm/system.h>
+#include <asm/pgtable.h>
 
 #ifdef CONFIG_DEBUG_LL
 #include <mach/debug-macro.S>
@@ -38,11 +39,20 @@
 #error KERNEL_RAM_VADDR must start at 0xXXXX8000
 #endif
 
+#ifdef CONFIG_ARM_LPAE
+	/* LPAE requires an additional page for the PGD */
+#define PG_DIR_SIZE	0x5000
+#define PMD_ORDER	3
+#else
+#define PG_DIR_SIZE	0x4000
+#define PMD_ORDER	2
+#endif
+
 	.globl	swapper_pg_dir
-	.equ	swapper_pg_dir, KERNEL_RAM_VADDR - 0x4000
+	.equ	swapper_pg_dir, KERNEL_RAM_VADDR - PG_DIR_SIZE
 
 	.macro	pgtbl, rd, phys
-	add	\rd, \phys, #TEXT_OFFSET - 0x4000
+	add	\rd, \phys, #TEXT_OFFSET - PG_DIR_SIZE
 	.endm
 
 #ifdef CONFIG_XIP_KERNEL
@@ -148,11 +158,11 @@ __create_page_tables:
 	pgtbl	r4, r8				@ page table address
 
 	/*
-	 * Clear the 16K level 1 swapper page table
+	 * Clear the swapper page table
 	 */
 	mov	r0, r4
 	mov	r3, #0
-	add	r6, r0, #0x4000
+	add	r6, r0, #PG_DIR_SIZE
 1:	str	r3, [r0], #4
 	str	r3, [r0], #4
 	str	r3, [r0], #4
@@ -160,6 +170,25 @@ __create_page_tables:
 	teq	r0, r6
 	bne	1b
 
+#ifdef CONFIG_ARM_LPAE
+	/*
+	 * Build the PGD table (first level) to point to the PMD table. A PGD
+	 * entry is 64-bit wide.
+	 */
+	mov	r0, r4
+	add	r3, r4, #0x1000			@ first PMD table address
+	orr	r3, r3, #3			@ PGD block type
+	mov	r6, #4				@ PTRS_PER_PGD
+	mov	r7, #1 << (55 - 32)		@ L_PGD_SWAPPER
+1:	str	r3, [r0], #4			@ set bottom PGD entry bits
+	str	r7, [r0], #4			@ set top PGD entry bits
+	add	r3, r3, #0x1000			@ next PMD table
+	subs	r6, r6, #1
+	bne	1b
+
+	add	r4, r4, #0x1000			@ point to the PMD tables
+#endif
+
 	ldr	r7, [r10, #PROCINFO_MM_MMUFLAGS] @ mm_mmuflags
 
 	/*
@@ -171,30 +200,30 @@ __create_page_tables:
 	sub	r0, r0, r3			@ virt->phys offset
 	add	r5, r5, r0			@ phys __enable_mmu
 	add	r6, r6, r0			@ phys __enable_mmu_end
-	mov	r5, r5, lsr #20
-	mov	r6, r6, lsr #20
+	mov	r5, r5, lsr #SECTION_SHIFT
+	mov	r6, r6, lsr #SECTION_SHIFT
 
-1:	orr	r3, r7, r5, lsl #20		@ flags + kernel base
-	str	r3, [r4, r5, lsl #2]		@ identity mapping
-	teq	r5, r6
-	addne	r5, r5, #1			@ next section
-	bne	1b
+1:	orr	r3, r7, r5, lsl #SECTION_SHIFT	@ flags + kernel base
+	str	r3, [r4, r5, lsl #PMD_ORDER]	@ identity mapping
+	cmp	r5, r6
+	addlo	r5, r5, #1			@ next section
+	blo	1b
 
 	/*
 	 * Now setup the pagetables for our kernel direct
 	 * mapped region.
 	 */
 	mov	r3, pc
-	mov	r3, r3, lsr #20
-	orr	r3, r7, r3, lsl #20
-	add	r0, r4,  #(KERNEL_START & 0xff000000) >> 18
-	str	r3, [r0, #(KERNEL_START & 0x00f00000) >> 18]!
+	mov	r3, r3, lsr #SECTION_SHIFT
+	orr	r3, r7, r3, lsl #SECTION_SHIFT
+	add	r0, r4,  #(KERNEL_START & 0xff000000) >> (SECTION_SHIFT - PMD_ORDER)
+	str	r3, [r0, #((KERNEL_START & 0x00f00000) >> SECTION_SHIFT) << PMD_ORDER]!
 	ldr	r6, =(KERNEL_END - 1)
-	add	r0, r0, #4
-	add	r6, r4, r6, lsr #18
+	add	r0, r0, #1 << PMD_ORDER
+	add	r6, r4, r6, lsr #(SECTION_SHIFT - PMD_ORDER)
 1:	cmp	r0, r6
-	add	r3, r3, #1 << 20
-	strls	r3, [r0], #4
+	add	r3, r3, #1 << SECTION_SHIFT
+	strls	r3, [r0], #1 << PMD_ORDER
 	bls	1b
 
 #ifdef CONFIG_XIP_KERNEL
@@ -203,11 +232,11 @@ __create_page_tables:
 	 */
 	add	r3, r8, #TEXT_OFFSET
 	orr	r3, r3, r7
-	add	r0, r4,  #(KERNEL_RAM_VADDR & 0xff000000) >> 18
-	str	r3, [r0, #(KERNEL_RAM_VADDR & 0x00f00000) >> 18]!
+	add	r0, r4,  #(KERNEL_RAM_VADDR & 0xff000000) >> (SECTION_SHIFT - PMD_ORDER)
+	str	r3, [r0, #(KERNEL_RAM_VADDR & 0x00f00000) >> (SECTION_SHIFT - PMD_ORDER)]!
 	ldr	r6, =(_end - 1)
 	add	r0, r0, #4
-	add	r6, r4, r6, lsr #18
+	add	r6, r4, r6, lsr #(SECTION_SHIFT - PMD_ORDER)
 1:	cmp	r0, r6
 	add	r3, r3, #1 << 20
 	strls	r3, [r0], #4
@@ -215,15 +244,15 @@ __create_page_tables:
 #endif
 
 	/*
-	 * Then map boot params address in r2 or
-	 * the first 1MB of ram if boot params address is not specified.
+	 * Then map boot params address in r2 or the first 1MB (2MB with LPAE)
+	 * of ram if boot params address is not specified.
 	 */
-	mov	r0, r2, lsr #20
-	movs	r0, r0, lsl #20
+	mov	r0, r2, lsr #SECTION_SHIFT
+	movs	r0, r0, lsl #SECTION_SHIFT
 	moveq	r0, r8
 	sub	r3, r0, r8
 	add	r3, r3, #PAGE_OFFSET
-	add	r3, r4, r3, lsr #18
+	add	r3, r4, r3, lsr #(SECTION_SHIFT - PMD_ORDER)
 	orr	r6, r7, r0
 	str	r6, [r3]
 
@@ -236,21 +265,27 @@ __create_page_tables:
 	 */
 	addruart r7, r3
 
-	mov	r3, r3, lsr #20
-	mov	r3, r3, lsl #2
+	mov	r3, r3, lsr #SECTION_SHIFT
+	mov	r3, r3, lsl #PMD_ORDER
 
 	add	r0, r4, r3
 	rsb	r3, r3, #0x4000			@ PTRS_PER_PGD*sizeof(long)
 	cmp	r3, #0x0800			@ limit to 512MB
 	movhi	r3, #0x0800
 	add	r6, r0, r3
-	mov	r3, r7, lsr #20
+	mov	r3, r7, lsr #SECTION_SHIFT
 	ldr	r7, [r10, #PROCINFO_IO_MMUFLAGS] @ io_mmuflags
-	orr	r3, r7, r3, lsl #20
+	orr	r3, r7, r3, lsl #SECTION_SHIFT
+#ifdef CONFIG_ARM_LPAE
+	mov	r7, #1 << (54 - 32)		@ XN
+#endif
 1:	str	r3, [r0], #4
-	add	r3, r3, #1 << 20
-	teq	r0, r6
-	bne	1b
+#ifdef CONFIG_ARM_LPAE
+	str	r7, [r0], #4
+#endif
+	add	r3, r3, #1 << SECTION_SHIFT
+	cmp	r0, r6
+	blo	1b
 
 #else /* CONFIG_DEBUG_ICEDCC */
 	/* we don't need any serial debugging mappings for ICEDCC */
@@ -262,7 +297,7 @@ __create_page_tables:
 	 * If we're using the NetWinder or CATS, we also need to map
 	 * in the 16550-type serial port for the debug messages
 	 */
-	add	r0, r4, #0xff000000 >> 18
+	add	r0, r4, #0xff000000 >> (SECTION_SHIFT - PMD_ORDER)
 	orr	r3, r7, #0x7c000000
 	str	r3, [r0]
 #endif
@@ -272,13 +307,16 @@ __create_page_tables:
 	 * Similar reasons here - for debug.  This is
 	 * only for Acorn RiscPC architectures.
 	 */
-	add	r0, r4, #0x02000000 >> 18
+	add	r0, r4, #0x02000000 >> (SECTION_SHIFT - PMD_ORDER)
 	orr	r3, r7, #0x02000000
 	str	r3, [r0]
-	add	r0, r4, #0xd8000000 >> 18
+	add	r0, r4, #0xd8000000 >> (SECTION_SHIFT - PMD_ORDER)
 	str	r3, [r0]
 #endif
 #endif
+#ifdef CONFIG_ARM_LPAE
+	sub	r4, r4, #0x1000		@ point to the PGD table
+#endif
 	mov	pc, lr
 ENDPROC(__create_page_tables)
 	.ltorg
@@ -356,7 +394,7 @@ __secondary_data:
  *  r13 = *virtual* address to jump to upon completion
  */
 __enable_mmu:
-#ifdef CONFIG_ALIGNMENT_TRAP
+#if defined(CONFIG_ALIGNMENT_TRAP) && __LINUX_ARM_ARCH__ < 6
 	orr	r0, r0, #CR_A
 #else
 	bic	r0, r0, #CR_A
@@ -370,12 +408,17 @@ __enable_mmu:
 #ifdef CONFIG_CPU_ICACHE_DISABLE
 	bic	r0, r0, #CR_I
 #endif
+#ifdef CONFIG_ARM_LPAE
+	mov	r5, #0
+	mcrr	p15, 0, r4, r5, c2		@ load TTBR0
+#else
 	mov	r5, #(domain_val(DOMAIN_USER, DOMAIN_MANAGER) | \
 		      domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) | \
 		      domain_val(DOMAIN_TABLE, DOMAIN_MANAGER) | \
 		      domain_val(DOMAIN_IO, DOMAIN_CLIENT))
 	mcr	p15, 0, r5, c3, c0, 0		@ load domain access register
 	mcr	p15, 0, r4, c2, c0, 0		@ load page table pointer
+#endif
 	b	__turn_mmu_on
 ENDPROC(__enable_mmu)
 
@@ -396,8 +439,10 @@ ENDPROC(__enable_mmu)
 	.align	5
 __turn_mmu_on:
 	mov	r0, r0
+	instr_sync
 	mcr	p15, 0, r0, c1, c0, 0		@ write control reg
 	mrc	p15, 0, r3, c0, c0, 0		@ read id reg
+	instr_sync
 	mov	r3, r3
 	mov	r3, r13
 	mov	pc, r3
diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index a927ca1f556..d6a95ef9131 100644
--- a/arch/arm/kernel/hw_breakpoint.c
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -45,7 +45,6 @@ static DEFINE_PER_CPU(struct perf_event *, wp_on_reg[ARM_MAX_WRP]);
 
 /* Number of BRP/WRP registers on this CPU. */
 static int core_num_brps;
-static int core_num_reserved_brps;
 static int core_num_wrps;
 
 /* Debug architecture version. */
@@ -137,10 +136,11 @@ static u8 get_debug_arch(void)
 	u32 didr;
 
 	/* Do we implement the extended CPUID interface? */
-	if (WARN_ONCE((((read_cpuid_id() >> 16) & 0xf) != 0xf),
-	    "CPUID feature registers not supported. "
-	    "Assuming v6 debug is present.\n"))
+	if (((read_cpuid_id() >> 16) & 0xf) != 0xf) {
+		pr_warning("CPUID feature registers not supported. "
+			   "Assuming v6 debug is present.\n");
 		return ARM_DEBUG_ARCH_V6;
+	}
 
 	ARM_DBG_READ(c0, 0, didr);
 	return (didr >> 16) & 0xf;
@@ -154,10 +154,21 @@ u8 arch_get_debug_arch(void)
 static int debug_arch_supported(void)
 {
 	u8 arch = get_debug_arch();
-	return arch >= ARM_DEBUG_ARCH_V6 && arch <= ARM_DEBUG_ARCH_V7_ECP14;
+
+	/* We don't support the memory-mapped interface. */
+	return (arch >= ARM_DEBUG_ARCH_V6 && arch <= ARM_DEBUG_ARCH_V7_ECP14) ||
+		arch >= ARM_DEBUG_ARCH_V7_1;
+}
+
+/* Determine number of WRP registers available. */
+static int get_num_wrp_resources(void)
+{
+	u32 didr;
+	ARM_DBG_READ(c0, 0, didr);
+	return ((didr >> 28) & 0xf) + 1;
 }
 
-/* Determine number of BRP register available. */
+/* Determine number of BRP registers available. */
 static int get_num_brp_resources(void)
 {
 	u32 didr;
@@ -176,9 +187,10 @@ static int core_has_mismatch_brps(void)
 static int get_num_wrps(void)
 {
 	/*
-	 * FIXME: When a watchpoint fires, the only way to work out which
-	 * watchpoint it was is by disassembling the faulting instruction
-	 * and working out the address of the memory access.
+	 * On debug architectures prior to 7.1, when a watchpoint fires, the
+	 * only way to work out which watchpoint it was is by disassembling
+	 * the faulting instruction and working out the address of the memory
+	 * access.
 	 *
 	 * Furthermore, we can only do this if the watchpoint was precise
 	 * since imprecise watchpoints prevent us from calculating register
@@ -192,36 +204,17 @@ static int get_num_wrps(void)
 	 * [the ARM ARM states that the DFAR is UNKNOWN, but experience shows
 	 * that it is set on some implementations].
 	 */
+	if (get_debug_arch() < ARM_DEBUG_ARCH_V7_1)
+		return 1;
 
-#if 0
-	int wrps;
-	u32 didr;
-	ARM_DBG_READ(c0, 0, didr);
-	wrps = ((didr >> 28) & 0xf) + 1;
-#endif
-	int wrps = 1;
-
-	if (core_has_mismatch_brps() && wrps >= get_num_brp_resources())
-		wrps = get_num_brp_resources() - 1;
-
-	return wrps;
-}
-
-/* We reserve one breakpoint for each watchpoint. */
-static int get_num_reserved_brps(void)
-{
-	if (core_has_mismatch_brps())
-		return get_num_wrps();
-	return 0;
+	return get_num_wrp_resources();
 }
 
 /* Determine number of usable BRPs available. */
 static int get_num_brps(void)
 {
 	int brps = get_num_brp_resources();
-	if (core_has_mismatch_brps())
-		brps -= get_num_reserved_brps();
-	return brps;
+	return core_has_mismatch_brps() ? brps - 1 : brps;
 }
 
 /*
@@ -239,7 +232,7 @@ static int enable_monitor_mode(void)
 
 	/* Ensure that halting mode is disabled. */
 	if (WARN_ONCE(dscr & ARM_DSCR_HDBGEN,
-			"halting debug mode enabled. Unable to access hardware resources.\n")) {
+		"halting debug mode enabled. Unable to access hardware resources.\n")) {
 		ret = -EPERM;
 		goto out;
 	}
@@ -255,6 +248,7 @@ static int enable_monitor_mode(void)
 		ARM_DBG_WRITE(c1, 0, (dscr | ARM_DSCR_MDBGEN));
 		break;
 	case ARM_DEBUG_ARCH_V7_ECP14:
+	case ARM_DEBUG_ARCH_V7_1:
 		ARM_DBG_WRITE(c2, 2, (dscr | ARM_DSCR_MDBGEN));
 		break;
 	default:
@@ -346,24 +340,10 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
 		val_base = ARM_BASE_BVR;
 		slots = (struct perf_event **)__get_cpu_var(bp_on_reg);
 		max_slots = core_num_brps;
-		if (info->step_ctrl.enabled) {
-			/* Override the breakpoint data with the step data. */
-			addr = info->trigger & ~0x3;
-			ctrl = encode_ctrl_reg(info->step_ctrl);
-		}
 	} else {
 		/* Watchpoint */
-		if (info->step_ctrl.enabled) {
-			/* Install into the reserved breakpoint region. */
-			ctrl_base = ARM_BASE_BCR + core_num_brps;
-			val_base = ARM_BASE_BVR + core_num_brps;
-			/* Override the watchpoint data with the step data. */
-			addr = info->trigger & ~0x3;
-			ctrl = encode_ctrl_reg(info->step_ctrl);
-		} else {
-			ctrl_base = ARM_BASE_WCR;
-			val_base = ARM_BASE_WVR;
-		}
+		ctrl_base = ARM_BASE_WCR;
+		val_base = ARM_BASE_WVR;
 		slots = (struct perf_event **)__get_cpu_var(wp_on_reg);
 		max_slots = core_num_wrps;
 	}
@@ -382,6 +362,17 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
 		goto out;
 	}
 
+	/* Override the breakpoint data with the step data. */
+	if (info->step_ctrl.enabled) {
+		addr = info->trigger & ~0x3;
+		ctrl = encode_ctrl_reg(info->step_ctrl);
+		if (info->ctrl.type != ARM_BREAKPOINT_EXECUTE) {
+			i = 0;
+			ctrl_base = ARM_BASE_BCR + core_num_brps;
+			val_base = ARM_BASE_BVR + core_num_brps;
+		}
+	}
+
 	/* Setup the address register. */
 	write_wb_reg(val_base + i, addr);
 
@@ -405,10 +396,7 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp)
 		max_slots = core_num_brps;
 	} else {
 		/* Watchpoint */
-		if (info->step_ctrl.enabled)
-			base = ARM_BASE_BCR + core_num_brps;
-		else
-			base = ARM_BASE_WCR;
+		base = ARM_BASE_WCR;
 		slots = (struct perf_event **)__get_cpu_var(wp_on_reg);
 		max_slots = core_num_wrps;
 	}
@@ -426,6 +414,13 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp)
 	if (WARN_ONCE(i == max_slots, "Can't find any breakpoint slot\n"))
 		return;
 
+	/* Ensure that we disable the mismatch breakpoint. */
+	if (info->ctrl.type != ARM_BREAKPOINT_EXECUTE &&
+	    info->step_ctrl.enabled) {
+		i = 0;
+		base = ARM_BASE_BCR + core_num_brps;
+	}
+
 	/* Reset the control register. */
 	write_wb_reg(base + i, 0);
 }
@@ -632,10 +627,9 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 	 * we can use the mismatch feature as a poor-man's hardware
 	 * single-step, but this only works for per-task breakpoints.
 	 */
-	if (WARN_ONCE(!bp->overflow_handler &&
-		(arch_check_bp_in_kernelspace(bp) || !core_has_mismatch_brps()
-		 || !bp->hw.bp_target),
-			"overflow handler required but none found\n")) {
+	if (!bp->overflow_handler && (arch_check_bp_in_kernelspace(bp) ||
+	    !core_has_mismatch_brps() || !bp->hw.bp_target)) {
+		pr_warning("overflow handler required but none found\n");
 		ret = -EINVAL;
 	}
 out:
@@ -666,34 +660,62 @@ static void disable_single_step(struct perf_event *bp)
 	arch_install_hw_breakpoint(bp);
 }
 
-static void watchpoint_handler(unsigned long unknown, struct pt_regs *regs)
+static void watchpoint_handler(unsigned long addr, unsigned int fsr,
+			       struct pt_regs *regs)
 {
-	int i;
+	int i, access;
+	u32 val, ctrl_reg, alignment_mask;
 	struct perf_event *wp, **slots;
 	struct arch_hw_breakpoint *info;
+	struct arch_hw_breakpoint_ctrl ctrl;
 
 	slots = (struct perf_event **)__get_cpu_var(wp_on_reg);
 
-	/* Without a disassembler, we can only handle 1 watchpoint. */
-	BUG_ON(core_num_wrps > 1);
-
 	for (i = 0; i < core_num_wrps; ++i) {
 		rcu_read_lock();
 
 		wp = slots[i];
 
-		if (wp == NULL) {
-			rcu_read_unlock();
-			continue;
-		}
+		if (wp == NULL)
+			goto unlock;
 
+		info = counter_arch_bp(wp);
 		/*
-		 * The DFAR is an unknown value. Since we only allow a
-		 * single watchpoint, we can set the trigger to the lowest
-		 * possible faulting address.
+		 * The DFAR is an unknown value on debug architectures prior
+		 * to 7.1. Since we only allow a single watchpoint on these
+		 * older CPUs, we can set the trigger to the lowest possible
+		 * faulting address.
 		 */
-		info = counter_arch_bp(wp);
-		info->trigger = wp->attr.bp_addr;
+		if (debug_arch < ARM_DEBUG_ARCH_V7_1) {
+			BUG_ON(i > 0);
+			info->trigger = wp->attr.bp_addr;
+		} else {
+			if (info->ctrl.len == ARM_BREAKPOINT_LEN_8)
+				alignment_mask = 0x7;
+			else
+				alignment_mask = 0x3;
+
+			/* Check if the watchpoint value matches. */
+			val = read_wb_reg(ARM_BASE_WVR + i);
+			if (val != (addr & ~alignment_mask))
+				goto unlock;
+
+			/* Possible match, check the byte address select. */
+			ctrl_reg = read_wb_reg(ARM_BASE_WCR + i);
+			decode_ctrl_reg(ctrl_reg, &ctrl);
+			if (!((1 << (addr & alignment_mask)) & ctrl.len))
+				goto unlock;
+
+			/* Check that the access type matches. */
+			access = (fsr & ARM_FSR_ACCESS_MASK) ? HW_BREAKPOINT_W :
+				 HW_BREAKPOINT_R;
+			if (!(access & hw_breakpoint_type(wp)))
+				goto unlock;
+
+			/* We have a winner. */
+			info->trigger = addr;
+		}
+
 		pr_debug("watchpoint fired: address = 0x%x\n", info->trigger);
 		perf_bp_event(wp, regs);
 
@@ -705,6 +727,7 @@ static void watchpoint_handler(unsigned long unknown, struct pt_regs *regs)
 		if (!wp->overflow_handler)
 			enable_single_step(wp, instruction_pointer(regs));
 
+unlock:
 		rcu_read_unlock();
 	}
 }
@@ -717,7 +740,7 @@ static void watchpoint_single_step_handler(unsigned long pc)
 
 	slots = (struct perf_event **)__get_cpu_var(wp_on_reg);
 
-	for (i = 0; i < core_num_reserved_brps; ++i) {
+	for (i = 0; i < core_num_wrps; ++i) {
 		rcu_read_lock();
 
 		wp = slots[i];
@@ -820,7 +843,7 @@ static int hw_breakpoint_pending(unsigned long addr, unsigned int fsr,
 	case ARM_ENTRY_ASYNC_WATCHPOINT:
 		WARN(1, "Asynchronous watchpoint exception taken. Debugging results may be unreliable\n");
 	case ARM_ENTRY_SYNC_WATCHPOINT:
-		watchpoint_handler(addr, regs);
+		watchpoint_handler(addr, fsr, regs);
 		break;
 	default:
 		ret = 1; /* Unhandled fault. */
@@ -834,11 +857,31 @@ static int hw_breakpoint_pending(unsigned long addr, unsigned int fsr,
 /*
  * One-time initialisation.
  */
-static void reset_ctrl_regs(void *info)
+static cpumask_t debug_err_mask;
+
+static int debug_reg_trap(struct pt_regs *regs, unsigned int instr)
 {
-	int i, cpu = smp_processor_id();
+	int cpu = smp_processor_id();
+
+	pr_warning("Debug register access (0x%x) caused undefined instruction on CPU %d\n",
+		   instr, cpu);
+
+	/* Set the error flag for this CPU and skip the faulting instruction. */
+	cpumask_set_cpu(cpu, &debug_err_mask);
+	instruction_pointer(regs) += 4;
+	return 0;
+}
+
+static struct undef_hook debug_reg_hook = {
+	.instr_mask	= 0x0fe80f10,
+	.instr_val	= 0x0e000e10,
+	.fn		= debug_reg_trap,
+};
+
+static void reset_ctrl_regs(void *unused)
+{
+	int i, raw_num_brps, err = 0, cpu = smp_processor_id();
 	u32 dbg_power;
-	cpumask_t *cpumask = info;
 
 	/*
 	 * v7 debug contains save and restore registers so that debug state
@@ -848,38 +891,57 @@ static void reset_ctrl_regs(void *info)
 	 * Access Register to avoid taking undefined instruction exceptions
 	 * later on.
 	 */
-	if (debug_arch >= ARM_DEBUG_ARCH_V7_ECP14) {
+	switch (debug_arch) {
+	case ARM_DEBUG_ARCH_V6:
+	case ARM_DEBUG_ARCH_V6_1:
+		/* ARMv6 cores just need to reset the registers. */
+		goto reset_regs;
+	case ARM_DEBUG_ARCH_V7_ECP14:
 		/*
 		 * Ensure sticky power-down is clear (i.e. debug logic is
 		 * powered up).
 		 */
 		asm volatile("mrc p14, 0, %0, c1, c5, 4" : "=r" (dbg_power));
-		if ((dbg_power & 0x1) == 0) {
-			pr_warning("CPU %d debug is powered down!\n", cpu);
-			cpumask_or(cpumask, cpumask, cpumask_of(cpu));
-			return;
-		}
-
+		if ((dbg_power & 0x1) == 0)
+			err = -EPERM;
+		break;
+	case ARM_DEBUG_ARCH_V7_1:
 		/*
-		 * Unconditionally clear the lock by writing a value
-		 * other than 0xC5ACCE55 to the access register.
+		 * Ensure the OS double lock is clear.
 		 */
-		asm volatile("mcr p14, 0, %0, c1, c0, 4" : : "r" (0));
-		isb();
+		asm volatile("mrc p14, 0, %0, c1, c3, 4" : "=r" (dbg_power));
+		if ((dbg_power & 0x1) == 1)
+			err = -EPERM;
+		break;
+	}
 
-		/*
-		 * Clear any configured vector-catch events before
-		 * enabling monitor mode.
-		 */
-		asm volatile("mcr p14, 0, %0, c0, c7, 0" : : "r" (0));
-		isb();
+	if (err) {
+		pr_warning("CPU %d debug is powered down!\n", cpu);
+		cpumask_or(&debug_err_mask, &debug_err_mask, cpumask_of(cpu));
+		return;
 	}
 
+	/*
+	 * Unconditionally clear the lock by writing a value
+	 * other than 0xC5ACCE55 to the access register.
+	 */
+	asm volatile("mcr p14, 0, %0, c1, c0, 4" : : "r" (0));
+	isb();
+
+	/*
+	 * Clear any configured vector-catch events before
+	 * enabling monitor mode.
+	 */
+	asm volatile("mcr p14, 0, %0, c0, c7, 0" : : "r" (0));
+	isb();
+
+reset_regs:
 	if (enable_monitor_mode())
 		return;
 
 	/* We must also reset any reserved registers. */
-	for (i = 0; i < core_num_brps + core_num_reserved_brps; ++i) {
+	raw_num_brps = get_num_brp_resources();
+	for (i = 0; i < raw_num_brps; ++i) {
 		write_wb_reg(ARM_BASE_BCR + i, 0UL);
 		write_wb_reg(ARM_BASE_BVR + i, 0UL);
 	}
@@ -895,6 +957,7 @@ static int __cpuinit dbg_reset_notify(struct notifier_block *self,
 {
 	if (action == CPU_ONLINE)
 		smp_call_function_single((int)cpu, reset_ctrl_regs, NULL, 1);
+
 	return NOTIFY_OK;
 }
 
@@ -905,7 +968,6 @@ static struct notifier_block __cpuinitdata dbg_reset_nb = {
 static int __init arch_hw_breakpoint_init(void)
 {
 	u32 dscr;
-	cpumask_t cpumask = { CPU_BITS_NONE };
 
 	debug_arch = get_debug_arch();
 
@@ -916,28 +978,31 @@ static int __init arch_hw_breakpoint_init(void)
 
 	/* Determine how many BRPs/WRPs are available. */
 	core_num_brps = get_num_brps();
-	core_num_reserved_brps = get_num_reserved_brps();
 	core_num_wrps = get_num_wrps();
 
-	pr_info("found %d breakpoint and %d watchpoint registers.\n",
-		core_num_brps + core_num_reserved_brps, core_num_wrps);
-
-	if (core_num_reserved_brps)
-		pr_info("%d breakpoint(s) reserved for watchpoint "
-				"single-step.\n", core_num_reserved_brps);
+	/*
+	 * We need to tread carefully here because DBGSWENABLE may be
+	 * driven low on this core and there isn't an architected way to
+	 * determine that.
+	 */
+	register_undef_hook(&debug_reg_hook);
 
 	/*
 	 * Reset the breakpoint resources. We assume that a halting
 	 * debugger will leave the world in a nice state for us.
 	 */
-	on_each_cpu(reset_ctrl_regs, &cpumask, 1);
-	if (!cpumask_empty(&cpumask)) {
+	on_each_cpu(reset_ctrl_regs, NULL, 1);
+	unregister_undef_hook(&debug_reg_hook);
+	if (!cpumask_empty(&debug_err_mask)) {
 		core_num_brps = 0;
-		core_num_reserved_brps = 0;
 		core_num_wrps = 0;
 		return 0;
 	}
 
+	pr_info("found %d " "%s" "breakpoint and %d watchpoint registers.\n",
+		core_num_brps, core_has_mismatch_brps() ? "(+1 reserved) " :
+		"", core_num_wrps);
+
 	ARM_DBG_READ(c1, 0, dscr);
 	if (dscr & ARM_DSCR_HDBGEN) {
 		max_watchpoint_len = 4;
@@ -951,10 +1016,10 @@ static int __init arch_hw_breakpoint_init(void)
 	}
 
 	/* Register debug fault handler. */
-	hook_fault_code(2, hw_breakpoint_pending, SIGTRAP, TRAP_HWBKPT,
-			"watchpoint debug exception");
-	hook_ifault_code(2, hw_breakpoint_pending, SIGTRAP, TRAP_HWBKPT,
-			"breakpoint debug exception");
+	hook_fault_code(FAULT_CODE_DEBUG, hw_breakpoint_pending, SIGTRAP,
+			TRAP_HWBKPT, "watchpoint debug exception");
+	hook_ifault_code(FAULT_CODE_DEBUG, hw_breakpoint_pending, SIGTRAP,
+			TRAP_HWBKPT, "breakpoint debug exception");
 
 	/* Register hotplug notifier. */
 	register_cpu_notifier(&dbg_reset_nb);
diff --git a/arch/arm/kernel/kprobes-arm.c b/arch/arm/kernel/kprobes-arm.c
index 79203ee1d03..9fe8910308a 100644
--- a/arch/arm/kernel/kprobes-arm.c
+++ b/arch/arm/kernel/kprobes-arm.c
@@ -60,6 +60,7 @@
 
 #include <linux/kernel.h>
 #include <linux/kprobes.h>
+#include <linux/module.h>
 
 #include "kprobes.h"
 
@@ -971,6 +972,9 @@ const union decode_item kprobe_decode_arm_table[] = {
 
 	DECODE_END
 };
+#ifdef CONFIG_ARM_KPROBES_TEST_MODULE
+EXPORT_SYMBOL_GPL(kprobe_decode_arm_table);
+#endif
 
 static void __kprobes arm_singlestep(struct kprobe *p, struct pt_regs *regs)
 {
diff --git a/arch/arm/kernel/kprobes-test-arm.c b/arch/arm/kernel/kprobes-test-arm.c
new file mode 100644
index 00000000000..20837823e92
--- /dev/null
+++ b/arch/arm/kernel/kprobes-test-arm.c
@@ -0,0 +1,1327 @@
+/*
+ * arch/arm/kernel/kprobes-test-arm.c
+ *
+ * Copyright (C) 2011 Jon Medhurst <tixy@yxit.co.uk>.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include "kprobes-test.h"
+
+
+#define TEST_ISA "32"
+
+#define TEST_ARM_TO_THUMB_INTERWORK_R(code1, reg, val, code2)	\
+	TESTCASE_START(code1 #reg code2)			\
+	TEST_ARG_REG(reg, val)					\
+	TEST_ARG_REG(14, 99f)					\
+	TEST_ARG_END("")					\
+	"50:	nop			\n\t"			\
+	"1:	"code1 #reg code2"	\n\t"			\
+	"	bx	lr		\n\t"			\
+	".thumb				\n\t"			\
+	"3:	adr	lr, 2f		\n\t"			\
+	"	bx	lr		\n\t"			\
+	".arm				\n\t"			\
+	"2:	nop			\n\t"			\
+	TESTCASE_END
+
+#define TEST_ARM_TO_THUMB_INTERWORK_P(code1, reg, val, code2)	\
+	TESTCASE_START(code1 #reg code2)			\
+	TEST_ARG_PTR(reg, val)					\
+	TEST_ARG_REG(14, 99f)					\
+	TEST_ARG_MEM(15, 3f+1)					\
+	TEST_ARG_END("")					\
+	"50:	nop			\n\t"			\
+	"1:	"code1 #reg code2"	\n\t"			\
+	"	bx	lr		\n\t"			\
+	".thumb				\n\t"			\
+	"3:	adr	lr, 2f		\n\t"			\
+	"	bx	lr		\n\t"			\
+	".arm				\n\t"			\
+	"2:	nop			\n\t"			\
+	TESTCASE_END
+
+
+void kprobe_arm_test_cases(void)
+{
+	kprobe_test_flags = 0;
+
+	TEST_GROUP("Data-processing (register), (register-shifted register), (immediate)")
+
+#define _DATA_PROCESSING_DNM(op,s,val)						\
+	TEST_RR(  op "eq" s "	r0,  r",1, VAL1,", r",2, val, "")		\
+	TEST_RR(  op "ne" s "	r1,  r",1, VAL1,", r",2, val, ", lsl #3")	\
+	TEST_RR(  op "cs" s "	r2,  r",3, VAL1,", r",2, val, ", lsr #4")	\
+	TEST_RR(  op "cc" s "	r3,  r",3, VAL1,", r",2, val, ", asr #5")	\
+	TEST_RR(  op "mi" s "	r4,  r",5, VAL1,", r",2, N(val),", asr #6")	\
+	TEST_RR(  op "pl" s "	r5,  r",5, VAL1,", r",2, val, ", ror #7")	\
+	TEST_RR(  op "vs" s "	r6,  r",7, VAL1,", r",2, val, ", rrx")		\
+	TEST_R(   op "vc" s "	r6,  r",7, VAL1,", pc, lsl #3")			\
+	TEST_R(   op "vc" s "	r6,  r",7, VAL1,", sp, lsr #4")			\
+	TEST_R(   op "vc" s "	r6,  pc, r",7, VAL1,", asr #5")			\
+	TEST_R(   op "vc" s "	r6,  sp, r",7, VAL1,", ror #6")			\
+	TEST_RRR( op "hi" s "	r8,  r",9, VAL1,", r",14,val, ", lsl r",0, 3,"")\
+	TEST_RRR( op "ls" s "	r9,  r",9, VAL1,", r",14,val, ", lsr r",7, 4,"")\
+	TEST_RRR( op "ge" s "	r10, r",11,VAL1,", r",14,val, ", asr r",7, 5,"")\
+	TEST_RRR( op "lt" s "	r11, r",11,VAL1,", r",14,N(val),", asr r",7, 6,"")\
+	TEST_RR(  op "gt" s "	r12, r13"       ", r",14,val, ", ror r",14,7,"")\
+	TEST_RR(  op "le" s "	r14, r",0, val, ", r13"       ", lsl r",14,8,"")\
+	TEST_RR(  op s "	r12, pc"        ", r",14,val, ", ror r",14,7,"")\
+	TEST_RR(  op s "	r14, r",0, val, ", pc"        ", lsl r",14,8,"")\
+	TEST_R(   op "eq" s "	r0,  r",11,VAL1,", #0xf5")			\
+	TEST_R(   op "ne" s "	r11, r",0, VAL1,", #0xf5000000")		\
+	TEST_R(   op s "	r7,  r",8, VAL2,", #0x000af000")		\
+	TEST(     op s "	r4,  pc"        ", #0x00005a00")
+
+#define DATA_PROCESSING_DNM(op,val)		\
+	_DATA_PROCESSING_DNM(op,"",val)		\
+	_DATA_PROCESSING_DNM(op,"s",val)
+
+#define DATA_PROCESSING_NM(op,val)						\
+	TEST_RR(  op "ne	r",1, VAL1,", r",2, val, "")			\
+	TEST_RR(  op "eq	r",1, VAL1,", r",2, val, ", lsl #3")		\
+	TEST_RR(  op "cc	r",3, VAL1,", r",2, val, ", lsr #4")		\
+	TEST_RR(  op "cs	r",3, VAL1,", r",2, val, ", asr #5")		\
+	TEST_RR(  op "pl	r",5, VAL1,", r",2, N(val),", asr #6")		\
+	TEST_RR(  op "mi	r",5, VAL1,", r",2, val, ", ror #7")		\
+	TEST_RR(  op "vc	r",7, VAL1,", r",2, val, ", rrx")		\
+	TEST_R (  op "vs	r",7, VAL1,", pc, lsl #3")			\
+	TEST_R (  op "vs	r",7, VAL1,", sp, lsr #4")			\
+	TEST_R(   op "vs	pc, r",7, VAL1,", asr #5")			\
+	TEST_R(   op "vs	sp, r",7, VAL1,", ror #6")			\
+	TEST_RRR( op "ls	r",9, VAL1,", r",14,val, ", lsl r",0, 3,"")	\
+	TEST_RRR( op "hi	r",9, VAL1,", r",14,val, ", lsr r",7, 4,"")	\
+	TEST_RRR( op "lt	r",11,VAL1,", r",14,val, ", asr r",7, 5,"")	\
+	TEST_RRR( op "ge	r",11,VAL1,", r",14,N(val),", asr r",7, 6,"")	\
+	TEST_RR(  op "le	r13"       ", r",14,val, ", ror r",14,7,"")	\
+	TEST_RR(  op "gt	r",0, val, ", r13"       ", lsl r",14,8,"")	\
+	TEST_RR(  op "	pc"        ", r",14,val, ", ror r",14,7,"")		\
+	TEST_RR(  op "	r",0, val, ", pc"        ", lsl r",14,8,"")		\
+	TEST_R(   op "eq	r",11,VAL1,", #0xf5")				\
+	TEST_R(   op "ne	r",0, VAL1,", #0xf5000000")			\
+	TEST_R(   op "	r",8, VAL2,", #0x000af000")
+
+#define _DATA_PROCESSING_DM(op,s,val)					\
+	TEST_R(   op "eq" s "	r0,  r",1, val, "")			\
+	TEST_R(   op "ne" s "	r1,  r",1, val, ", lsl #3")		\
+	TEST_R(   op "cs" s "	r2,  r",3, val, ", lsr #4")		\
+	TEST_R(   op "cc" s "	r3,  r",3, val, ", asr #5")		\
+	TEST_R(   op "mi" s "	r4,  r",5, N(val),", asr #6")		\
+	TEST_R(   op "pl" s "	r5,  r",5, val, ", ror #7")		\
+	TEST_R(   op "vs" s "	r6,  r",10,val, ", rrx")		\
+	TEST(     op "vs" s "	r7,  pc, lsl #3")			\
+	TEST(     op "vs" s "	r7,  sp, lsr #4")			\
+	TEST_RR(  op "vc" s "	r8,  r",7, val, ", lsl r",0, 3,"")	\
+	TEST_RR(  op "hi" s "	r9,  r",9, val, ", lsr r",7, 4,"")	\
+	TEST_RR(  op "ls" s "	r10, r",9, val, ", asr r",7, 5,"")	\
+	TEST_RR(  op "ge" s "	r11, r",11,N(val),", asr r",7, 6,"")	\
+	TEST_RR(  op "lt" s "	r12, r",11,val, ", ror r",14,7,"")	\
+	TEST_R(   op "gt" s "	r14, r13"       ", lsl r",14,8,"")	\
+	TEST_R(   op "le" s "	r14, pc"        ", lsl r",14,8,"")	\
+	TEST(     op "eq" s "	r0,  #0xf5")				\
+	TEST(     op "ne" s "	r11, #0xf5000000")			\
+	TEST(     op s "	r7,  #0x000af000")			\
+	TEST(     op s "	r4,  #0x00005a00")
+
+#define DATA_PROCESSING_DM(op,val)		\
+	_DATA_PROCESSING_DM(op,"",val)		\
+	_DATA_PROCESSING_DM(op,"s",val)
+
+	DATA_PROCESSING_DNM("and",0xf00f00ff)
+	DATA_PROCESSING_DNM("eor",0xf00f00ff)
+	DATA_PROCESSING_DNM("sub",VAL2)
+	DATA_PROCESSING_DNM("rsb",VAL2)
+	DATA_PROCESSING_DNM("add",VAL2)
+	DATA_PROCESSING_DNM("adc",VAL2)
+	DATA_PROCESSING_DNM("sbc",VAL2)
+	DATA_PROCESSING_DNM("rsc",VAL2)
+	DATA_PROCESSING_NM("tst",0xf00f00ff)
+	DATA_PROCESSING_NM("teq",0xf00f00ff)
+	DATA_PROCESSING_NM("cmp",VAL2)
+	DATA_PROCESSING_NM("cmn",VAL2)
+	DATA_PROCESSING_DNM("orr",0xf00f00ff)
+	DATA_PROCESSING_DM("mov",VAL2)
+	DATA_PROCESSING_DNM("bic",0xf00f00ff)
+	DATA_PROCESSING_DM("mvn",VAL2)
+
+	TEST("mov	ip, sp") /* This has special case emulation code */
+
+	TEST_SUPPORTED("mov	pc, #0x1000");
+	TEST_SUPPORTED("mov	sp, #0x1000");
+	TEST_SUPPORTED("cmp	pc, #0x1000");
+	TEST_SUPPORTED("cmp	sp, #0x1000");
+
+	/* Data-processing with PC as shift*/
+	TEST_UNSUPPORTED(".word 0xe15c0f1e	@ cmp	r12, r14, asl pc")
+	TEST_UNSUPPORTED(".word 0xe1a0cf1e	@ mov	r12, r14, asl pc")
+	TEST_UNSUPPORTED(".word 0xe08caf1e	@ add	r10, r12, r14, asl pc")
+
+	/* Data-processing with PC as shift*/
+	TEST_UNSUPPORTED("movs	pc, r1")
+	TEST_UNSUPPORTED("movs	pc, r1, lsl r2")
+	TEST_UNSUPPORTED("movs	pc, #0x10000")
+	TEST_UNSUPPORTED("adds	pc, lr, r1")
+	TEST_UNSUPPORTED("adds	pc, lr, r1, lsl r2")
+	TEST_UNSUPPORTED("adds	pc, lr, #4")
+
+	/* Data-processing with SP as target */
+	TEST("add	sp, sp, #16")
+	TEST("sub	sp, sp, #8")
+	TEST("bic	sp, sp, #0x20")
+	TEST("orr	sp, sp, #0x20")
+	TEST_PR( "add	sp, r",10,0,", r",11,4,"")
+	TEST_PRR("add	sp, r",10,0,", r",11,4,", asl r",12,1,"")
+	TEST_P(  "mov	sp, r",10,0,"")
+	TEST_PR( "mov	sp, r",10,0,", asl r",12,0,"")
+
+	/* Data-processing with PC as target */
+	TEST_BF(   "add	pc, pc, #2f-1b-8")
+	TEST_BF_R ("add	pc, pc, r",14,2f-1f-8,"")
+	TEST_BF_R ("add	pc, r",14,2f-1f-8,", pc")
+	TEST_BF_R ("mov	pc, r",0,2f,"")
+	TEST_BF_RR("mov	pc, r",0,2f,", asl r",1,0,"")
+	TEST_BB(   "sub	pc, pc, #1b-2b+8")
+#if __LINUX_ARM_ARCH__ >= 6
+	TEST_BB(   "sub	pc, pc, #1b-2b+8-2") /* UNPREDICTABLE before ARMv6 */
+#endif
+	TEST_BB_R( "sub	pc, pc, r",14, 1f-2f+8,"")
+	TEST_BB_R( "rsb	pc, r",14,1f-2f+8,", pc")
+	TEST_RR(   "add	pc, pc, r",10,-2,", asl r",11,1,"")
+#ifdef CONFIG_THUMB2_KERNEL
+	TEST_ARM_TO_THUMB_INTERWORK_R("add	pc, pc, r",0,3f-1f-8+1,"")
+	TEST_ARM_TO_THUMB_INTERWORK_R("sub	pc, r",0,3f+8+1,", #8")
+#endif
+	TEST_GROUP("Miscellaneous instructions")
+
+	TEST("mrs	r0, cpsr")
+	TEST("mrspl	r7, cpsr")
+	TEST("mrs	r14, cpsr")
+	TEST_UNSUPPORTED(".word 0xe10ff000	@ mrs r15, cpsr")
+	TEST_UNSUPPORTED("mrs	r0, spsr")
+	TEST_UNSUPPORTED("mrs	lr, spsr")
+
+	TEST_UNSUPPORTED("msr	cpsr, r0")
+	TEST_UNSUPPORTED("msr	cpsr_f, lr")
+	TEST_UNSUPPORTED("msr	spsr, r0")
+
+	TEST_BF_R("bx	r",0,2f,"")
+	TEST_BB_R("bx	r",7,2f,"")
+	TEST_BF_R("bxeq	r",14,2f,"")
+
+	TEST_R("clz	r0, r",0, 0x0,"")
+	TEST_R("clzeq	r7, r",14,0x1,"")
+	TEST_R("clz	lr, r",7, 0xffffffff,"")
+	TEST(  "clz	r4, sp")
+	TEST_UNSUPPORTED(".word 0x016fff10	@ clz pc, r0")
+	TEST_UNSUPPORTED(".word 0x016f0f1f	@ clz r0, pc")
+
+#if __LINUX_ARM_ARCH__ >= 6
+	TEST_UNSUPPORTED("bxj	r0")
+#endif
+
+	TEST_BF_R("blx	r",0,2f,"")
+	TEST_BB_R("blx	r",7,2f,"")
+	TEST_BF_R("blxeq	r",14,2f,"")
+	TEST_UNSUPPORTED(".word 0x0120003f	@ blx pc")
+
+	TEST_RR(   "qadd	r0, r",1, VAL1,", r",2, VAL2,"")
+	TEST_RR(   "qaddvs	lr, r",9, VAL2,", r",8, VAL1,"")
+	TEST_R(    "qadd	lr, r",9, VAL2,", r13")
+	TEST_RR(   "qsub	r0, r",1, VAL1,", r",2, VAL2,"")
+	TEST_RR(   "qsubvs	lr, r",9, VAL2,", r",8, VAL1,"")
+	TEST_R(    "qsub	lr, r",9, VAL2,", r13")
+	TEST_RR(   "qdadd	r0, r",1, VAL1,", r",2, VAL2,"")
+	TEST_RR(   "qdaddvs	lr, r",9, VAL2,", r",8, VAL1,"")
+	TEST_R(    "qdadd	lr, r",9, VAL2,", r13")
+	TEST_RR(   "qdsub	r0, r",1, VAL1,", r",2, VAL2,"")
+	TEST_RR(   "qdsubvs	lr, r",9, VAL2,", r",8, VAL1,"")
+	TEST_R(    "qdsub	lr, r",9, VAL2,", r13")
+	TEST_UNSUPPORTED(".word 0xe101f050	@ qadd pc, r0, r1")
+	TEST_UNSUPPORTED(".word 0xe121f050	@ qsub pc, r0, r1")
+	TEST_UNSUPPORTED(".word 0xe141f050	@ qdadd pc, r0, r1")
+	TEST_UNSUPPORTED(".word 0xe161f050	@ qdsub pc, r0, r1")
+	TEST_UNSUPPORTED(".word 0xe16f2050	@ qdsub r2, r0, pc")
+	TEST_UNSUPPORTED(".word 0xe161205f	@ qdsub r2, pc, r1")
+
+	TEST_UNSUPPORTED("bkpt	0xffff")
+	TEST_UNSUPPORTED("bkpt	0x0000")
+
+	TEST_UNSUPPORTED(".word 0xe1600070 @ smc #0")
+
+	TEST_GROUP("Halfword multiply and multiply-accumulate")
+
+	TEST_RRR(    "smlabb	r0, r",1, VAL1,", r",2, VAL2,", r",3,  VAL3,"")
+	TEST_RRR(    "smlabbge	r7, r",8, VAL3,", r",9, VAL1,", r",10, VAL2,"")
+	TEST_RR(     "smlabb	lr, r",1, VAL2,", r",2, VAL3,", r13")
+	TEST_UNSUPPORTED(".word 0xe10f3281 @ smlabb pc, r1, r2, r3")
+	TEST_RRR(    "smlatb	r0, r",1, VAL1,", r",2, VAL2,", r",3,  VAL3,"")
+	TEST_RRR(    "smlatbge	r7, r",8, VAL3,", r",9, VAL1,", r",10, VAL2,"")
+	TEST_RR(     "smlatb	lr, r",1, VAL2,", r",2, VAL3,", r13")
+	TEST_UNSUPPORTED(".word 0xe10f32a1 @ smlatb pc, r1, r2, r3")
+	TEST_RRR(    "smlabt	r0, r",1, VAL1,", r",2, VAL2,", r",3,  VAL3,"")
+	TEST_RRR(    "smlabtge	r7, r",8, VAL3,", r",9, VAL1,", r",10, VAL2,"")
+	TEST_RR(     "smlabt	lr, r",1, VAL2,", r",2, VAL3,", r13")
+	TEST_UNSUPPORTED(".word 0xe10f32c1 @ smlabt pc, r1, r2, r3")
+	TEST_RRR(    "smlatt	r0, r",1, VAL1,", r",2, VAL2,", r",3,  VAL3,"")
+	TEST_RRR(    "smlattge	r7, r",8, VAL3,", r",9, VAL1,", r",10, VAL2,"")
+	TEST_RR(     "smlatt	lr, r",1, VAL2,", r",2, VAL3,", r13")
+	TEST_UNSUPPORTED(".word 0xe10f32e1 @ smlatt pc, r1, r2, r3")
+
+	TEST_RRR(    "smlawb	r0, r",1, VAL1,", r",2, VAL2,", r",3,  VAL3,"")
+	TEST_RRR(    "smlawbge	r7, r",8, VAL3,", r",9, VAL1,", r",10, VAL2,"")
+	TEST_RR(     "smlawb	lr, r",1, VAL2,", r",2, VAL3,", r13")
+	TEST_UNSUPPORTED(".word 0xe12f3281 @ smlawb pc, r1, r2, r3")
+	TEST_RRR(    "smlawt	r0, r",1, VAL1,", r",2, VAL2,", r",3,  VAL3,"")
+	TEST_RRR(    "smlawtge	r7, r",8, VAL3,", r",9, VAL1,", r",10, VAL2,"")
+	TEST_RR(     "smlawt	lr, r",1, VAL2,", r",2, VAL3,", r13")
+	TEST_UNSUPPORTED(".word 0xe12f32c1 @ smlawt pc, r1, r2, r3")
+	TEST_UNSUPPORTED(".word 0xe12032cf @ smlawt r0, pc, r2, r3")
+	TEST_UNSUPPORTED(".word 0xe1203fc1 @ smlawt r0, r1, pc, r3")
+	TEST_UNSUPPORTED(".word 0xe120f2c1 @ smlawt r0, r1, r2, pc")
+
+	TEST_RR(    "smulwb	r0, r",1, VAL1,", r",2, VAL2,"")
+	TEST_RR(    "smulwbge	r7, r",8, VAL3,", r",9, VAL1,"")
+	TEST_R(     "smulwb	lr, r",1, VAL2,", r13")
+	TEST_UNSUPPORTED(".word 0xe12f02a1 @ smulwb pc, r1, r2")
+	TEST_RR(    "smulwt	r0, r",1, VAL1,", r",2, VAL2,"")
+	TEST_RR(    "smulwtge	r7, r",8, VAL3,", r",9, VAL1,"")
+	TEST_R(     "smulwt	lr, r",1, VAL2,", r13")
+	TEST_UNSUPPORTED(".word 0xe12f02e1 @ smulwt pc, r1, r2")
+
+	TEST_RRRR(  "smlalbb	r",0, VAL1,", r",1, VAL2,", r",2, VAL3,", r",3, VAL4)
+	TEST_RRRR(  "smlalbble	r",8, VAL4,", r",9, VAL1,", r",10,VAL2,", r",11,VAL3)
+	TEST_RRR(   "smlalbb	r",14,VAL3,", r",7, VAL4,", r",5, VAL1,", r13")
+	TEST_UNSUPPORTED(".word 0xe14f1382 @ smlalbb pc, r1, r2, r3")
+	TEST_UNSUPPORTED(".word 0xe141f382 @ smlalbb r1, pc, r2, r3")
+	TEST_RRRR(  "smlaltb	r",0, VAL1,", r",1, VAL2,", r",2, VAL3,", r",3, VAL4)
+	TEST_RRRR(  "smlaltble	r",8, VAL4,", r",9, VAL1,", r",10,VAL2,", r",11,VAL3)
+	TEST_RRR(   "smlaltb	r",14,VAL3,", r",7, VAL4,", r",5, VAL1,", r13")
+	TEST_UNSUPPORTED(".word 0xe14f13a2 @ smlaltb pc, r1, r2, r3")
+	TEST_UNSUPPORTED(".word 0xe141f3a2 @ smlaltb r1, pc, r2, r3")
+	TEST_RRRR(  "smlalbt	r",0, VAL1,", r",1, VAL2,", r",2, VAL3,", r",3, VAL4)
+	TEST_RRRR(  "smlalbtle	r",8, VAL4,", r",9, VAL1,", r",10,VAL2,", r",11,VAL3)
+	TEST_RRR(   "smlalbt	r",14,VAL3,", r",7, VAL4,", r",5, VAL1,", r13")
+	TEST_UNSUPPORTED(".word 0xe14f13c2 @ smlalbt pc, r1, r2, r3")
+	TEST_UNSUPPORTED(".word 0xe141f3c2 @ smlalbt r1, pc, r2, r3")
+	TEST_RRRR(  "smlaltt	r",0, VAL1,", r",1, VAL2,", r",2, VAL3,", r",3, VAL4)
+	TEST_RRRR(  "smlalttle	r",8, VAL4,", r",9, VAL1,", r",10,VAL2,", r",11,VAL3)
+	TEST_RRR(   "smlaltt	r",14,VAL3,", r",7, VAL4,", r",5, VAL1,", r13")
+	TEST_UNSUPPORTED(".word 0xe14f13e2 @ smlalbb pc, r1, r2, r3")
+	TEST_UNSUPPORTED(".word 0xe140f3e2 @ smlalbb r0, pc, r2, r3")
+	TEST_UNSUPPORTED(".word 0xe14013ef @ smlalbb r0, r1, pc, r3")
+	TEST_UNSUPPORTED(".word 0xe1401fe2 @ smlalbb r0, r1, r2, pc")
+
+	TEST_RR(    "smulbb	r0, r",1, VAL1,", r",2, VAL2,"")
+	TEST_RR(    "smulbbge	r7, r",8, VAL3,", r",9, VAL1,"")
+	TEST_R(     "smulbb	lr, r",1, VAL2,", r13")
+	TEST_UNSUPPORTED(".word 0xe16f0281 @ smulbb pc, r1, r2")
+	TEST_RR(    "smultb	r0, r",1, VAL1,", r",2, VAL2,"")
+	TEST_RR(    "smultbge	r7, r",8, VAL3,", r",9, VAL1,"")
+	TEST_R(     "smultb	lr, r",1, VAL2,", r13")
+	TEST_UNSUPPORTED(".word 0xe16f02a1 @ smultb pc, r1, r2")
+	TEST_RR(    "smulbt	r0, r",1, VAL1,", r",2, VAL2,"")
+	TEST_RR(    "smulbtge	r7, r",8, VAL3,", r",9, VAL1,"")
+	TEST_R(     "smulbt	lr, r",1, VAL2,", r13")
+	TEST_UNSUPPORTED(".word 0xe16f02c1 @ smultb pc, r1, r2")
+	TEST_RR(    "smultt	r0, r",1, VAL1,", r",2, VAL2,"")
+	TEST_RR(    "smulttge	r7, r",8, VAL3,", r",9, VAL1,"")
+	TEST_R(     "smultt	lr, r",1, VAL2,", r13")
+	TEST_UNSUPPORTED(".word 0xe16f02e1 @ smultt pc, r1, r2")
+	TEST_UNSUPPORTED(".word 0xe16002ef @ smultt r0, pc, r2")
+	TEST_UNSUPPORTED(".word 0xe1600fe1 @ smultt r0, r1, pc")
+
+	TEST_GROUP("Multiply and multiply-accumulate")
+
+	TEST_RR(    "mul	r0, r",1, VAL1,", r",2, VAL2,"")
+	TEST_RR(    "mulls	r7, r",8, VAL2,", r",9, VAL2,"")
+	TEST_R(     "mul	lr, r",4, VAL3,", r13")
+	TEST_UNSUPPORTED(".word 0xe00f0291 @ mul pc, r1, r2")
+	TEST_UNSUPPORTED(".word 0xe000029f @ mul r0, pc, r2")
+	TEST_UNSUPPORTED(".word 0xe0000f91 @ mul r0, r1, pc")
+	TEST_RR(    "muls	r0, r",1, VAL1,", r",2, VAL2,"")
+	TEST_RR(    "mullss	r7, r",8, VAL2,", r",9, VAL2,"")
+	TEST_R(     "muls	lr, r",4, VAL3,", r13")
+	TEST_UNSUPPORTED(".word 0xe01f0291 @ muls pc, r1, r2")
+
+	TEST_RRR(    "mla	r0, r",1, VAL1,", r",2, VAL2,", r",3,  VAL3,"")
+	TEST_RRR(    "mlahi	r7, r",8, VAL3,", r",9, VAL1,", r",10, VAL2,"")
+	TEST_RR(     "mla	lr, r",1, VAL2,", r",2, VAL3,", r13")
+	TEST_UNSUPPORTED(".word 0xe02f3291 @ mla pc, r1, r2, r3")
+	TEST_RRR(    "mlas	r0, r",1, VAL1,", r",2, VAL2,", r",3,  VAL3,"")
+	TEST_RRR(    "mlahis	r7, r",8, VAL3,", r",9, VAL1,", r",10, VAL2,"")
+	TEST_RR(     "mlas	lr, r",1, VAL2,", r",2, VAL3,", r13")
+	TEST_UNSUPPORTED(".word 0xe03f3291 @ mlas pc, r1, r2, r3")
+
+#if __LINUX_ARM_ARCH__ >= 6
+	TEST_RR(  "umaal	r0, r1, r",2, VAL1,", r",3, VAL2,"")
+	TEST_RR(  "umaalls	r7, r8, r",9, VAL2,", r",10, VAL1,"")
+	TEST_R(   "umaal	lr, r12, r",11,VAL3,", r13")
+	TEST_UNSUPPORTED(".word 0xe041f392 @ umaal pc, r1, r2, r3")
+	TEST_UNSUPPORTED(".word 0xe04f0392 @ umaal r0, pc, r2, r3")
+	TEST_UNSUPPORTED(".word 0xe0500090 @ undef")
+	TEST_UNSUPPORTED(".word 0xe05fff9f @ undef")
+
+#if __LINUX_ARM_ARCH__ >= 7
+	TEST_RRR(  "mls		r0, r",1, VAL1,", r",2, VAL2,", r",3,  VAL3,"")
+	TEST_RRR(  "mlshi	r7, r",8, VAL3,", r",9, VAL1,", r",10, VAL2,"")
+	TEST_RR(   "mls		lr, r",1, VAL2,", r",2, VAL3,", r13")
+#endif
+	TEST_UNSUPPORTED(".word 0xe06f3291 @ mls pc, r1, r2, r3")
+	TEST_UNSUPPORTED(".word 0xe060329f @ mls r0, pc, r2, r3")
+	TEST_UNSUPPORTED(".word 0xe0603f91 @ mls r0, r1, pc, r3")
+	TEST_UNSUPPORTED(".word 0xe060f291 @ mls r0, r1, r2, pc")
+#endif
+
+	TEST_UNSUPPORTED(".word 0xe0700090 @ undef")
+	TEST_UNSUPPORTED(".word 0xe07fff9f @ undef")
+
+	TEST_RR(  "umull	r0, r1, r",2, VAL1,", r",3, VAL2,"")
+	TEST_RR(  "umullls	r7, r8, r",9, VAL2,", r",10, VAL1,"")
+	TEST_R(   "umull	lr, r12, r",11,VAL3,", r13")
+	TEST_UNSUPPORTED(".word 0xe081f392 @ umull pc, r1, r2, r3")
+	TEST_UNSUPPORTED(".word 0xe08f1392 @ umull r1, pc, r2, r3")
+	TEST_RR(  "umulls	r0, r1, r",2, VAL1,", r",3, VAL2,"")
+	TEST_RR(  "umulllss	r7, r8, r",9, VAL2,", r",10, VAL1,"")
+	TEST_R(   "umulls	lr, r12, r",11,VAL3,", r13")
+	TEST_UNSUPPORTED(".word 0xe091f392 @ umulls pc, r1, r2, r3")
+	TEST_UNSUPPORTED(".word 0xe09f1392 @ umulls r1, pc, r2, r3")
+
+	TEST_RRRR(  "umlal	r",0, VAL1,", r",1, VAL2,", r",2, VAL3,", r",3, VAL4)
+	TEST_RRRR(  "umlalle	r",8, VAL4,", r",9, VAL1,", r",10,VAL2,", r",11,VAL3)
+	TEST_RRR(   "umlal	r",14,VAL3,", r",7, VAL4,", r",5, VAL1,", r13")
+	TEST_UNSUPPORTED(".word 0xe0af1392 @ umlal pc, r1, r2, r3")
+	TEST_UNSUPPORTED(".word 0xe0a1f392 @ umlal r1, pc, r2, r3")
+	TEST_RRRR(  "umlals	r",0, VAL1,", r",1, VAL2,", r",2, VAL3,", r",3, VAL4)
+	TEST_RRRR(  "umlalles	r",8, VAL4,", r",9, VAL1,", r",10,VAL2,", r",11,VAL3)
+	TEST_RRR(   "umlals	r",14,VAL3,", r",7, VAL4,", r",5, VAL1,", r13")
+	TEST_UNSUPPORTED(".word 0xe0bf1392 @ umlals pc, r1, r2, r3")
+	TEST_UNSUPPORTED(".word 0xe0b1f392 @ umlals r1, pc, r2, r3")
+
+	TEST_RR(  "smull	r0, r1, r",2, VAL1,", r",3, VAL2,"")
+	TEST_RR(  "smullls	r7, r8, r",9, VAL2,", r",10, VAL1,"")
+	TEST_R(   "smull	lr, r12, r",11,VAL3,", r13")
+	TEST_UNSUPPORTED(".word 0xe0c1f392 @ smull pc, r1, r2, r3")
+	TEST_UNSUPPORTED(".word 0xe0cf1392 @ smull r1, pc, r2, r3")
+	TEST_RR(  "smulls	r0, r1, r",2, VAL1,", r",3, VAL2,"")
+	TEST_RR(  "smulllss	r7, r8, r",9, VAL2,", r",10, VAL1,"")
+	TEST_R(   "smulls	lr, r12, r",11,VAL3,", r13")
+	TEST_UNSUPPORTED(".word 0xe0d1f392 @ smulls pc, r1, r2, r3")
+	TEST_UNSUPPORTED(".word 0xe0df1392 @ smulls r1, pc, r2, r3")
+
+	TEST_RRRR(  "smlal	r",0, VAL1,", r",1, VAL2,", r",2, VAL3,", r",3, VAL4)
+	TEST_RRRR(  "smlalle	r",8, VAL4,", r",9, VAL1,", r",10,VAL2,", r",11,VAL3)
+	TEST_RRR(   "smlal	r",14,VAL3,", r",7, VAL4,", r",5, VAL1,", r13")
+	TEST_UNSUPPORTED(".word 0xe0ef1392 @ smlal pc, r1, r2, r3")
+	TEST_UNSUPPORTED(".word 0xe0e1f392 @ smlal r1, pc, r2, r3")
+	TEST_RRRR(  "smlals	r",0, VAL1,", r",1, VAL2,", r",2, VAL3,", r",3, VAL4)
+	TEST_RRRR(  "smlalles	r",8, VAL4,", r",9, VAL1,", r",10,VAL2,", r",11,VAL3)
+	TEST_RRR(   "smlals	r",14,VAL3,", r",7, VAL4,", r",5, VAL1,", r13")
+	TEST_UNSUPPORTED(".word 0xe0ff1392 @ smlals pc, r1, r2, r3")
+	TEST_UNSUPPORTED(".word 0xe0f0f392 @ smlals r0, pc, r2, r3")
+	TEST_UNSUPPORTED(".word 0xe0f0139f @ smlals r0, r1, pc, r3")
+	TEST_UNSUPPORTED(".word 0xe0f01f92 @ smlals r0, r1, r2, pc")
+
+	TEST_GROUP("Synchronization primitives")
+
+	/*
+	 * Use hard coded constants for SWP instructions to avoid warnings
+	 * about deprecated instructions.
+	 */
+	TEST_RP( ".word 0xe108e097 @ swp	lr, r",7,VAL2,", [r",8,0,"]")
+	TEST_R(  ".word 0x610d0091 @ swpvs	r0, r",1,VAL1,", [sp]")
+	TEST_RP( ".word 0xe10cd09e @ swp	sp, r",14,VAL2,", [r",12,13*4,"]")
+	TEST_UNSUPPORTED(".word 0xe102f091 @ swp pc, r1, [r2]")
+	TEST_UNSUPPORTED(".word 0xe102009f @ swp r0, pc, [r2]")
+	TEST_UNSUPPORTED(".word 0xe10f0091 @ swp r0, r1, [pc]")
+	TEST_RP( ".word 0xe148e097 @ swpb	lr, r",7,VAL2,", [r",8,0,"]")
+	TEST_R(  ".word 0x614d0091 @ swpvsb	r0, r",1,VAL1,", [sp]")
+	TEST_UNSUPPORTED(".word 0xe142f091 @ swpb pc, r1, [r2]")
+
+	TEST_UNSUPPORTED(".word	0xe1100090") /* Unallocated space */
+	TEST_UNSUPPORTED(".word	0xe1200090") /* Unallocated space */
+	TEST_UNSUPPORTED(".word	0xe1300090") /* Unallocated space */
+	TEST_UNSUPPORTED(".word	0xe1500090") /* Unallocated space */
+	TEST_UNSUPPORTED(".word	0xe1600090") /* Unallocated space */
+	TEST_UNSUPPORTED(".word	0xe1700090") /* Unallocated space */
+#if __LINUX_ARM_ARCH__ >= 6
+	TEST_UNSUPPORTED("ldrex	r2, [sp]")
+#endif
+#if __LINUX_ARM_ARCH__ >= 7
+	TEST_UNSUPPORTED("strexd	r0, r2, r3, [sp]")
+	TEST_UNSUPPORTED("ldrexd	r2, r3, [sp]")
+	TEST_UNSUPPORTED("strexb	r0, r2, [sp]")
+	TEST_UNSUPPORTED("ldrexb	r2, [sp]")
+	TEST_UNSUPPORTED("strexh	r0, r2, [sp]")
+	TEST_UNSUPPORTED("ldrexh	r2, [sp]")
+#endif
+	TEST_GROUP("Extra load/store instructions")
+
+	TEST_RPR(  "strh	r",0, VAL1,", [r",1, 48,", -r",2, 24,"]")
+	TEST_RPR(  "streqh	r",14,VAL2,", [r",13,0, ", r",12, 48,"]")
+	TEST_RPR(  "strh	r",1, VAL1,", [r",2, 24,", r",3,  48,"]!")
+	TEST_RPR(  "strneh	r",12,VAL2,", [r",11,48,", -r",10,24,"]!")
+	TEST_RPR(  "strh	r",2, VAL1,", [r",3, 24,"], r",4, 48,"")
+	TEST_RPR(  "strh	r",10,VAL2,", [r",9, 48,"], -r",11,24,"")
+	TEST_UNSUPPORTED(".word 0xe1afc0ba	@ strh r12, [pc, r10]!")
+	TEST_UNSUPPORTED(".word 0xe089f0bb	@ strh pc, [r9], r11")
+	TEST_UNSUPPORTED(".word 0xe089a0bf	@ strh r10, [r9], pc")
+
+	TEST_PR(   "ldrh	r0, [r",0,  48,", -r",2, 24,"]")
+	TEST_PR(   "ldrcsh	r14, [r",13,0, ", r",12, 48,"]")
+	TEST_PR(   "ldrh	r1, [r",2,  24,", r",3,  48,"]!")
+	TEST_PR(   "ldrcch	r12, [r",11,48,", -r",10,24,"]!")
+	TEST_PR(   "ldrh	r2, [r",3,  24,"], r",4, 48,"")
+	TEST_PR(   "ldrh	r10, [r",9, 48,"], -r",11,24,"")
+	TEST_UNSUPPORTED(".word 0xe1bfc0ba	@ ldrh r12, [pc, r10]!")
+	TEST_UNSUPPORTED(".word 0xe099f0bb	@ ldrh pc, [r9], r11")
+	TEST_UNSUPPORTED(".word 0xe099a0bf	@ ldrh r10, [r9], pc")
+
+	TEST_RP(   "strh	r",0, VAL1,", [r",1, 24,", #-2]")
+	TEST_RP(   "strmih	r",14,VAL2,", [r",13,0, ", #2]")
+	TEST_RP(   "strh	r",1, VAL1,", [r",2, 24,", #4]!")
+	TEST_RP(   "strplh	r",12,VAL2,", [r",11,24,", #-4]!")
+	TEST_RP(   "strh	r",2, VAL1,", [r",3, 24,"], #48")
+	TEST_RP(   "strh	r",10,VAL2,", [r",9, 64,"], #-48")
+	TEST_UNSUPPORTED(".word 0xe1efc3b0	@ strh r12, [pc, #48]!")
+	TEST_UNSUPPORTED(".word 0xe0c9f3b0	@ strh pc, [r9], #48")
+
+	TEST_P(	   "ldrh	r0, [r",0,  24,", #-2]")
+	TEST_P(	   "ldrvsh	r14, [r",13,0, ", #2]")
+	TEST_P(	   "ldrh	r1, [r",2,  24,", #4]!")
+	TEST_P(	   "ldrvch	r12, [r",11,24,", #-4]!")
+	TEST_P(	   "ldrh	r2, [r",3,  24,"], #48")
+	TEST_P(	   "ldrh	r10, [r",9, 64,"], #-48")
+	TEST(      "ldrh	r0, [pc, #0]")
+	TEST_UNSUPPORTED(".word 0xe1ffc3b0	@ ldrh r12, [pc, #48]!")
+	TEST_UNSUPPORTED(".word 0xe0d9f3b0	@ ldrh pc, [r9], #48")
+
+	TEST_PR(   "ldrsb	r0, [r",0,  48,", -r",2, 24,"]")
+	TEST_PR(   "ldrhisb	r14, [r",13,0,", r",12,  48,"]")
+	TEST_PR(   "ldrsb	r1, [r",2,  24,", r",3,  48,"]!")
+	TEST_PR(   "ldrlssb	r12, [r",11,48,", -r",10,24,"]!")
+	TEST_PR(   "ldrsb	r2, [r",3,  24,"], r",4, 48,"")
+	TEST_PR(   "ldrsb	r10, [r",9, 48,"], -r",11,24,"")
+	TEST_UNSUPPORTED(".word 0xe1bfc0da	@ ldrsb r12, [pc, r10]!")
+	TEST_UNSUPPORTED(".word 0xe099f0db	@ ldrsb pc, [r9], r11")
+
+	TEST_P(	   "ldrsb	r0, [r",0,  24,", #-1]")
+	TEST_P(	   "ldrgesb	r14, [r",13,0, ", #1]")
+	TEST_P(	   "ldrsb	r1, [r",2,  24,", #4]!")
+	TEST_P(	   "ldrltsb	r12, [r",11,24,", #-4]!")
+	TEST_P(	   "ldrsb	r2, [r",3,  24,"], #48")
+	TEST_P(	   "ldrsb	r10, [r",9, 64,"], #-48")
+	TEST(      "ldrsb	r0, [pc, #0]")
+	TEST_UNSUPPORTED(".word 0xe1ffc3d0	@ ldrsb r12, [pc, #48]!")
+	TEST_UNSUPPORTED(".word 0xe0d9f3d0	@ ldrsb pc, [r9], #48")
+
+	TEST_PR(   "ldrsh	r0, [r",0,  48,", -r",2, 24,"]")
+	TEST_PR(   "ldrgtsh	r14, [r",13,0, ", r",12, 48,"]")
+	TEST_PR(   "ldrsh	r1, [r",2,  24,", r",3,  48,"]!")
+	TEST_PR(   "ldrlesh	r12, [r",11,48,", -r",10,24,"]!")
+	TEST_PR(   "ldrsh	r2, [r",3,  24,"], r",4, 48,"")
+	TEST_PR(   "ldrsh	r10, [r",9, 48,"], -r",11,24,"")
+	TEST_UNSUPPORTED(".word 0xe1bfc0fa	@ ldrsh r12, [pc, r10]!")
+	TEST_UNSUPPORTED(".word 0xe099f0fb	@ ldrsh pc, [r9], r11")
+
+	TEST_P(	   "ldrsh	r0, [r",0,  24,", #-1]")
+	TEST_P(	   "ldreqsh	r14, [r",13,0 ,", #1]")
+	TEST_P(	   "ldrsh	r1, [r",2,  24,", #4]!")
+	TEST_P(	   "ldrnesh	r12, [r",11,24,", #-4]!")
+	TEST_P(	   "ldrsh	r2, [r",3,  24,"], #48")
+	TEST_P(	   "ldrsh	r10, [r",9, 64,"], #-48")
+	TEST(      "ldrsh	r0, [pc, #0]")
+	TEST_UNSUPPORTED(".word 0xe1ffc3f0	@ ldrsh r12, [pc, #48]!")
+	TEST_UNSUPPORTED(".word 0xe0d9f3f0	@ ldrsh pc, [r9], #48")
+
+#if __LINUX_ARM_ARCH__ >= 7
+	TEST_UNSUPPORTED("strht	r1, [r2], r3")
+	TEST_UNSUPPORTED("ldrht	r1, [r2], r3")
+	TEST_UNSUPPORTED("strht	r1, [r2], #48")
+	TEST_UNSUPPORTED("ldrht	r1, [r2], #48")
+	TEST_UNSUPPORTED("ldrsbt	r1, [r2], r3")
+	TEST_UNSUPPORTED("ldrsbt	r1, [r2], #48")
+	TEST_UNSUPPORTED("ldrsht	r1, [r2], r3")
+	TEST_UNSUPPORTED("ldrsht	r1, [r2], #48")
+#endif
+
+	TEST_RPR(  "strd	r",0, VAL1,", [r",1, 48,", -r",2,24,"]")
+	TEST_RPR(  "strccd	r",8, VAL2,", [r",13,0, ", r",12,48,"]")
+	TEST_RPR(  "strd	r",4, VAL1,", [r",2, 24,", r",3, 48,"]!")
+	TEST_RPR(  "strcsd	r",12,VAL2,", [r",11,48,", -r",10,24,"]!")
+	TEST_RPR(  "strd	r",2, VAL1,", [r",3, 24,"], r",4,48,"")
+	TEST_RPR(  "strd	r",10,VAL2,", [r",9, 48,"], -r",7,24,"")
+	TEST_UNSUPPORTED(".word 0xe1afc0fa	@ strd r12, [pc, r10]!")
+
+	TEST_PR(   "ldrd	r0, [r",0, 48,", -r",2,24,"]")
+	TEST_PR(   "ldrmid	r8, [r",13,0, ", r",12,48,"]")
+	TEST_PR(   "ldrd	r4, [r",2, 24,", r",3, 48,"]!")
+	TEST_PR(   "ldrpld	r6, [r",11,48,", -r",10,24,"]!")
+	TEST_PR(   "ldrd	r2, [r",5, 24,"], r",4,48,"")
+	TEST_PR(   "ldrd	r10, [r",9,48,"], -r",7,24,"")
+	TEST_UNSUPPORTED(".word 0xe1afc0da	@ ldrd r12, [pc, r10]!")
+	TEST_UNSUPPORTED(".word 0xe089f0db	@ ldrd pc, [r9], r11")
+	TEST_UNSUPPORTED(".word 0xe089e0db	@ ldrd lr, [r9], r11")
+	TEST_UNSUPPORTED(".word 0xe089c0df	@ ldrd r12, [r9], pc")
+
+	TEST_RP(   "strd	r",0, VAL1,", [r",1, 24,", #-8]")
+	TEST_RP(   "strvsd	r",8, VAL2,", [r",13,0, ", #8]")
+	TEST_RP(   "strd	r",4, VAL1,", [r",2, 24,", #16]!")
+	TEST_RP(   "strvcd	r",12,VAL2,", [r",11,24,", #-16]!")
+	TEST_RP(   "strd	r",2, VAL1,", [r",4, 24,"], #48")
+	TEST_RP(   "strd	r",10,VAL2,", [r",9, 64,"], #-48")
+	TEST_UNSUPPORTED(".word 0xe1efc3f0	@ strd r12, [pc, #48]!")
+
+	TEST_P(	   "ldrd	r0, [r",0, 24,", #-8]")
+	TEST_P(	   "ldrhid	r8, [r",13,0, ", #8]")
+	TEST_P(	   "ldrd	r4, [r",2, 24,", #16]!")
+	TEST_P(	   "ldrlsd	r6, [r",11,24,", #-16]!")
+	TEST_P(	   "ldrd	r2, [r",5, 24,"], #48")
+	TEST_P(	   "ldrd	r10, [r",9,6,"], #-48")
+	TEST_UNSUPPORTED(".word 0xe1efc3d0	@ ldrd r12, [pc, #48]!")
+	TEST_UNSUPPORTED(".word 0xe0c9f3d0	@ ldrd pc, [r9], #48")
+	TEST_UNSUPPORTED(".word 0xe0c9e3d0	@ ldrd lr, [r9], #48")
+
+	TEST_GROUP("Miscellaneous")
+
+#if __LINUX_ARM_ARCH__ >= 7
+	TEST("movw	r0, #0")
+	TEST("movw	r0, #0xffff")
+	TEST("movw	lr, #0xffff")
+	TEST_UNSUPPORTED(".word 0xe300f000	@ movw pc, #0")
+	TEST_R("movt	r",0, VAL1,", #0")
+	TEST_R("movt	r",0, VAL2,", #0xffff")
+	TEST_R("movt	r",14,VAL1,", #0xffff")
+	TEST_UNSUPPORTED(".word 0xe340f000	@ movt pc, #0")
+#endif
+
+	TEST_UNSUPPORTED("msr	cpsr, 0x13")
+	TEST_UNSUPPORTED("msr	cpsr_f, 0xf0000000")
+	TEST_UNSUPPORTED("msr	spsr, 0x13")
+
+#if __LINUX_ARM_ARCH__ >= 7
+	TEST_SUPPORTED("yield")
+	TEST("sev")
+	TEST("nop")
+	TEST("wfi")
+	TEST_SUPPORTED("wfe")
+	TEST_UNSUPPORTED("dbg #0")
+#endif
+
+	TEST_GROUP("Load/store word and unsigned byte")
+
+#define LOAD_STORE(byte)							\
+	TEST_RP( "str"byte"	r",0, VAL1,", [r",1, 24,", #-2]")		\
+	TEST_RP( "str"byte"	r",14,VAL2,", [r",13,0, ", #2]")		\
+	TEST_RP( "str"byte"	r",1, VAL1,", [r",2, 24,", #4]!")		\
+	TEST_RP( "str"byte"	r",12,VAL2,", [r",11,24,", #-4]!")		\
+	TEST_RP( "str"byte"	r",2, VAL1,", [r",3, 24,"], #48")		\
+	TEST_RP( "str"byte"	r",10,VAL2,", [r",9, 64,"], #-48")		\
+	TEST_RPR("str"byte"	r",0, VAL1,", [r",1, 48,", -r",2, 24,"]")	\
+	TEST_RPR("str"byte"	r",14,VAL2,", [r",13,0, ", r",12, 48,"]")	\
+	TEST_RPR("str"byte"	r",1, VAL1,", [r",2, 24,", r",3,  48,"]!")	\
+	TEST_RPR("str"byte"	r",12,VAL2,", [r",11,48,", -r",10,24,"]!")	\
+	TEST_RPR("str"byte"	r",2, VAL1,", [r",3, 24,"], r",4, 48,"")	\
+	TEST_RPR("str"byte"	r",10,VAL2,", [r",9, 48,"], -r",11,24,"")	\
+	TEST_RPR("str"byte"	r",0, VAL1,", [r",1, 24,", r",2,  32,", asl #1]")\
+	TEST_RPR("str"byte"	r",14,VAL2,", [r",13,0, ", r",12, 32,", lsr #2]")\
+	TEST_RPR("str"byte"	r",1, VAL1,", [r",2, 24,", r",3,  32,", asr #3]!")\
+	TEST_RPR("str"byte"	r",12,VAL2,", [r",11,24,", r",10, 4,", ror #31]!")\
+	TEST_P(  "ldr"byte"	r0, [r",0,  24,", #-2]")			\
+	TEST_P(  "ldr"byte"	r14, [r",13,0, ", #2]")				\
+	TEST_P(  "ldr"byte"	r1, [r",2,  24,", #4]!")			\
+	TEST_P(  "ldr"byte"	r12, [r",11,24,", #-4]!")			\
+	TEST_P(  "ldr"byte"	r2, [r",3,  24,"], #48")			\
+	TEST_P(  "ldr"byte"	r10, [r",9, 64,"], #-48")			\
+	TEST_PR( "ldr"byte"	r0, [r",0,  48,", -r",2, 24,"]")		\
+	TEST_PR( "ldr"byte"	r14, [r",13,0, ", r",12, 48,"]")		\
+	TEST_PR( "ldr"byte"	r1, [r",2,  24,", r",3, 48,"]!")		\
+	TEST_PR( "ldr"byte"	r12, [r",11,48,", -r",10,24,"]!")		\
+	TEST_PR( "ldr"byte"	r2, [r",3,  24,"], r",4, 48,"")			\
+	TEST_PR( "ldr"byte"	r10, [r",9, 48,"], -r",11,24,"")		\
+	TEST_PR( "ldr"byte"	r0, [r",0,  24,", r",2,  32,", asl #1]")	\
+	TEST_PR( "ldr"byte"	r14, [r",13,0, ", r",12, 32,", lsr #2]")	\
+	TEST_PR( "ldr"byte"	r1, [r",2,  24,", r",3,  32,", asr #3]!")	\
+	TEST_PR( "ldr"byte"	r12, [r",11,24,", r",10, 4,", ror #31]!")	\
+	TEST(    "ldr"byte"	r0, [pc, #0]")					\
+	TEST_R(  "ldr"byte"	r12, [pc, r",14,0,"]")
+
+	LOAD_STORE("")
+	TEST_P(   "str	pc, [r",0,0,", #15*4]")
+	TEST_R(   "str	pc, [sp, r",2,15*4,"]")
+	TEST_BF(  "ldr	pc, [sp, #15*4]")
+	TEST_BF_R("ldr	pc, [sp, r",2,15*4,"]")
+
+	TEST_P(   "str	sp, [r",0,0,", #13*4]")
+	TEST_R(   "str	sp, [sp, r",2,13*4,"]")
+	TEST_BF(  "ldr	sp, [sp, #13*4]")
+	TEST_BF_R("ldr	sp, [sp, r",2,13*4,"]")
+
+#ifdef CONFIG_THUMB2_KERNEL
+	TEST_ARM_TO_THUMB_INTERWORK_P("ldr	pc, [r",0,0,", #15*4]")
+#endif
+	TEST_UNSUPPORTED(".word 0xe5af6008	@ str r6, [pc, #8]!")
+	TEST_UNSUPPORTED(".word 0xe7af6008	@ str r6, [pc, r8]!")
+	TEST_UNSUPPORTED(".word 0xe5bf6008	@ ldr r6, [pc, #8]!")
+	TEST_UNSUPPORTED(".word 0xe7bf6008	@ ldr r6, [pc, r8]!")
+	TEST_UNSUPPORTED(".word 0xe788600f	@ str r6, [r8, pc]")
+	TEST_UNSUPPORTED(".word 0xe798600f	@ ldr r6, [r8, pc]")
+
+	LOAD_STORE("b")
+	TEST_UNSUPPORTED(".word 0xe5f7f008	@ ldrb pc, [r7, #8]!")
+	TEST_UNSUPPORTED(".word 0xe7f7f008	@ ldrb pc, [r7, r8]!")
+	TEST_UNSUPPORTED(".word 0xe5ef6008	@ strb r6, [pc, #8]!")
+	TEST_UNSUPPORTED(".word 0xe7ef6008	@ strb r6, [pc, r3]!")
+	TEST_UNSUPPORTED(".word 0xe5ff6008	@ ldrb r6, [pc, #8]!")
+	TEST_UNSUPPORTED(".word 0xe7ff6008	@ ldrb r6, [pc, r3]!")
+
+	TEST_UNSUPPORTED("ldrt	r0, [r1], #4")
+	TEST_UNSUPPORTED("ldrt	r1, [r2], r3")
+	TEST_UNSUPPORTED("strt	r2, [r3], #4")
+	TEST_UNSUPPORTED("strt	r3, [r4], r5")
+	TEST_UNSUPPORTED("ldrbt	r4, [r5], #4")
+	TEST_UNSUPPORTED("ldrbt	r5, [r6], r7")
+	TEST_UNSUPPORTED("strbt	r6, [r7], #4")
+	TEST_UNSUPPORTED("strbt	r7, [r8], r9")
+
+#if __LINUX_ARM_ARCH__ >= 7
+	TEST_GROUP("Parallel addition and subtraction, signed")
+
+	TEST_UNSUPPORTED(".word 0xe6000010") /* Unallocated space */
+	TEST_UNSUPPORTED(".word 0xe60fffff") /* Unallocated space */
+
+	TEST_RR(    "sadd16	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "sadd16	r14, r",12,HH2,", r",10,HH1,"")
+	TEST_UNSUPPORTED(".word 0xe61cff1a	@ sadd16	pc, r12, r10")
+	TEST_RR(    "sasx	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "sasx	r14, r",12,HH2,", r",10,HH1,"")
+	TEST_UNSUPPORTED(".word 0xe61cff3a	@ sasx	pc, r12, r10")
+	TEST_RR(    "ssax	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "ssax	r14, r",12,HH2,", r",10,HH1,"")
+	TEST_UNSUPPORTED(".word 0xe61cff5a	@ ssax	pc, r12, r10")
+	TEST_RR(    "ssub16	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "ssub16	r14, r",12,HH2,", r",10,HH1,"")
+	TEST_UNSUPPORTED(".word 0xe61cff7a	@ ssub16	pc, r12, r10")
+	TEST_RR(    "sadd8	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "sadd8	r14, r",12,HH2,", r",10,HH1,"")
+	TEST_UNSUPPORTED(".word 0xe61cff9a	@ sadd8	pc, r12, r10")
+	TEST_UNSUPPORTED(".word 0xe61000b0") /* Unallocated space */
+	TEST_UNSUPPORTED(".word 0xe61fffbf") /* Unallocated space */
+	TEST_UNSUPPORTED(".word 0xe61000d0") /* Unallocated space */
+	TEST_UNSUPPORTED(".word 0xe61fffdf") /* Unallocated space */
+	TEST_RR(    "ssub8	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "ssub8	r14, r",12,HH2,", r",10,HH1,"")
+	TEST_UNSUPPORTED(".word 0xe61cfffa	@ ssub8	pc, r12, r10")
+
+	TEST_RR(    "qadd16	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "qadd16	r14, r",12,HH2,", r",10,HH1,"")
+	TEST_UNSUPPORTED(".word 0xe62cff1a	@ qadd16	pc, r12, r10")
+	TEST_RR(    "qasx	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "qasx	r14, r",12,HH2,", r",10,HH1,"")
+	TEST_UNSUPPORTED(".word 0xe62cff3a	@ qasx	pc, r12, r10")
+	TEST_RR(    "qsax	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "qsax	r14, r",12,HH2,", r",10,HH1,"")
+	TEST_UNSUPPORTED(".word 0xe62cff5a	@ qsax	pc, r12, r10")
+	TEST_RR(    "qsub16	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "qsub16	r14, r",12,HH2,", r",10,HH1,"")
+	TEST_UNSUPPORTED(".word 0xe62cff7a	@ qsub16	pc, r12, r10")
+	TEST_RR(    "qadd8	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "qadd8	r14, r",12,HH2,", r",10,HH1,"")
+	TEST_UNSUPPORTED(".word 0xe62cff9a	@ qadd8	pc, r12, r10")
+	TEST_UNSUPPORTED(".word 0xe62000b0") /* Unallocated space */
+	TEST_UNSUPPORTED(".word 0xe62fffbf") /* Unallocated space */
+	TEST_UNSUPPORTED(".word 0xe62000d0") /* Unallocated space */
+	TEST_UNSUPPORTED(".word 0xe62fffdf") /* Unallocated space */
+	TEST_RR(    "qsub8	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "qsub8	r14, r",12,HH2,", r",10,HH1,"")
+	TEST_UNSUPPORTED(".word 0xe62cfffa	@ qsub8	pc, r12, r10")
+
+	TEST_RR(    "shadd16	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "shadd16	r14, r",12,HH2,", r",10,HH1,"")
+	TEST_UNSUPPORTED(".word 0xe63cff1a	@ shadd16	pc, r12, r10")
+	TEST_RR(    "shasx	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "shasx	r14, r",12,HH2,", r",10,HH1,"")
+	TEST_UNSUPPORTED(".word 0xe63cff3a	@ shasx	pc, r12, r10")
+	TEST_RR(    "shsax	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "shsax	r14, r",12,HH2,", r",10,HH1,"")
+	TEST_UNSUPPORTED(".word 0xe63cff5a	@ shsax	pc, r12, r10")
+	TEST_RR(    "shsub16	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "shsub16	r14, r",12,HH2,", r",10,HH1,"")
+	TEST_UNSUPPORTED(".word 0xe63cff7a	@ shsub16	pc, r12, r10")
+	TEST_RR(    "shadd8	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "shadd8	r14, r",12,HH2,", r",10,HH1,"")
+	TEST_UNSUPPORTED(".word 0xe63cff9a	@ shadd8	pc, r12, r10")
+	TEST_UNSUPPORTED(".word 0xe63000b0") /* Unallocated space */
+	TEST_UNSUPPORTED(".word 0xe63fffbf") /* Unallocated space */
+	TEST_UNSUPPORTED(".word 0xe63000d0") /* Unallocated space */
+	TEST_UNSUPPORTED(".word 0xe63fffdf") /* Unallocated space */
+	TEST_RR(    "shsub8	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "shsub8	r14, r",12,HH2,", r",10,HH1,"")
+	TEST_UNSUPPORTED(".word 0xe63cfffa	@ shsub8	pc, r12, r10")
+
+	TEST_GROUP("Parallel addition and subtraction, unsigned")
+
+	TEST_UNSUPPORTED(".word 0xe6400010") /* Unallocated space */
+	TEST_UNSUPPORTED(".word 0xe64fffff") /* Unallocated space */
+
+	TEST_RR(    "uadd16	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "uadd16	r14, r",12,HH2,", r",10,HH1,"")
+	TEST_UNSUPPORTED(".word 0xe65cff1a	@ uadd16	pc, r12, r10")
+	TEST_RR(    "uasx	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "uasx	r14, r",12,HH2,", r",10,HH1,"")
+	TEST_UNSUPPORTED(".word 0xe65cff3a	@ uasx	pc, r12, r10")
+	TEST_RR(    "usax	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "usax	r14, r",12,HH2,", r",10,HH1,"")
+	TEST_UNSUPPORTED(".word 0xe65cff5a	@ usax	pc, r12, r10")
+	TEST_RR(    "usub16	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "usub16	r14, r",12,HH2,", r",10,HH1,"")
+	TEST_UNSUPPORTED(".word 0xe65cff7a	@ usub16	pc, r12, r10")
+	TEST_RR(    "uadd8	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "uadd8	r14, r",12,HH2,", r",10,HH1,"")
+	TEST_UNSUPPORTED(".word 0xe65cff9a	@ uadd8	pc, r12, r10")
+	TEST_UNSUPPORTED(".word 0xe65000b0") /* Unallocated space */
+	TEST_UNSUPPORTED(".word 0xe65fffbf") /* Unallocated space */
+	TEST_UNSUPPORTED(".word 0xe65000d0") /* Unallocated space */
+	TEST_UNSUPPORTED(".word 0xe65fffdf") /* Unallocated space */
+	TEST_RR(    "usub8	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "usub8	r14, r",12,HH2,", r",10,HH1,"")
+	TEST_UNSUPPORTED(".word 0xe65cfffa	@ usub8	pc, r12, r10")
+
+	TEST_RR(    "uqadd16	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "uqadd16	r14, r",12,HH2,", r",10,HH1,"")
+	TEST_UNSUPPORTED(".word 0xe66cff1a	@ uqadd16	pc, r12, r10")
+	TEST_RR(    "uqasx	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "uqasx	r14, r",12,HH2,", r",10,HH1,"")
+	TEST_UNSUPPORTED(".word 0xe66cff3a	@ uqasx	pc, r12, r10")
+	TEST_RR(    "uqsax	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "uqsax	r14, r",12,HH2,", r",10,HH1,"")
+	TEST_UNSUPPORTED(".word 0xe66cff5a	@ uqsax	pc, r12, r10")
+	TEST_RR(    "uqsub16	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "uqsub16	r14, r",12,HH2,", r",10,HH1,"")
+	TEST_UNSUPPORTED(".word 0xe66cff7a	@ uqsub16	pc, r12, r10")
+	TEST_RR(    "uqadd8	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "uqadd8	r14, r",12,HH2,", r",10,HH1,"")
+	TEST_UNSUPPORTED(".word 0xe66cff9a	@ uqadd8	pc, r12, r10")
+	TEST_UNSUPPORTED(".word 0xe66000b0") /* Unallocated space */
+	TEST_UNSUPPORTED(".word 0xe66fffbf") /* Unallocated space */
+	TEST_UNSUPPORTED(".word 0xe66000d0") /* Unallocated space */
+	TEST_UNSUPPORTED(".word 0xe66fffdf") /* Unallocated space */
+	TEST_RR(    "uqsub8	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "uqsub8	r14, r",12,HH2,", r",10,HH1,"")
+	TEST_UNSUPPORTED(".word 0xe66cfffa	@ uqsub8	pc, r12, r10")
+
+	TEST_RR(    "uhadd16	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "uhadd16	r14, r",12,HH2,", r",10,HH1,"")
+	TEST_UNSUPPORTED(".word 0xe67cff1a	@ uhadd16	pc, r12, r10")
+	TEST_RR(    "uhasx	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "uhasx	r14, r",12,HH2,", r",10,HH1,"")
+	TEST_UNSUPPORTED(".word 0xe67cff3a	@ uhasx	pc, r12, r10")
+	TEST_RR(    "uhsax	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "uhsax	r14, r",12,HH2,", r",10,HH1,"")
+	TEST_UNSUPPORTED(".word 0xe67cff5a	@ uhsax	pc, r12, r10")
+	TEST_RR(    "uhsub16	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "uhsub16	r14, r",12,HH2,", r",10,HH1,"")
+	TEST_UNSUPPORTED(".word 0xe67cff7a	@ uhsub16	pc, r12, r10")
+	TEST_RR(    "uhadd8	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "uhadd8	r14, r",12,HH2,", r",10,HH1,"")
+	TEST_UNSUPPORTED(".word 0xe67cff9a	@ uhadd8	pc, r12, r10")
+	TEST_UNSUPPORTED(".word 0xe67000b0") /* Unallocated space */
+	TEST_UNSUPPORTED(".word 0xe67fffbf") /* Unallocated space */
+	TEST_UNSUPPORTED(".word 0xe67000d0") /* Unallocated space */
+	TEST_UNSUPPORTED(".word 0xe67fffdf") /* Unallocated space */
+	TEST_RR(    "uhsub8	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "uhsub8	r14, r",12,HH2,", r",10,HH1,"")
+	TEST_UNSUPPORTED(".word 0xe67cfffa	@ uhsub8	pc, r12, r10")
+	TEST_UNSUPPORTED(".word 0xe67feffa	@ uhsub8	r14, pc, r10")
+	TEST_UNSUPPORTED(".word 0xe67cefff	@ uhsub8	r14, r12, pc")
+#endif /* __LINUX_ARM_ARCH__ >= 7 */
+
+#if __LINUX_ARM_ARCH__ >= 6
+	TEST_GROUP("Packing, unpacking, saturation, and reversal")
+
+	TEST_RR(    "pkhbt	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "pkhbt	r14,r",12, HH1,", r",10,HH2,", lsl #2")
+	TEST_UNSUPPORTED(".word 0xe68cf11a	@ pkhbt	pc, r12, r10, lsl #2")
+	TEST_RR(    "pkhtb	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "pkhtb	r14,r",12, HH1,", r",10,HH2,", asr #2")
+	TEST_UNSUPPORTED(".word 0xe68cf15a	@ pkhtb	pc, r12, r10, asr #2")
+	TEST_UNSUPPORTED(".word 0xe68fe15a	@ pkhtb	r14, pc, r10, asr #2")
+	TEST_UNSUPPORTED(".word 0xe68ce15f	@ pkhtb	r14, r12, pc, asr #2")
+	TEST_UNSUPPORTED(".word 0xe6900010") /* Unallocated space */
+	TEST_UNSUPPORTED(".word 0xe69fffdf") /* Unallocated space */
+
+	TEST_R(     "ssat	r0, #24, r",0,   VAL1,"")
+	TEST_R(     "ssat	r14, #24, r",12, VAL2,"")
+	TEST_R(     "ssat	r0, #24, r",0,   VAL1,", lsl #8")
+	TEST_R(     "ssat	r14, #24, r",12, VAL2,", asr #8")
+	TEST_UNSUPPORTED(".word 0xe6b7f01c	@ ssat	pc, #24, r12")
+
+	TEST_R(     "usat	r0, #24, r",0,   VAL1,"")
+	TEST_R(     "usat	r14, #24, r",12, VAL2,"")
+	TEST_R(     "usat	r0, #24, r",0,   VAL1,", lsl #8")
+	TEST_R(     "usat	r14, #24, r",12, VAL2,", asr #8")
+	TEST_UNSUPPORTED(".word 0xe6f7f01c	@ usat	pc, #24, r12")
+
+	TEST_RR(    "sxtab16	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "sxtab16	r14,r",12, HH2,", r",10,HH1,", ror #8")
+	TEST_R(     "sxtb16	r8, r",7,  HH1,"")
+	TEST_UNSUPPORTED(".word 0xe68cf47a	@ sxtab16	pc,r12, r10, ror #8")
+
+	TEST_RR(    "sel	r0, r",0,  VAL1,", r",1, VAL2,"")
+	TEST_RR(    "sel	r14, r",12,VAL1,", r",10, VAL2,"")
+	TEST_UNSUPPORTED(".word 0xe68cffba	@ sel	pc, r12, r10")
+	TEST_UNSUPPORTED(".word 0xe68fefba	@ sel	r14, pc, r10")
+	TEST_UNSUPPORTED(".word 0xe68cefbf	@ sel	r14, r12, pc")
+
+	TEST_R(     "ssat16	r0, #12, r",0,   HH1,"")
+	TEST_R(     "ssat16	r14, #12, r",12, HH2,"")
+	TEST_UNSUPPORTED(".word 0xe6abff3c	@ ssat16	pc, #12, r12")
+
+	TEST_RR(    "sxtab	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "sxtab	r14,r",12, HH2,", r",10,HH1,", ror #8")
+	TEST_R(     "sxtb	r8, r",7,  HH1,"")
+	TEST_UNSUPPORTED(".word 0xe6acf47a	@ sxtab	pc,r12, r10, ror #8")
+
+	TEST_R(     "rev	r0, r",0,   VAL1,"")
+	TEST_R(     "rev	r14, r",12, VAL2,"")
+	TEST_UNSUPPORTED(".word 0xe6bfff3c	@ rev	pc, r12")
+
+	TEST_RR(    "sxtah	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "sxtah	r14,r",12, HH2,", r",10,HH1,", ror #8")
+	TEST_R(     "sxth	r8, r",7,  HH1,"")
+	TEST_UNSUPPORTED(".word 0xe6bcf47a	@ sxtah	pc,r12, r10, ror #8")
+
+	TEST_R(     "rev16	r0, r",0,   VAL1,"")
+	TEST_R(     "rev16	r14, r",12, VAL2,"")
+	TEST_UNSUPPORTED(".word 0xe6bfffbc	@ rev16	pc, r12")
+
+	TEST_RR(    "uxtab16	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "uxtab16	r14,r",12, HH2,", r",10,HH1,", ror #8")
+	TEST_R(     "uxtb16	r8, r",7,  HH1,"")
+	TEST_UNSUPPORTED(".word 0xe6ccf47a	@ uxtab16	pc,r12, r10, ror #8")
+
+	TEST_R(     "usat16	r0, #12, r",0,   HH1,"")
+	TEST_R(     "usat16	r14, #12, r",12, HH2,"")
+	TEST_UNSUPPORTED(".word 0xe6ecff3c	@ usat16	pc, #12, r12")
+	TEST_UNSUPPORTED(".word 0xe6ecef3f	@ usat16	r14, #12, pc")
+
+	TEST_RR(    "uxtab	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "uxtab	r14,r",12, HH2,", r",10,HH1,", ror #8")
+	TEST_R(     "uxtb	r8, r",7,  HH1,"")
+	TEST_UNSUPPORTED(".word 0xe6ecf47a	@ uxtab	pc,r12, r10, ror #8")
+
+#if __LINUX_ARM_ARCH__ >= 7
+	TEST_R(     "rbit	r0, r",0,   VAL1,"")
+	TEST_R(     "rbit	r14, r",12, VAL2,"")
+	TEST_UNSUPPORTED(".word 0xe6ffff3c	@ rbit	pc, r12")
+#endif
+
+	TEST_RR(    "uxtah	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "uxtah	r14,r",12, HH2,", r",10,HH1,", ror #8")
+	TEST_R(     "uxth	r8, r",7,  HH1,"")
+	TEST_UNSUPPORTED(".word 0xe6fff077	@ uxth	pc, r7")
+	TEST_UNSUPPORTED(".word 0xe6ff807f	@ uxth	r8, pc")
+	TEST_UNSUPPORTED(".word 0xe6fcf47a	@ uxtah	pc, r12, r10, ror #8")
+	TEST_UNSUPPORTED(".word 0xe6fce47f	@ uxtah	r14, r12, pc, ror #8")
+
+	TEST_R(     "revsh	r0, r",0,   VAL1,"")
+	TEST_R(     "revsh	r14, r",12, VAL2,"")
+	TEST_UNSUPPORTED(".word 0xe6ffff3c	@ revsh	pc, r12")
+	TEST_UNSUPPORTED(".word 0xe6ffef3f	@ revsh	r14, pc")
+
+	TEST_UNSUPPORTED(".word 0xe6900070") /* Unallocated space */
+	TEST_UNSUPPORTED(".word 0xe69fff7f") /* Unallocated space */
+
+	TEST_UNSUPPORTED(".word 0xe6d00070") /* Unallocated space */
+	TEST_UNSUPPORTED(".word 0xe6dfff7f") /* Unallocated space */
+#endif /* __LINUX_ARM_ARCH__ >= 6 */
+
+#if __LINUX_ARM_ARCH__ >= 6
+	TEST_GROUP("Signed multiplies")
+
+	TEST_RRR(   "smlad	r0, r",0,  HH1,", r",1, HH2,", r",2, VAL1,"")
+	TEST_RRR(   "smlad	r14, r",12,HH2,", r",10,HH1,", r",8, VAL2,"")
+	TEST_UNSUPPORTED(".word 0xe70f8a1c	@ smlad	pc, r12, r10, r8")
+	TEST_RRR(   "smladx	r0, r",0,  HH1,", r",1, HH2,", r",2, VAL1,"")
+	TEST_RRR(   "smladx	r14, r",12,HH2,", r",10,HH1,", r",8, VAL2,"")
+	TEST_UNSUPPORTED(".word 0xe70f8a3c	@ smladx	pc, r12, r10, r8")
+
+	TEST_RR(   "smuad	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(   "smuad	r14, r",12,HH2,", r",10,HH1,"")
+	TEST_UNSUPPORTED(".word 0xe70ffa1c	@ smuad	pc, r12, r10")
+	TEST_RR(   "smuadx	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(   "smuadx	r14, r",12,HH2,", r",10,HH1,"")
+	TEST_UNSUPPORTED(".word 0xe70ffa3c	@ smuadx	pc, r12, r10")
+
+	TEST_RRR(   "smlsd	r0, r",0,  HH1,", r",1, HH2,", r",2, VAL1,"")
+	TEST_RRR(   "smlsd	r14, r",12,HH2,", r",10,HH1,", r",8, VAL2,"")
+	TEST_UNSUPPORTED(".word 0xe70f8a5c	@ smlsd	pc, r12, r10, r8")
+	TEST_RRR(   "smlsdx	r0, r",0,  HH1,", r",1, HH2,", r",2, VAL1,"")
+	TEST_RRR(   "smlsdx	r14, r",12,HH2,", r",10,HH1,", r",8, VAL2,"")
+	TEST_UNSUPPORTED(".word 0xe70f8a7c	@ smlsdx	pc, r12, r10, r8")
+
+	TEST_RR(   "smusd	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(   "smusd	r14, r",12,HH2,", r",10,HH1,"")
+	TEST_UNSUPPORTED(".word 0xe70ffa5c	@ smusd	pc, r12, r10")
+	TEST_RR(   "smusdx	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(   "smusdx	r14, r",12,HH2,", r",10,HH1,"")
+	TEST_UNSUPPORTED(".word 0xe70ffa7c	@ smusdx	pc, r12, r10")
+
+	TEST_RRRR( "smlald	r",0, VAL1,", r",1, VAL2, ", r",0, HH1,", r",1, HH2)
+	TEST_RRRR( "smlald	r",11,VAL2,", r",10,VAL1, ", r",9, HH2,", r",8, HH1)
+	TEST_UNSUPPORTED(".word 0xe74af819	@ smlald	pc, r10, r9, r8")
+	TEST_UNSUPPORTED(".word 0xe74fb819	@ smlald	r11, pc, r9, r8")
+	TEST_UNSUPPORTED(".word 0xe74ab81f	@ smlald	r11, r10, pc, r8")
+	TEST_UNSUPPORTED(".word 0xe74abf19	@ smlald	r11, r10, r9, pc")
+
+	TEST_RRRR( "smlaldx	r",0, VAL1,", r",1, VAL2, ", r",0, HH1,", r",1, HH2)
+	TEST_RRRR( "smlaldx	r",11,VAL2,", r",10,VAL1, ", r",9, HH2,", r",8, HH1)
+	TEST_UNSUPPORTED(".word 0xe74af839	@ smlaldx	pc, r10, r9, r8")
+	TEST_UNSUPPORTED(".word 0xe74fb839	@ smlaldx	r11, pc, r9, r8")
+
+	TEST_RRR(  "smmla	r0, r",0,  VAL1,", r",1, VAL2,", r",2, VAL1,"")
+	TEST_RRR(  "smmla	r14, r",12,VAL2,", r",10,VAL1,", r",8, VAL2,"")
+	TEST_UNSUPPORTED(".word 0xe75f8a1c	@ smmla	pc, r12, r10, r8")
+	TEST_RRR(  "smmlar	r0, r",0,  VAL1,", r",1, VAL2,", r",2, VAL1,"")
+	TEST_RRR(  "smmlar	r14, r",12,VAL2,", r",10,VAL1,", r",8, VAL2,"")
+	TEST_UNSUPPORTED(".word 0xe75f8a3c	@ smmlar	pc, r12, r10, r8")
+
+	TEST_RR(   "smmul	r0, r",0,  VAL1,", r",1, VAL2,"")
+	TEST_RR(   "smmul	r14, r",12,VAL2,", r",10,VAL1,"")
+	TEST_UNSUPPORTED(".word 0xe75ffa1c	@ smmul	pc, r12, r10")
+	TEST_RR(   "smmulr	r0, r",0,  VAL1,", r",1, VAL2,"")
+	TEST_RR(   "smmulr	r14, r",12,VAL2,", r",10,VAL1,"")
+	TEST_UNSUPPORTED(".word 0xe75ffa3c	@ smmulr	pc, r12, r10")
+
+	TEST_RRR(  "smmls	r0, r",0,  VAL1,", r",1, VAL2,", r",2, VAL1,"")
+	TEST_RRR(  "smmls	r14, r",12,VAL2,", r",10,VAL1,", r",8, VAL2,"")
+	TEST_UNSUPPORTED(".word 0xe75f8adc	@ smmls	pc, r12, r10, r8")
+	TEST_RRR(  "smmlsr	r0, r",0,  VAL1,", r",1, VAL2,", r",2, VAL1,"")
+	TEST_RRR(  "smmlsr	r14, r",12,VAL2,", r",10,VAL1,", r",8, VAL2,"")
+	TEST_UNSUPPORTED(".word 0xe75f8afc	@ smmlsr	pc, r12, r10, r8")
+	TEST_UNSUPPORTED(".word 0xe75e8aff	@ smmlsr	r14, pc, r10, r8")
+	TEST_UNSUPPORTED(".word 0xe75e8ffc	@ smmlsr	r14, r12, pc, r8")
+	TEST_UNSUPPORTED(".word 0xe75efafc	@ smmlsr	r14, r12, r10, pc")
+
+	TEST_RR(   "usad8	r0, r",0,  VAL1,", r",1, VAL2,"")
+	TEST_RR(   "usad8	r14, r",12,VAL2,", r",10,VAL1,"")
+	TEST_UNSUPPORTED(".word 0xe75ffa1c	@ usad8	pc, r12, r10")
+	TEST_UNSUPPORTED(".word 0xe75efa1f	@ usad8	r14, pc, r10")
+	TEST_UNSUPPORTED(".word 0xe75eff1c	@ usad8	r14, r12, pc")
+
+	TEST_RRR(  "usada8	r0, r",0,  VAL1,", r",1, VAL2,", r",2, VAL3,"")
+	TEST_RRR(  "usada8	r14, r",12,VAL2,", r",10,VAL1,", r",8, VAL3,"")
+	TEST_UNSUPPORTED(".word 0xe78f8a1c	@ usada8	pc, r12, r10, r8")
+	TEST_UNSUPPORTED(".word 0xe78e8a1f	@ usada8	r14, pc, r10, r8")
+	TEST_UNSUPPORTED(".word 0xe78e8f1c	@ usada8	r14, r12, pc, r8")
+#endif /* __LINUX_ARM_ARCH__ >= 6 */
+
+#if __LINUX_ARM_ARCH__ >= 7
+	TEST_GROUP("Bit Field")
+
+	TEST_R(     "sbfx	r0, r",0  , VAL1,", #0, #31")
+	TEST_R(     "sbfxeq	r14, r",12, VAL2,", #8, #16")
+	TEST_R(     "sbfx	r4, r",10,  VAL1,", #16, #15")
+	TEST_UNSUPPORTED(".word 0xe7aff45c	@ sbfx	pc, r12, #8, #16")
+
+	TEST_R(     "ubfx	r0, r",0  , VAL1,", #0, #31")
+	TEST_R(     "ubfxcs	r14, r",12, VAL2,", #8, #16")
+	TEST_R(     "ubfx	r4, r",10,  VAL1,", #16, #15")
+	TEST_UNSUPPORTED(".word 0xe7eff45c	@ ubfx	pc, r12, #8, #16")
+	TEST_UNSUPPORTED(".word 0xe7efc45f	@ ubfx	r12, pc, #8, #16")
+
+	TEST_R(     "bfc	r",0, VAL1,", #4, #20")
+	TEST_R(     "bfcvs	r",14,VAL2,", #4, #20")
+	TEST_R(     "bfc	r",7, VAL1,", #0, #31")
+	TEST_R(     "bfc	r",8, VAL2,", #0, #31")
+	TEST_UNSUPPORTED(".word 0xe7def01f	@ bfc	pc, #0, #31");
+
+	TEST_RR(    "bfi	r",0, VAL1,", r",0  , VAL2,", #0, #31")
+	TEST_RR(    "bfipl	r",12,VAL1,", r",14 , VAL2,", #4, #20")
+	TEST_UNSUPPORTED(".word 0xe7d7f21e	@ bfi	pc, r14, #4, #20")
+
+	TEST_UNSUPPORTED(".word 0x07f000f0")  /* Permanently UNDEFINED */
+	TEST_UNSUPPORTED(".word 0x07ffffff")  /* Permanently UNDEFINED */
+#endif /* __LINUX_ARM_ARCH__ >= 6 */
+
+	TEST_GROUP("Branch, branch with link, and block data transfer")
+
+	TEST_P(   "stmda	r",0, 16*4,", {r0}")
+	TEST_P(   "stmeqda	r",4, 16*4,", {r0-r15}")
+	TEST_P(   "stmneda	r",8, 16*4,"!, {r8-r15}")
+	TEST_P(   "stmda	r",12,16*4,"!, {r1,r3,r5,r7,r8-r11,r14}")
+	TEST_P(   "stmda	r",13,0,   "!, {pc}")
+
+	TEST_P(   "ldmda	r",0, 16*4,", {r0}")
+	TEST_BF_P("ldmcsda	r",4, 15*4,", {r0-r15}")
+	TEST_BF_P("ldmccda	r",7, 15*4,"!, {r8-r15}")
+	TEST_P(   "ldmda	r",12,16*4,"!, {r1,r3,r5,r7,r8-r11,r14}")
+	TEST_BF_P("ldmda	r",14,15*4,"!, {pc}")
+
+	TEST_P(   "stmia	r",0, 16*4,", {r0}")
+	TEST_P(   "stmmiia	r",4, 16*4,", {r0-r15}")
+	TEST_P(   "stmplia	r",8, 16*4,"!, {r8-r15}")
+	TEST_P(   "stmia	r",12,16*4,"!, {r1,r3,r5,r7,r8-r11,r14}")
+	TEST_P(   "stmia	r",14,0,   "!, {pc}")
+
+	TEST_P(   "ldmia	r",0, 16*4,", {r0}")
+	TEST_BF_P("ldmvsia	r",4, 0,   ", {r0-r15}")
+	TEST_BF_P("ldmvcia	r",7, 8*4, "!, {r8-r15}")
+	TEST_P(   "ldmia	r",12,16*4,"!, {r1,r3,r5,r7,r8-r11,r14}")
+	TEST_BF_P("ldmia	r",14,15*4,"!, {pc}")
+
+	TEST_P(   "stmdb	r",0, 16*4,", {r0}")
+	TEST_P(   "stmhidb	r",4, 16*4,", {r0-r15}")
+	TEST_P(   "stmlsdb	r",8, 16*4,"!, {r8-r15}")
+	TEST_P(   "stmdb	r",12,16*4,"!, {r1,r3,r5,r7,r8-r11,r14}")
+	TEST_P(   "stmdb	r",13,4,   "!, {pc}")
+
+	TEST_P(   "ldmdb	r",0, 16*4,", {r0}")
+	TEST_BF_P("ldmgedb	r",4, 16*4,", {r0-r15}")
+	TEST_BF_P("ldmltdb	r",7, 16*4,"!, {r8-r15}")
+	TEST_P(   "ldmdb	r",12,16*4,"!, {r1,r3,r5,r7,r8-r11,r14}")
+	TEST_BF_P("ldmdb	r",14,16*4,"!, {pc}")
+
+	TEST_P(   "stmib	r",0, 16*4,", {r0}")
+	TEST_P(   "stmgtib	r",4, 16*4,", {r0-r15}")
+	TEST_P(   "stmleib	r",8, 16*4,"!, {r8-r15}")
+	TEST_P(   "stmib	r",12,16*4,"!, {r1,r3,r5,r7,r8-r11,r14}")
+	TEST_P(   "stmib	r",13,-4,  "!, {pc}")
+
+	TEST_P(   "ldmib	r",0, 16*4,", {r0}")
+	TEST_BF_P("ldmeqib	r",4, -4,", {r0-r15}")
+	TEST_BF_P("ldmneib	r",7, 7*4,"!, {r8-r15}")
+	TEST_P(   "ldmib	r",12,16*4,"!, {r1,r3,r5,r7,r8-r11,r14}")
+	TEST_BF_P("ldmib	r",14,14*4,"!, {pc}")
+
+	TEST_P(   "stmdb	r",13,16*4,"!, {r3-r12,lr}")
+	TEST_P(	  "stmeqdb	r",13,16*4,"!, {r3-r12}")
+	TEST_P(   "stmnedb	r",2, 16*4,", {r3-r12,lr}")
+	TEST_P(   "stmdb	r",13,16*4,"!, {r2-r12,lr}")
+	TEST_P(   "stmdb	r",0, 16*4,", {r0-r12}")
+	TEST_P(   "stmdb	r",0, 16*4,", {r0-r12,lr}")
+
+	TEST_BF_P("ldmia	r",13,5*4, "!, {r3-r12,pc}")
+	TEST_P(	  "ldmccia	r",13,5*4, "!, {r3-r12}")
+	TEST_BF_P("ldmcsia	r",2, 5*4, "!, {r3-r12,pc}")
+	TEST_BF_P("ldmia	r",13,4*4, "!, {r2-r12,pc}")
+	TEST_P(   "ldmia	r",0, 16*4,", {r0-r12}")
+	TEST_P(   "ldmia	r",0, 16*4,", {r0-r12,lr}")
+
+#ifdef CONFIG_THUMB2_KERNEL
+	TEST_ARM_TO_THUMB_INTERWORK_P("ldmplia	r",0,15*4,", {pc}")
+	TEST_ARM_TO_THUMB_INTERWORK_P("ldmmiia	r",13,0,", {r0-r15}")
+#endif
+	TEST_BF("b	2f")
+	TEST_BF("bl	2f")
+	TEST_BB("b	2b")
+	TEST_BB("bl	2b")
+
+	TEST_BF("beq	2f")
+	TEST_BF("bleq	2f")
+	TEST_BB("bne	2b")
+	TEST_BB("blne	2b")
+
+	TEST_BF("bgt	2f")
+	TEST_BF("blgt	2f")
+	TEST_BB("blt	2b")
+	TEST_BB("bllt	2b")
+
+	TEST_GROUP("Supervisor Call, and coprocessor instructions")
+
+	/*
+	 * We can't really test these by executing them, so all
+	 * we can do is check that probes are, or are not allowed.
+	 * At the moment none are allowed...
+	 */
+#define TEST_COPROCESSOR(code) TEST_UNSUPPORTED(code)
+
+#define COPROCESSOR_INSTRUCTIONS_ST_LD(two,cc)					\
+	TEST_COPROCESSOR("stc"two"	0, cr0, [r13, #4]")			\
+	TEST_COPROCESSOR("stc"two"	0, cr0, [r13, #-4]")			\
+	TEST_COPROCESSOR("stc"two"	0, cr0, [r13, #4]!")			\
+	TEST_COPROCESSOR("stc"two"	0, cr0, [r13, #-4]!")			\
+	TEST_COPROCESSOR("stc"two"	0, cr0, [r13], #4")			\
+	TEST_COPROCESSOR("stc"two"	0, cr0, [r13], #-4")			\
+	TEST_COPROCESSOR("stc"two"	0, cr0, [r13], {1}")			\
+	TEST_COPROCESSOR("stc"two"l	0, cr0, [r13, #4]")			\
+	TEST_COPROCESSOR("stc"two"l	0, cr0, [r13, #-4]")			\
+	TEST_COPROCESSOR("stc"two"l	0, cr0, [r13, #4]!")			\
+	TEST_COPROCESSOR("stc"two"l	0, cr0, [r13, #-4]!")			\
+	TEST_COPROCESSOR("stc"two"l	0, cr0, [r13], #4")			\
+	TEST_COPROCESSOR("stc"two"l	0, cr0, [r13], #-4")			\
+	TEST_COPROCESSOR("stc"two"l	0, cr0, [r13], {1}")			\
+	TEST_COPROCESSOR("ldc"two"	0, cr0, [r13, #4]")			\
+	TEST_COPROCESSOR("ldc"two"	0, cr0, [r13, #-4]")			\
+	TEST_COPROCESSOR("ldc"two"	0, cr0, [r13, #4]!")			\
+	TEST_COPROCESSOR("ldc"two"	0, cr0, [r13, #-4]!")			\
+	TEST_COPROCESSOR("ldc"two"	0, cr0, [r13], #4")			\
+	TEST_COPROCESSOR("ldc"two"	0, cr0, [r13], #-4")			\
+	TEST_COPROCESSOR("ldc"two"	0, cr0, [r13], {1}")			\
+	TEST_COPROCESSOR("ldc"two"l	0, cr0, [r13, #4]")			\
+	TEST_COPROCESSOR("ldc"two"l	0, cr0, [r13, #-4]")			\
+	TEST_COPROCESSOR("ldc"two"l	0, cr0, [r13, #4]!")			\
+	TEST_COPROCESSOR("ldc"two"l	0, cr0, [r13, #-4]!")			\
+	TEST_COPROCESSOR("ldc"two"l	0, cr0, [r13], #4")			\
+	TEST_COPROCESSOR("ldc"two"l	0, cr0, [r13], #-4")			\
+	TEST_COPROCESSOR("ldc"two"l	0, cr0, [r13], {1}")			\
+										\
+	TEST_COPROCESSOR( "stc"two"	0, cr0, [r15, #4]")			\
+	TEST_COPROCESSOR( "stc"two"	0, cr0, [r15, #-4]")			\
+	TEST_UNSUPPORTED(".word 0x"cc"daf0001	@ stc"two"	0, cr0, [r15, #4]!")	\
+	TEST_UNSUPPORTED(".word 0x"cc"d2f0001	@ stc"two"	0, cr0, [r15, #-4]!")	\
+	TEST_UNSUPPORTED(".word 0x"cc"caf0001	@ stc"two"	0, cr0, [r15], #4")	\
+	TEST_UNSUPPORTED(".word 0x"cc"c2f0001	@ stc"two"	0, cr0, [r15], #-4")	\
+	TEST_COPROCESSOR( "stc"two"	0, cr0, [r15], {1}")			\
+	TEST_COPROCESSOR( "stc"two"l	0, cr0, [r15, #4]")			\
+	TEST_COPROCESSOR( "stc"two"l	0, cr0, [r15, #-4]")			\
+	TEST_UNSUPPORTED(".word 0x"cc"def0001	@ stc"two"l	0, cr0, [r15, #4]!")	\
+	TEST_UNSUPPORTED(".word 0x"cc"d6f0001	@ stc"two"l	0, cr0, [r15, #-4]!")	\
+	TEST_UNSUPPORTED(".word 0x"cc"cef0001	@ stc"two"l	0, cr0, [r15], #4")	\
+	TEST_UNSUPPORTED(".word 0x"cc"c6f0001	@ stc"two"l	0, cr0, [r15], #-4")	\
+	TEST_COPROCESSOR( "stc"two"l	0, cr0, [r15], {1}")			\
+	TEST_COPROCESSOR( "ldc"two"	0, cr0, [r15, #4]")			\
+	TEST_COPROCESSOR( "ldc"two"	0, cr0, [r15, #-4]")			\
+	TEST_UNSUPPORTED(".word 0x"cc"dbf0001	@ ldc"two"	0, cr0, [r15, #4]!")	\
+	TEST_UNSUPPORTED(".word 0x"cc"d3f0001	@ ldc"two"	0, cr0, [r15, #-4]!")	\
+	TEST_UNSUPPORTED(".word 0x"cc"cbf0001	@ ldc"two"	0, cr0, [r15], #4")	\
+	TEST_UNSUPPORTED(".word 0x"cc"c3f0001	@ ldc"two"	0, cr0, [r15], #-4")	\
+	TEST_COPROCESSOR( "ldc"two"	0, cr0, [r15], {1}")			\
+	TEST_COPROCESSOR( "ldc"two"l	0, cr0, [r15, #4]")			\
+	TEST_COPROCESSOR( "ldc"two"l	0, cr0, [r15, #-4]")			\
+	TEST_UNSUPPORTED(".word 0x"cc"dff0001	@ ldc"two"l	0, cr0, [r15, #4]!")	\
+	TEST_UNSUPPORTED(".word 0x"cc"d7f0001	@ ldc"two"l	0, cr0, [r15, #-4]!")	\
+	TEST_UNSUPPORTED(".word 0x"cc"cff0001	@ ldc"two"l	0, cr0, [r15], #4")	\
+	TEST_UNSUPPORTED(".word 0x"cc"c7f0001	@ ldc"two"l	0, cr0, [r15], #-4")	\
+	TEST_COPROCESSOR( "ldc"two"l	0, cr0, [r15], {1}")
+
+#define COPROCESSOR_INSTRUCTIONS_MC_MR(two,cc)					\
+										\
+	TEST_COPROCESSOR( "mcrr"two"	0, 15, r0, r14, cr0")			\
+	TEST_COPROCESSOR( "mcrr"two"	15, 0, r14, r0, cr15")			\
+	TEST_UNSUPPORTED(".word 0x"cc"c4f00f0	@ mcrr"two"	0, 15, r0, r15, cr0")	\
+	TEST_UNSUPPORTED(".word 0x"cc"c40ff0f	@ mcrr"two"	15, 0, r15, r0, cr15")	\
+	TEST_COPROCESSOR( "mrrc"two"	0, 15, r0, r14, cr0")			\
+	TEST_COPROCESSOR( "mrrc"two"	15, 0, r14, r0, cr15")			\
+	TEST_UNSUPPORTED(".word 0x"cc"c5f00f0	@ mrrc"two"	0, 15, r0, r15, cr0")	\
+	TEST_UNSUPPORTED(".word 0x"cc"c50ff0f	@ mrrc"two"	15, 0, r15, r0, cr15")	\
+	TEST_COPROCESSOR( "cdp"two"	15, 15, cr15, cr15, cr15, 7")		\
+	TEST_COPROCESSOR( "cdp"two"	0, 0, cr0, cr0, cr0, 0")		\
+	TEST_COPROCESSOR( "mcr"two"	15, 7, r15, cr15, cr15, 7")		\
+	TEST_COPROCESSOR( "mcr"two"	0, 0, r0, cr0, cr0, 0")			\
+	TEST_COPROCESSOR( "mrc"two"	15, 7, r15, cr15, cr15, 7")		\
+	TEST_COPROCESSOR( "mrc"two"	0, 0, r0, cr0, cr0, 0")
+
+	COPROCESSOR_INSTRUCTIONS_ST_LD("","e")
+	COPROCESSOR_INSTRUCTIONS_MC_MR("","e")
+	TEST_UNSUPPORTED("svc	0")
+	TEST_UNSUPPORTED("svc	0xffffff")
+
+	TEST_UNSUPPORTED("svc	0")
+
+	TEST_GROUP("Unconditional instruction")
+
+#if __LINUX_ARM_ARCH__ >= 6
+	TEST_UNSUPPORTED("srsda	sp, 0x13")
+	TEST_UNSUPPORTED("srsdb	sp, 0x13")
+	TEST_UNSUPPORTED("srsia	sp, 0x13")
+	TEST_UNSUPPORTED("srsib	sp, 0x13")
+	TEST_UNSUPPORTED("srsda	sp!, 0x13")
+	TEST_UNSUPPORTED("srsdb	sp!, 0x13")
+	TEST_UNSUPPORTED("srsia	sp!, 0x13")
+	TEST_UNSUPPORTED("srsib	sp!, 0x13")
+
+	TEST_UNSUPPORTED("rfeda	sp")
+	TEST_UNSUPPORTED("rfedb	sp")
+	TEST_UNSUPPORTED("rfeia	sp")
+	TEST_UNSUPPORTED("rfeib	sp")
+	TEST_UNSUPPORTED("rfeda	sp!")
+	TEST_UNSUPPORTED("rfedb	sp!")
+	TEST_UNSUPPORTED("rfeia	sp!")
+	TEST_UNSUPPORTED("rfeib	sp!")
+	TEST_UNSUPPORTED(".word 0xf81d0a00	@ rfeda	pc")
+	TEST_UNSUPPORTED(".word 0xf91d0a00	@ rfedb	pc")
+	TEST_UNSUPPORTED(".word 0xf89d0a00	@ rfeia	pc")
+	TEST_UNSUPPORTED(".word 0xf99d0a00	@ rfeib	pc")
+	TEST_UNSUPPORTED(".word 0xf83d0a00	@ rfeda	pc!")
+	TEST_UNSUPPORTED(".word 0xf93d0a00	@ rfedb	pc!")
+	TEST_UNSUPPORTED(".word 0xf8bd0a00	@ rfeia	pc!")
+	TEST_UNSUPPORTED(".word 0xf9bd0a00	@ rfeib	pc!")
+#endif /* __LINUX_ARM_ARCH__ >= 6 */
+
+#if __LINUX_ARM_ARCH__ >= 6
+	TEST_X(	"blx	__dummy_thumb_subroutine_even",
+		".thumb				\n\t"
+		".space 4			\n\t"
+		".type __dummy_thumb_subroutine_even, %%function \n\t"
+		"__dummy_thumb_subroutine_even:	\n\t"
+		"mov	r0, pc			\n\t"
+		"bx	lr			\n\t"
+		".arm				\n\t"
+	)
+	TEST(	"blx	__dummy_thumb_subroutine_even")
+
+	TEST_X(	"blx	__dummy_thumb_subroutine_odd",
+		".thumb				\n\t"
+		".space 2			\n\t"
+		".type __dummy_thumb_subroutine_odd, %%function	\n\t"
+		"__dummy_thumb_subroutine_odd:	\n\t"
+		"mov	r0, pc			\n\t"
+		"bx	lr			\n\t"
+		".arm				\n\t"
+	)
+	TEST(	"blx	__dummy_thumb_subroutine_odd")
+#endif /* __LINUX_ARM_ARCH__ >= 6 */
+
+	COPROCESSOR_INSTRUCTIONS_ST_LD("2","f")
+#if __LINUX_ARM_ARCH__ >= 6
+	COPROCESSOR_INSTRUCTIONS_MC_MR("2","f")
+#endif
+
+	TEST_GROUP("Miscellaneous instructions, memory hints, and Advanced SIMD instructions")
+
+#if __LINUX_ARM_ARCH__ >= 6
+	TEST_UNSUPPORTED("cps	0x13")
+	TEST_UNSUPPORTED("cpsie	i")
+	TEST_UNSUPPORTED("cpsid	i")
+	TEST_UNSUPPORTED("cpsie	i,0x13")
+	TEST_UNSUPPORTED("cpsid	i,0x13")
+	TEST_UNSUPPORTED("setend	le")
+	TEST_UNSUPPORTED("setend	be")
+#endif
+
+#if __LINUX_ARM_ARCH__ >= 7
+	TEST_P("pli	[r",0,0b,", #16]")
+	TEST(  "pli	[pc, #0]")
+	TEST_RR("pli	[r",12,0b,", r",0, 16,"]")
+	TEST_RR("pli	[r",0, 0b,", -r",12,16,", lsl #4]")
+#endif
+
+#if __LINUX_ARM_ARCH__ >= 5
+	TEST_P("pld	[r",0,32,", #-16]")
+	TEST(  "pld	[pc, #0]")
+	TEST_PR("pld	[r",7, 24, ", r",0, 16,"]")
+	TEST_PR("pld	[r",8, 24, ", -r",12,16,", lsl #4]")
+#endif
+
+#if __LINUX_ARM_ARCH__ >= 7
+	TEST_SUPPORTED(  ".word 0xf590f000	@ pldw [r0, #0]")
+	TEST_SUPPORTED(  ".word 0xf797f000	@ pldw	[r7, r0]")
+	TEST_SUPPORTED(  ".word 0xf798f18c	@ pldw	[r8, r12, lsl #3]");
+#endif
+
+#if __LINUX_ARM_ARCH__ >= 7
+	TEST_UNSUPPORTED("clrex")
+	TEST_UNSUPPORTED("dsb")
+	TEST_UNSUPPORTED("dmb")
+	TEST_UNSUPPORTED("isb")
+#endif
+
+	verbose("\n");
+}
+
diff --git a/arch/arm/kernel/kprobes-test-thumb.c b/arch/arm/kernel/kprobes-test-thumb.c
new file mode 100644
index 00000000000..5d8b8579222
--- /dev/null
+++ b/arch/arm/kernel/kprobes-test-thumb.c
@@ -0,0 +1,1187 @@
+/*
+ * arch/arm/kernel/kprobes-test-thumb.c
+ *
+ * Copyright (C) 2011 Jon Medhurst <tixy@yxit.co.uk>.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include "kprobes-test.h"
+
+
+#define TEST_ISA "16"
+
+#define DONT_TEST_IN_ITBLOCK(tests)			\
+	kprobe_test_flags |= TEST_FLAG_NO_ITBLOCK;	\
+	tests						\
+	kprobe_test_flags &= ~TEST_FLAG_NO_ITBLOCK;
+
+#define CONDITION_INSTRUCTIONS(cc_pos, tests)		\
+	kprobe_test_cc_position = cc_pos;		\
+	DONT_TEST_IN_ITBLOCK(tests)			\
+	kprobe_test_cc_position = 0;
+
+#define TEST_ITBLOCK(code)				\
+	kprobe_test_flags |= TEST_FLAG_FULL_ITBLOCK;	\
+	TESTCASE_START(code)				\
+	TEST_ARG_END("")				\
+	"50:	nop			\n\t"		\
+	"1:	"code"			\n\t"		\
+	"	mov r1, #0x11		\n\t"		\
+	"	mov r2, #0x22		\n\t"		\
+	"	mov r3, #0x33		\n\t"		\
+	"2:	nop			\n\t"		\
+	TESTCASE_END					\
+	kprobe_test_flags &= ~TEST_FLAG_FULL_ITBLOCK;
+
+#define TEST_THUMB_TO_ARM_INTERWORK_P(code1, reg, val, code2)	\
+	TESTCASE_START(code1 #reg code2)			\
+	TEST_ARG_PTR(reg, val)					\
+	TEST_ARG_REG(14, 99f+1)					\
+	TEST_ARG_MEM(15, 3f)					\
+	TEST_ARG_END("")					\
+	"	nop			\n\t" /* To align 1f */	\
+	"50:	nop			\n\t"			\
+	"1:	"code1 #reg code2"	\n\t"			\
+	"	bx	lr		\n\t"			\
+	".arm				\n\t"			\
+	"3:	adr	lr, 2f+1	\n\t"			\
+	"	bx	lr		\n\t"			\
+	".thumb				\n\t"			\
+	"2:	nop			\n\t"			\
+	TESTCASE_END
+
+
+void kprobe_thumb16_test_cases(void)
+{
+	kprobe_test_flags = TEST_FLAG_NARROW_INSTR;
+
+	TEST_GROUP("Shift (immediate), add, subtract, move, and compare")
+
+	TEST_R(    "lsls	r7, r",0,VAL1,", #5")
+	TEST_R(    "lsls	r0, r",7,VAL2,", #11")
+	TEST_R(    "lsrs	r7, r",0,VAL1,", #5")
+	TEST_R(    "lsrs	r0, r",7,VAL2,", #11")
+	TEST_R(    "asrs	r7, r",0,VAL1,", #5")
+	TEST_R(    "asrs	r0, r",7,VAL2,", #11")
+	TEST_RR(   "adds	r2, r",0,VAL1,", r",7,VAL2,"")
+	TEST_RR(   "adds	r5, r",7,VAL2,", r",0,VAL2,"")
+	TEST_RR(   "subs	r2, r",0,VAL1,", r",7,VAL2,"")
+	TEST_RR(   "subs	r5, r",7,VAL2,", r",0,VAL2,"")
+	TEST_R(    "adds	r7, r",0,VAL1,", #5")
+	TEST_R(    "adds	r0, r",7,VAL2,", #2")
+	TEST_R(    "subs	r7, r",0,VAL1,", #5")
+	TEST_R(    "subs	r0, r",7,VAL2,", #2")
+	TEST(      "movs.n	r0, #0x5f")
+	TEST(      "movs.n	r7, #0xa0")
+	TEST_R(    "cmp.n	r",0,0x5e, ", #0x5f")
+	TEST_R(    "cmp.n	r",5,0x15f,", #0x5f")
+	TEST_R(    "cmp.n	r",7,0xa0, ", #0xa0")
+	TEST_R(    "adds.n	r",0,VAL1,", #0x5f")
+	TEST_R(    "adds.n	r",7,VAL2,", #0xa0")
+	TEST_R(    "subs.n	r",0,VAL1,", #0x5f")
+	TEST_R(    "subs.n	r",7,VAL2,", #0xa0")
+
+	TEST_GROUP("16-bit Thumb data-processing instructions")
+
+#define DATA_PROCESSING16(op,val)			\
+	TEST_RR(   op"	r",0,VAL1,", r",7,val,"")	\
+	TEST_RR(   op"	r",7,VAL2,", r",0,val,"")
+
+	DATA_PROCESSING16("ands",0xf00f00ff)
+	DATA_PROCESSING16("eors",0xf00f00ff)
+	DATA_PROCESSING16("lsls",11)
+	DATA_PROCESSING16("lsrs",11)
+	DATA_PROCESSING16("asrs",11)
+	DATA_PROCESSING16("adcs",VAL2)
+	DATA_PROCESSING16("sbcs",VAL2)
+	DATA_PROCESSING16("rors",11)
+	DATA_PROCESSING16("tst",0xf00f00ff)
+	TEST_R("rsbs	r",0,VAL1,", #0")
+	TEST_R("rsbs	r",7,VAL2,", #0")
+	DATA_PROCESSING16("cmp",0xf00f00ff)
+	DATA_PROCESSING16("cmn",0xf00f00ff)
+	DATA_PROCESSING16("orrs",0xf00f00ff)
+	DATA_PROCESSING16("muls",VAL2)
+	DATA_PROCESSING16("bics",0xf00f00ff)
+	DATA_PROCESSING16("mvns",VAL2)
+
+	TEST_GROUP("Special data instructions and branch and exchange")
+
+	TEST_RR(  "add	r",0, VAL1,", r",7,VAL2,"")
+	TEST_RR(  "add	r",3, VAL2,", r",8,VAL3,"")
+	TEST_RR(  "add	r",8, VAL3,", r",0,VAL1,"")
+	TEST_R(   "add	sp"        ", r",8,-8,  "")
+	TEST_R(   "add	r",14,VAL1,", pc")
+	TEST_BF_R("add	pc"        ", r",0,2f-1f-8,"")
+	TEST_UNSUPPORTED(".short 0x44ff	@ add pc, pc")
+
+	TEST_RR(  "cmp	r",3,VAL1,", r",8,VAL2,"")
+	TEST_RR(  "cmp	r",8,VAL2,", r",0,VAL1,"")
+	TEST_R(   "cmp	sp"       ", r",8,-8,  "")
+
+	TEST_R(   "mov	r0, r",7,VAL2,"")
+	TEST_R(   "mov	r3, r",8,VAL3,"")
+	TEST_R(   "mov	r8, r",0,VAL1,"")
+	TEST_P(   "mov	sp, r",8,-8,  "")
+	TEST(     "mov	lr, pc")
+	TEST_BF_R("mov	pc, r",0,2f,  "")
+
+	TEST_BF_R("bx	r",0, 2f+1,"")
+	TEST_BF_R("bx	r",14,2f+1,"")
+	TESTCASE_START("bx	pc")
+		TEST_ARG_REG(14, 99f+1)
+		TEST_ARG_END("")
+		"	nop			\n\t" /* To align the bx pc*/
+		"50:	nop			\n\t"
+		"1:	bx	pc		\n\t"
+		"	bx	lr		\n\t"
+		".arm				\n\t"
+		"	adr	lr, 2f+1	\n\t"
+		"	bx	lr		\n\t"
+		".thumb				\n\t"
+		"2:	nop			\n\t"
+	TESTCASE_END
+
+	TEST_BF_R("blx	r",0, 2f+1,"")
+	TEST_BB_R("blx	r",14,2f+1,"")
+	TEST_UNSUPPORTED(".short 0x47f8	@ blx pc")
+
+	TEST_GROUP("Load from Literal Pool")
+
+	TEST_X( "ldr	r0, 3f",
+		".align					\n\t"
+		"3:	.word	"__stringify(VAL1))
+	TEST_X( "ldr	r7, 3f",
+		".space 128				\n\t"
+		".align					\n\t"
+		"3:	.word	"__stringify(VAL2))
+
+	TEST_GROUP("16-bit Thumb Load/store instructions")
+
+	TEST_RPR("str	r",0, VAL1,", [r",1, 24,", r",2,  48,"]")
+	TEST_RPR("str	r",7, VAL2,", [r",6, 24,", r",5,  48,"]")
+	TEST_RPR("strh	r",0, VAL1,", [r",1, 24,", r",2,  48,"]")
+	TEST_RPR("strh	r",7, VAL2,", [r",6, 24,", r",5,  48,"]")
+	TEST_RPR("strb	r",0, VAL1,", [r",1, 24,", r",2,  48,"]")
+	TEST_RPR("strb	r",7, VAL2,", [r",6, 24,", r",5,  48,"]")
+	TEST_PR( "ldrsb	r0, [r",1, 24,", r",2,  48,"]")
+	TEST_PR( "ldrsb	r7, [r",6, 24,", r",5,  50,"]")
+	TEST_PR( "ldr	r0, [r",1, 24,", r",2,  48,"]")
+	TEST_PR( "ldr	r7, [r",6, 24,", r",5,  48,"]")
+	TEST_PR( "ldrh	r0, [r",1, 24,", r",2,  48,"]")
+	TEST_PR( "ldrh	r7, [r",6, 24,", r",5,  50,"]")
+	TEST_PR( "ldrb	r0, [r",1, 24,", r",2,  48,"]")
+	TEST_PR( "ldrb	r7, [r",6, 24,", r",5,  50,"]")
+	TEST_PR( "ldrsh	r0, [r",1, 24,", r",2,  48,"]")
+	TEST_PR( "ldrsh	r7, [r",6, 24,", r",5,  50,"]")
+
+	TEST_RP("str	r",0, VAL1,", [r",1, 24,", #120]")
+	TEST_RP("str	r",7, VAL2,", [r",6, 24,", #120]")
+	TEST_P( "ldr	r0, [r",1, 24,", #120]")
+	TEST_P( "ldr	r7, [r",6, 24,", #120]")
+	TEST_RP("strb	r",0, VAL1,", [r",1, 24,", #30]")
+	TEST_RP("strb	r",7, VAL2,", [r",6, 24,", #30]")
+	TEST_P( "ldrb	r0, [r",1, 24,", #30]")
+	TEST_P( "ldrb	r7, [r",6, 24,", #30]")
+	TEST_RP("strh	r",0, VAL1,", [r",1, 24,", #60]")
+	TEST_RP("strh	r",7, VAL2,", [r",6, 24,", #60]")
+	TEST_P( "ldrh	r0, [r",1, 24,", #60]")
+	TEST_P( "ldrh	r7, [r",6, 24,", #60]")
+
+	TEST_R( "str	r",0, VAL1,", [sp, #0]")
+	TEST_R( "str	r",7, VAL2,", [sp, #160]")
+	TEST(   "ldr	r0, [sp, #0]")
+	TEST(   "ldr	r7, [sp, #160]")
+
+	TEST_RP("str	r",0, VAL1,", [r",0, 24,"]")
+	TEST_P( "ldr	r0, [r",0, 24,"]")
+
+	TEST_GROUP("Generate PC-/SP-relative address")
+
+	TEST("add	r0, pc, #4")
+	TEST("add	r7, pc, #1020")
+	TEST("add	r0, sp, #4")
+	TEST("add	r7, sp, #1020")
+
+	TEST_GROUP("Miscellaneous 16-bit instructions")
+
+	TEST_UNSUPPORTED( "cpsie	i")
+	TEST_UNSUPPORTED( "cpsid	i")
+	TEST_UNSUPPORTED( "setend	le")
+	TEST_UNSUPPORTED( "setend	be")
+
+	TEST("add	sp, #"__stringify(TEST_MEMORY_SIZE)) /* Assumes TEST_MEMORY_SIZE < 0x400 */
+	TEST("sub	sp, #0x7f*4")
+
+DONT_TEST_IN_ITBLOCK(
+	TEST_BF_R(  "cbnz	r",0,0, ", 2f")
+	TEST_BF_R(  "cbz	r",2,-1,", 2f")
+	TEST_BF_RX( "cbnz	r",4,1, ", 2f", SPACE_0x20)
+	TEST_BF_RX( "cbz	r",7,0, ", 2f", SPACE_0x40)
+)
+	TEST_R("sxth	r0, r",7, HH1,"")
+	TEST_R("sxth	r7, r",0, HH2,"")
+	TEST_R("sxtb	r0, r",7, HH1,"")
+	TEST_R("sxtb	r7, r",0, HH2,"")
+	TEST_R("uxth	r0, r",7, HH1,"")
+	TEST_R("uxth	r7, r",0, HH2,"")
+	TEST_R("uxtb	r0, r",7, HH1,"")
+	TEST_R("uxtb	r7, r",0, HH2,"")
+	TEST_R("rev	r0, r",7, VAL1,"")
+	TEST_R("rev	r7, r",0, VAL2,"")
+	TEST_R("rev16	r0, r",7, VAL1,"")
+	TEST_R("rev16	r7, r",0, VAL2,"")
+	TEST_UNSUPPORTED(".short 0xba80")
+	TEST_UNSUPPORTED(".short 0xbabf")
+	TEST_R("revsh	r0, r",7, VAL1,"")
+	TEST_R("revsh	r7, r",0, VAL2,"")
+
+#define TEST_POPPC(code, offset)	\
+	TESTCASE_START(code)		\
+	TEST_ARG_PTR(13, offset)	\
+	TEST_ARG_END("")		\
+	TEST_BRANCH_F(code)		\
+	TESTCASE_END
+
+	TEST("push	{r0}")
+	TEST("push	{r7}")
+	TEST("push	{r14}")
+	TEST("push	{r0-r7,r14}")
+	TEST("push	{r0,r2,r4,r6,r14}")
+	TEST("push	{r1,r3,r5,r7}")
+	TEST("pop	{r0}")
+	TEST("pop	{r7}")
+	TEST("pop	{r0,r2,r4,r6}")
+	TEST_POPPC("pop	{pc}",15*4)
+	TEST_POPPC("pop	{r0-r7,pc}",7*4)
+	TEST_POPPC("pop	{r1,r3,r5,r7,pc}",11*4)
+	TEST_THUMB_TO_ARM_INTERWORK_P("pop	{pc}	@ ",13,15*4,"")
+	TEST_THUMB_TO_ARM_INTERWORK_P("pop	{r0-r7,pc}	@ ",13,7*4,"")
+
+	TEST_UNSUPPORTED("bkpt.n	0")
+	TEST_UNSUPPORTED("bkpt.n	255")
+
+	TEST_SUPPORTED("yield")
+	TEST("sev")
+	TEST("nop")
+	TEST("wfi")
+	TEST_SUPPORTED("wfe")
+	TEST_UNSUPPORTED(".short 0xbf50") /* Unassigned hints */
+	TEST_UNSUPPORTED(".short 0xbff0") /* Unassigned hints */
+
+#define TEST_IT(code, code2)			\
+	TESTCASE_START(code)			\
+	TEST_ARG_END("")			\
+	"50:	nop			\n\t"	\
+	"1:	"code"			\n\t"	\
+	"	"code2"			\n\t"	\
+	"2:	nop			\n\t"	\
+	TESTCASE_END
+
+DONT_TEST_IN_ITBLOCK(
+	TEST_IT("it	eq","moveq r0,#0")
+	TEST_IT("it	vc","movvc r0,#0")
+	TEST_IT("it	le","movle r0,#0")
+	TEST_IT("ite	eq","moveq r0,#0\n\t  movne r1,#1")
+	TEST_IT("itet	vc","movvc r0,#0\n\t  movvs r1,#1\n\t  movvc r2,#2")
+	TEST_IT("itete	le","movle r0,#0\n\t  movgt r1,#1\n\t  movle r2,#2\n\t  movgt r3,#3")
+	TEST_IT("itttt	le","movle r0,#0\n\t  movle r1,#1\n\t  movle r2,#2\n\t  movle r3,#3")
+	TEST_IT("iteee	le","movle r0,#0\n\t  movgt r1,#1\n\t  movgt r2,#2\n\t  movgt r3,#3")
+)
+
+	TEST_GROUP("Load and store multiple")
+
+	TEST_P("ldmia	r",4, 16*4,"!, {r0,r7}")
+	TEST_P("ldmia	r",7, 16*4,"!, {r0-r6}")
+	TEST_P("stmia	r",4, 16*4,"!, {r0,r7}")
+	TEST_P("stmia	r",0, 16*4,"!, {r0-r7}")
+
+	TEST_GROUP("Conditional branch and Supervisor Call instructions")
+
+CONDITION_INSTRUCTIONS(8,
+	TEST_BF("beq	2f")
+	TEST_BB("bne	2b")
+	TEST_BF("bgt	2f")
+	TEST_BB("blt	2b")
+)
+	TEST_UNSUPPORTED(".short 0xde00")
+	TEST_UNSUPPORTED(".short 0xdeff")
+	TEST_UNSUPPORTED("svc	#0x00")
+	TEST_UNSUPPORTED("svc	#0xff")
+
+	TEST_GROUP("Unconditional branch")
+
+	TEST_BF(  "b	2f")
+	TEST_BB(  "b	2b")
+	TEST_BF_X("b	2f", SPACE_0x400)
+	TEST_BB_X("b	2b", SPACE_0x400)
+
+	TEST_GROUP("Testing instructions in IT blocks")
+
+	TEST_ITBLOCK("subs.n r0, r0")
+
+	verbose("\n");
+}
+
+
+void kprobe_thumb32_test_cases(void)
+{
+	kprobe_test_flags = 0;
+
+	TEST_GROUP("Load/store multiple")
+
+	TEST_UNSUPPORTED("rfedb	sp")
+	TEST_UNSUPPORTED("rfeia	sp")
+	TEST_UNSUPPORTED("rfedb	sp!")
+	TEST_UNSUPPORTED("rfeia	sp!")
+
+	TEST_P(   "stmia	r",0, 16*4,", {r0,r8}")
+	TEST_P(   "stmia	r",4, 16*4,", {r0-r12,r14}")
+	TEST_P(   "stmia	r",7, 16*4,"!, {r8-r12,r14}")
+	TEST_P(   "stmia	r",12,16*4,"!, {r1,r3,r5,r7,r8-r11,r14}")
+
+	TEST_P(   "ldmia	r",0, 16*4,", {r0,r8}")
+	TEST_P(   "ldmia	r",4, 0,   ", {r0-r12,r14}")
+	TEST_BF_P("ldmia	r",5, 8*4, "!, {r6-r12,r15}")
+	TEST_P(   "ldmia	r",12,16*4,"!, {r1,r3,r5,r7,r8-r11,r14}")
+	TEST_BF_P("ldmia	r",14,14*4,"!, {r4,pc}")
+
+	TEST_P(   "stmdb	r",0, 16*4,", {r0,r8}")
+	TEST_P(   "stmdb	r",4, 16*4,", {r0-r12,r14}")
+	TEST_P(   "stmdb	r",5, 16*4,"!, {r8-r12,r14}")
+	TEST_P(   "stmdb	r",12,16*4,"!, {r1,r3,r5,r7,r8-r11,r14}")
+
+	TEST_P(   "ldmdb	r",0, 16*4,", {r0,r8}")
+	TEST_P(   "ldmdb	r",4, 16*4,", {r0-r12,r14}")
+	TEST_BF_P("ldmdb	r",5, 16*4,"!, {r6-r12,r15}")
+	TEST_P(   "ldmdb	r",12,16*4,"!, {r1,r3,r5,r7,r8-r11,r14}")
+	TEST_BF_P("ldmdb	r",14,16*4,"!, {r4,pc}")
+
+	TEST_P(   "stmdb	r",13,16*4,"!, {r3-r12,lr}")
+	TEST_P(	  "stmdb	r",13,16*4,"!, {r3-r12}")
+	TEST_P(   "stmdb	r",2, 16*4,", {r3-r12,lr}")
+	TEST_P(   "stmdb	r",13,16*4,"!, {r2-r12,lr}")
+	TEST_P(   "stmdb	r",0, 16*4,", {r0-r12}")
+	TEST_P(   "stmdb	r",0, 16*4,", {r0-r12,lr}")
+
+	TEST_BF_P("ldmia	r",13,5*4, "!, {r3-r12,pc}")
+	TEST_P(	  "ldmia	r",13,5*4, "!, {r3-r12}")
+	TEST_BF_P("ldmia	r",2, 5*4, "!, {r3-r12,pc}")
+	TEST_BF_P("ldmia	r",13,4*4, "!, {r2-r12,pc}")
+	TEST_P(   "ldmia	r",0, 16*4,", {r0-r12}")
+	TEST_P(   "ldmia	r",0, 16*4,", {r0-r12,lr}")
+
+	TEST_THUMB_TO_ARM_INTERWORK_P("ldmia	r",0,14*4,", {r12,pc}")
+	TEST_THUMB_TO_ARM_INTERWORK_P("ldmia	r",13,2*4,", {r0-r12,pc}")
+
+	TEST_UNSUPPORTED(".short 0xe88f,0x0101	@ stmia	pc, {r0,r8}")
+	TEST_UNSUPPORTED(".short 0xe92f,0x5f00	@ stmdb	pc!, {r8-r12,r14}")
+	TEST_UNSUPPORTED(".short 0xe8bd,0xc000	@ ldmia	r13!, {r14,pc}")
+	TEST_UNSUPPORTED(".short 0xe93e,0xc000	@ ldmdb	r14!, {r14,pc}")
+	TEST_UNSUPPORTED(".short 0xe8a7,0x3f00	@ stmia	r7!, {r8-r12,sp}")
+	TEST_UNSUPPORTED(".short 0xe8a7,0x9f00	@ stmia	r7!, {r8-r12,pc}")
+	TEST_UNSUPPORTED(".short 0xe93e,0x2010	@ ldmdb	r14!, {r4,sp}")
+
+	TEST_GROUP("Load/store double or exclusive, table branch")
+
+	TEST_P(  "ldrd	r0, r1, [r",1, 24,", #-16]")
+	TEST(    "ldrd	r12, r14, [sp, #16]")
+	TEST_P(  "ldrd	r1, r0, [r",7, 24,", #-16]!")
+	TEST(    "ldrd	r14, r12, [sp, #16]!")
+	TEST_P(  "ldrd	r1, r0, [r",7, 24,"], #16")
+	TEST(    "ldrd	r7, r8, [sp], #-16")
+
+	TEST_X( "ldrd	r12, r14, 3f",
+		".align 3				\n\t"
+		"3:	.word	"__stringify(VAL1)"	\n\t"
+		"	.word	"__stringify(VAL2))
+
+	TEST_UNSUPPORTED(".short 0xe9ff,0xec04	@ ldrd	r14, r12, [pc, #16]!")
+	TEST_UNSUPPORTED(".short 0xe8ff,0xec04	@ ldrd	r14, r12, [pc], #16")
+	TEST_UNSUPPORTED(".short 0xe9d4,0xd800	@ ldrd	sp, r8, [r4]")
+	TEST_UNSUPPORTED(".short 0xe9d4,0xf800	@ ldrd	pc, r8, [r4]")
+	TEST_UNSUPPORTED(".short 0xe9d4,0x7d00	@ ldrd	r7, sp, [r4]")
+	TEST_UNSUPPORTED(".short 0xe9d4,0x7f00	@ ldrd	r7, pc, [r4]")
+
+	TEST_RRP("strd	r",0, VAL1,", r",1, VAL2,", [r",1, 24,", #-16]")
+	TEST_RR( "strd	r",12,VAL2,", r",14,VAL1,", [sp, #16]")
+	TEST_RRP("strd	r",1, VAL1,", r",0, VAL2,", [r",7, 24,", #-16]!")
+	TEST_RR( "strd	r",14,VAL2,", r",12,VAL1,", [sp, #16]!")
+	TEST_RRP("strd	r",1, VAL1,", r",0, VAL2,", [r",7, 24,"], #16")
+	TEST_RR( "strd	r",7, VAL2,", r",8, VAL1,", [sp], #-16")
+	TEST_UNSUPPORTED(".short 0xe9ef,0xec04	@ strd	r14, r12, [pc, #16]!")
+	TEST_UNSUPPORTED(".short 0xe8ef,0xec04	@ strd	r14, r12, [pc], #16")
+
+	TEST_RX("tbb	[pc, r",0, (9f-(1f+4)),"]",
+		"9:			\n\t"
+		".byte	(2f-1b-4)>>1	\n\t"
+		".byte	(3f-1b-4)>>1	\n\t"
+		"3:	mvn	r0, r0	\n\t"
+		"2:	nop		\n\t")
+
+	TEST_RX("tbb	[pc, r",4, (9f-(1f+4)+1),"]",
+		"9:			\n\t"
+		".byte	(2f-1b-4)>>1	\n\t"
+		".byte	(3f-1b-4)>>1	\n\t"
+		"3:	mvn	r0, r0	\n\t"
+		"2:	nop		\n\t")
+
+	TEST_RRX("tbb	[r",1,9f,", r",2,0,"]",
+		"9:			\n\t"
+		".byte	(2f-1b-4)>>1	\n\t"
+		".byte	(3f-1b-4)>>1	\n\t"
+		"3:	mvn	r0, r0	\n\t"
+		"2:	nop		\n\t")
+
+	TEST_RX("tbh	[pc, r",7, (9f-(1f+4))>>1,"]",
+		"9:			\n\t"
+		".short	(2f-1b-4)>>1	\n\t"
+		".short	(3f-1b-4)>>1	\n\t"
+		"3:	mvn	r0, r0	\n\t"
+		"2:	nop		\n\t")
+
+	TEST_RX("tbh	[pc, r",12, ((9f-(1f+4))>>1)+1,"]",
+		"9:			\n\t"
+		".short	(2f-1b-4)>>1	\n\t"
+		".short	(3f-1b-4)>>1	\n\t"
+		"3:	mvn	r0, r0	\n\t"
+		"2:	nop		\n\t")
+
+	TEST_RRX("tbh	[r",1,9f, ", r",14,1,"]",
+		"9:			\n\t"
+		".short	(2f-1b-4)>>1	\n\t"
+		".short	(3f-1b-4)>>1	\n\t"
+		"3:	mvn	r0, r0	\n\t"
+		"2:	nop		\n\t")
+
+	TEST_UNSUPPORTED(".short 0xe8d1,0xf01f	@ tbh [r1, pc]")
+	TEST_UNSUPPORTED(".short 0xe8d1,0xf01d	@ tbh [r1, sp]")
+	TEST_UNSUPPORTED(".short 0xe8dd,0xf012	@ tbh [sp, r2]")
+
+	TEST_UNSUPPORTED("strexb	r0, r1, [r2]")
+	TEST_UNSUPPORTED("strexh	r0, r1, [r2]")
+	TEST_UNSUPPORTED("strexd	r0, r1, [r2]")
+	TEST_UNSUPPORTED("ldrexb	r0, [r1]")
+	TEST_UNSUPPORTED("ldrexh	r0, [r1]")
+	TEST_UNSUPPORTED("ldrexd	r0, [r1]")
+
+	TEST_GROUP("Data-processing (shifted register) and (modified immediate)")
+
+#define _DATA_PROCESSING32_DNM(op,s,val)					\
+	TEST_RR(op s".w	r0,  r",1, VAL1,", r",2, val, "")			\
+	TEST_RR(op s"	r1,  r",1, VAL1,", r",2, val, ", lsl #3")		\
+	TEST_RR(op s"	r2,  r",3, VAL1,", r",2, val, ", lsr #4")		\
+	TEST_RR(op s"	r3,  r",3, VAL1,", r",2, val, ", asr #5")		\
+	TEST_RR(op s"	r4,  r",5, VAL1,", r",2, N(val),", asr #6")		\
+	TEST_RR(op s"	r5,  r",5, VAL1,", r",2, val, ", ror #7")		\
+	TEST_RR(op s"	r8,  r",9, VAL1,", r",10,val, ", rrx")			\
+	TEST_R( op s"	r0,  r",11,VAL1,", #0x00010001")			\
+	TEST_R( op s"	r11, r",0, VAL1,", #0xf5000000")			\
+	TEST_R( op s"	r7,  r",8, VAL2,", #0x000af000")
+
+#define DATA_PROCESSING32_DNM(op,val)		\
+	_DATA_PROCESSING32_DNM(op,"",val)	\
+	_DATA_PROCESSING32_DNM(op,"s",val)
+
+#define DATA_PROCESSING32_NM(op,val)					\
+	TEST_RR(op".w	r",1, VAL1,", r",2, val, "")			\
+	TEST_RR(op"	r",1, VAL1,", r",2, val, ", lsl #3")		\
+	TEST_RR(op"	r",3, VAL1,", r",2, val, ", lsr #4")		\
+	TEST_RR(op"	r",3, VAL1,", r",2, val, ", asr #5")		\
+	TEST_RR(op"	r",5, VAL1,", r",2, N(val),", asr #6")		\
+	TEST_RR(op"	r",5, VAL1,", r",2, val, ", ror #7")		\
+	TEST_RR(op"	r",9, VAL1,", r",10,val, ", rrx")		\
+	TEST_R( op"	r",11,VAL1,", #0x00010001")			\
+	TEST_R( op"	r",0, VAL1,", #0xf5000000")			\
+	TEST_R( op"	r",8, VAL2,", #0x000af000")
+
+#define _DATA_PROCESSING32_DM(op,s,val)				\
+	TEST_R( op s".w	r0,  r",14, val, "")			\
+	TEST_R( op s"	r1,  r",12, val, ", lsl #3")		\
+	TEST_R( op s"	r2,  r",11, val, ", lsr #4")		\
+	TEST_R( op s"	r3,  r",10, val, ", asr #5")		\
+	TEST_R( op s"	r4,  r",9, N(val),", asr #6")		\
+	TEST_R( op s"	r5,  r",8, val, ", ror #7")		\
+	TEST_R( op s"	r8,  r",7,val, ", rrx")			\
+	TEST(   op s"	r0,  #0x00010001")			\
+	TEST(   op s"	r11, #0xf5000000")			\
+	TEST(   op s"	r7,  #0x000af000")			\
+	TEST(   op s"	r4,  #0x00005a00")
+
+#define DATA_PROCESSING32_DM(op,val)		\
+	_DATA_PROCESSING32_DM(op,"",val)	\
+	_DATA_PROCESSING32_DM(op,"s",val)
+
+	DATA_PROCESSING32_DNM("and",0xf00f00ff)
+	DATA_PROCESSING32_NM("tst",0xf00f00ff)
+	DATA_PROCESSING32_DNM("bic",0xf00f00ff)
+	DATA_PROCESSING32_DNM("orr",0xf00f00ff)
+	DATA_PROCESSING32_DM("mov",VAL2)
+	DATA_PROCESSING32_DNM("orn",0xf00f00ff)
+	DATA_PROCESSING32_DM("mvn",VAL2)
+	DATA_PROCESSING32_DNM("eor",0xf00f00ff)
+	DATA_PROCESSING32_NM("teq",0xf00f00ff)
+	DATA_PROCESSING32_DNM("add",VAL2)
+	DATA_PROCESSING32_NM("cmn",VAL2)
+	DATA_PROCESSING32_DNM("adc",VAL2)
+	DATA_PROCESSING32_DNM("sbc",VAL2)
+	DATA_PROCESSING32_DNM("sub",VAL2)
+	DATA_PROCESSING32_NM("cmp",VAL2)
+	DATA_PROCESSING32_DNM("rsb",VAL2)
+
+	TEST_RR("pkhbt	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR("pkhbt	r14,r",12, HH1,", r",10,HH2,", lsl #2")
+	TEST_RR("pkhtb	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR("pkhtb	r14,r",12, HH1,", r",10,HH2,", asr #2")
+
+	TEST_UNSUPPORTED(".short 0xea17,0x0f0d	@ tst.w r7, sp")
+	TEST_UNSUPPORTED(".short 0xea17,0x0f0f	@ tst.w r7, pc")
+	TEST_UNSUPPORTED(".short 0xea1d,0x0f07	@ tst.w sp, r7")
+	TEST_UNSUPPORTED(".short 0xea1f,0x0f07	@ tst.w pc, r7")
+	TEST_UNSUPPORTED(".short 0xf01d,0x1f08	@ tst sp, #0x00080008")
+	TEST_UNSUPPORTED(".short 0xf01f,0x1f08	@ tst pc, #0x00080008")
+
+	TEST_UNSUPPORTED(".short 0xea97,0x0f0d	@ teq.w r7, sp")
+	TEST_UNSUPPORTED(".short 0xea97,0x0f0f	@ teq.w r7, pc")
+	TEST_UNSUPPORTED(".short 0xea9d,0x0f07	@ teq.w sp, r7")
+	TEST_UNSUPPORTED(".short 0xea9f,0x0f07	@ teq.w pc, r7")
+	TEST_UNSUPPORTED(".short 0xf09d,0x1f08	@ tst sp, #0x00080008")
+	TEST_UNSUPPORTED(".short 0xf09f,0x1f08	@ tst pc, #0x00080008")
+
+	TEST_UNSUPPORTED(".short 0xeb17,0x0f0d	@ cmn.w r7, sp")
+	TEST_UNSUPPORTED(".short 0xeb17,0x0f0f	@ cmn.w r7, pc")
+	TEST_P("cmn.w	sp, r",7,0,"")
+	TEST_UNSUPPORTED(".short 0xeb1f,0x0f07	@ cmn.w pc, r7")
+	TEST(  "cmn	sp, #0x00080008")
+	TEST_UNSUPPORTED(".short 0xf11f,0x1f08	@ cmn pc, #0x00080008")
+
+	TEST_UNSUPPORTED(".short 0xebb7,0x0f0d	@ cmp.w r7, sp")
+	TEST_UNSUPPORTED(".short 0xebb7,0x0f0f	@ cmp.w r7, pc")
+	TEST_P("cmp.w	sp, r",7,0,"")
+	TEST_UNSUPPORTED(".short 0xebbf,0x0f07	@ cmp.w pc, r7")
+	TEST(  "cmp	sp, #0x00080008")
+	TEST_UNSUPPORTED(".short 0xf1bf,0x1f08	@ cmp pc, #0x00080008")
+
+	TEST_UNSUPPORTED(".short 0xea5f,0x070d	@ movs.w r7, sp")
+	TEST_UNSUPPORTED(".short 0xea5f,0x070f	@ movs.w r7, pc")
+	TEST_UNSUPPORTED(".short 0xea5f,0x0d07	@ movs.w sp, r7")
+	TEST_UNSUPPORTED(".short 0xea4f,0x0f07	@ mov.w  pc, r7")
+	TEST_UNSUPPORTED(".short 0xf04f,0x1d08	@ mov sp, #0x00080008")
+	TEST_UNSUPPORTED(".short 0xf04f,0x1f08	@ mov pc, #0x00080008")
+
+	TEST_R("add.w	r0, sp, r",1, 4,"")
+	TEST_R("adds	r0, sp, r",1, 4,", asl #3")
+	TEST_R("add	r0, sp, r",1, 4,", asl #4")
+	TEST_R("add	r0, sp, r",1, 16,", ror #1")
+	TEST_R("add.w	sp, sp, r",1, 4,"")
+	TEST_R("add	sp, sp, r",1, 4,", asl #3")
+	TEST_UNSUPPORTED(".short 0xeb0d,0x1d01	@ add sp, sp, r1, asl #4")
+	TEST_UNSUPPORTED(".short 0xeb0d,0x0d71	@ add sp, sp, r1, ror #1")
+	TEST(  "add.w	r0, sp, #24")
+	TEST(  "add.w	sp, sp, #24")
+	TEST_UNSUPPORTED(".short 0xeb0d,0x0f01	@ add pc, sp, r1")
+	TEST_UNSUPPORTED(".short 0xeb0d,0x000f	@ add r0, sp, pc")
+	TEST_UNSUPPORTED(".short 0xeb0d,0x000d	@ add r0, sp, sp")
+	TEST_UNSUPPORTED(".short 0xeb0d,0x0d0f	@ add sp, sp, pc")
+	TEST_UNSUPPORTED(".short 0xeb0d,0x0d0d	@ add sp, sp, sp")
+
+	TEST_R("sub.w	r0, sp, r",1, 4,"")
+	TEST_R("subs	r0, sp, r",1, 4,", asl #3")
+	TEST_R("sub	r0, sp, r",1, 4,", asl #4")
+	TEST_R("sub	r0, sp, r",1, 16,", ror #1")
+	TEST_R("sub.w	sp, sp, r",1, 4,"")
+	TEST_R("sub	sp, sp, r",1, 4,", asl #3")
+	TEST_UNSUPPORTED(".short 0xebad,0x1d01	@ sub sp, sp, r1, asl #4")
+	TEST_UNSUPPORTED(".short 0xebad,0x0d71	@ sub sp, sp, r1, ror #1")
+	TEST_UNSUPPORTED(".short 0xebad,0x0f01	@ sub pc, sp, r1")
+	TEST(  "sub.w	r0, sp, #24")
+	TEST(  "sub.w	sp, sp, #24")
+
+	TEST_UNSUPPORTED(".short 0xea02,0x010f	@ and r1, r2, pc")
+	TEST_UNSUPPORTED(".short 0xea0f,0x0103	@ and r1, pc, r3")
+	TEST_UNSUPPORTED(".short 0xea02,0x0f03	@ and pc, r2, r3")
+	TEST_UNSUPPORTED(".short 0xea02,0x010d	@ and r1, r2, sp")
+	TEST_UNSUPPORTED(".short 0xea0d,0x0103	@ and r1, sp, r3")
+	TEST_UNSUPPORTED(".short 0xea02,0x0d03	@ and sp, r2, r3")
+	TEST_UNSUPPORTED(".short 0xf00d,0x1108	@ and r1, sp, #0x00080008")
+	TEST_UNSUPPORTED(".short 0xf00f,0x1108	@ and r1, pc, #0x00080008")
+	TEST_UNSUPPORTED(".short 0xf002,0x1d08	@ and sp, r8, #0x00080008")
+	TEST_UNSUPPORTED(".short 0xf002,0x1f08	@ and pc, r8, #0x00080008")
+
+	TEST_UNSUPPORTED(".short 0xeb02,0x010f	@ add r1, r2, pc")
+	TEST_UNSUPPORTED(".short 0xeb0f,0x0103	@ add r1, pc, r3")
+	TEST_UNSUPPORTED(".short 0xeb02,0x0f03	@ add pc, r2, r3")
+	TEST_UNSUPPORTED(".short 0xeb02,0x010d	@ add r1, r2, sp")
+	TEST_SUPPORTED(  ".short 0xeb0d,0x0103	@ add r1, sp, r3")
+	TEST_UNSUPPORTED(".short 0xeb02,0x0d03	@ add sp, r2, r3")
+	TEST_SUPPORTED(  ".short 0xf10d,0x1108	@ add r1, sp, #0x00080008")
+	TEST_UNSUPPORTED(".short 0xf10d,0x1f08	@ add pc, sp, #0x00080008")
+	TEST_UNSUPPORTED(".short 0xf10f,0x1108	@ add r1, pc, #0x00080008")
+	TEST_UNSUPPORTED(".short 0xf102,0x1d08	@ add sp, r8, #0x00080008")
+	TEST_UNSUPPORTED(".short 0xf102,0x1f08	@ add pc, r8, #0x00080008")
+
+	TEST_UNSUPPORTED(".short 0xeaa0,0x0000")
+	TEST_UNSUPPORTED(".short 0xeaf0,0x0000")
+	TEST_UNSUPPORTED(".short 0xeb20,0x0000")
+	TEST_UNSUPPORTED(".short 0xeb80,0x0000")
+	TEST_UNSUPPORTED(".short 0xebe0,0x0000")
+
+	TEST_UNSUPPORTED(".short 0xf0a0,0x0000")
+	TEST_UNSUPPORTED(".short 0xf0c0,0x0000")
+	TEST_UNSUPPORTED(".short 0xf0f0,0x0000")
+	TEST_UNSUPPORTED(".short 0xf120,0x0000")
+	TEST_UNSUPPORTED(".short 0xf180,0x0000")
+	TEST_UNSUPPORTED(".short 0xf1e0,0x0000")
+
+	TEST_GROUP("Coprocessor instructions")
+
+	TEST_UNSUPPORTED(".short 0xec00,0x0000")
+	TEST_UNSUPPORTED(".short 0xeff0,0x0000")
+	TEST_UNSUPPORTED(".short 0xfc00,0x0000")
+	TEST_UNSUPPORTED(".short 0xfff0,0x0000")
+
+	TEST_GROUP("Data-processing (plain binary immediate)")
+
+	TEST_R("addw	r0,  r",1, VAL1,", #0x123")
+	TEST(  "addw	r14, sp, #0xf5a")
+	TEST(  "addw	sp, sp, #0x20")
+	TEST(  "addw	r7,  pc, #0x888")
+	TEST_UNSUPPORTED(".short 0xf20f,0x1f20	@ addw pc, pc, #0x120")
+	TEST_UNSUPPORTED(".short 0xf20d,0x1f20	@ addw pc, sp, #0x120")
+	TEST_UNSUPPORTED(".short 0xf20f,0x1d20	@ addw sp, pc, #0x120")
+	TEST_UNSUPPORTED(".short 0xf200,0x1d20	@ addw sp, r0, #0x120")
+
+	TEST_R("subw	r0,  r",1, VAL1,", #0x123")
+	TEST(  "subw	r14, sp, #0xf5a")
+	TEST(  "subw	sp, sp, #0x20")
+	TEST(  "subw	r7,  pc, #0x888")
+	TEST_UNSUPPORTED(".short 0xf2af,0x1f20	@ subw pc, pc, #0x120")
+	TEST_UNSUPPORTED(".short 0xf2ad,0x1f20	@ subw pc, sp, #0x120")
+	TEST_UNSUPPORTED(".short 0xf2af,0x1d20	@ subw sp, pc, #0x120")
+	TEST_UNSUPPORTED(".short 0xf2a0,0x1d20	@ subw sp, r0, #0x120")
+
+	TEST("movw	r0, #0")
+	TEST("movw	r0, #0xffff")
+	TEST("movw	lr, #0xffff")
+	TEST_UNSUPPORTED(".short 0xf240,0x0d00	@ movw sp, #0")
+	TEST_UNSUPPORTED(".short 0xf240,0x0f00	@ movw pc, #0")
+
+	TEST_R("movt	r",0, VAL1,", #0")
+	TEST_R("movt	r",0, VAL2,", #0xffff")
+	TEST_R("movt	r",14,VAL1,", #0xffff")
+	TEST_UNSUPPORTED(".short 0xf2c0,0x0d00	@ movt sp, #0")
+	TEST_UNSUPPORTED(".short 0xf2c0,0x0f00	@ movt pc, #0")
+
+	TEST_R(     "ssat	r0, #24, r",0,   VAL1,"")
+	TEST_R(     "ssat	r14, #24, r",12, VAL2,"")
+	TEST_R(     "ssat	r0, #24, r",0,   VAL1,", lsl #8")
+	TEST_R(     "ssat	r14, #24, r",12, VAL2,", asr #8")
+	TEST_UNSUPPORTED(".short 0xf30c,0x0d17	@ ssat	sp, #24, r12")
+	TEST_UNSUPPORTED(".short 0xf30c,0x0f17	@ ssat	pc, #24, r12")
+	TEST_UNSUPPORTED(".short 0xf30d,0x0c17	@ ssat	r12, #24, sp")
+	TEST_UNSUPPORTED(".short 0xf30f,0x0c17	@ ssat	r12, #24, pc")
+
+	TEST_R(     "usat	r0, #24, r",0,   VAL1,"")
+	TEST_R(     "usat	r14, #24, r",12, VAL2,"")
+	TEST_R(     "usat	r0, #24, r",0,   VAL1,", lsl #8")
+	TEST_R(     "usat	r14, #24, r",12, VAL2,", asr #8")
+	TEST_UNSUPPORTED(".short 0xf38c,0x0d17	@ usat	sp, #24, r12")
+	TEST_UNSUPPORTED(".short 0xf38c,0x0f17	@ usat	pc, #24, r12")
+	TEST_UNSUPPORTED(".short 0xf38d,0x0c17	@ usat	r12, #24, sp")
+	TEST_UNSUPPORTED(".short 0xf38f,0x0c17	@ usat	r12, #24, pc")
+
+	TEST_R(     "ssat16	r0, #12, r",0,   HH1,"")
+	TEST_R(     "ssat16	r14, #12, r",12, HH2,"")
+	TEST_UNSUPPORTED(".short 0xf32c,0x0d0b	@ ssat16	sp, #12, r12")
+	TEST_UNSUPPORTED(".short 0xf32c,0x0f0b	@ ssat16	pc, #12, r12")
+	TEST_UNSUPPORTED(".short 0xf32d,0x0c0b	@ ssat16	r12, #12, sp")
+	TEST_UNSUPPORTED(".short 0xf32f,0x0c0b	@ ssat16	r12, #12, pc")
+
+	TEST_R(     "usat16	r0, #12, r",0,   HH1,"")
+	TEST_R(     "usat16	r14, #12, r",12, HH2,"")
+	TEST_UNSUPPORTED(".short 0xf3ac,0x0d0b	@ usat16	sp, #12, r12")
+	TEST_UNSUPPORTED(".short 0xf3ac,0x0f0b	@ usat16	pc, #12, r12")
+	TEST_UNSUPPORTED(".short 0xf3ad,0x0c0b	@ usat16	r12, #12, sp")
+	TEST_UNSUPPORTED(".short 0xf3af,0x0c0b	@ usat16	r12, #12, pc")
+
+	TEST_R(     "sbfx	r0, r",0  , VAL1,", #0, #31")
+	TEST_R(     "sbfx	r14, r",12, VAL2,", #8, #16")
+	TEST_R(     "sbfx	r4, r",10,  VAL1,", #16, #15")
+	TEST_UNSUPPORTED(".short 0xf34c,0x2d0f	@ sbfx	sp, r12, #8, #16")
+	TEST_UNSUPPORTED(".short 0xf34c,0x2f0f	@ sbfx	pc, r12, #8, #16")
+	TEST_UNSUPPORTED(".short 0xf34d,0x2c0f	@ sbfx	r12, sp, #8, #16")
+	TEST_UNSUPPORTED(".short 0xf34f,0x2c0f	@ sbfx	r12, pc, #8, #16")
+
+	TEST_R(     "ubfx	r0, r",0  , VAL1,", #0, #31")
+	TEST_R(     "ubfx	r14, r",12, VAL2,", #8, #16")
+	TEST_R(     "ubfx	r4, r",10,  VAL1,", #16, #15")
+	TEST_UNSUPPORTED(".short 0xf3cc,0x2d0f	@ ubfx	sp, r12, #8, #16")
+	TEST_UNSUPPORTED(".short 0xf3cc,0x2f0f	@ ubfx	pc, r12, #8, #16")
+	TEST_UNSUPPORTED(".short 0xf3cd,0x2c0f	@ ubfx	r12, sp, #8, #16")
+	TEST_UNSUPPORTED(".short 0xf3cf,0x2c0f	@ ubfx	r12, pc, #8, #16")
+
+	TEST_R(     "bfc	r",0, VAL1,", #4, #20")
+	TEST_R(     "bfc	r",14,VAL2,", #4, #20")
+	TEST_R(     "bfc	r",7, VAL1,", #0, #31")
+	TEST_R(     "bfc	r",8, VAL2,", #0, #31")
+	TEST_UNSUPPORTED(".short 0xf36f,0x0d1e	@ bfc	sp, #0, #31")
+	TEST_UNSUPPORTED(".short 0xf36f,0x0f1e	@ bfc	pc, #0, #31")
+
+	TEST_RR(    "bfi	r",0, VAL1,", r",0  , VAL2,", #0, #31")
+	TEST_RR(    "bfi	r",12,VAL1,", r",14 , VAL2,", #4, #20")
+	TEST_UNSUPPORTED(".short 0xf36e,0x1d17	@ bfi	sp, r14, #4, #20")
+	TEST_UNSUPPORTED(".short 0xf36e,0x1f17	@ bfi	pc, r14, #4, #20")
+	TEST_UNSUPPORTED(".short 0xf36d,0x1e17	@ bfi	r14, sp, #4, #20")
+
+	TEST_GROUP("Branches and miscellaneous control")
+
+CONDITION_INSTRUCTIONS(22,
+	TEST_BF("beq.w	2f")
+	TEST_BB("bne.w	2b")
+	TEST_BF("bgt.w	2f")
+	TEST_BB("blt.w	2b")
+	TEST_BF_X("bpl.w	2f", SPACE_0x1000)
+)
+
+	TEST_UNSUPPORTED("msr	cpsr, r0")
+	TEST_UNSUPPORTED("msr	cpsr_f, r1")
+	TEST_UNSUPPORTED("msr	spsr, r2")
+
+	TEST_UNSUPPORTED("cpsie.w	i")
+	TEST_UNSUPPORTED("cpsid.w	i")
+	TEST_UNSUPPORTED("cps	0x13")
+
+	TEST_SUPPORTED("yield.w")
+	TEST("sev.w")
+	TEST("nop.w")
+	TEST("wfi.w")
+	TEST_SUPPORTED("wfe.w")
+	TEST_UNSUPPORTED("dbg.w	#0")
+
+	TEST_UNSUPPORTED("clrex")
+	TEST_UNSUPPORTED("dsb")
+	TEST_UNSUPPORTED("dmb")
+	TEST_UNSUPPORTED("isb")
+
+	TEST_UNSUPPORTED("bxj	r0")
+
+	TEST_UNSUPPORTED("subs	pc, lr, #4")
+
+	TEST("mrs	r0, cpsr")
+	TEST("mrs	r14, cpsr")
+	TEST_UNSUPPORTED(".short 0xf3ef,0x8d00	@ mrs	sp, spsr")
+	TEST_UNSUPPORTED(".short 0xf3ef,0x8f00	@ mrs	pc, spsr")
+	TEST_UNSUPPORTED("mrs	r0, spsr")
+	TEST_UNSUPPORTED("mrs	lr, spsr")
+
+	TEST_UNSUPPORTED(".short 0xf7f0,0x8000 @ smc #0")
+
+	TEST_UNSUPPORTED(".short 0xf7f0,0xa000 @ undefeined")
+
+	TEST_BF(  "b.w	2f")
+	TEST_BB(  "b.w	2b")
+	TEST_BF_X("b.w	2f", SPACE_0x1000)
+
+	TEST_BF(  "bl.w	2f")
+	TEST_BB(  "bl.w	2b")
+	TEST_BB_X("bl.w	2b", SPACE_0x1000)
+
+	TEST_X(	"blx	__dummy_arm_subroutine",
+		".arm				\n\t"
+		".align				\n\t"
+		".type __dummy_arm_subroutine, %%function \n\t"
+		"__dummy_arm_subroutine:	\n\t"
+		"mov	r0, pc			\n\t"
+		"bx	lr			\n\t"
+		".thumb				\n\t"
+	)
+	TEST(	"blx	__dummy_arm_subroutine")
+
+	TEST_GROUP("Store single data item")
+
+#define SINGLE_STORE(size)							\
+	TEST_RP( "str"size"	r",0, VAL1,", [r",11,-1024,", #1024]")		\
+	TEST_RP( "str"size"	r",14,VAL2,", [r",1, -1024,", #1080]")		\
+	TEST_RP( "str"size"	r",0, VAL1,", [r",11,256,  ", #-120]")		\
+	TEST_RP( "str"size"	r",14,VAL2,", [r",1, 256,  ", #-128]")		\
+	TEST_RP( "str"size"	r",0, VAL1,", [r",11,24,  "], #120")		\
+	TEST_RP( "str"size"	r",14,VAL2,", [r",1, 24,  "], #128")		\
+	TEST_RP( "str"size"	r",0, VAL1,", [r",11,24,  "], #-120")		\
+	TEST_RP( "str"size"	r",14,VAL2,", [r",1, 24,  "], #-128")		\
+	TEST_RP( "str"size"	r",0, VAL1,", [r",11,24,   ", #120]!")		\
+	TEST_RP( "str"size"	r",14,VAL2,", [r",1, 24,   ", #128]!")		\
+	TEST_RP( "str"size"	r",0, VAL1,", [r",11,256,  ", #-120]!")		\
+	TEST_RP( "str"size"	r",14,VAL2,", [r",1, 256,  ", #-128]!")		\
+	TEST_RPR("str"size".w	r",0, VAL1,", [r",1, 0,", r",2, 4,"]")		\
+	TEST_RPR("str"size"	r",14,VAL2,", [r",10,0,", r",11,4,", lsl #1]")	\
+	TEST_R(  "str"size".w	r",7, VAL1,", [sp, #24]")			\
+	TEST_RP( "str"size".w	r",0, VAL2,", [r",0,0, "]")			\
+	TEST_UNSUPPORTED("str"size"t	r0, [r1, #4]")
+
+	SINGLE_STORE("b")
+	SINGLE_STORE("h")
+	SINGLE_STORE("")
+
+	TEST("str	sp, [sp]")
+	TEST_UNSUPPORTED(".short 0xf8cf,0xe000	@ str	r14, [pc]")
+	TEST_UNSUPPORTED(".short 0xf8ce,0xf000	@ str	pc, [r14]")
+
+	TEST_GROUP("Advanced SIMD element or structure load/store instructions")
+
+	TEST_UNSUPPORTED(".short 0xf900,0x0000")
+	TEST_UNSUPPORTED(".short 0xf92f,0xffff")
+	TEST_UNSUPPORTED(".short 0xf980,0x0000")
+	TEST_UNSUPPORTED(".short 0xf9ef,0xffff")
+
+	TEST_GROUP("Load single data item and memory hints")
+
+#define SINGLE_LOAD(size)						\
+	TEST_P( "ldr"size"	r0, [r",11,-1024, ", #1024]")		\
+	TEST_P( "ldr"size"	r14, [r",1, -1024,", #1080]")		\
+	TEST_P( "ldr"size"	r0, [r",11,256,   ", #-120]")		\
+	TEST_P( "ldr"size"	r14, [r",1, 256,  ", #-128]")		\
+	TEST_P( "ldr"size"	r0, [r",11,24,   "], #120")		\
+	TEST_P( "ldr"size"	r14, [r",1, 24,  "], #128")		\
+	TEST_P( "ldr"size"	r0, [r",11,24,   "], #-120")		\
+	TEST_P( "ldr"size"	r14, [r",1,24,   "], #-128")		\
+	TEST_P( "ldr"size"	r0, [r",11,24,    ", #120]!")		\
+	TEST_P( "ldr"size"	r14, [r",1, 24,   ", #128]!")		\
+	TEST_P( "ldr"size"	r0, [r",11,256,   ", #-120]!")		\
+	TEST_P( "ldr"size"	r14, [r",1, 256,  ", #-128]!")		\
+	TEST_PR("ldr"size".w	r0, [r",1, 0,", r",2, 4,"]")		\
+	TEST_PR("ldr"size"	r14, [r",10,0,", r",11,4,", lsl #1]")	\
+	TEST_X( "ldr"size".w	r0, 3f",				\
+		".align 3				\n\t"		\
+		"3:	.word	"__stringify(VAL1))			\
+	TEST_X( "ldr"size".w	r14, 3f",				\
+		".align 3				\n\t"		\
+		"3:	.word	"__stringify(VAL2))			\
+	TEST(   "ldr"size".w	r7, 3b")				\
+	TEST(   "ldr"size".w	r7, [sp, #24]")				\
+	TEST_P( "ldr"size".w	r0, [r",0,0, "]")			\
+	TEST_UNSUPPORTED("ldr"size"t	r0, [r1, #4]")
+
+	SINGLE_LOAD("b")
+	SINGLE_LOAD("sb")
+	SINGLE_LOAD("h")
+	SINGLE_LOAD("sh")
+	SINGLE_LOAD("")
+
+	TEST_BF_P("ldr	pc, [r",14, 15*4,"]")
+	TEST_P(   "ldr	sp, [r",14, 13*4,"]")
+	TEST_BF_R("ldr	pc, [sp, r",14, 15*4,"]")
+	TEST_R(   "ldr	sp, [sp, r",14, 13*4,"]")
+	TEST_THUMB_TO_ARM_INTERWORK_P("ldr	pc, [r",0,0,", #15*4]")
+	TEST_SUPPORTED("ldr	sp, 99f")
+	TEST_SUPPORTED("ldr	pc, 99f")
+
+	TEST_UNSUPPORTED(".short 0xf854,0x700d	@ ldr	r7, [r4, sp]")
+	TEST_UNSUPPORTED(".short 0xf854,0x700f	@ ldr	r7, [r4, pc]")
+	TEST_UNSUPPORTED(".short 0xf814,0x700d	@ ldrb	r7, [r4, sp]")
+	TEST_UNSUPPORTED(".short 0xf814,0x700f	@ ldrb	r7, [r4, pc]")
+	TEST_UNSUPPORTED(".short 0xf89f,0xd004	@ ldrb	sp, 99f")
+	TEST_UNSUPPORTED(".short 0xf814,0xd008	@ ldrb	sp, [r4, r8]")
+	TEST_UNSUPPORTED(".short 0xf894,0xd000	@ ldrb	sp, [r4]")
+
+	TEST_UNSUPPORTED(".short 0xf860,0x0000") /* Unallocated space */
+	TEST_UNSUPPORTED(".short 0xf9ff,0xffff") /* Unallocated space */
+	TEST_UNSUPPORTED(".short 0xf950,0x0000") /* Unallocated space */
+	TEST_UNSUPPORTED(".short 0xf95f,0xffff") /* Unallocated space */
+	TEST_UNSUPPORTED(".short 0xf800,0x0800") /* Unallocated space */
+	TEST_UNSUPPORTED(".short 0xf97f,0xfaff") /* Unallocated space */
+
+	TEST(   "pli	[pc, #4]")
+	TEST(   "pli	[pc, #-4]")
+	TEST(   "pld	[pc, #4]")
+	TEST(   "pld	[pc, #-4]")
+
+	TEST_P( "pld	[r",0,-1024,", #1024]")
+	TEST(   ".short 0xf8b0,0xf400	@ pldw	[r0, #1024]")
+	TEST_P( "pli	[r",4, 0b,", #1024]")
+	TEST_P( "pld	[r",7, 120,", #-120]")
+	TEST(   ".short 0xf837,0xfc78	@ pldw	[r7, #-120]")
+	TEST_P( "pli	[r",11,120,", #-120]")
+	TEST(   "pld	[sp, #0]")
+
+	TEST_PR("pld	[r",7, 24, ", r",0, 16,"]")
+	TEST_PR("pld	[r",8, 24, ", r",12,16,", lsl #3]")
+	TEST_SUPPORTED(".short 0xf837,0xf000	@ pldw	[r7, r0]")
+	TEST_SUPPORTED(".short 0xf838,0xf03c	@ pldw	[r8, r12, lsl #3]");
+	TEST_RR("pli	[r",12,0b,", r",0, 16,"]")
+	TEST_RR("pli	[r",0, 0b,", r",12,16,", lsl #3]")
+	TEST_R( "pld	[sp, r",1, 16,"]")
+	TEST_UNSUPPORTED(".short 0xf817,0xf00d  @pld	[r7, sp]")
+	TEST_UNSUPPORTED(".short 0xf817,0xf00f  @pld	[r7, pc]")
+
+	TEST_GROUP("Data-processing (register)")
+
+#define SHIFTS32(op)					\
+	TEST_RR(op"	r0,  r",1, VAL1,", r",2, 3, "")	\
+	TEST_RR(op"	r14, r",12,VAL2,", r",11,10,"")
+
+	SHIFTS32("lsl")
+	SHIFTS32("lsls")
+	SHIFTS32("lsr")
+	SHIFTS32("lsrs")
+	SHIFTS32("asr")
+	SHIFTS32("asrs")
+	SHIFTS32("ror")
+	SHIFTS32("rors")
+
+	TEST_UNSUPPORTED(".short 0xfa01,0xff02	@ lsl	pc, r1, r2")
+	TEST_UNSUPPORTED(".short 0xfa01,0xfd02	@ lsl	sp, r1, r2")
+	TEST_UNSUPPORTED(".short 0xfa0f,0xf002	@ lsl	r0, pc, r2")
+	TEST_UNSUPPORTED(".short 0xfa0d,0xf002	@ lsl	r0, sp, r2")
+	TEST_UNSUPPORTED(".short 0xfa01,0xf00f	@ lsl	r0, r1, pc")
+	TEST_UNSUPPORTED(".short 0xfa01,0xf00d	@ lsl	r0, r1, sp")
+
+	TEST_RR(    "sxtah	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "sxtah	r14,r",12, HH2,", r",10,HH1,", ror #8")
+	TEST_R(     "sxth	r8, r",7,  HH1,"")
+
+	TEST_UNSUPPORTED(".short 0xfa0f,0xff87	@ sxth	pc, r7");
+	TEST_UNSUPPORTED(".short 0xfa0f,0xfd87	@ sxth	sp, r7");
+	TEST_UNSUPPORTED(".short 0xfa0f,0xf88f	@ sxth	r8, pc");
+	TEST_UNSUPPORTED(".short 0xfa0f,0xf88d	@ sxth	r8, sp");
+
+	TEST_RR(    "uxtah	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "uxtah	r14,r",12, HH2,", r",10,HH1,", ror #8")
+	TEST_R(     "uxth	r8, r",7,  HH1,"")
+
+	TEST_RR(    "sxtab16	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "sxtab16	r14,r",12, HH2,", r",10,HH1,", ror #8")
+	TEST_R(     "sxtb16	r8, r",7,  HH1,"")
+
+	TEST_RR(    "uxtab16	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "uxtab16	r14,r",12, HH2,", r",10,HH1,", ror #8")
+	TEST_R(     "uxtb16	r8, r",7,  HH1,"")
+
+	TEST_RR(    "sxtab	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "sxtab	r14,r",12, HH2,", r",10,HH1,", ror #8")
+	TEST_R(     "sxtb	r8, r",7,  HH1,"")
+
+	TEST_RR(    "uxtab	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "uxtab	r14,r",12, HH2,", r",10,HH1,", ror #8")
+	TEST_R(     "uxtb	r8, r",7,  HH1,"")
+
+	TEST_UNSUPPORTED(".short 0xfa60,0x00f0")
+	TEST_UNSUPPORTED(".short 0xfa7f,0xffff")
+
+#define PARALLEL_ADD_SUB(op)					\
+	TEST_RR(  op"add16	r0, r",0,  HH1,", r",1, HH2,"")	\
+	TEST_RR(  op"add16	r14, r",12,HH2,", r",10,HH1,"")	\
+	TEST_RR(  op"asx	r0, r",0,  HH1,", r",1, HH2,"")	\
+	TEST_RR(  op"asx	r14, r",12,HH2,", r",10,HH1,"")	\
+	TEST_RR(  op"sax	r0, r",0,  HH1,", r",1, HH2,"")	\
+	TEST_RR(  op"sax	r14, r",12,HH2,", r",10,HH1,"")	\
+	TEST_RR(  op"sub16	r0, r",0,  HH1,", r",1, HH2,"")	\
+	TEST_RR(  op"sub16	r14, r",12,HH2,", r",10,HH1,"")	\
+	TEST_RR(  op"add8	r0, r",0,  HH1,", r",1, HH2,"")	\
+	TEST_RR(  op"add8	r14, r",12,HH2,", r",10,HH1,"")	\
+	TEST_RR(  op"sub8	r0, r",0,  HH1,", r",1, HH2,"")	\
+	TEST_RR(  op"sub8	r14, r",12,HH2,", r",10,HH1,"")
+
+	TEST_GROUP("Parallel addition and subtraction, signed")
+
+	PARALLEL_ADD_SUB("s")
+	PARALLEL_ADD_SUB("q")
+	PARALLEL_ADD_SUB("sh")
+
+	TEST_GROUP("Parallel addition and subtraction, unsigned")
+
+	PARALLEL_ADD_SUB("u")
+	PARALLEL_ADD_SUB("uq")
+	PARALLEL_ADD_SUB("uh")
+
+	TEST_GROUP("Miscellaneous operations")
+
+	TEST_RR("qadd	r0, r",1, VAL1,", r",2, VAL2,"")
+	TEST_RR("qadd	lr, r",9, VAL2,", r",8, VAL1,"")
+	TEST_RR("qsub	r0, r",1, VAL1,", r",2, VAL2,"")
+	TEST_RR("qsub	lr, r",9, VAL2,", r",8, VAL1,"")
+	TEST_RR("qdadd	r0, r",1, VAL1,", r",2, VAL2,"")
+	TEST_RR("qdadd	lr, r",9, VAL2,", r",8, VAL1,"")
+	TEST_RR("qdsub	r0, r",1, VAL1,", r",2, VAL2,"")
+	TEST_RR("qdsub	lr, r",9, VAL2,", r",8, VAL1,"")
+
+	TEST_R("rev.w	r0, r",0,   VAL1,"")
+	TEST_R("rev	r14, r",12, VAL2,"")
+	TEST_R("rev16.w	r0, r",0,   VAL1,"")
+	TEST_R("rev16	r14, r",12, VAL2,"")
+	TEST_R("rbit	r0, r",0,   VAL1,"")
+	TEST_R("rbit	r14, r",12, VAL2,"")
+	TEST_R("revsh.w	r0, r",0,   VAL1,"")
+	TEST_R("revsh	r14, r",12, VAL2,"")
+
+	TEST_UNSUPPORTED(".short 0xfa9c,0xff8c	@ rev	pc, r12");
+	TEST_UNSUPPORTED(".short 0xfa9c,0xfd8c	@ rev	sp, r12");
+	TEST_UNSUPPORTED(".short 0xfa9f,0xfe8f	@ rev	r14, pc");
+	TEST_UNSUPPORTED(".short 0xfa9d,0xfe8d	@ rev	r14, sp");
+
+	TEST_RR("sel	r0, r",0,  VAL1,", r",1, VAL2,"")
+	TEST_RR("sel	r14, r",12,VAL1,", r",10, VAL2,"")
+
+	TEST_R("clz	r0, r",0, 0x0,"")
+	TEST_R("clz	r7, r",14,0x1,"")
+	TEST_R("clz	lr, r",7, 0xffffffff,"")
+
+	TEST_UNSUPPORTED(".short 0xfa80,0xf030") /* Unallocated space */
+	TEST_UNSUPPORTED(".short 0xfaff,0xff7f") /* Unallocated space */
+	TEST_UNSUPPORTED(".short 0xfab0,0xf000") /* Unallocated space */
+	TEST_UNSUPPORTED(".short 0xfaff,0xff7f") /* Unallocated space */
+
+	TEST_GROUP("Multiply, multiply accumulate, and absolute difference operations")
+
+	TEST_RR(    "mul	r0, r",1, VAL1,", r",2, VAL2,"")
+	TEST_RR(    "mul	r7, r",8, VAL2,", r",9, VAL2,"")
+	TEST_UNSUPPORTED(".short 0xfb08,0xff09	@ mul	pc, r8, r9")
+	TEST_UNSUPPORTED(".short 0xfb08,0xfd09	@ mul	sp, r8, r9")
+	TEST_UNSUPPORTED(".short 0xfb0f,0xf709	@ mul	r7, pc, r9")
+	TEST_UNSUPPORTED(".short 0xfb0d,0xf709	@ mul	r7, sp, r9")
+	TEST_UNSUPPORTED(".short 0xfb08,0xf70f	@ mul	r7, r8, pc")
+	TEST_UNSUPPORTED(".short 0xfb08,0xf70d	@ mul	r7, r8, sp")
+
+	TEST_RRR(   "mla	r0, r",1, VAL1,", r",2, VAL2,", r",3,  VAL3,"")
+	TEST_RRR(   "mla	r7, r",8, VAL3,", r",9, VAL1,", r",10, VAL2,"")
+	TEST_UNSUPPORTED(".short 0xfb08,0xaf09	@ mla	pc, r8, r9, r10");
+	TEST_UNSUPPORTED(".short 0xfb08,0xad09	@ mla	sp, r8, r9, r10");
+	TEST_UNSUPPORTED(".short 0xfb0f,0xa709	@ mla	r7, pc, r9, r10");
+	TEST_UNSUPPORTED(".short 0xfb0d,0xa709	@ mla	r7, sp, r9, r10");
+	TEST_UNSUPPORTED(".short 0xfb08,0xa70f	@ mla	r7, r8, pc, r10");
+	TEST_UNSUPPORTED(".short 0xfb08,0xa70d	@ mla	r7, r8, sp, r10");
+	TEST_UNSUPPORTED(".short 0xfb08,0xd709	@ mla	r7, r8, r9, sp");
+
+	TEST_RRR(   "mls	r0, r",1, VAL1,", r",2, VAL2,", r",3,  VAL3,"")
+	TEST_RRR(   "mls	r7, r",8, VAL3,", r",9, VAL1,", r",10, VAL2,"")
+
+	TEST_RRR(   "smlabb	r0, r",1, VAL1,", r",2, VAL2,", r",3,  VAL3,"")
+	TEST_RRR(   "smlabb	r7, r",8, VAL3,", r",9, VAL1,", r",10, VAL2,"")
+	TEST_RRR(   "smlatb	r0, r",1, VAL1,", r",2, VAL2,", r",3,  VAL3,"")
+	TEST_RRR(   "smlatb	r7, r",8, VAL3,", r",9, VAL1,", r",10, VAL2,"")
+	TEST_RRR(   "smlabt	r0, r",1, VAL1,", r",2, VAL2,", r",3,  VAL3,"")
+	TEST_RRR(   "smlabt	r7, r",8, VAL3,", r",9, VAL1,", r",10, VAL2,"")
+	TEST_RRR(   "smlatt	r0, r",1, VAL1,", r",2, VAL2,", r",3,  VAL3,"")
+	TEST_RRR(   "smlatt	r7, r",8, VAL3,", r",9, VAL1,", r",10, VAL2,"")
+	TEST_RR(    "smulbb	r0, r",1, VAL1,", r",2, VAL2,"")
+	TEST_RR(    "smulbb	r7, r",8, VAL3,", r",9, VAL1,"")
+	TEST_RR(    "smultb	r0, r",1, VAL1,", r",2, VAL2,"")
+	TEST_RR(    "smultb	r7, r",8, VAL3,", r",9, VAL1,"")
+	TEST_RR(    "smulbt	r0, r",1, VAL1,", r",2, VAL2,"")
+	TEST_RR(    "smulbt	r7, r",8, VAL3,", r",9, VAL1,"")
+	TEST_RR(    "smultt	r0, r",1, VAL1,", r",2, VAL2,"")
+	TEST_RR(    "smultt	r7, r",8, VAL3,", r",9, VAL1,"")
+
+	TEST_RRR(   "smlad	r0, r",0,  HH1,", r",1, HH2,", r",2, VAL1,"")
+	TEST_RRR(   "smlad	r14, r",12,HH2,", r",10,HH1,", r",8, VAL2,"")
+	TEST_RRR(   "smladx	r0, r",0,  HH1,", r",1, HH2,", r",2, VAL1,"")
+	TEST_RRR(   "smladx	r14, r",12,HH2,", r",10,HH1,", r",8, VAL2,"")
+	TEST_RR(    "smuad	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "smuad	r14, r",12,HH2,", r",10,HH1,"")
+	TEST_RR(    "smuadx	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "smuadx	r14, r",12,HH2,", r",10,HH1,"")
+
+	TEST_RRR(   "smlawb	r0, r",1, VAL1,", r",2, VAL2,", r",3,  VAL3,"")
+	TEST_RRR(   "smlawb	r7, r",8, VAL3,", r",9, VAL1,", r",10, VAL2,"")
+	TEST_RRR(   "smlawt	r0, r",1, VAL1,", r",2, VAL2,", r",3,  VAL3,"")
+	TEST_RRR(   "smlawt	r7, r",8, VAL3,", r",9, VAL1,", r",10, VAL2,"")
+	TEST_RR(    "smulwb	r0, r",1, VAL1,", r",2, VAL2,"")
+	TEST_RR(    "smulwb	r7, r",8, VAL3,", r",9, VAL1,"")
+	TEST_RR(    "smulwt	r0, r",1, VAL1,", r",2, VAL2,"")
+	TEST_RR(    "smulwt	r7, r",8, VAL3,", r",9, VAL1,"")
+
+	TEST_RRR(   "smlsd	r0, r",0,  HH1,", r",1, HH2,", r",2, VAL1,"")
+	TEST_RRR(   "smlsd	r14, r",12,HH2,", r",10,HH1,", r",8, VAL2,"")
+	TEST_RRR(   "smlsdx	r0, r",0,  HH1,", r",1, HH2,", r",2, VAL1,"")
+	TEST_RRR(   "smlsdx	r14, r",12,HH2,", r",10,HH1,", r",8, VAL2,"")
+	TEST_RR(    "smusd	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "smusd	r14, r",12,HH2,", r",10,HH1,"")
+	TEST_RR(    "smusdx	r0, r",0,  HH1,", r",1, HH2,"")
+	TEST_RR(    "smusdx	r14, r",12,HH2,", r",10,HH1,"")
+
+	TEST_RRR(   "smmla	r0, r",0,  VAL1,", r",1, VAL2,", r",2, VAL1,"")
+	TEST_RRR(   "smmla	r14, r",12,VAL2,", r",10,VAL1,", r",8, VAL2,"")
+	TEST_RRR(   "smmlar	r0, r",0,  VAL1,", r",1, VAL2,", r",2, VAL1,"")
+	TEST_RRR(   "smmlar	r14, r",12,VAL2,", r",10,VAL1,", r",8, VAL2,"")
+	TEST_RR(    "smmul	r0, r",0,  VAL1,", r",1, VAL2,"")
+	TEST_RR(    "smmul	r14, r",12,VAL2,", r",10,VAL1,"")
+	TEST_RR(    "smmulr	r0, r",0,  VAL1,", r",1, VAL2,"")
+	TEST_RR(    "smmulr	r14, r",12,VAL2,", r",10,VAL1,"")
+
+	TEST_RRR(   "smmls	r0, r",0,  VAL1,", r",1, VAL2,", r",2, VAL1,"")
+	TEST_RRR(   "smmls	r14, r",12,VAL2,", r",10,VAL1,", r",8, VAL2,"")
+	TEST_RRR(   "smmlsr	r0, r",0,  VAL1,", r",1, VAL2,", r",2, VAL1,"")
+	TEST_RRR(   "smmlsr	r14, r",12,VAL2,", r",10,VAL1,", r",8, VAL2,"")
+
+	TEST_RRR(   "usada8	r0, r",0,  VAL1,", r",1, VAL2,", r",2, VAL3,"")
+	TEST_RRR(   "usada8	r14, r",12,VAL2,", r",10,VAL1,", r",8, VAL3,"")
+	TEST_RR(    "usad8	r0, r",0,  VAL1,", r",1, VAL2,"")
+	TEST_RR(    "usad8	r14, r",12,VAL2,", r",10,VAL1,"")
+
+	TEST_UNSUPPORTED(".short 0xfb00,0xf010") /* Unallocated space */
+	TEST_UNSUPPORTED(".short 0xfb0f,0xff1f") /* Unallocated space */
+	TEST_UNSUPPORTED(".short 0xfb70,0xf010") /* Unallocated space */
+	TEST_UNSUPPORTED(".short 0xfb7f,0xff1f") /* Unallocated space */
+	TEST_UNSUPPORTED(".short 0xfb70,0x0010") /* Unallocated space */
+	TEST_UNSUPPORTED(".short 0xfb7f,0xff1f") /* Unallocated space */
+
+	TEST_GROUP("Long multiply, long multiply accumulate, and divide")
+
+	TEST_RR(   "smull	r0, r1, r",2, VAL1,", r",3, VAL2,"")
+	TEST_RR(   "smull	r7, r8, r",9, VAL2,", r",10, VAL1,"")
+	TEST_UNSUPPORTED(".short 0xfb89,0xf80a	@ smull	pc, r8, r9, r10");
+	TEST_UNSUPPORTED(".short 0xfb89,0xd80a	@ smull	sp, r8, r9, r10");
+	TEST_UNSUPPORTED(".short 0xfb89,0x7f0a	@ smull	r7, pc, r9, r10");
+	TEST_UNSUPPORTED(".short 0xfb89,0x7d0a	@ smull	r7, sp, r9, r10");
+	TEST_UNSUPPORTED(".short 0xfb8f,0x780a	@ smull	r7, r8, pc, r10");
+	TEST_UNSUPPORTED(".short 0xfb8d,0x780a	@ smull	r7, r8, sp, r10");
+	TEST_UNSUPPORTED(".short 0xfb89,0x780f	@ smull	r7, r8, r9, pc");
+	TEST_UNSUPPORTED(".short 0xfb89,0x780d	@ smull	r7, r8, r9, sp");
+
+	TEST_RR(   "umull	r0, r1, r",2, VAL1,", r",3, VAL2,"")
+	TEST_RR(   "umull	r7, r8, r",9, VAL2,", r",10, VAL1,"")
+
+	TEST_RRRR( "smlal	r",0, VAL1,", r",1, VAL2,", r",2, VAL3,", r",3, VAL4)
+	TEST_RRRR( "smlal	r",8, VAL4,", r",9, VAL1,", r",10,VAL2,", r",11,VAL3)
+
+	TEST_RRRR( "smlalbb	r",0, VAL1,", r",1, VAL2,", r",2, VAL3,", r",3, VAL4)
+	TEST_RRRR( "smlalbb	r",8, VAL4,", r",9, VAL1,", r",10,VAL2,", r",11,VAL3)
+	TEST_RRRR( "smlalbt	r",0, VAL1,", r",1, VAL2,", r",2, VAL3,", r",3, VAL4)
+	TEST_RRRR( "smlalbt	r",8, VAL4,", r",9, VAL1,", r",10,VAL2,", r",11,VAL3)
+	TEST_RRRR( "smlaltb	r",0, VAL1,", r",1, VAL2,", r",2, VAL3,", r",3, VAL4)
+	TEST_RRRR( "smlaltb	r",8, VAL4,", r",9, VAL1,", r",10,VAL2,", r",11,VAL3)
+	TEST_RRRR( "smlaltt	r",0, VAL1,", r",1, VAL2,", r",2, VAL3,", r",3, VAL4)
+	TEST_RRRR( "smlaltt	r",8, VAL4,", r",9, VAL1,", r",10,VAL2,", r",11,VAL3)
+
+	TEST_RRRR( "smlald	r",0, VAL1,", r",1, VAL2, ", r",0, HH1,", r",1, HH2)
+	TEST_RRRR( "smlald	r",11,VAL2,", r",10,VAL1, ", r",9, HH2,", r",8, HH1)
+	TEST_RRRR( "smlaldx	r",0, VAL1,", r",1, VAL2, ", r",0, HH1,", r",1, HH2)
+	TEST_RRRR( "smlaldx	r",11,VAL2,", r",10,VAL1, ", r",9, HH2,", r",8, HH1)
+
+	TEST_RRRR( "smlsld	r",0, VAL1,", r",1, VAL2, ", r",0, HH1,", r",1, HH2)
+	TEST_RRRR( "smlsld	r",11,VAL2,", r",10,VAL1, ", r",9, HH2,", r",8, HH1)
+	TEST_RRRR( "smlsldx	r",0, VAL1,", r",1, VAL2, ", r",0, HH1,", r",1, HH2)
+	TEST_RRRR( "smlsldx	r",11,VAL2,", r",10,VAL1, ", r",9, HH2,", r",8, HH1)
+
+	TEST_RRRR( "umlal	r",0, VAL1,", r",1, VAL2,", r",2, VAL3,", r",3, VAL4)
+	TEST_RRRR( "umlal	r",8, VAL4,", r",9, VAL1,", r",10,VAL2,", r",11,VAL3)
+	TEST_RRRR( "umaal	r",0, VAL1,", r",1, VAL2,", r",2, VAL3,", r",3, VAL4)
+	TEST_RRRR( "umaal	r",8, VAL4,", r",9, VAL1,", r",10,VAL2,", r",11,VAL3)
+
+	TEST_GROUP("Coprocessor instructions")
+
+	TEST_UNSUPPORTED(".short 0xfc00,0x0000")
+	TEST_UNSUPPORTED(".short 0xffff,0xffff")
+
+	TEST_GROUP("Testing instructions in IT blocks")
+
+	TEST_ITBLOCK("sub.w	r0, r0")
+
+	verbose("\n");
+}
+
diff --git a/arch/arm/kernel/kprobes-test.c b/arch/arm/kernel/kprobes-test.c
new file mode 100644
index 00000000000..e17cdd6d90d
--- /dev/null
+++ b/arch/arm/kernel/kprobes-test.c
@@ -0,0 +1,1748 @@
+/*
+ * arch/arm/kernel/kprobes-test.c
+ *
+ * Copyright (C) 2011 Jon Medhurst <tixy@yxit.co.uk>.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*
+ * This file contains test code for ARM kprobes.
+ *
+ * The top level function run_all_tests() executes tests for all of the
+ * supported instruction sets: ARM, 16-bit Thumb, and 32-bit Thumb. These tests
+ * fall into two categories; run_api_tests() checks basic functionality of the
+ * kprobes API, and run_test_cases() is a comprehensive test for kprobes
+ * instruction decoding and simulation.
+ *
+ * run_test_cases() first checks the kprobes decoding table for self consistency
+ * (using table_test()) then executes a series of test cases for each of the CPU
+ * instruction forms. coverage_start() and coverage_end() are used to verify
+ * that these test cases cover all of the possible combinations of instructions
+ * described by the kprobes decoding tables.
+ *
+ * The individual test cases are in kprobes-test-arm.c and kprobes-test-thumb.c
+ * which use the macros defined in kprobes-test.h. The rest of this
+ * documentation will describe the operation of the framework used by these
+ * test cases.
+ */
+
+/*
+ * TESTING METHODOLOGY
+ * -------------------
+ *
+ * The methodology used to test an ARM instruction 'test_insn' is to use
+ * inline assembler like:
+ *
+ * test_before: nop
+ * test_case:	test_insn
+ * test_after:	nop
+ *
+ * When the test case is run a kprobe is placed of each nop. The
+ * post-handler of the test_before probe is used to modify the saved CPU
+ * register context to that which we require for the test case. The
+ * pre-handler of the of the test_after probe saves a copy of the CPU
+ * register context. In this way we can execute test_insn with a specific
+ * register context and see the results afterwards.
+ *
+ * To actually test the kprobes instruction emulation we perform the above
+ * step a second time but with an additional kprobe on the test_case
+ * instruction itself. If the emulation is accurate then the results seen
+ * by the test_after probe will be identical to the first run which didn't
+ * have a probe on test_case.
+ *
+ * Each test case is run several times with a variety of variations in the
+ * flags value of stored in CPSR, and for Thumb code, different ITState.
+ *
+ * For instructions which can modify PC, a second test_after probe is used
+ * like this:
+ *
+ * test_before: nop
+ * test_case:	test_insn
+ * test_after:	nop
+ *		b test_done
+ * test_after2: nop
+ * test_done:
+ *
+ * The test case is constructed such that test_insn branches to
+ * test_after2, or, if testing a conditional instruction, it may just
+ * continue to test_after. The probes inserted at both locations let us
+ * determine which happened. A similar approach is used for testing
+ * backwards branches...
+ *
+ *		b test_before
+ *		b test_done  @ helps to cope with off by 1 branches
+ * test_after2: nop
+ *		b test_done
+ * test_before: nop
+ * test_case:	test_insn
+ * test_after:	nop
+ * test_done:
+ *
+ * The macros used to generate the assembler instructions describe above
+ * are TEST_INSTRUCTION, TEST_BRANCH_F (branch forwards) and TEST_BRANCH_B
+ * (branch backwards). In these, the local variables numbered 1, 50, 2 and
+ * 99 represent: test_before, test_case, test_after2 and test_done.
+ *
+ * FRAMEWORK
+ * ---------
+ *
+ * Each test case is wrapped between the pair of macros TESTCASE_START and
+ * TESTCASE_END. As well as performing the inline assembler boilerplate,
+ * these call out to the kprobes_test_case_start() and
+ * kprobes_test_case_end() functions which drive the execution of the test
+ * case. The specific arguments to use for each test case are stored as
+ * inline data constructed using the various TEST_ARG_* macros. Putting
+ * this all together, a simple test case may look like:
+ *
+ *	TESTCASE_START("Testing mov r0, r7")
+ *	TEST_ARG_REG(7, 0x12345678) // Set r7=0x12345678
+ *	TEST_ARG_END("")
+ *	TEST_INSTRUCTION("mov r0, r7")
+ *	TESTCASE_END
+ *
+ * Note, in practice the single convenience macro TEST_R would be used for this
+ * instead.
+ *
+ * The above would expand to assembler looking something like:
+ *
+ *	@ TESTCASE_START
+ *	bl	__kprobes_test_case_start
+ *	@ start of inline data...
+ *	.ascii "mov r0, r7"	@ text title for test case
+ *	.byte	0
+ *	.align	2
+ *
+ *	@ TEST_ARG_REG
+ *	.byte	ARG_TYPE_REG
+ *	.byte	7
+ *	.short	0
+ *	.word	0x1234567
+ *
+ *	@ TEST_ARG_END
+ *	.byte	ARG_TYPE_END
+ *	.byte	TEST_ISA	@ flags, including ISA being tested
+ *	.short	50f-0f		@ offset of 'test_before'
+ *	.short	2f-0f		@ offset of 'test_after2' (if relevent)
+ *	.short	99f-0f		@ offset of 'test_done'
+ *	@ start of test case code...
+ *	0:
+ *	.code	TEST_ISA	@ switch to ISA being tested
+ *
+ *	@ TEST_INSTRUCTION
+ *	50:	nop		@ location for 'test_before' probe
+ *	1:	mov r0, r7	@ the test case instruction 'test_insn'
+ *		nop		@ location for 'test_after' probe
+ *
+ *	// TESTCASE_END
+ *	2:
+ *	99:	bl __kprobes_test_case_end_##TEST_ISA
+ *	.code	NONMAL_ISA
+ *
+ * When the above is execute the following happens...
+ *
+ * __kprobes_test_case_start() is an assembler wrapper which sets up space
+ * for a stack buffer and calls the C function kprobes_test_case_start().
+ * This C function will do some initial processing of the inline data and
+ * setup some global state. It then inserts the test_before and test_after
+ * kprobes and returns a value which causes the assembler wrapper to jump
+ * to the start of the test case code, (local label '0').
+ *
+ * When the test case code executes, the test_before probe will be hit and
+ * test_before_post_handler will call setup_test_context(). This fills the
+ * stack buffer and CPU registers with a test pattern and then processes
+ * the test case arguments. In our example there is one TEST_ARG_REG which
+ * indicates that R7 should be loaded with the value 0x12345678.
+ *
+ * When the test_before probe ends, the test case continues and executes
+ * the "mov r0, r7" instruction. It then hits the test_after probe and the
+ * pre-handler for this (test_after_pre_handler) will save a copy of the
+ * CPU register context. This should now have R0 holding the same value as
+ * R7.
+ *
+ * Finally we get to the call to __kprobes_test_case_end_{32,16}. This is
+ * an assembler wrapper which switches back to the ISA used by the test
+ * code and calls the C function kprobes_test_case_end().
+ *
+ * For each run through the test case, test_case_run_count is incremented
+ * by one. For even runs, kprobes_test_case_end() saves a copy of the
+ * register and stack buffer contents from the test case just run. It then
+ * inserts a kprobe on the test case instruction 'test_insn' and returns a
+ * value to cause the test case code to be re-run.
+ *
+ * For odd numbered runs, kprobes_test_case_end() compares the register and
+ * stack buffer contents to those that were saved on the previous even
+ * numbered run (the one without the kprobe on test_insn). These should be
+ * the same if the kprobe instruction simulation routine is correct.
+ *
+ * The pair of test case runs is repeated with different combinations of
+ * flag values in CPSR and, for Thumb, different ITState. This is
+ * controlled by test_context_cpsr().
+ *
+ * BUILDING TEST CASES
+ * -------------------
+ *
+ *
+ * As an aid to building test cases, the stack buffer is initialised with
+ * some special values:
+ *
+ *   [SP+13*4]	Contains SP+120. This can be used to test instructions
+ *		which load a value into SP.
+ *
+ *   [SP+15*4]	When testing branching instructions using TEST_BRANCH_{F,B},
+ *		this holds the target address of the branch, 'test_after2'.
+ *		This can be used to test instructions which load a PC value
+ *		from memory.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/kprobes.h>
+
+#include "kprobes.h"
+#include "kprobes-test.h"
+
+
+#define BENCHMARKING	1
+
+
+/*
+ * Test basic API
+ */
+
+static bool test_regs_ok;
+static int test_func_instance;
+static int pre_handler_called;
+static int post_handler_called;
+static int jprobe_func_called;
+static int kretprobe_handler_called;
+
+#define FUNC_ARG1 0x12345678
+#define FUNC_ARG2 0xabcdef
+
+
+#ifndef CONFIG_THUMB2_KERNEL
+
+long arm_func(long r0, long r1);
+
+static void __used __naked __arm_kprobes_test_func(void)
+{
+	__asm__ __volatile__ (
+		".arm					\n\t"
+		".type arm_func, %%function		\n\t"
+		"arm_func:				\n\t"
+		"adds	r0, r0, r1			\n\t"
+		"bx	lr				\n\t"
+		".code "NORMAL_ISA	 /* Back to Thumb if necessary */
+		: : : "r0", "r1", "cc"
+	);
+}
+
+#else /* CONFIG_THUMB2_KERNEL */
+
+long thumb16_func(long r0, long r1);
+long thumb32even_func(long r0, long r1);
+long thumb32odd_func(long r0, long r1);
+
+static void __used __naked __thumb_kprobes_test_funcs(void)
+{
+	__asm__ __volatile__ (
+		".type thumb16_func, %%function		\n\t"
+		"thumb16_func:				\n\t"
+		"adds.n	r0, r0, r1			\n\t"
+		"bx	lr				\n\t"
+
+		".align					\n\t"
+		".type thumb32even_func, %%function	\n\t"
+		"thumb32even_func:			\n\t"
+		"adds.w	r0, r0, r1			\n\t"
+		"bx	lr				\n\t"
+
+		".align					\n\t"
+		"nop.n					\n\t"
+		".type thumb32odd_func, %%function	\n\t"
+		"thumb32odd_func:			\n\t"
+		"adds.w	r0, r0, r1			\n\t"
+		"bx	lr				\n\t"
+
+		: : : "r0", "r1", "cc"
+	);
+}
+
+#endif /* CONFIG_THUMB2_KERNEL */
+
+
+static int call_test_func(long (*func)(long, long), bool check_test_regs)
+{
+	long ret;
+
+	++test_func_instance;
+	test_regs_ok = false;
+
+	ret = (*func)(FUNC_ARG1, FUNC_ARG2);
+	if (ret != FUNC_ARG1 + FUNC_ARG2) {
+		pr_err("FAIL: call_test_func: func returned %lx\n", ret);
+		return false;
+	}
+
+	if (check_test_regs && !test_regs_ok) {
+		pr_err("FAIL: test regs not OK\n");
+		return false;
+	}
+
+	return true;
+}
+
+static int __kprobes pre_handler(struct kprobe *p, struct pt_regs *regs)
+{
+	pre_handler_called = test_func_instance;
+	if (regs->ARM_r0 == FUNC_ARG1 && regs->ARM_r1 == FUNC_ARG2)
+		test_regs_ok = true;
+	return 0;
+}
+
+static void __kprobes post_handler(struct kprobe *p, struct pt_regs *regs,
+				unsigned long flags)
+{
+	post_handler_called = test_func_instance;
+	if (regs->ARM_r0 != FUNC_ARG1 + FUNC_ARG2 || regs->ARM_r1 != FUNC_ARG2)
+		test_regs_ok = false;
+}
+
+static struct kprobe the_kprobe = {
+	.addr		= 0,
+	.pre_handler	= pre_handler,
+	.post_handler	= post_handler
+};
+
+static int test_kprobe(long (*func)(long, long))
+{
+	int ret;
+
+	the_kprobe.addr = (kprobe_opcode_t *)func;
+	ret = register_kprobe(&the_kprobe);
+	if (ret < 0) {
+		pr_err("FAIL: register_kprobe failed with %d\n", ret);
+		return ret;
+	}
+
+	ret = call_test_func(func, true);
+
+	unregister_kprobe(&the_kprobe);
+	the_kprobe.flags = 0; /* Clear disable flag to allow reuse */
+
+	if (!ret)
+		return -EINVAL;
+	if (pre_handler_called != test_func_instance) {
+		pr_err("FAIL: kprobe pre_handler not called\n");
+		return -EINVAL;
+	}
+	if (post_handler_called != test_func_instance) {
+		pr_err("FAIL: kprobe post_handler not called\n");
+		return -EINVAL;
+	}
+	if (!call_test_func(func, false))
+		return -EINVAL;
+	if (pre_handler_called == test_func_instance ||
+				post_handler_called == test_func_instance) {
+		pr_err("FAIL: probe called after unregistering\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void __kprobes jprobe_func(long r0, long r1)
+{
+	jprobe_func_called = test_func_instance;
+	if (r0 == FUNC_ARG1 && r1 == FUNC_ARG2)
+		test_regs_ok = true;
+	jprobe_return();
+}
+
+static struct jprobe the_jprobe = {
+	.entry		= jprobe_func,
+};
+
+static int test_jprobe(long (*func)(long, long))
+{
+	int ret;
+
+	the_jprobe.kp.addr = (kprobe_opcode_t *)func;
+	ret = register_jprobe(&the_jprobe);
+	if (ret < 0) {
+		pr_err("FAIL: register_jprobe failed with %d\n", ret);
+		return ret;
+	}
+
+	ret = call_test_func(func, true);
+
+	unregister_jprobe(&the_jprobe);
+	the_jprobe.kp.flags = 0; /* Clear disable flag to allow reuse */
+
+	if (!ret)
+		return -EINVAL;
+	if (jprobe_func_called != test_func_instance) {
+		pr_err("FAIL: jprobe handler function not called\n");
+		return -EINVAL;
+	}
+	if (!call_test_func(func, false))
+		return -EINVAL;
+	if (jprobe_func_called == test_func_instance) {
+		pr_err("FAIL: probe called after unregistering\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int __kprobes
+kretprobe_handler(struct kretprobe_instance *ri, struct pt_regs *regs)
+{
+	kretprobe_handler_called = test_func_instance;
+	if (regs_return_value(regs) == FUNC_ARG1 + FUNC_ARG2)
+		test_regs_ok = true;
+	return 0;
+}
+
+static struct kretprobe the_kretprobe = {
+	.handler	= kretprobe_handler,
+};
+
+static int test_kretprobe(long (*func)(long, long))
+{
+	int ret;
+
+	the_kretprobe.kp.addr = (kprobe_opcode_t *)func;
+	ret = register_kretprobe(&the_kretprobe);
+	if (ret < 0) {
+		pr_err("FAIL: register_kretprobe failed with %d\n", ret);
+		return ret;
+	}
+
+	ret = call_test_func(func, true);
+
+	unregister_kretprobe(&the_kretprobe);
+	the_kretprobe.kp.flags = 0; /* Clear disable flag to allow reuse */
+
+	if (!ret)
+		return -EINVAL;
+	if (kretprobe_handler_called != test_func_instance) {
+		pr_err("FAIL: kretprobe handler not called\n");
+		return -EINVAL;
+	}
+	if (!call_test_func(func, false))
+		return -EINVAL;
+	if (jprobe_func_called == test_func_instance) {
+		pr_err("FAIL: kretprobe called after unregistering\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int run_api_tests(long (*func)(long, long))
+{
+	int ret;
+
+	pr_info("    kprobe\n");
+	ret = test_kprobe(func);
+	if (ret < 0)
+		return ret;
+
+	pr_info("    jprobe\n");
+	ret = test_jprobe(func);
+	if (ret < 0)
+		return ret;
+
+	pr_info("    kretprobe\n");
+	ret = test_kretprobe(func);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+
+/*
+ * Benchmarking
+ */
+
+#if BENCHMARKING
+
+static void __naked benchmark_nop(void)
+{
+	__asm__ __volatile__ (
+		"nop		\n\t"
+		"bx	lr"
+	);
+}
+
+#ifdef CONFIG_THUMB2_KERNEL
+#define wide ".w"
+#else
+#define wide
+#endif
+
+static void __naked benchmark_pushpop1(void)
+{
+	__asm__ __volatile__ (
+		"stmdb"wide"	sp!, {r3-r11,lr}  \n\t"
+		"ldmia"wide"	sp!, {r3-r11,pc}"
+	);
+}
+
+static void __naked benchmark_pushpop2(void)
+{
+	__asm__ __volatile__ (
+		"stmdb"wide"	sp!, {r0-r8,lr}  \n\t"
+		"ldmia"wide"	sp!, {r0-r8,pc}"
+	);
+}
+
+static void __naked benchmark_pushpop3(void)
+{
+	__asm__ __volatile__ (
+		"stmdb"wide"	sp!, {r4,lr}  \n\t"
+		"ldmia"wide"	sp!, {r4,pc}"
+	);
+}
+
+static void __naked benchmark_pushpop4(void)
+{
+	__asm__ __volatile__ (
+		"stmdb"wide"	sp!, {r0,lr}  \n\t"
+		"ldmia"wide"	sp!, {r0,pc}"
+	);
+}
+
+
+#ifdef CONFIG_THUMB2_KERNEL
+
+static void __naked benchmark_pushpop_thumb(void)
+{
+	__asm__ __volatile__ (
+		"push.n	{r0-r7,lr}  \n\t"
+		"pop.n	{r0-r7,pc}"
+	);
+}
+
+#endif
+
+static int __kprobes
+benchmark_pre_handler(struct kprobe *p, struct pt_regs *regs)
+{
+	return 0;
+}
+
+static int benchmark(void(*fn)(void))
+{
+	unsigned n, i, t, t0;
+
+	for (n = 1000; ; n *= 2) {
+		t0 = sched_clock();
+		for (i = n; i > 0; --i)
+			fn();
+		t = sched_clock() - t0;
+		if (t >= 250000000)
+			break; /* Stop once we took more than 0.25 seconds */
+	}
+	return t / n; /* Time for one iteration in nanoseconds */
+};
+
+static int kprobe_benchmark(void(*fn)(void), unsigned offset)
+{
+	struct kprobe k = {
+		.addr		= (kprobe_opcode_t *)((uintptr_t)fn + offset),
+		.pre_handler	= benchmark_pre_handler,
+	};
+
+	int ret = register_kprobe(&k);
+	if (ret < 0) {
+		pr_err("FAIL: register_kprobe failed with %d\n", ret);
+		return ret;
+	}
+
+	ret = benchmark(fn);
+
+	unregister_kprobe(&k);
+	return ret;
+};
+
+struct benchmarks {
+	void		(*fn)(void);
+	unsigned	offset;
+	const char	*title;
+};
+
+static int run_benchmarks(void)
+{
+	int ret;
+	struct benchmarks list[] = {
+		{&benchmark_nop, 0, "nop"},
+		/*
+		 * benchmark_pushpop{1,3} will have the optimised
+		 * instruction emulation, whilst benchmark_pushpop{2,4} will
+		 * be the equivalent unoptimised instructions.
+		 */
+		{&benchmark_pushpop1, 0, "stmdb	sp!, {r3-r11,lr}"},
+		{&benchmark_pushpop1, 4, "ldmia	sp!, {r3-r11,pc}"},
+		{&benchmark_pushpop2, 0, "stmdb	sp!, {r0-r8,lr}"},
+		{&benchmark_pushpop2, 4, "ldmia	sp!, {r0-r8,pc}"},
+		{&benchmark_pushpop3, 0, "stmdb	sp!, {r4,lr}"},
+		{&benchmark_pushpop3, 4, "ldmia	sp!, {r4,pc}"},
+		{&benchmark_pushpop4, 0, "stmdb	sp!, {r0,lr}"},
+		{&benchmark_pushpop4, 4, "ldmia	sp!, {r0,pc}"},
+#ifdef CONFIG_THUMB2_KERNEL
+		{&benchmark_pushpop_thumb, 0, "push.n	{r0-r7,lr}"},
+		{&benchmark_pushpop_thumb, 2, "pop.n	{r0-r7,pc}"},
+#endif
+		{0}
+	};
+
+	struct benchmarks *b;
+	for (b = list; b->fn; ++b) {
+		ret = kprobe_benchmark(b->fn, b->offset);
+		if (ret < 0)
+			return ret;
+		pr_info("    %dns for kprobe %s\n", ret, b->title);
+	}
+
+	pr_info("\n");
+	return 0;
+}
+
+#endif /* BENCHMARKING */
+
+
+/*
+ * Decoding table self-consistency tests
+ */
+
+static const int decode_struct_sizes[NUM_DECODE_TYPES] = {
+	[DECODE_TYPE_TABLE]	= sizeof(struct decode_table),
+	[DECODE_TYPE_CUSTOM]	= sizeof(struct decode_custom),
+	[DECODE_TYPE_SIMULATE]	= sizeof(struct decode_simulate),
+	[DECODE_TYPE_EMULATE]	= sizeof(struct decode_emulate),
+	[DECODE_TYPE_OR]	= sizeof(struct decode_or),
+	[DECODE_TYPE_REJECT]	= sizeof(struct decode_reject)
+};
+
+static int table_iter(const union decode_item *table,
+			int (*fn)(const struct decode_header *, void *),
+			void *args)
+{
+	const struct decode_header *h = (struct decode_header *)table;
+	int result;
+
+	for (;;) {
+		enum decode_type type = h->type_regs.bits & DECODE_TYPE_MASK;
+
+		if (type == DECODE_TYPE_END)
+			return 0;
+
+		result = fn(h, args);
+		if (result)
+			return result;
+
+		h = (struct decode_header *)
+			((uintptr_t)h + decode_struct_sizes[type]);
+
+	}
+}
+
+static int table_test_fail(const struct decode_header *h, const char* message)
+{
+
+	pr_err("FAIL: kprobes test failure \"%s\" (mask %08x, value %08x)\n",
+					message, h->mask.bits, h->value.bits);
+	return -EINVAL;
+}
+
+struct table_test_args {
+	const union decode_item *root_table;
+	u32			parent_mask;
+	u32			parent_value;
+};
+
+static int table_test_fn(const struct decode_header *h, void *args)
+{
+	struct table_test_args *a = (struct table_test_args *)args;
+	enum decode_type type = h->type_regs.bits & DECODE_TYPE_MASK;
+
+	if (h->value.bits & ~h->mask.bits)
+		return table_test_fail(h, "Match value has bits not in mask");
+
+	if ((h->mask.bits & a->parent_mask) != a->parent_mask)
+		return table_test_fail(h, "Mask has bits not in parent mask");
+
+	if ((h->value.bits ^ a->parent_value) & a->parent_mask)
+		return table_test_fail(h, "Value is inconsistent with parent");
+
+	if (type == DECODE_TYPE_TABLE) {
+		struct decode_table *d = (struct decode_table *)h;
+		struct table_test_args args2 = *a;
+		args2.parent_mask = h->mask.bits;
+		args2.parent_value = h->value.bits;
+		return table_iter(d->table.table, table_test_fn, &args2);
+	}
+
+	return 0;
+}
+
+static int table_test(const union decode_item *table)
+{
+	struct table_test_args args = {
+		.root_table	= table,
+		.parent_mask	= 0,
+		.parent_value	= 0
+	};
+	return table_iter(args.root_table, table_test_fn, &args);
+}
+
+
+/*
+ * Decoding table test coverage analysis
+ *
+ * coverage_start() builds a coverage_table which contains a list of
+ * coverage_entry's to match each entry in the specified kprobes instruction
+ * decoding table.
+ *
+ * When test cases are run, coverage_add() is called to process each case.
+ * This looks up the corresponding entry in the coverage_table and sets it as
+ * being matched, as well as clearing the regs flag appropriate for the test.
+ *
+ * After all test cases have been run, coverage_end() is called to check that
+ * all entries in coverage_table have been matched and that all regs flags are
+ * cleared. I.e. that all possible combinations of instructions described by
+ * the kprobes decoding tables have had a test case executed for them.
+ */
+
+bool coverage_fail;
+
+#define MAX_COVERAGE_ENTRIES 256
+
+struct coverage_entry {
+	const struct decode_header	*header;
+	unsigned			regs;
+	unsigned			nesting;
+	char				matched;
+};
+
+struct coverage_table {
+	struct coverage_entry	*base;
+	unsigned		num_entries;
+	unsigned		nesting;
+};
+
+struct coverage_table coverage;
+
+#define COVERAGE_ANY_REG	(1<<0)
+#define COVERAGE_SP		(1<<1)
+#define COVERAGE_PC		(1<<2)
+#define COVERAGE_PCWB		(1<<3)
+
+static const char coverage_register_lookup[16] = {
+	[REG_TYPE_ANY]		= COVERAGE_ANY_REG | COVERAGE_SP | COVERAGE_PC,
+	[REG_TYPE_SAMEAS16]	= COVERAGE_ANY_REG,
+	[REG_TYPE_SP]		= COVERAGE_SP,
+	[REG_TYPE_PC]		= COVERAGE_PC,
+	[REG_TYPE_NOSP]		= COVERAGE_ANY_REG | COVERAGE_SP,
+	[REG_TYPE_NOSPPC]	= COVERAGE_ANY_REG | COVERAGE_SP | COVERAGE_PC,
+	[REG_TYPE_NOPC]		= COVERAGE_ANY_REG | COVERAGE_PC,
+	[REG_TYPE_NOPCWB]	= COVERAGE_ANY_REG | COVERAGE_PC | COVERAGE_PCWB,
+	[REG_TYPE_NOPCX]	= COVERAGE_ANY_REG,
+	[REG_TYPE_NOSPPCX]	= COVERAGE_ANY_REG | COVERAGE_SP,
+};
+
+unsigned coverage_start_registers(const struct decode_header *h)
+{
+	unsigned regs = 0;
+	int i;
+	for (i = 0; i < 20; i += 4) {
+		int r = (h->type_regs.bits >> (DECODE_TYPE_BITS + i)) & 0xf;
+		regs |= coverage_register_lookup[r] << i;
+	}
+	return regs;
+}
+
+static int coverage_start_fn(const struct decode_header *h, void *args)
+{
+	struct coverage_table *coverage = (struct coverage_table *)args;
+	enum decode_type type = h->type_regs.bits & DECODE_TYPE_MASK;
+	struct coverage_entry *entry = coverage->base + coverage->num_entries;
+
+	if (coverage->num_entries == MAX_COVERAGE_ENTRIES - 1) {
+		pr_err("FAIL: Out of space for test coverage data");
+		return -ENOMEM;
+	}
+
+	++coverage->num_entries;
+
+	entry->header = h;
+	entry->regs = coverage_start_registers(h);
+	entry->nesting = coverage->nesting;
+	entry->matched = false;
+
+	if (type == DECODE_TYPE_TABLE) {
+		struct decode_table *d = (struct decode_table *)h;
+		int ret;
+		++coverage->nesting;
+		ret = table_iter(d->table.table, coverage_start_fn, coverage);
+		--coverage->nesting;
+		return ret;
+	}
+
+	return 0;
+}
+
+static int coverage_start(const union decode_item *table)
+{
+	coverage.base = kmalloc(MAX_COVERAGE_ENTRIES *
+				sizeof(struct coverage_entry), GFP_KERNEL);
+	coverage.num_entries = 0;
+	coverage.nesting = 0;
+	return table_iter(table, coverage_start_fn, &coverage);
+}
+
+static void
+coverage_add_registers(struct coverage_entry *entry, kprobe_opcode_t insn)
+{
+	int regs = entry->header->type_regs.bits >> DECODE_TYPE_BITS;
+	int i;
+	for (i = 0; i < 20; i += 4) {
+		enum decode_reg_type reg_type = (regs >> i) & 0xf;
+		int reg = (insn >> i) & 0xf;
+		int flag;
+
+		if (!reg_type)
+			continue;
+
+		if (reg == 13)
+			flag = COVERAGE_SP;
+		else if (reg == 15)
+			flag = COVERAGE_PC;
+		else
+			flag = COVERAGE_ANY_REG;
+		entry->regs &= ~(flag << i);
+
+		switch (reg_type) {
+
+		case REG_TYPE_NONE:
+		case REG_TYPE_ANY:
+		case REG_TYPE_SAMEAS16:
+			break;
+
+		case REG_TYPE_SP:
+			if (reg != 13)
+				return;
+			break;
+
+		case REG_TYPE_PC:
+			if (reg != 15)
+				return;
+			break;
+
+		case REG_TYPE_NOSP:
+			if (reg == 13)
+				return;
+			break;
+
+		case REG_TYPE_NOSPPC:
+		case REG_TYPE_NOSPPCX:
+			if (reg == 13 || reg == 15)
+				return;
+			break;
+
+		case REG_TYPE_NOPCWB:
+			if (!is_writeback(insn))
+				break;
+			if (reg == 15) {
+				entry->regs &= ~(COVERAGE_PCWB << i);
+				return;
+			}
+			break;
+
+		case REG_TYPE_NOPC:
+		case REG_TYPE_NOPCX:
+			if (reg == 15)
+				return;
+			break;
+		}
+
+	}
+}
+
+static void coverage_add(kprobe_opcode_t insn)
+{
+	struct coverage_entry *entry = coverage.base;
+	struct coverage_entry *end = coverage.base + coverage.num_entries;
+	bool matched = false;
+	unsigned nesting = 0;
+
+	for (; entry < end; ++entry) {
+		const struct decode_header *h = entry->header;
+		enum decode_type type = h->type_regs.bits & DECODE_TYPE_MASK;
+
+		if (entry->nesting > nesting)
+			continue; /* Skip sub-table we didn't match */
+
+		if (entry->nesting < nesting)
+			break; /* End of sub-table we were scanning */
+
+		if (!matched) {
+			if ((insn & h->mask.bits) != h->value.bits)
+				continue;
+			entry->matched = true;
+		}
+
+		switch (type) {
+
+		case DECODE_TYPE_TABLE:
+			++nesting;
+			break;
+
+		case DECODE_TYPE_CUSTOM:
+		case DECODE_TYPE_SIMULATE:
+		case DECODE_TYPE_EMULATE:
+			coverage_add_registers(entry, insn);
+			return;
+
+		case DECODE_TYPE_OR:
+			matched = true;
+			break;
+
+		case DECODE_TYPE_REJECT:
+		default:
+			return;
+		}
+
+	}
+}
+
+static void coverage_end(void)
+{
+	struct coverage_entry *entry = coverage.base;
+	struct coverage_entry *end = coverage.base + coverage.num_entries;
+
+	for (; entry < end; ++entry) {
+		u32 mask = entry->header->mask.bits;
+		u32 value = entry->header->value.bits;
+
+		if (entry->regs) {
+			pr_err("FAIL: Register test coverage missing for %08x %08x (%05x)\n",
+				mask, value, entry->regs);
+			coverage_fail = true;
+		}
+		if (!entry->matched) {
+			pr_err("FAIL: Test coverage entry missing for %08x %08x\n",
+				mask, value);
+			coverage_fail = true;
+		}
+	}
+
+	kfree(coverage.base);
+}
+
+
+/*
+ * Framework for instruction set test cases
+ */
+
+void __naked __kprobes_test_case_start(void)
+{
+	__asm__ __volatile__ (
+		"stmdb	sp!, {r4-r11}				\n\t"
+		"sub	sp, sp, #"__stringify(TEST_MEMORY_SIZE)"\n\t"
+		"bic	r0, lr, #1  @ r0 = inline title string	\n\t"
+		"mov	r1, sp					\n\t"
+		"bl	kprobes_test_case_start			\n\t"
+		"bx	r0					\n\t"
+	);
+}
+
+#ifndef CONFIG_THUMB2_KERNEL
+
+void __naked __kprobes_test_case_end_32(void)
+{
+	__asm__ __volatile__ (
+		"mov	r4, lr					\n\t"
+		"bl	kprobes_test_case_end			\n\t"
+		"cmp	r0, #0					\n\t"
+		"movne	pc, r0					\n\t"
+		"mov	r0, r4					\n\t"
+		"add	sp, sp, #"__stringify(TEST_MEMORY_SIZE)"\n\t"
+		"ldmia	sp!, {r4-r11}				\n\t"
+		"mov	pc, r0					\n\t"
+	);
+}
+
+#else /* CONFIG_THUMB2_KERNEL */
+
+void __naked __kprobes_test_case_end_16(void)
+{
+	__asm__ __volatile__ (
+		"mov	r4, lr					\n\t"
+		"bl	kprobes_test_case_end			\n\t"
+		"cmp	r0, #0					\n\t"
+		"bxne	r0					\n\t"
+		"mov	r0, r4					\n\t"
+		"add	sp, sp, #"__stringify(TEST_MEMORY_SIZE)"\n\t"
+		"ldmia	sp!, {r4-r11}				\n\t"
+		"bx	r0					\n\t"
+	);
+}
+
+void __naked __kprobes_test_case_end_32(void)
+{
+	__asm__ __volatile__ (
+		".arm						\n\t"
+		"orr	lr, lr, #1  @ will return to Thumb code	\n\t"
+		"ldr	pc, 1f					\n\t"
+		"1:						\n\t"
+		".word	__kprobes_test_case_end_16		\n\t"
+	);
+}
+
+#endif
+
+
+int kprobe_test_flags;
+int kprobe_test_cc_position;
+
+static int test_try_count;
+static int test_pass_count;
+static int test_fail_count;
+
+static struct pt_regs initial_regs;
+static struct pt_regs expected_regs;
+static struct pt_regs result_regs;
+
+static u32 expected_memory[TEST_MEMORY_SIZE/sizeof(u32)];
+
+static const char *current_title;
+static struct test_arg *current_args;
+static u32 *current_stack;
+static uintptr_t current_branch_target;
+
+static uintptr_t current_code_start;
+static kprobe_opcode_t current_instruction;
+
+
+#define TEST_CASE_PASSED -1
+#define TEST_CASE_FAILED -2
+
+static int test_case_run_count;
+static bool test_case_is_thumb;
+static int test_instance;
+
+/*
+ * We ignore the state of the imprecise abort disable flag (CPSR.A) because this
+ * can change randomly as the kernel doesn't take care to preserve or initialise
+ * this across context switches. Also, with Security Extentions, the flag may
+ * not be under control of the kernel; for this reason we ignore the state of
+ * the FIQ disable flag CPSR.F as well.
+ */
+#define PSR_IGNORE_BITS (PSR_A_BIT | PSR_F_BIT)
+
+static unsigned long test_check_cc(int cc, unsigned long cpsr)
+{
+	unsigned long temp;
+
+	switch (cc) {
+	case 0x0: /* eq */
+		return cpsr & PSR_Z_BIT;
+
+	case 0x1: /* ne */
+		return (~cpsr) & PSR_Z_BIT;
+
+	case 0x2: /* cs */
+		return cpsr & PSR_C_BIT;
+
+	case 0x3: /* cc */
+		return (~cpsr) & PSR_C_BIT;
+
+	case 0x4: /* mi */
+		return cpsr & PSR_N_BIT;
+
+	case 0x5: /* pl */
+		return (~cpsr) & PSR_N_BIT;
+
+	case 0x6: /* vs */
+		return cpsr & PSR_V_BIT;
+
+	case 0x7: /* vc */
+		return (~cpsr) & PSR_V_BIT;
+
+	case 0x8: /* hi */
+		cpsr &= ~(cpsr >> 1); /* PSR_C_BIT &= ~PSR_Z_BIT */
+		return cpsr & PSR_C_BIT;
+
+	case 0x9: /* ls */
+		cpsr &= ~(cpsr >> 1); /* PSR_C_BIT &= ~PSR_Z_BIT */
+		return (~cpsr) & PSR_C_BIT;
+
+	case 0xa: /* ge */
+		cpsr ^= (cpsr << 3); /* PSR_N_BIT ^= PSR_V_BIT */
+		return (~cpsr) & PSR_N_BIT;
+
+	case 0xb: /* lt */
+		cpsr ^= (cpsr << 3); /* PSR_N_BIT ^= PSR_V_BIT */
+		return cpsr & PSR_N_BIT;
+
+	case 0xc: /* gt */
+		temp = cpsr ^ (cpsr << 3); /* PSR_N_BIT ^= PSR_V_BIT */
+		temp |= (cpsr << 1);	   /* PSR_N_BIT |= PSR_Z_BIT */
+		return (~temp) & PSR_N_BIT;
+
+	case 0xd: /* le */
+		temp = cpsr ^ (cpsr << 3); /* PSR_N_BIT ^= PSR_V_BIT */
+		temp |= (cpsr << 1);	   /* PSR_N_BIT |= PSR_Z_BIT */
+		return temp & PSR_N_BIT;
+
+	case 0xe: /* al */
+	case 0xf: /* unconditional */
+		return true;
+	}
+	BUG();
+	return false;
+}
+
+static int is_last_scenario;
+static int probe_should_run; /* 0 = no, 1 = yes, -1 = unknown */
+static int memory_needs_checking;
+
+static unsigned long test_context_cpsr(int scenario)
+{
+	unsigned long cpsr;
+
+	probe_should_run = 1;
+
+	/* Default case is that we cycle through 16 combinations of flags */
+	cpsr  = (scenario & 0xf) << 28; /* N,Z,C,V flags */
+	cpsr |= (scenario & 0xf) << 16; /* GE flags */
+	cpsr |= (scenario & 0x1) << 27; /* Toggle Q flag */
+
+	if (!test_case_is_thumb) {
+		/* Testing ARM code */
+		probe_should_run = test_check_cc(current_instruction >> 28, cpsr) != 0;
+		if (scenario == 15)
+			is_last_scenario = true;
+
+	} else if (kprobe_test_flags & TEST_FLAG_NO_ITBLOCK) {
+		/* Testing Thumb code without setting ITSTATE */
+		if (kprobe_test_cc_position) {
+			int cc = (current_instruction >> kprobe_test_cc_position) & 0xf;
+			probe_should_run = test_check_cc(cc, cpsr) != 0;
+		}
+
+		if (scenario == 15)
+			is_last_scenario = true;
+
+	} else if (kprobe_test_flags & TEST_FLAG_FULL_ITBLOCK) {
+		/* Testing Thumb code with all combinations of ITSTATE */
+		unsigned x = (scenario >> 4);
+		unsigned cond_base = x % 7; /* ITSTATE<7:5> */
+		unsigned mask = x / 7 + 2;  /* ITSTATE<4:0>, bits reversed */
+
+		if (mask > 0x1f) {
+			/* Finish by testing state from instruction 'itt al' */
+			cond_base = 7;
+			mask = 0x4;
+			if ((scenario & 0xf) == 0xf)
+				is_last_scenario = true;
+		}
+
+		cpsr |= cond_base << 13;	/* ITSTATE<7:5> */
+		cpsr |= (mask & 0x1) << 12;	/* ITSTATE<4> */
+		cpsr |= (mask & 0x2) << 10;	/* ITSTATE<3> */
+		cpsr |= (mask & 0x4) << 8;	/* ITSTATE<2> */
+		cpsr |= (mask & 0x8) << 23;	/* ITSTATE<1> */
+		cpsr |= (mask & 0x10) << 21;	/* ITSTATE<0> */
+
+		probe_should_run = test_check_cc((cpsr >> 12) & 0xf, cpsr) != 0;
+
+	} else {
+		/* Testing Thumb code with several combinations of ITSTATE */
+		switch (scenario) {
+		case 16: /* Clear NZCV flags and 'it eq' state (false as Z=0) */
+			cpsr = 0x00000800;
+			probe_should_run = 0;
+			break;
+		case 17: /* Set NZCV flags and 'it vc' state (false as V=1) */
+			cpsr = 0xf0007800;
+			probe_should_run = 0;
+			break;
+		case 18: /* Clear NZCV flags and 'it ls' state (true as C=0) */
+			cpsr = 0x00009800;
+			break;
+		case 19: /* Set NZCV flags and 'it cs' state (true as C=1) */
+			cpsr = 0xf0002800;
+			is_last_scenario = true;
+			break;
+		}
+	}
+
+	return cpsr;
+}
+
+static void setup_test_context(struct pt_regs *regs)
+{
+	int scenario = test_case_run_count>>1;
+	unsigned long val;
+	struct test_arg *args;
+	int i;
+
+	is_last_scenario = false;
+	memory_needs_checking = false;
+
+	/* Initialise test memory on stack */
+	val = (scenario & 1) ? VALM : ~VALM;
+	for (i = 0; i < TEST_MEMORY_SIZE / sizeof(current_stack[0]); ++i)
+		current_stack[i] = val + (i << 8);
+	/* Put target of branch on stack for tests which load PC from memory */
+	if (current_branch_target)
+		current_stack[15] = current_branch_target;
+	/* Put a value for SP on stack for tests which load SP from memory */
+	current_stack[13] = (u32)current_stack + 120;
+
+	/* Initialise register values to their default state */
+	val = (scenario & 2) ? VALR : ~VALR;
+	for (i = 0; i < 13; ++i)
+		regs->uregs[i] = val ^ (i << 8);
+	regs->ARM_lr = val ^ (14 << 8);
+	regs->ARM_cpsr &= ~(APSR_MASK | PSR_IT_MASK);
+	regs->ARM_cpsr |= test_context_cpsr(scenario);
+
+	/* Perform testcase specific register setup  */
+	args = current_args;
+	for (; args[0].type != ARG_TYPE_END; ++args)
+		switch (args[0].type) {
+		case ARG_TYPE_REG: {
+			struct test_arg_regptr *arg =
+				(struct test_arg_regptr *)args;
+			regs->uregs[arg->reg] = arg->val;
+			break;
+		}
+		case ARG_TYPE_PTR: {
+			struct test_arg_regptr *arg =
+				(struct test_arg_regptr *)args;
+			regs->uregs[arg->reg] =
+				(unsigned long)current_stack + arg->val;
+			memory_needs_checking = true;
+			break;
+		}
+		case ARG_TYPE_MEM: {
+			struct test_arg_mem *arg = (struct test_arg_mem *)args;
+			current_stack[arg->index] = arg->val;
+			break;
+		}
+		default:
+			break;
+		}
+}
+
+struct test_probe {
+	struct kprobe	kprobe;
+	bool		registered;
+	int		hit;
+};
+
+static void unregister_test_probe(struct test_probe *probe)
+{
+	if (probe->registered) {
+		unregister_kprobe(&probe->kprobe);
+		probe->kprobe.flags = 0; /* Clear disable flag to allow reuse */
+	}
+	probe->registered = false;
+}
+
+static int register_test_probe(struct test_probe *probe)
+{
+	int ret;
+
+	if (probe->registered)
+		BUG();
+
+	ret = register_kprobe(&probe->kprobe);
+	if (ret >= 0) {
+		probe->registered = true;
+		probe->hit = -1;
+	}
+	return ret;
+}
+
+static int __kprobes
+test_before_pre_handler(struct kprobe *p, struct pt_regs *regs)
+{
+	container_of(p, struct test_probe, kprobe)->hit = test_instance;
+	return 0;
+}
+
+static void __kprobes
+test_before_post_handler(struct kprobe *p, struct pt_regs *regs,
+							unsigned long flags)
+{
+	setup_test_context(regs);
+	initial_regs = *regs;
+	initial_regs.ARM_cpsr &= ~PSR_IGNORE_BITS;
+}
+
+static int __kprobes
+test_case_pre_handler(struct kprobe *p, struct pt_regs *regs)
+{
+	container_of(p, struct test_probe, kprobe)->hit = test_instance;
+	return 0;
+}
+
+static int __kprobes
+test_after_pre_handler(struct kprobe *p, struct pt_regs *regs)
+{
+	if (container_of(p, struct test_probe, kprobe)->hit == test_instance)
+		return 0; /* Already run for this test instance */
+
+	result_regs = *regs;
+	result_regs.ARM_cpsr &= ~PSR_IGNORE_BITS;
+
+	/* Undo any changes done to SP by the test case */
+	regs->ARM_sp = (unsigned long)current_stack;
+
+	container_of(p, struct test_probe, kprobe)->hit = test_instance;
+	return 0;
+}
+
+static struct test_probe test_before_probe = {
+	.kprobe.pre_handler	= test_before_pre_handler,
+	.kprobe.post_handler	= test_before_post_handler,
+};
+
+static struct test_probe test_case_probe = {
+	.kprobe.pre_handler	= test_case_pre_handler,
+};
+
+static struct test_probe test_after_probe = {
+	.kprobe.pre_handler	= test_after_pre_handler,
+};
+
+static struct test_probe test_after2_probe = {
+	.kprobe.pre_handler	= test_after_pre_handler,
+};
+
+static void test_case_cleanup(void)
+{
+	unregister_test_probe(&test_before_probe);
+	unregister_test_probe(&test_case_probe);
+	unregister_test_probe(&test_after_probe);
+	unregister_test_probe(&test_after2_probe);
+}
+
+static void print_registers(struct pt_regs *regs)
+{
+	pr_err("r0  %08lx | r1  %08lx | r2  %08lx | r3  %08lx\n",
+		regs->ARM_r0, regs->ARM_r1, regs->ARM_r2, regs->ARM_r3);
+	pr_err("r4  %08lx | r5  %08lx | r6  %08lx | r7  %08lx\n",
+		regs->ARM_r4, regs->ARM_r5, regs->ARM_r6, regs->ARM_r7);
+	pr_err("r8  %08lx | r9  %08lx | r10 %08lx | r11 %08lx\n",
+		regs->ARM_r8, regs->ARM_r9, regs->ARM_r10, regs->ARM_fp);
+	pr_err("r12 %08lx | sp  %08lx | lr  %08lx | pc  %08lx\n",
+		regs->ARM_ip, regs->ARM_sp, regs->ARM_lr, regs->ARM_pc);
+	pr_err("cpsr %08lx\n", regs->ARM_cpsr);
+}
+
+static void print_memory(u32 *mem, size_t size)
+{
+	int i;
+	for (i = 0; i < size / sizeof(u32); i += 4)
+		pr_err("%08x %08x %08x %08x\n", mem[i], mem[i+1],
+						mem[i+2], mem[i+3]);
+}
+
+static size_t expected_memory_size(u32 *sp)
+{
+	size_t size = sizeof(expected_memory);
+	int offset = (uintptr_t)sp - (uintptr_t)current_stack;
+	if (offset > 0)
+		size -= offset;
+	return size;
+}
+
+static void test_case_failed(const char *message)
+{
+	test_case_cleanup();
+
+	pr_err("FAIL: %s\n", message);
+	pr_err("FAIL: Test %s\n", current_title);
+	pr_err("FAIL: Scenario %d\n", test_case_run_count >> 1);
+}
+
+static unsigned long next_instruction(unsigned long pc)
+{
+#ifdef CONFIG_THUMB2_KERNEL
+	if ((pc & 1) && !is_wide_instruction(*(u16 *)(pc - 1)))
+		return pc + 2;
+	else
+#endif
+	return pc + 4;
+}
+
+static uintptr_t __used kprobes_test_case_start(const char *title, void *stack)
+{
+	struct test_arg *args;
+	struct test_arg_end *end_arg;
+	unsigned long test_code;
+
+	args = (struct test_arg *)PTR_ALIGN(title + strlen(title) + 1, 4);
+
+	current_title = title;
+	current_args = args;
+	current_stack = stack;
+
+	++test_try_count;
+
+	while (args->type != ARG_TYPE_END)
+		++args;
+	end_arg = (struct test_arg_end *)args;
+
+	test_code = (unsigned long)(args + 1); /* Code starts after args */
+
+	test_case_is_thumb = end_arg->flags & ARG_FLAG_THUMB;
+	if (test_case_is_thumb)
+		test_code |= 1;
+
+	current_code_start = test_code;
+
+	current_branch_target = 0;
+	if (end_arg->branch_offset != end_arg->end_offset)
+		current_branch_target = test_code + end_arg->branch_offset;
+
+	test_code += end_arg->code_offset;
+	test_before_probe.kprobe.addr = (kprobe_opcode_t *)test_code;
+
+	test_code = next_instruction(test_code);
+	test_case_probe.kprobe.addr = (kprobe_opcode_t *)test_code;
+
+	if (test_case_is_thumb) {
+		u16 *p = (u16 *)(test_code & ~1);
+		current_instruction = p[0];
+		if (is_wide_instruction(current_instruction)) {
+			current_instruction <<= 16;
+			current_instruction |= p[1];
+		}
+	} else {
+		current_instruction = *(u32 *)test_code;
+	}
+
+	if (current_title[0] == '.')
+		verbose("%s\n", current_title);
+	else
+		verbose("%s\t@ %0*x\n", current_title,
+					test_case_is_thumb ? 4 : 8,
+					current_instruction);
+
+	test_code = next_instruction(test_code);
+	test_after_probe.kprobe.addr = (kprobe_opcode_t *)test_code;
+
+	if (kprobe_test_flags & TEST_FLAG_NARROW_INSTR) {
+		if (!test_case_is_thumb ||
+			is_wide_instruction(current_instruction)) {
+				test_case_failed("expected 16-bit instruction");
+				goto fail;
+		}
+	} else {
+		if (test_case_is_thumb &&
+			!is_wide_instruction(current_instruction)) {
+				test_case_failed("expected 32-bit instruction");
+				goto fail;
+		}
+	}
+
+	coverage_add(current_instruction);
+
+	if (end_arg->flags & ARG_FLAG_UNSUPPORTED) {
+		if (register_test_probe(&test_case_probe) < 0)
+			goto pass;
+		test_case_failed("registered probe for unsupported instruction");
+		goto fail;
+	}
+
+	if (end_arg->flags & ARG_FLAG_SUPPORTED) {
+		if (register_test_probe(&test_case_probe) >= 0)
+			goto pass;
+		test_case_failed("couldn't register probe for supported instruction");
+		goto fail;
+	}
+
+	if (register_test_probe(&test_before_probe) < 0) {
+		test_case_failed("register test_before_probe failed");
+		goto fail;
+	}
+	if (register_test_probe(&test_after_probe) < 0) {
+		test_case_failed("register test_after_probe failed");
+		goto fail;
+	}
+	if (current_branch_target) {
+		test_after2_probe.kprobe.addr =
+				(kprobe_opcode_t *)current_branch_target;
+		if (register_test_probe(&test_after2_probe) < 0) {
+			test_case_failed("register test_after2_probe failed");
+			goto fail;
+		}
+	}
+
+	/* Start first run of test case */
+	test_case_run_count = 0;
+	++test_instance;
+	return current_code_start;
+pass:
+	test_case_run_count = TEST_CASE_PASSED;
+	return (uintptr_t)test_after_probe.kprobe.addr;
+fail:
+	test_case_run_count = TEST_CASE_FAILED;
+	return (uintptr_t)test_after_probe.kprobe.addr;
+}
+
+static bool check_test_results(void)
+{
+	size_t mem_size = 0;
+	u32 *mem = 0;
+
+	if (memcmp(&expected_regs, &result_regs, sizeof(expected_regs))) {
+		test_case_failed("registers differ");
+		goto fail;
+	}
+
+	if (memory_needs_checking) {
+		mem = (u32 *)result_regs.ARM_sp;
+		mem_size = expected_memory_size(mem);
+		if (memcmp(expected_memory, mem, mem_size)) {
+			test_case_failed("test memory differs");
+			goto fail;
+		}
+	}
+
+	return true;
+
+fail:
+	pr_err("initial_regs:\n");
+	print_registers(&initial_regs);
+	pr_err("expected_regs:\n");
+	print_registers(&expected_regs);
+	pr_err("result_regs:\n");
+	print_registers(&result_regs);
+
+	if (mem) {
+		pr_err("current_stack=%p\n", current_stack);
+		pr_err("expected_memory:\n");
+		print_memory(expected_memory, mem_size);
+		pr_err("result_memory:\n");
+		print_memory(mem, mem_size);
+	}
+
+	return false;
+}
+
+static uintptr_t __used kprobes_test_case_end(void)
+{
+	if (test_case_run_count < 0) {
+		if (test_case_run_count == TEST_CASE_PASSED)
+			/* kprobes_test_case_start did all the needed testing */
+			goto pass;
+		else
+			/* kprobes_test_case_start failed */
+			goto fail;
+	}
+
+	if (test_before_probe.hit != test_instance) {
+		test_case_failed("test_before_handler not run");
+		goto fail;
+	}
+
+	if (test_after_probe.hit != test_instance &&
+				test_after2_probe.hit != test_instance) {
+		test_case_failed("test_after_handler not run");
+		goto fail;
+	}
+
+	/*
+	 * Even numbered test runs ran without a probe on the test case so
+	 * we can gather reference results. The subsequent odd numbered run
+	 * will have the probe inserted.
+	*/
+	if ((test_case_run_count & 1) == 0) {
+		/* Save results from run without probe */
+		u32 *mem = (u32 *)result_regs.ARM_sp;
+		expected_regs = result_regs;
+		memcpy(expected_memory, mem, expected_memory_size(mem));
+
+		/* Insert probe onto test case instruction */
+		if (register_test_probe(&test_case_probe) < 0) {
+			test_case_failed("register test_case_probe failed");
+			goto fail;
+		}
+	} else {
+		/* Check probe ran as expected */
+		if (probe_should_run == 1) {
+			if (test_case_probe.hit != test_instance) {
+				test_case_failed("test_case_handler not run");
+				goto fail;
+			}
+		} else if (probe_should_run == 0) {
+			if (test_case_probe.hit == test_instance) {
+				test_case_failed("test_case_handler ran");
+				goto fail;
+			}
+		}
+
+		/* Remove probe for any subsequent reference run */
+		unregister_test_probe(&test_case_probe);
+
+		if (!check_test_results())
+			goto fail;
+
+		if (is_last_scenario)
+			goto pass;
+	}
+
+	/* Do next test run */
+	++test_case_run_count;
+	++test_instance;
+	return current_code_start;
+fail:
+	++test_fail_count;
+	goto end;
+pass:
+	++test_pass_count;
+end:
+	test_case_cleanup();
+	return 0;
+}
+
+
+/*
+ * Top level test functions
+ */
+
+static int run_test_cases(void (*tests)(void), const union decode_item *table)
+{
+	int ret;
+
+	pr_info("    Check decoding tables\n");
+	ret = table_test(table);
+	if (ret)
+		return ret;
+
+	pr_info("    Run test cases\n");
+	ret = coverage_start(table);
+	if (ret)
+		return ret;
+
+	tests();
+
+	coverage_end();
+	return 0;
+}
+
+
+static int __init run_all_tests(void)
+{
+	int ret = 0;
+
+	pr_info("Begining kprobe tests...\n");
+
+#ifndef CONFIG_THUMB2_KERNEL
+
+	pr_info("Probe ARM code\n");
+	ret = run_api_tests(arm_func);
+	if (ret)
+		goto out;
+
+	pr_info("ARM instruction simulation\n");
+	ret = run_test_cases(kprobe_arm_test_cases, kprobe_decode_arm_table);
+	if (ret)
+		goto out;
+
+#else /* CONFIG_THUMB2_KERNEL */
+
+	pr_info("Probe 16-bit Thumb code\n");
+	ret = run_api_tests(thumb16_func);
+	if (ret)
+		goto out;
+
+	pr_info("Probe 32-bit Thumb code, even halfword\n");
+	ret = run_api_tests(thumb32even_func);
+	if (ret)
+		goto out;
+
+	pr_info("Probe 32-bit Thumb code, odd halfword\n");
+	ret = run_api_tests(thumb32odd_func);
+	if (ret)
+		goto out;
+
+	pr_info("16-bit Thumb instruction simulation\n");
+	ret = run_test_cases(kprobe_thumb16_test_cases,
+				kprobe_decode_thumb16_table);
+	if (ret)
+		goto out;
+
+	pr_info("32-bit Thumb instruction simulation\n");
+	ret = run_test_cases(kprobe_thumb32_test_cases,
+				kprobe_decode_thumb32_table);
+	if (ret)
+		goto out;
+#endif
+
+	pr_info("Total instruction simulation tests=%d, pass=%d fail=%d\n",
+		test_try_count, test_pass_count, test_fail_count);
+	if (test_fail_count) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+#if BENCHMARKING
+	pr_info("Benchmarks\n");
+	ret = run_benchmarks();
+	if (ret)
+		goto out;
+#endif
+
+#if __LINUX_ARM_ARCH__ >= 7
+	/* We are able to run all test cases so coverage should be complete */
+	if (coverage_fail) {
+		pr_err("FAIL: Test coverage checks failed\n");
+		ret = -EINVAL;
+		goto out;
+	}
+#endif
+
+out:
+	if (ret == 0)
+		pr_info("Finished kprobe tests OK\n");
+	else
+		pr_err("kprobe tests failed\n");
+
+	return ret;
+}
+
+
+/*
+ * Module setup
+ */
+
+#ifdef MODULE
+
+static void __exit kprobe_test_exit(void)
+{
+}
+
+module_init(run_all_tests)
+module_exit(kprobe_test_exit)
+MODULE_LICENSE("GPL");
+
+#else /* !MODULE */
+
+late_initcall(run_all_tests);
+
+#endif
diff --git a/arch/arm/kernel/kprobes-test.h b/arch/arm/kernel/kprobes-test.h
new file mode 100644
index 00000000000..e28a869b1ae
--- /dev/null
+++ b/arch/arm/kernel/kprobes-test.h
@@ -0,0 +1,432 @@
+/*
+ * arch/arm/kernel/kprobes-test.h
+ *
+ * Copyright (C) 2011 Jon Medhurst <tixy@yxit.co.uk>.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#define VERBOSE 0 /* Set to '1' for more logging of test cases */
+
+#ifdef CONFIG_THUMB2_KERNEL
+#define NORMAL_ISA "16"
+#else
+#define NORMAL_ISA "32"
+#endif
+
+
+/* Flags used in kprobe_test_flags */
+#define TEST_FLAG_NO_ITBLOCK	(1<<0)
+#define TEST_FLAG_FULL_ITBLOCK	(1<<1)
+#define TEST_FLAG_NARROW_INSTR	(1<<2)
+
+extern int kprobe_test_flags;
+extern int kprobe_test_cc_position;
+
+
+#define TEST_MEMORY_SIZE 256
+
+
+/*
+ * Test case structures.
+ *
+ * The arguments given to test cases can be one of three types.
+ *
+ *   ARG_TYPE_REG
+ *	Load a register with the given value.
+ *
+ *   ARG_TYPE_PTR
+ *	Load a register with a pointer into the stack buffer (SP + given value).
+ *
+ *   ARG_TYPE_MEM
+ *	Store the given value into the stack buffer at [SP+index].
+ *
+ */
+
+#define	ARG_TYPE_END	0
+#define	ARG_TYPE_REG	1
+#define	ARG_TYPE_PTR	2
+#define	ARG_TYPE_MEM	3
+
+#define ARG_FLAG_UNSUPPORTED	0x01
+#define ARG_FLAG_SUPPORTED	0x02
+#define ARG_FLAG_THUMB		0x10	/* Must be 16 so TEST_ISA can be used */
+#define ARG_FLAG_ARM		0x20	/* Must be 32 so TEST_ISA can be used */
+
+struct test_arg {
+	u8	type;		/* ARG_TYPE_x */
+	u8	_padding[7];
+};
+
+struct test_arg_regptr {
+	u8	type;		/* ARG_TYPE_REG or ARG_TYPE_PTR */
+	u8	reg;
+	u8	_padding[2];
+	u32	val;
+};
+
+struct test_arg_mem {
+	u8	type;		/* ARG_TYPE_MEM */
+	u8	index;
+	u8	_padding[2];
+	u32	val;
+};
+
+struct test_arg_end {
+	u8	type;		/* ARG_TYPE_END */
+	u8	flags;		/* ARG_FLAG_x */
+	u16	code_offset;
+	u16	branch_offset;
+	u16	end_offset;
+};
+
+
+/*
+ * Building blocks for test cases.
+ *
+ * Each test case is wrapped between TESTCASE_START and TESTCASE_END.
+ *
+ * To specify arguments for a test case the TEST_ARG_{REG,PTR,MEM} macros are
+ * used followed by a terminating TEST_ARG_END.
+ *
+ * After this, the instruction to be tested is defined with TEST_INSTRUCTION.
+ * Or for branches, TEST_BRANCH_B and TEST_BRANCH_F (branch forwards/backwards).
+ *
+ * Some specific test cases may make use of other custom constructs.
+ */
+
+#if VERBOSE
+#define verbose(fmt, ...) pr_info(fmt, ##__VA_ARGS__)
+#else
+#define verbose(fmt, ...)
+#endif
+
+#define TEST_GROUP(title)					\
+	verbose("\n");						\
+	verbose(title"\n");					\
+	verbose("---------------------------------------------------------\n");
+
+#define TESTCASE_START(title)					\
+	__asm__ __volatile__ (					\
+	"bl	__kprobes_test_case_start		\n\t"	\
+	/* don't use .asciz here as 'title' may be */		\
+	/* multiple strings to be concatenated.  */		\
+	".ascii "#title"				\n\t"	\
+	".byte	0					\n\t"	\
+	".align	2					\n\t"
+
+#define	TEST_ARG_REG(reg, val)					\
+	".byte	"__stringify(ARG_TYPE_REG)"		\n\t"	\
+	".byte	"#reg"					\n\t"	\
+	".short	0					\n\t"	\
+	".word	"#val"					\n\t"
+
+#define	TEST_ARG_PTR(reg, val)					\
+	".byte	"__stringify(ARG_TYPE_PTR)"		\n\t"	\
+	".byte	"#reg"					\n\t"	\
+	".short	0					\n\t"	\
+	".word	"#val"					\n\t"
+
+#define	TEST_ARG_MEM(index, val)				\
+	".byte	"__stringify(ARG_TYPE_MEM)"		\n\t"	\
+	".byte	"#index"				\n\t"	\
+	".short	0					\n\t"	\
+	".word	"#val"					\n\t"
+
+#define	TEST_ARG_END(flags)					\
+	".byte	"__stringify(ARG_TYPE_END)"		\n\t"	\
+	".byte	"TEST_ISA flags"			\n\t"	\
+	".short	50f-0f					\n\t"	\
+	".short	2f-0f					\n\t"	\
+	".short	99f-0f					\n\t"	\
+	".code "TEST_ISA"				\n\t"	\
+	"0:						\n\t"
+
+#define TEST_INSTRUCTION(instruction)				\
+	"50:	nop					\n\t"	\
+	"1:	"instruction"				\n\t"	\
+	"	nop					\n\t"
+
+#define TEST_BRANCH_F(instruction)				\
+	TEST_INSTRUCTION(instruction)				\
+	"	b	99f				\n\t"	\
+	"2:	nop					\n\t"
+
+#define TEST_BRANCH_B(instruction)				\
+	"	b	50f				\n\t"	\
+	"	b	99f				\n\t"	\
+	"2:	nop					\n\t"	\
+	"	b	99f				\n\t"	\
+	TEST_INSTRUCTION(instruction)
+
+#define TEST_BRANCH_FX(instruction, codex)			\
+	TEST_INSTRUCTION(instruction)				\
+	"	b	99f				\n\t"	\
+	codex"						\n\t"	\
+	"	b	99f				\n\t"	\
+	"2:	nop					\n\t"
+
+#define TEST_BRANCH_BX(instruction, codex)			\
+	"	b	50f				\n\t"	\
+	"	b	99f				\n\t"	\
+	"2:	nop					\n\t"	\
+	"	b	99f				\n\t"	\
+	codex"						\n\t"	\
+	TEST_INSTRUCTION(instruction)
+
+#define TESTCASE_END						\
+	"2:						\n\t"	\
+	"99:						\n\t"	\
+	"	bl __kprobes_test_case_end_"TEST_ISA"	\n\t"	\
+	".code "NORMAL_ISA"				\n\t"	\
+	: :							\
+	: "r0", "r1", "r2", "r3", "ip", "lr", "memory", "cc"	\
+	);
+
+
+/*
+ * Macros to define test cases.
+ *
+ * Those of the form TEST_{R,P,M}* can be used to define test cases
+ * which take combinations of the three basic types of arguments. E.g.
+ *
+ *   TEST_R	One register argument
+ *   TEST_RR	Two register arguments
+ *   TEST_RPR	A register, a pointer, then a register argument
+ *
+ * For testing instructions which may branch, there are macros TEST_BF_*
+ * and TEST_BB_* for branching forwards and backwards.
+ *
+ * TEST_SUPPORTED and TEST_UNSUPPORTED don't cause the code to be executed,
+ * the just verify that a kprobe is or is not allowed on the given instruction.
+ */
+
+#define TEST(code)				\
+	TESTCASE_START(code)			\
+	TEST_ARG_END("")			\
+	TEST_INSTRUCTION(code)			\
+	TESTCASE_END
+
+#define TEST_UNSUPPORTED(code)					\
+	TESTCASE_START(code)					\
+	TEST_ARG_END("|"__stringify(ARG_FLAG_UNSUPPORTED))	\
+	TEST_INSTRUCTION(code)					\
+	TESTCASE_END
+
+#define TEST_SUPPORTED(code)					\
+	TESTCASE_START(code)					\
+	TEST_ARG_END("|"__stringify(ARG_FLAG_SUPPORTED))	\
+	TEST_INSTRUCTION(code)					\
+	TESTCASE_END
+
+#define TEST_R(code1, reg, val, code2)			\
+	TESTCASE_START(code1 #reg code2)		\
+	TEST_ARG_REG(reg, val)				\
+	TEST_ARG_END("")				\
+	TEST_INSTRUCTION(code1 #reg code2)		\
+	TESTCASE_END
+
+#define TEST_RR(code1, reg1, val1, code2, reg2, val2, code3)	\
+	TESTCASE_START(code1 #reg1 code2 #reg2 code3)		\
+	TEST_ARG_REG(reg1, val1)				\
+	TEST_ARG_REG(reg2, val2)				\
+	TEST_ARG_END("")					\
+	TEST_INSTRUCTION(code1 #reg1 code2 #reg2 code3)		\
+	TESTCASE_END
+
+#define TEST_RRR(code1, reg1, val1, code2, reg2, val2, code3, reg3, val3, code4)\
+	TESTCASE_START(code1 #reg1 code2 #reg2 code3 #reg3 code4)		\
+	TEST_ARG_REG(reg1, val1)						\
+	TEST_ARG_REG(reg2, val2)						\
+	TEST_ARG_REG(reg3, val3)						\
+	TEST_ARG_END("")							\
+	TEST_INSTRUCTION(code1 #reg1 code2 #reg2 code3 #reg3 code4)		\
+	TESTCASE_END
+
+#define TEST_RRRR(code1, reg1, val1, code2, reg2, val2, code3, reg3, val3, code4, reg4, val4)	\
+	TESTCASE_START(code1 #reg1 code2 #reg2 code3 #reg3 code4 #reg4)		\
+	TEST_ARG_REG(reg1, val1)						\
+	TEST_ARG_REG(reg2, val2)						\
+	TEST_ARG_REG(reg3, val3)						\
+	TEST_ARG_REG(reg4, val4)						\
+	TEST_ARG_END("")							\
+	TEST_INSTRUCTION(code1 #reg1 code2 #reg2 code3 #reg3 code4 #reg4)	\
+	TESTCASE_END
+
+#define TEST_P(code1, reg1, val1, code2)	\
+	TESTCASE_START(code1 #reg1 code2)	\
+	TEST_ARG_PTR(reg1, val1)		\
+	TEST_ARG_END("")			\
+	TEST_INSTRUCTION(code1 #reg1 code2)	\
+	TESTCASE_END
+
+#define TEST_PR(code1, reg1, val1, code2, reg2, val2, code3)	\
+	TESTCASE_START(code1 #reg1 code2 #reg2 code3)		\
+	TEST_ARG_PTR(reg1, val1)				\
+	TEST_ARG_REG(reg2, val2)				\
+	TEST_ARG_END("")					\
+	TEST_INSTRUCTION(code1 #reg1 code2 #reg2 code3)		\
+	TESTCASE_END
+
+#define TEST_RP(code1, reg1, val1, code2, reg2, val2, code3)	\
+	TESTCASE_START(code1 #reg1 code2 #reg2 code3)		\
+	TEST_ARG_REG(reg1, val1)				\
+	TEST_ARG_PTR(reg2, val2)				\
+	TEST_ARG_END("")					\
+	TEST_INSTRUCTION(code1 #reg1 code2 #reg2 code3)		\
+	TESTCASE_END
+
+#define TEST_PRR(code1, reg1, val1, code2, reg2, val2, code3, reg3, val3, code4)\
+	TESTCASE_START(code1 #reg1 code2 #reg2 code3 #reg3 code4)		\
+	TEST_ARG_PTR(reg1, val1)						\
+	TEST_ARG_REG(reg2, val2)						\
+	TEST_ARG_REG(reg3, val3)						\
+	TEST_ARG_END("")							\
+	TEST_INSTRUCTION(code1 #reg1 code2 #reg2 code3 #reg3 code4)		\
+	TESTCASE_END
+
+#define TEST_RPR(code1, reg1, val1, code2, reg2, val2, code3, reg3, val3, code4)\
+	TESTCASE_START(code1 #reg1 code2 #reg2 code3 #reg3 code4)		\
+	TEST_ARG_REG(reg1, val1)						\
+	TEST_ARG_PTR(reg2, val2)						\
+	TEST_ARG_REG(reg3, val3)						\
+	TEST_ARG_END("")							\
+	TEST_INSTRUCTION(code1 #reg1 code2 #reg2 code3 #reg3 code4)		\
+	TESTCASE_END
+
+#define TEST_RRP(code1, reg1, val1, code2, reg2, val2, code3, reg3, val3, code4)\
+	TESTCASE_START(code1 #reg1 code2 #reg2 code3 #reg3 code4)		\
+	TEST_ARG_REG(reg1, val1)						\
+	TEST_ARG_REG(reg2, val2)						\
+	TEST_ARG_PTR(reg3, val3)						\
+	TEST_ARG_END("")							\
+	TEST_INSTRUCTION(code1 #reg1 code2 #reg2 code3 #reg3 code4)		\
+	TESTCASE_END
+
+#define TEST_BF_P(code1, reg1, val1, code2)	\
+	TESTCASE_START(code1 #reg1 code2)	\
+	TEST_ARG_PTR(reg1, val1)		\
+	TEST_ARG_END("")			\
+	TEST_BRANCH_F(code1 #reg1 code2)	\
+	TESTCASE_END
+
+#define TEST_BF(code)				\
+	TESTCASE_START(code)			\
+	TEST_ARG_END("")			\
+	TEST_BRANCH_F(code)			\
+	TESTCASE_END
+
+#define TEST_BB(code)				\
+	TESTCASE_START(code)			\
+	TEST_ARG_END("")			\
+	TEST_BRANCH_B(code)			\
+	TESTCASE_END
+
+#define TEST_BF_R(code1, reg, val, code2)	\
+	TESTCASE_START(code1 #reg code2)	\
+	TEST_ARG_REG(reg, val)			\
+	TEST_ARG_END("")			\
+	TEST_BRANCH_F(code1 #reg code2)		\
+	TESTCASE_END
+
+#define TEST_BB_R(code1, reg, val, code2)	\
+	TESTCASE_START(code1 #reg code2)	\
+	TEST_ARG_REG(reg, val)			\
+	TEST_ARG_END("")			\
+	TEST_BRANCH_B(code1 #reg code2)		\
+	TESTCASE_END
+
+#define TEST_BF_RR(code1, reg1, val1, code2, reg2, val2, code3)	\
+	TESTCASE_START(code1 #reg1 code2 #reg2 code3)		\
+	TEST_ARG_REG(reg1, val1)				\
+	TEST_ARG_REG(reg2, val2)				\
+	TEST_ARG_END("")					\
+	TEST_BRANCH_F(code1 #reg1 code2 #reg2 code3)		\
+	TESTCASE_END
+
+#define TEST_BF_X(code, codex)			\
+	TESTCASE_START(code)			\
+	TEST_ARG_END("")			\
+	TEST_BRANCH_FX(code, codex)		\
+	TESTCASE_END
+
+#define TEST_BB_X(code, codex)			\
+	TESTCASE_START(code)			\
+	TEST_ARG_END("")			\
+	TEST_BRANCH_BX(code, codex)		\
+	TESTCASE_END
+
+#define TEST_BF_RX(code1, reg, val, code2, codex)	\
+	TESTCASE_START(code1 #reg code2)		\
+	TEST_ARG_REG(reg, val)				\
+	TEST_ARG_END("")				\
+	TEST_BRANCH_FX(code1 #reg code2, codex)		\
+	TESTCASE_END
+
+#define TEST_X(code, codex)			\
+	TESTCASE_START(code)			\
+	TEST_ARG_END("")			\
+	TEST_INSTRUCTION(code)			\
+	"	b	99f		\n\t"	\
+	"	"codex"			\n\t"	\
+	TESTCASE_END
+
+#define TEST_RX(code1, reg, val, code2, codex)		\
+	TESTCASE_START(code1 #reg code2)		\
+	TEST_ARG_REG(reg, val)				\
+	TEST_ARG_END("")				\
+	TEST_INSTRUCTION(code1 __stringify(reg) code2)	\
+	"	b	99f		\n\t"		\
+	"	"codex"			\n\t"		\
+	TESTCASE_END
+
+#define TEST_RRX(code1, reg1, val1, code2, reg2, val2, code3, codex)		\
+	TESTCASE_START(code1 #reg1 code2 #reg2 code3)				\
+	TEST_ARG_REG(reg1, val1)						\
+	TEST_ARG_REG(reg2, val2)						\
+	TEST_ARG_END("")							\
+	TEST_INSTRUCTION(code1 __stringify(reg1) code2 __stringify(reg2) code3)	\
+	"	b	99f		\n\t"					\
+	"	"codex"			\n\t"					\
+	TESTCASE_END
+
+
+/*
+ * Macros for defining space directives spread over multiple lines.
+ * These are required so the compiler guesses better the length of inline asm
+ * code and will spill the literal pool early enough to avoid generating PC
+ * relative loads with out of range offsets.
+ */
+#define TWICE(x)	x x
+#define SPACE_0x8	TWICE(".space 4\n\t")
+#define SPACE_0x10	TWICE(SPACE_0x8)
+#define SPACE_0x20	TWICE(SPACE_0x10)
+#define SPACE_0x40	TWICE(SPACE_0x20)
+#define SPACE_0x80	TWICE(SPACE_0x40)
+#define SPACE_0x100	TWICE(SPACE_0x80)
+#define SPACE_0x200	TWICE(SPACE_0x100)
+#define SPACE_0x400	TWICE(SPACE_0x200)
+#define SPACE_0x800	TWICE(SPACE_0x400)
+#define SPACE_0x1000	TWICE(SPACE_0x800)
+
+
+/* Various values used in test cases... */
+#define N(val)	(val ^ 0xffffffff)
+#define VAL1	0x12345678
+#define VAL2	N(VAL1)
+#define VAL3	0xa5f801
+#define VAL4	N(VAL3)
+#define VALM	0x456789ab
+#define VALR	0xdeaddead
+#define HH1	0x0123fecb
+#define HH2	0xa9874567
+
+
+#ifdef CONFIG_THUMB2_KERNEL
+void kprobe_thumb16_test_cases(void);
+void kprobe_thumb32_test_cases(void);
+#else
+void kprobe_arm_test_cases(void);
+#endif
diff --git a/arch/arm/kernel/kprobes-thumb.c b/arch/arm/kernel/kprobes-thumb.c
index 902ca59e8b1..8f96ec778e8 100644
--- a/arch/arm/kernel/kprobes-thumb.c
+++ b/arch/arm/kernel/kprobes-thumb.c
@@ -10,6 +10,7 @@
 
 #include <linux/kernel.h>
 #include <linux/kprobes.h>
+#include <linux/module.h>
 
 #include "kprobes.h"
 
@@ -943,6 +944,9 @@ const union decode_item kprobe_decode_thumb32_table[] = {
 	 */
 	DECODE_END
 };
+#ifdef CONFIG_ARM_KPROBES_TEST_MODULE
+EXPORT_SYMBOL_GPL(kprobe_decode_thumb32_table);
+#endif
 
 static void __kprobes
 t16_simulate_bxblx(struct kprobe *p, struct pt_regs *regs)
@@ -1423,6 +1427,9 @@ const union decode_item kprobe_decode_thumb16_table[] = {
 
 	DECODE_END
 };
+#ifdef CONFIG_ARM_KPROBES_TEST_MODULE
+EXPORT_SYMBOL_GPL(kprobe_decode_thumb16_table);
+#endif
 
 static unsigned long __kprobes thumb_check_cc(unsigned long cpsr)
 {
diff --git a/arch/arm/kernel/kprobes.h b/arch/arm/kernel/kprobes.h
index a6aeda0a6c7..38945f78f9f 100644
--- a/arch/arm/kernel/kprobes.h
+++ b/arch/arm/kernel/kprobes.h
@@ -413,6 +413,14 @@ struct decode_reject {
 	DECODE_HEADER(DECODE_TYPE_REJECT, _mask, _value, 0)
 
 
+#ifdef CONFIG_THUMB2_KERNEL
+extern const union decode_item kprobe_decode_thumb16_table[];
+extern const union decode_item kprobe_decode_thumb32_table[];
+#else
+extern const union decode_item kprobe_decode_arm_table[];
+#endif
+
+
 int kprobe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi,
 			const union decode_item *table, bool thumb16);
 
diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c
index cc2020c2c70..1e9be5d25e5 100644
--- a/arch/arm/kernel/module.c
+++ b/arch/arm/kernel/module.c
@@ -33,7 +33,7 @@
  * recompiling the whole kernel when CONFIG_XIP_KERNEL is turned on/off.
  */
 #undef MODULES_VADDR
-#define MODULES_VADDR	(((unsigned long)_etext + ~PGDIR_MASK) & PGDIR_MASK)
+#define MODULES_VADDR	(((unsigned long)_etext + ~PMD_MASK) & PMD_MASK)
 #endif
 
 #ifdef CONFIG_MMU
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index 53c9c2610cb..eacc1b09060 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -12,6 +12,7 @@
  */
 #define pr_fmt(fmt) "hw perfevents: " fmt
 
+#include <linux/bitmap.h>
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -26,16 +27,8 @@
 #include <asm/pmu.h>
 #include <asm/stacktrace.h>
 
-static struct platform_device *pmu_device;
-
 /*
- * Hardware lock to serialize accesses to PMU registers. Needed for the
- * read/modify/write sequences.
- */
-static DEFINE_RAW_SPINLOCK(pmu_lock);
-
-/*
- * ARMv6 supports a maximum of 3 events, starting from index 1. If we add
+ * ARMv6 supports a maximum of 3 events, starting from index 0. If we add
  * another platform that supports more, we need to increase this to be the
  * largest of all platforms.
  *
@@ -43,62 +36,24 @@ static DEFINE_RAW_SPINLOCK(pmu_lock);
  *  cycle counter CCNT + 31 events counters CNT0..30.
  *  Cortex-A8 has 1+4 counters, Cortex-A9 has 1+6 counters.
  */
-#define ARMPMU_MAX_HWEVENTS		33
+#define ARMPMU_MAX_HWEVENTS		32
 
-/* The events for a given CPU. */
-struct cpu_hw_events {
-	/*
-	 * The events that are active on the CPU for the given index. Index 0
-	 * is reserved.
-	 */
-	struct perf_event	*events[ARMPMU_MAX_HWEVENTS];
+static DEFINE_PER_CPU(struct perf_event * [ARMPMU_MAX_HWEVENTS], hw_events);
+static DEFINE_PER_CPU(unsigned long [BITS_TO_LONGS(ARMPMU_MAX_HWEVENTS)], used_mask);
+static DEFINE_PER_CPU(struct pmu_hw_events, cpu_hw_events);
 
-	/*
-	 * A 1 bit for an index indicates that the counter is being used for
-	 * an event. A 0 means that the counter can be used.
-	 */
-	unsigned long		used_mask[BITS_TO_LONGS(ARMPMU_MAX_HWEVENTS)];
-
-	/*
-	 * A 1 bit for an index indicates that the counter is actively being
-	 * used.
-	 */
-	unsigned long		active_mask[BITS_TO_LONGS(ARMPMU_MAX_HWEVENTS)];
-};
-static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events);
-
-struct arm_pmu {
-	enum arm_perf_pmu_ids id;
-	const char	*name;
-	irqreturn_t	(*handle_irq)(int irq_num, void *dev);
-	void		(*enable)(struct hw_perf_event *evt, int idx);
-	void		(*disable)(struct hw_perf_event *evt, int idx);
-	int		(*get_event_idx)(struct cpu_hw_events *cpuc,
-					 struct hw_perf_event *hwc);
-	u32		(*read_counter)(int idx);
-	void		(*write_counter)(int idx, u32 val);
-	void		(*start)(void);
-	void		(*stop)(void);
-	void		(*reset)(void *);
-	const unsigned	(*cache_map)[PERF_COUNT_HW_CACHE_MAX]
-				    [PERF_COUNT_HW_CACHE_OP_MAX]
-				    [PERF_COUNT_HW_CACHE_RESULT_MAX];
-	const unsigned	(*event_map)[PERF_COUNT_HW_MAX];
-	u32		raw_event_mask;
-	int		num_events;
-	u64		max_period;
-};
+#define to_arm_pmu(p) (container_of(p, struct arm_pmu, pmu))
 
 /* Set at runtime when we know what CPU type we are. */
-static const struct arm_pmu *armpmu;
+static struct arm_pmu *cpu_pmu;
 
 enum arm_perf_pmu_ids
 armpmu_get_pmu_id(void)
 {
 	int id = -ENODEV;
 
-	if (armpmu != NULL)
-		id = armpmu->id;
+	if (cpu_pmu != NULL)
+		id = cpu_pmu->id;
 
 	return id;
 }
@@ -109,8 +64,8 @@ armpmu_get_max_events(void)
 {
 	int max_events = 0;
 
-	if (armpmu != NULL)
-		max_events = armpmu->num_events;
+	if (cpu_pmu != NULL)
+		max_events = cpu_pmu->num_events;
 
 	return max_events;
 }
@@ -130,7 +85,11 @@ EXPORT_SYMBOL_GPL(perf_num_counters);
 #define CACHE_OP_UNSUPPORTED		0xFFFF
 
 static int
-armpmu_map_cache_event(u64 config)
+armpmu_map_cache_event(const unsigned (*cache_map)
+				      [PERF_COUNT_HW_CACHE_MAX]
+				      [PERF_COUNT_HW_CACHE_OP_MAX]
+				      [PERF_COUNT_HW_CACHE_RESULT_MAX],
+		       u64 config)
 {
 	unsigned int cache_type, cache_op, cache_result, ret;
 
@@ -146,7 +105,7 @@ armpmu_map_cache_event(u64 config)
 	if (cache_result >= PERF_COUNT_HW_CACHE_RESULT_MAX)
 		return -EINVAL;
 
-	ret = (int)(*armpmu->cache_map)[cache_type][cache_op][cache_result];
+	ret = (int)(*cache_map)[cache_type][cache_op][cache_result];
 
 	if (ret == CACHE_OP_UNSUPPORTED)
 		return -ENOENT;
@@ -155,23 +114,46 @@ armpmu_map_cache_event(u64 config)
 }
 
 static int
-armpmu_map_event(u64 config)
+armpmu_map_event(const unsigned (*event_map)[PERF_COUNT_HW_MAX], u64 config)
 {
-	int mapping = (*armpmu->event_map)[config];
-	return mapping == HW_OP_UNSUPPORTED ? -EOPNOTSUPP : mapping;
+	int mapping = (*event_map)[config];
+	return mapping == HW_OP_UNSUPPORTED ? -ENOENT : mapping;
 }
 
 static int
-armpmu_map_raw_event(u64 config)
+armpmu_map_raw_event(u32 raw_event_mask, u64 config)
 {
-	return (int)(config & armpmu->raw_event_mask);
+	return (int)(config & raw_event_mask);
 }
 
-static int
+static int map_cpu_event(struct perf_event *event,
+			 const unsigned (*event_map)[PERF_COUNT_HW_MAX],
+			 const unsigned (*cache_map)
+					[PERF_COUNT_HW_CACHE_MAX]
+					[PERF_COUNT_HW_CACHE_OP_MAX]
+					[PERF_COUNT_HW_CACHE_RESULT_MAX],
+			 u32 raw_event_mask)
+{
+	u64 config = event->attr.config;
+
+	switch (event->attr.type) {
+	case PERF_TYPE_HARDWARE:
+		return armpmu_map_event(event_map, config);
+	case PERF_TYPE_HW_CACHE:
+		return armpmu_map_cache_event(cache_map, config);
+	case PERF_TYPE_RAW:
+		return armpmu_map_raw_event(raw_event_mask, config);
+	}
+
+	return -ENOENT;
+}
+
+int
 armpmu_event_set_period(struct perf_event *event,
 			struct hw_perf_event *hwc,
 			int idx)
 {
+	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	s64 left = local64_read(&hwc->period_left);
 	s64 period = hwc->sample_period;
 	int ret = 0;
@@ -202,11 +184,12 @@ armpmu_event_set_period(struct perf_event *event,
 	return ret;
 }
 
-static u64
+u64
 armpmu_event_update(struct perf_event *event,
 		    struct hw_perf_event *hwc,
 		    int idx, int overflow)
 {
+	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	u64 delta, prev_raw_count, new_raw_count;
 
 again:
@@ -246,11 +229,9 @@ armpmu_read(struct perf_event *event)
 static void
 armpmu_stop(struct perf_event *event, int flags)
 {
+	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
 
-	if (!armpmu)
-		return;
-
 	/*
 	 * ARM pmu always has to update the counter, so ignore
 	 * PERF_EF_UPDATE, see comments in armpmu_start().
@@ -266,11 +247,9 @@ armpmu_stop(struct perf_event *event, int flags)
 static void
 armpmu_start(struct perf_event *event, int flags)
 {
+	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
 
-	if (!armpmu)
-		return;
-
 	/*
 	 * ARM pmu always has to reprogram the period, so ignore
 	 * PERF_EF_RELOAD, see the comment below.
@@ -293,16 +272,16 @@ armpmu_start(struct perf_event *event, int flags)
 static void
 armpmu_del(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
+	struct pmu_hw_events *hw_events = armpmu->get_hw_events();
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 
 	WARN_ON(idx < 0);
 
-	clear_bit(idx, cpuc->active_mask);
 	armpmu_stop(event, PERF_EF_UPDATE);
-	cpuc->events[idx] = NULL;
-	clear_bit(idx, cpuc->used_mask);
+	hw_events->events[idx] = NULL;
+	clear_bit(idx, hw_events->used_mask);
 
 	perf_event_update_userpage(event);
 }
@@ -310,7 +289,8 @@ armpmu_del(struct perf_event *event, int flags)
 static int
 armpmu_add(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
+	struct pmu_hw_events *hw_events = armpmu->get_hw_events();
 	struct hw_perf_event *hwc = &event->hw;
 	int idx;
 	int err = 0;
@@ -318,7 +298,7 @@ armpmu_add(struct perf_event *event, int flags)
 	perf_pmu_disable(event->pmu);
 
 	/* If we don't have a space for the counter then finish early. */
-	idx = armpmu->get_event_idx(cpuc, hwc);
+	idx = armpmu->get_event_idx(hw_events, hwc);
 	if (idx < 0) {
 		err = idx;
 		goto out;
@@ -330,8 +310,7 @@ armpmu_add(struct perf_event *event, int flags)
 	 */
 	event->hw.idx = idx;
 	armpmu->disable(hwc, idx);
-	cpuc->events[idx] = event;
-	set_bit(idx, cpuc->active_mask);
+	hw_events->events[idx] = event;
 
 	hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
 	if (flags & PERF_EF_START)
@@ -345,27 +324,33 @@ out:
 	return err;
 }
 
-static struct pmu pmu;
-
 static int
-validate_event(struct cpu_hw_events *cpuc,
+validate_event(struct pmu_hw_events *hw_events,
 	       struct perf_event *event)
 {
+	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event fake_event = event->hw;
+	struct pmu *leader_pmu = event->group_leader->pmu;
 
-	if (event->pmu != &pmu || event->state <= PERF_EVENT_STATE_OFF)
+	if (event->pmu != leader_pmu || event->state <= PERF_EVENT_STATE_OFF)
 		return 1;
 
-	return armpmu->get_event_idx(cpuc, &fake_event) >= 0;
+	return armpmu->get_event_idx(hw_events, &fake_event) >= 0;
 }
 
 static int
 validate_group(struct perf_event *event)
 {
 	struct perf_event *sibling, *leader = event->group_leader;
-	struct cpu_hw_events fake_pmu;
+	struct pmu_hw_events fake_pmu;
+	DECLARE_BITMAP(fake_used_mask, ARMPMU_MAX_HWEVENTS);
 
-	memset(&fake_pmu, 0, sizeof(fake_pmu));
+	/*
+	 * Initialise the fake PMU. We only need to populate the
+	 * used_mask for the purposes of validation.
+	 */
+	memset(fake_used_mask, 0, sizeof(fake_used_mask));
+	fake_pmu.used_mask = fake_used_mask;
 
 	if (!validate_event(&fake_pmu, leader))
 		return -ENOSPC;
@@ -383,110 +368,122 @@ validate_group(struct perf_event *event)
 
 static irqreturn_t armpmu_platform_irq(int irq, void *dev)
 {
-	struct arm_pmu_platdata *plat = dev_get_platdata(&pmu_device->dev);
+	struct arm_pmu *armpmu = (struct arm_pmu *) dev;
+	struct platform_device *plat_device = armpmu->plat_device;
+	struct arm_pmu_platdata *plat = dev_get_platdata(&plat_device->dev);
 
 	return plat->handle_irq(irq, dev, armpmu->handle_irq);
 }
 
+static void
+armpmu_release_hardware(struct arm_pmu *armpmu)
+{
+	int i, irq, irqs;
+	struct platform_device *pmu_device = armpmu->plat_device;
+
+	irqs = min(pmu_device->num_resources, num_possible_cpus());
+
+	for (i = 0; i < irqs; ++i) {
+		if (!cpumask_test_and_clear_cpu(i, &armpmu->active_irqs))
+			continue;
+		irq = platform_get_irq(pmu_device, i);
+		if (irq >= 0)
+			free_irq(irq, armpmu);
+	}
+
+	release_pmu(armpmu->type);
+}
+
 static int
-armpmu_reserve_hardware(void)
+armpmu_reserve_hardware(struct arm_pmu *armpmu)
 {
 	struct arm_pmu_platdata *plat;
 	irq_handler_t handle_irq;
-	int i, err = -ENODEV, irq;
+	int i, err, irq, irqs;
+	struct platform_device *pmu_device = armpmu->plat_device;
 
-	pmu_device = reserve_pmu(ARM_PMU_DEVICE_CPU);
-	if (IS_ERR(pmu_device)) {
+	if (!pmu_device)
+		return -ENODEV;
+
+	err = reserve_pmu(armpmu->type);
+	if (err) {
 		pr_warning("unable to reserve pmu\n");
-		return PTR_ERR(pmu_device);
+		return err;
 	}
 
-	init_pmu(ARM_PMU_DEVICE_CPU);
-
 	plat = dev_get_platdata(&pmu_device->dev);
 	if (plat && plat->handle_irq)
 		handle_irq = armpmu_platform_irq;
 	else
 		handle_irq = armpmu->handle_irq;
 
-	if (pmu_device->num_resources < 1) {
+	irqs = min(pmu_device->num_resources, num_possible_cpus());
+	if (irqs < 1) {
 		pr_err("no irqs for PMUs defined\n");
 		return -ENODEV;
 	}
 
-	for (i = 0; i < pmu_device->num_resources; ++i) {
+	for (i = 0; i < irqs; ++i) {
+		err = 0;
 		irq = platform_get_irq(pmu_device, i);
 		if (irq < 0)
 			continue;
 
+		/*
+		 * If we have a single PMU interrupt that we can't shift,
+		 * assume that we're running on a uniprocessor machine and
+		 * continue. Otherwise, continue without this interrupt.
+		 */
+		if (irq_set_affinity(irq, cpumask_of(i)) && irqs > 1) {
+			pr_warning("unable to set irq affinity (irq=%d, cpu=%u)\n",
+				    irq, i);
+			continue;
+		}
+
 		err = request_irq(irq, handle_irq,
 				  IRQF_DISABLED | IRQF_NOBALANCING,
-				  "armpmu", NULL);
+				  "arm-pmu", armpmu);
 		if (err) {
-			pr_warning("unable to request IRQ%d for ARM perf "
-				"counters\n", irq);
-			break;
+			pr_err("unable to request IRQ%d for ARM PMU counters\n",
+				irq);
+			armpmu_release_hardware(armpmu);
+			return err;
 		}
-	}
 
-	if (err) {
-		for (i = i - 1; i >= 0; --i) {
-			irq = platform_get_irq(pmu_device, i);
-			if (irq >= 0)
-				free_irq(irq, NULL);
-		}
-		release_pmu(ARM_PMU_DEVICE_CPU);
-		pmu_device = NULL;
+		cpumask_set_cpu(i, &armpmu->active_irqs);
 	}
 
-	return err;
+	return 0;
 }
 
 static void
-armpmu_release_hardware(void)
+hw_perf_event_destroy(struct perf_event *event)
 {
-	int i, irq;
+	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
+	atomic_t *active_events	 = &armpmu->active_events;
+	struct mutex *pmu_reserve_mutex = &armpmu->reserve_mutex;
 
-	for (i = pmu_device->num_resources - 1; i >= 0; --i) {
-		irq = platform_get_irq(pmu_device, i);
-		if (irq >= 0)
-			free_irq(irq, NULL);
+	if (atomic_dec_and_mutex_lock(active_events, pmu_reserve_mutex)) {
+		armpmu_release_hardware(armpmu);
+		mutex_unlock(pmu_reserve_mutex);
 	}
-	armpmu->stop();
-
-	release_pmu(ARM_PMU_DEVICE_CPU);
-	pmu_device = NULL;
 }
 
-static atomic_t active_events = ATOMIC_INIT(0);
-static DEFINE_MUTEX(pmu_reserve_mutex);
-
-static void
-hw_perf_event_destroy(struct perf_event *event)
+static int
+event_requires_mode_exclusion(struct perf_event_attr *attr)
 {
-	if (atomic_dec_and_mutex_lock(&active_events, &pmu_reserve_mutex)) {
-		armpmu_release_hardware();
-		mutex_unlock(&pmu_reserve_mutex);
-	}
+	return attr->exclude_idle || attr->exclude_user ||
+	       attr->exclude_kernel || attr->exclude_hv;
 }
 
 static int
 __hw_perf_event_init(struct perf_event *event)
 {
+	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
 	int mapping, err;
 
-	/* Decode the generic type into an ARM event identifier. */
-	if (PERF_TYPE_HARDWARE == event->attr.type) {
-		mapping = armpmu_map_event(event->attr.config);
-	} else if (PERF_TYPE_HW_CACHE == event->attr.type) {
-		mapping = armpmu_map_cache_event(event->attr.config);
-	} else if (PERF_TYPE_RAW == event->attr.type) {
-		mapping = armpmu_map_raw_event(event->attr.config);
-	} else {
-		pr_debug("event type %x not supported\n", event->attr.type);
-		return -EOPNOTSUPP;
-	}
+	mapping = armpmu->map_event(event);
 
 	if (mapping < 0) {
 		pr_debug("event %x:%llx not supported\n", event->attr.type,
@@ -495,34 +492,31 @@ __hw_perf_event_init(struct perf_event *event)
 	}
 
 	/*
+	 * We don't assign an index until we actually place the event onto
+	 * hardware. Use -1 to signify that we haven't decided where to put it
+	 * yet. For SMP systems, each core has it's own PMU so we can't do any
+	 * clever allocation or constraints checking at this point.
+	 */
+	hwc->idx		= -1;
+	hwc->config_base	= 0;
+	hwc->config		= 0;
+	hwc->event_base		= 0;
+
+	/*
 	 * Check whether we need to exclude the counter from certain modes.
-	 * The ARM performance counters are on all of the time so if someone
-	 * has asked us for some excludes then we have to fail.
 	 */
-	if (event->attr.exclude_kernel || event->attr.exclude_user ||
-	    event->attr.exclude_hv || event->attr.exclude_idle) {
+	if ((!armpmu->set_event_filter ||
+	     armpmu->set_event_filter(hwc, &event->attr)) &&
+	     event_requires_mode_exclusion(&event->attr)) {
 		pr_debug("ARM performance counters do not support "
 			 "mode exclusion\n");
 		return -EPERM;
 	}
 
 	/*
-	 * We don't assign an index until we actually place the event onto
-	 * hardware. Use -1 to signify that we haven't decided where to put it
-	 * yet. For SMP systems, each core has it's own PMU so we can't do any
-	 * clever allocation or constraints checking at this point.
+	 * Store the event encoding into the config_base field.
 	 */
-	hwc->idx = -1;
-
-	/*
-	 * Store the event encoding into the config_base field. config and
-	 * event_base are unused as the only 2 things we need to know are
-	 * the event mapping and the counter to use. The counter to use is
-	 * also the indx and the config_base is the event type.
-	 */
-	hwc->config_base	    = (unsigned long)mapping;
-	hwc->config		    = 0;
-	hwc->event_base		    = 0;
+	hwc->config_base	    |= (unsigned long)mapping;
 
 	if (!hwc->sample_period) {
 		hwc->sample_period  = armpmu->max_period;
@@ -542,32 +536,23 @@ __hw_perf_event_init(struct perf_event *event)
 
 static int armpmu_event_init(struct perf_event *event)
 {
+	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	int err = 0;
+	atomic_t *active_events = &armpmu->active_events;
 
-	switch (event->attr.type) {
-	case PERF_TYPE_RAW:
-	case PERF_TYPE_HARDWARE:
-	case PERF_TYPE_HW_CACHE:
-		break;
-
-	default:
+	if (armpmu->map_event(event) == -ENOENT)
 		return -ENOENT;
-	}
-
-	if (!armpmu)
-		return -ENODEV;
 
 	event->destroy = hw_perf_event_destroy;
 
-	if (!atomic_inc_not_zero(&active_events)) {
-		mutex_lock(&pmu_reserve_mutex);
-		if (atomic_read(&active_events) == 0) {
-			err = armpmu_reserve_hardware();
-		}
+	if (!atomic_inc_not_zero(active_events)) {
+		mutex_lock(&armpmu->reserve_mutex);
+		if (atomic_read(active_events) == 0)
+			err = armpmu_reserve_hardware(armpmu);
 
 		if (!err)
-			atomic_inc(&active_events);
-		mutex_unlock(&pmu_reserve_mutex);
+			atomic_inc(active_events);
+		mutex_unlock(&armpmu->reserve_mutex);
 	}
 
 	if (err)
@@ -582,22 +567,9 @@ static int armpmu_event_init(struct perf_event *event)
 
 static void armpmu_enable(struct pmu *pmu)
 {
-	/* Enable all of the perf events on hardware. */
-	int idx, enabled = 0;
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
-
-	if (!armpmu)
-		return;
-
-	for (idx = 0; idx <= armpmu->num_events; ++idx) {
-		struct perf_event *event = cpuc->events[idx];
-
-		if (!event)
-			continue;
-
-		armpmu->enable(&event->hw, idx);
-		enabled = 1;
-	}
+	struct arm_pmu *armpmu = to_arm_pmu(pmu);
+	struct pmu_hw_events *hw_events = armpmu->get_hw_events();
+	int enabled = bitmap_weight(hw_events->used_mask, armpmu->num_events);
 
 	if (enabled)
 		armpmu->start();
@@ -605,20 +577,32 @@ static void armpmu_enable(struct pmu *pmu)
 
 static void armpmu_disable(struct pmu *pmu)
 {
-	if (armpmu)
-		armpmu->stop();
+	struct arm_pmu *armpmu = to_arm_pmu(pmu);
+	armpmu->stop();
+}
+
+static void __init armpmu_init(struct arm_pmu *armpmu)
+{
+	atomic_set(&armpmu->active_events, 0);
+	mutex_init(&armpmu->reserve_mutex);
+
+	armpmu->pmu = (struct pmu) {
+		.pmu_enable	= armpmu_enable,
+		.pmu_disable	= armpmu_disable,
+		.event_init	= armpmu_event_init,
+		.add		= armpmu_add,
+		.del		= armpmu_del,
+		.start		= armpmu_start,
+		.stop		= armpmu_stop,
+		.read		= armpmu_read,
+	};
 }
 
-static struct pmu pmu = {
-	.pmu_enable	= armpmu_enable,
-	.pmu_disable	= armpmu_disable,
-	.event_init	= armpmu_event_init,
-	.add		= armpmu_add,
-	.del		= armpmu_del,
-	.start		= armpmu_start,
-	.stop		= armpmu_stop,
-	.read		= armpmu_read,
-};
+int __init armpmu_register(struct arm_pmu *armpmu, char *name, int type)
+{
+	armpmu_init(armpmu);
+	return perf_pmu_register(&armpmu->pmu, name, type);
+}
 
 /* Include the PMU-specific implementations. */
 #include "perf_event_xscale.c"
@@ -630,14 +614,75 @@ static struct pmu pmu = {
  * This requires SMP to be available, so exists as a separate initcall.
  */
 static int __init
-armpmu_reset(void)
+cpu_pmu_reset(void)
 {
-	if (armpmu && armpmu->reset)
-		return on_each_cpu(armpmu->reset, NULL, 1);
+	if (cpu_pmu && cpu_pmu->reset)
+		return on_each_cpu(cpu_pmu->reset, NULL, 1);
 	return 0;
 }
-arch_initcall(armpmu_reset);
+arch_initcall(cpu_pmu_reset);
 
+/*
+ * PMU platform driver and devicetree bindings.
+ */
+static struct of_device_id armpmu_of_device_ids[] = {
+	{.compatible = "arm,cortex-a9-pmu"},
+	{.compatible = "arm,cortex-a8-pmu"},
+	{.compatible = "arm,arm1136-pmu"},
+	{.compatible = "arm,arm1176-pmu"},
+	{},
+};
+
+static struct platform_device_id armpmu_plat_device_ids[] = {
+	{.name = "arm-pmu"},
+	{},
+};
+
+static int __devinit armpmu_device_probe(struct platform_device *pdev)
+{
+	if (!cpu_pmu)
+		return -ENODEV;
+
+	cpu_pmu->plat_device = pdev;
+	return 0;
+}
+
+static struct platform_driver armpmu_driver = {
+	.driver		= {
+		.name	= "arm-pmu",
+		.of_match_table = armpmu_of_device_ids,
+	},
+	.probe		= armpmu_device_probe,
+	.id_table	= armpmu_plat_device_ids,
+};
+
+static int __init register_pmu_driver(void)
+{
+	return platform_driver_register(&armpmu_driver);
+}
+device_initcall(register_pmu_driver);
+
+static struct pmu_hw_events *armpmu_get_cpu_events(void)
+{
+	return &__get_cpu_var(cpu_hw_events);
+}
+
+static void __init cpu_pmu_init(struct arm_pmu *armpmu)
+{
+	int cpu;
+	for_each_possible_cpu(cpu) {
+		struct pmu_hw_events *events = &per_cpu(cpu_hw_events, cpu);
+		events->events = per_cpu(hw_events, cpu);
+		events->used_mask = per_cpu(used_mask, cpu);
+		raw_spin_lock_init(&events->pmu_lock);
+	}
+	armpmu->get_hw_events = armpmu_get_cpu_events;
+	armpmu->type = ARM_PMU_DEVICE_CPU;
+}
+
+/*
+ * CPU PMU identification and registration.
+ */
 static int __init
 init_hw_perf_events(void)
 {
@@ -651,22 +696,22 @@ init_hw_perf_events(void)
 		case 0xB360:	/* ARM1136 */
 		case 0xB560:	/* ARM1156 */
 		case 0xB760:	/* ARM1176 */
-			armpmu = armv6pmu_init();
+			cpu_pmu = armv6pmu_init();
 			break;
 		case 0xB020:	/* ARM11mpcore */
-			armpmu = armv6mpcore_pmu_init();
+			cpu_pmu = armv6mpcore_pmu_init();
 			break;
 		case 0xC080:	/* Cortex-A8 */
-			armpmu = armv7_a8_pmu_init();
+			cpu_pmu = armv7_a8_pmu_init();
 			break;
 		case 0xC090:	/* Cortex-A9 */
-			armpmu = armv7_a9_pmu_init();
+			cpu_pmu = armv7_a9_pmu_init();
 			break;
 		case 0xC050:	/* Cortex-A5 */
-			armpmu = armv7_a5_pmu_init();
+			cpu_pmu = armv7_a5_pmu_init();
 			break;
 		case 0xC0F0:	/* Cortex-A15 */
-			armpmu = armv7_a15_pmu_init();
+			cpu_pmu = armv7_a15_pmu_init();
 			break;
 		}
 	/* Intel CPUs [xscale]. */
@@ -674,23 +719,23 @@ init_hw_perf_events(void)
 		part_number = (cpuid >> 13) & 0x7;
 		switch (part_number) {
 		case 1:
-			armpmu = xscale1pmu_init();
+			cpu_pmu = xscale1pmu_init();
 			break;
 		case 2:
-			armpmu = xscale2pmu_init();
+			cpu_pmu = xscale2pmu_init();
 			break;
 		}
 	}
 
-	if (armpmu) {
+	if (cpu_pmu) {
 		pr_info("enabled with %s PMU driver, %d counters available\n",
-			armpmu->name, armpmu->num_events);
+			cpu_pmu->name, cpu_pmu->num_events);
+		cpu_pmu_init(cpu_pmu);
+		armpmu_register(cpu_pmu, "cpu", PERF_TYPE_RAW);
 	} else {
 		pr_info("no hardware support available\n");
 	}
 
-	perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW);
-
 	return 0;
 }
 early_initcall(init_hw_perf_events);
diff --git a/arch/arm/kernel/perf_event_v6.c b/arch/arm/kernel/perf_event_v6.c
index dd7f3b9f4cb..e63d8115c01 100644
--- a/arch/arm/kernel/perf_event_v6.c
+++ b/arch/arm/kernel/perf_event_v6.c
@@ -54,7 +54,7 @@ enum armv6_perf_types {
 };
 
 enum armv6_counters {
-	ARMV6_CYCLE_COUNTER = 1,
+	ARMV6_CYCLE_COUNTER = 0,
 	ARMV6_COUNTER0,
 	ARMV6_COUNTER1,
 };
@@ -433,6 +433,7 @@ armv6pmu_enable_event(struct hw_perf_event *hwc,
 		      int idx)
 {
 	unsigned long val, mask, evt, flags;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
 	if (ARMV6_CYCLE_COUNTER == idx) {
 		mask	= 0;
@@ -454,12 +455,29 @@ armv6pmu_enable_event(struct hw_perf_event *hwc,
 	 * Mask out the current event and set the counter to count the event
 	 * that we're interested in.
 	 */
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = armv6_pmcr_read();
 	val &= ~mask;
 	val |= evt;
 	armv6_pmcr_write(val);
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
+}
+
+static int counter_is_active(unsigned long pmcr, int idx)
+{
+	unsigned long mask = 0;
+	if (idx == ARMV6_CYCLE_COUNTER)
+		mask = ARMV6_PMCR_CCOUNT_IEN;
+	else if (idx == ARMV6_COUNTER0)
+		mask = ARMV6_PMCR_COUNT0_IEN;
+	else if (idx == ARMV6_COUNTER1)
+		mask = ARMV6_PMCR_COUNT1_IEN;
+
+	if (mask)
+		return pmcr & mask;
+
+	WARN_ONCE(1, "invalid counter number (%d)\n", idx);
+	return 0;
 }
 
 static irqreturn_t
@@ -468,7 +486,7 @@ armv6pmu_handle_irq(int irq_num,
 {
 	unsigned long pmcr = armv6_pmcr_read();
 	struct perf_sample_data data;
-	struct cpu_hw_events *cpuc;
+	struct pmu_hw_events *cpuc;
 	struct pt_regs *regs;
 	int idx;
 
@@ -487,11 +505,11 @@ armv6pmu_handle_irq(int irq_num,
 	perf_sample_data_init(&data, 0);
 
 	cpuc = &__get_cpu_var(cpu_hw_events);
-	for (idx = 0; idx <= armpmu->num_events; ++idx) {
+	for (idx = 0; idx < cpu_pmu->num_events; ++idx) {
 		struct perf_event *event = cpuc->events[idx];
 		struct hw_perf_event *hwc;
 
-		if (!test_bit(idx, cpuc->active_mask))
+		if (!counter_is_active(pmcr, idx))
 			continue;
 
 		/*
@@ -508,7 +526,7 @@ armv6pmu_handle_irq(int irq_num,
 			continue;
 
 		if (perf_event_overflow(event, &data, regs))
-			armpmu->disable(hwc, idx);
+			cpu_pmu->disable(hwc, idx);
 	}
 
 	/*
@@ -527,28 +545,30 @@ static void
 armv6pmu_start(void)
 {
 	unsigned long flags, val;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = armv6_pmcr_read();
 	val |= ARMV6_PMCR_ENABLE;
 	armv6_pmcr_write(val);
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void
 armv6pmu_stop(void)
 {
 	unsigned long flags, val;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = armv6_pmcr_read();
 	val &= ~ARMV6_PMCR_ENABLE;
 	armv6_pmcr_write(val);
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static int
-armv6pmu_get_event_idx(struct cpu_hw_events *cpuc,
+armv6pmu_get_event_idx(struct pmu_hw_events *cpuc,
 		       struct hw_perf_event *event)
 {
 	/* Always place a cycle counter into the cycle counter. */
@@ -578,6 +598,7 @@ armv6pmu_disable_event(struct hw_perf_event *hwc,
 		       int idx)
 {
 	unsigned long val, mask, evt, flags;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
 	if (ARMV6_CYCLE_COUNTER == idx) {
 		mask	= ARMV6_PMCR_CCOUNT_IEN;
@@ -598,12 +619,12 @@ armv6pmu_disable_event(struct hw_perf_event *hwc,
 	 * of ETM bus signal assertion cycles. The external reporting should
 	 * be disabled and so this should never increment.
 	 */
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = armv6_pmcr_read();
 	val &= ~mask;
 	val |= evt;
 	armv6_pmcr_write(val);
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void
@@ -611,6 +632,7 @@ armv6mpcore_pmu_disable_event(struct hw_perf_event *hwc,
 			      int idx)
 {
 	unsigned long val, mask, flags, evt = 0;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
 	if (ARMV6_CYCLE_COUNTER == idx) {
 		mask	= ARMV6_PMCR_CCOUNT_IEN;
@@ -627,15 +649,21 @@ armv6mpcore_pmu_disable_event(struct hw_perf_event *hwc,
 	 * Unlike UP ARMv6, we don't have a way of stopping the counters. We
 	 * simply disable the interrupt reporting.
 	 */
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = armv6_pmcr_read();
 	val &= ~mask;
 	val |= evt;
 	armv6_pmcr_write(val);
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
+}
+
+static int armv6_map_event(struct perf_event *event)
+{
+	return map_cpu_event(event, &armv6_perf_map,
+				&armv6_perf_cache_map, 0xFF);
 }
 
-static const struct arm_pmu armv6pmu = {
+static struct arm_pmu armv6pmu = {
 	.id			= ARM_PERF_PMU_ID_V6,
 	.name			= "v6",
 	.handle_irq		= armv6pmu_handle_irq,
@@ -646,14 +674,12 @@ static const struct arm_pmu armv6pmu = {
 	.get_event_idx		= armv6pmu_get_event_idx,
 	.start			= armv6pmu_start,
 	.stop			= armv6pmu_stop,
-	.cache_map		= &armv6_perf_cache_map,
-	.event_map		= &armv6_perf_map,
-	.raw_event_mask		= 0xFF,
+	.map_event		= armv6_map_event,
 	.num_events		= 3,
 	.max_period		= (1LLU << 32) - 1,
 };
 
-static const struct arm_pmu *__init armv6pmu_init(void)
+static struct arm_pmu *__init armv6pmu_init(void)
 {
 	return &armv6pmu;
 }
@@ -665,7 +691,14 @@ static const struct arm_pmu *__init armv6pmu_init(void)
  * disable the interrupt reporting and update the event. When unthrottling we
  * reset the period and enable the interrupt reporting.
  */
-static const struct arm_pmu armv6mpcore_pmu = {
+
+static int armv6mpcore_map_event(struct perf_event *event)
+{
+	return map_cpu_event(event, &armv6mpcore_perf_map,
+				&armv6mpcore_perf_cache_map, 0xFF);
+}
+
+static struct arm_pmu armv6mpcore_pmu = {
 	.id			= ARM_PERF_PMU_ID_V6MP,
 	.name			= "v6mpcore",
 	.handle_irq		= armv6pmu_handle_irq,
@@ -676,24 +709,22 @@ static const struct arm_pmu armv6mpcore_pmu = {
 	.get_event_idx		= armv6pmu_get_event_idx,
 	.start			= armv6pmu_start,
 	.stop			= armv6pmu_stop,
-	.cache_map		= &armv6mpcore_perf_cache_map,
-	.event_map		= &armv6mpcore_perf_map,
-	.raw_event_mask		= 0xFF,
+	.map_event		= armv6mpcore_map_event,
 	.num_events		= 3,
 	.max_period		= (1LLU << 32) - 1,
 };
 
-static const struct arm_pmu *__init armv6mpcore_pmu_init(void)
+static struct arm_pmu *__init armv6mpcore_pmu_init(void)
 {
 	return &armv6mpcore_pmu;
 }
 #else
-static const struct arm_pmu *__init armv6pmu_init(void)
+static struct arm_pmu *__init armv6pmu_init(void)
 {
 	return NULL;
 }
 
-static const struct arm_pmu *__init armv6mpcore_pmu_init(void)
+static struct arm_pmu *__init armv6mpcore_pmu_init(void)
 {
 	return NULL;
 }
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index 6be3e2e4d83..1ef6d0034b8 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -17,6 +17,9 @@
  */
 
 #ifdef CONFIG_CPU_V7
+
+static struct arm_pmu armv7pmu;
+
 /*
  * Common ARMv7 event types
  *
@@ -676,23 +679,24 @@ static const unsigned armv7_a15_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 };
 
 /*
- * Perf Events counters
+ * Perf Events' indices
  */
-enum armv7_counters {
-	ARMV7_CYCLE_COUNTER		= 1,	/* Cycle counter */
-	ARMV7_COUNTER0			= 2,	/* First event counter */
-};
+#define	ARMV7_IDX_CYCLE_COUNTER	0
+#define	ARMV7_IDX_COUNTER0	1
+#define	ARMV7_IDX_COUNTER_LAST	(ARMV7_IDX_CYCLE_COUNTER + cpu_pmu->num_events - 1)
+
+#define	ARMV7_MAX_COUNTERS	32
+#define	ARMV7_COUNTER_MASK	(ARMV7_MAX_COUNTERS - 1)
 
 /*
- * The cycle counter is ARMV7_CYCLE_COUNTER.
- * The first event counter is ARMV7_COUNTER0.
- * The last event counter is (ARMV7_COUNTER0 + armpmu->num_events - 1).
+ * ARMv7 low level PMNC access
  */
-#define	ARMV7_COUNTER_LAST	(ARMV7_COUNTER0 + armpmu->num_events - 1)
 
 /*
- * ARMv7 low level PMNC access
+ * Perf Event to low level counters mapping
  */
+#define	ARMV7_IDX_TO_COUNTER(x)	\
+	(((x) - ARMV7_IDX_COUNTER0) & ARMV7_COUNTER_MASK)
 
 /*
  * Per-CPU PMNC: config reg
@@ -708,103 +712,76 @@ enum armv7_counters {
 #define	ARMV7_PMNC_MASK		0x3f	 /* Mask for writable bits */
 
 /*
- * Available counters
- */
-#define ARMV7_CNT0		0	/* First event counter */
-#define ARMV7_CCNT		31	/* Cycle counter */
-
-/* Perf Event to low level counters mapping */
-#define ARMV7_EVENT_CNT_TO_CNTx	(ARMV7_COUNTER0 - ARMV7_CNT0)
-
-/*
- * CNTENS: counters enable reg
- */
-#define ARMV7_CNTENS_P(idx)	(1 << (idx - ARMV7_EVENT_CNT_TO_CNTx))
-#define ARMV7_CNTENS_C		(1 << ARMV7_CCNT)
-
-/*
- * CNTENC: counters disable reg
- */
-#define ARMV7_CNTENC_P(idx)	(1 << (idx - ARMV7_EVENT_CNT_TO_CNTx))
-#define ARMV7_CNTENC_C		(1 << ARMV7_CCNT)
-
-/*
- * INTENS: counters overflow interrupt enable reg
- */
-#define ARMV7_INTENS_P(idx)	(1 << (idx - ARMV7_EVENT_CNT_TO_CNTx))
-#define ARMV7_INTENS_C		(1 << ARMV7_CCNT)
-
-/*
- * INTENC: counters overflow interrupt disable reg
- */
-#define ARMV7_INTENC_P(idx)	(1 << (idx - ARMV7_EVENT_CNT_TO_CNTx))
-#define ARMV7_INTENC_C		(1 << ARMV7_CCNT)
-
-/*
- * EVTSEL: Event selection reg
+ * FLAG: counters overflow flag status reg
  */
-#define	ARMV7_EVTSEL_MASK	0xff		/* Mask for writable bits */
+#define	ARMV7_FLAG_MASK		0xffffffff	/* Mask for writable bits */
+#define	ARMV7_OVERFLOWED_MASK	ARMV7_FLAG_MASK
 
 /*
- * SELECT: Counter selection reg
+ * PMXEVTYPER: Event selection reg
  */
-#define	ARMV7_SELECT_MASK	0x1f		/* Mask for writable bits */
+#define	ARMV7_EVTYPE_MASK	0xc00000ff	/* Mask for writable bits */
+#define	ARMV7_EVTYPE_EVENT	0xff		/* Mask for EVENT bits */
 
 /*
- * FLAG: counters overflow flag status reg
+ * Event filters for PMUv2
  */
-#define ARMV7_FLAG_P(idx)	(1 << (idx - ARMV7_EVENT_CNT_TO_CNTx))
-#define ARMV7_FLAG_C		(1 << ARMV7_CCNT)
-#define	ARMV7_FLAG_MASK		0xffffffff	/* Mask for writable bits */
-#define	ARMV7_OVERFLOWED_MASK	ARMV7_FLAG_MASK
+#define	ARMV7_EXCLUDE_PL1	(1 << 31)
+#define	ARMV7_EXCLUDE_USER	(1 << 30)
+#define	ARMV7_INCLUDE_HYP	(1 << 27)
 
-static inline unsigned long armv7_pmnc_read(void)
+static inline u32 armv7_pmnc_read(void)
 {
 	u32 val;
 	asm volatile("mrc p15, 0, %0, c9, c12, 0" : "=r"(val));
 	return val;
 }
 
-static inline void armv7_pmnc_write(unsigned long val)
+static inline void armv7_pmnc_write(u32 val)
 {
 	val &= ARMV7_PMNC_MASK;
 	isb();
 	asm volatile("mcr p15, 0, %0, c9, c12, 0" : : "r"(val));
 }
 
-static inline int armv7_pmnc_has_overflowed(unsigned long pmnc)
+static inline int armv7_pmnc_has_overflowed(u32 pmnc)
 {
 	return pmnc & ARMV7_OVERFLOWED_MASK;
 }
 
-static inline int armv7_pmnc_counter_has_overflowed(unsigned long pmnc,
-					enum armv7_counters counter)
+static inline int armv7_pmnc_counter_valid(int idx)
+{
+	return idx >= ARMV7_IDX_CYCLE_COUNTER && idx <= ARMV7_IDX_COUNTER_LAST;
+}
+
+static inline int armv7_pmnc_counter_has_overflowed(u32 pmnc, int idx)
 {
 	int ret = 0;
+	u32 counter;
 
-	if (counter == ARMV7_CYCLE_COUNTER)
-		ret = pmnc & ARMV7_FLAG_C;
-	else if ((counter >= ARMV7_COUNTER0) && (counter <= ARMV7_COUNTER_LAST))
-		ret = pmnc & ARMV7_FLAG_P(counter);
-	else
+	if (!armv7_pmnc_counter_valid(idx)) {
 		pr_err("CPU%u checking wrong counter %d overflow status\n",
-			smp_processor_id(), counter);
+			smp_processor_id(), idx);
+	} else {
+		counter = ARMV7_IDX_TO_COUNTER(idx);
+		ret = pmnc & BIT(counter);
+	}
 
 	return ret;
 }
 
-static inline int armv7_pmnc_select_counter(unsigned int idx)
+static inline int armv7_pmnc_select_counter(int idx)
 {
-	u32 val;
+	u32 counter;
 
-	if ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST)) {
-		pr_err("CPU%u selecting wrong PMNC counter"
-			" %d\n", smp_processor_id(), idx);
-		return -1;
+	if (!armv7_pmnc_counter_valid(idx)) {
+		pr_err("CPU%u selecting wrong PMNC counter %d\n",
+			smp_processor_id(), idx);
+		return -EINVAL;
 	}
 
-	val = (idx - ARMV7_EVENT_CNT_TO_CNTx) & ARMV7_SELECT_MASK;
-	asm volatile("mcr p15, 0, %0, c9, c12, 5" : : "r" (val));
+	counter = ARMV7_IDX_TO_COUNTER(idx);
+	asm volatile("mcr p15, 0, %0, c9, c12, 5" : : "r" (counter));
 	isb();
 
 	return idx;
@@ -812,124 +789,95 @@ static inline int armv7_pmnc_select_counter(unsigned int idx)
 
 static inline u32 armv7pmu_read_counter(int idx)
 {
-	unsigned long value = 0;
+	u32 value = 0;
 
-	if (idx == ARMV7_CYCLE_COUNTER)
-		asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (value));
-	else if ((idx >= ARMV7_COUNTER0) && (idx <= ARMV7_COUNTER_LAST)) {
-		if (armv7_pmnc_select_counter(idx) == idx)
-			asm volatile("mrc p15, 0, %0, c9, c13, 2"
-				     : "=r" (value));
-	} else
+	if (!armv7_pmnc_counter_valid(idx))
 		pr_err("CPU%u reading wrong counter %d\n",
 			smp_processor_id(), idx);
+	else if (idx == ARMV7_IDX_CYCLE_COUNTER)
+		asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (value));
+	else if (armv7_pmnc_select_counter(idx) == idx)
+		asm volatile("mrc p15, 0, %0, c9, c13, 2" : "=r" (value));
 
 	return value;
 }
 
 static inline void armv7pmu_write_counter(int idx, u32 value)
 {
-	if (idx == ARMV7_CYCLE_COUNTER)
-		asm volatile("mcr p15, 0, %0, c9, c13, 0" : : "r" (value));
-	else if ((idx >= ARMV7_COUNTER0) && (idx <= ARMV7_COUNTER_LAST)) {
-		if (armv7_pmnc_select_counter(idx) == idx)
-			asm volatile("mcr p15, 0, %0, c9, c13, 2"
-				     : : "r" (value));
-	} else
+	if (!armv7_pmnc_counter_valid(idx))
 		pr_err("CPU%u writing wrong counter %d\n",
 			smp_processor_id(), idx);
+	else if (idx == ARMV7_IDX_CYCLE_COUNTER)
+		asm volatile("mcr p15, 0, %0, c9, c13, 0" : : "r" (value));
+	else if (armv7_pmnc_select_counter(idx) == idx)
+		asm volatile("mcr p15, 0, %0, c9, c13, 2" : : "r" (value));
 }
 
-static inline void armv7_pmnc_write_evtsel(unsigned int idx, u32 val)
+static inline void armv7_pmnc_write_evtsel(int idx, u32 val)
 {
 	if (armv7_pmnc_select_counter(idx) == idx) {
-		val &= ARMV7_EVTSEL_MASK;
+		val &= ARMV7_EVTYPE_MASK;
 		asm volatile("mcr p15, 0, %0, c9, c13, 1" : : "r" (val));
 	}
 }
 
-static inline u32 armv7_pmnc_enable_counter(unsigned int idx)
+static inline int armv7_pmnc_enable_counter(int idx)
 {
-	u32 val;
+	u32 counter;
 
-	if ((idx != ARMV7_CYCLE_COUNTER) &&
-	    ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST))) {
-		pr_err("CPU%u enabling wrong PMNC counter"
-			" %d\n", smp_processor_id(), idx);
-		return -1;
+	if (!armv7_pmnc_counter_valid(idx)) {
+		pr_err("CPU%u enabling wrong PMNC counter %d\n",
+			smp_processor_id(), idx);
+		return -EINVAL;
 	}
 
-	if (idx == ARMV7_CYCLE_COUNTER)
-		val = ARMV7_CNTENS_C;
-	else
-		val = ARMV7_CNTENS_P(idx);
-
-	asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (val));
-
+	counter = ARMV7_IDX_TO_COUNTER(idx);
+	asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (BIT(counter)));
 	return idx;
 }
 
-static inline u32 armv7_pmnc_disable_counter(unsigned int idx)
+static inline int armv7_pmnc_disable_counter(int idx)
 {
-	u32 val;
-
+	u32 counter;
 
-	if ((idx != ARMV7_CYCLE_COUNTER) &&
-	    ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST))) {
-		pr_err("CPU%u disabling wrong PMNC counter"
-			" %d\n", smp_processor_id(), idx);
-		return -1;
+	if (!armv7_pmnc_counter_valid(idx)) {
+		pr_err("CPU%u disabling wrong PMNC counter %d\n",
+			smp_processor_id(), idx);
+		return -EINVAL;
 	}
 
-	if (idx == ARMV7_CYCLE_COUNTER)
-		val = ARMV7_CNTENC_C;
-	else
-		val = ARMV7_CNTENC_P(idx);
-
-	asm volatile("mcr p15, 0, %0, c9, c12, 2" : : "r" (val));
-
+	counter = ARMV7_IDX_TO_COUNTER(idx);
+	asm volatile("mcr p15, 0, %0, c9, c12, 2" : : "r" (BIT(counter)));
 	return idx;
 }
 
-static inline u32 armv7_pmnc_enable_intens(unsigned int idx)
+static inline int armv7_pmnc_enable_intens(int idx)
 {
-	u32 val;
+	u32 counter;
 
-	if ((idx != ARMV7_CYCLE_COUNTER) &&
-	    ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST))) {
-		pr_err("CPU%u enabling wrong PMNC counter"
-			" interrupt enable %d\n", smp_processor_id(), idx);
-		return -1;
+	if (!armv7_pmnc_counter_valid(idx)) {
+		pr_err("CPU%u enabling wrong PMNC counter IRQ enable %d\n",
+			smp_processor_id(), idx);
+		return -EINVAL;
 	}
 
-	if (idx == ARMV7_CYCLE_COUNTER)
-		val = ARMV7_INTENS_C;
-	else
-		val = ARMV7_INTENS_P(idx);
-
-	asm volatile("mcr p15, 0, %0, c9, c14, 1" : : "r" (val));
-
+	counter = ARMV7_IDX_TO_COUNTER(idx);
+	asm volatile("mcr p15, 0, %0, c9, c14, 1" : : "r" (BIT(counter)));
 	return idx;
 }
 
-static inline u32 armv7_pmnc_disable_intens(unsigned int idx)
+static inline int armv7_pmnc_disable_intens(int idx)
 {
-	u32 val;
+	u32 counter;
 
-	if ((idx != ARMV7_CYCLE_COUNTER) &&
-	    ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST))) {
-		pr_err("CPU%u disabling wrong PMNC counter"
-			" interrupt enable %d\n", smp_processor_id(), idx);
-		return -1;
+	if (!armv7_pmnc_counter_valid(idx)) {
+		pr_err("CPU%u disabling wrong PMNC counter IRQ enable %d\n",
+			smp_processor_id(), idx);
+		return -EINVAL;
 	}
 
-	if (idx == ARMV7_CYCLE_COUNTER)
-		val = ARMV7_INTENC_C;
-	else
-		val = ARMV7_INTENC_P(idx);
-
-	asm volatile("mcr p15, 0, %0, c9, c14, 2" : : "r" (val));
-
+	counter = ARMV7_IDX_TO_COUNTER(idx);
+	asm volatile("mcr p15, 0, %0, c9, c14, 2" : : "r" (BIT(counter)));
 	return idx;
 }
 
@@ -973,14 +921,14 @@ static void armv7_pmnc_dump_regs(void)
 	asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (val));
 	printk(KERN_INFO "CCNT  =0x%08x\n", val);
 
-	for (cnt = ARMV7_COUNTER0; cnt < ARMV7_COUNTER_LAST; cnt++) {
+	for (cnt = ARMV7_IDX_COUNTER0; cnt <= ARMV7_IDX_COUNTER_LAST; cnt++) {
 		armv7_pmnc_select_counter(cnt);
 		asm volatile("mrc p15, 0, %0, c9, c13, 2" : "=r" (val));
 		printk(KERN_INFO "CNT[%d] count =0x%08x\n",
-			cnt-ARMV7_EVENT_CNT_TO_CNTx, val);
+			ARMV7_IDX_TO_COUNTER(cnt), val);
 		asm volatile("mrc p15, 0, %0, c9, c13, 1" : "=r" (val));
 		printk(KERN_INFO "CNT[%d] evtsel=0x%08x\n",
-			cnt-ARMV7_EVENT_CNT_TO_CNTx, val);
+			ARMV7_IDX_TO_COUNTER(cnt), val);
 	}
 }
 #endif
@@ -988,12 +936,13 @@ static void armv7_pmnc_dump_regs(void)
 static void armv7pmu_enable_event(struct hw_perf_event *hwc, int idx)
 {
 	unsigned long flags;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
 	/*
 	 * Enable counter and interrupt, and set the counter to count
 	 * the event that we're interested in.
 	 */
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 
 	/*
 	 * Disable counter
@@ -1002,9 +951,10 @@ static void armv7pmu_enable_event(struct hw_perf_event *hwc, int idx)
 
 	/*
 	 * Set event (if destined for PMNx counters)
-	 * We don't need to set the event if it's a cycle count
+	 * We only need to set the event for the cycle counter if we
+	 * have the ability to perform event filtering.
 	 */
-	if (idx != ARMV7_CYCLE_COUNTER)
+	if (armv7pmu.set_event_filter || idx != ARMV7_IDX_CYCLE_COUNTER)
 		armv7_pmnc_write_evtsel(idx, hwc->config_base);
 
 	/*
@@ -1017,17 +967,18 @@ static void armv7pmu_enable_event(struct hw_perf_event *hwc, int idx)
 	 */
 	armv7_pmnc_enable_counter(idx);
 
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void armv7pmu_disable_event(struct hw_perf_event *hwc, int idx)
 {
 	unsigned long flags;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
 	/*
 	 * Disable counter and interrupt
 	 */
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 
 	/*
 	 * Disable counter
@@ -1039,14 +990,14 @@ static void armv7pmu_disable_event(struct hw_perf_event *hwc, int idx)
 	 */
 	armv7_pmnc_disable_intens(idx);
 
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev)
 {
-	unsigned long pmnc;
+	u32 pmnc;
 	struct perf_sample_data data;
-	struct cpu_hw_events *cpuc;
+	struct pmu_hw_events *cpuc;
 	struct pt_regs *regs;
 	int idx;
 
@@ -1069,13 +1020,10 @@ static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev)
 	perf_sample_data_init(&data, 0);
 
 	cpuc = &__get_cpu_var(cpu_hw_events);
-	for (idx = 0; idx <= armpmu->num_events; ++idx) {
+	for (idx = 0; idx < cpu_pmu->num_events; ++idx) {
 		struct perf_event *event = cpuc->events[idx];
 		struct hw_perf_event *hwc;
 
-		if (!test_bit(idx, cpuc->active_mask))
-			continue;
-
 		/*
 		 * We have a single interrupt for all counters. Check that
 		 * each counter has overflowed before we process it.
@@ -1090,7 +1038,7 @@ static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev)
 			continue;
 
 		if (perf_event_overflow(event, &data, regs))
-			armpmu->disable(hwc, idx);
+			cpu_pmu->disable(hwc, idx);
 	}
 
 	/*
@@ -1108,61 +1056,114 @@ static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev)
 static void armv7pmu_start(void)
 {
 	unsigned long flags;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	/* Enable all counters */
 	armv7_pmnc_write(armv7_pmnc_read() | ARMV7_PMNC_E);
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void armv7pmu_stop(void)
 {
 	unsigned long flags;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	/* Disable all counters */
 	armv7_pmnc_write(armv7_pmnc_read() & ~ARMV7_PMNC_E);
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
-static int armv7pmu_get_event_idx(struct cpu_hw_events *cpuc,
+static int armv7pmu_get_event_idx(struct pmu_hw_events *cpuc,
 				  struct hw_perf_event *event)
 {
 	int idx;
+	unsigned long evtype = event->config_base & ARMV7_EVTYPE_EVENT;
 
 	/* Always place a cycle counter into the cycle counter. */
-	if (event->config_base == ARMV7_PERFCTR_CPU_CYCLES) {
-		if (test_and_set_bit(ARMV7_CYCLE_COUNTER, cpuc->used_mask))
+	if (evtype == ARMV7_PERFCTR_CPU_CYCLES) {
+		if (test_and_set_bit(ARMV7_IDX_CYCLE_COUNTER, cpuc->used_mask))
 			return -EAGAIN;
 
-		return ARMV7_CYCLE_COUNTER;
-	} else {
-		/*
-		 * For anything other than a cycle counter, try and use
-		 * the events counters
-		 */
-		for (idx = ARMV7_COUNTER0; idx <= armpmu->num_events; ++idx) {
-			if (!test_and_set_bit(idx, cpuc->used_mask))
-				return idx;
-		}
+		return ARMV7_IDX_CYCLE_COUNTER;
+	}
 
-		/* The counters are all in use. */
-		return -EAGAIN;
+	/*
+	 * For anything other than a cycle counter, try and use
+	 * the events counters
+	 */
+	for (idx = ARMV7_IDX_COUNTER0; idx < cpu_pmu->num_events; ++idx) {
+		if (!test_and_set_bit(idx, cpuc->used_mask))
+			return idx;
 	}
+
+	/* The counters are all in use. */
+	return -EAGAIN;
+}
+
+/*
+ * Add an event filter to a given event. This will only work for PMUv2 PMUs.
+ */
+static int armv7pmu_set_event_filter(struct hw_perf_event *event,
+				     struct perf_event_attr *attr)
+{
+	unsigned long config_base = 0;
+
+	if (attr->exclude_idle)
+		return -EPERM;
+	if (attr->exclude_user)
+		config_base |= ARMV7_EXCLUDE_USER;
+	if (attr->exclude_kernel)
+		config_base |= ARMV7_EXCLUDE_PL1;
+	if (!attr->exclude_hv)
+		config_base |= ARMV7_INCLUDE_HYP;
+
+	/*
+	 * Install the filter into config_base as this is used to
+	 * construct the event type.
+	 */
+	event->config_base = config_base;
+
+	return 0;
 }
 
 static void armv7pmu_reset(void *info)
 {
-	u32 idx, nb_cnt = armpmu->num_events;
+	u32 idx, nb_cnt = cpu_pmu->num_events;
 
 	/* The counter and interrupt enable registers are unknown at reset. */
-	for (idx = 1; idx < nb_cnt; ++idx)
+	for (idx = ARMV7_IDX_CYCLE_COUNTER; idx < nb_cnt; ++idx)
 		armv7pmu_disable_event(NULL, idx);
 
 	/* Initialize & Reset PMNC: C and P bits */
 	armv7_pmnc_write(ARMV7_PMNC_P | ARMV7_PMNC_C);
 }
 
+static int armv7_a8_map_event(struct perf_event *event)
+{
+	return map_cpu_event(event, &armv7_a8_perf_map,
+				&armv7_a8_perf_cache_map, 0xFF);
+}
+
+static int armv7_a9_map_event(struct perf_event *event)
+{
+	return map_cpu_event(event, &armv7_a9_perf_map,
+				&armv7_a9_perf_cache_map, 0xFF);
+}
+
+static int armv7_a5_map_event(struct perf_event *event)
+{
+	return map_cpu_event(event, &armv7_a5_perf_map,
+				&armv7_a5_perf_cache_map, 0xFF);
+}
+
+static int armv7_a15_map_event(struct perf_event *event)
+{
+	return map_cpu_event(event, &armv7_a15_perf_map,
+				&armv7_a15_perf_cache_map, 0xFF);
+}
+
 static struct arm_pmu armv7pmu = {
 	.handle_irq		= armv7pmu_handle_irq,
 	.enable			= armv7pmu_enable_event,
@@ -1173,7 +1174,6 @@ static struct arm_pmu armv7pmu = {
 	.start			= armv7pmu_start,
 	.stop			= armv7pmu_stop,
 	.reset			= armv7pmu_reset,
-	.raw_event_mask		= 0xFF,
 	.max_period		= (1LLU << 32) - 1,
 };
 
@@ -1188,62 +1188,59 @@ static u32 __init armv7_read_num_pmnc_events(void)
 	return nb_cnt + 1;
 }
 
-static const struct arm_pmu *__init armv7_a8_pmu_init(void)
+static struct arm_pmu *__init armv7_a8_pmu_init(void)
 {
 	armv7pmu.id		= ARM_PERF_PMU_ID_CA8;
 	armv7pmu.name		= "ARMv7 Cortex-A8";
-	armv7pmu.cache_map	= &armv7_a8_perf_cache_map;
-	armv7pmu.event_map	= &armv7_a8_perf_map;
+	armv7pmu.map_event	= armv7_a8_map_event;
 	armv7pmu.num_events	= armv7_read_num_pmnc_events();
 	return &armv7pmu;
 }
 
-static const struct arm_pmu *__init armv7_a9_pmu_init(void)
+static struct arm_pmu *__init armv7_a9_pmu_init(void)
 {
 	armv7pmu.id		= ARM_PERF_PMU_ID_CA9;
 	armv7pmu.name		= "ARMv7 Cortex-A9";
-	armv7pmu.cache_map	= &armv7_a9_perf_cache_map;
-	armv7pmu.event_map	= &armv7_a9_perf_map;
+	armv7pmu.map_event	= armv7_a9_map_event;
 	armv7pmu.num_events	= armv7_read_num_pmnc_events();
 	return &armv7pmu;
 }
 
-static const struct arm_pmu *__init armv7_a5_pmu_init(void)
+static struct arm_pmu *__init armv7_a5_pmu_init(void)
 {
 	armv7pmu.id		= ARM_PERF_PMU_ID_CA5;
 	armv7pmu.name		= "ARMv7 Cortex-A5";
-	armv7pmu.cache_map	= &armv7_a5_perf_cache_map;
-	armv7pmu.event_map	= &armv7_a5_perf_map;
+	armv7pmu.map_event	= armv7_a5_map_event;
 	armv7pmu.num_events	= armv7_read_num_pmnc_events();
 	return &armv7pmu;
 }
 
-static const struct arm_pmu *__init armv7_a15_pmu_init(void)
+static struct arm_pmu *__init armv7_a15_pmu_init(void)
 {
 	armv7pmu.id		= ARM_PERF_PMU_ID_CA15;
 	armv7pmu.name		= "ARMv7 Cortex-A15";
-	armv7pmu.cache_map	= &armv7_a15_perf_cache_map;
-	armv7pmu.event_map	= &armv7_a15_perf_map;
+	armv7pmu.map_event	= armv7_a15_map_event;
 	armv7pmu.num_events	= armv7_read_num_pmnc_events();
+	armv7pmu.set_event_filter = armv7pmu_set_event_filter;
 	return &armv7pmu;
 }
 #else
-static const struct arm_pmu *__init armv7_a8_pmu_init(void)
+static struct arm_pmu *__init armv7_a8_pmu_init(void)
 {
 	return NULL;
 }
 
-static const struct arm_pmu *__init armv7_a9_pmu_init(void)
+static struct arm_pmu *__init armv7_a9_pmu_init(void)
 {
 	return NULL;
 }
 
-static const struct arm_pmu *__init armv7_a5_pmu_init(void)
+static struct arm_pmu *__init armv7_a5_pmu_init(void)
 {
 	return NULL;
 }
 
-static const struct arm_pmu *__init armv7_a15_pmu_init(void)
+static struct arm_pmu *__init armv7_a15_pmu_init(void)
 {
 	return NULL;
 }
diff --git a/arch/arm/kernel/perf_event_xscale.c b/arch/arm/kernel/perf_event_xscale.c
index 3c4397491d0..e0cca10a841 100644
--- a/arch/arm/kernel/perf_event_xscale.c
+++ b/arch/arm/kernel/perf_event_xscale.c
@@ -40,7 +40,7 @@ enum xscale_perf_types {
 };
 
 enum xscale_counters {
-	XSCALE_CYCLE_COUNTER	= 1,
+	XSCALE_CYCLE_COUNTER	= 0,
 	XSCALE_COUNTER0,
 	XSCALE_COUNTER1,
 	XSCALE_COUNTER2,
@@ -222,7 +222,7 @@ xscale1pmu_handle_irq(int irq_num, void *dev)
 {
 	unsigned long pmnc;
 	struct perf_sample_data data;
-	struct cpu_hw_events *cpuc;
+	struct pmu_hw_events *cpuc;
 	struct pt_regs *regs;
 	int idx;
 
@@ -249,13 +249,10 @@ xscale1pmu_handle_irq(int irq_num, void *dev)
 	perf_sample_data_init(&data, 0);
 
 	cpuc = &__get_cpu_var(cpu_hw_events);
-	for (idx = 0; idx <= armpmu->num_events; ++idx) {
+	for (idx = 0; idx < cpu_pmu->num_events; ++idx) {
 		struct perf_event *event = cpuc->events[idx];
 		struct hw_perf_event *hwc;
 
-		if (!test_bit(idx, cpuc->active_mask))
-			continue;
-
 		if (!xscale1_pmnc_counter_has_overflowed(pmnc, idx))
 			continue;
 
@@ -266,7 +263,7 @@ xscale1pmu_handle_irq(int irq_num, void *dev)
 			continue;
 
 		if (perf_event_overflow(event, &data, regs))
-			armpmu->disable(hwc, idx);
+			cpu_pmu->disable(hwc, idx);
 	}
 
 	irq_work_run();
@@ -284,6 +281,7 @@ static void
 xscale1pmu_enable_event(struct hw_perf_event *hwc, int idx)
 {
 	unsigned long val, mask, evt, flags;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
 	switch (idx) {
 	case XSCALE_CYCLE_COUNTER:
@@ -305,18 +303,19 @@ xscale1pmu_enable_event(struct hw_perf_event *hwc, int idx)
 		return;
 	}
 
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = xscale1pmu_read_pmnc();
 	val &= ~mask;
 	val |= evt;
 	xscale1pmu_write_pmnc(val);
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void
 xscale1pmu_disable_event(struct hw_perf_event *hwc, int idx)
 {
 	unsigned long val, mask, evt, flags;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
 	switch (idx) {
 	case XSCALE_CYCLE_COUNTER:
@@ -336,16 +335,16 @@ xscale1pmu_disable_event(struct hw_perf_event *hwc, int idx)
 		return;
 	}
 
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = xscale1pmu_read_pmnc();
 	val &= ~mask;
 	val |= evt;
 	xscale1pmu_write_pmnc(val);
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static int
-xscale1pmu_get_event_idx(struct cpu_hw_events *cpuc,
+xscale1pmu_get_event_idx(struct pmu_hw_events *cpuc,
 			struct hw_perf_event *event)
 {
 	if (XSCALE_PERFCTR_CCNT == event->config_base) {
@@ -368,24 +367,26 @@ static void
 xscale1pmu_start(void)
 {
 	unsigned long flags, val;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = xscale1pmu_read_pmnc();
 	val |= XSCALE_PMU_ENABLE;
 	xscale1pmu_write_pmnc(val);
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void
 xscale1pmu_stop(void)
 {
 	unsigned long flags, val;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = xscale1pmu_read_pmnc();
 	val &= ~XSCALE_PMU_ENABLE;
 	xscale1pmu_write_pmnc(val);
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static inline u32
@@ -424,7 +425,13 @@ xscale1pmu_write_counter(int counter, u32 val)
 	}
 }
 
-static const struct arm_pmu xscale1pmu = {
+static int xscale_map_event(struct perf_event *event)
+{
+	return map_cpu_event(event, &xscale_perf_map,
+				&xscale_perf_cache_map, 0xFF);
+}
+
+static struct arm_pmu xscale1pmu = {
 	.id		= ARM_PERF_PMU_ID_XSCALE1,
 	.name		= "xscale1",
 	.handle_irq	= xscale1pmu_handle_irq,
@@ -435,14 +442,12 @@ static const struct arm_pmu xscale1pmu = {
 	.get_event_idx	= xscale1pmu_get_event_idx,
 	.start		= xscale1pmu_start,
 	.stop		= xscale1pmu_stop,
-	.cache_map	= &xscale_perf_cache_map,
-	.event_map	= &xscale_perf_map,
-	.raw_event_mask	= 0xFF,
+	.map_event	= xscale_map_event,
 	.num_events	= 3,
 	.max_period	= (1LLU << 32) - 1,
 };
 
-static const struct arm_pmu *__init xscale1pmu_init(void)
+static struct arm_pmu *__init xscale1pmu_init(void)
 {
 	return &xscale1pmu;
 }
@@ -560,7 +565,7 @@ xscale2pmu_handle_irq(int irq_num, void *dev)
 {
 	unsigned long pmnc, of_flags;
 	struct perf_sample_data data;
-	struct cpu_hw_events *cpuc;
+	struct pmu_hw_events *cpuc;
 	struct pt_regs *regs;
 	int idx;
 
@@ -581,13 +586,10 @@ xscale2pmu_handle_irq(int irq_num, void *dev)
 	perf_sample_data_init(&data, 0);
 
 	cpuc = &__get_cpu_var(cpu_hw_events);
-	for (idx = 0; idx <= armpmu->num_events; ++idx) {
+	for (idx = 0; idx < cpu_pmu->num_events; ++idx) {
 		struct perf_event *event = cpuc->events[idx];
 		struct hw_perf_event *hwc;
 
-		if (!test_bit(idx, cpuc->active_mask))
-			continue;
-
 		if (!xscale2_pmnc_counter_has_overflowed(pmnc, idx))
 			continue;
 
@@ -598,7 +600,7 @@ xscale2pmu_handle_irq(int irq_num, void *dev)
 			continue;
 
 		if (perf_event_overflow(event, &data, regs))
-			armpmu->disable(hwc, idx);
+			cpu_pmu->disable(hwc, idx);
 	}
 
 	irq_work_run();
@@ -616,6 +618,7 @@ static void
 xscale2pmu_enable_event(struct hw_perf_event *hwc, int idx)
 {
 	unsigned long flags, ien, evtsel;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
 	ien = xscale2pmu_read_int_enable();
 	evtsel = xscale2pmu_read_event_select();
@@ -649,16 +652,17 @@ xscale2pmu_enable_event(struct hw_perf_event *hwc, int idx)
 		return;
 	}
 
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	xscale2pmu_write_event_select(evtsel);
 	xscale2pmu_write_int_enable(ien);
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void
 xscale2pmu_disable_event(struct hw_perf_event *hwc, int idx)
 {
 	unsigned long flags, ien, evtsel;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
 	ien = xscale2pmu_read_int_enable();
 	evtsel = xscale2pmu_read_event_select();
@@ -692,14 +696,14 @@ xscale2pmu_disable_event(struct hw_perf_event *hwc, int idx)
 		return;
 	}
 
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	xscale2pmu_write_event_select(evtsel);
 	xscale2pmu_write_int_enable(ien);
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static int
-xscale2pmu_get_event_idx(struct cpu_hw_events *cpuc,
+xscale2pmu_get_event_idx(struct pmu_hw_events *cpuc,
 			struct hw_perf_event *event)
 {
 	int idx = xscale1pmu_get_event_idx(cpuc, event);
@@ -718,24 +722,26 @@ static void
 xscale2pmu_start(void)
 {
 	unsigned long flags, val;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = xscale2pmu_read_pmnc() & ~XSCALE_PMU_CNT64;
 	val |= XSCALE_PMU_ENABLE;
 	xscale2pmu_write_pmnc(val);
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void
 xscale2pmu_stop(void)
 {
 	unsigned long flags, val;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = xscale2pmu_read_pmnc();
 	val &= ~XSCALE_PMU_ENABLE;
 	xscale2pmu_write_pmnc(val);
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static inline u32
@@ -786,7 +792,7 @@ xscale2pmu_write_counter(int counter, u32 val)
 	}
 }
 
-static const struct arm_pmu xscale2pmu = {
+static struct arm_pmu xscale2pmu = {
 	.id		= ARM_PERF_PMU_ID_XSCALE2,
 	.name		= "xscale2",
 	.handle_irq	= xscale2pmu_handle_irq,
@@ -797,24 +803,22 @@ static const struct arm_pmu xscale2pmu = {
 	.get_event_idx	= xscale2pmu_get_event_idx,
 	.start		= xscale2pmu_start,
 	.stop		= xscale2pmu_stop,
-	.cache_map	= &xscale_perf_cache_map,
-	.event_map	= &xscale_perf_map,
-	.raw_event_mask	= 0xFF,
+	.map_event	= xscale_map_event,
 	.num_events	= 5,
 	.max_period	= (1LLU << 32) - 1,
 };
 
-static const struct arm_pmu *__init xscale2pmu_init(void)
+static struct arm_pmu *__init xscale2pmu_init(void)
 {
 	return &xscale2pmu;
 }
 #else
-static const struct arm_pmu *__init xscale1pmu_init(void)
+static struct arm_pmu *__init xscale1pmu_init(void)
 {
 	return NULL;
 }
 
-static const struct arm_pmu *__init xscale2pmu_init(void)
+static struct arm_pmu *__init xscale2pmu_init(void)
 {
 	return NULL;
 }
diff --git a/arch/arm/kernel/pmu.c b/arch/arm/kernel/pmu.c
index c53474fe84d..2c3407ee857 100644
--- a/arch/arm/kernel/pmu.c
+++ b/arch/arm/kernel/pmu.c
@@ -10,192 +10,26 @@
  *
  */
 
-#define pr_fmt(fmt) "PMU: " fmt
-
-#include <linux/cpumask.h>
 #include <linux/err.h>
-#include <linux/interrupt.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
-#include <linux/platform_device.h>
 
 #include <asm/pmu.h>
 
-static volatile long pmu_lock;
-
-static struct platform_device *pmu_devices[ARM_NUM_PMU_DEVICES];
-
-static int __devinit pmu_register(struct platform_device *pdev,
-					enum arm_pmu_type type)
-{
-	if (type < 0 || type >= ARM_NUM_PMU_DEVICES) {
-		pr_warning("received registration request for unknown "
-				"PMU device type %d\n", type);
-		return -EINVAL;
-	}
-
-	if (pmu_devices[type]) {
-		pr_warning("rejecting duplicate registration of PMU device "
-			"type %d.", type);
-		return -ENOSPC;
-	}
-
-	pr_info("registered new PMU device of type %d\n", type);
-	pmu_devices[type] = pdev;
-	return 0;
-}
-
-#define OF_MATCH_PMU(_name, _type) {	\
-	.compatible = _name,		\
-	.data = (void *)_type,		\
-}
-
-#define OF_MATCH_CPU(name)	OF_MATCH_PMU(name, ARM_PMU_DEVICE_CPU)
-
-static struct of_device_id armpmu_of_device_ids[] = {
-	OF_MATCH_CPU("arm,cortex-a9-pmu"),
-	OF_MATCH_CPU("arm,cortex-a8-pmu"),
-	OF_MATCH_CPU("arm,arm1136-pmu"),
-	OF_MATCH_CPU("arm,arm1176-pmu"),
-	{},
-};
-
-#define PLAT_MATCH_PMU(_name, _type) {	\
-	.name		= _name,	\
-	.driver_data	= _type,	\
-}
-
-#define PLAT_MATCH_CPU(_name)	PLAT_MATCH_PMU(_name, ARM_PMU_DEVICE_CPU)
-
-static struct platform_device_id armpmu_plat_device_ids[] = {
-	PLAT_MATCH_CPU("arm-pmu"),
-	{},
-};
-
-enum arm_pmu_type armpmu_device_type(struct platform_device *pdev)
-{
-	const struct of_device_id	*of_id;
-	const struct platform_device_id *pdev_id;
-
-	/* provided by of_device_id table */
-	if (pdev->dev.of_node) {
-		of_id = of_match_device(armpmu_of_device_ids, &pdev->dev);
-		BUG_ON(!of_id);
-		return (enum arm_pmu_type)of_id->data;
-	}
-
-	/* Provided by platform_device_id table */
-	pdev_id = platform_get_device_id(pdev);
-	BUG_ON(!pdev_id);
-	return pdev_id->driver_data;
-}
-
-static int __devinit armpmu_device_probe(struct platform_device *pdev)
-{
-	return pmu_register(pdev, armpmu_device_type(pdev));
-}
-
-static struct platform_driver armpmu_driver = {
-	.driver		= {
-		.name	= "arm-pmu",
-		.of_match_table = armpmu_of_device_ids,
-	},
-	.probe		= armpmu_device_probe,
-	.id_table	= armpmu_plat_device_ids,
-};
-
-static int __init register_pmu_driver(void)
-{
-	return platform_driver_register(&armpmu_driver);
-}
-device_initcall(register_pmu_driver);
+/*
+ * PMU locking to ensure mutual exclusion between different subsystems.
+ */
+static unsigned long pmu_lock[BITS_TO_LONGS(ARM_NUM_PMU_DEVICES)];
 
-struct platform_device *
+int
 reserve_pmu(enum arm_pmu_type type)
 {
-	struct platform_device *pdev;
-
-	if (test_and_set_bit_lock(type, &pmu_lock)) {
-		pdev = ERR_PTR(-EBUSY);
-	} else if (pmu_devices[type] == NULL) {
-		clear_bit_unlock(type, &pmu_lock);
-		pdev = ERR_PTR(-ENODEV);
-	} else {
-		pdev = pmu_devices[type];
-	}
-
-	return pdev;
+	return test_and_set_bit_lock(type, pmu_lock) ? -EBUSY : 0;
 }
 EXPORT_SYMBOL_GPL(reserve_pmu);
 
-int
+void
 release_pmu(enum arm_pmu_type type)
 {
-	if (WARN_ON(!pmu_devices[type]))
-		return -EINVAL;
-	clear_bit_unlock(type, &pmu_lock);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(release_pmu);
-
-static int
-set_irq_affinity(int irq,
-		 unsigned int cpu)
-{
-#ifdef CONFIG_SMP
-	int err = irq_set_affinity(irq, cpumask_of(cpu));
-	if (err)
-		pr_warning("unable to set irq affinity (irq=%d, cpu=%u)\n",
-			   irq, cpu);
-	return err;
-#else
-	return -EINVAL;
-#endif
-}
-
-static int
-init_cpu_pmu(void)
-{
-	int i, irqs, err = 0;
-	struct platform_device *pdev = pmu_devices[ARM_PMU_DEVICE_CPU];
-
-	if (!pdev)
-		return -ENODEV;
-
-	irqs = pdev->num_resources;
-
-	/*
-	 * If we have a single PMU interrupt that we can't shift, assume that
-	 * we're running on a uniprocessor machine and continue.
-	 */
-	if (irqs == 1 && !irq_can_set_affinity(platform_get_irq(pdev, 0)))
-		return 0;
-
-	for (i = 0; i < irqs; ++i) {
-		err = set_irq_affinity(platform_get_irq(pdev, i), i);
-		if (err)
-			break;
-	}
-
-	return err;
-}
-
-int
-init_pmu(enum arm_pmu_type type)
-{
-	int err = 0;
-
-	switch (type) {
-	case ARM_PMU_DEVICE_CPU:
-		err = init_cpu_pmu();
-		break;
-	default:
-		pr_warning("attempt to initialise PMU of unknown "
-			   "type %d\n", type);
-		err = -EINVAL;
-	}
-
-	return err;
+	clear_bit_unlock(type, pmu_lock);
 }
-EXPORT_SYMBOL_GPL(init_pmu);
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index f48b1c2e958..74e4f7bc0eb 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -201,6 +201,9 @@ void cpu_idle(void)
 #endif
 
 			local_irq_disable();
+#ifdef CONFIG_PL310_ERRATA_769419
+			wmb();
+#endif
 			if (hlt_counter) {
 				local_irq_enable();
 				cpu_relax();
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index e514c76043b..b7479455901 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -29,6 +29,8 @@
 #include <linux/fs.h>
 #include <linux/proc_fs.h>
 #include <linux/memblock.h>
+#include <linux/bug.h>
+#include <linux/compiler.h>
 
 #include <asm/unified.h>
 #include <asm/cpu.h>
@@ -42,6 +44,7 @@
 #include <asm/cacheflush.h>
 #include <asm/cachetype.h>
 #include <asm/tlbflush.h>
+#include <asm/system.h>
 
 #include <asm/prom.h>
 #include <asm/mach/arch.h>
@@ -115,6 +118,13 @@ struct outer_cache_fns outer_cache __read_mostly;
 EXPORT_SYMBOL(outer_cache);
 #endif
 
+/*
+ * Cached cpu_architecture() result for use by assembler code.
+ * C code should use the cpu_architecture() function instead of accessing this
+ * variable directly.
+ */
+int __cpu_architecture __read_mostly = CPU_ARCH_UNKNOWN;
+
 struct stack {
 	u32 irq[3];
 	u32 abt[3];
@@ -210,7 +220,7 @@ static const char *proc_arch[] = {
 	"?(17)",
 };
 
-int cpu_architecture(void)
+static int __get_cpu_architecture(void)
 {
 	int cpu_arch;
 
@@ -243,6 +253,13 @@ int cpu_architecture(void)
 	return cpu_arch;
 }
 
+int __pure cpu_architecture(void)
+{
+	BUG_ON(__cpu_architecture == CPU_ARCH_UNKNOWN);
+
+	return __cpu_architecture;
+}
+
 static int cpu_has_aliasing_icache(unsigned int arch)
 {
 	int aliasing_icache;
@@ -414,6 +431,7 @@ static void __init setup_processor(void)
 	}
 
 	cpu_name = list->cpu_name;
+	__cpu_architecture = __get_cpu_architecture();
 
 #ifdef MULTI_CPU
 	processor = *list->proc;
@@ -820,25 +838,8 @@ static struct machine_desc * __init setup_machine_tags(unsigned int nr)
 
 	if (__atags_pointer)
 		tags = phys_to_virt(__atags_pointer);
-	else if (mdesc->boot_params) {
-#ifdef CONFIG_MMU
-		/*
-		 * We still are executing with a minimal MMU mapping created
-		 * with the presumption that the machine default for this
-		 * is located in the first MB of RAM.  Anything else will
-		 * fault and silently hang the kernel at this point.
-		 */
-		if (mdesc->boot_params < PHYS_OFFSET ||
-		    mdesc->boot_params >= PHYS_OFFSET + SZ_1M) {
-			printk(KERN_WARNING
-			       "Default boot params at physical 0x%08lx out of reach\n",
-			       mdesc->boot_params);
-		} else
-#endif
-		{
-			tags = phys_to_virt(mdesc->boot_params);
-		}
-	}
+	else if (mdesc->atag_offset)
+		tags = (void *)(PAGE_OFFSET + mdesc->atag_offset);
 
 #if defined(CONFIG_DEPRECATED_PARAM_STRUCT)
 	/*
diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S
index dc902f2c684..4ac45fe955f 100644
--- a/arch/arm/kernel/sleep.S
+++ b/arch/arm/kernel/sleep.S
@@ -8,92 +8,63 @@
 	.text
 
 /*
- * Save CPU state for a suspend
- *  r1 = v:p offset
- *  r2 = suspend function arg0
- *  r3 = suspend function
+ * Save CPU state for a suspend.  This saves the CPU general purpose
+ * registers, and allocates space on the kernel stack to save the CPU
+ * specific registers and some other data for resume.
+ *  r0 = suspend function arg0
+ *  r1 = suspend function
  */
 ENTRY(__cpu_suspend)
 	stmfd	sp!, {r4 - r11, lr}
 #ifdef MULTI_CPU
 	ldr	r10, =processor
-	ldr	r5, [r10, #CPU_SLEEP_SIZE] @ size of CPU sleep state
-	ldr	ip, [r10, #CPU_DO_RESUME] @ virtual resume function
+	ldr	r4, [r10, #CPU_SLEEP_SIZE] @ size of CPU sleep state
 #else
-	ldr	r5, =cpu_suspend_size
-	ldr	ip, =cpu_do_resume
+	ldr	r4, =cpu_suspend_size
 #endif
-	mov	r6, sp			@ current virtual SP
-	sub	sp, sp, r5		@ allocate CPU state on stack
-	mov	r0, sp			@ save pointer to CPU save block
-	add	ip, ip, r1		@ convert resume fn to phys
-	stmfd	sp!, {r1, r6, ip}	@ save v:p, virt SP, phys resume fn
-	ldr	r5, =sleep_save_sp
-	add	r6, sp, r1		@ convert SP to phys
-	stmfd	sp!, {r2, r3}		@ save suspend func arg and pointer
+	mov	r5, sp			@ current virtual SP
+	add	r4, r4, #12		@ Space for pgd, virt sp, phys resume fn
+	sub	sp, sp, r4		@ allocate CPU state on stack
+	stmfd	sp!, {r0, r1}		@ save suspend func arg and pointer
+	add	r0, sp, #8		@ save pointer to save block
+	mov	r1, r4			@ size of save block
+	mov	r2, r5			@ virtual SP
+	ldr	r3, =sleep_save_sp
 #ifdef CONFIG_SMP
 	ALT_SMP(mrc p15, 0, lr, c0, c0, 5)
 	ALT_UP(mov lr, #0)
 	and	lr, lr, #15
-	str	r6, [r5, lr, lsl #2]	@ save phys SP
-#else
-	str	r6, [r5]		@ save phys SP
-#endif
-#ifdef MULTI_CPU
-	mov	lr, pc
-	ldr	pc, [r10, #CPU_DO_SUSPEND] @ save CPU state
-#else
-	bl	cpu_do_suspend
-#endif
-
-	@ flush data cache
-#ifdef MULTI_CACHE
-	ldr	r10, =cpu_cache
-	mov	lr, pc
-	ldr	pc, [r10, #CACHE_FLUSH_KERN_ALL]
-#else
-	bl	__cpuc_flush_kern_all
+	add	r3, r3, lr, lsl #2
 #endif
+	bl	__cpu_suspend_save
 	adr	lr, BSYM(cpu_suspend_abort)
 	ldmfd	sp!, {r0, pc}		@ call suspend fn
 ENDPROC(__cpu_suspend)
 	.ltorg
 
 cpu_suspend_abort:
-	ldmia	sp!, {r1 - r3}		@ pop v:p, virt SP, phys resume fn
+	ldmia	sp!, {r1 - r3}		@ pop phys pgd, virt SP, phys resume fn
+	teq	r0, #0
+	moveq	r0, #1			@ force non-zero value
 	mov	sp, r2
 	ldmfd	sp!, {r4 - r11, pc}
 ENDPROC(cpu_suspend_abort)
 
 /*
  * r0 = control register value
- * r1 = v:p offset (preserved by cpu_do_resume)
- * r2 = phys page table base
- * r3 = L1 section flags
  */
+	.align	5
 ENTRY(cpu_resume_mmu)
-	adr	r4, cpu_resume_turn_mmu_on
-	mov	r4, r4, lsr #20
-	orr	r3, r3, r4, lsl #20
-	ldr	r5, [r2, r4, lsl #2]	@ save old mapping
-	str	r3, [r2, r4, lsl #2]	@ setup 1:1 mapping for mmu code
-	sub	r2, r2, r1
 	ldr	r3, =cpu_resume_after_mmu
-	bic	r1, r0, #CR_C		@ ensure D-cache is disabled
-	b	cpu_resume_turn_mmu_on
-ENDPROC(cpu_resume_mmu)
-	.ltorg
-	.align	5
-cpu_resume_turn_mmu_on:
-	mcr	p15, 0, r1, c1, c0, 0	@ turn on MMU, I-cache, etc
-	mrc	p15, 0, r1, c0, c0, 0	@ read id reg
-	mov	r1, r1
-	mov	r1, r1
+	instr_sync
+	mcr	p15, 0, r0, c1, c0, 0	@ turn on MMU, I-cache, etc
+	mrc	p15, 0, r0, c0, c0, 0	@ read id reg
+	instr_sync
+	mov	r0, r0
+	mov	r0, r0
 	mov	pc, r3			@ jump to virtual address
-ENDPROC(cpu_resume_turn_mmu_on)
+ENDPROC(cpu_resume_mmu)
 cpu_resume_after_mmu:
-	str	r5, [r2, r4, lsl #2]	@ restore old mapping
-	mcr	p15, 0, r0, c1, c0, 0	@ turn on D-cache
 	bl	cpu_init		@ restore the und/abt/irq banked regs
 	mov	r0, #0			@ return zero on success
 	ldmfd	sp!, {r4 - r11, pc}
@@ -119,7 +90,7 @@ ENTRY(cpu_resume)
 	ldr	r0, sleep_save_sp	@ stack phys addr
 #endif
 	setmode	PSR_I_BIT | PSR_F_BIT | SVC_MODE, r1  @ set SVC, irqs off
-	@ load v:p, stack, resume fn
+	@ load phys pgd, stack, resume fn
   ARM(	ldmia	r0!, {r1, sp, pc}	)
 THUMB(	ldmia	r0!, {r1, r2, r3}	)
 THUMB(	mov	sp, r2			)
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index fe9e2954ee4..66aa455a171 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -31,6 +31,7 @@
 #include <asm/cacheflush.h>
 #include <asm/cpu.h>
 #include <asm/cputype.h>
+#include <asm/topology.h>
 #include <asm/mmu_context.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -268,6 +269,8 @@ static void __cpuinit smp_store_cpu_info(unsigned int cpuid)
 	struct cpuinfo_arm *cpu_info = &per_cpu(cpu_data, cpuid);
 
 	cpu_info->loops_per_jiffy = loops_per_jiffy;
+
+	store_cpu_topology(cpuid);
 }
 
 /*
@@ -356,6 +359,8 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 {
 	unsigned int ncores = num_possible_cpus();
 
+	init_cpu_topology();
+
 	smp_store_cpu_info(smp_processor_id());
 
 	/*
diff --git a/arch/arm/kernel/smp_scu.c b/arch/arm/kernel/smp_scu.c
index 7fcddb75c87..8f5dd796335 100644
--- a/arch/arm/kernel/smp_scu.c
+++ b/arch/arm/kernel/smp_scu.c
@@ -34,7 +34,7 @@ unsigned int __init scu_get_core_count(void __iomem *scu_base)
 /*
  * Enable the SCU
  */
-void __init scu_enable(void __iomem *scu_base)
+void scu_enable(void __iomem *scu_base)
 {
 	u32 scu_ctrl;
 
diff --git a/arch/arm/kernel/suspend.c b/arch/arm/kernel/suspend.c
new file mode 100644
index 00000000000..93a22d282c1
--- /dev/null
+++ b/arch/arm/kernel/suspend.c
@@ -0,0 +1,72 @@
+#include <linux/init.h>
+
+#include <asm/pgalloc.h>
+#include <asm/pgtable.h>
+#include <asm/memory.h>
+#include <asm/suspend.h>
+#include <asm/tlbflush.h>
+
+static pgd_t *suspend_pgd;
+
+extern int __cpu_suspend(unsigned long, int (*)(unsigned long));
+extern void cpu_resume_mmu(void);
+
+/*
+ * This is called by __cpu_suspend() to save the state, and do whatever
+ * flushing is required to ensure that when the CPU goes to sleep we have
+ * the necessary data available when the caches are not searched.
+ */
+void __cpu_suspend_save(u32 *ptr, u32 ptrsz, u32 sp, u32 *save_ptr)
+{
+	*save_ptr = virt_to_phys(ptr);
+
+	/* This must correspond to the LDM in cpu_resume() assembly */
+	*ptr++ = virt_to_phys(suspend_pgd);
+	*ptr++ = sp;
+	*ptr++ = virt_to_phys(cpu_do_resume);
+
+	cpu_do_suspend(ptr);
+
+	flush_cache_all();
+	outer_clean_range(*save_ptr, *save_ptr + ptrsz);
+	outer_clean_range(virt_to_phys(save_ptr),
+			  virt_to_phys(save_ptr) + sizeof(*save_ptr));
+}
+
+/*
+ * Hide the first two arguments to __cpu_suspend - these are an implementation
+ * detail which platform code shouldn't have to know about.
+ */
+int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
+{
+	struct mm_struct *mm = current->active_mm;
+	int ret;
+
+	if (!suspend_pgd)
+		return -EINVAL;
+
+	/*
+	 * Provide a temporary page table with an identity mapping for
+	 * the MMU-enable code, required for resuming.  On successful
+	 * resume (indicated by a zero return code), we need to switch
+	 * back to the correct page tables.
+	 */
+	ret = __cpu_suspend(arg, fn);
+	if (ret == 0) {
+		cpu_switch_mm(mm->pgd, mm);
+		local_flush_tlb_all();
+	}
+
+	return ret;
+}
+
+static int __init cpu_suspend_init(void)
+{
+	suspend_pgd = pgd_alloc(&init_mm);
+	if (suspend_pgd) {
+		unsigned long addr = virt_to_phys(cpu_resume_mmu);
+		identity_mapping_add(suspend_pgd, addr, addr + SECTION_SIZE);
+	}
+	return suspend_pgd ? 0 : -ENOMEM;
+}
+core_initcall(cpu_suspend_init);
diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c
new file mode 100644
index 00000000000..053ce9cbc0b
--- /dev/null
+++ b/arch/arm/kernel/topology.c
@@ -0,0 +1,589 @@
+/*
+ * arch/arm/kernel/topology.c
+ *
+ * Copyright (C) 2011 Linaro Limited.
+ * Written by: Vincent Guittot
+ *
+ * based on arch/sh/kernel/topology.c
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/init.h>
+#include <linux/percpu.h>
+#include <linux/node.h>
+#include <linux/nodemask.h>
+#include <linux/sched.h>
+#include <linux/cpumask.h>
+#include <linux/cpuset.h>
+
+#ifdef CONFIG_CPU_FREQ
+#include <linux/cpufreq.h>
+#endif
+
+#ifdef CONFIG_DEBUG_FS
+#include <linux/debugfs.h>
+#include <linux/uaccess.h>	/* for copy_from_user */
+#endif
+
+#include <asm/cputype.h>
+#include <asm/topology.h>
+
+#define MPIDR_SMP_BITMASK (0x3 << 30)
+#define MPIDR_SMP_VALUE (0x2 << 30)
+
+#define MPIDR_MT_BITMASK (0x1 << 24)
+
+/*
+ * These masks reflect the current use of the affinity levels.
+ * The affinity level can be up to 16 bits according to ARM ARM
+ */
+
+#define MPIDR_LEVEL0_MASK 0x3
+#define MPIDR_LEVEL0_SHIFT 0
+
+#define MPIDR_LEVEL1_MASK 0xF
+#define MPIDR_LEVEL1_SHIFT 8
+
+#define MPIDR_LEVEL2_MASK 0xFF
+#define MPIDR_LEVEL2_SHIFT 16
+
+struct cputopo_arm cpu_topology[NR_CPUS];
+
+/*
+ * cpu power scale management
+ */
+
+/*
+ * a per cpu data structure should be better because each cpu is mainly
+ * using its own cpu_power even it's not always true because of
+ * no_hz_idle_balance
+ */
+
+static DEFINE_PER_CPU(unsigned int, cpu_scale);
+
+/*
+ * cpu topology mask management
+ */
+
+unsigned int advanced_topology = 1;
+
+static void normal_cpu_topology_mask(void);
+static void (*set_cpu_topology_mask)(void) = normal_cpu_topology_mask;
+
+#ifdef CONFIG_CPU_FREQ
+/*
+ * This struct describes parameters to compute cpu_power
+ */
+struct cputopo_power {
+	int id;
+	int max; /* max idx in the table */
+	unsigned int step; /* frequency step for the table */
+	unsigned int *table; /* table of cpu_power */
+};
+
+/* default table with one default cpu_power value */
+unsigned int table_default_power[1] = {
+	1024
+};
+
+static struct cputopo_power default_cpu_power = {
+	.max  = 1,
+	.step = 1,
+	.table = table_default_power,
+};
+
+/* CA-9 table with cpufreq modifying cpu_power */
+#define CPU_MAX_FREQ 10
+/* we use a 200Mhz step for scaling cpu power */
+#define CPU_TOPO_FREQ_STEP 200000
+/* This table sets the cpu_power scale of a cpu according to 2 inputs which are
+ * the frequency and the sched_mc mode. The content of this table could be SoC
+ * specific so we should add a method to overwrite this default table.
+ * TODO: Study how to use DT for setting this table
+ */
+unsigned int table_ca9_power[CPU_MAX_FREQ] = {
+/* freq< 200   400   600   800  1000  1200  1400  1600  1800  other*/
+	4096, 4096, 4096, 1024, 1024, 1024, 1024, 1024, 1024, 1024, /* Power save mode CA9 MP */
+};
+
+static struct cputopo_power CA9_cpu_power = {
+	.max  = CPU_MAX_FREQ,
+	.step = CPU_TOPO_FREQ_STEP,
+	.table = table_ca9_power,
+};
+
+#define ARM_CORTEX_A9_DEFAULT_SCALE 0
+#define ARM_CORTEX_A9_POWER_SCALE 1
+/* This table list all possible cpu power configuration */
+struct cputopo_power *table_config[2] = {
+	&default_cpu_power,
+	&CA9_cpu_power,
+};
+
+struct cputopo_scale {
+	int id;
+	int freq;
+	struct cputopo_power *power;
+};
+
+/*
+ * The table will be mostly used by one cpu which will update the
+ * configuration for all cpu on a cpufreq notification
+ * or a sched_mc level change
+ */
+static struct cputopo_scale cpu_power[NR_CPUS];
+
+static void set_cpufreq_scale(unsigned int cpuid, unsigned int freq)
+{
+	unsigned int idx;
+
+	cpu_power[cpuid].freq = freq;
+
+	idx = freq / cpu_power[cpuid].power->step;
+	if (idx >= cpu_power[cpuid].power->max)
+		idx = cpu_power[cpuid].power->max - 1;
+
+	per_cpu(cpu_scale, cpuid) = cpu_power[cpuid].power->table[idx];
+	smp_wmb();
+}
+
+static void set_power_scale(unsigned int cpu, unsigned int idx)
+{
+	cpu_power[cpu].id = idx;
+	cpu_power[cpu].power = table_config[idx];
+
+	set_cpufreq_scale(cpu, cpu_power[cpu].freq);
+}
+
+static int topo_cpufreq_transition(struct notifier_block *nb,
+	unsigned long state, void *data)
+{
+	struct cpufreq_freqs *freqs = data;
+
+	if (state == CPUFREQ_POSTCHANGE || state == CPUFREQ_RESUMECHANGE)
+		set_cpufreq_scale(freqs->cpu, freqs->new);
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block topo_cpufreq_nb = {
+	.notifier_call = topo_cpufreq_transition,
+};
+
+static int topo_cpufreq_init(void)
+{
+	unsigned int cpu;
+
+	/* TODO set initial value according to current freq */
+
+	/* init core mask */
+	for_each_possible_cpu(cpu) {
+		cpu_power[cpu].freq = 0;
+		cpu_power[cpu].power = &default_cpu_power;
+	}
+
+	return cpufreq_register_notifier(&topo_cpufreq_nb,
+			CPUFREQ_TRANSITION_NOTIFIER);
+}
+#else
+#define ARM_CORTEX_A9_DEFAULT_SCALE 0
+#define ARM_CORTEX_A9_POWER_SCALE 0
+/* This table list all possible cpu power configuration */
+unsigned int table_config[1] = {
+	1024,
+};
+
+static void set_power_scale(unsigned int cpu, unsigned int idx)
+{
+	per_cpu(cpu_scale, cpu) = table_config[idx];
+}
+
+static inline int topo_cpufreq_init(void) {return 0; }
+#endif
+
+static int init_cpu_power_scale(void)
+{
+	/* register cpufreq notifer */
+	topo_cpufreq_init();
+
+	/* Do we need to change default config */
+	advanced_topology = 1;
+
+	/* Force a cpu topology update */
+	rebuild_sched_domains();
+
+	return 0;
+}
+
+core_initcall(init_cpu_power_scale);
+
+/*
+ * Update the cpu power
+ */
+
+unsigned long arch_scale_freq_power(struct sched_domain *sd, int cpu)
+{
+	return per_cpu(cpu_scale, cpu);
+}
+
+/*
+ * sched_domain flag configuration
+ */
+/* TODO add a config flag for this function */
+int arch_sd_sibling_asym_packing(void)
+{
+	if (sched_smt_power_savings || sched_mc_power_savings)
+		return SD_ASYM_PACKING;
+	return 0;
+}
+
+/*
+ * default topology function
+ */
+
+const struct cpumask *cpu_coregroup_mask(int cpu)
+{
+	return &cpu_topology[cpu].core_sibling;
+}
+
+/*
+ * clear cpu topology masks
+ */
+static void clear_cpu_topology_mask(void)
+{
+	unsigned int cpuid;
+	for_each_possible_cpu(cpuid) {
+		struct cputopo_arm *cpuid_topo = &(cpu_topology[cpuid]);
+		cpumask_clear(&cpuid_topo->core_sibling);
+		cpumask_clear(&cpuid_topo->thread_sibling);
+	}
+	smp_wmb();
+}
+
+/*
+ * default_cpu_topology_mask set the core and thread mask as described in the
+ * ARM ARM
+ */
+static inline void default_cpu_topology_mask(unsigned int cpuid)
+{
+	struct cputopo_arm *cpuid_topo = &cpu_topology[cpuid];
+	unsigned int cpu;
+
+	for_each_possible_cpu(cpu) {
+		struct cputopo_arm *cpu_topo = &cpu_topology[cpu];
+
+		if (cpuid_topo->socket_id == cpu_topo->socket_id) {
+			cpumask_set_cpu(cpuid, &cpu_topo->core_sibling);
+			if (cpu != cpuid)
+				cpumask_set_cpu(cpu,
+					&cpuid_topo->core_sibling);
+
+			if (cpuid_topo->core_id == cpu_topo->core_id) {
+				cpumask_set_cpu(cpuid,
+					&cpu_topo->thread_sibling);
+				if (cpu != cpuid)
+					cpumask_set_cpu(cpu,
+						&cpuid_topo->thread_sibling);
+			}
+		}
+	}
+	smp_wmb();
+}
+
+static void normal_cpu_topology_mask(void)
+{
+	unsigned int cpuid;
+
+	for_each_possible_cpu(cpuid) {
+		default_cpu_topology_mask(cpuid);
+		set_power_scale(cpuid, ARM_CORTEX_A9_DEFAULT_SCALE);
+	}
+	smp_wmb();
+}
+
+/*
+ * For Cortex-A9 MPcore, we emulate a multi-package topology in power mode.
+ * The goal is to gathers tasks on 1 virtual package
+ */
+static void power_cpu_topology_mask_CA9(void)
+{
+	unsigned int cpuid, cpu;
+
+	for_each_possible_cpu(cpuid) {
+		struct cputopo_arm *cpuid_topo = &cpu_topology[cpuid];
+
+		for_each_possible_cpu(cpu) {
+			struct cputopo_arm *cpu_topo = &cpu_topology[cpu];
+
+			if ((cpuid_topo->socket_id == cpu_topo->socket_id)
+			&& ((cpuid & 0x1) == (cpu & 0x1))) {
+				cpumask_set_cpu(cpuid, &cpu_topo->core_sibling);
+				if (cpu != cpuid)
+					cpumask_set_cpu(cpu,
+						&cpuid_topo->core_sibling);
+
+				if (cpuid_topo->core_id == cpu_topo->core_id) {
+					cpumask_set_cpu(cpuid,
+						&cpu_topo->thread_sibling);
+					if (cpu != cpuid)
+						cpumask_set_cpu(cpu,
+							&cpuid_topo->thread_sibling);
+				}
+			}
+		}
+		set_power_scale(cpuid, ARM_CORTEX_A9_POWER_SCALE);
+	}
+	smp_wmb();
+}
+
+#define ARM_FAMILY_MASK 0xFF0FFFF0
+#define ARM_CORTEX_A9_FAMILY 0x410FC090
+
+/* update_cpu_topology_policy select a cpu topology policy according to the
+ * available cores.
+ * TODO: The current version assumes that all cores are exactly the same which
+ * might not be true. We need to update it to take into account various
+ * configuration among which system with different kind of core.
+ */
+static int update_cpu_topology_policy(void)
+{
+	unsigned long cpuid;
+
+	if (sched_mc_power_savings == POWERSAVINGS_BALANCE_NONE) {
+		set_cpu_topology_mask = normal_cpu_topology_mask;
+		return 0;
+	}
+
+	cpuid = read_cpuid_id();
+	cpuid &= ARM_FAMILY_MASK;
+
+	switch (cpuid) {
+	case ARM_CORTEX_A9_FAMILY:
+		set_cpu_topology_mask = power_cpu_topology_mask_CA9;
+	break;
+	default:
+		set_cpu_topology_mask = normal_cpu_topology_mask;
+	break;
+	}
+
+	return 0;
+}
+
+/*
+ * store_cpu_topology is called at boot when only one cpu is running
+ * and with the mutex cpu_hotplug.lock locked, when several cpus have booted,
+ * which prevents simultaneous write access to cpu_topology array
+ */
+void store_cpu_topology(unsigned int cpuid)
+{
+	struct cputopo_arm *cpuid_topo = &cpu_topology[cpuid];
+	unsigned int mpidr;
+
+	/* If the cpu topology has been already set, just return */
+	if (cpuid_topo->core_id != -1)
+		return;
+
+	mpidr = read_cpuid_mpidr();
+
+	/* create cpu topology mapping */
+	if ((mpidr & MPIDR_SMP_BITMASK) == MPIDR_SMP_VALUE) {
+		/*
+		 * This is a multiprocessor system
+		 * multiprocessor format & multiprocessor mode field are set
+		 */
+
+		if (mpidr & MPIDR_MT_BITMASK) {
+			/* core performance interdependency */
+			cpuid_topo->thread_id = (mpidr >> MPIDR_LEVEL0_SHIFT)
+				& MPIDR_LEVEL0_MASK;
+			cpuid_topo->core_id = (mpidr >> MPIDR_LEVEL1_SHIFT)
+				& MPIDR_LEVEL1_MASK;
+			cpuid_topo->socket_id = (mpidr >> MPIDR_LEVEL2_SHIFT)
+				& MPIDR_LEVEL2_MASK;
+		} else {
+			/* largely independent cores */
+			cpuid_topo->thread_id = -1;
+			cpuid_topo->core_id = (mpidr >> MPIDR_LEVEL0_SHIFT)
+				& MPIDR_LEVEL0_MASK;
+			cpuid_topo->socket_id = (mpidr >> MPIDR_LEVEL1_SHIFT)
+				& MPIDR_LEVEL1_MASK;
+		}
+	} else {
+		/*
+		 * This is an uniprocessor system
+		 * we are in multiprocessor format but uniprocessor system
+		 * or in the old uniprocessor format
+		 */
+		cpuid_topo->thread_id = -1;
+		cpuid_topo->core_id = 0;
+		cpuid_topo->socket_id = -1;
+	}
+
+	/*
+	 * The core and thread sibling masks can also be updated during the
+	 * call of arch_update_cpu_topology
+	 */
+	default_cpu_topology_mask(cpuid);
+
+	printk(KERN_INFO "CPU%u: thread %d, cpu %d, socket %d, mpidr %x\n",
+		cpuid, cpu_topology[cpuid].thread_id,
+		cpu_topology[cpuid].core_id,
+		cpu_topology[cpuid].socket_id, mpidr);
+}
+
+/*
+ * arch_update_cpu_topology is called by the scheduler before building
+ * a new sched_domain hierarchy.
+ */
+int arch_update_cpu_topology(void)
+{
+	if (!advanced_topology)
+		return 0;
+
+	/* clear core threads mask */
+	clear_cpu_topology_mask();
+
+	/* set topology policy */
+	update_cpu_topology_policy();
+
+	/* set topology mask and power */
+	(*set_cpu_topology_mask)();
+
+	return 1;
+}
+
+/*
+ * init_cpu_topology is called at boot when only one cpu is running
+ * which prevent simultaneous write access to cpu_topology array
+ */
+void init_cpu_topology(void)
+{
+	unsigned int cpu;
+
+	/* init core mask */
+	for_each_possible_cpu(cpu) {
+		struct cputopo_arm *cpu_topo = &(cpu_topology[cpu]);
+
+		cpu_topo->thread_id = -1;
+		cpu_topo->core_id =  -1;
+		cpu_topo->socket_id = -1;
+		cpumask_clear(&cpu_topo->core_sibling);
+		cpumask_clear(&cpu_topo->thread_sibling);
+
+		per_cpu(cpu_scale, cpu) = SCHED_POWER_SCALE;
+	}
+	smp_wmb();
+}
+
+/*
+ * debugfs interface for scaling cpu power
+ */
+
+#ifdef CONFIG_DEBUG_FS
+static struct dentry *topo_debugfs_root;
+
+static ssize_t dbg_write(struct file *file, const char __user *buf,
+						size_t size, loff_t *off)
+{
+	unsigned int *value = file->f_dentry->d_inode->i_private;
+	char cdata[128];
+	unsigned long tmp;
+	unsigned int cpu;
+
+	if (size < (sizeof(cdata)-1)) {
+		if (copy_from_user(cdata, buf, size))
+			return -EFAULT;
+		cdata[size] = 0;
+		if (!strict_strtoul(cdata, 10, &tmp)) {
+			*value = tmp;
+
+#ifdef CONFIG_CPU_FREQ
+			for_each_online_cpu(cpu)
+				set_power_scale(cpu, cpu_power[cpu].id);
+#endif
+		}
+		return size;
+	}
+	return -EINVAL;
+}
+
+static ssize_t dbg_read(struct file *file, char __user *buf,
+						size_t size, loff_t *off)
+{
+	unsigned int *value = file->f_dentry->d_inode->i_private;
+	char cdata[128];
+	unsigned int len;
+
+	len = sprintf(cdata, "%u\n", *value);
+	return simple_read_from_buffer(buf, size, off, cdata, len);
+}
+
+static const struct file_operations debugfs_fops = {
+	.read = dbg_read,
+	.write = dbg_write,
+};
+
+static struct dentry *topo_debugfs_register(unsigned int cpu,
+						struct dentry *parent)
+{
+	struct dentry *cpu_d, *d;
+	char cpu_name[16];
+
+	sprintf(cpu_name, "cpu%u", cpu);
+
+	cpu_d = debugfs_create_dir(cpu_name, parent);
+	if (!cpu_d)
+		return NULL;
+
+	d = debugfs_create_file("cpu_power", S_IRUGO  | S_IWUGO,
+				cpu_d, &per_cpu(cpu_scale, cpu), &debugfs_fops);
+	if (!d)
+		goto err_out;
+
+#ifdef CONFIG_CPU_FREQ
+	d = debugfs_create_file("scale", S_IRUGO | S_IWUGO,
+				cpu_d, &cpu_power[cpu].id, &debugfs_fops);
+	if (!d)
+		goto err_out;
+
+	d = debugfs_create_file("freq", S_IRUGO,
+				cpu_d, &cpu_power[cpu].freq, &debugfs_fops);
+	if (!d)
+		goto err_out;
+#endif
+	return cpu_d;
+
+err_out:
+	debugfs_remove_recursive(cpu_d);
+	return NULL;
+}
+
+static int __init topo_debugfs_init(void)
+{
+	struct dentry *d;
+	unsigned int cpu;
+
+	d = debugfs_create_dir("cpu_topo", NULL);
+	if (!d)
+		return -ENOMEM;
+	topo_debugfs_root = d;
+
+	for_each_possible_cpu(cpu) {
+		d = topo_debugfs_register(cpu, topo_debugfs_root);
+		if (d == NULL)
+			goto err_out;
+	}
+	return 0;
+
+err_out:
+	debugfs_remove_recursive(topo_debugfs_root);
+	return -ENOMEM;
+}
+
+late_initcall(topo_debugfs_init);
+#endif
diff --git a/arch/arm/mach-at91/at91cap9_devices.c b/arch/arm/mach-at91/at91cap9_devices.c
index dba0d8d8a4b..0512baf0a21 100644
--- a/arch/arm/mach-at91/at91cap9_devices.c
+++ b/arch/arm/mach-at91/at91cap9_devices.c
@@ -92,7 +92,7 @@ void __init at91_add_device_usbh(struct at91_usbh_data *data) {}
  *  USB HS Device (Gadget)
  * -------------------------------------------------------------------- */
 
-#if defined(CONFIG_USB_GADGET_ATMEL_USBA) || defined(CONFIG_USB_GADGET_ATMEL_USBA_MODULE)
+#if defined(CONFIG_USB_ATMEL_USBA) || defined(CONFIG_USB_ATMEL_USBA_MODULE)
 
 static struct resource usba_udc_resources[] = {
 	[0] = {
diff --git a/arch/arm/mach-at91/at91sam9g45.c b/arch/arm/mach-at91/at91sam9g45.c
index e04c5fb6f1e..1532b508c81 100644
--- a/arch/arm/mach-at91/at91sam9g45.c
+++ b/arch/arm/mach-at91/at91sam9g45.c
@@ -12,6 +12,7 @@
 
 #include <linux/module.h>
 #include <linux/pm.h>
+#include <linux/dma-mapping.h>
 
 #include <asm/irq.h>
 #include <asm/mach/arch.h>
@@ -319,6 +320,7 @@ static void at91sam9g45_poweroff(void)
 static void __init at91sam9g45_map_io(void)
 {
 	at91_init_sram(0, AT91SAM9G45_SRAM_BASE, AT91SAM9G45_SRAM_SIZE);
+	init_consistent_dma_size(SZ_4M);
 }
 
 static void __init at91sam9g45_initialize(void)
diff --git a/arch/arm/mach-at91/at91sam9g45_devices.c b/arch/arm/mach-at91/at91sam9g45_devices.c
index 600bffb01ed..371bb0ecb0d 100644
--- a/arch/arm/mach-at91/at91sam9g45_devices.c
+++ b/arch/arm/mach-at91/at91sam9g45_devices.c
@@ -191,7 +191,7 @@ void __init at91_add_device_usbh_ehci(struct at91_usbh_data *data) {}
  *  USB HS Device (Gadget)
  * -------------------------------------------------------------------- */
 
-#if defined(CONFIG_USB_GADGET_ATMEL_USBA) || defined(CONFIG_USB_GADGET_ATMEL_USBA_MODULE)
+#if defined(CONFIG_USB_ATMEL_USBA) || defined(CONFIG_USB_ATMEL_USBA_MODULE)
 static struct resource usba_udc_resources[] = {
 	[0] = {
 		.start	= AT91SAM9G45_UDPHS_FIFO,
diff --git a/arch/arm/mach-at91/at91sam9rl_devices.c b/arch/arm/mach-at91/at91sam9rl_devices.c
index aacb19dc922..c884d590b00 100644
--- a/arch/arm/mach-at91/at91sam9rl_devices.c
+++ b/arch/arm/mach-at91/at91sam9rl_devices.c
@@ -75,7 +75,7 @@ void __init at91_add_device_hdmac(void) {}
  *  USB HS Device (Gadget)
  * -------------------------------------------------------------------- */
 
-#if defined(CONFIG_USB_GADGET_ATMEL_USBA) || defined(CONFIG_USB_GADGET_ATMEL_USBA_MODULE)
+#if defined(CONFIG_USB_ATMEL_USBA) || defined(CONFIG_USB_ATMEL_USBA_MODULE)
 
 static struct resource usba_udc_resources[] = {
 	[0] = {
diff --git a/arch/arm/mach-at91/include/mach/at91sam9g45.h b/arch/arm/mach-at91/include/mach/at91sam9g45.h
index 2c611b9a013..406bb649680 100644
--- a/arch/arm/mach-at91/include/mach/at91sam9g45.h
+++ b/arch/arm/mach-at91/include/mach/at91sam9g45.h
@@ -128,8 +128,6 @@
 #define AT91SAM9G45_EHCI_BASE	0x00800000	/* USB Host controller (EHCI) */
 #define AT91SAM9G45_VDEC_BASE	0x00900000	/* Video Decoder Controller */
 
-#define CONSISTENT_DMA_SIZE	SZ_4M
-
 /*
  * DMA peripheral identifiers
  * for hardware handshaking interface
diff --git a/arch/arm/mach-bcmring/include/mach/memory.h b/arch/arm/mach-bcmring/include/mach/memory.h
index 15162e4c75f..8848a5bb344 100644
--- a/arch/arm/mach-bcmring/include/mach/memory.h
+++ b/arch/arm/mach-bcmring/include/mach/memory.h
@@ -25,9 +25,4 @@
 
 #define PLAT_PHYS_OFFSET CFG_GLOBAL_RAM_BASE
 
-/*
- * Maximum DMA memory allowed is 14M
- */
-#define CONSISTENT_DMA_SIZE (SZ_16M - SZ_2M)
-
 #endif
diff --git a/arch/arm/mach-bcmring/mm.c b/arch/arm/mach-bcmring/mm.c
index 0f1c37e4523..8616876abb9 100644
--- a/arch/arm/mach-bcmring/mm.c
+++ b/arch/arm/mach-bcmring/mm.c
@@ -13,6 +13,7 @@
 *****************************************************************************/
 
 #include <linux/platform_device.h>
+#include <linux/dma-mapping.h>
 #include <asm/mach/map.h>
 
 #include <mach/hardware.h>
@@ -53,4 +54,6 @@ void __init bcmring_map_io(void)
 {
 
 	iotable_init(bcmring_io_desc, ARRAY_SIZE(bcmring_io_desc));
+	/* Maximum DMA memory allowed is 14M */
+	init_consistent_dma_size(14 << 20);
 }
diff --git a/arch/arm/mach-clps711x/autcpu12.c b/arch/arm/mach-clps711x/autcpu12.c
index 4a74b2c959b..0276091b7f8 100644
--- a/arch/arm/mach-clps711x/autcpu12.c
+++ b/arch/arm/mach-clps711x/autcpu12.c
@@ -64,7 +64,7 @@ void __init autcpu12_map_io(void)
 
 MACHINE_START(AUTCPU12, "autronix autcpu12")
 	/* Maintainer: Thomas Gleixner */
-	.boot_params	= 0xc0020000,
+	.atag_offset	= 0x20000,
 	.map_io		= autcpu12_map_io,
 	.init_irq	= clps711x_init_irq,
 	.timer		= &clps711x_timer,
diff --git a/arch/arm/mach-clps711x/cdb89712.c b/arch/arm/mach-clps711x/cdb89712.c
index 5a1689d4879..25b3bfd0e85 100644
--- a/arch/arm/mach-clps711x/cdb89712.c
+++ b/arch/arm/mach-clps711x/cdb89712.c
@@ -55,7 +55,7 @@ static void __init cdb89712_map_io(void)
 
 MACHINE_START(CDB89712, "Cirrus-CDB89712")
 	/* Maintainer: Ray Lehtiniemi */
-	.boot_params	= 0xc0000100,
+	.atag_offset	= 0x100,
 	.map_io		= cdb89712_map_io,
 	.init_irq	= clps711x_init_irq,
 	.timer		= &clps711x_timer,
diff --git a/arch/arm/mach-clps711x/ceiva.c b/arch/arm/mach-clps711x/ceiva.c
index 16481cf3e93..1df9ec67aa9 100644
--- a/arch/arm/mach-clps711x/ceiva.c
+++ b/arch/arm/mach-clps711x/ceiva.c
@@ -56,7 +56,7 @@ static void __init ceiva_map_io(void)
 
 MACHINE_START(CEIVA, "CEIVA/Polaroid Photo MAX Digital Picture Frame")
 	/* Maintainer: Rob Scott */
-	.boot_params	= 0xc0000100,
+	.atag_offset	= 0x100,
 	.map_io		= ceiva_map_io,
 	.init_irq	= clps711x_init_irq,
 	.timer		= &clps711x_timer,
diff --git a/arch/arm/mach-clps711x/clep7312.c b/arch/arm/mach-clps711x/clep7312.c
index 67b5abb4a60..06c8abd9371 100644
--- a/arch/arm/mach-clps711x/clep7312.c
+++ b/arch/arm/mach-clps711x/clep7312.c
@@ -37,7 +37,7 @@ fixup_clep7312(struct machine_desc *desc, struct tag *tags,
 
 MACHINE_START(CLEP7212, "Cirrus Logic 7212/7312")
 	/* Maintainer: Nobody */
-	.boot_params	= 0xc0000100,
+	.atag_offset	= 0x0100,
 	.fixup		= fixup_clep7312,
 	.map_io		= clps711x_map_io,
 	.init_irq	= clps711x_init_irq,
diff --git a/arch/arm/mach-clps711x/edb7211-arch.c b/arch/arm/mach-clps711x/edb7211-arch.c
index 98ca5b2e940..abf522d1ec9 100644
--- a/arch/arm/mach-clps711x/edb7211-arch.c
+++ b/arch/arm/mach-clps711x/edb7211-arch.c
@@ -57,7 +57,7 @@ fixup_edb7211(struct machine_desc *desc, struct tag *tags,
 
 MACHINE_START(EDB7211, "CL-EDB7211 (EP7211 eval board)")
 	/* Maintainer: Jon McClintock */
-	.boot_params	= 0xc0020100,	/* 0xc0000000 - 0xc001ffff can be video RAM */
+	.atag_offset	= 0x20100,	/* 0xc0000000 - 0xc001ffff can be video RAM */
 	.fixup		= fixup_edb7211,
 	.map_io		= edb7211_map_io,
 	.reserve	= edb7211_reserve,
diff --git a/arch/arm/mach-clps711x/fortunet.c b/arch/arm/mach-clps711x/fortunet.c
index b1cb479e71e..b6f7d86bb1c 100644
--- a/arch/arm/mach-clps711x/fortunet.c
+++ b/arch/arm/mach-clps711x/fortunet.c
@@ -75,7 +75,6 @@ fortunet_fixup(struct machine_desc *desc, struct tag *tags,
 
 MACHINE_START(FORTUNET, "ARM-FortuNet")
 	/* Maintainer: FortuNet Inc. */
-	.boot_params	= 0x00000000,
 	.fixup		= fortunet_fixup,
 	.map_io		= clps711x_map_io,
 	.init_irq	= clps711x_init_irq,
diff --git a/arch/arm/mach-clps711x/p720t.c b/arch/arm/mach-clps711x/p720t.c
index cefbce0480b..e7f75aeb1e5 100644
--- a/arch/arm/mach-clps711x/p720t.c
+++ b/arch/arm/mach-clps711x/p720t.c
@@ -89,7 +89,7 @@ static void __init p720t_map_io(void)
 
 MACHINE_START(P720T, "ARM-Prospector720T")
 	/* Maintainer: ARM Ltd/Deep Blue Solutions Ltd */
-	.boot_params	= 0xc0000100,
+	.atag_offset	= 0x100,
 	.fixup		= fixup_p720t,
 	.map_io		= p720t_map_io,
 	.init_irq	= clps711x_init_irq,
diff --git a/arch/arm/mach-cns3xxx/cns3420vb.c b/arch/arm/mach-cns3xxx/cns3420vb.c
index 3e7d1496cb4..55f7b4b08ab 100644
--- a/arch/arm/mach-cns3xxx/cns3420vb.c
+++ b/arch/arm/mach-cns3xxx/cns3420vb.c
@@ -197,7 +197,7 @@ static void __init cns3420_map_io(void)
 }
 
 MACHINE_START(CNS3420VB, "Cavium Networks CNS3420 Validation Board")
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.map_io		= cns3420_map_io,
 	.init_irq	= cns3xxx_init_irq,
 	.timer		= &cns3xxx_timer,
diff --git a/arch/arm/mach-davinci/board-da830-evm.c b/arch/arm/mach-davinci/board-da830-evm.c
index 84fd7868486..26d94c0b555 100644
--- a/arch/arm/mach-davinci/board-da830-evm.c
+++ b/arch/arm/mach-davinci/board-da830-evm.c
@@ -676,7 +676,7 @@ static void __init da830_evm_map_io(void)
 }
 
 MACHINE_START(DAVINCI_DA830_EVM, "DaVinci DA830/OMAP-L137/AM17x EVM")
-	.boot_params	= (DA8XX_DDR_BASE + 0x100),
+	.atag_offset	= 0x100,
 	.map_io		= da830_evm_map_io,
 	.init_irq	= cp_intc_init,
 	.timer		= &davinci_timer,
diff --git a/arch/arm/mach-davinci/board-da850-evm.c b/arch/arm/mach-davinci/board-da850-evm.c
index 008d51407cd..6e41cb5baeb 100644
--- a/arch/arm/mach-davinci/board-da850-evm.c
+++ b/arch/arm/mach-davinci/board-da850-evm.c
@@ -1291,7 +1291,7 @@ static void __init da850_evm_map_io(void)
 }
 
 MACHINE_START(DAVINCI_DA850_EVM, "DaVinci DA850/OMAP-L138/AM18x EVM")
-	.boot_params	= (DA8XX_DDR_BASE + 0x100),
+	.atag_offset	= 0x100,
 	.map_io		= da850_evm_map_io,
 	.init_irq	= cp_intc_init,
 	.timer		= &davinci_timer,
diff --git a/arch/arm/mach-davinci/board-dm355-evm.c b/arch/arm/mach-davinci/board-dm355-evm.c
index 241a6bd6740..65566280b7c 100644
--- a/arch/arm/mach-davinci/board-dm355-evm.c
+++ b/arch/arm/mach-davinci/board-dm355-evm.c
@@ -351,7 +351,7 @@ static __init void dm355_evm_init(void)
 }
 
 MACHINE_START(DAVINCI_DM355_EVM, "DaVinci DM355 EVM")
-	.boot_params  = (0x80000100),
+	.atag_offset  = 0x100,
 	.map_io	      = dm355_evm_map_io,
 	.init_irq     = davinci_irq_init,
 	.timer	      = &davinci_timer,
diff --git a/arch/arm/mach-davinci/board-dm355-leopard.c b/arch/arm/mach-davinci/board-dm355-leopard.c
index bee284ca7fd..b307470b071 100644
--- a/arch/arm/mach-davinci/board-dm355-leopard.c
+++ b/arch/arm/mach-davinci/board-dm355-leopard.c
@@ -270,7 +270,7 @@ static __init void dm355_leopard_init(void)
 }
 
 MACHINE_START(DM355_LEOPARD, "DaVinci DM355 leopard")
-	.boot_params  = (0x80000100),
+	.atag_offset  = 0x100,
 	.map_io	      = dm355_leopard_map_io,
 	.init_irq     = davinci_irq_init,
 	.timer	      = &davinci_timer,
diff --git a/arch/arm/mach-davinci/board-dm365-evm.c b/arch/arm/mach-davinci/board-dm365-evm.c
index 9818f214d4f..04c43abcca6 100644
--- a/arch/arm/mach-davinci/board-dm365-evm.c
+++ b/arch/arm/mach-davinci/board-dm365-evm.c
@@ -612,7 +612,7 @@ static __init void dm365_evm_init(void)
 }
 
 MACHINE_START(DAVINCI_DM365_EVM, "DaVinci DM365 EVM")
-	.boot_params	= (0x80000100),
+	.atag_offset	= 0x100,
 	.map_io		= dm365_evm_map_io,
 	.init_irq	= davinci_irq_init,
 	.timer		= &davinci_timer,
diff --git a/arch/arm/mach-davinci/board-dm644x-evm.c b/arch/arm/mach-davinci/board-dm644x-evm.c
index 95607a191e0..a005e7691dd 100644
--- a/arch/arm/mach-davinci/board-dm644x-evm.c
+++ b/arch/arm/mach-davinci/board-dm644x-evm.c
@@ -712,7 +712,7 @@ static __init void davinci_evm_init(void)
 
 MACHINE_START(DAVINCI_EVM, "DaVinci DM644x EVM")
 	/* Maintainer: MontaVista Software <source@mvista.com> */
-	.boot_params  = (DAVINCI_DDR_BASE + 0x100),
+	.atag_offset  = 0x100,
 	.map_io	      = davinci_evm_map_io,
 	.init_irq     = davinci_irq_init,
 	.timer	      = &davinci_timer,
diff --git a/arch/arm/mach-davinci/board-dm646x-evm.c b/arch/arm/mach-davinci/board-dm646x-evm.c
index 993a3146fd3..337c45e3e44 100644
--- a/arch/arm/mach-davinci/board-dm646x-evm.c
+++ b/arch/arm/mach-davinci/board-dm646x-evm.c
@@ -792,7 +792,7 @@ static __init void evm_init(void)
 }
 
 MACHINE_START(DAVINCI_DM6467_EVM, "DaVinci DM646x EVM")
-	.boot_params  = (0x80000100),
+	.atag_offset  = 0x100,
 	.map_io       = davinci_map_io,
 	.init_irq     = davinci_irq_init,
 	.timer        = &davinci_timer,
@@ -801,7 +801,7 @@ MACHINE_START(DAVINCI_DM6467_EVM, "DaVinci DM646x EVM")
 MACHINE_END
 
 MACHINE_START(DAVINCI_DM6467TEVM, "DaVinci DM6467T EVM")
-	.boot_params  = (0x80000100),
+	.atag_offset  = 0x100,
 	.map_io       = davinci_map_io,
 	.init_irq     = davinci_irq_init,
 	.timer        = &davinci_timer,
diff --git a/arch/arm/mach-davinci/board-mityomapl138.c b/arch/arm/mach-davinci/board-mityomapl138.c
index c278226627a..6efc84cceca 100644
--- a/arch/arm/mach-davinci/board-mityomapl138.c
+++ b/arch/arm/mach-davinci/board-mityomapl138.c
@@ -566,7 +566,7 @@ static void __init mityomapl138_map_io(void)
 }
 
 MACHINE_START(MITYOMAPL138, "MityDSP-L138/MityARM-1808")
-	.boot_params	= (DA8XX_DDR_BASE + 0x100),
+	.atag_offset	= 0x100,
 	.map_io		= mityomapl138_map_io,
 	.init_irq	= cp_intc_init,
 	.timer		= &davinci_timer,
diff --git a/arch/arm/mach-davinci/board-neuros-osd2.c b/arch/arm/mach-davinci/board-neuros-osd2.c
index d60a80028ba..38d6f644d8b 100644
--- a/arch/arm/mach-davinci/board-neuros-osd2.c
+++ b/arch/arm/mach-davinci/board-neuros-osd2.c
@@ -272,7 +272,7 @@ static __init void davinci_ntosd2_init(void)
 
 MACHINE_START(NEUROS_OSD2, "Neuros OSD2")
 	/* Maintainer: Neuros Technologies <neuros@groups.google.com> */
-	.boot_params	= (DAVINCI_DDR_BASE + 0x100),
+	.atag_offset	= 0x100,
 	.map_io		 = davinci_ntosd2_map_io,
 	.init_irq	= davinci_irq_init,
 	.timer		= &davinci_timer,
diff --git a/arch/arm/mach-davinci/board-omapl138-hawk.c b/arch/arm/mach-davinci/board-omapl138-hawk.c
index 237332a1142..c6701e4a795 100644
--- a/arch/arm/mach-davinci/board-omapl138-hawk.c
+++ b/arch/arm/mach-davinci/board-omapl138-hawk.c
@@ -338,7 +338,7 @@ static void __init omapl138_hawk_map_io(void)
 }
 
 MACHINE_START(OMAPL138_HAWKBOARD, "AM18x/OMAP-L138 Hawkboard")
-	.boot_params	= (DA8XX_DDR_BASE + 0x100),
+	.atag_offset	= 0x100,
 	.map_io		= omapl138_hawk_map_io,
 	.init_irq	= cp_intc_init,
 	.timer		= &davinci_timer,
diff --git a/arch/arm/mach-davinci/board-sffsdr.c b/arch/arm/mach-davinci/board-sffsdr.c
index 5f4385c0a08..5dd4da9d230 100644
--- a/arch/arm/mach-davinci/board-sffsdr.c
+++ b/arch/arm/mach-davinci/board-sffsdr.c
@@ -151,7 +151,7 @@ static __init void davinci_sffsdr_init(void)
 
 MACHINE_START(SFFSDR, "Lyrtech SFFSDR")
 	/* Maintainer: Hugo Villeneuve hugo.villeneuve@lyrtech.com */
-	.boot_params  = (DAVINCI_DDR_BASE + 0x100),
+	.atag_offset  = 0x100,
 	.map_io	      = davinci_sffsdr_map_io,
 	.init_irq     = davinci_irq_init,
 	.timer	      = &davinci_timer,
diff --git a/arch/arm/mach-davinci/board-tnetv107x-evm.c b/arch/arm/mach-davinci/board-tnetv107x-evm.c
index 78289206568..90ee7b5aabd 100644
--- a/arch/arm/mach-davinci/board-tnetv107x-evm.c
+++ b/arch/arm/mach-davinci/board-tnetv107x-evm.c
@@ -277,7 +277,7 @@ console_initcall(tnetv107x_evm_console_init);
 #endif
 
 MACHINE_START(TNETV107X, "TNETV107X EVM")
-	.boot_params	= (TNETV107X_DDR_BASE + 0x100),
+	.atag_offset	= 0x100,
 	.map_io		= tnetv107x_init,
 	.init_irq	= cp_intc_init,
 	.timer		= &davinci_timer,
diff --git a/arch/arm/mach-davinci/common.c b/arch/arm/mach-davinci/common.c
index 1d255739423..865ffe5899a 100644
--- a/arch/arm/mach-davinci/common.c
+++ b/arch/arm/mach-davinci/common.c
@@ -12,6 +12,7 @@
 #include <linux/io.h>
 #include <linux/etherdevice.h>
 #include <linux/davinci_emac.h>
+#include <linux/dma-mapping.h>
 
 #include <asm/tlb.h>
 #include <asm/mach/map.h>
@@ -86,6 +87,8 @@ void __init davinci_common_init(struct davinci_soc_info *soc_info)
 		iotable_init(davinci_soc_info.io_desc,
 				davinci_soc_info.io_desc_num);
 
+	init_consistent_dma_size(14 << 20);
+
 	/*
 	 * Normally devicemaps_init() would flush caches and tlb after
 	 * mdesc->map_io(), but we must also do it here because of the CPU
diff --git a/arch/arm/mach-davinci/include/mach/memory.h b/arch/arm/mach-davinci/include/mach/memory.h
index 78731944a70..885d2331966 100644
--- a/arch/arm/mach-davinci/include/mach/memory.h
+++ b/arch/arm/mach-davinci/include/mach/memory.h
@@ -36,9 +36,4 @@
 #define DDR2_MCLKSTOPEN_BIT	BIT(30)
 #define DDR2_LPMODEN_BIT	BIT(31)
 
-/*
- * Increase size of DMA-consistent memory region
- */
-#define CONSISTENT_DMA_SIZE (14<<20)
-
 #endif /* __ASM_ARCH_MEMORY_H */
diff --git a/arch/arm/mach-dove/cm-a510.c b/arch/arm/mach-dove/cm-a510.c
index 03e11f9dca9..c8a406f7e94 100644
--- a/arch/arm/mach-dove/cm-a510.c
+++ b/arch/arm/mach-dove/cm-a510.c
@@ -87,7 +87,7 @@ static void __init cm_a510_init(void)
 }
 
 MACHINE_START(CM_A510, "Compulab CM-A510 Board")
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= cm_a510_init,
 	.map_io		= dove_map_io,
 	.init_early	= dove_init_early,
diff --git a/arch/arm/mach-dove/dove-db-setup.c b/arch/arm/mach-dove/dove-db-setup.c
index 2ac34ecfa74..11ea34e4fc7 100644
--- a/arch/arm/mach-dove/dove-db-setup.c
+++ b/arch/arm/mach-dove/dove-db-setup.c
@@ -94,7 +94,7 @@ static void __init dove_db_init(void)
 }
 
 MACHINE_START(DOVE_DB, "Marvell DB-MV88AP510-BP Development Board")
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= dove_db_init,
 	.map_io		= dove_map_io,
 	.init_early	= dove_init_early,
diff --git a/arch/arm/mach-ebsa110/core.c b/arch/arm/mach-ebsa110/core.c
index 087bc771ac2..d0ce8abdd4b 100644
--- a/arch/arm/mach-ebsa110/core.c
+++ b/arch/arm/mach-ebsa110/core.c
@@ -280,7 +280,7 @@ arch_initcall(ebsa110_init);
 
 MACHINE_START(EBSA110, "EBSA110")
 	/* Maintainer: Russell King */
-	.boot_params	= 0x00000400,
+	.atag_offset	= 0x400,
 	.reserve_lp0	= 1,
 	.reserve_lp2	= 1,
 	.soft_reboot	= 1,
diff --git a/arch/arm/mach-ep93xx/adssphere.c b/arch/arm/mach-ep93xx/adssphere.c
index 61b98ce4b67..0713448206a 100644
--- a/arch/arm/mach-ep93xx/adssphere.c
+++ b/arch/arm/mach-ep93xx/adssphere.c
@@ -33,7 +33,7 @@ static void __init adssphere_init_machine(void)
 
 MACHINE_START(ADSSPHERE, "ADS Sphere board")
 	/* Maintainer: Lennert Buytenhek <buytenh@wantstofly.org> */
-	.boot_params	= EP93XX_SDCE3_PHYS_BASE_SYNC + 0x100,
+	.atag_offset	= 0x100,
 	.map_io		= ep93xx_map_io,
 	.init_irq	= ep93xx_init_irq,
 	.timer		= &ep93xx_timer,
diff --git a/arch/arm/mach-ep93xx/edb93xx.c b/arch/arm/mach-ep93xx/edb93xx.c
index 9969bb115f6..257175edc57 100644
--- a/arch/arm/mach-ep93xx/edb93xx.c
+++ b/arch/arm/mach-ep93xx/edb93xx.c
@@ -240,7 +240,7 @@ static void __init edb93xx_init_machine(void)
 #ifdef CONFIG_MACH_EDB9301
 MACHINE_START(EDB9301, "Cirrus Logic EDB9301 Evaluation Board")
 	/* Maintainer: H Hartley Sweeten <hsweeten@visionengravers.com> */
-	.boot_params	= EP93XX_SDCE3_PHYS_BASE_SYNC + 0x100,
+	.atag_offset	= 0x100,
 	.map_io		= ep93xx_map_io,
 	.init_irq	= ep93xx_init_irq,
 	.timer		= &ep93xx_timer,
@@ -251,7 +251,7 @@ MACHINE_END
 #ifdef CONFIG_MACH_EDB9302
 MACHINE_START(EDB9302, "Cirrus Logic EDB9302 Evaluation Board")
 	/* Maintainer: George Kashperko <george@chas.com.ua> */
-	.boot_params	= EP93XX_SDCE3_PHYS_BASE_SYNC + 0x100,
+	.atag_offset	= 0x100,
 	.map_io		= ep93xx_map_io,
 	.init_irq	= ep93xx_init_irq,
 	.timer		= &ep93xx_timer,
@@ -262,7 +262,7 @@ MACHINE_END
 #ifdef CONFIG_MACH_EDB9302A
 MACHINE_START(EDB9302A, "Cirrus Logic EDB9302A Evaluation Board")
 	/* Maintainer: Lennert Buytenhek <buytenh@wantstofly.org> */
-	.boot_params	= EP93XX_SDCE0_PHYS_BASE + 0x100,
+	.atag_offset	= 0x100,
 	.map_io		= ep93xx_map_io,
 	.init_irq	= ep93xx_init_irq,
 	.timer		= &ep93xx_timer,
@@ -273,7 +273,7 @@ MACHINE_END
 #ifdef CONFIG_MACH_EDB9307
 MACHINE_START(EDB9307, "Cirrus Logic EDB9307 Evaluation Board")
 	/* Maintainer: Herbert Valerio Riedel <hvr@gnu.org> */
-	.boot_params	= EP93XX_SDCE3_PHYS_BASE_SYNC + 0x100,
+	.atag_offset	= 0x100,
 	.map_io		= ep93xx_map_io,
 	.init_irq	= ep93xx_init_irq,
 	.timer		= &ep93xx_timer,
@@ -284,7 +284,7 @@ MACHINE_END
 #ifdef CONFIG_MACH_EDB9307A
 MACHINE_START(EDB9307A, "Cirrus Logic EDB9307A Evaluation Board")
 	/* Maintainer: H Hartley Sweeten <hsweeten@visionengravers.com> */
-	.boot_params	= EP93XX_SDCE0_PHYS_BASE + 0x100,
+	.atag_offset	= 0x100,
 	.map_io		= ep93xx_map_io,
 	.init_irq	= ep93xx_init_irq,
 	.timer		= &ep93xx_timer,
@@ -295,7 +295,7 @@ MACHINE_END
 #ifdef CONFIG_MACH_EDB9312
 MACHINE_START(EDB9312, "Cirrus Logic EDB9312 Evaluation Board")
 	/* Maintainer: Toufeeq Hussain <toufeeq_hussain@infosys.com> */
-	.boot_params	= EP93XX_SDCE3_PHYS_BASE_SYNC + 0x100,
+	.atag_offset	= 0x100,
 	.map_io		= ep93xx_map_io,
 	.init_irq	= ep93xx_init_irq,
 	.timer		= &ep93xx_timer,
@@ -306,7 +306,7 @@ MACHINE_END
 #ifdef CONFIG_MACH_EDB9315
 MACHINE_START(EDB9315, "Cirrus Logic EDB9315 Evaluation Board")
 	/* Maintainer: Lennert Buytenhek <buytenh@wantstofly.org> */
-	.boot_params	= EP93XX_SDCE3_PHYS_BASE_SYNC + 0x100,
+	.atag_offset	= 0x100,
 	.map_io		= ep93xx_map_io,
 	.init_irq	= ep93xx_init_irq,
 	.timer		= &ep93xx_timer,
@@ -317,7 +317,7 @@ MACHINE_END
 #ifdef CONFIG_MACH_EDB9315A
 MACHINE_START(EDB9315A, "Cirrus Logic EDB9315A Evaluation Board")
 	/* Maintainer: Lennert Buytenhek <buytenh@wantstofly.org> */
-	.boot_params	= EP93XX_SDCE0_PHYS_BASE + 0x100,
+	.atag_offset	= 0x100,
 	.map_io		= ep93xx_map_io,
 	.init_irq	= ep93xx_init_irq,
 	.timer		= &ep93xx_timer,
diff --git a/arch/arm/mach-ep93xx/gesbc9312.c b/arch/arm/mach-ep93xx/gesbc9312.c
index 9bd3152bff9..45ee205856f 100644
--- a/arch/arm/mach-ep93xx/gesbc9312.c
+++ b/arch/arm/mach-ep93xx/gesbc9312.c
@@ -33,7 +33,7 @@ static void __init gesbc9312_init_machine(void)
 
 MACHINE_START(GESBC9312, "Glomation GESBC-9312-sx")
 	/* Maintainer: Lennert Buytenhek <buytenh@wantstofly.org> */
-	.boot_params	= EP93XX_SDCE3_PHYS_BASE_SYNC + 0x100,
+	.atag_offset	= 0x100,
 	.map_io		= ep93xx_map_io,
 	.init_irq	= ep93xx_init_irq,
 	.timer		= &ep93xx_timer,
diff --git a/arch/arm/mach-ep93xx/micro9.c b/arch/arm/mach-ep93xx/micro9.c
index 7adea6258ef..e72f7368876 100644
--- a/arch/arm/mach-ep93xx/micro9.c
+++ b/arch/arm/mach-ep93xx/micro9.c
@@ -77,7 +77,7 @@ static void __init micro9_init_machine(void)
 #ifdef CONFIG_MACH_MICRO9H
 MACHINE_START(MICRO9, "Contec Micro9-High")
 	/* Maintainer: Hubert Feurstein <hubert.feurstein@contec.at> */
-	.boot_params	= EP93XX_SDCE3_PHYS_BASE_SYNC + 0x100,
+	.atag_offset	= 0x100,
 	.map_io		= ep93xx_map_io,
 	.init_irq	= ep93xx_init_irq,
 	.timer		= &ep93xx_timer,
@@ -88,7 +88,7 @@ MACHINE_END
 #ifdef CONFIG_MACH_MICRO9M
 MACHINE_START(MICRO9M, "Contec Micro9-Mid")
 	/* Maintainer: Hubert Feurstein <hubert.feurstein@contec.at> */
-	.boot_params	= EP93XX_SDCE3_PHYS_BASE_ASYNC + 0x100,
+	.atag_offset	= 0x100,
 	.map_io		= ep93xx_map_io,
 	.init_irq	= ep93xx_init_irq,
 	.timer		= &ep93xx_timer,
@@ -99,7 +99,7 @@ MACHINE_END
 #ifdef CONFIG_MACH_MICRO9L
 MACHINE_START(MICRO9L, "Contec Micro9-Lite")
 	/* Maintainer: Hubert Feurstein <hubert.feurstein@contec.at> */
-	.boot_params	= EP93XX_SDCE3_PHYS_BASE_SYNC + 0x100,
+	.atag_offset	= 0x100,
 	.map_io		= ep93xx_map_io,
 	.init_irq	= ep93xx_init_irq,
 	.timer		= &ep93xx_timer,
@@ -110,7 +110,7 @@ MACHINE_END
 #ifdef CONFIG_MACH_MICRO9S
 MACHINE_START(MICRO9S, "Contec Micro9-Slim")
 	/* Maintainer: Hubert Feurstein <hubert.feurstein@contec.at> */
-	.boot_params	= EP93XX_SDCE3_PHYS_BASE_ASYNC + 0x100,
+	.atag_offset	= 0x100,
 	.map_io		= ep93xx_map_io,
 	.init_irq	= ep93xx_init_irq,
 	.timer		= &ep93xx_timer,
diff --git a/arch/arm/mach-ep93xx/simone.c b/arch/arm/mach-ep93xx/simone.c
index 8392e95d7ce..238bc603da8 100644
--- a/arch/arm/mach-ep93xx/simone.c
+++ b/arch/arm/mach-ep93xx/simone.c
@@ -65,8 +65,8 @@ static void __init simone_init_machine(void)
 }
 
 MACHINE_START(SIM_ONE, "Simplemachines Sim.One Board")
-/* Maintainer: Ryan Mallon */
-	.boot_params	= EP93XX_SDCE0_PHYS_BASE + 0x100,
+	/* Maintainer: Ryan Mallon */
+	.atag_offset	= 0x100,
 	.map_io		= ep93xx_map_io,
 	.init_irq	= ep93xx_init_irq,
 	.timer		= &ep93xx_timer,
diff --git a/arch/arm/mach-ep93xx/snappercl15.c b/arch/arm/mach-ep93xx/snappercl15.c
index 2e9c614757e..3bdf3a2e5ad 100644
--- a/arch/arm/mach-ep93xx/snappercl15.c
+++ b/arch/arm/mach-ep93xx/snappercl15.c
@@ -163,7 +163,7 @@ static void __init snappercl15_init_machine(void)
 
 MACHINE_START(SNAPPER_CL15, "Bluewater Systems Snapper CL15")
 	/* Maintainer: Ryan Mallon */
-	.boot_params	= EP93XX_SDCE0_PHYS_BASE + 0x100,
+	.atag_offset	= 0x100,
 	.map_io		= ep93xx_map_io,
 	.init_irq	= ep93xx_init_irq,
 	.timer 		= &ep93xx_timer,
diff --git a/arch/arm/mach-ep93xx/ts72xx.c b/arch/arm/mach-ep93xx/ts72xx.c
index c2d2cf40ead..1ade3c34050 100644
--- a/arch/arm/mach-ep93xx/ts72xx.c
+++ b/arch/arm/mach-ep93xx/ts72xx.c
@@ -257,7 +257,7 @@ static void __init ts72xx_init_machine(void)
 
 MACHINE_START(TS72XX, "Technologic Systems TS-72xx SBC")
 	/* Maintainer: Lennert Buytenhek <buytenh@wantstofly.org> */
-	.boot_params	= EP93XX_SDCE3_PHYS_BASE_SYNC + 0x100,
+	.atag_offset	= 0x100,
 	.map_io		= ts72xx_map_io,
 	.init_irq	= ep93xx_init_irq,
 	.timer		= &ep93xx_timer,
diff --git a/arch/arm/mach-exynos4/Kconfig b/arch/arm/mach-exynos4/Kconfig
index 0c77ab99fa1..f83526865d1 100644
--- a/arch/arm/mach-exynos4/Kconfig
+++ b/arch/arm/mach-exynos4/Kconfig
@@ -46,6 +46,17 @@ config EXYNOS4_DEV_DWMCI
 	help
 	  Compile in platform device definitions for DWMCI
 
+config EXYNOS4_DEV_TMU
+	bool "Exynos4 tmu device support"
+	default n
+	depends on ARCH_EXYNOS4
+	---help---
+	  Compile in platform device definitions for TMU. This macro also
+	  enables compilation hwmon base TMU driver and also allows compilation
+	  of the platform device files. The platform data in this case is trip
+	  temperature and some tmu h/w configurations related parameter.
+
+
 config EXYNOS4_SETUP_I2C1
 	bool
 	help
@@ -218,6 +229,17 @@ config MACH_NURI
 	help
 	  Machine support for Samsung Mobile NURI Board.
 
+config MACH_ORIGEN
+	bool "ORIGEN"
+	select CPU_EXYNOS4210
+	select S3C_DEV_RTC
+	select S3C_DEV_WDT
+	select S3C_DEV_HSMMC2
+	select EXYNOS4_DEV_TMU
+	select EXYNOS4_SETUP_SDHCI
+	help
+	  Machine support for ORIGEN based on Samsung EXYNOS4210
+
 endmenu
 
 comment "Configuration for HSMMC bus width"
diff --git a/arch/arm/mach-exynos4/Makefile b/arch/arm/mach-exynos4/Makefile
index b7fe1d7b0b1..8e5c098db7c 100644
--- a/arch/arm/mach-exynos4/Makefile
+++ b/arch/arm/mach-exynos4/Makefile
@@ -30,6 +30,7 @@ obj-$(CONFIG_MACH_SMDKV310)		+= mach-smdkv310.o
 obj-$(CONFIG_MACH_ARMLEX4210)		+= mach-armlex4210.o
 obj-$(CONFIG_MACH_UNIVERSAL_C210)	+= mach-universal_c210.o
 obj-$(CONFIG_MACH_NURI)			+= mach-nuri.o
+obj-$(CONFIG_MACH_ORIGEN)		+= mach-origen.o
 
 # device support
 
@@ -38,6 +39,7 @@ obj-$(CONFIG_EXYNOS4_DEV_AHCI)		+= dev-ahci.o
 obj-$(CONFIG_EXYNOS4_DEV_PD)		+= dev-pd.o
 obj-$(CONFIG_EXYNOS4_DEV_SYSMMU)	+= dev-sysmmu.o
 obj-$(CONFIG_EXYNOS4_DEV_DWMCI)	+= dev-dwmci.o
+obj-$(CONFIG_EXYNOS4_DEV_TMU)           += dev-tmu.o
 
 obj-$(CONFIG_EXYNOS4_SETUP_FIMC)	+= setup-fimc.o
 obj-$(CONFIG_EXYNOS4_SETUP_FIMD0)	+= setup-fimd0.o
diff --git a/arch/arm/mach-exynos4/Makefile.boot b/arch/arm/mach-exynos4/Makefile.boot
index d65956ffb43..fcee6b5384a 100644
--- a/arch/arm/mach-exynos4/Makefile.boot
+++ b/arch/arm/mach-exynos4/Makefile.boot
@@ -1,2 +1,4 @@
    zreladdr-y	:= 0x40008000
 params_phys-y	:= 0x40000100
+
+dtb-$(CONFIG_MACH_SMDKV310) += exynos4-smdkv310.dtb
diff --git a/arch/arm/mach-exynos4/clock.c b/arch/arm/mach-exynos4/clock.c
index 86964d2e9e1..b90920e526f 100644
--- a/arch/arm/mach-exynos4/clock.c
+++ b/arch/arm/mach-exynos4/clock.c
@@ -468,6 +468,10 @@ static struct clk init_clocks_off[] = {
 		.enable		= exynos4_clk_ip_peril_ctrl,
 		.ctrlbit	= (1 << 15),
 	}, {
+		.name		= "tmu_apbif",
+		.enable		= exynos4_clk_ip_perir_ctrl,
+		.ctrlbit	= (1 << 17),
+	}, {
 		.name		= "keypad",
 		.enable		= exynos4_clk_ip_perir_ctrl,
 		.ctrlbit	= (1 << 16),
diff --git a/arch/arm/mach-exynos4/cpu.c b/arch/arm/mach-exynos4/cpu.c
index 746d6fc6d39..c1cb39df589 100644
--- a/arch/arm/mach-exynos4/cpu.c
+++ b/arch/arm/mach-exynos4/cpu.c
@@ -11,6 +11,7 @@
 #include <linux/sched.h>
 #include <linux/sysdev.h>
 
+#include <asm/cacheflush.h>
 #include <asm/mach/map.h>
 #include <asm/mach/irq.h>
 
@@ -31,6 +32,7 @@
 
 #include <mach/regs-irq.h>
 #include <mach/regs-pmu.h>
+#include <mach/pmu.h>
 
 extern int combiner_init(unsigned int combiner_nr, void __iomem *base,
 			 unsigned int irq_start);
@@ -221,16 +223,34 @@ core_initcall(exynos4_core_init);
 #ifdef CONFIG_CACHE_L2X0
 static int __init exynos4_l2x0_cache_init(void)
 {
-	/* TAG, Data Latency Control: 2cycle */
-	__raw_writel(0x110, S5P_VA_L2CC + L2X0_TAG_LATENCY_CTRL);
-	__raw_writel(0x110, S5P_VA_L2CC + L2X0_DATA_LATENCY_CTRL);
+	if (!(__raw_readl(S5P_VA_L2CC + L2X0_CTRL) & 0x1)) {
 
-	/* L2X0 Prefetch Control */
-	__raw_writel(0x30000007, S5P_VA_L2CC + L2X0_PREFETCH_CTRL);
+		l2x0_saved_regs.phy_base = EXYNOS4_PA_L2CC;
+		/* TAG, Data Latency Control: 2 cycles */
+		l2x0_saved_regs.tag_latency = 0x110;
+		l2x0_saved_regs.data_latency = 0x110;
+		l2x0_saved_regs.prefetch_ctrl = 0x30000007;
+		l2x0_saved_regs.pwr_ctrl =
+			(L2X0_DYNAMIC_CLK_GATING_EN | L2X0_STNDBY_MODE_EN);
 
-	/* L2X0 Power Control */
-	__raw_writel(L2X0_DYNAMIC_CLK_GATING_EN | L2X0_STNDBY_MODE_EN,
-		     S5P_VA_L2CC + L2X0_POWER_CTRL);
+		l2x0_regs_phys = virt_to_phys(&l2x0_saved_regs);
+
+		__raw_writel(l2x0_saved_regs.tag_latency,
+				S5P_VA_L2CC + L2X0_TAG_LATENCY_CTRL);
+		__raw_writel(l2x0_saved_regs.data_latency,
+				S5P_VA_L2CC + L2X0_DATA_LATENCY_CTRL);
+
+		/* L2X0 Prefetch Control */
+		__raw_writel(l2x0_saved_regs.prefetch_ctrl,
+				S5P_VA_L2CC + L2X0_PREFETCH_CTRL);
+
+		/* L2X0 Power Control */
+		__raw_writel(l2x0_saved_regs.pwr_ctrl,
+				S5P_VA_L2CC + L2X0_POWER_CTRL);
+
+		clean_dcache_area(&l2x0_regs_phys, sizeof(unsigned long));
+		clean_dcache_area(&l2x0_saved_regs, sizeof(struct l2x0_regs));
+	}
 
 	l2x0_init(S5P_VA_L2CC, 0x7C470001, 0xC200ffff);
 
@@ -240,6 +260,15 @@ static int __init exynos4_l2x0_cache_init(void)
 early_initcall(exynos4_l2x0_cache_init);
 #endif
 
+int exynos4_subrev(void)
+{
+	static int subrev = -1;
+	if (unlikely(subrev < 0))
+		subrev = readl(S5P_VA_CHIPID) & 0xf;
+
+	return subrev;
+}
+
 int __init exynos4_init(void)
 {
 	printk(KERN_INFO "EXYNOS4: Initializing architecture\n");
diff --git a/arch/arm/mach-exynos4/cpuidle.c b/arch/arm/mach-exynos4/cpuidle.c
index bf7e96f2793..6d527610c5a 100644
--- a/arch/arm/mach-exynos4/cpuidle.c
+++ b/arch/arm/mach-exynos4/cpuidle.c
@@ -11,22 +11,48 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/cpuidle.h>
+#include <linux/cpu_pm.h>
 #include <linux/io.h>
-
+#include <linux/suspend.h>
+#include <linux/err.h>
 #include <asm/proc-fns.h>
+#include <asm/smp_scu.h>
+#include <asm/suspend.h>
+#include <asm/unified.h>
+#include <mach/regs-pmu.h>
+#include <mach/pmu.h>
+
+#include <plat/exynos4.h>
+#include <plat/cpu.h>
+
+#define REG_DIRECTGO_ADDR	(exynos4_subrev() == 0 ?\
+				(S5P_VA_SYSRAM + 0x24) : S5P_INFORM7)
+#define REG_DIRECTGO_FLAG	(exynos4_subrev() == 0 ?\
+				(S5P_VA_SYSRAM + 0x20) : S5P_INFORM6)
 
 static int exynos4_enter_idle(struct cpuidle_device *dev,
 			      struct cpuidle_state *state);
 
+static int exynos4_enter_lowpower(struct cpuidle_device *dev,
+				  struct cpuidle_state *state);
+
 static struct cpuidle_state exynos4_cpuidle_set[] = {
 	[0] = {
 		.enter			= exynos4_enter_idle,
 		.exit_latency		= 1,
 		.target_residency	= 100000,
 		.flags			= CPUIDLE_FLAG_TIME_VALID,
-		.name			= "IDLE",
+		.name			= "C0",
 		.desc			= "ARM clock gating(WFI)",
 	},
+	[1] = {
+		.enter			= exynos4_enter_lowpower,
+		.exit_latency		= 300,
+		.target_residency	= 100000,
+		.flags			= CPUIDLE_FLAG_TIME_VALID,
+		.name			= "C1",
+		.desc			= "ARM power down",
+	},
 };
 
 static DEFINE_PER_CPU(struct cpuidle_device, exynos4_cpuidle_device);
@@ -36,6 +62,96 @@ static struct cpuidle_driver exynos4_idle_driver = {
 	.owner		= THIS_MODULE,
 };
 
+/* Ext-GIC nIRQ/nFIQ is the only wakeup source in AFTR */
+static void exynos4_set_wakeupmask(void)
+{
+	__raw_writel(0x0000ff3e, S5P_WAKEUP_MASK);
+}
+
+static unsigned int g_pwr_ctrl, g_diag_reg;
+
+static void save_cpu_arch_register(void)
+{
+	/*read power control register*/
+	asm("mrc p15, 0, %0, c15, c0, 0" : "=r"(g_pwr_ctrl) : : "cc");
+	/*read diagnostic register*/
+	asm("mrc p15, 0, %0, c15, c0, 1" : "=r"(g_diag_reg) : : "cc");
+	return;
+}
+
+static void restore_cpu_arch_register(void)
+{
+	/*write power control register*/
+	asm("mcr p15, 0, %0, c15, c0, 0" : : "r"(g_pwr_ctrl) : "cc");
+	/*write diagnostic register*/
+	asm("mcr p15, 0, %0, c15, c0, 1" : : "r"(g_diag_reg) : "cc");
+	return;
+}
+
+static int idle_finisher(unsigned long flags)
+{
+	cpu_do_idle();
+	return 1;
+}
+
+static int exynos4_enter_core0_aftr(struct cpuidle_device *dev,
+				    struct cpuidle_state *state)
+{
+	struct timeval before, after;
+	int idle_time;
+	unsigned long tmp;
+
+	local_irq_disable();
+	do_gettimeofday(&before);
+
+	exynos4_set_wakeupmask();
+
+	/* Set value of power down register for aftr mode */
+	exynos4_sys_powerdown_conf(SYS_AFTR);
+
+	save_cpu_arch_register();
+
+	/* Setting Central Sequence Register for power down mode */
+	tmp = __raw_readl(S5P_CENTRAL_SEQ_CONFIGURATION);
+	tmp &= ~S5P_CENTRAL_LOWPWR_CFG;
+	__raw_writel(tmp, S5P_CENTRAL_SEQ_CONFIGURATION);
+
+	cpu_pm_enter();
+	cpu_cluster_pm_enter();
+
+	cpu_suspend(0, idle_finisher);
+
+	scu_enable(S5P_VA_SCU);
+
+	cpu_cluster_pm_exit();
+	cpu_pm_exit();
+
+	restore_cpu_arch_register();
+
+	/*
+	 * If PMU failed while entering sleep mode, WFI will be
+	 * ignored by PMU and then exiting cpu_do_idle().
+	 * S5P_CENTRAL_LOWPWR_CFG bit will not be set automatically
+	 * in this situation.
+	 */
+	tmp = __raw_readl(S5P_CENTRAL_SEQ_CONFIGURATION);
+	if (!(tmp & S5P_CENTRAL_LOWPWR_CFG)) {
+		tmp |= S5P_CENTRAL_LOWPWR_CFG;
+		__raw_writel(tmp, S5P_CENTRAL_SEQ_CONFIGURATION);
+	}
+
+	/* Clear wakeup state register */
+	__raw_writel(0x0, S5P_WAKEUP_STAT);
+
+	do_gettimeofday(&after);
+
+	local_irq_enable();
+	idle_time = (after.tv_sec - before.tv_sec) * USEC_PER_SEC +
+		    (after.tv_usec - before.tv_usec);
+
+	return idle_time;
+}
+
 static int exynos4_enter_idle(struct cpuidle_device *dev,
 			      struct cpuidle_state *state)
 {
@@ -55,6 +171,26 @@ static int exynos4_enter_idle(struct cpuidle_device *dev,
 	return idle_time;
 }
 
+static int exynos4_enter_lowpower(struct cpuidle_device *dev,
+				  struct cpuidle_state *state)
+{
+	struct cpuidle_state *new_state = state;
+
+	/* This mode only can be entered when Core1 is offline */
+	if (num_online_cpus() > 1) {
+		BUG_ON(!dev->safe_state);
+		new_state = dev->safe_state;
+	}
+	dev->last_state = new_state;
+
+	if (new_state == &dev->states[0])
+		return exynos4_enter_idle(dev, new_state);
+	else
+		return exynos4_enter_core0_aftr(dev, new_state);
+
+	return exynos4_enter_idle(dev, new_state);
+}
+
 static int __init exynos4_init_cpuidle(void)
 {
 	int i, max_cpuidle_state, cpu_id;
@@ -66,8 +202,11 @@ static int __init exynos4_init_cpuidle(void)
 		device = &per_cpu(exynos4_cpuidle_device, cpu_id);
 		device->cpu = cpu_id;
 
-		device->state_count = (sizeof(exynos4_cpuidle_set) /
+		if (cpu_id == 0)
+			device->state_count = (sizeof(exynos4_cpuidle_set) /
 					       sizeof(struct cpuidle_state));
+		else
+			device->state_count = 1;	/* Support IDLE only */
 
 		max_cpuidle_state = device->state_count;
 
@@ -76,11 +215,18 @@ static int __init exynos4_init_cpuidle(void)
 					sizeof(struct cpuidle_state));
 		}
 
+		device->safe_state = &device->states[0];
+
 		if (cpuidle_register_device(device)) {
 			printk(KERN_ERR "CPUidle register device failed\n,");
 			return -EIO;
 		}
 	}
+
+	__raw_writel(BSYM(virt_to_phys(s3c_cpu_resume)),
+						 REG_DIRECTGO_ADDR);
+	__raw_writel(0xfcba0d10, REG_DIRECTGO_FLAG);
+
 	return 0;
 }
 device_initcall(exynos4_init_cpuidle);
diff --git a/arch/arm/mach-exynos4/dev-tmu.c b/arch/arm/mach-exynos4/dev-tmu.c
new file mode 100644
index 00000000000..c1e9e9648b6
--- /dev/null
+++ b/arch/arm/mach-exynos4/dev-tmu.c
@@ -0,0 +1,68 @@
+/* linux/arch/arm/mach-exynos4/dev-tmu.c
+ *
+ * Copyright 2011 by SAMSUNG
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/platform_data/exynos4_tmu.h>
+#include <asm/irq.h>
+
+#include <mach/irqs.h>
+#include <mach/map.h>
+#include <plat/devs.h>
+
+static struct resource exynos4_tmu_resource[] = {
+	[0] = {
+		.start	= EXYNOS4_PA_TMU,
+		.end	= EXYNOS4_PA_TMU + 0xFFFF - 1,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= IRQ_TMU_TRIG0,
+		.end	= IRQ_TMU_TRIG0,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct exynos4_tmu_platform_data default_tmu_data = {
+	.threshold = 55,
+	.trigger_levels[0] = 0xFF,
+	.trigger_levels[1] = 5,
+	.trigger_levels[2] = 20,
+	.trigger_levels[3] = 30,
+	.trigger_level0_en = 0,
+	.trigger_level1_en = 1,
+	.trigger_level2_en = 1,
+	.trigger_level3_en = 1,
+	.gain = 15,
+	.reference_voltage = 7,
+	.cal_type = TYPE_ONE_POINT_TRIMMING,
+	.freq_tab[0] = {
+		.freq_clip_pctg[0] = 50,
+		},
+	.freq_tab[1] = {
+		.freq_clip_pctg[0] = 99,
+		},
+	.freq_tab[2] = {
+		.freq_clip_pctg[0] = 99,
+		},
+	.level_count = 3,
+};
+
+struct platform_device exynos4_device_tmu = {
+	.name		= "exynos4-tmu",
+	.id		= -1,
+	.num_resources	= ARRAY_SIZE(exynos4_tmu_resource),
+	.resource	= exynos4_tmu_resource,
+	.dev	= {
+		.platform_data	= &default_tmu_data,
+	},
+};
+EXPORT_SYMBOL(exynos4_device_tmu);
diff --git a/arch/arm/mach-exynos4/include/mach/cpufreq.h b/arch/arm/mach-exynos4/include/mach/cpufreq.h
new file mode 100644
index 00000000000..7e0093111da
--- /dev/null
+++ b/arch/arm/mach-exynos4/include/mach/cpufreq.h
@@ -0,0 +1,39 @@
+/* linux/arch/arm/mach-exynos4/include/mach/cpufreq.h
+ *
+ * Copyright (c) 2011 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * EXYNOS4 - CPUFreq support
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*
+ * CPU frequency level index for using cpufreq lock API
+ * This should be same with cpufreq_frequency_table
+ */
+enum cpufreq_level_request {
+	CPU_L0,		/* 1200MHz */
+	CPU_L1,		/* 1000MHz */
+	CPU_L2,		/* 800MHz */
+	CPU_L3,		/* 500MHz */
+	CPU_L4,		/* 200MHz */
+	CPU_LEVEL_END,
+};
+
+enum cpufreq_lock_ID {
+	DVFS_LOCK_ID_G2D,	/* G2D */
+	DVFS_LOCK_ID_TV,	/* TV */
+	DVFS_LOCK_ID_MFC,	/* MFC */
+	DVFS_LOCK_ID_USB,	/* USB */
+	DVFS_LOCK_ID_CAM,	/* CAM */
+	DVFS_LOCK_ID_PM,	/* PM */
+	DVFS_LOCK_ID_USER,	/* USER */
+	DVFS_LOCK_ID_END,
+};
+
+int exynos4_cpufreq_lock(unsigned int nId,
+			enum cpufreq_level_request cpufreq_level);
+void exynos4_cpufreq_lock_free(unsigned int nId);
diff --git a/arch/arm/mach-exynos4/include/mach/irqs.h b/arch/arm/mach-exynos4/include/mach/irqs.h
index f8952f8f375..94e87a9172c 100644
--- a/arch/arm/mach-exynos4/include/mach/irqs.h
+++ b/arch/arm/mach-exynos4/include/mach/irqs.h
@@ -119,6 +119,8 @@
 #define COMBINER_GROUP(x)	((x) * MAX_IRQ_IN_COMBINER + IRQ_SPI(128))
 #define COMBINER_IRQ(x, y)	(COMBINER_GROUP(x) + y)
 
+#define IRQ_TMU_TRIG0		COMBINER_IRQ(2, 4)
+#define IRQ_TMU_TRIG1		COMBINER_IRQ(3, 4)
 #define IRQ_SYSMMU_MDMA0_0	COMBINER_IRQ(4, 0)
 #define IRQ_SYSMMU_SSS_0	COMBINER_IRQ(4, 1)
 #define IRQ_SYSMMU_FIMC0_0	COMBINER_IRQ(4, 2)
diff --git a/arch/arm/mach-exynos4/include/mach/map.h b/arch/arm/mach-exynos4/include/mach/map.h
index d32296dc65e..233525bfa43 100644
--- a/arch/arm/mach-exynos4/include/mach/map.h
+++ b/arch/arm/mach-exynos4/include/mach/map.h
@@ -66,6 +66,7 @@
 #define EXYNOS4_PA_COREPERI		0x10500000
 #define EXYNOS4_PA_TWD			0x10500600
 #define EXYNOS4_PA_L2CC			0x10502000
+#define EXYNOS4_PA_TMU			0x100C0000
 
 #define EXYNOS4_PA_MDMA			0x10810000
 #define EXYNOS4_PA_PDMA0		0x12680000
diff --git a/arch/arm/mach-exynos4/include/mach/pmu.h b/arch/arm/mach-exynos4/include/mach/pmu.h
index a952904b010..31d1ed8e3c6 100644
--- a/arch/arm/mach-exynos4/include/mach/pmu.h
+++ b/arch/arm/mach-exynos4/include/mach/pmu.h
@@ -20,6 +20,8 @@ enum sys_powerdown {
 	NUM_SYS_POWERDOWN,
 };
 
+extern unsigned long l2x0_regs_phys;
 extern void exynos4_sys_powerdown_conf(enum sys_powerdown mode);
+extern void s3c_cpu_resume(void);
 
 #endif /* __ASM_ARCH_PMU_H */
diff --git a/arch/arm/mach-exynos4/mach-armlex4210.c b/arch/arm/mach-exynos4/mach-armlex4210.c
index b482c6285fc..f0ca6c157d2 100644
--- a/arch/arm/mach-exynos4/mach-armlex4210.c
+++ b/arch/arm/mach-exynos4/mach-armlex4210.c
@@ -207,7 +207,7 @@ static void __init armlex4210_machine_init(void)
 
 MACHINE_START(ARMLEX4210, "ARMLEX4210")
 	/* Maintainer: Alim Akhtar <alim.akhtar@samsung.com> */
-	.boot_params	= S5P_PA_SDRAM + 0x100,
+	.atag_offset	= 0x100,
 	.init_irq	= exynos4_init_irq,
 	.map_io		= armlex4210_map_io,
 	.init_machine	= armlex4210_machine_init,
diff --git a/arch/arm/mach-exynos4/mach-nuri.c b/arch/arm/mach-exynos4/mach-nuri.c
index 43be71b799c..6e0536818bf 100644
--- a/arch/arm/mach-exynos4/mach-nuri.c
+++ b/arch/arm/mach-exynos4/mach-nuri.c
@@ -1152,7 +1152,7 @@ static void __init nuri_machine_init(void)
 
 MACHINE_START(NURI, "NURI")
 	/* Maintainer: Kyungmin Park <kyungmin.park@samsung.com> */
-	.boot_params	= S5P_PA_SDRAM + 0x100,
+	.atag_offset	= 0x100,
 	.init_irq	= exynos4_init_irq,
 	.map_io		= nuri_map_io,
 	.init_machine	= nuri_machine_init,
diff --git a/arch/arm/mach-exynos4/mach-origen.c b/arch/arm/mach-exynos4/mach-origen.c
new file mode 100644
index 00000000000..74180441852
--- /dev/null
+++ b/arch/arm/mach-exynos4/mach-origen.c
@@ -0,0 +1,109 @@
+/* linux/arch/arm/mach-exynos4/mach-origen.c
+ *
+ * Copyright (c) 2011 Insignal Co., Ltd.
+ *		http://www.insignal.co.kr/
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+*/
+
+#include <linux/serial_core.h>
+#include <linux/gpio.h>
+#include <linux/mmc/host.h>
+#include <linux/platform_device.h>
+#include <linux/io.h>
+#include <linux/input.h>
+
+#include <asm/mach/arch.h>
+#include <asm/mach-types.h>
+
+#include <plat/regs-serial.h>
+#include <plat/exynos4.h>
+#include <plat/cpu.h>
+#include <plat/devs.h>
+#include <plat/sdhci.h>
+#include <plat/iic.h>
+
+#include <mach/map.h>
+
+/* Following are default values for UCON, ULCON and UFCON UART registers */
+#define ORIGEN_UCON_DEFAULT	(S3C2410_UCON_TXILEVEL |	\
+				 S3C2410_UCON_RXILEVEL |	\
+				 S3C2410_UCON_TXIRQMODE |	\
+				 S3C2410_UCON_RXIRQMODE |	\
+				 S3C2410_UCON_RXFIFO_TOI |	\
+				 S3C2443_UCON_RXERR_IRQEN)
+
+#define ORIGEN_ULCON_DEFAULT	S3C2410_LCON_CS8
+
+#define ORIGEN_UFCON_DEFAULT	(S3C2410_UFCON_FIFOMODE |	\
+				 S5PV210_UFCON_TXTRIG4 |	\
+				 S5PV210_UFCON_RXTRIG4)
+
+static struct s3c2410_uartcfg origen_uartcfgs[] __initdata = {
+	[0] = {
+		.hwport		= 0,
+		.flags		= 0,
+		.ucon		= ORIGEN_UCON_DEFAULT,
+		.ulcon		= ORIGEN_ULCON_DEFAULT,
+		.ufcon		= ORIGEN_UFCON_DEFAULT,
+	},
+	[1] = {
+		.hwport		= 1,
+		.flags		= 0,
+		.ucon		= ORIGEN_UCON_DEFAULT,
+		.ulcon		= ORIGEN_ULCON_DEFAULT,
+		.ufcon		= ORIGEN_UFCON_DEFAULT,
+	},
+	[2] = {
+		.hwport		= 2,
+		.flags		= 0,
+		.ucon		= ORIGEN_UCON_DEFAULT,
+		.ulcon		= ORIGEN_ULCON_DEFAULT,
+		.ufcon		= ORIGEN_UFCON_DEFAULT,
+	},
+	[3] = {
+		.hwport		= 3,
+		.flags		= 0,
+		.ucon		= ORIGEN_UCON_DEFAULT,
+		.ulcon		= ORIGEN_ULCON_DEFAULT,
+		.ufcon		= ORIGEN_UFCON_DEFAULT,
+	},
+};
+
+static struct s3c_sdhci_platdata origen_hsmmc2_pdata __initdata = {
+	.cd_type		= S3C_SDHCI_CD_GPIO,
+	.ext_cd_gpio		= EXYNOS4_GPK2(2),
+	.ext_cd_gpio_invert	= 1,
+	.clk_type		= S3C_SDHCI_CLK_DIV_EXTERNAL,
+};
+
+static struct platform_device *origen_devices[] __initdata = {
+	&s3c_device_hsmmc2,
+	&s3c_device_rtc,
+	&s3c_device_wdt,
+	&exynos4_device_tmu,
+};
+
+static void __init origen_map_io(void)
+{
+	s5p_init_io(NULL, 0, S5P_VA_CHIPID);
+	s3c24xx_init_clocks(24000000);
+	s3c24xx_init_uarts(origen_uartcfgs, ARRAY_SIZE(origen_uartcfgs));
+}
+
+static void __init origen_machine_init(void)
+{
+	s3c_sdhci2_set_platdata(&origen_hsmmc2_pdata);
+	platform_add_devices(origen_devices, ARRAY_SIZE(origen_devices));
+}
+
+MACHINE_START(ORIGEN, "ORIGEN")
+	/* Maintainer: JeongHyeon Kim <jhkim@insignal.co.kr> */
+	.atag_offset	= 0x100,
+	.init_irq	= exynos4_init_irq,
+	.map_io		= origen_map_io,
+	.init_machine	= origen_machine_init,
+	.timer		= &exynos4_timer,
+MACHINE_END
diff --git a/arch/arm/mach-exynos4/mach-smdkc210.c b/arch/arm/mach-exynos4/mach-smdkc210.c
index a7c65e05c1e..b24ddd7ad8f 100644
--- a/arch/arm/mach-exynos4/mach-smdkc210.c
+++ b/arch/arm/mach-exynos4/mach-smdkc210.c
@@ -301,7 +301,7 @@ static void __init smdkc210_machine_init(void)
 
 MACHINE_START(SMDKC210, "SMDKC210")
 	/* Maintainer: Kukjin Kim <kgene.kim@samsung.com> */
-	.boot_params	= S5P_PA_SDRAM + 0x100,
+	.atag_offset	= 0x100,
 	.init_irq	= exynos4_init_irq,
 	.map_io		= smdkc210_map_io,
 	.init_machine	= smdkc210_machine_init,
diff --git a/arch/arm/mach-exynos4/mach-smdkv310.c b/arch/arm/mach-exynos4/mach-smdkv310.c
index ea414955686..1d7bf2138dd 100644
--- a/arch/arm/mach-exynos4/mach-smdkv310.c
+++ b/arch/arm/mach-exynos4/mach-smdkv310.c
@@ -252,12 +252,18 @@ static void __init smdkv310_machine_init(void)
 	platform_add_devices(smdkv310_devices, ARRAY_SIZE(smdkv310_devices));
 }
 
+static char const *smdkv310_dt_compat[] __initdata = {
+	"samsung,smdkv310",
+	NULL
+};
+
 MACHINE_START(SMDKV310, "SMDKV310")
 	/* Maintainer: Kukjin Kim <kgene.kim@samsung.com> */
 	/* Maintainer: Changhwan Youn <chaos.youn@samsung.com> */
-	.boot_params	= S5P_PA_SDRAM + 0x100,
+	.atag_offset	= 0x100,
 	.init_irq	= exynos4_init_irq,
 	.map_io		= smdkv310_map_io,
 	.init_machine	= smdkv310_machine_init,
 	.timer		= &exynos4_timer,
+	.dt_compat	= smdkv310_dt_compat,
 MACHINE_END
diff --git a/arch/arm/mach-exynos4/mach-universal_c210.c b/arch/arm/mach-exynos4/mach-universal_c210.c
index b3b5d891100..2aac6f755c8 100644
--- a/arch/arm/mach-exynos4/mach-universal_c210.c
+++ b/arch/arm/mach-exynos4/mach-universal_c210.c
@@ -762,7 +762,7 @@ static void __init universal_machine_init(void)
 
 MACHINE_START(UNIVERSAL_C210, "UNIVERSAL_C210")
 	/* Maintainer: Kyungmin Park <kyungmin.park@samsung.com> */
-	.boot_params	= S5P_PA_SDRAM + 0x100,
+	.atag_offset	= 0x100,
 	.init_irq	= exynos4_init_irq,
 	.map_io		= universal_map_io,
 	.init_machine	= universal_machine_init,
diff --git a/arch/arm/mach-exynos4/platsmp.c b/arch/arm/mach-exynos4/platsmp.c
index df6ef1b2f98..c345b783cde 100644
--- a/arch/arm/mach-exynos4/platsmp.c
+++ b/arch/arm/mach-exynos4/platsmp.c
@@ -30,9 +30,11 @@
 #include <mach/regs-clock.h>
 #include <mach/regs-pmu.h>
 
+#include <plat/exynos4.h>
+
 extern void exynos4_secondary_startup(void);
 
-#define CPU1_BOOT_REG S5P_VA_SYSRAM
+#define CPU1_BOOT_REG (exynos4_subrev() == 0 ? S5P_VA_SYSRAM : S5P_INFORM5)
 
 /*
  * control for which core is the next to come out of the secondary
@@ -193,12 +195,10 @@ void __init smp_init_cpus(void)
 	ncores = scu_base ? scu_get_core_count(scu_base) : 1;
 
 	/* sanity check */
-	if (ncores > NR_CPUS) {
-		printk(KERN_WARNING
-		       "EXYNOS4: no. of cores (%d) greater than configured "
-		       "maximum of %d - clipping\n",
-		       ncores, NR_CPUS);
-		ncores = NR_CPUS;
+	if (ncores > nr_cpu_ids) {
+		pr_warn("SMP: %u cores greater than maximum (%u), clipping\n",
+			ncores, nr_cpu_ids);
+		ncores = nr_cpu_ids;
 	}
 
 	for (i = 0; i < ncores; i++)
@@ -218,5 +218,6 @@ void __init platform_smp_prepare_cpus(unsigned int max_cpus)
 	 * until it receives a soft interrupt, and then the
 	 * secondary CPU branches to this address.
 	 */
-	__raw_writel(BSYM(virt_to_phys(exynos4_secondary_startup)), S5P_VA_SYSRAM);
+	__raw_writel(BSYM(virt_to_phys(exynos4_secondary_startup)),
+						CPU1_BOOT_REG);
 }
diff --git a/arch/arm/mach-exynos4/pm.c b/arch/arm/mach-exynos4/pm.c
index bc6ca9482de..47d5428887d 100644
--- a/arch/arm/mach-exynos4/pm.c
+++ b/arch/arm/mach-exynos4/pm.c
@@ -131,78 +131,6 @@ static struct sleep_save exynos4_core_save[] = {
 	SAVE_ITEM(S5P_CLKGATE_SCLKCPU),
 	SAVE_ITEM(S5P_CLKGATE_IP_CPU),
 
-	/* GIC side */
-	SAVE_ITEM(S5P_VA_GIC_CPU + 0x000),
-	SAVE_ITEM(S5P_VA_GIC_CPU + 0x004),
-	SAVE_ITEM(S5P_VA_GIC_CPU + 0x008),
-	SAVE_ITEM(S5P_VA_GIC_CPU + 0x00C),
-	SAVE_ITEM(S5P_VA_GIC_CPU + 0x014),
-	SAVE_ITEM(S5P_VA_GIC_CPU + 0x018),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x000),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x004),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x100),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x104),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x108),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x300),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x304),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x308),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x400),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x404),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x408),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x40C),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x410),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x414),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x418),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x41C),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x420),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x424),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x428),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x42C),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x430),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x434),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x438),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x43C),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x440),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x444),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x448),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x44C),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x450),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x454),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x458),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x45C),
-
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x800),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x804),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x808),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x80C),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x810),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x814),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x818),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x81C),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x820),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x824),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x828),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x82C),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x830),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x834),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x838),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x83C),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x840),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x844),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x848),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x84C),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x850),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x854),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x858),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0x85C),
-
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0xC00),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0xC04),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0xC08),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0xC0C),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0xC10),
-	SAVE_ITEM(S5P_VA_GIC_DIST + 0xC14),
-
 	SAVE_ITEM(S5P_VA_COMBINER_BASE + 0x000),
 	SAVE_ITEM(S5P_VA_COMBINER_BASE + 0x010),
 	SAVE_ITEM(S5P_VA_COMBINER_BASE + 0x020),
@@ -222,13 +150,6 @@ static struct sleep_save exynos4_core_save[] = {
 	SAVE_ITEM(S5P_SROM_BC3),
 };
 
-static struct sleep_save exynos4_l2cc_save[] = {
-	SAVE_ITEM(S5P_VA_L2CC + L2X0_TAG_LATENCY_CTRL),
-	SAVE_ITEM(S5P_VA_L2CC + L2X0_DATA_LATENCY_CTRL),
-	SAVE_ITEM(S5P_VA_L2CC + L2X0_PREFETCH_CTRL),
-	SAVE_ITEM(S5P_VA_L2CC + L2X0_POWER_CTRL),
-	SAVE_ITEM(S5P_VA_L2CC + L2X0_AUX_CTRL),
-};
 
 /* For Cortex-A9 Diagnostic and Power control register */
 static unsigned int save_arm_register[2];
@@ -249,7 +170,6 @@ static void exynos4_pm_prepare(void)
 	u32 tmp;
 
 	s3c_pm_do_save(exynos4_core_save, ARRAY_SIZE(exynos4_core_save));
-	s3c_pm_do_save(exynos4_l2cc_save, ARRAY_SIZE(exynos4_l2cc_save));
 	s3c_pm_do_save(exynos4_epll_save, ARRAY_SIZE(exynos4_epll_save));
 	s3c_pm_do_save(exynos4_vpll_save, ARRAY_SIZE(exynos4_vpll_save));
 
@@ -462,13 +382,6 @@ static void exynos4_pm_resume(void)
 
 	exynos4_scu_enable(S5P_VA_SCU);
 
-#ifdef CONFIG_CACHE_L2X0
-	s3c_pm_do_restore_core(exynos4_l2cc_save, ARRAY_SIZE(exynos4_l2cc_save));
-	outer_inv_all();
-	/* enable L2X0*/
-	writel_relaxed(1, S5P_VA_L2CC + L2X0_CTRL);
-#endif
-
 early_wakeup:
 	return;
 }
diff --git a/arch/arm/mach-exynos4/sleep.S b/arch/arm/mach-exynos4/sleep.S
index 0984078f1eb..3284213a1a3 100644
--- a/arch/arm/mach-exynos4/sleep.S
+++ b/arch/arm/mach-exynos4/sleep.S
@@ -27,8 +27,8 @@
 */
 
 #include <linux/linkage.h>
-#include <asm/assembler.h>
-#include <asm/memory.h>
+#include <asm/asm-offsets.h>
+#include <asm/hardware/cache-l2x0.h>
 
 	.text
 
@@ -49,6 +49,31 @@
 	 * other way of restoring the stack pointer after sleep, and we
 	 * must not write to the code segment (code is read-only)
 	 */
+	.align
+	.data
 
 ENTRY(s3c_cpu_resume)
+	adr	r0, l2x0_regs_phys
+	ldr	r0, [r0]
+	ldr	r1, [r0, #L2X0_R_PHY_BASE]
+	ldr	r2, [r1, #L2X0_CTRL]
+	tst	r2, #0x1
+	bne	resume_l2on
+	ldr	r2, [r0, #L2X0_R_AUX_CTRL]
+	str	r2, [r1, #L2X0_AUX_CTRL]
+	ldr	r2, [r0, #L2X0_R_TAG_LATENCY]
+	str	r2, [r1, #L2X0_TAG_LATENCY_CTRL]
+	ldr	r2, [r0, #L2X0_R_DATA_LATENCY]
+	str	r2, [r1, #L2X0_DATA_LATENCY_CTRL]
+	ldr	r2, [r0, #L2X0_R_PREFETCH_CTRL]
+	str	r2, [r1, #L2X0_PREFETCH_CTRL]
+	ldr	r2, [r0, #L2X0_R_PWR_CTRL]
+	str	r2, [r1, #L2X0_POWER_CTRL]
+	mov	r2, #1
+	str	r2, [r1, #L2X0_CTRL]
+resume_l2on:
 	b	cpu_resume
+ENDPROC(s3c_cpu_resume)
+	.globl l2x0_regs_phys
+l2x0_regs_phys:
+	.long	0
diff --git a/arch/arm/mach-footbridge/cats-hw.c b/arch/arm/mach-footbridge/cats-hw.c
index 5b1a8db779b..a3da5d1106c 100644
--- a/arch/arm/mach-footbridge/cats-hw.c
+++ b/arch/arm/mach-footbridge/cats-hw.c
@@ -86,7 +86,7 @@ fixup_cats(struct machine_desc *desc, struct tag *tags,
 
 MACHINE_START(CATS, "Chalice-CATS")
 	/* Maintainer: Philip Blundell */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.soft_reboot	= 1,
 	.fixup		= fixup_cats,
 	.map_io		= footbridge_map_io,
diff --git a/arch/arm/mach-footbridge/ebsa285.c b/arch/arm/mach-footbridge/ebsa285.c
index 2ef69ff44ba..012210cf7d1 100644
--- a/arch/arm/mach-footbridge/ebsa285.c
+++ b/arch/arm/mach-footbridge/ebsa285.c
@@ -15,7 +15,7 @@
 
 MACHINE_START(EBSA285, "EBSA285")
 	/* Maintainer: Russell King */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.video_start	= 0x000a0000,
 	.video_end	= 0x000bffff,
 	.map_io		= footbridge_map_io,
diff --git a/arch/arm/mach-footbridge/netwinder-hw.c b/arch/arm/mach-footbridge/netwinder-hw.c
index 06e514f372d..d8c1c922e24 100644
--- a/arch/arm/mach-footbridge/netwinder-hw.c
+++ b/arch/arm/mach-footbridge/netwinder-hw.c
@@ -648,7 +648,7 @@ fixup_netwinder(struct machine_desc *desc, struct tag *tags,
 
 MACHINE_START(NETWINDER, "Rebel-NetWinder")
 	/* Maintainer: Russell King/Rebel.com */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.video_start	= 0x000a0000,
 	.video_end	= 0x000bffff,
 	.reserve_lp0	= 1,
diff --git a/arch/arm/mach-footbridge/personal.c b/arch/arm/mach-footbridge/personal.c
index 3285e91ca8c..f41dba39b32 100644
--- a/arch/arm/mach-footbridge/personal.c
+++ b/arch/arm/mach-footbridge/personal.c
@@ -15,7 +15,7 @@
 
 MACHINE_START(PERSONAL_SERVER, "Compaq-PersonalServer")
 	/* Maintainer: Jamey Hicks / George France */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.map_io		= footbridge_map_io,
 	.init_irq	= footbridge_init_irq,
 	.timer		= &footbridge_timer,
diff --git a/arch/arm/mach-gemini/board-nas4220b.c b/arch/arm/mach-gemini/board-nas4220b.c
index 0cf7a07c3f3..5927d3c253a 100644
--- a/arch/arm/mach-gemini/board-nas4220b.c
+++ b/arch/arm/mach-gemini/board-nas4220b.c
@@ -102,7 +102,7 @@ static void __init ib4220b_init(void)
 }
 
 MACHINE_START(NAS4220B, "Raidsonic NAS IB-4220-B")
-	.boot_params	= 0x100,
+	.atag_offset	= 0x100,
 	.map_io		= gemini_map_io,
 	.init_irq	= gemini_init_irq,
 	.timer		= &ib4220b_timer,
diff --git a/arch/arm/mach-gemini/board-rut1xx.c b/arch/arm/mach-gemini/board-rut1xx.c
index 4fa09af9949..cd7437a1cea 100644
--- a/arch/arm/mach-gemini/board-rut1xx.c
+++ b/arch/arm/mach-gemini/board-rut1xx.c
@@ -86,7 +86,7 @@ static void __init rut1xx_init(void)
 }
 
 MACHINE_START(RUT100, "Teltonika RUT100")
-	.boot_params	= 0x100,
+	.atag_offset	= 0x100,
 	.map_io		= gemini_map_io,
 	.init_irq	= gemini_init_irq,
 	.timer		= &rut1xx_timer,
diff --git a/arch/arm/mach-gemini/board-wbd111.c b/arch/arm/mach-gemini/board-wbd111.c
index 88cc422ee44..a367880368f 100644
--- a/arch/arm/mach-gemini/board-wbd111.c
+++ b/arch/arm/mach-gemini/board-wbd111.c
@@ -129,7 +129,7 @@ static void __init wbd111_init(void)
 }
 
 MACHINE_START(WBD111, "Wiliboard WBD-111")
-	.boot_params	= 0x100,
+	.atag_offset	= 0x100,
 	.map_io		= gemini_map_io,
 	.init_irq	= gemini_init_irq,
 	.timer		= &wbd111_timer,
diff --git a/arch/arm/mach-gemini/board-wbd222.c b/arch/arm/mach-gemini/board-wbd222.c
index 3a220347bc8..f382811c131 100644
--- a/arch/arm/mach-gemini/board-wbd222.c
+++ b/arch/arm/mach-gemini/board-wbd222.c
@@ -129,7 +129,7 @@ static void __init wbd222_init(void)
 }
 
 MACHINE_START(WBD222, "Wiliboard WBD-222")
-	.boot_params	= 0x100,
+	.atag_offset	= 0x100,
 	.map_io		= gemini_map_io,
 	.init_irq	= gemini_init_irq,
 	.timer		= &wbd222_timer,
diff --git a/arch/arm/mach-h720x/h7201-eval.c b/arch/arm/mach-h720x/h7201-eval.c
index 65f1bea958e..9886f19805f 100644
--- a/arch/arm/mach-h720x/h7201-eval.c
+++ b/arch/arm/mach-h720x/h7201-eval.c
@@ -29,7 +29,7 @@
 
 MACHINE_START(H7201, "Hynix GMS30C7201")
 	/* Maintainer: Robert Schwebel, Pengutronix */
-	.boot_params	= 0xc0001000,
+	.atag_offset	= 0x1000,
 	.map_io		= h720x_map_io,
 	.init_irq	= h720x_init_irq,
 	.timer		= &h7201_timer,
diff --git a/arch/arm/mach-h720x/h7202-eval.c b/arch/arm/mach-h720x/h7202-eval.c
index 884584a0975..284a134819e 100644
--- a/arch/arm/mach-h720x/h7202-eval.c
+++ b/arch/arm/mach-h720x/h7202-eval.c
@@ -71,7 +71,7 @@ static void __init init_eval_h7202(void)
 
 MACHINE_START(H7202, "Hynix HMS30C7202")
 	/* Maintainer: Robert Schwebel, Pengutronix */
-	.boot_params	= 0x40000100,
+	.atag_offset	= 0x100,
 	.map_io		= h720x_map_io,
 	.init_irq	= h7202_init_irq,
 	.timer		= &h7202_timer,
diff --git a/arch/arm/mach-imx/mach-armadillo5x0.c b/arch/arm/mach-imx/mach-armadillo5x0.c
index ede2710f8b7..21525908394 100644
--- a/arch/arm/mach-imx/mach-armadillo5x0.c
+++ b/arch/arm/mach-imx/mach-armadillo5x0.c
@@ -558,7 +558,7 @@ static struct sys_timer armadillo5x0_timer = {
 
 MACHINE_START(ARMADILLO5X0, "Armadillo-500")
 	/* Maintainer: Alberto Panizzo  */
-	.boot_params = MX3x_PHYS_OFFSET + 0x100,
+	.atag_offset = 0x100,
 	.map_io = mx31_map_io,
 	.init_early = imx31_init_early,
 	.init_irq = mx31_init_irq,
diff --git a/arch/arm/mach-imx/mach-cpuimx27.c b/arch/arm/mach-imx/mach-cpuimx27.c
index f851fe90368..b1ec2cf53bb 100644
--- a/arch/arm/mach-imx/mach-cpuimx27.c
+++ b/arch/arm/mach-imx/mach-cpuimx27.c
@@ -311,7 +311,7 @@ static struct sys_timer eukrea_cpuimx27_timer = {
 };
 
 MACHINE_START(EUKREA_CPUIMX27, "EUKREA CPUIMX27")
-	.boot_params = MX27_PHYS_OFFSET + 0x100,
+	.atag_offset = 0x100,
 	.map_io = mx27_map_io,
 	.init_early = imx27_init_early,
 	.init_irq = mx27_init_irq,
diff --git a/arch/arm/mach-imx/mach-cpuimx35.c b/arch/arm/mach-imx/mach-cpuimx35.c
index 4bd083ba9af..470b654b0e6 100644
--- a/arch/arm/mach-imx/mach-cpuimx35.c
+++ b/arch/arm/mach-imx/mach-cpuimx35.c
@@ -194,7 +194,7 @@ struct sys_timer eukrea_cpuimx35_timer = {
 
 MACHINE_START(EUKREA_CPUIMX35SD, "Eukrea CPUIMX35")
 	/* Maintainer: Eukrea Electromatique */
-	.boot_params = MX3x_PHYS_OFFSET + 0x100,
+	.atag_offset = 0x100,
 	.map_io = mx35_map_io,
 	.init_early = imx35_init_early,
 	.init_irq = mx35_init_irq,
diff --git a/arch/arm/mach-imx/mach-eukrea_cpuimx25.c b/arch/arm/mach-imx/mach-eukrea_cpuimx25.c
index 2442d5da883..9163318e95a 100644
--- a/arch/arm/mach-imx/mach-eukrea_cpuimx25.c
+++ b/arch/arm/mach-imx/mach-eukrea_cpuimx25.c
@@ -163,7 +163,7 @@ static struct sys_timer eukrea_cpuimx25_timer = {
 
 MACHINE_START(EUKREA_CPUIMX25SD, "Eukrea CPUIMX25")
 	/* Maintainer: Eukrea Electromatique */
-	.boot_params = MX25_PHYS_OFFSET + 0x100,
+	.atag_offset = 0x100,
 	.map_io = mx25_map_io,
 	.init_early = imx25_init_early,
 	.init_irq = mx25_init_irq,
diff --git a/arch/arm/mach-imx/mach-imx27_visstrim_m10.c b/arch/arm/mach-imx/mach-imx27_visstrim_m10.c
index 6778f8193bc..22306ce2865 100644
--- a/arch/arm/mach-imx/mach-imx27_visstrim_m10.c
+++ b/arch/arm/mach-imx/mach-imx27_visstrim_m10.c
@@ -275,7 +275,7 @@ static struct sys_timer visstrim_m10_timer = {
 };
 
 MACHINE_START(IMX27_VISSTRIM_M10, "Vista Silicon Visstrim_M10")
-	.boot_params = MX27_PHYS_OFFSET + 0x100,
+	.atag_offset = 0x100,
 	.map_io = mx27_map_io,
 	.init_early = imx27_init_early,
 	.init_irq = mx27_init_irq,
diff --git a/arch/arm/mach-imx/mach-imx27ipcam.c b/arch/arm/mach-imx/mach-imx27ipcam.c
index 272f793e924..8da48b33fc5 100644
--- a/arch/arm/mach-imx/mach-imx27ipcam.c
+++ b/arch/arm/mach-imx/mach-imx27ipcam.c
@@ -71,7 +71,7 @@ static struct sys_timer mx27ipcam_timer = {
 
 MACHINE_START(IMX27IPCAM, "Freescale IMX27IPCAM")
 	/* maintainer: Freescale Semiconductor, Inc. */
-	.boot_params = MX27_PHYS_OFFSET + 0x100,
+	.atag_offset = 0x100,
 	.map_io = mx27_map_io,
 	.init_early = imx27_init_early,
 	.init_irq = mx27_init_irq,
diff --git a/arch/arm/mach-imx/mach-imx27lite.c b/arch/arm/mach-imx/mach-imx27lite.c
index d81a769fe89..21a14a20e2c 100644
--- a/arch/arm/mach-imx/mach-imx27lite.c
+++ b/arch/arm/mach-imx/mach-imx27lite.c
@@ -77,7 +77,7 @@ static struct sys_timer mx27lite_timer = {
 };
 
 MACHINE_START(IMX27LITE, "LogicPD i.MX27LITE")
-	.boot_params = MX27_PHYS_OFFSET + 0x100,
+	.atag_offset = 0x100,
 	.map_io = mx27_map_io,
 	.init_early = imx27_init_early,
 	.init_irq = mx27_init_irq,
diff --git a/arch/arm/mach-imx/mach-kzm_arm11_01.c b/arch/arm/mach-imx/mach-kzm_arm11_01.c
index e472a1d8805..7c20e9e5800 100644
--- a/arch/arm/mach-imx/mach-kzm_arm11_01.c
+++ b/arch/arm/mach-imx/mach-kzm_arm11_01.c
@@ -271,7 +271,7 @@ static struct sys_timer kzm_timer = {
 };
 
 MACHINE_START(KZM_ARM11_01, "Kyoto Microcomputer Co., Ltd. KZM-ARM11-01")
-	.boot_params = MX3x_PHYS_OFFSET + 0x100,
+	.atag_offset = 0x100,
 	.map_io = kzm_map_io,
 	.init_early = imx31_init_early,
 	.init_irq = mx31_init_irq,
diff --git a/arch/arm/mach-imx/mach-mx1ads.c b/arch/arm/mach-imx/mach-mx1ads.c
index 5cd8bee4696..530ea08dbaf 100644
--- a/arch/arm/mach-imx/mach-mx1ads.c
+++ b/arch/arm/mach-imx/mach-mx1ads.c
@@ -145,7 +145,7 @@ struct sys_timer mx1ads_timer = {
 
 MACHINE_START(MX1ADS, "Freescale MX1ADS")
 	/* Maintainer: Sascha Hauer, Pengutronix */
-	.boot_params = MX1_PHYS_OFFSET + 0x100,
+	.atag_offset = 0x100,
 	.map_io = mx1_map_io,
 	.init_early = imx1_init_early,
 	.init_irq = mx1_init_irq,
@@ -154,7 +154,7 @@ MACHINE_START(MX1ADS, "Freescale MX1ADS")
 MACHINE_END
 
 MACHINE_START(MXLADS, "Freescale MXLADS")
-	.boot_params = MX1_PHYS_OFFSET + 0x100,
+	.atag_offset = 0x100,
 	.map_io = mx1_map_io,
 	.init_early = imx1_init_early,
 	.init_irq = mx1_init_irq,
diff --git a/arch/arm/mach-imx/mach-mx21ads.c b/arch/arm/mach-imx/mach-mx21ads.c
index d389ecf9b5a..e56828da26b 100644
--- a/arch/arm/mach-imx/mach-mx21ads.c
+++ b/arch/arm/mach-imx/mach-mx21ads.c
@@ -305,7 +305,7 @@ static struct sys_timer mx21ads_timer = {
 
 MACHINE_START(MX21ADS, "Freescale i.MX21ADS")
 	/* maintainer: Freescale Semiconductor, Inc. */
-	.boot_params = MX21_PHYS_OFFSET + 0x100,
+	.atag_offset = 0x100,
 	.map_io = mx21ads_map_io,
 	.init_early = imx21_init_early,
 	.init_irq = mx21_init_irq,
diff --git a/arch/arm/mach-imx/mach-mx25_3ds.c b/arch/arm/mach-imx/mach-mx25_3ds.c
index 7f66a91df36..dd25ee82e70 100644
--- a/arch/arm/mach-imx/mach-mx25_3ds.c
+++ b/arch/arm/mach-imx/mach-mx25_3ds.c
@@ -253,7 +253,7 @@ static struct sys_timer mx25pdk_timer = {
 
 MACHINE_START(MX25_3DS, "Freescale MX25PDK (3DS)")
 	/* Maintainer: Freescale Semiconductor, Inc. */
-	.boot_params = MX25_PHYS_OFFSET + 0x100,
+	.atag_offset = 0x100,
 	.map_io = mx25_map_io,
 	.init_early = imx25_init_early,
 	.init_irq = mx25_init_irq,
diff --git a/arch/arm/mach-imx/mach-mx27_3ds.c b/arch/arm/mach-imx/mach-mx27_3ds.c
index 6fa6934ab15..2eafbac2c76 100644
--- a/arch/arm/mach-imx/mach-mx27_3ds.c
+++ b/arch/arm/mach-imx/mach-mx27_3ds.c
@@ -421,7 +421,7 @@ static struct sys_timer mx27pdk_timer = {
 
 MACHINE_START(MX27_3DS, "Freescale MX27PDK")
 	/* maintainer: Freescale Semiconductor, Inc. */
-	.boot_params = MX27_PHYS_OFFSET + 0x100,
+	.atag_offset = 0x100,
 	.map_io = mx27_map_io,
 	.init_early = imx27_init_early,
 	.init_irq = mx27_init_irq,
diff --git a/arch/arm/mach-imx/mach-mx27ads.c b/arch/arm/mach-imx/mach-mx27ads.c
index fc26ed71b9e..efe6109099f 100644
--- a/arch/arm/mach-imx/mach-mx27ads.c
+++ b/arch/arm/mach-imx/mach-mx27ads.c
@@ -345,7 +345,7 @@ static void __init mx27ads_map_io(void)
 
 MACHINE_START(MX27ADS, "Freescale i.MX27ADS")
 	/* maintainer: Freescale Semiconductor, Inc. */
-	.boot_params = MX27_PHYS_OFFSET + 0x100,
+	.atag_offset = 0x100,
 	.map_io = mx27ads_map_io,
 	.init_early = imx27_init_early,
 	.init_irq = mx27_init_irq,
diff --git a/arch/arm/mach-imx/mach-mx31_3ds.c b/arch/arm/mach-imx/mach-mx31_3ds.c
index c20be753092..589066fb331 100644
--- a/arch/arm/mach-imx/mach-mx31_3ds.c
+++ b/arch/arm/mach-imx/mach-mx31_3ds.c
@@ -764,7 +764,7 @@ static void __init mx31_3ds_reserve(void)
 
 MACHINE_START(MX31_3DS, "Freescale MX31PDK (3DS)")
 	/* Maintainer: Freescale Semiconductor, Inc. */
-	.boot_params = MX3x_PHYS_OFFSET + 0x100,
+	.atag_offset = 0x100,
 	.map_io = mx31_map_io,
 	.init_early = imx31_init_early,
 	.init_irq = mx31_init_irq,
diff --git a/arch/arm/mach-imx/mach-mx31ads.c b/arch/arm/mach-imx/mach-mx31ads.c
index 29ca8907a78..910c4561d35 100644
--- a/arch/arm/mach-imx/mach-mx31ads.c
+++ b/arch/arm/mach-imx/mach-mx31ads.c
@@ -535,7 +535,7 @@ static struct sys_timer mx31ads_timer = {
 
 MACHINE_START(MX31ADS, "Freescale MX31ADS")
 	/* Maintainer: Freescale Semiconductor, Inc. */
-	.boot_params = MX3x_PHYS_OFFSET + 0x100,
+	.atag_offset = 0x100,
 	.map_io = mx31ads_map_io,
 	.init_early = imx31_init_early,
 	.init_irq = mx31ads_init_irq,
diff --git a/arch/arm/mach-imx/mach-mx31lilly.c b/arch/arm/mach-imx/mach-mx31lilly.c
index 126913ad106..e92eaf91a7b 100644
--- a/arch/arm/mach-imx/mach-mx31lilly.c
+++ b/arch/arm/mach-imx/mach-mx31lilly.c
@@ -295,7 +295,7 @@ static struct sys_timer mx31lilly_timer = {
 };
 
 MACHINE_START(LILLY1131, "INCO startec LILLY-1131")
-	.boot_params = MX3x_PHYS_OFFSET + 0x100,
+	.atag_offset = 0x100,
 	.map_io = mx31_map_io,
 	.init_early = imx31_init_early,
 	.init_irq = mx31_init_irq,
diff --git a/arch/arm/mach-imx/mach-mx31lite.c b/arch/arm/mach-imx/mach-mx31lite.c
index 4b47fd9fdd8..5242cb78b56 100644
--- a/arch/arm/mach-imx/mach-mx31lite.c
+++ b/arch/arm/mach-imx/mach-mx31lite.c
@@ -280,7 +280,7 @@ struct sys_timer mx31lite_timer = {
 
 MACHINE_START(MX31LITE, "LogicPD i.MX31 SOM")
 	/* Maintainer: Freescale Semiconductor, Inc. */
-	.boot_params = MX3x_PHYS_OFFSET + 0x100,
+	.atag_offset = 0x100,
 	.map_io = mx31lite_map_io,
 	.init_early = imx31_init_early,
 	.init_irq = mx31_init_irq,
diff --git a/arch/arm/mach-imx/mach-mx31moboard.c b/arch/arm/mach-imx/mach-mx31moboard.c
index b358383120e..1d01ef28f25 100644
--- a/arch/arm/mach-imx/mach-mx31moboard.c
+++ b/arch/arm/mach-imx/mach-mx31moboard.c
@@ -567,7 +567,7 @@ static void __init mx31moboard_reserve(void)
 
 MACHINE_START(MX31MOBOARD, "EPFL Mobots mx31moboard")
 	/* Maintainer: Valentin Longchamp, EPFL Mobots group */
-	.boot_params = MX3x_PHYS_OFFSET + 0x100,
+	.atag_offset = 0x100,
 	.reserve = mx31moboard_reserve,
 	.map_io = mx31_map_io,
 	.init_early = imx31_init_early,
diff --git a/arch/arm/mach-imx/mach-mx35_3ds.c b/arch/arm/mach-imx/mach-mx35_3ds.c
index b3b9bd8ac2a..f2a873dc08c 100644
--- a/arch/arm/mach-imx/mach-mx35_3ds.c
+++ b/arch/arm/mach-imx/mach-mx35_3ds.c
@@ -217,7 +217,7 @@ struct sys_timer mx35pdk_timer = {
 
 MACHINE_START(MX35_3DS, "Freescale MX35PDK")
 	/* Maintainer: Freescale Semiconductor, Inc */
-	.boot_params = MX3x_PHYS_OFFSET + 0x100,
+	.atag_offset = 0x100,
 	.map_io = mx35_map_io,
 	.init_early = imx35_init_early,
 	.init_irq = mx35_init_irq,
diff --git a/arch/arm/mach-imx/mach-mxt_td60.c b/arch/arm/mach-imx/mach-mxt_td60.c
index c85876fed66..5ec3989704f 100644
--- a/arch/arm/mach-imx/mach-mxt_td60.c
+++ b/arch/arm/mach-imx/mach-mxt_td60.c
@@ -267,7 +267,7 @@ static struct sys_timer mxt_td60_timer = {
 
 MACHINE_START(MXT_TD60, "Maxtrack i-MXT TD60")
 	/* maintainer: Maxtrack Industrial */
-	.boot_params = MX27_PHYS_OFFSET + 0x100,
+	.atag_offset = 0x100,
 	.map_io = mx27_map_io,
 	.init_early = imx27_init_early,
 	.init_irq = mx27_init_irq,
diff --git a/arch/arm/mach-imx/mach-pca100.c b/arch/arm/mach-imx/mach-pca100.c
index 71083aa1603..0f6bd119903 100644
--- a/arch/arm/mach-imx/mach-pca100.c
+++ b/arch/arm/mach-imx/mach-pca100.c
@@ -435,7 +435,7 @@ static struct sys_timer pca100_timer = {
 };
 
 MACHINE_START(PCA100, "phyCARD-i.MX27")
-	.boot_params = MX27_PHYS_OFFSET + 0x100,
+	.atag_offset = 0x100,
 	.map_io = mx27_map_io,
 	.init_early = imx27_init_early,
 	.init_irq = mx27_init_irq,
diff --git a/arch/arm/mach-imx/mach-pcm037.c b/arch/arm/mach-imx/mach-pcm037.c
index f45b7cd72c8..186d4eb9079 100644
--- a/arch/arm/mach-imx/mach-pcm037.c
+++ b/arch/arm/mach-imx/mach-pcm037.c
@@ -688,7 +688,7 @@ static void __init pcm037_reserve(void)
 
 MACHINE_START(PCM037, "Phytec Phycore pcm037")
 	/* Maintainer: Pengutronix */
-	.boot_params = MX3x_PHYS_OFFSET + 0x100,
+	.atag_offset = 0x100,
 	.reserve = pcm037_reserve,
 	.map_io = mx31_map_io,
 	.init_early = imx31_init_early,
diff --git a/arch/arm/mach-imx/mach-pcm038.c b/arch/arm/mach-imx/mach-pcm038.c
index 2d6a64bbac4..091bcf87e1a 100644
--- a/arch/arm/mach-imx/mach-pcm038.c
+++ b/arch/arm/mach-imx/mach-pcm038.c
@@ -349,7 +349,7 @@ static struct sys_timer pcm038_timer = {
 };
 
 MACHINE_START(PCM038, "phyCORE-i.MX27")
-	.boot_params = MX27_PHYS_OFFSET + 0x100,
+	.atag_offset = 0x100,
 	.map_io = mx27_map_io,
 	.init_early = imx27_init_early,
 	.init_irq = mx27_init_irq,
diff --git a/arch/arm/mach-imx/mach-pcm043.c b/arch/arm/mach-imx/mach-pcm043.c
index 660ec3e80cf..0a4d31de773 100644
--- a/arch/arm/mach-imx/mach-pcm043.c
+++ b/arch/arm/mach-imx/mach-pcm043.c
@@ -418,7 +418,7 @@ struct sys_timer pcm043_timer = {
 
 MACHINE_START(PCM043, "Phytec Phycore pcm043")
 	/* Maintainer: Pengutronix */
-	.boot_params = MX3x_PHYS_OFFSET + 0x100,
+	.atag_offset = 0x100,
 	.map_io = mx35_map_io,
 	.init_early = imx35_init_early,
 	.init_irq = mx35_init_irq,
diff --git a/arch/arm/mach-imx/mach-qong.c b/arch/arm/mach-imx/mach-qong.c
index 3626f486498..9e11359c324 100644
--- a/arch/arm/mach-imx/mach-qong.c
+++ b/arch/arm/mach-imx/mach-qong.c
@@ -262,7 +262,7 @@ static struct sys_timer qong_timer = {
 
 MACHINE_START(QONG, "Dave/DENX QongEVB-LITE")
 	/* Maintainer: DENX Software Engineering GmbH */
-	.boot_params = MX3x_PHYS_OFFSET + 0x100,
+	.atag_offset = 0x100,
 	.map_io = mx31_map_io,
 	.init_early = imx31_init_early,
 	.init_irq = mx31_init_irq,
diff --git a/arch/arm/mach-imx/mach-scb9328.c b/arch/arm/mach-imx/mach-scb9328.c
index db2d60470e1..85d32845ee1 100644
--- a/arch/arm/mach-imx/mach-scb9328.c
+++ b/arch/arm/mach-imx/mach-scb9328.c
@@ -137,7 +137,7 @@ static struct sys_timer scb9328_timer = {
 
 MACHINE_START(SCB9328, "Synertronixx scb9328")
 	/* Sascha Hauer */
-	.boot_params = 0x08000100,
+	.atag_offset = 100,
 	.map_io = mx1_map_io,
 	.init_early = imx1_init_early,
 	.init_irq = mx1_init_irq,
diff --git a/arch/arm/mach-integrator/integrator_ap.c b/arch/arm/mach-integrator/integrator_ap.c
index 8cdc730dcb3..a20fb3f2bc4 100644
--- a/arch/arm/mach-integrator/integrator_ap.c
+++ b/arch/arm/mach-integrator/integrator_ap.c
@@ -459,7 +459,7 @@ static struct sys_timer ap_timer = {
 
 MACHINE_START(INTEGRATOR, "ARM-Integrator")
 	/* Maintainer: ARM Ltd/Deep Blue Solutions Ltd */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.reserve	= integrator_reserve,
 	.map_io		= ap_map_io,
 	.init_early	= integrator_init_early,
diff --git a/arch/arm/mach-integrator/integrator_cp.c b/arch/arm/mach-integrator/integrator_cp.c
index 4eb03ab5cb4..5de49c33e4d 100644
--- a/arch/arm/mach-integrator/integrator_cp.c
+++ b/arch/arm/mach-integrator/integrator_cp.c
@@ -492,7 +492,7 @@ static struct sys_timer cp_timer = {
 
 MACHINE_START(CINTEGRATOR, "ARM-IntegratorCP")
 	/* Maintainer: ARM Ltd/Deep Blue Solutions Ltd */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.reserve	= integrator_reserve,
 	.map_io		= intcp_map_io,
 	.init_early	= intcp_init_early,
diff --git a/arch/arm/mach-iop13xx/iq81340mc.c b/arch/arm/mach-iop13xx/iq81340mc.c
index 23dfaffc586..4cf2cc477ea 100644
--- a/arch/arm/mach-iop13xx/iq81340mc.c
+++ b/arch/arm/mach-iop13xx/iq81340mc.c
@@ -91,7 +91,7 @@ static struct sys_timer iq81340mc_timer = {
 
 MACHINE_START(IQ81340MC, "Intel IQ81340MC")
 	/* Maintainer: Dan Williams <dan.j.williams@intel.com> */
-	.boot_params    = 0x00000100,
+	.atag_offset    = 0x100,
 	.map_io         = iop13xx_map_io,
 	.init_irq       = iop13xx_init_irq,
 	.timer          = &iq81340mc_timer,
diff --git a/arch/arm/mach-iop13xx/iq81340sc.c b/arch/arm/mach-iop13xx/iq81340sc.c
index df3492a9c28..cd9e27499a1 100644
--- a/arch/arm/mach-iop13xx/iq81340sc.c
+++ b/arch/arm/mach-iop13xx/iq81340sc.c
@@ -93,7 +93,7 @@ static struct sys_timer iq81340sc_timer = {
 
 MACHINE_START(IQ81340SC, "Intel IQ81340SC")
 	/* Maintainer: Dan Williams <dan.j.williams@intel.com> */
-	.boot_params    = 0x00000100,
+	.atag_offset    = 0x100,
 	.map_io         = iop13xx_map_io,
 	.init_irq       = iop13xx_init_irq,
 	.timer          = &iq81340sc_timer,
diff --git a/arch/arm/mach-iop32x/em7210.c b/arch/arm/mach-iop32x/em7210.c
index 6cbffbfc2bb..4325055d4e1 100644
--- a/arch/arm/mach-iop32x/em7210.c
+++ b/arch/arm/mach-iop32x/em7210.c
@@ -203,7 +203,7 @@ static void __init em7210_init_machine(void)
 }
 
 MACHINE_START(EM7210, "Lanner EM7210")
-	.boot_params	= 0xa0000100,
+	.atag_offset	= 0x100,
 	.map_io		= em7210_map_io,
 	.init_irq	= iop32x_init_irq,
 	.timer		= &em7210_timer,
diff --git a/arch/arm/mach-iop32x/glantank.c b/arch/arm/mach-iop32x/glantank.c
index ceef5d4dce1..0edc8802057 100644
--- a/arch/arm/mach-iop32x/glantank.c
+++ b/arch/arm/mach-iop32x/glantank.c
@@ -207,7 +207,7 @@ static void __init glantank_init_machine(void)
 
 MACHINE_START(GLANTANK, "GLAN Tank")
 	/* Maintainer: Lennert Buytenhek <buytenh@wantstofly.org> */
-	.boot_params	= 0xa0000100,
+	.atag_offset	= 0x100,
 	.map_io		= glantank_map_io,
 	.init_irq	= iop32x_init_irq,
 	.timer		= &glantank_timer,
diff --git a/arch/arm/mach-iop32x/iq31244.c b/arch/arm/mach-iop32x/iq31244.c
index 3a62514dae7..9e7aaccfeba 100644
--- a/arch/arm/mach-iop32x/iq31244.c
+++ b/arch/arm/mach-iop32x/iq31244.c
@@ -313,7 +313,7 @@ __setup("force_ep80219", force_ep80219_setup);
 
 MACHINE_START(IQ31244, "Intel IQ31244")
 	/* Maintainer: Intel Corp. */
-	.boot_params	= 0xa0000100,
+	.atag_offset	= 0x100,
 	.map_io		= iq31244_map_io,
 	.init_irq	= iop32x_init_irq,
 	.timer		= &iq31244_timer,
@@ -327,7 +327,7 @@ MACHINE_END
  */
 MACHINE_START(EP80219, "Intel EP80219")
 	/* Maintainer: Intel Corp. */
-	.boot_params	= 0xa0000100,
+	.atag_offset	= 0x100,
 	.map_io		= iq31244_map_io,
 	.init_irq	= iop32x_init_irq,
 	.timer		= &iq31244_timer,
diff --git a/arch/arm/mach-iop32x/iq80321.c b/arch/arm/mach-iop32x/iq80321.c
index 35b7e6914d3..53ea86f649d 100644
--- a/arch/arm/mach-iop32x/iq80321.c
+++ b/arch/arm/mach-iop32x/iq80321.c
@@ -186,7 +186,7 @@ static void __init iq80321_init_machine(void)
 
 MACHINE_START(IQ80321, "Intel IQ80321")
 	/* Maintainer: Intel Corp. */
-	.boot_params	= 0xa0000100,
+	.atag_offset	= 0x100,
 	.map_io		= iq80321_map_io,
 	.init_irq	= iop32x_init_irq,
 	.timer		= &iq80321_timer,
diff --git a/arch/arm/mach-iop32x/n2100.c b/arch/arm/mach-iop32x/n2100.c
index 1a374eab600..d7269279968 100644
--- a/arch/arm/mach-iop32x/n2100.c
+++ b/arch/arm/mach-iop32x/n2100.c
@@ -327,7 +327,7 @@ static void __init n2100_init_machine(void)
 
 MACHINE_START(N2100, "Thecus N2100")
 	/* Maintainer: Lennert Buytenhek <buytenh@wantstofly.org> */
-	.boot_params	= 0xa0000100,
+	.atag_offset	= 0x100,
 	.map_io		= n2100_map_io,
 	.init_irq	= iop32x_init_irq,
 	.timer		= &n2100_timer,
diff --git a/arch/arm/mach-iop33x/iq80331.c b/arch/arm/mach-iop33x/iq80331.c
index 637c0272d5e..9e14ccc56f8 100644
--- a/arch/arm/mach-iop33x/iq80331.c
+++ b/arch/arm/mach-iop33x/iq80331.c
@@ -141,7 +141,7 @@ static void __init iq80331_init_machine(void)
 
 MACHINE_START(IQ80331, "Intel IQ80331")
 	/* Maintainer: Intel Corp. */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.map_io		= iop3xx_map_io,
 	.init_irq	= iop33x_init_irq,
 	.timer		= &iq80331_timer,
diff --git a/arch/arm/mach-iop33x/iq80332.c b/arch/arm/mach-iop33x/iq80332.c
index 90a0436d725..09c899a2523 100644
--- a/arch/arm/mach-iop33x/iq80332.c
+++ b/arch/arm/mach-iop33x/iq80332.c
@@ -141,7 +141,7 @@ static void __init iq80332_init_machine(void)
 
 MACHINE_START(IQ80332, "Intel IQ80332")
 	/* Maintainer: Intel Corp. */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.map_io		= iop3xx_map_io,
 	.init_irq	= iop33x_init_irq,
 	.timer		= &iq80332_timer,
diff --git a/arch/arm/mach-ixp2000/enp2611.c b/arch/arm/mach-ixp2000/enp2611.c
index 62c60ade527..af9994537e0 100644
--- a/arch/arm/mach-ixp2000/enp2611.c
+++ b/arch/arm/mach-ixp2000/enp2611.c
@@ -254,7 +254,7 @@ static void __init enp2611_init_machine(void)
 
 MACHINE_START(ENP2611, "Radisys ENP-2611 PCI network processor board")
 	/* Maintainer: Lennert Buytenhek <buytenh@wantstofly.org> */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.map_io		= enp2611_map_io,
 	.init_irq	= ixp2000_init_irq,
 	.timer		= &enp2611_timer,
diff --git a/arch/arm/mach-ixp2000/ixdp2400.c b/arch/arm/mach-ixp2000/ixdp2400.c
index 5bad1a8419b..f7dfd970014 100644
--- a/arch/arm/mach-ixp2000/ixdp2400.c
+++ b/arch/arm/mach-ixp2000/ixdp2400.c
@@ -171,7 +171,7 @@ void __init ixdp2400_init_irq(void)
 
 MACHINE_START(IXDP2400, "Intel IXDP2400 Development Platform")
 	/* Maintainer: MontaVista Software, Inc. */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.map_io		= ixdp2x00_map_io,
 	.init_irq	= ixdp2400_init_irq,
 	.timer		= &ixdp2400_timer,
diff --git a/arch/arm/mach-ixp2000/ixdp2800.c b/arch/arm/mach-ixp2000/ixdp2800.c
index 3d3cef87646..d33bcac1ec9 100644
--- a/arch/arm/mach-ixp2000/ixdp2800.c
+++ b/arch/arm/mach-ixp2000/ixdp2800.c
@@ -286,7 +286,7 @@ void __init ixdp2800_init_irq(void)
 
 MACHINE_START(IXDP2800, "Intel IXDP2800 Development Platform")
 	/* Maintainer: MontaVista Software, Inc. */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.map_io		= ixdp2x00_map_io,
 	.init_irq	= ixdp2800_init_irq,
 	.timer		= &ixdp2800_timer,
diff --git a/arch/arm/mach-ixp2000/ixdp2x01.c b/arch/arm/mach-ixp2000/ixdp2x01.c
index be2a254f137..61a28676b5b 100644
--- a/arch/arm/mach-ixp2000/ixdp2x01.c
+++ b/arch/arm/mach-ixp2000/ixdp2x01.c
@@ -417,7 +417,7 @@ static void __init ixdp2x01_init_machine(void)
 #ifdef CONFIG_ARCH_IXDP2401
 MACHINE_START(IXDP2401, "Intel IXDP2401 Development Platform")
 	/* Maintainer: MontaVista Software, Inc. */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.map_io		= ixdp2x01_map_io,
 	.init_irq	= ixdp2x01_init_irq,
 	.timer		= &ixdp2x01_timer,
@@ -428,7 +428,7 @@ MACHINE_END
 #ifdef CONFIG_ARCH_IXDP2801
 MACHINE_START(IXDP2801, "Intel IXDP2801 Development Platform")
 	/* Maintainer: MontaVista Software, Inc. */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.map_io		= ixdp2x01_map_io,
 	.init_irq	= ixdp2x01_init_irq,
 	.timer		= &ixdp2x01_timer,
@@ -441,7 +441,7 @@ MACHINE_END
  */
 MACHINE_START(IXDP28X5, "Intel IXDP2805/2855 Development Platform")
 	/* Maintainer: MontaVista Software, Inc. */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.map_io		= ixdp2x01_map_io,
 	.init_irq	= ixdp2x01_init_irq,
 	.timer		= &ixdp2x01_timer,
diff --git a/arch/arm/mach-ixp23xx/espresso.c b/arch/arm/mach-ixp23xx/espresso.c
index e25e5fe183b..30dd31652e9 100644
--- a/arch/arm/mach-ixp23xx/espresso.c
+++ b/arch/arm/mach-ixp23xx/espresso.c
@@ -88,6 +88,6 @@ MACHINE_START(ESPRESSO, "IP Fabrics Double Espresso")
 	.map_io		= ixp23xx_map_io,
 	.init_irq	= ixp23xx_init_irq,
 	.timer		= &ixp23xx_timer,
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= espresso_init,
 MACHINE_END
diff --git a/arch/arm/mach-ixp23xx/ixdp2351.c b/arch/arm/mach-ixp23xx/ixdp2351.c
index ec028e35f40..b3a57e0f341 100644
--- a/arch/arm/mach-ixp23xx/ixdp2351.c
+++ b/arch/arm/mach-ixp23xx/ixdp2351.c
@@ -331,6 +331,6 @@ MACHINE_START(IXDP2351, "Intel IXDP2351 Development Platform")
 	.map_io		= ixdp2351_map_io,
 	.init_irq	= ixdp2351_init_irq,
 	.timer		= &ixp23xx_timer,
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= ixdp2351_init,
 MACHINE_END
diff --git a/arch/arm/mach-ixp23xx/roadrunner.c b/arch/arm/mach-ixp23xx/roadrunner.c
index 844551d2368..8f4dcbba902 100644
--- a/arch/arm/mach-ixp23xx/roadrunner.c
+++ b/arch/arm/mach-ixp23xx/roadrunner.c
@@ -175,6 +175,6 @@ MACHINE_START(ROADRUNNER, "ADI Engineering RoadRunner Development Platform")
 	.map_io		= ixp23xx_map_io,
 	.init_irq	= ixp23xx_init_irq,
 	.timer		= &ixp23xx_timer,
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= roadrunner_init,
 MACHINE_END
diff --git a/arch/arm/mach-ixp4xx/avila-setup.c b/arch/arm/mach-ixp4xx/avila-setup.c
index ee19c1d383a..37609a22c45 100644
--- a/arch/arm/mach-ixp4xx/avila-setup.c
+++ b/arch/arm/mach-ixp4xx/avila-setup.c
@@ -167,7 +167,7 @@ MACHINE_START(AVILA, "Gateworks Avila Network Platform")
 	.map_io		= ixp4xx_map_io,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
-	.boot_params	= 0x0100,
+	.atag_offset	= 0x100,
 	.init_machine	= avila_init,
 #if defined(CONFIG_PCI)
 	.dma_zone_size	= SZ_64M,
@@ -185,7 +185,7 @@ MACHINE_START(LOFT, "Giant Shoulder Inc Loft board")
 	.map_io		= ixp4xx_map_io,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
-	.boot_params	= 0x0100,
+	.atag_offset	= 0x100,
 	.init_machine	= avila_init,
 #if defined(CONFIG_PCI)
 	.dma_zone_size	= SZ_64M,
diff --git a/arch/arm/mach-ixp4xx/coyote-setup.c b/arch/arm/mach-ixp4xx/coyote-setup.c
index e24564b5d93..81dfec31842 100644
--- a/arch/arm/mach-ixp4xx/coyote-setup.c
+++ b/arch/arm/mach-ixp4xx/coyote-setup.c
@@ -112,7 +112,7 @@ MACHINE_START(ADI_COYOTE, "ADI Engineering Coyote")
 	.map_io		= ixp4xx_map_io,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
-	.boot_params	= 0x0100,
+	.atag_offset	= 0x100,
 	.init_machine	= coyote_init,
 #if defined(CONFIG_PCI)
 	.dma_zone_size	= SZ_64M,
@@ -130,7 +130,7 @@ MACHINE_START(IXDPG425, "Intel IXDPG425")
 	.map_io		= ixp4xx_map_io,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
-	.boot_params	= 0x0100,
+	.atag_offset	= 0x100,
 	.init_machine	= coyote_init,
 MACHINE_END
 #endif
diff --git a/arch/arm/mach-ixp4xx/dsmg600-setup.c b/arch/arm/mach-ixp4xx/dsmg600-setup.c
index 03e54515e8b..71607a7ecc7 100644
--- a/arch/arm/mach-ixp4xx/dsmg600-setup.c
+++ b/arch/arm/mach-ixp4xx/dsmg600-setup.c
@@ -279,7 +279,7 @@ static void __init dsmg600_init(void)
 
 MACHINE_START(DSMG600, "D-Link DSM-G600 RevA")
 	/* Maintainer: www.nslu2-linux.org */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.map_io		= ixp4xx_map_io,
 	.init_irq	= ixp4xx_init_irq,
 	.timer          = &dsmg600_timer,
diff --git a/arch/arm/mach-ixp4xx/fsg-setup.c b/arch/arm/mach-ixp4xx/fsg-setup.c
index 23a8b361456..a9540cd9037 100644
--- a/arch/arm/mach-ixp4xx/fsg-setup.c
+++ b/arch/arm/mach-ixp4xx/fsg-setup.c
@@ -273,7 +273,7 @@ MACHINE_START(FSG, "Freecom FSG-3")
 	.map_io		= ixp4xx_map_io,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
-	.boot_params	= 0x0100,
+	.atag_offset	= 0x100,
 	.init_machine	= fsg_init,
 #if defined(CONFIG_PCI)
 	.dma_zone_size	= SZ_64M,
diff --git a/arch/arm/mach-ixp4xx/gateway7001-setup.c b/arch/arm/mach-ixp4xx/gateway7001-setup.c
index d4f851bdd9a..d69d1b053bb 100644
--- a/arch/arm/mach-ixp4xx/gateway7001-setup.c
+++ b/arch/arm/mach-ixp4xx/gateway7001-setup.c
@@ -99,7 +99,7 @@ MACHINE_START(GATEWAY7001, "Gateway 7001 AP")
 	.map_io		= ixp4xx_map_io,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
-	.boot_params	= 0x0100,
+	.atag_offset	= 0x100,
 	.init_machine	= gateway7001_init,
 #if defined(CONFIG_PCI)
 	.dma_zone_size	= SZ_64M,
diff --git a/arch/arm/mach-ixp4xx/goramo_mlr.c b/arch/arm/mach-ixp4xx/goramo_mlr.c
index 7548d9a2efe..bf6678d1a92 100644
--- a/arch/arm/mach-ixp4xx/goramo_mlr.c
+++ b/arch/arm/mach-ixp4xx/goramo_mlr.c
@@ -499,7 +499,7 @@ MACHINE_START(GORAMO_MLR, "MultiLink")
 	.map_io		= ixp4xx_map_io,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
-	.boot_params	= 0x0100,
+	.atag_offset	= 0x100,
 	.init_machine	= gmlr_init,
 #if defined(CONFIG_PCI)
 	.dma_zone_size	= SZ_64M,
diff --git a/arch/arm/mach-ixp4xx/gtwx5715-setup.c b/arch/arm/mach-ixp4xx/gtwx5715-setup.c
index 3790dffd3c3..aa029fc1914 100644
--- a/arch/arm/mach-ixp4xx/gtwx5715-setup.c
+++ b/arch/arm/mach-ixp4xx/gtwx5715-setup.c
@@ -167,7 +167,7 @@ MACHINE_START(GTWX5715, "Gemtek GTWX5715 (Linksys WRV54G)")
 	.map_io		= ixp4xx_map_io,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
-	.boot_params	= 0x0100,
+	.atag_offset	= 0x100,
 	.init_machine	= gtwx5715_init,
 #if defined(CONFIG_PCI)
 	.dma_zone_size	= SZ_64M,
diff --git a/arch/arm/mach-ixp4xx/ixdp425-setup.c b/arch/arm/mach-ixp4xx/ixdp425-setup.c
index 6a2927956bf..f235f829dfa 100644
--- a/arch/arm/mach-ixp4xx/ixdp425-setup.c
+++ b/arch/arm/mach-ixp4xx/ixdp425-setup.c
@@ -256,7 +256,7 @@ MACHINE_START(IXDP425, "Intel IXDP425 Development Platform")
 	.map_io		= ixp4xx_map_io,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
-	.boot_params	= 0x0100,
+	.atag_offset	= 0x100,
 	.init_machine	= ixdp425_init,
 #if defined(CONFIG_PCI)
 	.dma_zone_size	= SZ_64M,
@@ -270,7 +270,7 @@ MACHINE_START(IXDP465, "Intel IXDP465 Development Platform")
 	.map_io		= ixp4xx_map_io,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
-	.boot_params	= 0x0100,
+	.atag_offset	= 0x100,
 	.init_machine	= ixdp425_init,
 #if defined(CONFIG_PCI)
 	.dma_zone_size	= SZ_64M,
@@ -284,7 +284,7 @@ MACHINE_START(IXCDP1100, "Intel IXCDP1100 Development Platform")
 	.map_io		= ixp4xx_map_io,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
-	.boot_params	= 0x0100,
+	.atag_offset	= 0x100,
 	.init_machine	= ixdp425_init,
 #if defined(CONFIG_PCI)
 	.dma_zone_size	= SZ_64M,
@@ -298,7 +298,7 @@ MACHINE_START(KIXRP435, "Intel KIXRP435 Reference Platform")
 	.map_io		= ixp4xx_map_io,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
-	.boot_params	= 0x0100,
+	.atag_offset	= 0x100,
 	.init_machine	= ixdp425_init,
 #if defined(CONFIG_PCI)
 	.dma_zone_size	= SZ_64M,
diff --git a/arch/arm/mach-ixp4xx/nas100d-setup.c b/arch/arm/mach-ixp4xx/nas100d-setup.c
index afb51879d9a..9f4669260d4 100644
--- a/arch/arm/mach-ixp4xx/nas100d-setup.c
+++ b/arch/arm/mach-ixp4xx/nas100d-setup.c
@@ -314,7 +314,7 @@ static void __init nas100d_init(void)
 
 MACHINE_START(NAS100D, "Iomega NAS 100d")
 	/* Maintainer: www.nslu2-linux.org */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.map_io		= ixp4xx_map_io,
 	.init_irq	= ixp4xx_init_irq,
 	.timer          = &ixp4xx_timer,
diff --git a/arch/arm/mach-ixp4xx/nslu2-setup.c b/arch/arm/mach-ixp4xx/nslu2-setup.c
index 69e40f2cf09..3676fbf6ef9 100644
--- a/arch/arm/mach-ixp4xx/nslu2-setup.c
+++ b/arch/arm/mach-ixp4xx/nslu2-setup.c
@@ -300,7 +300,7 @@ static void __init nslu2_init(void)
 
 MACHINE_START(NSLU2, "Linksys NSLU2")
 	/* Maintainer: www.nslu2-linux.org */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.map_io		= ixp4xx_map_io,
 	.init_irq	= ixp4xx_init_irq,
 	.timer          = &nslu2_timer,
diff --git a/arch/arm/mach-ixp4xx/vulcan-setup.c b/arch/arm/mach-ixp4xx/vulcan-setup.c
index 045336c833a..27e469ef452 100644
--- a/arch/arm/mach-ixp4xx/vulcan-setup.c
+++ b/arch/arm/mach-ixp4xx/vulcan-setup.c
@@ -239,7 +239,7 @@ MACHINE_START(ARCOM_VULCAN, "Arcom/Eurotech Vulcan")
 	.map_io		= ixp4xx_map_io,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
-	.boot_params	= 0x0100,
+	.atag_offset	= 0x100,
 	.init_machine	= vulcan_init,
 #if defined(CONFIG_PCI)
 	.dma_zone_size	= SZ_64M,
diff --git a/arch/arm/mach-ixp4xx/wg302v2-setup.c b/arch/arm/mach-ixp4xx/wg302v2-setup.c
index 40b9fad800b..b14144b967a 100644
--- a/arch/arm/mach-ixp4xx/wg302v2-setup.c
+++ b/arch/arm/mach-ixp4xx/wg302v2-setup.c
@@ -100,7 +100,7 @@ MACHINE_START(WG302V2, "Netgear WG302 v2 / WAG302 v2")
 	.map_io		= ixp4xx_map_io,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
-	.boot_params	= 0x0100,
+	.atag_offset	= 0x100,
 	.init_machine	= wg302v2_init,
 #if defined(CONFIG_PCI)
 	.dma_zone_size	= SZ_64M,
diff --git a/arch/arm/mach-kirkwood/d2net_v2-setup.c b/arch/arm/mach-kirkwood/d2net_v2-setup.c
index 043cfd5e140..f457e07a65f 100644
--- a/arch/arm/mach-kirkwood/d2net_v2-setup.c
+++ b/arch/arm/mach-kirkwood/d2net_v2-setup.c
@@ -221,7 +221,7 @@ static void __init d2net_v2_init(void)
 }
 
 MACHINE_START(D2NET_V2, "LaCie d2 Network v2")
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= d2net_v2_init,
 	.map_io		= kirkwood_map_io,
 	.init_early	= kirkwood_init_early,
diff --git a/arch/arm/mach-kirkwood/db88f6281-bp-setup.c b/arch/arm/mach-kirkwood/db88f6281-bp-setup.c
index bff04e04d67..ff4c21c1f92 100644
--- a/arch/arm/mach-kirkwood/db88f6281-bp-setup.c
+++ b/arch/arm/mach-kirkwood/db88f6281-bp-setup.c
@@ -97,7 +97,7 @@ subsys_initcall(db88f6281_pci_init);
 
 MACHINE_START(DB88F6281_BP, "Marvell DB-88F6281-BP Development Board")
 	/* Maintainer: Saeed Bishara <saeed@marvell.com> */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= db88f6281_init,
 	.map_io		= kirkwood_map_io,
 	.init_early	= kirkwood_init_early,
diff --git a/arch/arm/mach-kirkwood/dockstar-setup.c b/arch/arm/mach-kirkwood/dockstar-setup.c
index f14dfb8508c..e4d199b2b1e 100644
--- a/arch/arm/mach-kirkwood/dockstar-setup.c
+++ b/arch/arm/mach-kirkwood/dockstar-setup.c
@@ -102,7 +102,7 @@ static void __init dockstar_init(void)
 }
 
 MACHINE_START(DOCKSTAR, "Seagate FreeAgent DockStar")
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= dockstar_init,
 	.map_io		= kirkwood_map_io,
 	.init_early	= kirkwood_init_early,
diff --git a/arch/arm/mach-kirkwood/guruplug-setup.c b/arch/arm/mach-kirkwood/guruplug-setup.c
index 41d1b40696a..6c40f784b51 100644
--- a/arch/arm/mach-kirkwood/guruplug-setup.c
+++ b/arch/arm/mach-kirkwood/guruplug-setup.c
@@ -121,7 +121,7 @@ static void __init guruplug_init(void)
 
 MACHINE_START(GURUPLUG, "Marvell GuruPlug Reference Board")
 	/* Maintainer: Siddarth Gore <gores@marvell.com> */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= guruplug_init,
 	.map_io		= kirkwood_map_io,
 	.init_early	= kirkwood_init_early,
diff --git a/arch/arm/mach-kirkwood/mv88f6281gtw_ge-setup.c b/arch/arm/mach-kirkwood/mv88f6281gtw_ge-setup.c
index 00cca22eca6..9a1e917352f 100644
--- a/arch/arm/mach-kirkwood/mv88f6281gtw_ge-setup.c
+++ b/arch/arm/mach-kirkwood/mv88f6281gtw_ge-setup.c
@@ -163,7 +163,7 @@ subsys_initcall(mv88f6281gtw_ge_pci_init);
 
 MACHINE_START(MV88F6281GTW_GE, "Marvell 88F6281 GTW GE Board")
 	/* Maintainer: Lennert Buytenhek <buytenh@marvell.com> */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= mv88f6281gtw_ge_init,
 	.map_io		= kirkwood_map_io,
 	.init_early	= kirkwood_init_early,
diff --git a/arch/arm/mach-kirkwood/netspace_v2-setup.c b/arch/arm/mach-kirkwood/netspace_v2-setup.c
index 7cdab577645..8849bcc7328 100644
--- a/arch/arm/mach-kirkwood/netspace_v2-setup.c
+++ b/arch/arm/mach-kirkwood/netspace_v2-setup.c
@@ -258,7 +258,7 @@ static void __init netspace_v2_init(void)
 
 #ifdef CONFIG_MACH_NETSPACE_V2
 MACHINE_START(NETSPACE_V2, "LaCie Network Space v2")
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= netspace_v2_init,
 	.map_io		= kirkwood_map_io,
 	.init_early	= kirkwood_init_early,
@@ -269,7 +269,7 @@ MACHINE_END
 
 #ifdef CONFIG_MACH_INETSPACE_V2
 MACHINE_START(INETSPACE_V2, "LaCie Internet Space v2")
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= netspace_v2_init,
 	.map_io		= kirkwood_map_io,
 	.init_early	= kirkwood_init_early,
@@ -280,7 +280,7 @@ MACHINE_END
 
 #ifdef CONFIG_MACH_NETSPACE_MAX_V2
 MACHINE_START(NETSPACE_MAX_V2, "LaCie Network Space Max v2")
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= netspace_v2_init,
 	.map_io		= kirkwood_map_io,
 	.init_early	= kirkwood_init_early,
diff --git a/arch/arm/mach-kirkwood/netxbig_v2-setup.c b/arch/arm/mach-kirkwood/netxbig_v2-setup.c
index 6be627deb0f..1ba12c4dff8 100644
--- a/arch/arm/mach-kirkwood/netxbig_v2-setup.c
+++ b/arch/arm/mach-kirkwood/netxbig_v2-setup.c
@@ -399,7 +399,7 @@ static void __init netxbig_v2_init(void)
 
 #ifdef CONFIG_MACH_NET2BIG_V2
 MACHINE_START(NET2BIG_V2, "LaCie 2Big Network v2")
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= netxbig_v2_init,
 	.map_io		= kirkwood_map_io,
 	.init_early	= kirkwood_init_early,
@@ -410,7 +410,7 @@ MACHINE_END
 
 #ifdef CONFIG_MACH_NET5BIG_V2
 MACHINE_START(NET5BIG_V2, "LaCie 5Big Network v2")
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= netxbig_v2_init,
 	.map_io		= kirkwood_map_io,
 	.init_early	= kirkwood_init_early,
diff --git a/arch/arm/mach-kirkwood/openrd-setup.c b/arch/arm/mach-kirkwood/openrd-setup.c
index f69beeff445..5660ca6c3d8 100644
--- a/arch/arm/mach-kirkwood/openrd-setup.c
+++ b/arch/arm/mach-kirkwood/openrd-setup.c
@@ -214,7 +214,7 @@ subsys_initcall(openrd_pci_init);
 #ifdef CONFIG_MACH_OPENRD_BASE
 MACHINE_START(OPENRD_BASE, "Marvell OpenRD Base Board")
 	/* Maintainer: Dhaval Vasa <dhaval.vasa@einfochips.com> */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= openrd_init,
 	.map_io		= kirkwood_map_io,
 	.init_early	= kirkwood_init_early,
@@ -226,7 +226,7 @@ MACHINE_END
 #ifdef CONFIG_MACH_OPENRD_CLIENT
 MACHINE_START(OPENRD_CLIENT, "Marvell OpenRD Client Board")
 	/* Maintainer: Dhaval Vasa <dhaval.vasa@einfochips.com> */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= openrd_init,
 	.map_io		= kirkwood_map_io,
 	.init_early	= kirkwood_init_early,
@@ -238,7 +238,7 @@ MACHINE_END
 #ifdef CONFIG_MACH_OPENRD_ULTIMATE
 MACHINE_START(OPENRD_ULTIMATE, "Marvell OpenRD Ultimate Board")
 	/* Maintainer: Dhaval Vasa <dhaval.vasa@einfochips.com> */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= openrd_init,
 	.map_io		= kirkwood_map_io,
 	.init_early	= kirkwood_init_early,
diff --git a/arch/arm/mach-kirkwood/rd88f6192-nas-setup.c b/arch/arm/mach-kirkwood/rd88f6192-nas-setup.c
index 75c6601b8d8..6663869773a 100644
--- a/arch/arm/mach-kirkwood/rd88f6192-nas-setup.c
+++ b/arch/arm/mach-kirkwood/rd88f6192-nas-setup.c
@@ -79,7 +79,7 @@ subsys_initcall(rd88f6192_pci_init);
 
 MACHINE_START(RD88F6192_NAS, "Marvell RD-88F6192-NAS Development Board")
 	/* Maintainer: Saeed Bishara <saeed@marvell.com> */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= rd88f6192_init,
 	.map_io		= kirkwood_map_io,
 	.init_early	= kirkwood_init_early,
diff --git a/arch/arm/mach-kirkwood/rd88f6281-setup.c b/arch/arm/mach-kirkwood/rd88f6281-setup.c
index 0f75494d590..66b3c05e37a 100644
--- a/arch/arm/mach-kirkwood/rd88f6281-setup.c
+++ b/arch/arm/mach-kirkwood/rd88f6281-setup.c
@@ -115,7 +115,7 @@ subsys_initcall(rd88f6281_pci_init);
 
 MACHINE_START(RD88F6281, "Marvell RD-88F6281 Reference Board")
 	/* Maintainer: Saeed Bishara <saeed@marvell.com> */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= rd88f6281_init,
 	.map_io		= kirkwood_map_io,
 	.init_early	= kirkwood_init_early,
diff --git a/arch/arm/mach-kirkwood/sheevaplug-setup.c b/arch/arm/mach-kirkwood/sheevaplug-setup.c
index 17de0bf53c0..8b102d62e82 100644
--- a/arch/arm/mach-kirkwood/sheevaplug-setup.c
+++ b/arch/arm/mach-kirkwood/sheevaplug-setup.c
@@ -138,7 +138,7 @@ static void __init sheevaplug_init(void)
 #ifdef CONFIG_MACH_SHEEVAPLUG
 MACHINE_START(SHEEVAPLUG, "Marvell SheevaPlug Reference Board")
 	/* Maintainer: shadi Ammouri <shadi@marvell.com> */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= sheevaplug_init,
 	.map_io		= kirkwood_map_io,
 	.init_early	= kirkwood_init_early,
@@ -149,7 +149,7 @@ MACHINE_END
 
 #ifdef CONFIG_MACH_ESATA_SHEEVAPLUG
 MACHINE_START(ESATA_SHEEVAPLUG, "Marvell eSATA SheevaPlug Reference Board")
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= sheevaplug_init,
 	.map_io		= kirkwood_map_io,
 	.init_early	= kirkwood_init_early,
diff --git a/arch/arm/mach-kirkwood/t5325-setup.c b/arch/arm/mach-kirkwood/t5325-setup.c
index e6b9b1b22a3..ea104fb5ec3 100644
--- a/arch/arm/mach-kirkwood/t5325-setup.c
+++ b/arch/arm/mach-kirkwood/t5325-setup.c
@@ -201,7 +201,7 @@ subsys_initcall(hp_t5325_pci_init);
 
 MACHINE_START(T5325, "HP t5325 Thin Client")
 	/* Maintainer: Martin Michlmayr <tbm@cyrius.com> */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= hp_t5325_init,
 	.map_io		= kirkwood_map_io,
 	.init_early	= kirkwood_init_early,
diff --git a/arch/arm/mach-kirkwood/ts219-setup.c b/arch/arm/mach-kirkwood/ts219-setup.c
index 68f32f2bf55..262c034836d 100644
--- a/arch/arm/mach-kirkwood/ts219-setup.c
+++ b/arch/arm/mach-kirkwood/ts219-setup.c
@@ -132,7 +132,7 @@ subsys_initcall(ts219_pci_init);
 
 MACHINE_START(TS219, "QNAP TS-119/TS-219")
 	/* Maintainer: Martin Michlmayr <tbm@cyrius.com> */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= qnap_ts219_init,
 	.map_io		= kirkwood_map_io,
 	.init_early	= kirkwood_init_early,
diff --git a/arch/arm/mach-kirkwood/ts41x-setup.c b/arch/arm/mach-kirkwood/ts41x-setup.c
index d5d00997070..b68f5b4a9ec 100644
--- a/arch/arm/mach-kirkwood/ts41x-setup.c
+++ b/arch/arm/mach-kirkwood/ts41x-setup.c
@@ -176,7 +176,7 @@ subsys_initcall(ts41x_pci_init);
 
 MACHINE_START(TS41X, "QNAP TS-41x")
 	/* Maintainer: Martin Michlmayr <tbm@cyrius.com> */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= qnap_ts41x_init,
 	.map_io		= kirkwood_map_io,
 	.init_early	= kirkwood_init_early,
diff --git a/arch/arm/mach-ks8695/board-acs5k.c b/arch/arm/mach-ks8695/board-acs5k.c
index 3ca4f8e6f54..a5fcc7c7fe1 100644
--- a/arch/arm/mach-ks8695/board-acs5k.c
+++ b/arch/arm/mach-ks8695/board-acs5k.c
@@ -223,7 +223,7 @@ static void __init acs5k_init(void)
 
 MACHINE_START(ACS5K, "Brivo Systems LLC ACS-5000 Master board")
 	/* Maintainer: Simtec Electronics. */
-	.boot_params	= KS8695_SDRAM_PA + 0x100,
+	.atag_offset	= 0x100,
 	.map_io		= ks8695_map_io,
 	.init_irq	= ks8695_init_irq,
 	.init_machine	= acs5k_init,
diff --git a/arch/arm/mach-ks8695/board-dsm320.c b/arch/arm/mach-ks8695/board-dsm320.c
index 1338cb3e982..fb91a716a7d 100644
--- a/arch/arm/mach-ks8695/board-dsm320.c
+++ b/arch/arm/mach-ks8695/board-dsm320.c
@@ -121,7 +121,7 @@ static void __init dsm320_init(void)
 
 MACHINE_START(DSM320, "D-Link DSM-320 Wireless Media Player")
 	/* Maintainer: Simtec Electronics. */
-	.boot_params	= KS8695_SDRAM_PA + 0x100,
+	.atag_offset	= 0x100,
 	.map_io		= ks8695_map_io,
 	.init_irq	= ks8695_init_irq,
 	.init_machine	= dsm320_init,
diff --git a/arch/arm/mach-ks8695/board-micrel.c b/arch/arm/mach-ks8695/board-micrel.c
index e2e3cba8dcd..8f67a750b6c 100644
--- a/arch/arm/mach-ks8695/board-micrel.c
+++ b/arch/arm/mach-ks8695/board-micrel.c
@@ -53,7 +53,7 @@ static void __init micrel_init(void)
 
 MACHINE_START(KS8695, "KS8695 Centaur Development Board")
 	/* Maintainer: Micrel Semiconductor Inc. */
-	.boot_params	= KS8695_SDRAM_PA + 0x100,
+	.atag_offset	= 0x100,
 	.map_io		= ks8695_map_io,
 	.init_irq	= ks8695_init_irq,
 	.init_machine	= micrel_init,
diff --git a/arch/arm/mach-lpc32xx/phy3250.c b/arch/arm/mach-lpc32xx/phy3250.c
index 7993b096778..9b621e14d16 100644
--- a/arch/arm/mach-lpc32xx/phy3250.c
+++ b/arch/arm/mach-lpc32xx/phy3250.c
@@ -382,7 +382,7 @@ arch_initcall(lpc32xx_display_uid);
 
 MACHINE_START(PHY3250, "Phytec 3250 board with the LPC3250 Microcontroller")
 	/* Maintainer: Kevin Wells, NXP Semiconductors */
-	.boot_params	= 0x80000100,
+	.atag_offset	= 0x100,
 	.map_io		= lpc32xx_map_io,
 	.init_irq	= lpc32xx_init_irq,
 	.timer		= &lpc32xx_timer,
diff --git a/arch/arm/mach-msm/board-halibut.c b/arch/arm/mach-msm/board-halibut.c
index 18a3c97bc86..16c86f8b4f3 100644
--- a/arch/arm/mach-msm/board-halibut.c
+++ b/arch/arm/mach-msm/board-halibut.c
@@ -93,7 +93,7 @@ static void __init halibut_map_io(void)
 }
 
 MACHINE_START(HALIBUT, "Halibut Board (QCT SURF7200A)")
-	.boot_params	= 0x10000100,
+	.atag_offset	= 0x100,
 	.fixup		= halibut_fixup,
 	.map_io		= halibut_map_io,
 	.init_irq	= halibut_init_irq,
diff --git a/arch/arm/mach-msm/board-mahimahi.c b/arch/arm/mach-msm/board-mahimahi.c
index 7a9a03eb189..8a1672ee4e4 100644
--- a/arch/arm/mach-msm/board-mahimahi.c
+++ b/arch/arm/mach-msm/board-mahimahi.c
@@ -74,7 +74,7 @@ static void __init mahimahi_map_io(void)
 extern struct sys_timer msm_timer;
 
 MACHINE_START(MAHIMAHI, "mahimahi")
-	.boot_params	= 0x20000100,
+	.atag_offset	= 0x100,
 	.fixup		= mahimahi_fixup,
 	.map_io		= mahimahi_map_io,
 	.init_irq	= msm_init_irq,
diff --git a/arch/arm/mach-msm/board-msm7x27.c b/arch/arm/mach-msm/board-msm7x27.c
index c03f269e2e4..a80765533f1 100644
--- a/arch/arm/mach-msm/board-msm7x27.c
+++ b/arch/arm/mach-msm/board-msm7x27.c
@@ -130,7 +130,7 @@ static void __init msm7x2x_map_io(void)
 }
 
 MACHINE_START(MSM7X27_SURF, "QCT MSM7x27 SURF")
-	.boot_params	= PLAT_PHYS_OFFSET + 0x100,
+	.atag_offset	= 0x100,
 	.map_io		= msm7x2x_map_io,
 	.init_irq	= msm7x2x_init_irq,
 	.init_machine	= msm7x2x_init,
@@ -138,7 +138,7 @@ MACHINE_START(MSM7X27_SURF, "QCT MSM7x27 SURF")
 MACHINE_END
 
 MACHINE_START(MSM7X27_FFA, "QCT MSM7x27 FFA")
-	.boot_params	= PLAT_PHYS_OFFSET + 0x100,
+	.atag_offset	= 0x100,
 	.map_io		= msm7x2x_map_io,
 	.init_irq	= msm7x2x_init_irq,
 	.init_machine	= msm7x2x_init,
@@ -146,7 +146,7 @@ MACHINE_START(MSM7X27_FFA, "QCT MSM7x27 FFA")
 MACHINE_END
 
 MACHINE_START(MSM7X25_SURF, "QCT MSM7x25 SURF")
-	.boot_params	= PLAT_PHYS_OFFSET + 0x100,
+	.atag_offset	= 0x100,
 	.map_io		= msm7x2x_map_io,
 	.init_irq	= msm7x2x_init_irq,
 	.init_machine	= msm7x2x_init,
@@ -154,7 +154,7 @@ MACHINE_START(MSM7X25_SURF, "QCT MSM7x25 SURF")
 MACHINE_END
 
 MACHINE_START(MSM7X25_FFA, "QCT MSM7x25 FFA")
-	.boot_params	= PLAT_PHYS_OFFSET + 0x100,
+	.atag_offset	= 0x100,
 	.map_io		= msm7x2x_map_io,
 	.init_irq	= msm7x2x_init_irq,
 	.init_machine	= msm7x2x_init,
diff --git a/arch/arm/mach-msm/board-msm7x30.c b/arch/arm/mach-msm/board-msm7x30.c
index b7a84966b71..5a2ab685518 100644
--- a/arch/arm/mach-msm/board-msm7x30.c
+++ b/arch/arm/mach-msm/board-msm7x30.c
@@ -106,7 +106,7 @@ static void __init msm7x30_map_io(void)
 }
 
 MACHINE_START(MSM7X30_SURF, "QCT MSM7X30 SURF")
-	.boot_params = PLAT_PHYS_OFFSET + 0x100,
+	.atag_offset = 0x100,
 	.map_io = msm7x30_map_io,
 	.init_irq = msm7x30_init_irq,
 	.init_machine = msm7x30_init,
@@ -114,7 +114,7 @@ MACHINE_START(MSM7X30_SURF, "QCT MSM7X30 SURF")
 MACHINE_END
 
 MACHINE_START(MSM7X30_FFA, "QCT MSM7X30 FFA")
-	.boot_params = PLAT_PHYS_OFFSET + 0x100,
+	.atag_offset = 0x100,
 	.map_io = msm7x30_map_io,
 	.init_irq = msm7x30_init_irq,
 	.init_machine = msm7x30_init,
@@ -122,7 +122,7 @@ MACHINE_START(MSM7X30_FFA, "QCT MSM7X30 FFA")
 MACHINE_END
 
 MACHINE_START(MSM7X30_FLUID, "QCT MSM7X30 FLUID")
-	.boot_params = PLAT_PHYS_OFFSET + 0x100,
+	.atag_offset = 0x100,
 	.map_io = msm7x30_map_io,
 	.init_irq = msm7x30_init_irq,
 	.init_machine = msm7x30_init,
diff --git a/arch/arm/mach-msm/board-qsd8x50.c b/arch/arm/mach-msm/board-qsd8x50.c
index 6a96911b0ad..51109b1f434 100644
--- a/arch/arm/mach-msm/board-qsd8x50.c
+++ b/arch/arm/mach-msm/board-qsd8x50.c
@@ -193,7 +193,7 @@ static void __init qsd8x50_init(void)
 }
 
 MACHINE_START(QSD8X50_SURF, "QCT QSD8X50 SURF")
-	.boot_params = PLAT_PHYS_OFFSET + 0x100,
+	.atag_offset = 0x100,
 	.map_io = qsd8x50_map_io,
 	.init_irq = qsd8x50_init_irq,
 	.init_machine = qsd8x50_init,
@@ -201,7 +201,7 @@ MACHINE_START(QSD8X50_SURF, "QCT QSD8X50 SURF")
 MACHINE_END
 
 MACHINE_START(QSD8X50A_ST1_5, "QCT QSD8X50A ST1.5")
-	.boot_params = PLAT_PHYS_OFFSET + 0x100,
+	.atag_offset = 0x100,
 	.map_io = qsd8x50_map_io,
 	.init_irq = qsd8x50_init_irq,
 	.init_machine = qsd8x50_init,
diff --git a/arch/arm/mach-msm/board-sapphire.c b/arch/arm/mach-msm/board-sapphire.c
index 68f930f07d7..dc0bcb5a6b9 100644
--- a/arch/arm/mach-msm/board-sapphire.c
+++ b/arch/arm/mach-msm/board-sapphire.c
@@ -105,7 +105,7 @@ static void __init sapphire_map_io(void)
 
 MACHINE_START(SAPPHIRE, "sapphire")
 /* Maintainer: Brian Swetland <swetland@google.com> */
-	.boot_params    = PLAT_PHYS_OFFSET + 0x100,
+	.atag_offset    = 0x100,
 	.fixup          = sapphire_fixup,
 	.map_io         = sapphire_map_io,
 	.init_irq       = sapphire_init_irq,
diff --git a/arch/arm/mach-msm/board-trout.c b/arch/arm/mach-msm/board-trout.c
index 814386772c6..22d5694f5fe 100644
--- a/arch/arm/mach-msm/board-trout.c
+++ b/arch/arm/mach-msm/board-trout.c
@@ -93,7 +93,7 @@ static void __init trout_map_io(void)
 }
 
 MACHINE_START(TROUT, "HTC Dream")
-	.boot_params	= 0x10000100,
+	.atag_offset	= 0x100,
 	.fixup		= trout_fixup,
 	.map_io		= trout_map_io,
 	.init_irq	= trout_init_irq,
diff --git a/arch/arm/mach-msm/platsmp.c b/arch/arm/mach-msm/platsmp.c
index 1a1af9e5625..72765952091 100644
--- a/arch/arm/mach-msm/platsmp.c
+++ b/arch/arm/mach-msm/platsmp.c
@@ -156,6 +156,12 @@ void __init smp_init_cpus(void)
 {
 	unsigned int i, ncores = get_core_count();
 
+	if (ncores > nr_cpu_ids) {
+		pr_warn("SMP: %u cores greater than maximum (%u), clipping\n",
+			ncores, nr_cpu_ids);
+		ncores = nr_cpu_ids;
+	}
+
 	for (i = 0; i < ncores; i++)
 		set_cpu_possible(i, true);
 
diff --git a/arch/arm/mach-mv78xx0/buffalo-wxl-setup.c b/arch/arm/mach-mv78xx0/buffalo-wxl-setup.c
index 20f3f125ed2..0e94268d6e6 100644
--- a/arch/arm/mach-mv78xx0/buffalo-wxl-setup.c
+++ b/arch/arm/mach-mv78xx0/buffalo-wxl-setup.c
@@ -145,7 +145,7 @@ subsys_initcall(wxl_pci_init);
 
 MACHINE_START(TERASTATION_WXL, "Buffalo Nas WXL")
 	/* Maintainer: Sebastien Requiem <sebastien@requiem.fr> */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= wxl_init,
 	.map_io		= mv78xx0_map_io,
 	.init_early	= mv78xx0_init_early,
diff --git a/arch/arm/mach-mv78xx0/db78x00-bp-setup.c b/arch/arm/mach-mv78xx0/db78x00-bp-setup.c
index df5aebe5b0f..50b85ae2da5 100644
--- a/arch/arm/mach-mv78xx0/db78x00-bp-setup.c
+++ b/arch/arm/mach-mv78xx0/db78x00-bp-setup.c
@@ -93,7 +93,7 @@ subsys_initcall(db78x00_pci_init);
 
 MACHINE_START(DB78X00_BP, "Marvell DB-78x00-BP Development Board")
 	/* Maintainer: Lennert Buytenhek <buytenh@marvell.com> */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= db78x00_init,
 	.map_io		= mv78xx0_map_io,
 	.init_early	= mv78xx0_init_early,
diff --git a/arch/arm/mach-mv78xx0/rd78x00-masa-setup.c b/arch/arm/mach-mv78xx0/rd78x00-masa-setup.c
index d927f14c681..e85222e5357 100644
--- a/arch/arm/mach-mv78xx0/rd78x00-masa-setup.c
+++ b/arch/arm/mach-mv78xx0/rd78x00-masa-setup.c
@@ -78,7 +78,7 @@ subsys_initcall(rd78x00_pci_init);
 
 MACHINE_START(RD78X00_MASA, "Marvell RD-78x00-MASA Development Board")
 	/* Maintainer: Lennert Buytenhek <buytenh@marvell.com> */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= rd78x00_masa_init,
 	.map_io		= mv78xx0_map_io,
 	.init_early	= mv78xx0_init_early,
diff --git a/arch/arm/mach-mx5/Makefile b/arch/arm/mach-mx5/Makefile
index 383e7cd3fbc..4471ce76e39 100644
--- a/arch/arm/mach-mx5/Makefile
+++ b/arch/arm/mach-mx5/Makefile
@@ -3,9 +3,8 @@
 #
 
 # Object file lists.
-obj-y   := cpu.o mm.o clock-mx51-mx53.o devices.o ehci.o system.o
+obj-y   := cpu.o mm.o clock-mx51-mx53.o devices.o ehci.o system.o cpuidle.o
 obj-$(CONFIG_SOC_IMX50) += mm-mx50.o
-
 obj-$(CONFIG_PM) += pm-imx5.o
 obj-$(CONFIG_CPU_FREQ_IMX)    += cpu_op-mx51.o
 obj-$(CONFIG_MACH_MX51_BABBAGE) += board-mx51_babbage.o
diff --git a/arch/arm/mach-mx5/Makefile.boot b/arch/arm/mach-mx5/Makefile.boot
index e928be1b675..4111462e242 100644
--- a/arch/arm/mach-mx5/Makefile.boot
+++ b/arch/arm/mach-mx5/Makefile.boot
@@ -7,3 +7,8 @@ initrd_phys-$(CONFIG_ARCH_MX51)	:= 0x90800000
    zreladdr-$(CONFIG_ARCH_MX53)	:= 0x70008000
 params_phys-$(CONFIG_ARCH_MX53)	:= 0x70000100
 initrd_phys-$(CONFIG_ARCH_MX53)	:= 0x70800000
+
+dtb-$(CONFIG_MACH_MX51_BABBAGE) += mx51-babbage.dtb
+dtb-$(CONFIG_MACH_MX51_EFIKAMX) += genesi-efikamx.dtb
+dtb-$(CONFIG_MACH_MX51_EFIKASB) += genesi-efikasb.dtb
+dtb-$(CONFIG_MACH_MX53_LOCO) += mx53-loco.dtb
diff --git a/arch/arm/mach-mx5/board-cpuimx51.c b/arch/arm/mach-mx5/board-cpuimx51.c
index 68934ea8725..e01af948e04 100644
--- a/arch/arm/mach-mx5/board-cpuimx51.c
+++ b/arch/arm/mach-mx5/board-cpuimx51.c
@@ -293,7 +293,7 @@ static struct sys_timer mxc_timer = {
 
 MACHINE_START(EUKREA_CPUIMX51, "Eukrea CPUIMX51 Module")
 	/* Maintainer: Eric Bénard <eric@eukrea.com> */
-	.boot_params = MX51_PHYS_OFFSET + 0x100,
+	.atag_offset = 0x100,
 	.map_io = mx51_map_io,
 	.init_early = imx51_init_early,
 	.init_irq = mx51_init_irq,
diff --git a/arch/arm/mach-mx5/board-cpuimx51sd.c b/arch/arm/mach-mx5/board-cpuimx51sd.c
index ff096d58729..b41fc274a42 100644
--- a/arch/arm/mach-mx5/board-cpuimx51sd.c
+++ b/arch/arm/mach-mx5/board-cpuimx51sd.c
@@ -331,7 +331,7 @@ static struct sys_timer mxc_timer = {
 
 MACHINE_START(EUKREA_CPUIMX51SD, "Eukrea CPUIMX51SD")
 	/* Maintainer: Eric Bénard <eric@eukrea.com> */
-	.boot_params = MX51_PHYS_OFFSET + 0x100,
+	.atag_offset = 0x100,
 	.map_io = mx51_map_io,
 	.init_early = imx51_init_early,
 	.init_irq = mx51_init_irq,
diff --git a/arch/arm/mach-mx5/board-mx51_3ds.c b/arch/arm/mach-mx5/board-mx51_3ds.c
index 07a38154da2..a50174e69e2 100644
--- a/arch/arm/mach-mx5/board-mx51_3ds.c
+++ b/arch/arm/mach-mx5/board-mx51_3ds.c
@@ -169,7 +169,7 @@ static struct sys_timer mx51_3ds_timer = {
 
 MACHINE_START(MX51_3DS, "Freescale MX51 3-Stack Board")
 	/* Maintainer: Freescale Semiconductor, Inc. */
-	.boot_params = MX51_PHYS_OFFSET + 0x100,
+	.atag_offset = 0x100,
 	.map_io = mx51_map_io,
 	.init_early = imx51_init_early,
 	.init_irq = mx51_init_irq,
diff --git a/arch/arm/mach-mx5/board-mx51_babbage.c b/arch/arm/mach-mx5/board-mx51_babbage.c
index 11b0ff67f89..8c65ede42b7 100644
--- a/arch/arm/mach-mx5/board-mx51_babbage.c
+++ b/arch/arm/mach-mx5/board-mx51_babbage.c
@@ -414,12 +414,18 @@ static struct sys_timer mx51_babbage_timer = {
 	.init = mx51_babbage_timer_init,
 };
 
+static const char *mx51_babbage_dt_match[] __initdata = {
+	"fsl,mx51-babbage",
+	NULL
+};
+
 MACHINE_START(MX51_BABBAGE, "Freescale MX51 Babbage Board")
 	/* Maintainer: Amit Kucheria <amit.kucheria@canonical.com> */
-	.boot_params = MX51_PHYS_OFFSET + 0x100,
+	.atag_offset = 0x100,
 	.map_io = mx51_map_io,
 	.init_early = imx51_init_early,
 	.init_irq = mx51_init_irq,
 	.timer = &mx51_babbage_timer,
 	.init_machine = mx51_babbage_init,
+	.dt_compat = mx51_babbage_dt_match,
 MACHINE_END
diff --git a/arch/arm/mach-mx5/board-mx51_efikamx.c b/arch/arm/mach-mx5/board-mx51_efikamx.c
index 551daf85ff8..b183efc7396 100644
--- a/arch/arm/mach-mx5/board-mx51_efikamx.c
+++ b/arch/arm/mach-mx5/board-mx51_efikamx.c
@@ -278,12 +278,18 @@ static struct sys_timer mx51_efikamx_timer = {
 	.init = mx51_efikamx_timer_init,
 };
 
+static const char *mx51_efikamx_dt_match[] __initdata = {
+	"genesi,efikamx",
+	NULL
+};
+
 MACHINE_START(MX51_EFIKAMX, "Genesi EfikaMX nettop")
 	/* Maintainer: Amit Kucheria <amit.kucheria@linaro.org> */
-	.boot_params = MX51_PHYS_OFFSET + 0x100,
+	.atag_offset = 0x100,
 	.map_io = mx51_map_io,
 	.init_early = imx51_init_early,
 	.init_irq = mx51_init_irq,
 	.timer = &mx51_efikamx_timer,
 	.init_machine = mx51_efikamx_init,
+	.dt_compat = mx51_efikamx_dt_match,
 MACHINE_END
diff --git a/arch/arm/mach-mx5/board-mx51_efikasb.c b/arch/arm/mach-mx5/board-mx51_efikasb.c
index 8a9bca22beb..dfdc011cc72 100644
--- a/arch/arm/mach-mx5/board-mx51_efikasb.c
+++ b/arch/arm/mach-mx5/board-mx51_efikasb.c
@@ -265,11 +265,17 @@ static struct sys_timer mx51_efikasb_timer = {
 	.init	= mx51_efikasb_timer_init,
 };
 
+static const char *mx51_efikasb_dt_match[] __initdata = {
+	"genesi,efikasb",
+	NULL
+};
+
 MACHINE_START(MX51_EFIKASB, "Genesi Efika Smartbook")
-	.boot_params = MX51_PHYS_OFFSET + 0x100,
+	.atag_offset = 0x100,
 	.map_io = mx51_map_io,
 	.init_early = imx51_init_early,
 	.init_irq = mx51_init_irq,
 	.init_machine =  efikasb_board_init,
 	.timer = &mx51_efikasb_timer,
+	.dt_compat = mx51_efikasb_dt_match,
 MACHINE_END
diff --git a/arch/arm/mach-mx5/board-mx53_loco.c b/arch/arm/mach-mx5/board-mx53_loco.c
index 4e1d51d252d..13cddd703be 100644
--- a/arch/arm/mach-mx5/board-mx53_loco.c
+++ b/arch/arm/mach-mx5/board-mx53_loco.c
@@ -284,10 +284,15 @@ static struct sys_timer mx53_loco_timer = {
 	.init	= mx53_loco_timer_init,
 };
 
+static const char *mx53_loco_dt_match[] __initdata = {
+	"fsl,mx53-loco",
+	NULL
+};
 MACHINE_START(MX53_LOCO, "Freescale MX53 LOCO Board")
 	.map_io = mx53_map_io,
 	.init_early = imx53_init_early,
 	.init_irq = mx53_init_irq,
 	.timer = &mx53_loco_timer,
 	.init_machine = mx53_loco_board_init,
+	.dt_compat = mx53_loco_dt_match,
 MACHINE_END
diff --git a/arch/arm/mach-mx5/cpuidle.c b/arch/arm/mach-mx5/cpuidle.c
new file mode 100644
index 00000000000..fa3ea6a66f8
--- /dev/null
+++ b/arch/arm/mach-mx5/cpuidle.c
@@ -0,0 +1,82 @@
+/*
+ * Copyright 2011 Freescale Semiconductor, Inc.
+ * Copyright 2011 Linaro Ltd.
+ *
+ * The code contained herein is licensed under the GNU General Public
+ * License. You may obtain a copy of the GNU General Public License
+ * Version 2 or later at the following locations:
+ *
+ * http://www.opensource.org/licenses/gpl-license.html
+ * http://www.gnu.org/copyleft/gpl.html
+ */
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/platform_device.h>
+#include <linux/io.h>
+#include <linux/clk.h>
+#include <linux/err.h>
+#include <asm/proc-fns.h>
+#include <mach/cpuidle.h>
+#include <mach/system.h>
+
+static int mx5_cpuidle_init(void *init_data);
+static int mx5_cpuidle(struct cpuidle_device *dev, struct cpuidle_state *state);
+
+static struct imx_cpuidle_state_data mx5_cpuidle_state_data[] __initdata = {
+	{
+		.name = "powered_noclock",
+		.desc = "idle cpu powered, unclocked.",
+		.exit_latency = 12,
+		.mach_cpu_pwr_state = WAIT_UNCLOCKED,
+	}, {
+		.name = "nopower_noclock",
+		.desc = "idle cpu unpowered, unclocked.",
+		.exit_latency = 20,
+		.mach_cpu_pwr_state = WAIT_UNCLOCKED_POWER_OFF,
+	}
+};
+
+static struct cpuidle_driver mx5_cpuidle_driver = {
+	.name	= "imx5_cpuidle",
+	.owner	= THIS_MODULE,
+};
+
+struct imx_cpuidle_data mx5_cpuidle_data __initdata = {
+	.imx_cpuidle_driver = &mx5_cpuidle_driver,
+	.state_data = mx5_cpuidle_state_data,
+	.mach_cpuidle = mx5_cpuidle,
+	.mach_cpuidle_init = mx5_cpuidle_init,
+	.num_states = ARRAY_SIZE(mx5_cpuidle_state_data),
+};
+
+int mx5_cpuidle(struct cpuidle_device *dev, struct cpuidle_state *state)
+{
+	mx5_cpu_lp_set((enum mxc_cpu_pwr_mode)state->driver_data);
+
+	cpu_do_idle();
+
+	return 0;
+}
+
+int __init mx5_cpuidle_init(void * init_data)
+{
+	int ret;
+	struct clk *gpc_dvfs_clk;
+
+	gpc_dvfs_clk = clk_get(NULL, "gpc_dvfs");
+
+	if (IS_ERR(gpc_dvfs_clk)) {
+		pr_err("%s: Failed to get gpc_dvfs clock\n", __func__);
+		return (int)gpc_dvfs_clk;
+	}
+
+	ret = clk_enable(gpc_dvfs_clk);
+
+	if (IS_ERR(&ret)) {
+		pr_err("%s: Failed to enable gpc_dvfs clock\n", __func__);
+		return ret;
+	}
+
+	return 0;
+}
diff --git a/arch/arm/mach-mx5/cpuidle.h b/arch/arm/mach-mx5/cpuidle.h
new file mode 100644
index 00000000000..270ffa651d6
--- /dev/null
+++ b/arch/arm/mach-mx5/cpuidle.h
@@ -0,0 +1,13 @@
+/*
+ * Copyright 2011 Freescale Semiconductor, Inc.
+ * Copyright 2011 Linaro Ltd.
+ *
+ * The code contained herein is licensed under the GNU General Public
+ * License. You may obtain a copy of the GNU General Public License
+ * Version 2 or later at the following locations:
+ *
+ * http://www.opensource.org/licenses/gpl-license.html
+ * http://www.gnu.org/copyleft/gpl.html
+ */
+
+extern struct imx_cpuidle_data mx5_cpuidle_data;
diff --git a/arch/arm/mach-mx5/mm.c b/arch/arm/mach-mx5/mm.c
index baea6e5cddd..29bb785a398 100644
--- a/arch/arm/mach-mx5/mm.c
+++ b/arch/arm/mach-mx5/mm.c
@@ -20,6 +20,8 @@
 #include <mach/common.h>
 #include <mach/devices-common.h>
 #include <mach/iomux-v3.h>
+#include <mach/cpuidle.h>
+#include "cpuidle.h"
 
 /*
  * Define the MX51 memory map.
@@ -148,6 +150,8 @@ void __init imx51_soc_init(void)
 
 	/* i.mx51 has the i.mx35 type sdma */
 	imx_add_imx_sdma("imx35-sdma", MX51_SDMA_BASE_ADDR, MX51_INT_SDMA, &imx51_sdma_pdata);
+
+	imx_cpuidle_init(&mx5_cpuidle_data);
 }
 
 void __init imx53_soc_init(void)
diff --git a/arch/arm/mach-mxs/clock-mx28.c b/arch/arm/mach-mxs/clock-mx28.c
index 5dcc59d5b9e..b3a71245f38 100644
--- a/arch/arm/mach-mxs/clock-mx28.c
+++ b/arch/arm/mach-mxs/clock-mx28.c
@@ -404,7 +404,7 @@ static int name##_set_rate(struct clk *clk, unsigned long rate)		\
 	reg = __raw_readl(CLKCTRL_BASE_ADDR + HW_CLKCTRL_##dr);		\
 	reg &= ~BM_CLKCTRL_##dr##_DIV;					\
 	reg |= div << BP_CLKCTRL_##dr##_DIV;				\
-	if (reg | (1 << clk->enable_shift)) {				\
+	if (reg & (1 << clk->enable_shift)) {				\
 		pr_err("%s: clock is gated\n", __func__);		\
 		return -EINVAL;						\
 	}								\
diff --git a/arch/arm/mach-netx/nxdb500.c b/arch/arm/mach-netx/nxdb500.c
index ca8b203a3c9..90903dd44cb 100644
--- a/arch/arm/mach-netx/nxdb500.c
+++ b/arch/arm/mach-netx/nxdb500.c
@@ -200,7 +200,7 @@ static void __init nxdb500_init(void)
 }
 
 MACHINE_START(NXDB500, "Hilscher nxdb500")
-	.boot_params	= 0x80000100,
+	.atag_offset	= 0x100,
 	.map_io		= netx_map_io,
 	.init_irq	= netx_init_irq,
 	.timer		= &netx_timer,
diff --git a/arch/arm/mach-netx/nxdkn.c b/arch/arm/mach-netx/nxdkn.c
index d775cbe0727..c63384aba50 100644
--- a/arch/arm/mach-netx/nxdkn.c
+++ b/arch/arm/mach-netx/nxdkn.c
@@ -93,7 +93,7 @@ static void __init nxdkn_init(void)
 }
 
 MACHINE_START(NXDKN, "Hilscher nxdkn")
-	.boot_params	= 0x80000100,
+	.atag_offset	= 0x100,
 	.map_io		= netx_map_io,
 	.init_irq	= netx_init_irq,
 	.timer		= &netx_timer,
diff --git a/arch/arm/mach-netx/nxeb500hmi.c b/arch/arm/mach-netx/nxeb500hmi.c
index de369cd1dcb..8f548ec83ad 100644
--- a/arch/arm/mach-netx/nxeb500hmi.c
+++ b/arch/arm/mach-netx/nxeb500hmi.c
@@ -177,7 +177,7 @@ static void __init nxeb500hmi_init(void)
 }
 
 MACHINE_START(NXEB500HMI, "Hilscher nxeb500hmi")
-	.boot_params	= 0x80000100,
+	.atag_offset	= 0x100,
 	.map_io		= netx_map_io,
 	.init_irq	= netx_init_irq,
 	.timer		= &netx_timer,
diff --git a/arch/arm/mach-nomadik/board-nhk8815.c b/arch/arm/mach-nomadik/board-nhk8815.c
index 139930350d9..398a75f62be 100644
--- a/arch/arm/mach-nomadik/board-nhk8815.c
+++ b/arch/arm/mach-nomadik/board-nhk8815.c
@@ -276,7 +276,7 @@ static void __init nhk8815_platform_init(void)
 
 MACHINE_START(NOMADIK, "NHK8815")
 	/* Maintainer: ST MicroElectronics */
-	.boot_params	= 0x100,
+	.atag_offset	= 0x100,
 	.map_io		= cpu8815_map_io,
 	.init_irq	= cpu8815_init_irq,
 	.timer		= &nomadik_timer,
diff --git a/arch/arm/mach-nuc93x/mach-nuc932evb.c b/arch/arm/mach-nuc93x/mach-nuc932evb.c
index d7025704248..1f741b1c160 100644
--- a/arch/arm/mach-nuc93x/mach-nuc932evb.c
+++ b/arch/arm/mach-nuc93x/mach-nuc932evb.c
@@ -35,7 +35,6 @@ static void __init nuc932evb_init(void)
 
 MACHINE_START(NUC932EVB, "NUC932EVB")
 	/* Maintainer: Wan ZongShun */
-	.boot_params	= 0,
 	.map_io		= nuc932evb_map_io,
 	.init_irq	= nuc93x_init_irq,
 	.init_machine	= nuc932evb_init,
diff --git a/arch/arm/mach-omap1/board-ams-delta.c b/arch/arm/mach-omap1/board-ams-delta.c
index 312ea6b0409..eb36b25450a 100644
--- a/arch/arm/mach-omap1/board-ams-delta.c
+++ b/arch/arm/mach-omap1/board-ams-delta.c
@@ -386,7 +386,7 @@ static void __init ams_delta_map_io(void)
 
 MACHINE_START(AMS_DELTA, "Amstrad E3 (Delta)")
 	/* Maintainer: Jonathan McDowell <noodles@earth.li> */
-	.boot_params	= 0x10000100,
+	.atag_offset	= 0x100,
 	.map_io		= ams_delta_map_io,
 	.reserve	= omap_reserve,
 	.init_irq	= ams_delta_init_irq,
diff --git a/arch/arm/mach-omap1/board-fsample.c b/arch/arm/mach-omap1/board-fsample.c
index a6b1bea5037..999789c4811 100644
--- a/arch/arm/mach-omap1/board-fsample.c
+++ b/arch/arm/mach-omap1/board-fsample.c
@@ -389,7 +389,7 @@ static void __init omap_fsample_map_io(void)
 
 MACHINE_START(OMAP_FSAMPLE, "OMAP730 F-Sample")
 /* Maintainer: Brian Swetland <swetland@google.com> */
-	.boot_params	= 0x10000100,
+	.atag_offset	= 0x100,
 	.map_io		= omap_fsample_map_io,
 	.reserve	= omap_reserve,
 	.init_irq	= omap_fsample_init_irq,
diff --git a/arch/arm/mach-omap1/board-generic.c b/arch/arm/mach-omap1/board-generic.c
index 04fc356c40f..23cc9e4ad50 100644
--- a/arch/arm/mach-omap1/board-generic.c
+++ b/arch/arm/mach-omap1/board-generic.c
@@ -94,7 +94,7 @@ static void __init omap_generic_map_io(void)
 
 MACHINE_START(OMAP_GENERIC, "Generic OMAP1510/1610/1710")
 	/* Maintainer: Tony Lindgren <tony@atomide.com> */
-	.boot_params	= 0x10000100,
+	.atag_offset	= 0x100,
 	.map_io		= omap_generic_map_io,
 	.reserve	= omap_reserve,
 	.init_irq	= omap_generic_init_irq,
diff --git a/arch/arm/mach-omap1/board-h2.c b/arch/arm/mach-omap1/board-h2.c
index cb7fb1aa3dc..6c70c28d055 100644
--- a/arch/arm/mach-omap1/board-h2.c
+++ b/arch/arm/mach-omap1/board-h2.c
@@ -461,7 +461,7 @@ static void __init h2_map_io(void)
 
 MACHINE_START(OMAP_H2, "TI-H2")
 	/* Maintainer: Imre Deak <imre.deak@nokia.com> */
-	.boot_params	= 0x10000100,
+	.atag_offset	= 0x100,
 	.map_io		= h2_map_io,
 	.reserve	= omap_reserve,
 	.init_irq	= h2_init_irq,
diff --git a/arch/arm/mach-omap1/board-h3.c b/arch/arm/mach-omap1/board-h3.c
index 31f34875ffa..8e2b64a4692 100644
--- a/arch/arm/mach-omap1/board-h3.c
+++ b/arch/arm/mach-omap1/board-h3.c
@@ -449,7 +449,7 @@ static void __init h3_map_io(void)
 
 MACHINE_START(OMAP_H3, "TI OMAP1710 H3 board")
 	/* Maintainer: Texas Instruments, Inc. */
-	.boot_params	= 0x10000100,
+	.atag_offset	= 0x100,
 	.map_io		= h3_map_io,
 	.reserve	= omap_reserve,
 	.init_irq	= h3_init_irq,
diff --git a/arch/arm/mach-omap1/board-htcherald.c b/arch/arm/mach-omap1/board-htcherald.c
index 36e06ea7ec6..e81ead1c89e 100644
--- a/arch/arm/mach-omap1/board-htcherald.c
+++ b/arch/arm/mach-omap1/board-htcherald.c
@@ -611,7 +611,7 @@ static void __init htcherald_init_irq(void)
 MACHINE_START(HERALD, "HTC Herald")
 	/* Maintainer: Cory Maccarrone <darkstar6262@gmail.com> */
 	/* Maintainer: wing-linux.sourceforge.net */
-	.boot_params    = 0x10000100,
+	.atag_offset    = 0x100,
 	.map_io         = htcherald_map_io,
 	.reserve	= omap_reserve,
 	.init_irq       = htcherald_init_irq,
diff --git a/arch/arm/mach-omap1/board-innovator.c b/arch/arm/mach-omap1/board-innovator.c
index 0b1ba462d38..8b034594fbc 100644
--- a/arch/arm/mach-omap1/board-innovator.c
+++ b/arch/arm/mach-omap1/board-innovator.c
@@ -459,7 +459,7 @@ static void __init innovator_map_io(void)
 
 MACHINE_START(OMAP_INNOVATOR, "TI-Innovator")
 	/* Maintainer: MontaVista Software, Inc. */
-	.boot_params	= 0x10000100,
+	.atag_offset	= 0x100,
 	.map_io		= innovator_map_io,
 	.reserve	= omap_reserve,
 	.init_irq	= innovator_init_irq,
diff --git a/arch/arm/mach-omap1/board-nokia770.c b/arch/arm/mach-omap1/board-nokia770.c
index 5469ce247ff..6825635ac68 100644
--- a/arch/arm/mach-omap1/board-nokia770.c
+++ b/arch/arm/mach-omap1/board-nokia770.c
@@ -264,7 +264,7 @@ static void __init omap_nokia770_map_io(void)
 }
 
 MACHINE_START(NOKIA770, "Nokia 770")
-	.boot_params	= 0x10000100,
+	.atag_offset	= 0x100,
 	.map_io		= omap_nokia770_map_io,
 	.reserve	= omap_reserve,
 	.init_irq	= omap_nokia770_init_irq,
diff --git a/arch/arm/mach-omap1/board-osk.c b/arch/arm/mach-omap1/board-osk.c
index b08a2138077..44b8e9362bf 100644
--- a/arch/arm/mach-omap1/board-osk.c
+++ b/arch/arm/mach-omap1/board-osk.c
@@ -583,7 +583,7 @@ static void __init osk_map_io(void)
 
 MACHINE_START(OMAP_OSK, "TI-OSK")
 	/* Maintainer: Dirk Behme <dirk.behme@de.bosch.com> */
-	.boot_params	= 0x10000100,
+	.atag_offset	= 0x100,
 	.map_io		= osk_map_io,
 	.reserve	= omap_reserve,
 	.init_irq	= osk_init_irq,
diff --git a/arch/arm/mach-omap1/board-palmte.c b/arch/arm/mach-omap1/board-palmte.c
index 459cb6bfed5..3d8cd90b1db 100644
--- a/arch/arm/mach-omap1/board-palmte.c
+++ b/arch/arm/mach-omap1/board-palmte.c
@@ -275,7 +275,7 @@ static void __init omap_palmte_map_io(void)
 }
 
 MACHINE_START(OMAP_PALMTE, "OMAP310 based Palm Tungsten E")
-	.boot_params	= 0x10000100,
+	.atag_offset	= 0x100,
 	.map_io		= omap_palmte_map_io,
 	.reserve	= omap_reserve,
 	.init_irq	= omap_palmte_init_irq,
diff --git a/arch/arm/mach-omap1/board-palmtt.c b/arch/arm/mach-omap1/board-palmtt.c
index b214f45f646..d0eefe81cd1 100644
--- a/arch/arm/mach-omap1/board-palmtt.c
+++ b/arch/arm/mach-omap1/board-palmtt.c
@@ -321,7 +321,7 @@ static void __init omap_palmtt_map_io(void)
 }
 
 MACHINE_START(OMAP_PALMTT, "OMAP1510 based Palm Tungsten|T")
-	.boot_params	= 0x10000100,
+	.atag_offset	= 0x100,
 	.map_io		= omap_palmtt_map_io,
 	.reserve	= omap_reserve,
 	.init_irq	= omap_palmtt_init_irq,
diff --git a/arch/arm/mach-omap1/board-palmz71.c b/arch/arm/mach-omap1/board-palmz71.c
index 9b0ea48d35f..98e79bc0921 100644
--- a/arch/arm/mach-omap1/board-palmz71.c
+++ b/arch/arm/mach-omap1/board-palmz71.c
@@ -341,7 +341,7 @@ omap_palmz71_map_io(void)
 }
 
 MACHINE_START(OMAP_PALMZ71, "OMAP310 based Palm Zire71")
-	.boot_params	= 0x10000100,
+	.atag_offset	= 0x100,
 	.map_io		= omap_palmz71_map_io,
 	.reserve	= omap_reserve,
 	.init_irq	= omap_palmz71_init_irq,
diff --git a/arch/arm/mach-omap1/board-perseus2.c b/arch/arm/mach-omap1/board-perseus2.c
index 67acd414263..ad3a1567604 100644
--- a/arch/arm/mach-omap1/board-perseus2.c
+++ b/arch/arm/mach-omap1/board-perseus2.c
@@ -350,7 +350,7 @@ static void __init omap_perseus2_map_io(void)
 
 MACHINE_START(OMAP_PERSEUS2, "OMAP730 Perseus2")
 	/* Maintainer: Kevin Hilman <kjh@hilman.org> */
-	.boot_params	= 0x10000100,
+	.atag_offset	= 0x100,
 	.map_io		= omap_perseus2_map_io,
 	.reserve	= omap_reserve,
 	.init_irq	= omap_perseus2_init_irq,
diff --git a/arch/arm/mach-omap1/board-sx1.c b/arch/arm/mach-omap1/board-sx1.c
index 9c3b7c52d9c..602b55c39d3 100644
--- a/arch/arm/mach-omap1/board-sx1.c
+++ b/arch/arm/mach-omap1/board-sx1.c
@@ -421,7 +421,7 @@ static void __init omap_sx1_map_io(void)
 }
 
 MACHINE_START(SX1, "OMAP310 based Siemens SX1")
-	.boot_params	= 0x10000100,
+	.atag_offset	= 0x100,
 	.map_io		= omap_sx1_map_io,
 	.reserve	= omap_reserve,
 	.init_irq	= omap_sx1_init_irq,
diff --git a/arch/arm/mach-omap1/board-voiceblue.c b/arch/arm/mach-omap1/board-voiceblue.c
index 036edc0ee9b..80165154617 100644
--- a/arch/arm/mach-omap1/board-voiceblue.c
+++ b/arch/arm/mach-omap1/board-voiceblue.c
@@ -301,7 +301,7 @@ static void __init voiceblue_init(void)
 
 MACHINE_START(VOICEBLUE, "VoiceBlue OMAP5910")
 	/* Maintainer: Ladislav Michl <michl@2n.cz> */
-	.boot_params	= 0x10000100,
+	.atag_offset	= 0x100,
 	.map_io		= voiceblue_map_io,
 	.reserve	= omap_reserve,
 	.init_irq	= voiceblue_init_irq,
diff --git a/arch/arm/mach-omap1/io.c b/arch/arm/mach-omap1/io.c
index 870886a2959..1cfa1b6bb62 100644
--- a/arch/arm/mach-omap1/io.c
+++ b/arch/arm/mach-omap1/io.c
@@ -121,6 +121,7 @@ void __init omap1_map_common_io(void)
 #endif
 
 	omap_sram_init();
+	omap_init_consistent_dma_size();
 }
 
 /*
diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig
index 57b66d590c5..b45c88d4276 100644
--- a/arch/arm/mach-omap2/Kconfig
+++ b/arch/arm/mach-omap2/Kconfig
@@ -329,6 +329,7 @@ config MACH_OMAP4_PANDA
 config OMAP3_EMU
 	bool "OMAP3 debugging peripherals"
 	depends on ARCH_OMAP3
+	select ARM_AMBA
 	select OC_ETM
 	help
 	  Say Y here to enable debugging hardware of omap3
diff --git a/arch/arm/mach-omap2/Makefile.boot b/arch/arm/mach-omap2/Makefile.boot
index 565aff7f37a..422c1700ccf 100644
--- a/arch/arm/mach-omap2/Makefile.boot
+++ b/arch/arm/mach-omap2/Makefile.boot
@@ -1,3 +1,9 @@
   zreladdr-y		:= 0x80008000
 params_phys-y		:= 0x80000100
 initrd_phys-y		:= 0x80800000
+
+dtb-$(CONFIG_MACH_OMAP3_BEAGLE) += omap3-beagle.dtb
+dtb-$(CONFIG_MACH_OMAP4_PANDA) += omap4-panda.dtb
+dtb-$(CONFIG_MACH_OVERO) += omap3-overo.dtb
+dtb-$(CONFIG_MACH_IGEP0020) += isee-igep-v2.dtb
+dtb-$(CONFIG_MACH_IGEP0030) += isee-igep-v3.dtb
diff --git a/arch/arm/mach-omap2/board-2430sdp.c b/arch/arm/mach-omap2/board-2430sdp.c
index f79b7d2a8ed..87f43ade440 100644
--- a/arch/arm/mach-omap2/board-2430sdp.c
+++ b/arch/arm/mach-omap2/board-2430sdp.c
@@ -257,7 +257,7 @@ static void __init omap_2430sdp_map_io(void)
 
 MACHINE_START(OMAP_2430SDP, "OMAP2430 sdp2430 board")
 	/* Maintainer: Syed Khasim - Texas Instruments Inc */
-	.boot_params	= 0x80000100,
+	.atag_offset	= 0x100,
 	.reserve	= omap_reserve,
 	.map_io		= omap_2430sdp_map_io,
 	.init_early	= omap_2430sdp_init_early,
diff --git a/arch/arm/mach-omap2/board-3430sdp.c b/arch/arm/mach-omap2/board-3430sdp.c
index bd600cfb7f8..2430531b223 100644
--- a/arch/arm/mach-omap2/board-3430sdp.c
+++ b/arch/arm/mach-omap2/board-3430sdp.c
@@ -729,7 +729,7 @@ static void __init omap_3430sdp_init(void)
 
 MACHINE_START(OMAP_3430SDP, "OMAP3430 3430SDP board")
 	/* Maintainer: Syed Khasim - Texas Instruments Inc */
-	.boot_params	= 0x80000100,
+	.atag_offset	= 0x100,
 	.reserve	= omap_reserve,
 	.map_io		= omap3_map_io,
 	.init_early	= omap_3430sdp_init_early,
diff --git a/arch/arm/mach-omap2/board-3630sdp.c b/arch/arm/mach-omap2/board-3630sdp.c
index e4f37b57a0c..8b5b5aa751e 100644
--- a/arch/arm/mach-omap2/board-3630sdp.c
+++ b/arch/arm/mach-omap2/board-3630sdp.c
@@ -215,7 +215,7 @@ static void __init omap_sdp_init(void)
 }
 
 MACHINE_START(OMAP_3630SDP, "OMAP 3630SDP board")
-	.boot_params	= 0x80000100,
+	.atag_offset	= 0x100,
 	.reserve	= omap_reserve,
 	.map_io		= omap3_map_io,
 	.init_early	= omap_sdp_init_early,
diff --git a/arch/arm/mach-omap2/board-4430sdp.c b/arch/arm/mach-omap2/board-4430sdp.c
index c7cef44c75d..be931105d68 100644
--- a/arch/arm/mach-omap2/board-4430sdp.c
+++ b/arch/arm/mach-omap2/board-4430sdp.c
@@ -838,7 +838,7 @@ static void __init omap_4430sdp_map_io(void)
 
 MACHINE_START(OMAP_4430SDP, "OMAP4430 4430SDP board")
 	/* Maintainer: Santosh Shilimkar - Texas Instruments Inc */
-	.boot_params	= 0x80000100,
+	.atag_offset	= 0x100,
 	.reserve	= omap_reserve,
 	.map_io		= omap_4430sdp_map_io,
 	.init_early	= omap_4430sdp_init_early,
diff --git a/arch/arm/mach-omap2/board-am3517crane.c b/arch/arm/mach-omap2/board-am3517crane.c
index 933e9353cb3..db110fdb8b2 100644
--- a/arch/arm/mach-omap2/board-am3517crane.c
+++ b/arch/arm/mach-omap2/board-am3517crane.c
@@ -98,7 +98,7 @@ static void __init am3517_crane_init(void)
 }
 
 MACHINE_START(CRANEBOARD, "AM3517/05 CRANEBOARD")
-	.boot_params	= 0x80000100,
+	.atag_offset	= 0x100,
 	.reserve	= omap_reserve,
 	.map_io		= omap3_map_io,
 	.init_early	= am3517_crane_init_early,
diff --git a/arch/arm/mach-omap2/board-am3517evm.c b/arch/arm/mach-omap2/board-am3517evm.c
index f3006c30415..1325085e453 100644
--- a/arch/arm/mach-omap2/board-am3517evm.c
+++ b/arch/arm/mach-omap2/board-am3517evm.c
@@ -490,7 +490,7 @@ static void __init am3517_evm_init(void)
 }
 
 MACHINE_START(OMAP3517EVM, "OMAP3517/AM3517 EVM")
-	.boot_params	= 0x80000100,
+	.atag_offset	= 0x100,
 	.reserve	= omap_reserve,
 	.map_io		= omap3_map_io,
 	.init_early	= am3517_evm_init_early,
diff --git a/arch/arm/mach-omap2/board-apollon.c b/arch/arm/mach-omap2/board-apollon.c
index 70211703ff9..67800e647d7 100644
--- a/arch/arm/mach-omap2/board-apollon.c
+++ b/arch/arm/mach-omap2/board-apollon.c
@@ -350,7 +350,7 @@ static void __init omap_apollon_map_io(void)
 
 MACHINE_START(OMAP_APOLLON, "OMAP24xx Apollon")
 	/* Maintainer: Kyungmin Park <kyungmin.park@samsung.com> */
-	.boot_params	= 0x80000100,
+	.atag_offset	= 0x100,
 	.reserve	= omap_reserve,
 	.map_io		= omap_apollon_map_io,
 	.init_early	= omap_apollon_init_early,
diff --git a/arch/arm/mach-omap2/board-cm-t35.c b/arch/arm/mach-omap2/board-cm-t35.c
index 3af8aab435b..38179c17550 100644
--- a/arch/arm/mach-omap2/board-cm-t35.c
+++ b/arch/arm/mach-omap2/board-cm-t35.c
@@ -634,7 +634,7 @@ static void __init cm_t3730_init(void)
 }
 
 MACHINE_START(CM_T35, "Compulab CM-T35")
-	.boot_params	= 0x80000100,
+	.atag_offset	= 0x100,
 	.reserve	= omap_reserve,
 	.map_io		= omap3_map_io,
 	.init_early	= cm_t35_init_early,
@@ -644,7 +644,7 @@ MACHINE_START(CM_T35, "Compulab CM-T35")
 MACHINE_END
 
 MACHINE_START(CM_T3730, "Compulab CM-T3730")
-	.boot_params    = 0x80000100,
+	.atag_offset    = 0x100,
 	.reserve        = omap_reserve,
 	.map_io         = omap3_map_io,
 	.init_early     = cm_t35_init_early,
diff --git a/arch/arm/mach-omap2/board-cm-t3517.c b/arch/arm/mach-omap2/board-cm-t3517.c
index 05c72f4c1b5..aed9c29f9fa 100644
--- a/arch/arm/mach-omap2/board-cm-t3517.c
+++ b/arch/arm/mach-omap2/board-cm-t3517.c
@@ -299,7 +299,7 @@ static void __init cm_t3517_init(void)
 }
 
 MACHINE_START(CM_T3517, "Compulab CM-T3517")
-	.boot_params	= 0x80000100,
+	.atag_offset	= 0x100,
 	.reserve        = omap_reserve,
 	.map_io		= omap3_map_io,
 	.init_early	= cm_t3517_init_early,
diff --git a/arch/arm/mach-omap2/board-devkit8000.c b/arch/arm/mach-omap2/board-devkit8000.c
index b6002ec31c6..99a42432ac9 100644
--- a/arch/arm/mach-omap2/board-devkit8000.c
+++ b/arch/arm/mach-omap2/board-devkit8000.c
@@ -667,7 +667,7 @@ static void __init devkit8000_init(void)
 }
 
 MACHINE_START(DEVKIT8000, "OMAP3 Devkit8000")
-	.boot_params	= 0x80000100,
+	.atag_offset	= 0x100,
 	.reserve	= omap_reserve,
 	.map_io		= omap3_map_io,
 	.init_early	= devkit8000_init_early,
diff --git a/arch/arm/mach-omap2/board-generic.c b/arch/arm/mach-omap2/board-generic.c
index 54db41a84a9..25642697281 100644
--- a/arch/arm/mach-omap2/board-generic.c
+++ b/arch/arm/mach-omap2/board-generic.c
@@ -66,7 +66,7 @@ static void __init omap_generic_map_io(void)
 /* XXX This machine entry name should be updated */
 MACHINE_START(OMAP_GENERIC, "Generic OMAP24xx")
 	/* Maintainer: Paul Mundt <paul.mundt@nokia.com> */
-	.boot_params	= 0x80000100,
+	.atag_offset	= 0x100,
 	.reserve	= omap_reserve,
 	.map_io		= omap_generic_map_io,
 	.init_early	= omap_generic_init_early,
diff --git a/arch/arm/mach-omap2/board-h4.c b/arch/arm/mach-omap2/board-h4.c
index 45de2b319ec..a58c6ba06f7 100644
--- a/arch/arm/mach-omap2/board-h4.c
+++ b/arch/arm/mach-omap2/board-h4.c
@@ -382,7 +382,7 @@ static void __init omap_h4_map_io(void)
 
 MACHINE_START(OMAP_H4, "OMAP2420 H4 board")
 	/* Maintainer: Paul Mundt <paul.mundt@nokia.com> */
-	.boot_params	= 0x80000100,
+	.atag_offset	= 0x100,
 	.reserve	= omap_reserve,
 	.map_io		= omap_h4_map_io,
 	.init_early	= omap_h4_init_early,
diff --git a/arch/arm/mach-omap2/board-igep0020.c b/arch/arm/mach-omap2/board-igep0020.c
index 35be778caf1..cfa2870df34 100644
--- a/arch/arm/mach-omap2/board-igep0020.c
+++ b/arch/arm/mach-omap2/board-igep0020.c
@@ -671,22 +671,34 @@ static void __init igep_init(void)
 	}
 }
 
+static const char *igep2_dt_compat[] = {
+	"ISEE,igep-v2",
+	NULL
+};
+
 MACHINE_START(IGEP0020, "IGEP v2 board")
-	.boot_params	= 0x80000100,
+	.atag_offset	= 0x100,
 	.reserve	= omap_reserve,
 	.map_io		= omap3_map_io,
 	.init_early	= igep_init_early,
 	.init_irq	= omap3_init_irq,
 	.init_machine	= igep_init,
 	.timer		= &omap3_timer,
+	.dt_compat	= igep2_dt_compat,
 MACHINE_END
 
+static const char *igep3_dt_compat[] = {
+	"ISEE,igep-v3",
+	NULL
+};
+
 MACHINE_START(IGEP0030, "IGEP OMAP3 module")
-	.boot_params	= 0x80000100,
+	.atag_offset	= 0x100,
 	.reserve	= omap_reserve,
 	.map_io		= omap3_map_io,
 	.init_early	= igep_init_early,
 	.init_irq	= omap3_init_irq,
 	.init_machine	= igep_init,
 	.timer		= &omap3_timer,
+	.dt_compat	= &igep3_dt_compat,
 MACHINE_END
diff --git a/arch/arm/mach-omap2/board-ldp.c b/arch/arm/mach-omap2/board-ldp.c
index 218764c9377..edf752bb24b 100644
--- a/arch/arm/mach-omap2/board-ldp.c
+++ b/arch/arm/mach-omap2/board-ldp.c
@@ -333,7 +333,7 @@ static void __init omap_ldp_init(void)
 }
 
 MACHINE_START(OMAP_LDP, "OMAP LDP board")
-	.boot_params	= 0x80000100,
+	.atag_offset	= 0x100,
 	.reserve	= omap_reserve,
 	.map_io		= omap3_map_io,
 	.init_early	= omap_ldp_init_early,
diff --git a/arch/arm/mach-omap2/board-n8x0.c b/arch/arm/mach-omap2/board-n8x0.c
index e11f0c5d608..6ce748154f2 100644
--- a/arch/arm/mach-omap2/board-n8x0.c
+++ b/arch/arm/mach-omap2/board-n8x0.c
@@ -695,7 +695,7 @@ static void __init n8x0_init_machine(void)
 }
 
 MACHINE_START(NOKIA_N800, "Nokia N800")
-	.boot_params	= 0x80000100,
+	.atag_offset	= 0x100,
 	.reserve	= omap_reserve,
 	.map_io		= n8x0_map_io,
 	.init_early	= n8x0_init_early,
@@ -705,7 +705,7 @@ MACHINE_START(NOKIA_N800, "Nokia N800")
 MACHINE_END
 
 MACHINE_START(NOKIA_N810, "Nokia N810")
-	.boot_params	= 0x80000100,
+	.atag_offset	= 0x100,
 	.reserve	= omap_reserve,
 	.map_io		= n8x0_map_io,
 	.init_early	= n8x0_init_early,
@@ -715,7 +715,7 @@ MACHINE_START(NOKIA_N810, "Nokia N810")
 MACHINE_END
 
 MACHINE_START(NOKIA_N810_WIMAX, "Nokia N810 WiMAX")
-	.boot_params	= 0x80000100,
+	.atag_offset	= 0x100,
 	.reserve	= omap_reserve,
 	.map_io		= n8x0_map_io,
 	.init_early	= n8x0_init_early,
diff --git a/arch/arm/mach-omap2/board-omap3beagle.c b/arch/arm/mach-omap2/board-omap3beagle.c
index 3ae16b4e3f5..d73ec628f83 100644
--- a/arch/arm/mach-omap2/board-omap3beagle.c
+++ b/arch/arm/mach-omap2/board-omap3beagle.c
@@ -555,13 +555,19 @@ static void __init omap3_beagle_init(void)
 	beagle_opp_init();
 }
 
+static const char *omap3_beagle_dt_match[] = {
+	"ti,omap3-beagle",
+	NULL
+};
+
 MACHINE_START(OMAP3_BEAGLE, "OMAP3 Beagle Board")
 	/* Maintainer: Syed Mohammed Khasim - http://beagleboard.org */
-	.boot_params	= 0x80000100,
+	.atag_offset	= 0x100,
 	.reserve	= omap_reserve,
 	.map_io		= omap3_map_io,
 	.init_early	= omap3_beagle_init_early,
 	.init_irq	= omap3_beagle_init_irq,
 	.init_machine	= omap3_beagle_init,
 	.timer		= &omap3_secure_timer,
+	.dt_compat	= omap3_beagle_dt_match,
 MACHINE_END
diff --git a/arch/arm/mach-omap2/board-omap3evm.c b/arch/arm/mach-omap2/board-omap3evm.c
index c452b3f3331..15c69a0c1ce 100644
--- a/arch/arm/mach-omap2/board-omap3evm.c
+++ b/arch/arm/mach-omap2/board-omap3evm.c
@@ -681,7 +681,7 @@ static void __init omap3_evm_init(void)
 
 MACHINE_START(OMAP3EVM, "OMAP3 EVM")
 	/* Maintainer: Syed Mohammed Khasim - Texas Instruments */
-	.boot_params	= 0x80000100,
+	.atag_offset	= 0x100,
 	.reserve	= omap_reserve,
 	.map_io		= omap3_map_io,
 	.init_early	= omap3_evm_init_early,
diff --git a/arch/arm/mach-omap2/board-omap3logic.c b/arch/arm/mach-omap2/board-omap3logic.c
index 703aeb5b8fd..01354a214ca 100644
--- a/arch/arm/mach-omap2/board-omap3logic.c
+++ b/arch/arm/mach-omap2/board-omap3logic.c
@@ -209,7 +209,7 @@ static void __init omap3logic_init(void)
 }
 
 MACHINE_START(OMAP3_TORPEDO, "Logic OMAP3 Torpedo board")
-	.boot_params	= 0x80000100,
+	.atag_offset	= 0x100,
 	.map_io		= omap3_map_io,
 	.init_early	= omap3logic_init_early,
 	.init_irq	= omap3_init_irq,
@@ -218,7 +218,7 @@ MACHINE_START(OMAP3_TORPEDO, "Logic OMAP3 Torpedo board")
 MACHINE_END
 
 MACHINE_START(OMAP3530_LV_SOM, "OMAP Logic 3530 LV SOM board")
-	.boot_params	= 0x80000100,
+	.atag_offset	= 0x100,
 	.map_io		= omap3_map_io,
 	.init_early	= omap3logic_init_early,
 	.init_irq	= omap3_init_irq,
diff --git a/arch/arm/mach-omap2/board-omap3pandora.c b/arch/arm/mach-omap2/board-omap3pandora.c
index 080d7bd6795..ace56938dd3 100644
--- a/arch/arm/mach-omap2/board-omap3pandora.c
+++ b/arch/arm/mach-omap2/board-omap3pandora.c
@@ -606,7 +606,7 @@ static void __init omap3pandora_init(void)
 }
 
 MACHINE_START(OMAP3_PANDORA, "Pandora Handheld Console")
-	.boot_params	= 0x80000100,
+	.atag_offset	= 0x100,
 	.reserve	= omap_reserve,
 	.map_io		= omap3_map_io,
 	.init_early	= omap3pandora_init_early,
diff --git a/arch/arm/mach-omap2/board-omap3stalker.c b/arch/arm/mach-omap2/board-omap3stalker.c
index 8e104980ea2..ba13e1d5d0a 100644
--- a/arch/arm/mach-omap2/board-omap3stalker.c
+++ b/arch/arm/mach-omap2/board-omap3stalker.c
@@ -494,7 +494,7 @@ static void __init omap3_stalker_init(void)
 
 MACHINE_START(SBC3530, "OMAP3 STALKER")
 	/* Maintainer: Jason Lam -lzg@ema-tech.com */
-	.boot_params		= 0x80000100,
+	.atag_offset		= 0x100,
 	.map_io			= omap3_map_io,
 	.init_early		= omap3_stalker_init_early,
 	.init_irq		= omap3_stalker_init_irq,
diff --git a/arch/arm/mach-omap2/board-omap3touchbook.c b/arch/arm/mach-omap2/board-omap3touchbook.c
index 852ea046405..49e4bd207cb 100644
--- a/arch/arm/mach-omap2/board-omap3touchbook.c
+++ b/arch/arm/mach-omap2/board-omap3touchbook.c
@@ -404,7 +404,7 @@ static void __init omap3_touchbook_init(void)
 
 MACHINE_START(TOUCHBOOK, "OMAP3 touchbook Board")
 	/* Maintainer: Gregoire Gentil - http://www.alwaysinnovating.com */
-	.boot_params	= 0x80000100,
+	.atag_offset	= 0x100,
 	.reserve	= omap_reserve,
 	.map_io		= omap3_map_io,
 	.init_early	= omap3_touchbook_init_early,
diff --git a/arch/arm/mach-omap2/board-omap4panda.c b/arch/arm/mach-omap2/board-omap4panda.c
index 9aaa9605766..124cf21a221 100644
--- a/arch/arm/mach-omap2/board-omap4panda.c
+++ b/arch/arm/mach-omap2/board-omap4panda.c
@@ -581,13 +581,19 @@ static void __init omap4_panda_map_io(void)
 	omap44xx_map_common_io();
 }
 
+static const char *omap4_panda_match[] = {
+	"ti,omap4-panda",
+	NULL,
+};
+
 MACHINE_START(OMAP4_PANDA, "OMAP4 Panda board")
 	/* Maintainer: David Anders - Texas Instruments Inc */
-	.boot_params	= 0x80000100,
+	.atag_offset	= 0x100,
 	.reserve	= omap_reserve,
 	.map_io		= omap4_panda_map_io,
 	.init_early	= omap4_panda_init_early,
 	.init_irq	= gic_init_irq,
 	.init_machine	= omap4_panda_init,
 	.timer		= &omap4_timer,
+	.dt_compat	= omap4_panda_match,
 MACHINE_END
diff --git a/arch/arm/mach-omap2/board-overo.c b/arch/arm/mach-omap2/board-overo.c
index f949a9954d7..0fccc7b0d38 100644
--- a/arch/arm/mach-omap2/board-overo.c
+++ b/arch/arm/mach-omap2/board-overo.c
@@ -560,12 +560,18 @@ static void __init overo_init(void)
 					"OVERO_GPIO_USBH_CPEN\n");
 }
 
+static const char *omap3_overo_dt_match[] = {
+	"gumstix,omap3-overo",
+	NULL
+};
+
 MACHINE_START(OVERO, "Gumstix Overo")
-	.boot_params	= 0x80000100,
+	.atag_offset	= 0x100,
 	.reserve	= omap_reserve,
 	.map_io		= omap3_map_io,
 	.init_early	= overo_init_early,
 	.init_irq	= omap3_init_irq,
 	.init_machine	= overo_init,
 	.timer		= &omap3_timer,
+	.dt_compat	= omap3_overo_dt_match,
 MACHINE_END
diff --git a/arch/arm/mach-omap2/board-rm680.c b/arch/arm/mach-omap2/board-rm680.c
index 7dfed24ee12..9a8ce239ba9 100644
--- a/arch/arm/mach-omap2/board-rm680.c
+++ b/arch/arm/mach-omap2/board-rm680.c
@@ -153,7 +153,7 @@ static void __init rm680_map_io(void)
 }
 
 MACHINE_START(NOKIA_RM680, "Nokia RM-680 board")
-	.boot_params	= 0x80000100,
+	.atag_offset	= 0x100,
 	.reserve	= omap_reserve,
 	.map_io		= rm680_map_io,
 	.init_early	= rm680_init_early,
diff --git a/arch/arm/mach-omap2/board-rx51.c b/arch/arm/mach-omap2/board-rx51.c
index 5ea142f9bc9..a6c473bbb3d 100644
--- a/arch/arm/mach-omap2/board-rx51.c
+++ b/arch/arm/mach-omap2/board-rx51.c
@@ -156,7 +156,7 @@ static void __init rx51_reserve(void)
 
 MACHINE_START(NOKIA_RX51, "Nokia RX-51 board")
 	/* Maintainer: Lauri Leukkunen <lauri.leukkunen@nokia.com> */
-	.boot_params	= 0x80000100,
+	.atag_offset	= 0x100,
 	.reserve	= rx51_reserve,
 	.map_io		= rx51_map_io,
 	.init_early	= rx51_init_early,
diff --git a/arch/arm/mach-omap2/board-ti8168evm.c b/arch/arm/mach-omap2/board-ti8168evm.c
index a85d5b0b11d..e41958acb6b 100644
--- a/arch/arm/mach-omap2/board-ti8168evm.c
+++ b/arch/arm/mach-omap2/board-ti8168evm.c
@@ -48,7 +48,7 @@ static void __init ti8168_evm_map_io(void)
 
 MACHINE_START(TI8168EVM, "ti8168evm")
 	/* Maintainer: Texas Instruments */
-	.boot_params	= 0x80000100,
+	.atag_offset	= 0x100,
 	.map_io		= ti8168_evm_map_io,
 	.init_early	= ti8168_init_early,
 	.init_irq	= ti816x_init_irq,
diff --git a/arch/arm/mach-omap2/board-zoom.c b/arch/arm/mach-omap2/board-zoom.c
index 8a98c3c303f..72f1db4863e 100644
--- a/arch/arm/mach-omap2/board-zoom.c
+++ b/arch/arm/mach-omap2/board-zoom.c
@@ -133,7 +133,7 @@ static void __init omap_zoom_init(void)
 }
 
 MACHINE_START(OMAP_ZOOM2, "OMAP Zoom2 board")
-	.boot_params	= 0x80000100,
+	.atag_offset	= 0x100,
 	.reserve	= omap_reserve,
 	.map_io		= omap3_map_io,
 	.init_early	= omap_zoom_init_early,
@@ -143,7 +143,7 @@ MACHINE_START(OMAP_ZOOM2, "OMAP Zoom2 board")
 MACHINE_END
 
 MACHINE_START(OMAP_ZOOM3, "OMAP Zoom3 board")
-	.boot_params	= 0x80000100,
+	.atag_offset	= 0x100,
 	.reserve	= omap_reserve,
 	.map_io		= omap3_map_io,
 	.init_early	= omap_zoom_init_early,
diff --git a/arch/arm/mach-omap2/io.c b/arch/arm/mach-omap2/io.c
index 2ce1ce6fb4d..d6d01cb7f28 100644
--- a/arch/arm/mach-omap2/io.c
+++ b/arch/arm/mach-omap2/io.c
@@ -16,7 +16,6 @@
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
-
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
@@ -250,6 +249,7 @@ static void __init _omap2_map_common_io(void)
 
 	omap2_check_revision();
 	omap_sram_init();
+	omap_init_consistent_dma_size();
 }
 
 #ifdef CONFIG_SOC_OMAP2420
diff --git a/arch/arm/mach-omap2/omap-smp.c b/arch/arm/mach-omap2/omap-smp.c
index ce65e9329c7..889464dc7b2 100644
--- a/arch/arm/mach-omap2/omap-smp.c
+++ b/arch/arm/mach-omap2/omap-smp.c
@@ -109,12 +109,10 @@ void __init smp_init_cpus(void)
 	ncores = scu_get_core_count(scu_base);
 
 	/* sanity check */
-	if (ncores > NR_CPUS) {
-		printk(KERN_WARNING
-		       "OMAP4: no. of cores (%d) greater than configured "
-		       "maximum of %d - clipping\n",
-		       ncores, NR_CPUS);
-		ncores = NR_CPUS;
+	if (ncores > nr_cpu_ids) {
+		pr_warn("SMP: %u cores greater than maximum (%u), clipping\n",
+			ncores, nr_cpu_ids);
+		ncores = nr_cpu_ids;
 	}
 
 	for (i = 0; i < ncores; i++)
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index 84cc0bdda3a..f396c83a30c 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -749,7 +749,7 @@ static int _count_mpu_irqs(struct omap_hwmod *oh)
 		ohii = &oh->mpu_irqs[i++];
 	} while (ohii->irq != -1);
 
-	return i;
+	return i-1;
 }
 
 /**
@@ -772,7 +772,7 @@ static int _count_sdma_reqs(struct omap_hwmod *oh)
 		ohdi = &oh->sdma_reqs[i++];
 	} while (ohdi->dma_req != -1);
 
-	return i;
+	return i-1;
 }
 
 /**
@@ -795,7 +795,7 @@ static int _count_ocp_if_addr_spaces(struct omap_hwmod_ocp_if *os)
 		mem = &os->addr[i++];
 	} while (mem->pa_start != mem->pa_end);
 
-	return i;
+	return i-1;
 }
 
 /**
diff --git a/arch/arm/mach-omap2/pm.c b/arch/arm/mach-omap2/pm.c
index 472bf22d5e8..95eb863f780 100644
--- a/arch/arm/mach-omap2/pm.c
+++ b/arch/arm/mach-omap2/pm.c
@@ -23,6 +23,7 @@
 #include "powerdomain.h"
 #include "clockdomain.h"
 #include "pm.h"
+#include "twl-common.h"
 
 static struct omap_device_pm_latency *pm_lats;
 
@@ -251,11 +252,8 @@ postcore_initcall(omap2_common_pm_init);
 
 static int __init omap2_common_pm_late_init(void)
 {
-	/* Init the OMAP TWL parameters */
-	omap3_twl_init();
-	omap4_twl_init();
-
 	/* Init the voltage layer */
+	omap_pmic_late_init();
 	omap_voltage_late_init();
 
 	/* Initialize the voltages */
diff --git a/arch/arm/mach-omap2/smartreflex.c b/arch/arm/mach-omap2/smartreflex.c
index 34c01a7de81..19ff0104374 100644
--- a/arch/arm/mach-omap2/smartreflex.c
+++ b/arch/arm/mach-omap2/smartreflex.c
@@ -137,7 +137,7 @@ static irqreturn_t sr_interrupt(int irq, void *data)
 		sr_write_reg(sr_info, ERRCONFIG_V1, status);
 	} else if (sr_info->ip_type == SR_TYPE_V2) {
 		/* Read the status bits */
-		sr_read_reg(sr_info, IRQSTATUS);
+		status = sr_read_reg(sr_info, IRQSTATUS);
 
 		/* Clear them by writing back */
 		sr_write_reg(sr_info, IRQSTATUS, status);
diff --git a/arch/arm/mach-omap2/twl-common.c b/arch/arm/mach-omap2/twl-common.c
index daa056ed873..47133fae60d 100644
--- a/arch/arm/mach-omap2/twl-common.c
+++ b/arch/arm/mach-omap2/twl-common.c
@@ -30,6 +30,7 @@
 #include <plat/usb.h>
 
 #include "twl-common.h"
+#include "pm.h"
 
 static struct i2c_board_info __initdata pmic_i2c_board_info = {
 	.addr		= 0x48,
@@ -48,6 +49,16 @@ void __init omap_pmic_init(int bus, u32 clkrate,
 	omap_register_i2c_bus(bus, clkrate, &pmic_i2c_board_info, 1);
 }
 
+void __init omap_pmic_late_init(void)
+{
+	/* Init the OMAP TWL parameters (if PMIC has been registerd) */
+	if (!pmic_i2c_board_info.irq)
+		return;
+
+	omap3_twl_init();
+	omap4_twl_init();
+}
+
 #if defined(CONFIG_ARCH_OMAP3)
 static struct twl4030_usb_data omap3_usb_pdata = {
 	.usb_mode	= T2_USB_MODE_ULPI,
diff --git a/arch/arm/mach-omap2/twl-common.h b/arch/arm/mach-omap2/twl-common.h
index 5e83a5bd37f..275dde8cb27 100644
--- a/arch/arm/mach-omap2/twl-common.h
+++ b/arch/arm/mach-omap2/twl-common.h
@@ -1,6 +1,8 @@
 #ifndef __OMAP_PMIC_COMMON__
 #define __OMAP_PMIC_COMMON__
 
+#include <plat/irqs.h>
+
 #define TWL_COMMON_PDATA_USB		(1 << 0)
 #define TWL_COMMON_PDATA_BCI		(1 << 1)
 #define TWL_COMMON_PDATA_MADC		(1 << 2)
@@ -30,6 +32,7 @@ struct twl4030_platform_data;
 
 void omap_pmic_init(int bus, u32 clkrate, const char *pmic_type, int pmic_irq,
 		    struct twl4030_platform_data *pmic_data);
+void omap_pmic_late_init(void);
 
 static inline void omap2_pmic_init(const char *pmic_type,
 				   struct twl4030_platform_data *pmic_data)
diff --git a/arch/arm/mach-orion5x/d2net-setup.c b/arch/arm/mach-orion5x/d2net-setup.c
index 19cf5bf99f1..8c8300951f4 100644
--- a/arch/arm/mach-orion5x/d2net-setup.c
+++ b/arch/arm/mach-orion5x/d2net-setup.c
@@ -336,7 +336,7 @@ static void __init d2net_init(void)
 
 #ifdef CONFIG_MACH_D2NET
 MACHINE_START(D2NET, "LaCie d2 Network")
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= d2net_init,
 	.map_io		= orion5x_map_io,
 	.init_early	= orion5x_init_early,
@@ -348,7 +348,7 @@ MACHINE_END
 
 #ifdef CONFIG_MACH_BIGDISK
 MACHINE_START(BIGDISK, "LaCie Big Disk Network")
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= d2net_init,
 	.map_io		= orion5x_map_io,
 	.init_early	= orion5x_init_early,
diff --git a/arch/arm/mach-orion5x/db88f5281-setup.c b/arch/arm/mach-orion5x/db88f5281-setup.c
index a3e3e9e5e32..88432aba972 100644
--- a/arch/arm/mach-orion5x/db88f5281-setup.c
+++ b/arch/arm/mach-orion5x/db88f5281-setup.c
@@ -359,7 +359,7 @@ static void __init db88f5281_init(void)
 
 MACHINE_START(DB88F5281, "Marvell Orion-2 Development Board")
 	/* Maintainer: Tzachi Perelstein <tzachi@marvell.com> */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= db88f5281_init,
 	.map_io		= orion5x_map_io,
 	.init_early	= orion5x_init_early,
diff --git a/arch/arm/mach-orion5x/dns323-setup.c b/arch/arm/mach-orion5x/dns323-setup.c
index c105556a0ee..9e5c1663fc4 100644
--- a/arch/arm/mach-orion5x/dns323-setup.c
+++ b/arch/arm/mach-orion5x/dns323-setup.c
@@ -730,7 +730,7 @@ static void __init dns323_init(void)
 /* Warning: D-Link uses a wrong mach-type (=526) in their bootloader */
 MACHINE_START(DNS323, "D-Link DNS-323")
 	/* Maintainer: Herbert Valerio Riedel <hvr@gnu.org> */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= dns323_init,
 	.map_io		= orion5x_map_io,
 	.init_early	= orion5x_init_early,
diff --git a/arch/arm/mach-orion5x/edmini_v2-setup.c b/arch/arm/mach-orion5x/edmini_v2-setup.c
index b67cff0d4cf..70a4e9265f0 100644
--- a/arch/arm/mach-orion5x/edmini_v2-setup.c
+++ b/arch/arm/mach-orion5x/edmini_v2-setup.c
@@ -251,7 +251,7 @@ static void __init edmini_v2_init(void)
 /* Warning: LaCie use a wrong mach-type (0x20e=526) in their bootloader. */
 MACHINE_START(EDMINI_V2, "LaCie Ethernet Disk mini V2")
 	/* Maintainer: Christopher Moore <moore@free.fr> */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= edmini_v2_init,
 	.map_io		= orion5x_map_io,
 	.init_early	= orion5x_init_early,
diff --git a/arch/arm/mach-orion5x/kurobox_pro-setup.c b/arch/arm/mach-orion5x/kurobox_pro-setup.c
index 00381249d76..9115511dc03 100644
--- a/arch/arm/mach-orion5x/kurobox_pro-setup.c
+++ b/arch/arm/mach-orion5x/kurobox_pro-setup.c
@@ -380,7 +380,7 @@ static void __init kurobox_pro_init(void)
 #ifdef CONFIG_MACH_KUROBOX_PRO
 MACHINE_START(KUROBOX_PRO, "Buffalo/Revogear Kurobox Pro")
 	/* Maintainer: Ronen Shitrit <rshitrit@marvell.com> */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= kurobox_pro_init,
 	.map_io		= orion5x_map_io,
 	.init_early	= orion5x_init_early,
@@ -393,7 +393,7 @@ MACHINE_END
 #ifdef CONFIG_MACH_LINKSTATION_PRO
 MACHINE_START(LINKSTATION_PRO, "Buffalo Linkstation Pro/Live")
 	/* Maintainer: Byron Bradley <byron.bbradley@gmail.com> */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= kurobox_pro_init,
 	.map_io		= orion5x_map_io,
 	.init_early	= orion5x_init_early,
diff --git a/arch/arm/mach-orion5x/ls-chl-setup.c b/arch/arm/mach-orion5x/ls-chl-setup.c
index 5065803ca82..9503fff404e 100644
--- a/arch/arm/mach-orion5x/ls-chl-setup.c
+++ b/arch/arm/mach-orion5x/ls-chl-setup.c
@@ -318,7 +318,7 @@ static void __init lschl_init(void)
 
 MACHINE_START(LINKSTATION_LSCHL, "Buffalo Linkstation LiveV3 (LS-CHL)")
 	/* Maintainer: Ash Hughes <ashley.hughes@blueyonder.co.uk> */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= lschl_init,
 	.map_io		= orion5x_map_io,
 	.init_early	= orion5x_init_early,
diff --git a/arch/arm/mach-orion5x/ls_hgl-setup.c b/arch/arm/mach-orion5x/ls_hgl-setup.c
index 8503d0a42d4..ed6d772f4a2 100644
--- a/arch/arm/mach-orion5x/ls_hgl-setup.c
+++ b/arch/arm/mach-orion5x/ls_hgl-setup.c
@@ -265,7 +265,7 @@ static void __init ls_hgl_init(void)
 
 MACHINE_START(LINKSTATION_LS_HGL, "Buffalo Linkstation LS-HGL")
 	/* Maintainer: Zhu Qingsen <zhuqs@cn.fujistu.com> */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= ls_hgl_init,
 	.map_io		= orion5x_map_io,
 	.init_early	= orion5x_init_early,
diff --git a/arch/arm/mach-orion5x/lsmini-setup.c b/arch/arm/mach-orion5x/lsmini-setup.c
index 9c82723c05c..743f7f1db18 100644
--- a/arch/arm/mach-orion5x/lsmini-setup.c
+++ b/arch/arm/mach-orion5x/lsmini-setup.c
@@ -267,7 +267,7 @@ static void __init lsmini_init(void)
 #ifdef CONFIG_MACH_LINKSTATION_MINI
 MACHINE_START(LINKSTATION_MINI, "Buffalo Linkstation Mini")
 	/* Maintainer: Alexey Kopytko <alexey@kopytko.ru> */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= lsmini_init,
 	.map_io		= orion5x_map_io,
 	.init_early	= orion5x_init_early,
diff --git a/arch/arm/mach-orion5x/mss2-setup.c b/arch/arm/mach-orion5x/mss2-setup.c
index ef3bb8e9a4c..6020e26b1c7 100644
--- a/arch/arm/mach-orion5x/mss2-setup.c
+++ b/arch/arm/mach-orion5x/mss2-setup.c
@@ -261,7 +261,7 @@ static void __init mss2_init(void)
 
 MACHINE_START(MSS2, "Maxtor Shared Storage II")
 	/* Maintainer: Sylver Bruneau <sylver.bruneau@googlemail.com> */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= mss2_init,
 	.map_io		= orion5x_map_io,
 	.init_early	= orion5x_init_early,
diff --git a/arch/arm/mach-orion5x/mv2120-setup.c b/arch/arm/mach-orion5x/mv2120-setup.c
index 63ff10c3c46..b3356ada64b 100644
--- a/arch/arm/mach-orion5x/mv2120-setup.c
+++ b/arch/arm/mach-orion5x/mv2120-setup.c
@@ -229,7 +229,7 @@ static void __init mv2120_init(void)
 /* Warning: HP uses a wrong mach-type (=526) in their bootloader */
 MACHINE_START(MV2120, "HP Media Vault mv2120")
 	/* Maintainer: Martin Michlmayr <tbm@cyrius.com> */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= mv2120_init,
 	.map_io		= orion5x_map_io,
 	.init_early	= orion5x_init_early,
diff --git a/arch/arm/mach-orion5x/net2big-setup.c b/arch/arm/mach-orion5x/net2big-setup.c
index e43b39cc7fe..6197c79a2ec 100644
--- a/arch/arm/mach-orion5x/net2big-setup.c
+++ b/arch/arm/mach-orion5x/net2big-setup.c
@@ -419,7 +419,7 @@ static void __init net2big_init(void)
 
 /* Warning: LaCie use a wrong mach-type (0x20e=526) in their bootloader. */
 MACHINE_START(NET2BIG, "LaCie 2Big Network")
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= net2big_init,
 	.map_io		= orion5x_map_io,
 	.init_early	= orion5x_init_early,
diff --git a/arch/arm/mach-orion5x/rd88f5181l-fxo-setup.c b/arch/arm/mach-orion5x/rd88f5181l-fxo-setup.c
index 291d22bf44c..8c876664f49 100644
--- a/arch/arm/mach-orion5x/rd88f5181l-fxo-setup.c
+++ b/arch/arm/mach-orion5x/rd88f5181l-fxo-setup.c
@@ -169,7 +169,7 @@ subsys_initcall(rd88f5181l_fxo_pci_init);
 
 MACHINE_START(RD88F5181L_FXO, "Marvell Orion-VoIP FXO Reference Design")
 	/* Maintainer: Nicolas Pitre <nico@marvell.com> */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= rd88f5181l_fxo_init,
 	.map_io		= orion5x_map_io,
 	.init_early	= orion5x_init_early,
diff --git a/arch/arm/mach-orion5x/rd88f5181l-ge-setup.c b/arch/arm/mach-orion5x/rd88f5181l-ge-setup.c
index 3f02362e163..994644f59d8 100644
--- a/arch/arm/mach-orion5x/rd88f5181l-ge-setup.c
+++ b/arch/arm/mach-orion5x/rd88f5181l-ge-setup.c
@@ -181,7 +181,7 @@ subsys_initcall(rd88f5181l_ge_pci_init);
 
 MACHINE_START(RD88F5181L_GE, "Marvell Orion-VoIP GE Reference Design")
 	/* Maintainer: Lennert Buytenhek <buytenh@marvell.com> */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= rd88f5181l_ge_init,
 	.map_io		= orion5x_map_io,
 	.init_early	= orion5x_init_early,
diff --git a/arch/arm/mach-orion5x/rd88f5182-setup.c b/arch/arm/mach-orion5x/rd88f5182-setup.c
index 27fd38e658b..1903d25ecae 100644
--- a/arch/arm/mach-orion5x/rd88f5182-setup.c
+++ b/arch/arm/mach-orion5x/rd88f5182-setup.c
@@ -306,7 +306,7 @@ static void __init rd88f5182_init(void)
 
 MACHINE_START(RD88F5182, "Marvell Orion-NAS Reference Design")
 	/* Maintainer: Ronen Shitrit <rshitrit@marvell.com> */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= rd88f5182_init,
 	.map_io		= orion5x_map_io,
 	.init_early	= orion5x_init_early,
diff --git a/arch/arm/mach-orion5x/rd88f6183ap-ge-setup.c b/arch/arm/mach-orion5x/rd88f6183ap-ge-setup.c
index ad2eba9286a..e06fdae77f0 100644
--- a/arch/arm/mach-orion5x/rd88f6183ap-ge-setup.c
+++ b/arch/arm/mach-orion5x/rd88f6183ap-ge-setup.c
@@ -122,7 +122,7 @@ subsys_initcall(rd88f6183ap_ge_pci_init);
 
 MACHINE_START(RD88F6183AP_GE, "Marvell Orion-1-90 AP GE Reference Design")
 	/* Maintainer: Lennert Buytenhek <buytenh@marvell.com> */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= rd88f6183ap_ge_init,
 	.map_io		= orion5x_map_io,
 	.init_early	= orion5x_init_early,
diff --git a/arch/arm/mach-orion5x/terastation_pro2-setup.c b/arch/arm/mach-orion5x/terastation_pro2-setup.c
index a34e4fac72b..306183273eb 100644
--- a/arch/arm/mach-orion5x/terastation_pro2-setup.c
+++ b/arch/arm/mach-orion5x/terastation_pro2-setup.c
@@ -358,7 +358,7 @@ static void __init tsp2_init(void)
 
 MACHINE_START(TERASTATION_PRO2, "Buffalo Terastation Pro II/Live")
 	/* Maintainer:  Sylver Bruneau <sylver.bruneau@googlemail.com> */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= tsp2_init,
 	.map_io		= orion5x_map_io,
 	.init_early	= orion5x_init_early,
diff --git a/arch/arm/mach-orion5x/ts209-setup.c b/arch/arm/mach-orion5x/ts209-setup.c
index c9831614e35..3dbcd5ed77e 100644
--- a/arch/arm/mach-orion5x/ts209-setup.c
+++ b/arch/arm/mach-orion5x/ts209-setup.c
@@ -323,7 +323,7 @@ static void __init qnap_ts209_init(void)
 
 MACHINE_START(TS209, "QNAP TS-109/TS-209")
 	/* Maintainer: Byron Bradley <byron.bbradley@gmail.com> */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= qnap_ts209_init,
 	.map_io		= orion5x_map_io,
 	.init_early	= orion5x_init_early,
diff --git a/arch/arm/mach-orion5x/ts409-setup.c b/arch/arm/mach-orion5x/ts409-setup.c
index cc33b2222ba..23c9e2e5e55 100644
--- a/arch/arm/mach-orion5x/ts409-setup.c
+++ b/arch/arm/mach-orion5x/ts409-setup.c
@@ -312,7 +312,7 @@ static void __init qnap_ts409_init(void)
 
 MACHINE_START(TS409, "QNAP TS-409")
 	/* Maintainer:  Sylver Bruneau <sylver.bruneau@gmail.com> */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= qnap_ts409_init,
 	.map_io		= orion5x_map_io,
 	.init_early	= orion5x_init_early,
diff --git a/arch/arm/mach-orion5x/ts78xx-setup.c b/arch/arm/mach-orion5x/ts78xx-setup.c
index 6b7b54116f3..6c75cd35c4c 100644
--- a/arch/arm/mach-orion5x/ts78xx-setup.c
+++ b/arch/arm/mach-orion5x/ts78xx-setup.c
@@ -621,7 +621,7 @@ static void __init ts78xx_init(void)
 
 MACHINE_START(TS78XX, "Technologic Systems TS-78xx SBC")
 	/* Maintainer: Alexander Clouter <alex@digriz.org.uk> */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= ts78xx_init,
 	.map_io		= ts78xx_map_io,
 	.init_early	= orion5x_init_early,
diff --git a/arch/arm/mach-orion5x/wnr854t-setup.c b/arch/arm/mach-orion5x/wnr854t-setup.c
index 2653595f901..1c63a76f3ca 100644
--- a/arch/arm/mach-orion5x/wnr854t-setup.c
+++ b/arch/arm/mach-orion5x/wnr854t-setup.c
@@ -173,7 +173,7 @@ subsys_initcall(wnr854t_pci_init);
 
 MACHINE_START(WNR854T, "Netgear WNR854T")
 	/* Maintainer: Imre Kaloz <kaloz@openwrt.org> */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= wnr854t_init,
 	.map_io		= orion5x_map_io,
 	.init_early	= orion5x_init_early,
diff --git a/arch/arm/mach-orion5x/wrt350n-v2-setup.c b/arch/arm/mach-orion5x/wrt350n-v2-setup.c
index 251ef1543e5..4fd9f18c9d5 100644
--- a/arch/arm/mach-orion5x/wrt350n-v2-setup.c
+++ b/arch/arm/mach-orion5x/wrt350n-v2-setup.c
@@ -261,7 +261,7 @@ subsys_initcall(wrt350n_v2_pci_init);
 
 MACHINE_START(WRT350N_V2, "Linksys WRT350N v2")
 	/* Maintainer: Lennert Buytenhek <buytenh@marvell.com> */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= wrt350n_v2_init,
 	.map_io		= orion5x_map_io,
 	.init_early	= orion5x_init_early,
diff --git a/arch/arm/mach-pnx4008/core.c b/arch/arm/mach-pnx4008/core.c
index 63399755f19..cdb95e726f5 100644
--- a/arch/arm/mach-pnx4008/core.c
+++ b/arch/arm/mach-pnx4008/core.c
@@ -264,7 +264,7 @@ extern struct sys_timer pnx4008_timer;
 
 MACHINE_START(PNX4008, "Philips PNX4008")
 	/* Maintainer: MontaVista Software Inc. */
-	.boot_params		= 0x80000100,
+	.atag_offset		= 0x100,
 	.map_io 		= pnx4008_map_io,
 	.init_irq 		= pnx4008_init_irq,
 	.init_machine 		= pnx4008_init,
diff --git a/arch/arm/mach-prima2/prima2.c b/arch/arm/mach-prima2/prima2.c
index f57124bdd14..5654a04319f 100644
--- a/arch/arm/mach-prima2/prima2.c
+++ b/arch/arm/mach-prima2/prima2.c
@@ -31,7 +31,7 @@ static const char *prima2cb_dt_match[] __initdata = {
 
 MACHINE_START(PRIMA2_EVB, "prima2cb")
 	/* Maintainer: Barry Song <baohua.song@csr.com> */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_early     = sirfsoc_of_clk_init,
 	.map_io         = sirfsoc_map_lluart,
 	.init_irq	= sirfsoc_of_irq_init,
diff --git a/arch/arm/mach-pxa/balloon3.c b/arch/arm/mach-pxa/balloon3.c
index ef3e8b1e06c..cb6cf16097f 100644
--- a/arch/arm/mach-pxa/balloon3.c
+++ b/arch/arm/mach-pxa/balloon3.c
@@ -307,7 +307,7 @@ static inline void balloon3_mmc_init(void) {}
 /******************************************************************************
  * USB Gadget
  ******************************************************************************/
-#if defined(CONFIG_USB_GADGET_PXA27X)||defined(CONFIG_USB_GADGET_PXA27X_MODULE)
+#if defined(CONFIG_USB_PXA27X)||defined(CONFIG_USB_PXA27X_MODULE)
 static void balloon3_udc_command(int cmd)
 {
 	if (cmd == PXA2XX_UDC_CMD_CONNECT)
@@ -828,5 +828,5 @@ MACHINE_START(BALLOON3, "Balloon3")
 	.handle_irq	= pxa27x_handle_irq,
 	.timer		= &pxa_timer,
 	.init_machine	= balloon3_init,
-	.boot_params	= PLAT_PHYS_OFFSET + 0x100,
+	.atag_offset	= 0x100,
 MACHINE_END
diff --git a/arch/arm/mach-pxa/capc7117.c b/arch/arm/mach-pxa/capc7117.c
index 648b0ab2bf7..4efc16d39c7 100644
--- a/arch/arm/mach-pxa/capc7117.c
+++ b/arch/arm/mach-pxa/capc7117.c
@@ -148,7 +148,7 @@ static void __init capc7117_init(void)
 
 MACHINE_START(CAPC7117,
 	      "Embedian CAPC-7117 evaluation kit based on the MXM-8x10 CoM")
-	.boot_params = 0xa0000100,
+	.atag_offset = 0x100,
 	.map_io = pxa3xx_map_io,
 	.init_irq = pxa3xx_init_irq,
 	.handle_irq = pxa3xx_handle_irq,
diff --git a/arch/arm/mach-pxa/cm-x2xx.c b/arch/arm/mach-pxa/cm-x2xx.c
index 13cf518bbbf..349896c53ab 100644
--- a/arch/arm/mach-pxa/cm-x2xx.c
+++ b/arch/arm/mach-pxa/cm-x2xx.c
@@ -513,7 +513,7 @@ static void __init cmx2xx_map_io(void)
 #endif
 
 MACHINE_START(ARMCORE, "Compulab CM-X2XX")
-	.boot_params	= 0xa0000100,
+	.atag_offset	= 0x100,
 	.map_io		= cmx2xx_map_io,
 	.nr_irqs	= CMX2XX_NR_IRQS,
 	.init_irq	= cmx2xx_init_irq,
diff --git a/arch/arm/mach-pxa/cm-x300.c b/arch/arm/mach-pxa/cm-x300.c
index b6a51340270..e40dc47cf2f 100644
--- a/arch/arm/mach-pxa/cm-x300.c
+++ b/arch/arm/mach-pxa/cm-x300.c
@@ -775,7 +775,6 @@ static struct gpio cm_x300_wi2wi_gpios[] __initdata = {
 
 static void __init cm_x300_init_wi2wi(void)
 {
-	int bt_reset, wlan_en;
 	int err;
 
 	if (system_rev < 130) {
@@ -791,12 +790,11 @@ static void __init cm_x300_init_wi2wi(void)
 	}
 
 	udelay(10);
-	gpio_set_value(bt_reset, 0);
+	gpio_set_value(cm_x300_wi2wi_gpios[1].gpio, 0);
 	udelay(10);
-	gpio_set_value(bt_reset, 1);
+	gpio_set_value(cm_x300_wi2wi_gpios[1].gpio, 1);
 
-	gpio_free(wlan_en);
-	gpio_free(bt_reset);
+	gpio_free_array(ARRAY_AND_SIZE(cm_x300_wi2wi_gpios));
 }
 
 /* MFP */
@@ -852,7 +850,7 @@ static void __init cm_x300_fixup(struct machine_desc *mdesc, struct tag *tags,
 }
 
 MACHINE_START(CM_X300, "CM-X300 module")
-	.boot_params	= 0xa0000100,
+	.atag_offset	= 0x100,
 	.map_io		= pxa3xx_map_io,
 	.init_irq	= pxa3xx_init_irq,
 	.handle_irq	= pxa3xx_handle_irq,
diff --git a/arch/arm/mach-pxa/colibri-pxa270.c b/arch/arm/mach-pxa/colibri-pxa270.c
index 870920934ec..7db66465716 100644
--- a/arch/arm/mach-pxa/colibri-pxa270.c
+++ b/arch/arm/mach-pxa/colibri-pxa270.c
@@ -306,7 +306,7 @@ static void __init colibri_pxa270_income_init(void)
 }
 
 MACHINE_START(COLIBRI, "Toradex Colibri PXA270")
-	.boot_params	= COLIBRI_SDRAM_BASE + 0x100,
+	.atag_offset	= 0x100,
 	.init_machine	= colibri_pxa270_init,
 	.map_io		= pxa27x_map_io,
 	.init_irq	= pxa27x_init_irq,
@@ -315,7 +315,7 @@ MACHINE_START(COLIBRI, "Toradex Colibri PXA270")
 MACHINE_END
 
 MACHINE_START(INCOME, "Income s.r.o. SH-Dmaster PXA270 SBC")
-	.boot_params	= 0xa0000100,
+	.atag_offset	= 0x100,
 	.init_machine	= colibri_pxa270_income_init,
 	.map_io		= pxa27x_map_io,
 	.init_irq	= pxa27x_init_irq,
diff --git a/arch/arm/mach-pxa/colibri-pxa300.c b/arch/arm/mach-pxa/colibri-pxa300.c
index 60a6781e7a8..c825e8bf2db 100644
--- a/arch/arm/mach-pxa/colibri-pxa300.c
+++ b/arch/arm/mach-pxa/colibri-pxa300.c
@@ -183,7 +183,7 @@ void __init colibri_pxa300_init(void)
 }
 
 MACHINE_START(COLIBRI300, "Toradex Colibri PXA300")
-	.boot_params	= COLIBRI_SDRAM_BASE + 0x100,
+	.atag_offset	= 0x100,
 	.init_machine	= colibri_pxa300_init,
 	.map_io		= pxa3xx_map_io,
 	.init_irq	= pxa3xx_init_irq,
diff --git a/arch/arm/mach-pxa/colibri-pxa320.c b/arch/arm/mach-pxa/colibri-pxa320.c
index d2c6631915d..d23b92b8048 100644
--- a/arch/arm/mach-pxa/colibri-pxa320.c
+++ b/arch/arm/mach-pxa/colibri-pxa320.c
@@ -146,7 +146,7 @@ static void __init colibri_pxa320_init_eth(void)
 static inline void __init colibri_pxa320_init_eth(void) {}
 #endif /* CONFIG_AX88796 */
 
-#if defined(CONFIG_USB_GADGET_PXA27X)||defined(CONFIG_USB_GADGET_PXA27X_MODULE)
+#if defined(CONFIG_USB_PXA27X)||defined(CONFIG_USB_PXA27X_MODULE)
 static struct gpio_vbus_mach_info colibri_pxa320_gpio_vbus_info = {
 	.gpio_vbus		= mfp_to_gpio(MFP_PIN_GPIO96),
 	.gpio_pullup		= -1,
@@ -253,7 +253,7 @@ void __init colibri_pxa320_init(void)
 }
 
 MACHINE_START(COLIBRI320, "Toradex Colibri PXA320")
-	.boot_params	= COLIBRI_SDRAM_BASE + 0x100,
+	.atag_offset	= 0x100,
 	.init_machine	= colibri_pxa320_init,
 	.map_io		= pxa3xx_map_io,
 	.init_irq	= pxa3xx_init_irq,
diff --git a/arch/arm/mach-pxa/csb726.c b/arch/arm/mach-pxa/csb726.c
index fe812eafb1f..5e2cf39e9e4 100644
--- a/arch/arm/mach-pxa/csb726.c
+++ b/arch/arm/mach-pxa/csb726.c
@@ -272,7 +272,7 @@ static void __init csb726_init(void)
 }
 
 MACHINE_START(CSB726, "Cogent CSB726")
-	.boot_params	= 0xa0000100,
+	.atag_offset	= 0x100,
 	.map_io         = pxa27x_map_io,
 	.init_irq       = pxa27x_init_irq,
 	.handle_irq       = pxa27x_handle_irq,
diff --git a/arch/arm/mach-pxa/em-x270.c b/arch/arm/mach-pxa/em-x270.c
index 2e37ea52b37..94acc0b01dd 100644
--- a/arch/arm/mach-pxa/em-x270.c
+++ b/arch/arm/mach-pxa/em-x270.c
@@ -1299,7 +1299,7 @@ static void __init em_x270_init(void)
 }
 
 MACHINE_START(EM_X270, "Compulab EM-X270")
-	.boot_params	= 0xa0000100,
+	.atag_offset	= 0x100,
 	.map_io		= pxa27x_map_io,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
@@ -1308,7 +1308,7 @@ MACHINE_START(EM_X270, "Compulab EM-X270")
 MACHINE_END
 
 MACHINE_START(EXEDA, "Compulab eXeda")
-	.boot_params	= 0xa0000100,
+	.atag_offset	= 0x100,
 	.map_io		= pxa27x_map_io,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
diff --git a/arch/arm/mach-pxa/eseries.c b/arch/arm/mach-pxa/eseries.c
index b4599ec9d61..e823c54057f 100644
--- a/arch/arm/mach-pxa/eseries.c
+++ b/arch/arm/mach-pxa/eseries.c
@@ -189,7 +189,7 @@ static void __init e330_init(void)
 
 MACHINE_START(E330, "Toshiba e330")
 	/* Maintainer: Ian Molton (spyro@f2s.com) */
-	.boot_params	= 0xa0000100,
+	.atag_offset	= 0x100,
 	.map_io		= pxa25x_map_io,
 	.nr_irqs	= ESERIES_NR_IRQS,
 	.init_irq	= pxa25x_init_irq,
@@ -239,7 +239,7 @@ static void __init e350_init(void)
 
 MACHINE_START(E350, "Toshiba e350")
 	/* Maintainer: Ian Molton (spyro@f2s.com) */
-	.boot_params	= 0xa0000100,
+	.atag_offset	= 0x100,
 	.map_io		= pxa25x_map_io,
 	.nr_irqs	= ESERIES_NR_IRQS,
 	.init_irq	= pxa25x_init_irq,
@@ -362,7 +362,7 @@ static void __init e400_init(void)
 
 MACHINE_START(E400, "Toshiba e400")
 	/* Maintainer: Ian Molton (spyro@f2s.com) */
-	.boot_params	= 0xa0000100,
+	.atag_offset	= 0x100,
 	.map_io		= pxa25x_map_io,
 	.nr_irqs	= ESERIES_NR_IRQS,
 	.init_irq	= pxa25x_init_irq,
@@ -551,7 +551,7 @@ static void __init e740_init(void)
 
 MACHINE_START(E740, "Toshiba e740")
 	/* Maintainer: Ian Molton (spyro@f2s.com) */
-	.boot_params	= 0xa0000100,
+	.atag_offset	= 0x100,
 	.map_io		= pxa25x_map_io,
 	.nr_irqs	= ESERIES_NR_IRQS,
 	.init_irq	= pxa25x_init_irq,
@@ -743,7 +743,7 @@ static void __init e750_init(void)
 
 MACHINE_START(E750, "Toshiba e750")
 	/* Maintainer: Ian Molton (spyro@f2s.com) */
-	.boot_params	= 0xa0000100,
+	.atag_offset	= 0x100,
 	.map_io		= pxa25x_map_io,
 	.nr_irqs	= ESERIES_NR_IRQS,
 	.init_irq	= pxa25x_init_irq,
@@ -948,7 +948,7 @@ static void __init e800_init(void)
 
 MACHINE_START(E800, "Toshiba e800")
 	/* Maintainer: Ian Molton (spyro@f2s.com) */
-	.boot_params	= 0xa0000100,
+	.atag_offset	= 0x100,
 	.map_io		= pxa25x_map_io,
 	.nr_irqs	= ESERIES_NR_IRQS,
 	.init_irq	= pxa25x_init_irq,
diff --git a/arch/arm/mach-pxa/ezx.c b/arch/arm/mach-pxa/ezx.c
index b73eadb9f5d..8308eee5a92 100644
--- a/arch/arm/mach-pxa/ezx.c
+++ b/arch/arm/mach-pxa/ezx.c
@@ -797,7 +797,7 @@ static void __init a780_init(void)
 }
 
 MACHINE_START(EZX_A780, "Motorola EZX A780")
-	.boot_params    = 0xa0000100,
+	.atag_offset    = 0x100,
 	.map_io         = pxa27x_map_io,
 	.nr_irqs	= EZX_NR_IRQS,
 	.init_irq       = pxa27x_init_irq,
@@ -863,7 +863,7 @@ static void __init e680_init(void)
 }
 
 MACHINE_START(EZX_E680, "Motorola EZX E680")
-	.boot_params    = 0xa0000100,
+	.atag_offset    = 0x100,
 	.map_io         = pxa27x_map_io,
 	.nr_irqs	= EZX_NR_IRQS,
 	.init_irq       = pxa27x_init_irq,
@@ -929,7 +929,7 @@ static void __init a1200_init(void)
 }
 
 MACHINE_START(EZX_A1200, "Motorola EZX A1200")
-	.boot_params    = 0xa0000100,
+	.atag_offset    = 0x100,
 	.map_io         = pxa27x_map_io,
 	.nr_irqs	= EZX_NR_IRQS,
 	.init_irq       = pxa27x_init_irq,
@@ -1120,7 +1120,7 @@ static void __init a910_init(void)
 }
 
 MACHINE_START(EZX_A910, "Motorola EZX A910")
-	.boot_params    = 0xa0000100,
+	.atag_offset    = 0x100,
 	.map_io         = pxa27x_map_io,
 	.nr_irqs	= EZX_NR_IRQS,
 	.init_irq       = pxa27x_init_irq,
@@ -1186,7 +1186,7 @@ static void __init e6_init(void)
 }
 
 MACHINE_START(EZX_E6, "Motorola EZX E6")
-	.boot_params    = 0xa0000100,
+	.atag_offset    = 0x100,
 	.map_io         = pxa27x_map_io,
 	.nr_irqs	= EZX_NR_IRQS,
 	.init_irq       = pxa27x_init_irq,
@@ -1226,7 +1226,7 @@ static void __init e2_init(void)
 }
 
 MACHINE_START(EZX_E2, "Motorola EZX E2")
-	.boot_params    = 0xa0000100,
+	.atag_offset    = 0x100,
 	.map_io         = pxa27x_map_io,
 	.nr_irqs	= EZX_NR_IRQS,
 	.init_irq       = pxa27x_init_irq,
diff --git a/arch/arm/mach-pxa/gumstix.c b/arch/arm/mach-pxa/gumstix.c
index deaa111c91f..ffdd70dad32 100644
--- a/arch/arm/mach-pxa/gumstix.c
+++ b/arch/arm/mach-pxa/gumstix.c
@@ -106,7 +106,7 @@ static void __init gumstix_mmc_init(void)
 }
 #endif
 
-#ifdef CONFIG_USB_GADGET_PXA25X
+#ifdef CONFIG_USB_PXA25X
 static struct gpio_vbus_mach_info gumstix_udc_info = {
 	.gpio_vbus		= GPIO_GUMSTIX_USB_GPIOn,
 	.gpio_pullup		= GPIO_GUMSTIX_USB_GPIOx,
@@ -233,7 +233,7 @@ static void __init gumstix_init(void)
 }
 
 MACHINE_START(GUMSTIX, "Gumstix")
-	.boot_params	= 0xa0000100, /* match u-boot bi_boot_params */
+	.atag_offset	= 0x100, /* match u-boot bi_boot_params */
 	.map_io		= pxa25x_map_io,
 	.init_irq	= pxa25x_init_irq,
 	.handle_irq	= pxa25x_handle_irq,
diff --git a/arch/arm/mach-pxa/h5000.c b/arch/arm/mach-pxa/h5000.c
index 0a235128914..4b5e110640b 100644
--- a/arch/arm/mach-pxa/h5000.c
+++ b/arch/arm/mach-pxa/h5000.c
@@ -203,7 +203,7 @@ static void __init h5000_init(void)
 }
 
 MACHINE_START(H5400, "HP iPAQ H5000")
-	.boot_params = 0xa0000100,
+	.atag_offset = 0x100,
 	.map_io = pxa25x_map_io,
 	.init_irq = pxa25x_init_irq,
 	.handle_irq = pxa25x_handle_irq,
diff --git a/arch/arm/mach-pxa/himalaya.c b/arch/arm/mach-pxa/himalaya.c
index a997d0ab287..f2c32457084 100644
--- a/arch/arm/mach-pxa/himalaya.c
+++ b/arch/arm/mach-pxa/himalaya.c
@@ -158,7 +158,7 @@ static void __init himalaya_init(void)
 
 
 MACHINE_START(HIMALAYA, "HTC Himalaya")
-	.boot_params = 0xa0000100,
+	.atag_offset = 0x100,
 	.map_io = pxa25x_map_io,
 	.init_irq = pxa25x_init_irq,
 	.handle_irq = pxa25x_handle_irq,
diff --git a/arch/arm/mach-pxa/hx4700.c b/arch/arm/mach-pxa/hx4700.c
index c748a473a2f..6f6368ece9b 100644
--- a/arch/arm/mach-pxa/hx4700.c
+++ b/arch/arm/mach-pxa/hx4700.c
@@ -838,7 +838,7 @@ static void __init hx4700_init(void)
 }
 
 MACHINE_START(H4700, "HP iPAQ HX4700")
-	.boot_params  = 0xa0000100,
+	.atag_offset  = 0x100,
 	.map_io       = pxa27x_map_io,
 	.nr_irqs      = HX4700_NR_IRQS,
 	.init_irq     = pxa27x_init_irq,
diff --git a/arch/arm/mach-pxa/icontrol.c b/arch/arm/mach-pxa/icontrol.c
index d427429f1f3..f78d5db758d 100644
--- a/arch/arm/mach-pxa/icontrol.c
+++ b/arch/arm/mach-pxa/icontrol.c
@@ -191,7 +191,7 @@ static void __init icontrol_init(void)
 }
 
 MACHINE_START(ICONTROL, "iControl/SafeTcam boards using Embedian MXM-8x10 CoM")
-	.boot_params	= 0xa0000100,
+	.atag_offset	= 0x100,
 	.map_io		= pxa3xx_map_io,
 	.init_irq	= pxa3xx_init_irq,
 	.handle_irq	= pxa3xx_handle_irq,
diff --git a/arch/arm/mach-pxa/include/mach/palm27x.h b/arch/arm/mach-pxa/include/mach/palm27x.h
index 0a5e5eadebf..8d560437e6e 100644
--- a/arch/arm/mach-pxa/include/mach/palm27x.h
+++ b/arch/arm/mach-pxa/include/mach/palm27x.h
@@ -37,8 +37,8 @@ extern void __init palm27x_lcd_init(int power,
 static inline void palm27x_lcd_init(int power, struct pxafb_mode_info *mode) {}
 #endif
 
-#if	defined(CONFIG_USB_GADGET_PXA27X) || \
-	defined(CONFIG_USB_GADGET_PXA27X_MODULE)
+#if	defined(CONFIG_USB_PXA27X) || \
+	defined(CONFIG_USB_PXA27X_MODULE)
 extern void __init palm27x_udc_init(int vbus, int pullup,
 					int vbus_inverted);
 #else
diff --git a/arch/arm/mach-pxa/littleton.c b/arch/arm/mach-pxa/littleton.c
index 8f97e15e86e..0037e57e0ce 100644
--- a/arch/arm/mach-pxa/littleton.c
+++ b/arch/arm/mach-pxa/littleton.c
@@ -437,7 +437,7 @@ static void __init littleton_init(void)
 }
 
 MACHINE_START(LITTLETON, "Marvell Form Factor Development Platform (aka Littleton)")
-	.boot_params	= 0xa0000100,
+	.atag_offset	= 0x100,
 	.map_io		= pxa3xx_map_io,
 	.nr_irqs	= LITTLETON_NR_IRQS,
 	.init_irq	= pxa3xx_init_irq,
diff --git a/arch/arm/mach-pxa/lpd270.c b/arch/arm/mach-pxa/lpd270.c
index c171d6ebee4..16df0fc0879 100644
--- a/arch/arm/mach-pxa/lpd270.c
+++ b/arch/arm/mach-pxa/lpd270.c
@@ -499,7 +499,7 @@ static void __init lpd270_map_io(void)
 
 MACHINE_START(LOGICPD_PXA270, "LogicPD PXA270 Card Engine")
 	/* Maintainer: Peter Barada */
-	.boot_params	= 0xa0000100,
+	.atag_offset	= 0x100,
 	.map_io		= lpd270_map_io,
 	.nr_irqs	= LPD270_NR_IRQS,
 	.init_irq	= lpd270_init_irq,
diff --git a/arch/arm/mach-pxa/magician.c b/arch/arm/mach-pxa/magician.c
index 5fe5bcd7c0a..4b796c37af3 100644
--- a/arch/arm/mach-pxa/magician.c
+++ b/arch/arm/mach-pxa/magician.c
@@ -753,7 +753,7 @@ static void __init magician_init(void)
 
 
 MACHINE_START(MAGICIAN, "HTC Magician")
-	.boot_params = 0xa0000100,
+	.atag_offset = 0x100,
 	.map_io = pxa27x_map_io,
 	.nr_irqs = MAGICIAN_NR_IRQS,
 	.init_irq = pxa27x_init_irq,
diff --git a/arch/arm/mach-pxa/mainstone.c b/arch/arm/mach-pxa/mainstone.c
index 4622eb78ef2..cc6e14f6d11 100644
--- a/arch/arm/mach-pxa/mainstone.c
+++ b/arch/arm/mach-pxa/mainstone.c
@@ -616,7 +616,7 @@ static void __init mainstone_map_io(void)
 
 MACHINE_START(MAINSTONE, "Intel HCDDBBVA0 Development Platform (aka Mainstone)")
 	/* Maintainer: MontaVista Software Inc. */
-	.boot_params	= 0xa0000100,	/* BLOB boot parameter setting */
+	.atag_offset	= 0x100,	/* BLOB boot parameter setting */
 	.map_io		= mainstone_map_io,
 	.nr_irqs	= MAINSTONE_NR_IRQS,
 	.init_irq	= mainstone_init_irq,
diff --git a/arch/arm/mach-pxa/mioa701.c b/arch/arm/mach-pxa/mioa701.c
index 64810f908e5..b938fc2c316 100644
--- a/arch/arm/mach-pxa/mioa701.c
+++ b/arch/arm/mach-pxa/mioa701.c
@@ -751,7 +751,7 @@ static void mioa701_machine_exit(void)
 }
 
 MACHINE_START(MIOA701, "MIO A701")
-	.boot_params	= 0xa0000100,
+	.atag_offset	= 0x100,
 	.map_io		= &pxa27x_map_io,
 	.init_irq	= &pxa27x_init_irq,
 	.handle_irq	= &pxa27x_handle_irq,
diff --git a/arch/arm/mach-pxa/mp900.c b/arch/arm/mach-pxa/mp900.c
index fb408861dbc..4af5d513c38 100644
--- a/arch/arm/mach-pxa/mp900.c
+++ b/arch/arm/mach-pxa/mp900.c
@@ -92,7 +92,7 @@ static void __init mp900c_init(void)
 
 /* Maintainer - Michael Petchkovsky <mkpetch@internode.on.net> */
 MACHINE_START(NEC_MP900, "MobilePro900/C")
-	.boot_params	= 0xa0220100,
+	.atag_offset	= 0x220100,
 	.timer		= &pxa_timer,
 	.map_io		= pxa25x_map_io,
 	.init_irq	= pxa25x_init_irq,
diff --git a/arch/arm/mach-pxa/palm27x.c b/arch/arm/mach-pxa/palm27x.c
index 325c245c0a0..fbc10d7b95d 100644
--- a/arch/arm/mach-pxa/palm27x.c
+++ b/arch/arm/mach-pxa/palm27x.c
@@ -164,8 +164,8 @@ void __init palm27x_lcd_init(int power, struct pxafb_mode_info *mode)
 /******************************************************************************
  * USB Gadget
  ******************************************************************************/
-#if	defined(CONFIG_USB_GADGET_PXA27X) || \
-	defined(CONFIG_USB_GADGET_PXA27X_MODULE)
+#if	defined(CONFIG_USB_PXA27X) || \
+	defined(CONFIG_USB_PXA27X_MODULE)
 static struct gpio_vbus_mach_info palm27x_udc_info = {
 	.gpio_vbus_inverted	= 1,
 };
diff --git a/arch/arm/mach-pxa/palmld.c b/arch/arm/mach-pxa/palmld.c
index 6b77365ed93..3d4a2819cae 100644
--- a/arch/arm/mach-pxa/palmld.c
+++ b/arch/arm/mach-pxa/palmld.c
@@ -342,7 +342,7 @@ static void __init palmld_init(void)
 }
 
 MACHINE_START(PALMLD, "Palm LifeDrive")
-	.boot_params	= 0xa0000100,
+	.atag_offset	= 0x100,
 	.map_io		= palmld_map_io,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
diff --git a/arch/arm/mach-pxa/palmt5.c b/arch/arm/mach-pxa/palmt5.c
index 9bd3e47486f..99d6bcf1f97 100644
--- a/arch/arm/mach-pxa/palmt5.c
+++ b/arch/arm/mach-pxa/palmt5.c
@@ -202,7 +202,7 @@ static void __init palmt5_init(void)
 }
 
 MACHINE_START(PALMT5, "Palm Tungsten|T5")
-	.boot_params	= 0xa0000100,
+	.atag_offset	= 0x100,
 	.map_io		= pxa27x_map_io,
 	.reserve	= palmt5_reserve,
 	.init_irq	= pxa27x_init_irq,
diff --git a/arch/arm/mach-pxa/palmtc.c b/arch/arm/mach-pxa/palmtc.c
index 6ad4a6c7bc9..2c24c67fd92 100644
--- a/arch/arm/mach-pxa/palmtc.c
+++ b/arch/arm/mach-pxa/palmtc.c
@@ -338,7 +338,7 @@ static inline void palmtc_mkp_init(void) {}
 /******************************************************************************
  * UDC
  ******************************************************************************/
-#if defined(CONFIG_USB_GADGET_PXA25X)||defined(CONFIG_USB_GADGET_PXA25X_MODULE)
+#if defined(CONFIG_USB_PXA25X)||defined(CONFIG_USB_PXA25X_MODULE)
 static struct gpio_vbus_mach_info palmtc_udc_info = {
 	.gpio_vbus		= GPIO_NR_PALMTC_USB_DETECT_N,
 	.gpio_vbus_inverted	= 1,
@@ -537,7 +537,7 @@ static void __init palmtc_init(void)
 };
 
 MACHINE_START(PALMTC, "Palm Tungsten|C")
-	.boot_params 	= 0xa0000100,
+	.atag_offset 	= 0x100,
 	.map_io		= pxa25x_map_io,
 	.init_irq	= pxa25x_init_irq,
 	.handle_irq	= pxa25x_handle_irq,
diff --git a/arch/arm/mach-pxa/palmte2.c b/arch/arm/mach-pxa/palmte2.c
index 664232f3e62..9376da06404 100644
--- a/arch/arm/mach-pxa/palmte2.c
+++ b/arch/arm/mach-pxa/palmte2.c
@@ -356,7 +356,7 @@ static void __init palmte2_init(void)
 }
 
 MACHINE_START(PALMTE2, "Palm Tungsten|E2")
-	.boot_params	= 0xa0000100,
+	.atag_offset	= 0x100,
 	.map_io		= pxa25x_map_io,
 	.init_irq	= pxa25x_init_irq,
 	.handle_irq	= pxa25x_handle_irq,
diff --git a/arch/arm/mach-pxa/palmtreo.c b/arch/arm/mach-pxa/palmtreo.c
index bb27d4b688d..7346fbfa810 100644
--- a/arch/arm/mach-pxa/palmtreo.c
+++ b/arch/arm/mach-pxa/palmtreo.c
@@ -440,7 +440,7 @@ static void __init centro_init(void)
 }
 
 MACHINE_START(TREO680, "Palm Treo 680")
-	.boot_params    = 0xa0000100,
+	.atag_offset    = 0x100,
 	.map_io         = pxa27x_map_io,
 	.reserve	= treo_reserve,
 	.init_irq       = pxa27x_init_irq,
@@ -450,7 +450,7 @@ MACHINE_START(TREO680, "Palm Treo 680")
 MACHINE_END
 
 MACHINE_START(CENTRO, "Palm Centro 685")
-	.boot_params    = 0xa0000100,
+	.atag_offset    = 0x100,
 	.map_io         = pxa27x_map_io,
 	.reserve	= treo_reserve,
 	.init_irq       = pxa27x_init_irq,
diff --git a/arch/arm/mach-pxa/palmtx.c b/arch/arm/mach-pxa/palmtx.c
index fc4285589c1..2b9e76fc2c9 100644
--- a/arch/arm/mach-pxa/palmtx.c
+++ b/arch/arm/mach-pxa/palmtx.c
@@ -364,7 +364,7 @@ static void __init palmtx_init(void)
 }
 
 MACHINE_START(PALMTX, "Palm T|X")
-	.boot_params	= 0xa0000100,
+	.atag_offset	= 0x100,
 	.map_io		= palmtx_map_io,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
diff --git a/arch/arm/mach-pxa/palmz72.c b/arch/arm/mach-pxa/palmz72.c
index e61c1cc0551..68e18baf8e0 100644
--- a/arch/arm/mach-pxa/palmz72.c
+++ b/arch/arm/mach-pxa/palmz72.c
@@ -399,7 +399,7 @@ static void __init palmz72_init(void)
 }
 
 MACHINE_START(PALMZ72, "Palm Zire72")
-	.boot_params	= 0xa0000100,
+	.atag_offset	= 0x100,
 	.map_io		= pxa27x_map_io,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
diff --git a/arch/arm/mach-pxa/pcm027.c b/arch/arm/mach-pxa/pcm027.c
index ffa65dfb8c6..0b825a35353 100644
--- a/arch/arm/mach-pxa/pcm027.c
+++ b/arch/arm/mach-pxa/pcm027.c
@@ -258,7 +258,7 @@ static void __init pcm027_map_io(void)
 
 MACHINE_START(PCM027, "Phytec Messtechnik GmbH phyCORE-PXA270")
 	/* Maintainer: Pengutronix */
-	.boot_params	= 0xa0000100,
+	.atag_offset	= 0x100,
 	.map_io		= pcm027_map_io,
 	.nr_irqs	= PCM027_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
diff --git a/arch/arm/mach-pxa/raumfeld.c b/arch/arm/mach-pxa/raumfeld.c
index bbcd90562eb..6810cddec92 100644
--- a/arch/arm/mach-pxa/raumfeld.c
+++ b/arch/arm/mach-pxa/raumfeld.c
@@ -1086,7 +1086,7 @@ static void __init raumfeld_speaker_init(void)
 
 #ifdef CONFIG_MACH_RAUMFELD_RC
 MACHINE_START(RAUMFELD_RC, "Raumfeld Controller")
-	.boot_params	= RAUMFELD_SDRAM_BASE + 0x100,
+	.atag_offset	= 0x100,
 	.init_machine	= raumfeld_controller_init,
 	.map_io		= pxa3xx_map_io,
 	.init_irq	= pxa3xx_init_irq,
@@ -1097,7 +1097,7 @@ MACHINE_END
 
 #ifdef CONFIG_MACH_RAUMFELD_CONNECTOR
 MACHINE_START(RAUMFELD_CONNECTOR, "Raumfeld Connector")
-	.boot_params	= RAUMFELD_SDRAM_BASE + 0x100,
+	.atag_offset	= 0x100,
 	.init_machine	= raumfeld_connector_init,
 	.map_io		= pxa3xx_map_io,
 	.init_irq	= pxa3xx_init_irq,
@@ -1108,7 +1108,7 @@ MACHINE_END
 
 #ifdef CONFIG_MACH_RAUMFELD_SPEAKER
 MACHINE_START(RAUMFELD_SPEAKER, "Raumfeld Speaker")
-	.boot_params	= RAUMFELD_SDRAM_BASE + 0x100,
+	.atag_offset	= 0x100,
 	.init_machine	= raumfeld_speaker_init,
 	.map_io		= pxa3xx_map_io,
 	.init_irq	= pxa3xx_init_irq,
diff --git a/arch/arm/mach-pxa/saar.c b/arch/arm/mach-pxa/saar.c
index df4356e8aca..602d70b50f8 100644
--- a/arch/arm/mach-pxa/saar.c
+++ b/arch/arm/mach-pxa/saar.c
@@ -596,7 +596,7 @@ static void __init saar_init(void)
 
 MACHINE_START(SAAR, "PXA930 Handheld Platform (aka SAAR)")
 	/* Maintainer: Eric Miao <eric.miao@marvell.com> */
-	.boot_params    = 0xa0000100,
+	.atag_offset    = 0x100,
 	.map_io         = pxa3xx_map_io,
 	.init_irq       = pxa3xx_init_irq,
 	.handle_irq       = pxa3xx_handle_irq,
diff --git a/arch/arm/mach-pxa/saarb.c b/arch/arm/mach-pxa/saarb.c
index ebd6379c496..5ce340320ab 100644
--- a/arch/arm/mach-pxa/saarb.c
+++ b/arch/arm/mach-pxa/saarb.c
@@ -103,7 +103,7 @@ static void __init saarb_init(void)
 }
 
 MACHINE_START(SAARB, "PXA955 Handheld Platform (aka SAARB)")
-	.boot_params    = 0xa0000100,
+	.atag_offset    = 0x100,
 	.map_io         = pxa3xx_map_io,
 	.nr_irqs	= SAARB_NR_IRQS,
 	.init_irq       = pxa95x_init_irq,
diff --git a/arch/arm/mach-pxa/stargate2.c b/arch/arm/mach-pxa/stargate2.c
index 3f8d0af9e2f..4c9a48bef56 100644
--- a/arch/arm/mach-pxa/stargate2.c
+++ b/arch/arm/mach-pxa/stargate2.c
@@ -1004,7 +1004,7 @@ MACHINE_START(INTELMOTE2, "IMOTE 2")
 	.handle_irq	= pxa27x_handle_irq,
 	.timer		= &pxa_timer,
 	.init_machine	= imote2_init,
-	.boot_params	= 0xA0000100,
+	.atag_offset	= 0x100,
 MACHINE_END
 #endif
 
@@ -1016,6 +1016,6 @@ MACHINE_START(STARGATE2, "Stargate 2")
 	.handle_irq = pxa27x_handle_irq,
 	.timer = &pxa_timer,
 	.init_machine = stargate2_init,
-	.boot_params = 0xA0000100,
+	.atag_offset = 0x100,
 MACHINE_END
 #endif
diff --git a/arch/arm/mach-pxa/tavorevb.c b/arch/arm/mach-pxa/tavorevb.c
index 32fb58e01b1..ad47bb98f30 100644
--- a/arch/arm/mach-pxa/tavorevb.c
+++ b/arch/arm/mach-pxa/tavorevb.c
@@ -489,7 +489,7 @@ static void __init tavorevb_init(void)
 
 MACHINE_START(TAVOREVB, "PXA930 Evaluation Board (aka TavorEVB)")
 	/* Maintainer: Eric Miao <eric.miao@marvell.com> */
-	.boot_params    = 0xa0000100,
+	.atag_offset    = 0x100,
 	.map_io         = pxa3xx_map_io,
 	.init_irq       = pxa3xx_init_irq,
 	.handle_irq       = pxa3xx_handle_irq,
diff --git a/arch/arm/mach-pxa/tavorevb3.c b/arch/arm/mach-pxa/tavorevb3.c
index fd5a8eae0a8..fd569167302 100644
--- a/arch/arm/mach-pxa/tavorevb3.c
+++ b/arch/arm/mach-pxa/tavorevb3.c
@@ -125,7 +125,7 @@ static void __init evb3_init(void)
 }
 
 MACHINE_START(TAVOREVB3, "PXA950 Evaluation Board (aka TavorEVB3)")
-	.boot_params	= 0xa0000100,
+	.atag_offset	= 0x100,
 	.map_io         = pxa3xx_map_io,
 	.nr_irqs	= TAVOREVB3_NR_IRQS,
 	.init_irq       = pxa3xx_init_irq,
diff --git a/arch/arm/mach-pxa/trizeps4.c b/arch/arm/mach-pxa/trizeps4.c
index c0417508f39..35bbf13724b 100644
--- a/arch/arm/mach-pxa/trizeps4.c
+++ b/arch/arm/mach-pxa/trizeps4.c
@@ -554,7 +554,7 @@ static void __init trizeps4_map_io(void)
 
 MACHINE_START(TRIZEPS4, "Keith und Koep Trizeps IV module")
 	/* MAINTAINER("Jürgen Schindele") */
-	.boot_params	= TRIZEPS4_SDRAM_BASE + 0x100,
+	.atag_offset	= 0x100,
 	.init_machine	= trizeps4_init,
 	.map_io		= trizeps4_map_io,
 	.init_irq	= pxa27x_init_irq,
@@ -564,7 +564,7 @@ MACHINE_END
 
 MACHINE_START(TRIZEPS4WL, "Keith und Koep Trizeps IV-WL module")
 	/* MAINTAINER("Jürgen Schindele") */
-	.boot_params	= TRIZEPS4_SDRAM_BASE + 0x100,
+	.atag_offset	= 0x100,
 	.init_machine	= trizeps4_init,
 	.map_io		= trizeps4_map_io,
 	.init_irq	= pxa27x_init_irq,
diff --git a/arch/arm/mach-pxa/viper.c b/arch/arm/mach-pxa/viper.c
index d4a3dc74e84..242ddae332d 100644
--- a/arch/arm/mach-pxa/viper.c
+++ b/arch/arm/mach-pxa/viper.c
@@ -992,7 +992,7 @@ static void __init viper_map_io(void)
 
 MACHINE_START(VIPER, "Arcom/Eurotech VIPER SBC")
 	/* Maintainer: Marc Zyngier <maz@misterjones.org> */
-	.boot_params	= 0xa0000100,
+	.atag_offset	= 0x100,
 	.map_io		= viper_map_io,
 	.init_irq	= viper_init_irq,
 	.handle_irq	= pxa25x_handle_irq,
diff --git a/arch/arm/mach-pxa/vpac270.c b/arch/arm/mach-pxa/vpac270.c
index 5f8490ab07c..ca0c6615028 100644
--- a/arch/arm/mach-pxa/vpac270.c
+++ b/arch/arm/mach-pxa/vpac270.c
@@ -343,7 +343,7 @@ static inline void vpac270_uhc_init(void) {}
 /******************************************************************************
  * USB Gadget
  ******************************************************************************/
-#if defined(CONFIG_USB_GADGET_PXA27X)||defined(CONFIG_USB_GADGET_PXA27X_MODULE)
+#if defined(CONFIG_USB_PXA27X)||defined(CONFIG_USB_PXA27X_MODULE)
 static struct gpio_vbus_mach_info vpac270_gpio_vbus_info = {
 	.gpio_vbus		= GPIO41_VPAC270_UDC_DETECT,
 	.gpio_pullup		= -1,
@@ -716,7 +716,7 @@ static void __init vpac270_init(void)
 }
 
 MACHINE_START(VPAC270, "Voipac PXA270")
-	.boot_params	= 0xa0000100,
+	.atag_offset	= 0x100,
 	.map_io		= pxa27x_map_io,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
diff --git a/arch/arm/mach-pxa/xcep.c b/arch/arm/mach-pxa/xcep.c
index acc600f5e72..54930cccbe5 100644
--- a/arch/arm/mach-pxa/xcep.c
+++ b/arch/arm/mach-pxa/xcep.c
@@ -180,7 +180,7 @@ static void __init xcep_init(void)
 }
 
 MACHINE_START(XCEP, "Iskratel XCEP")
-	.boot_params	= 0xa0000100,
+	.atag_offset	= 0x100,
 	.init_machine	= xcep_init,
 	.map_io		= pxa25x_map_io,
 	.init_irq	= pxa25x_init_irq,
diff --git a/arch/arm/mach-pxa/z2.c b/arch/arm/mach-pxa/z2.c
index 6c9275a20c9..65fed3753fa 100644
--- a/arch/arm/mach-pxa/z2.c
+++ b/arch/arm/mach-pxa/z2.c
@@ -718,7 +718,7 @@ static void __init z2_init(void)
 }
 
 MACHINE_START(ZIPIT2, "Zipit Z2")
-	.boot_params	= 0xa0000100,
+	.atag_offset	= 0x100,
 	.map_io		= pxa27x_map_io,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
diff --git a/arch/arm/mach-pxa/zeus.c b/arch/arm/mach-pxa/zeus.c
index 99c49bcd9f7..c424e7d85ce 100644
--- a/arch/arm/mach-pxa/zeus.c
+++ b/arch/arm/mach-pxa/zeus.c
@@ -904,7 +904,7 @@ static void __init zeus_map_io(void)
 
 MACHINE_START(ARCOM_ZEUS, "Arcom/Eurotech ZEUS")
 	/* Maintainer: Marc Zyngier <maz@misterjones.org> */
-	.boot_params	= 0xa0000100,
+	.atag_offset	= 0x100,
 	.map_io		= zeus_map_io,
 	.nr_irqs	= ZEUS_NR_IRQS,
 	.init_irq	= zeus_init_irq,
diff --git a/arch/arm/mach-pxa/zylonite.c b/arch/arm/mach-pxa/zylonite.c
index 15ec66b3471..31d49689189 100644
--- a/arch/arm/mach-pxa/zylonite.c
+++ b/arch/arm/mach-pxa/zylonite.c
@@ -422,7 +422,7 @@ static void __init zylonite_init(void)
 }
 
 MACHINE_START(ZYLONITE, "PXA3xx Platform Development Kit (aka Zylonite)")
-	.boot_params	= 0xa0000100,
+	.atag_offset	= 0x100,
 	.map_io		= pxa3xx_map_io,
 	.nr_irqs	= ZYLONITE_NR_IRQS,
 	.init_irq	= pxa3xx_init_irq,
diff --git a/arch/arm/mach-realview/platsmp.c b/arch/arm/mach-realview/platsmp.c
index 4ae943bafa9..e83c654a58d 100644
--- a/arch/arm/mach-realview/platsmp.c
+++ b/arch/arm/mach-realview/platsmp.c
@@ -52,12 +52,10 @@ void __init smp_init_cpus(void)
 	ncores = scu_base ? scu_get_core_count(scu_base) : 1;
 
 	/* sanity check */
-	if (ncores > NR_CPUS) {
-		printk(KERN_WARNING
-		       "Realview: no. of cores (%d) greater than configured "
-		       "maximum of %d - clipping\n",
-		       ncores, NR_CPUS);
-		ncores = NR_CPUS;
+	if (ncores > nr_cpu_ids) {
+		pr_warn("SMP: %u cores greater than maximum (%u), clipping\n",
+			ncores, nr_cpu_ids);
+		ncores = nr_cpu_ids;
 	}
 
 	for (i = 0; i < ncores; i++)
diff --git a/arch/arm/mach-realview/realview_eb.c b/arch/arm/mach-realview/realview_eb.c
index 7a4e3b18cb3..026c66ad7ec 100644
--- a/arch/arm/mach-realview/realview_eb.c
+++ b/arch/arm/mach-realview/realview_eb.c
@@ -463,7 +463,7 @@ static void __init realview_eb_init(void)
 
 MACHINE_START(REALVIEW_EB, "ARM-RealView EB")
 	/* Maintainer: ARM Ltd/Deep Blue Solutions Ltd */
-	.boot_params	= PLAT_PHYS_OFFSET + 0x00000100,
+	.atag_offset	= 0x100,
 	.fixup		= realview_fixup,
 	.map_io		= realview_eb_map_io,
 	.init_early	= realview_init_early,
diff --git a/arch/arm/mach-realview/realview_pb1176.c b/arch/arm/mach-realview/realview_pb1176.c
index ad5671acb66..7263dea7777 100644
--- a/arch/arm/mach-realview/realview_pb1176.c
+++ b/arch/arm/mach-realview/realview_pb1176.c
@@ -358,7 +358,7 @@ static void __init realview_pb1176_init(void)
 
 MACHINE_START(REALVIEW_PB1176, "ARM-RealView PB1176")
 	/* Maintainer: ARM Ltd/Deep Blue Solutions Ltd */
-	.boot_params	= PLAT_PHYS_OFFSET + 0x00000100,
+	.atag_offset	= 0x100,
 	.fixup		= realview_pb1176_fixup,
 	.map_io		= realview_pb1176_map_io,
 	.init_early	= realview_init_early,
diff --git a/arch/arm/mach-realview/realview_pb11mp.c b/arch/arm/mach-realview/realview_pb11mp.c
index b43644b3685..671ad6d6ff0 100644
--- a/arch/arm/mach-realview/realview_pb11mp.c
+++ b/arch/arm/mach-realview/realview_pb11mp.c
@@ -360,7 +360,7 @@ static void __init realview_pb11mp_init(void)
 
 MACHINE_START(REALVIEW_PB11MP, "ARM-RealView PB11MPCore")
 	/* Maintainer: ARM Ltd/Deep Blue Solutions Ltd */
-	.boot_params	= PLAT_PHYS_OFFSET + 0x00000100,
+	.atag_offset	= 0x100,
 	.fixup		= realview_fixup,
 	.map_io		= realview_pb11mp_map_io,
 	.init_early	= realview_init_early,
diff --git a/arch/arm/mach-realview/realview_pba8.c b/arch/arm/mach-realview/realview_pba8.c
index 763e8f38c15..cbf22df4ad5 100644
--- a/arch/arm/mach-realview/realview_pba8.c
+++ b/arch/arm/mach-realview/realview_pba8.c
@@ -310,7 +310,7 @@ static void __init realview_pba8_init(void)
 
 MACHINE_START(REALVIEW_PBA8, "ARM-RealView PB-A8")
 	/* Maintainer: ARM Ltd/Deep Blue Solutions Ltd */
-	.boot_params	= PLAT_PHYS_OFFSET + 0x00000100,
+	.atag_offset	= 0x100,
 	.fixup		= realview_fixup,
 	.map_io		= realview_pba8_map_io,
 	.init_early	= realview_init_early,
diff --git a/arch/arm/mach-realview/realview_pbx.c b/arch/arm/mach-realview/realview_pbx.c
index 363b0ab5615..8ec7e52618b 100644
--- a/arch/arm/mach-realview/realview_pbx.c
+++ b/arch/arm/mach-realview/realview_pbx.c
@@ -393,7 +393,7 @@ static void __init realview_pbx_init(void)
 
 MACHINE_START(REALVIEW_PBX, "ARM-RealView PBX")
 	/* Maintainer: ARM Ltd/Deep Blue Solutions Ltd */
-	.boot_params	= PLAT_PHYS_OFFSET + 0x00000100,
+	.atag_offset	= 0x100,
 	.fixup		= realview_pbx_fixup,
 	.map_io		= realview_pbx_map_io,
 	.init_early	= realview_init_early,
diff --git a/arch/arm/mach-rpc/riscpc.c b/arch/arm/mach-rpc/riscpc.c
index 580b3c73d2c..a9241eb8772 100644
--- a/arch/arm/mach-rpc/riscpc.c
+++ b/arch/arm/mach-rpc/riscpc.c
@@ -218,7 +218,7 @@ extern struct sys_timer ioc_timer;
 
 MACHINE_START(RISCPC, "Acorn-RiscPC")
 	/* Maintainer: Russell King */
-	.boot_params	= 0x10000100,
+	.atag_offset	= 0x100,
 	.reserve_lp0	= 1,
 	.reserve_lp1	= 1,
 	.map_io		= rpc_map_io,
diff --git a/arch/arm/mach-s3c2410/mach-amlm5900.c b/arch/arm/mach-s3c2410/mach-amlm5900.c
index dabc141243f..79838942b0a 100644
--- a/arch/arm/mach-s3c2410/mach-amlm5900.c
+++ b/arch/arm/mach-s3c2410/mach-amlm5900.c
@@ -236,7 +236,7 @@ static void __init amlm5900_init(void)
 }
 
 MACHINE_START(AML_M5900, "AML_M5900")
-	.boot_params	= S3C2410_SDRAM_PA + 0x100,
+	.atag_offset	= 0x100,
 	.map_io		= amlm5900_map_io,
 	.init_irq	= s3c24xx_init_irq,
 	.init_machine	= amlm5900_init,
diff --git a/arch/arm/mach-s3c2410/mach-bast.c b/arch/arm/mach-s3c2410/mach-bast.c
index 1e2d536adda..a20ae1ad406 100644
--- a/arch/arm/mach-s3c2410/mach-bast.c
+++ b/arch/arm/mach-s3c2410/mach-bast.c
@@ -657,7 +657,7 @@ static void __init bast_init(void)
 
 MACHINE_START(BAST, "Simtec-BAST")
 	/* Maintainer: Ben Dooks <ben@simtec.co.uk> */
-	.boot_params	= S3C2410_SDRAM_PA + 0x100,
+	.atag_offset	= 0x100,
 	.map_io		= bast_map_io,
 	.init_irq	= s3c24xx_init_irq,
 	.init_machine	= bast_init,
diff --git a/arch/arm/mach-s3c2410/mach-h1940.c b/arch/arm/mach-s3c2410/mach-h1940.c
index 2a2fa062013..556c535829f 100644
--- a/arch/arm/mach-s3c2410/mach-h1940.c
+++ b/arch/arm/mach-s3c2410/mach-h1940.c
@@ -744,7 +744,7 @@ static void __init h1940_init(void)
 
 MACHINE_START(H1940, "IPAQ-H1940")
 	/* Maintainer: Ben Dooks <ben-linux@fluff.org> */
-	.boot_params	= S3C2410_SDRAM_PA + 0x100,
+	.atag_offset	= 0x100,
 	.map_io		= h1940_map_io,
 	.reserve	= h1940_reserve,
 	.init_irq	= h1940_init_irq,
diff --git a/arch/arm/mach-s3c2410/mach-n30.c b/arch/arm/mach-s3c2410/mach-n30.c
index 079dcaa602d..1dc3e323441 100644
--- a/arch/arm/mach-s3c2410/mach-n30.c
+++ b/arch/arm/mach-s3c2410/mach-n30.c
@@ -586,7 +586,7 @@ MACHINE_START(N30, "Acer-N30")
 	/* Maintainer: Christer Weinigel <christer@weinigel.se>,
 				Ben Dooks <ben-linux@fluff.org>
 	*/
-	.boot_params	= S3C2410_SDRAM_PA + 0x100,
+	.atag_offset	= 0x100,
 	.timer		= &s3c24xx_timer,
 	.init_machine	= n30_init,
 	.init_irq	= s3c24xx_init_irq,
@@ -596,7 +596,7 @@ MACHINE_END
 MACHINE_START(N35, "Acer-N35")
 	/* Maintainer: Christer Weinigel <christer@weinigel.se>
 	*/
-	.boot_params	= S3C2410_SDRAM_PA + 0x100,
+	.atag_offset	= 0x100,
 	.timer		= &s3c24xx_timer,
 	.init_machine	= n30_init,
 	.init_irq	= s3c24xx_init_irq,
diff --git a/arch/arm/mach-s3c2410/mach-otom.c b/arch/arm/mach-s3c2410/mach-otom.c
index 0aa16cd5acb..f03f3fd9cec 100644
--- a/arch/arm/mach-s3c2410/mach-otom.c
+++ b/arch/arm/mach-s3c2410/mach-otom.c
@@ -116,7 +116,7 @@ static void __init otom11_init(void)
 
 MACHINE_START(OTOM, "Nex Vision - Otom 1.1")
 	/* Maintainer: Guillaume GOURAT <guillaume.gourat@nexvision.tv> */
-	.boot_params	= S3C2410_SDRAM_PA + 0x100,
+	.atag_offset	= 0x100,
 	.map_io		= otom11_map_io,
 	.init_machine	= otom11_init,
 	.init_irq	= s3c24xx_init_irq,
diff --git a/arch/arm/mach-s3c2410/mach-qt2410.c b/arch/arm/mach-s3c2410/mach-qt2410.c
index f44f77531b1..367d376deb9 100644
--- a/arch/arm/mach-s3c2410/mach-qt2410.c
+++ b/arch/arm/mach-s3c2410/mach-qt2410.c
@@ -344,7 +344,7 @@ static void __init qt2410_machine_init(void)
 }
 
 MACHINE_START(QT2410, "QT2410")
-	.boot_params	= S3C2410_SDRAM_PA + 0x100,
+	.atag_offset	= 0x100,
 	.map_io		= qt2410_map_io,
 	.init_irq	= s3c24xx_init_irq,
 	.init_machine	= qt2410_machine_init,
diff --git a/arch/arm/mach-s3c2410/mach-smdk2410.c b/arch/arm/mach-s3c2410/mach-smdk2410.c
index e17f03387ab..99c9dfdb71c 100644
--- a/arch/arm/mach-s3c2410/mach-smdk2410.c
+++ b/arch/arm/mach-s3c2410/mach-smdk2410.c
@@ -111,7 +111,7 @@ static void __init smdk2410_init(void)
 MACHINE_START(SMDK2410, "SMDK2410") /* @TODO: request a new identifier and switch
 				    * to SMDK2410 */
 	/* Maintainer: Jonas Dietsche */
-	.boot_params	= S3C2410_SDRAM_PA + 0x100,
+	.atag_offset	= 0x100,
 	.map_io		= smdk2410_map_io,
 	.init_irq	= s3c24xx_init_irq,
 	.init_machine	= smdk2410_init,
diff --git a/arch/arm/mach-s3c2410/mach-tct_hammer.c b/arch/arm/mach-s3c2410/mach-tct_hammer.c
index 43c2b831b9e..e0d0b6fb280 100644
--- a/arch/arm/mach-s3c2410/mach-tct_hammer.c
+++ b/arch/arm/mach-s3c2410/mach-tct_hammer.c
@@ -146,7 +146,7 @@ static void __init tct_hammer_init(void)
 }
 
 MACHINE_START(TCT_HAMMER, "TCT_HAMMER")
-	.boot_params	= S3C2410_SDRAM_PA + 0x100,
+	.atag_offset	= 0x100,
 	.map_io		= tct_hammer_map_io,
 	.init_irq	= s3c24xx_init_irq,
 	.init_machine	= tct_hammer_init,
diff --git a/arch/arm/mach-s3c2410/mach-vr1000.c b/arch/arm/mach-s3c2410/mach-vr1000.c
index 6ccce5a761b..df47e8e9006 100644
--- a/arch/arm/mach-s3c2410/mach-vr1000.c
+++ b/arch/arm/mach-s3c2410/mach-vr1000.c
@@ -400,7 +400,7 @@ static void __init vr1000_init(void)
 
 MACHINE_START(VR1000, "Thorcom-VR1000")
 	/* Maintainer: Ben Dooks <ben@simtec.co.uk> */
-	.boot_params	= S3C2410_SDRAM_PA + 0x100,
+	.atag_offset	= 0x100,
 	.map_io		= vr1000_map_io,
 	.init_machine	= vr1000_init,
 	.init_irq	= s3c24xx_init_irq,
diff --git a/arch/arm/mach-s3c2412/mach-jive.c b/arch/arm/mach-s3c2412/mach-jive.c
index 5eeb47580b0..286ef1738c6 100644
--- a/arch/arm/mach-s3c2412/mach-jive.c
+++ b/arch/arm/mach-s3c2412/mach-jive.c
@@ -655,7 +655,7 @@ static void __init jive_machine_init(void)
 
 MACHINE_START(JIVE, "JIVE")
 	/* Maintainer: Ben Dooks <ben-linux@fluff.org> */
-	.boot_params	= S3C2410_SDRAM_PA + 0x100,
+	.atag_offset	= 0x100,
 
 	.init_irq	= s3c24xx_init_irq,
 	.map_io		= jive_map_io,
diff --git a/arch/arm/mach-s3c2412/mach-smdk2413.c b/arch/arm/mach-s3c2412/mach-smdk2413.c
index 834cfb61bcf..d6325ede9f2 100644
--- a/arch/arm/mach-s3c2412/mach-smdk2413.c
+++ b/arch/arm/mach-s3c2412/mach-smdk2413.c
@@ -128,7 +128,7 @@ static void __init smdk2413_machine_init(void)
 
 MACHINE_START(S3C2413, "S3C2413")
 	/* Maintainer: Ben Dooks <ben-linux@fluff.org> */
-	.boot_params	= S3C2410_SDRAM_PA + 0x100,
+	.atag_offset	= 0x100,
 
 	.fixup		= smdk2413_fixup,
 	.init_irq	= s3c24xx_init_irq,
@@ -139,7 +139,7 @@ MACHINE_END
 
 MACHINE_START(SMDK2412, "SMDK2412")
 	/* Maintainer: Ben Dooks <ben-linux@fluff.org> */
-	.boot_params	= S3C2410_SDRAM_PA + 0x100,
+	.atag_offset	= 0x100,
 
 	.fixup		= smdk2413_fixup,
 	.init_irq	= s3c24xx_init_irq,
@@ -150,7 +150,7 @@ MACHINE_END
 
 MACHINE_START(SMDK2413, "SMDK2413")
 	/* Maintainer: Ben Dooks <ben-linux@fluff.org> */
-	.boot_params	= S3C2410_SDRAM_PA + 0x100,
+	.atag_offset	= 0x100,
 
 	.fixup		= smdk2413_fixup,
 	.init_irq	= s3c24xx_init_irq,
diff --git a/arch/arm/mach-s3c2412/mach-vstms.c b/arch/arm/mach-s3c2412/mach-vstms.c
index 83544ebe20a..5955c15018b 100644
--- a/arch/arm/mach-s3c2412/mach-vstms.c
+++ b/arch/arm/mach-s3c2412/mach-vstms.c
@@ -156,7 +156,7 @@ static void __init vstms_init(void)
 }
 
 MACHINE_START(VSTMS, "VSTMS")
-	.boot_params	= S3C2410_SDRAM_PA + 0x100,
+	.atag_offset	= 0x100,
 
 	.fixup		= vstms_fixup,
 	.init_irq	= s3c24xx_init_irq,
diff --git a/arch/arm/mach-s3c2416/mach-smdk2416.c b/arch/arm/mach-s3c2416/mach-smdk2416.c
index ac27ebb31c9..a9eee531ca7 100644
--- a/arch/arm/mach-s3c2416/mach-smdk2416.c
+++ b/arch/arm/mach-s3c2416/mach-smdk2416.c
@@ -245,7 +245,7 @@ static void __init smdk2416_machine_init(void)
 
 MACHINE_START(SMDK2416, "SMDK2416")
 	/* Maintainer: Yauhen Kharuzhy <jekhor@gmail.com> */
-	.boot_params	= S3C2410_SDRAM_PA + 0x100,
+	.atag_offset	= 0x100,
 
 	.init_irq	= s3c24xx_init_irq,
 	.map_io		= smdk2416_map_io,
diff --git a/arch/arm/mach-s3c2440/mach-anubis.c b/arch/arm/mach-s3c2440/mach-anubis.c
index d7086788b1f..74f92fc3fd0 100644
--- a/arch/arm/mach-s3c2440/mach-anubis.c
+++ b/arch/arm/mach-s3c2440/mach-anubis.c
@@ -498,7 +498,7 @@ static void __init anubis_init(void)
 
 MACHINE_START(ANUBIS, "Simtec-Anubis")
 	/* Maintainer: Ben Dooks <ben@simtec.co.uk> */
-	.boot_params	= S3C2410_SDRAM_PA + 0x100,
+	.atag_offset	= 0x100,
 	.map_io		= anubis_map_io,
 	.init_machine	= anubis_init,
 	.init_irq	= s3c24xx_init_irq,
diff --git a/arch/arm/mach-s3c2440/mach-at2440evb.c b/arch/arm/mach-s3c2440/mach-at2440evb.c
index 6c98b789b8c..38887ee0c78 100644
--- a/arch/arm/mach-s3c2440/mach-at2440evb.c
+++ b/arch/arm/mach-s3c2440/mach-at2440evb.c
@@ -233,7 +233,7 @@ static void __init at2440evb_init(void)
 
 
 MACHINE_START(AT2440EVB, "AT2440EVB")
-	.boot_params	= S3C2410_SDRAM_PA + 0x100,
+	.atag_offset	= 0x100,
 	.map_io		= at2440evb_map_io,
 	.init_machine	= at2440evb_init,
 	.init_irq	= s3c24xx_init_irq,
diff --git a/arch/arm/mach-s3c2440/mach-gta02.c b/arch/arm/mach-s3c2440/mach-gta02.c
index c10ddf4ed7f..de1e0ff46ce 100644
--- a/arch/arm/mach-s3c2440/mach-gta02.c
+++ b/arch/arm/mach-s3c2440/mach-gta02.c
@@ -595,7 +595,7 @@ static void __init gta02_machine_init(void)
 
 MACHINE_START(NEO1973_GTA02, "GTA02")
 	/* Maintainer: Nelson Castillo <arhuaco@freaks-unidos.net> */
-	.boot_params	= S3C2410_SDRAM_PA + 0x100,
+	.atag_offset	= 0x100,
 	.map_io		= gta02_map_io,
 	.init_irq	= s3c24xx_init_irq,
 	.init_machine	= gta02_machine_init,
diff --git a/arch/arm/mach-s3c2440/mach-mini2440.c b/arch/arm/mach-s3c2440/mach-mini2440.c
index fc2dc0b3d4f..91fe0b4c95f 100644
--- a/arch/arm/mach-s3c2440/mach-mini2440.c
+++ b/arch/arm/mach-s3c2440/mach-mini2440.c
@@ -676,7 +676,7 @@ static void __init mini2440_init(void)
 
 MACHINE_START(MINI2440, "MINI2440")
 	/* Maintainer: Michel Pollet <buserror@gmail.com> */
-	.boot_params	= S3C2410_SDRAM_PA + 0x100,
+	.atag_offset	= 0x100,
 	.map_io		= mini2440_map_io,
 	.init_machine	= mini2440_init,
 	.init_irq	= s3c24xx_init_irq,
diff --git a/arch/arm/mach-s3c2440/mach-nexcoder.c b/arch/arm/mach-s3c2440/mach-nexcoder.c
index 37dd306fb7d..61c0bf14816 100644
--- a/arch/arm/mach-s3c2440/mach-nexcoder.c
+++ b/arch/arm/mach-s3c2440/mach-nexcoder.c
@@ -151,7 +151,7 @@ static void __init nexcoder_init(void)
 
 MACHINE_START(NEXCODER_2440, "NexVision - Nexcoder 2440")
 	/* Maintainer: Guillaume GOURAT <guillaume.gourat@nexvision.tv> */
-	.boot_params	= S3C2410_SDRAM_PA + 0x100,
+	.atag_offset	= 0x100,
 	.map_io		= nexcoder_map_io,
 	.init_machine	= nexcoder_init,
 	.init_irq	= s3c24xx_init_irq,
diff --git a/arch/arm/mach-s3c2440/mach-osiris.c b/arch/arm/mach-s3c2440/mach-osiris.c
index d8853639331..dc142ebf8cb 100644
--- a/arch/arm/mach-s3c2440/mach-osiris.c
+++ b/arch/arm/mach-s3c2440/mach-osiris.c
@@ -447,7 +447,7 @@ static void __init osiris_init(void)
 
 MACHINE_START(OSIRIS, "Simtec-OSIRIS")
 	/* Maintainer: Ben Dooks <ben@simtec.co.uk> */
-	.boot_params	= S3C2410_SDRAM_PA + 0x100,
+	.atag_offset	= 0x100,
 	.map_io		= osiris_map_io,
 	.init_irq	= s3c24xx_init_irq,
 	.init_machine	= osiris_init,
diff --git a/arch/arm/mach-s3c2440/mach-rx1950.c b/arch/arm/mach-s3c2440/mach-rx1950.c
index 27ea95096fe..684dbb3567f 100644
--- a/arch/arm/mach-s3c2440/mach-rx1950.c
+++ b/arch/arm/mach-s3c2440/mach-rx1950.c
@@ -825,7 +825,7 @@ static void __init rx1950_reserve(void)
 
 MACHINE_START(RX1950, "HP iPAQ RX1950")
     /* Maintainers: Vasily Khoruzhick */
-	.boot_params = S3C2410_SDRAM_PA + 0x100,
+	.atag_offset = 0x100,
 	.map_io = rx1950_map_io,
 	.reserve	= rx1950_reserve,
 	.init_irq = s3c24xx_init_irq,
diff --git a/arch/arm/mach-s3c2440/mach-rx3715.c b/arch/arm/mach-s3c2440/mach-rx3715.c
index 1472b1a5b2f..e19499c2f90 100644
--- a/arch/arm/mach-s3c2440/mach-rx3715.c
+++ b/arch/arm/mach-s3c2440/mach-rx3715.c
@@ -218,7 +218,7 @@ static void __init rx3715_init_machine(void)
 
 MACHINE_START(RX3715, "IPAQ-RX3715")
 	/* Maintainer: Ben Dooks <ben-linux@fluff.org> */
-	.boot_params	= S3C2410_SDRAM_PA + 0x100,
+	.atag_offset	= 0x100,
 	.map_io		= rx3715_map_io,
 	.reserve	= rx3715_reserve,
 	.init_irq	= rx3715_init_irq,
diff --git a/arch/arm/mach-s3c2440/mach-smdk2440.c b/arch/arm/mach-s3c2440/mach-smdk2440.c
index eedfe0f1164..36eeb4197a8 100644
--- a/arch/arm/mach-s3c2440/mach-smdk2440.c
+++ b/arch/arm/mach-s3c2440/mach-smdk2440.c
@@ -175,7 +175,7 @@ static void __init smdk2440_machine_init(void)
 
 MACHINE_START(S3C2440, "SMDK2440")
 	/* Maintainer: Ben Dooks <ben-linux@fluff.org> */
-	.boot_params	= S3C2410_SDRAM_PA + 0x100,
+	.atag_offset	= 0x100,
 
 	.init_irq	= s3c24xx_init_irq,
 	.map_io		= smdk2440_map_io,
diff --git a/arch/arm/mach-s3c2443/mach-smdk2443.c b/arch/arm/mach-s3c2443/mach-smdk2443.c
index 514275e43ca..bec107e0044 100644
--- a/arch/arm/mach-s3c2443/mach-smdk2443.c
+++ b/arch/arm/mach-s3c2443/mach-smdk2443.c
@@ -139,7 +139,7 @@ static void __init smdk2443_machine_init(void)
 
 MACHINE_START(SMDK2443, "SMDK2443")
 	/* Maintainer: Ben Dooks <ben-linux@fluff.org> */
-	.boot_params	= S3C2410_SDRAM_PA + 0x100,
+	.atag_offset	= 0x100,
 
 	.init_irq	= s3c24xx_init_irq,
 	.map_io		= smdk2443_map_io,
diff --git a/arch/arm/mach-s3c64xx/cpu.c b/arch/arm/mach-s3c64xx/cpu.c
index 374e45e566b..8dc05763a7e 100644
--- a/arch/arm/mach-s3c64xx/cpu.c
+++ b/arch/arm/mach-s3c64xx/cpu.c
@@ -20,6 +20,7 @@
 #include <linux/serial_core.h>
 #include <linux/platform_device.h>
 #include <linux/io.h>
+#include <linux/dma-mapping.h>
 
 #include <mach/hardware.h>
 #include <mach/map.h>
@@ -145,6 +146,7 @@ void __init s3c64xx_init_io(struct map_desc *mach_desc, int size)
 	/* initialise the io descriptors we need for initialisation */
 	iotable_init(s3c_iodesc, ARRAY_SIZE(s3c_iodesc));
 	iotable_init(mach_desc, size);
+	init_consistent_dma_size(SZ_8M);
 
 	idcode = __raw_readl(S3C_VA_SYS + 0x118);
 	if (!idcode) {
diff --git a/arch/arm/mach-s3c64xx/include/mach/memory.h b/arch/arm/mach-s3c64xx/include/mach/memory.h
index 4760cdae1eb..b704669f95f 100644
--- a/arch/arm/mach-s3c64xx/include/mach/memory.h
+++ b/arch/arm/mach-s3c64xx/include/mach/memory.h
@@ -15,6 +15,4 @@
 
 #define PLAT_PHYS_OFFSET     UL(0x50000000)
 
-#define CONSISTENT_DMA_SIZE	SZ_8M
-
 #endif
diff --git a/arch/arm/mach-s3c64xx/mach-anw6410.c b/arch/arm/mach-s3c64xx/mach-anw6410.c
index cb8864327ac..d164a282bfb 100644
--- a/arch/arm/mach-s3c64xx/mach-anw6410.c
+++ b/arch/arm/mach-s3c64xx/mach-anw6410.c
@@ -233,7 +233,7 @@ static void __init anw6410_machine_init(void)
 
 MACHINE_START(ANW6410, "A&W6410")
 	/* Maintainer: Kwangwoo Lee <kwangwoo.lee@gmail.com> */
-	.boot_params	= S3C64XX_PA_SDRAM + 0x100,
+	.atag_offset	= 0x100,
 
 	.init_irq	= s3c6410_init_irq,
 	.map_io		= anw6410_map_io,
diff --git a/arch/arm/mach-s3c64xx/mach-crag6410.c b/arch/arm/mach-s3c64xx/mach-crag6410.c
index af0c2fe1ea3..4c76e08423f 100644
--- a/arch/arm/mach-s3c64xx/mach-crag6410.c
+++ b/arch/arm/mach-s3c64xx/mach-crag6410.c
@@ -766,7 +766,7 @@ static void __init crag6410_machine_init(void)
 
 MACHINE_START(WLF_CRAGG_6410, "Wolfson Cragganmore 6410")
 	/* Maintainer: Mark Brown <broonie@opensource.wolfsonmicro.com> */
-	.boot_params	= S3C64XX_PA_SDRAM + 0x100,
+	.atag_offset	= 0x100,
 	.init_irq	= s3c6410_init_irq,
 	.map_io		= crag6410_map_io,
 	.init_machine	= crag6410_machine_init,
diff --git a/arch/arm/mach-s3c64xx/mach-hmt.c b/arch/arm/mach-s3c64xx/mach-hmt.c
index b3d93cc8dde..19a0887e1c1 100644
--- a/arch/arm/mach-s3c64xx/mach-hmt.c
+++ b/arch/arm/mach-s3c64xx/mach-hmt.c
@@ -265,7 +265,7 @@ static void __init hmt_machine_init(void)
 
 MACHINE_START(HMT, "Airgoo-HMT")
 	/* Maintainer: Peter Korsgaard <jacmet@sunsite.dk> */
-	.boot_params	= S3C64XX_PA_SDRAM + 0x100,
+	.atag_offset	= 0x100,
 	.init_irq	= s3c6410_init_irq,
 	.map_io		= hmt_map_io,
 	.init_machine	= hmt_machine_init,
diff --git a/arch/arm/mach-s3c64xx/mach-mini6410.c b/arch/arm/mach-s3c64xx/mach-mini6410.c
index 527f49bd1b5..e91f63f7a49 100644
--- a/arch/arm/mach-s3c64xx/mach-mini6410.c
+++ b/arch/arm/mach-s3c64xx/mach-mini6410.c
@@ -349,7 +349,7 @@ static void __init mini6410_machine_init(void)
 
 MACHINE_START(MINI6410, "MINI6410")
 	/* Maintainer: Darius Augulis <augulis.darius@gmail.com> */
-	.boot_params	= S3C64XX_PA_SDRAM + 0x100,
+	.atag_offset	= 0x100,
 	.init_irq	= s3c6410_init_irq,
 	.map_io		= mini6410_map_io,
 	.init_machine	= mini6410_machine_init,
diff --git a/arch/arm/mach-s3c64xx/mach-ncp.c b/arch/arm/mach-s3c64xx/mach-ncp.c
index 01c6857c5b6..c30f2e5e0d8 100644
--- a/arch/arm/mach-s3c64xx/mach-ncp.c
+++ b/arch/arm/mach-s3c64xx/mach-ncp.c
@@ -97,7 +97,7 @@ static void __init ncp_machine_init(void)
 
 MACHINE_START(NCP, "NCP")
 	/* Maintainer: Samsung Electronics */
-	.boot_params	= S3C64XX_PA_SDRAM + 0x100,
+	.atag_offset	= 0x100,
 	.init_irq	= s3c6410_init_irq,
 	.map_io		= ncp_map_io,
 	.init_machine	= ncp_machine_init,
diff --git a/arch/arm/mach-s3c64xx/mach-real6410.c b/arch/arm/mach-s3c64xx/mach-real6410.c
index 95b04b1729e..10870cb5b39 100644
--- a/arch/arm/mach-s3c64xx/mach-real6410.c
+++ b/arch/arm/mach-s3c64xx/mach-real6410.c
@@ -329,7 +329,7 @@ static void __init real6410_machine_init(void)
 
 MACHINE_START(REAL6410, "REAL6410")
 	/* Maintainer: Darius Augulis <augulis.darius@gmail.com> */
-	.boot_params	= S3C64XX_PA_SDRAM + 0x100,
+	.atag_offset	= 0x100,
 
 	.init_irq	= s3c6410_init_irq,
 	.map_io		= real6410_map_io,
diff --git a/arch/arm/mach-s3c64xx/mach-smartq5.c b/arch/arm/mach-s3c64xx/mach-smartq5.c
index 342e8dfddf8..cbb57ded3d9 100644
--- a/arch/arm/mach-s3c64xx/mach-smartq5.c
+++ b/arch/arm/mach-s3c64xx/mach-smartq5.c
@@ -146,7 +146,7 @@ static void __init smartq5_machine_init(void)
 
 MACHINE_START(SMARTQ5, "SmartQ 5")
 	/* Maintainer: Maurus Cuelenaere <mcuelenaere AT gmail DOT com> */
-	.boot_params	= S3C64XX_PA_SDRAM + 0x100,
+	.atag_offset	= 0x100,
 	.init_irq	= s3c6410_init_irq,
 	.map_io		= smartq_map_io,
 	.init_machine	= smartq5_machine_init,
diff --git a/arch/arm/mach-s3c64xx/mach-smartq7.c b/arch/arm/mach-s3c64xx/mach-smartq7.c
index 57963977da8..04f914b85fd 100644
--- a/arch/arm/mach-s3c64xx/mach-smartq7.c
+++ b/arch/arm/mach-s3c64xx/mach-smartq7.c
@@ -162,7 +162,7 @@ static void __init smartq7_machine_init(void)
 
 MACHINE_START(SMARTQ7, "SmartQ 7")
 	/* Maintainer: Maurus Cuelenaere <mcuelenaere AT gmail DOT com> */
-	.boot_params	= S3C64XX_PA_SDRAM + 0x100,
+	.atag_offset	= 0x100,
 	.init_irq	= s3c6410_init_irq,
 	.map_io		= smartq_map_io,
 	.init_machine	= smartq7_machine_init,
diff --git a/arch/arm/mach-s3c64xx/mach-smdk6400.c b/arch/arm/mach-s3c64xx/mach-smdk6400.c
index 3cca642f1e6..6fd5e95f8f7 100644
--- a/arch/arm/mach-s3c64xx/mach-smdk6400.c
+++ b/arch/arm/mach-s3c64xx/mach-smdk6400.c
@@ -85,7 +85,7 @@ static void __init smdk6400_machine_init(void)
 
 MACHINE_START(SMDK6400, "SMDK6400")
 	/* Maintainer: Ben Dooks <ben-linux@fluff.org> */
-	.boot_params	= S3C64XX_PA_SDRAM + 0x100,
+	.atag_offset	= 0x100,
 
 	.init_irq	= s3c6400_init_irq,
 	.map_io		= smdk6400_map_io,
diff --git a/arch/arm/mach-s3c64xx/mach-smdk6410.c b/arch/arm/mach-s3c64xx/mach-smdk6410.c
index a9f3183e029..7b66ede9fbc 100644
--- a/arch/arm/mach-s3c64xx/mach-smdk6410.c
+++ b/arch/arm/mach-s3c64xx/mach-smdk6410.c
@@ -703,7 +703,7 @@ static void __init smdk6410_machine_init(void)
 
 MACHINE_START(SMDK6410, "SMDK6410")
 	/* Maintainer: Ben Dooks <ben-linux@fluff.org> */
-	.boot_params	= S3C64XX_PA_SDRAM + 0x100,
+	.atag_offset	= 0x100,
 
 	.init_irq	= s3c6410_init_irq,
 	.map_io		= smdk6410_map_io,
diff --git a/arch/arm/mach-s5p64x0/cpu.c b/arch/arm/mach-s5p64x0/cpu.c
index a5c00952ea3..8a938542c54 100644
--- a/arch/arm/mach-s5p64x0/cpu.c
+++ b/arch/arm/mach-s5p64x0/cpu.c
@@ -20,6 +20,7 @@
 #include <linux/serial_core.h>
 #include <linux/platform_device.h>
 #include <linux/sched.h>
+#include <linux/dma-mapping.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
@@ -111,6 +112,7 @@ void __init s5p6440_map_io(void)
 
 	iotable_init(s5p64x0_iodesc, ARRAY_SIZE(s5p64x0_iodesc));
 	iotable_init(s5p6440_iodesc, ARRAY_SIZE(s5p6440_iodesc));
+	init_consistent_dma_size(SZ_8M);
 }
 
 void __init s5p6450_map_io(void)
@@ -120,6 +122,7 @@ void __init s5p6450_map_io(void)
 
 	iotable_init(s5p64x0_iodesc, ARRAY_SIZE(s5p64x0_iodesc));
 	iotable_init(s5p6450_iodesc, ARRAY_SIZE(s5p6450_iodesc));
+	init_consistent_dma_size(SZ_8M);
 }
 
 /*
diff --git a/arch/arm/mach-s5p64x0/include/mach/memory.h b/arch/arm/mach-s5p64x0/include/mach/memory.h
index 365a6eb4b88..b14cbc3f521 100644
--- a/arch/arm/mach-s5p64x0/include/mach/memory.h
+++ b/arch/arm/mach-s5p64x0/include/mach/memory.h
@@ -14,6 +14,5 @@
 #define __ASM_ARCH_MEMORY_H __FILE__
 
 #define PLAT_PHYS_OFFSET		UL(0x20000000)
-#define CONSISTENT_DMA_SIZE	SZ_8M
 
 #endif /* __ASM_ARCH_MEMORY_H */
diff --git a/arch/arm/mach-s5p64x0/mach-smdk6440.c b/arch/arm/mach-s5p64x0/mach-smdk6440.c
index 346f8dfa6f3..3b84e9bfd07 100644
--- a/arch/arm/mach-s5p64x0/mach-smdk6440.c
+++ b/arch/arm/mach-s5p64x0/mach-smdk6440.c
@@ -171,7 +171,7 @@ static void __init smdk6440_machine_init(void)
 
 MACHINE_START(SMDK6440, "SMDK6440")
 	/* Maintainer: Kukjin Kim <kgene.kim@samsung.com> */
-	.boot_params	= S5P64X0_PA_SDRAM + 0x100,
+	.atag_offset	= 0x100,
 
 	.init_irq	= s5p6440_init_irq,
 	.map_io		= smdk6440_map_io,
diff --git a/arch/arm/mach-s5p64x0/mach-smdk6450.c b/arch/arm/mach-s5p64x0/mach-smdk6450.c
index 33f2adf8f3f..d99d29b5558 100644
--- a/arch/arm/mach-s5p64x0/mach-smdk6450.c
+++ b/arch/arm/mach-s5p64x0/mach-smdk6450.c
@@ -190,7 +190,7 @@ static void __init smdk6450_machine_init(void)
 
 MACHINE_START(SMDK6450, "SMDK6450")
 	/* Maintainer: Kukjin Kim <kgene.kim@samsung.com> */
-	.boot_params	= S5P64X0_PA_SDRAM + 0x100,
+	.atag_offset	= 0x100,
 
 	.init_irq	= s5p6450_init_irq,
 	.map_io		= smdk6450_map_io,
diff --git a/arch/arm/mach-s5pc100/mach-smdkc100.c b/arch/arm/mach-s5pc100/mach-smdkc100.c
index 227d8908aab..688f45b7cd0 100644
--- a/arch/arm/mach-s5pc100/mach-smdkc100.c
+++ b/arch/arm/mach-s5pc100/mach-smdkc100.c
@@ -254,7 +254,7 @@ static void __init smdkc100_machine_init(void)
 
 MACHINE_START(SMDKC100, "SMDKC100")
 	/* Maintainer: Byungho Min <bhmin@samsung.com> */
-	.boot_params	= S5P_PA_SDRAM + 0x100,
+	.atag_offset	= 0x100,
 	.init_irq	= s5pc100_init_irq,
 	.map_io		= smdkc100_map_io,
 	.init_machine	= smdkc100_machine_init,
diff --git a/arch/arm/mach-s5pv210/cpu.c b/arch/arm/mach-s5pv210/cpu.c
index 79907ec78d4..91145720822 100644
--- a/arch/arm/mach-s5pv210/cpu.c
+++ b/arch/arm/mach-s5pv210/cpu.c
@@ -20,6 +20,7 @@
 #include <linux/sysdev.h>
 #include <linux/platform_device.h>
 #include <linux/sched.h>
+#include <linux/dma-mapping.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
@@ -119,6 +120,7 @@ static void s5pv210_sw_reset(void)
 void __init s5pv210_map_io(void)
 {
 	iotable_init(s5pv210_iodesc, ARRAY_SIZE(s5pv210_iodesc));
+	init_consistent_dma_size(14 << 20);
 
 	/* initialise device information early */
 	s5pv210_default_sdhci0();
diff --git a/arch/arm/mach-s5pv210/include/mach/memory.h b/arch/arm/mach-s5pv210/include/mach/memory.h
index 7b5fcf0da0c..2d3cfa221d5 100644
--- a/arch/arm/mach-s5pv210/include/mach/memory.h
+++ b/arch/arm/mach-s5pv210/include/mach/memory.h
@@ -14,7 +14,6 @@
 #define __ASM_ARCH_MEMORY_H
 
 #define PLAT_PHYS_OFFSET		UL(0x20000000)
-#define CONSISTENT_DMA_SIZE	(SZ_8M + SZ_4M + SZ_2M)
 
 /*
  * Sparsemem support
diff --git a/arch/arm/mach-s5pv210/mach-aquila.c b/arch/arm/mach-s5pv210/mach-aquila.c
index 509627f2511..5811a96125f 100644
--- a/arch/arm/mach-s5pv210/mach-aquila.c
+++ b/arch/arm/mach-s5pv210/mach-aquila.c
@@ -678,7 +678,7 @@ MACHINE_START(AQUILA, "Aquila")
 	/* Maintainers:
 	   Marek Szyprowski <m.szyprowski@samsung.com>
 	   Kyungmin Park <kyungmin.park@samsung.com> */
-	.boot_params	= S5P_PA_SDRAM + 0x100,
+	.atag_offset	= 0x100,
 	.init_irq	= s5pv210_init_irq,
 	.map_io		= aquila_map_io,
 	.init_machine	= aquila_machine_init,
diff --git a/arch/arm/mach-s5pv210/mach-goni.c b/arch/arm/mach-s5pv210/mach-goni.c
index 85c2d51a095..061cc7e4f48 100644
--- a/arch/arm/mach-s5pv210/mach-goni.c
+++ b/arch/arm/mach-s5pv210/mach-goni.c
@@ -897,7 +897,7 @@ static void __init goni_machine_init(void)
 
 MACHINE_START(GONI, "GONI")
 	/* Maintainers: Kyungmin Park <kyungmin.park@samsung.com> */
-	.boot_params	= S5P_PA_SDRAM + 0x100,
+	.atag_offset	= 0x100,
 	.init_irq	= s5pv210_init_irq,
 	.map_io		= goni_map_io,
 	.init_machine	= goni_machine_init,
diff --git a/arch/arm/mach-s5pv210/mach-smdkc110.c b/arch/arm/mach-s5pv210/mach-smdkc110.c
index 6c412c8cecc..f7266bb0cac 100644
--- a/arch/arm/mach-s5pv210/mach-smdkc110.c
+++ b/arch/arm/mach-s5pv210/mach-smdkc110.c
@@ -136,7 +136,7 @@ static void __init smdkc110_machine_init(void)
 
 MACHINE_START(SMDKC110, "SMDKC110")
 	/* Maintainer: Kukjin Kim <kgene.kim@samsung.com> */
-	.boot_params	= S5P_PA_SDRAM + 0x100,
+	.atag_offset	= 0x100,
 	.init_irq	= s5pv210_init_irq,
 	.map_io		= smdkc110_map_io,
 	.init_machine	= smdkc110_machine_init,
diff --git a/arch/arm/mach-s5pv210/mach-smdkv210.c b/arch/arm/mach-s5pv210/mach-smdkv210.c
index 5e011fc6720..e73e3b6d41b 100644
--- a/arch/arm/mach-s5pv210/mach-smdkv210.c
+++ b/arch/arm/mach-s5pv210/mach-smdkv210.c
@@ -319,7 +319,7 @@ static void __init smdkv210_machine_init(void)
 
 MACHINE_START(SMDKV210, "SMDKV210")
 	/* Maintainer: Kukjin Kim <kgene.kim@samsung.com> */
-	.boot_params	= S5P_PA_SDRAM + 0x100,
+	.atag_offset	= 0x100,
 	.init_irq	= s5pv210_init_irq,
 	.map_io		= smdkv210_map_io,
 	.init_machine	= smdkv210_machine_init,
diff --git a/arch/arm/mach-s5pv210/mach-torbreck.c b/arch/arm/mach-s5pv210/mach-torbreck.c
index 925fc0dc625..97cc066c536 100644
--- a/arch/arm/mach-s5pv210/mach-torbreck.c
+++ b/arch/arm/mach-s5pv210/mach-torbreck.c
@@ -125,7 +125,7 @@ static void __init torbreck_machine_init(void)
 
 MACHINE_START(TORBRECK, "TORBRECK")
 	/* Maintainer: Hyunchul Ko <ghcstop@gmail.com> */
-	.boot_params	= S5P_PA_SDRAM + 0x100,
+	.atag_offset	= 0x100,
 	.init_irq	= s5pv210_init_irq,
 	.map_io		= torbreck_map_io,
 	.init_machine	= torbreck_machine_init,
diff --git a/arch/arm/mach-sa1100/assabet.c b/arch/arm/mach-sa1100/assabet.c
index 26257df19b6..d40da5f1f37 100644
--- a/arch/arm/mach-sa1100/assabet.c
+++ b/arch/arm/mach-sa1100/assabet.c
@@ -447,7 +447,7 @@ static void __init assabet_map_io(void)
 
 
 MACHINE_START(ASSABET, "Intel-Assabet")
-	.boot_params	= 0xc0000100,
+	.atag_offset	= 0x100,
 	.fixup		= fixup_assabet,
 	.map_io		= assabet_map_io,
 	.init_irq	= sa1100_init_irq,
diff --git a/arch/arm/mach-sa1100/badge4.c b/arch/arm/mach-sa1100/badge4.c
index b4311b0a439..bda83e1ab07 100644
--- a/arch/arm/mach-sa1100/badge4.c
+++ b/arch/arm/mach-sa1100/badge4.c
@@ -302,7 +302,7 @@ static void __init badge4_map_io(void)
 }
 
 MACHINE_START(BADGE4, "Hewlett-Packard Laboratories BadgePAD 4")
-	.boot_params	= 0xc0000100,
+	.atag_offset	= 0x100,
 	.map_io		= badge4_map_io,
 	.init_irq	= sa1100_init_irq,
 	.timer		= &sa1100_timer,
diff --git a/arch/arm/mach-sa1100/h3100.c b/arch/arm/mach-sa1100/h3100.c
index 03d7376cf8a..b30733a2b82 100644
--- a/arch/arm/mach-sa1100/h3100.c
+++ b/arch/arm/mach-sa1100/h3100.c
@@ -84,7 +84,7 @@ static void __init h3100_mach_init(void)
 }
 
 MACHINE_START(H3100, "Compaq iPAQ H3100")
-	.boot_params	= 0xc0000100,
+	.atag_offset	= 0x100,
 	.map_io		= h3100_map_io,
 	.init_irq	= sa1100_init_irq,
 	.timer		= &sa1100_timer,
diff --git a/arch/arm/mach-sa1100/h3600.c b/arch/arm/mach-sa1100/h3600.c
index 965f64a836f..6fd324d9238 100644
--- a/arch/arm/mach-sa1100/h3600.c
+++ b/arch/arm/mach-sa1100/h3600.c
@@ -125,7 +125,7 @@ static void __init h3600_mach_init(void)
 }
 
 MACHINE_START(H3600, "Compaq iPAQ H3600")
-	.boot_params	= 0xc0000100,
+	.atag_offset	= 0x100,
 	.map_io		= h3600_map_io,
 	.init_irq	= sa1100_init_irq,
 	.timer		= &sa1100_timer,
diff --git a/arch/arm/mach-sa1100/hackkit.c b/arch/arm/mach-sa1100/hackkit.c
index db5e434a17d..30f4a551b8e 100644
--- a/arch/arm/mach-sa1100/hackkit.c
+++ b/arch/arm/mach-sa1100/hackkit.c
@@ -195,7 +195,7 @@ static void __init hackkit_init(void)
  */
 
 MACHINE_START(HACKKIT, "HackKit Cpu Board")
-	.boot_params	= 0xc0000100,
+	.atag_offset	= 0x100,
 	.map_io		= hackkit_map_io,
 	.init_irq	= sa1100_init_irq,
 	.timer		= &sa1100_timer,
diff --git a/arch/arm/mach-sa1100/jornada720.c b/arch/arm/mach-sa1100/jornada720.c
index 176c066aec7..0bb520d48ed 100644
--- a/arch/arm/mach-sa1100/jornada720.c
+++ b/arch/arm/mach-sa1100/jornada720.c
@@ -364,7 +364,7 @@ static void __init jornada720_mach_init(void)
 
 MACHINE_START(JORNADA720, "HP Jornada 720")
 	/* Maintainer: Kristoffer Ericson <Kristoffer.Ericson@gmail.com> */
-	.boot_params	= 0xc0000100,
+	.atag_offset	= 0x100,
 	.map_io		= jornada720_map_io,
 	.init_irq	= sa1100_init_irq,
 	.timer		= &sa1100_timer,
diff --git a/arch/arm/mach-sa1100/lart.c b/arch/arm/mach-sa1100/lart.c
index 7b9556b5905..5bc59d0947b 100644
--- a/arch/arm/mach-sa1100/lart.c
+++ b/arch/arm/mach-sa1100/lart.c
@@ -61,7 +61,7 @@ static void __init lart_map_io(void)
 }
 
 MACHINE_START(LART, "LART")
-	.boot_params	= 0xc0000100,
+	.atag_offset	= 0x100,
 	.map_io		= lart_map_io,
 	.init_irq	= sa1100_init_irq,
 	.init_machine	= lart_init,
diff --git a/arch/arm/mach-sa1100/nanoengine.c b/arch/arm/mach-sa1100/nanoengine.c
index 72087f0658b..032f3881d14 100644
--- a/arch/arm/mach-sa1100/nanoengine.c
+++ b/arch/arm/mach-sa1100/nanoengine.c
@@ -111,7 +111,7 @@ static void __init nanoengine_init(void)
 }
 
 MACHINE_START(NANOENGINE, "BSE nanoEngine")
-	.boot_params	= 0xc0000000,
+	.atag_offset	= 0x100,
 	.map_io		= nanoengine_map_io,
 	.init_irq	= sa1100_init_irq,
 	.timer		= &sa1100_timer,
diff --git a/arch/arm/mach-sa1100/shannon.c b/arch/arm/mach-sa1100/shannon.c
index 7917b240557..1cccbf5b9e9 100644
--- a/arch/arm/mach-sa1100/shannon.c
+++ b/arch/arm/mach-sa1100/shannon.c
@@ -82,7 +82,7 @@ static void __init shannon_map_io(void)
 }
 
 MACHINE_START(SHANNON, "Shannon (AKA: Tuxscreen)")
-	.boot_params	= 0xc0000100,
+	.atag_offset	= 0x100,
 	.map_io		= shannon_map_io,
 	.init_irq	= sa1100_init_irq,
 	.timer		= &sa1100_timer,
diff --git a/arch/arm/mach-sa1100/simpad.c b/arch/arm/mach-sa1100/simpad.c
index cfb76077bd2..a1c2427655d 100644
--- a/arch/arm/mach-sa1100/simpad.c
+++ b/arch/arm/mach-sa1100/simpad.c
@@ -229,7 +229,7 @@ arch_initcall(simpad_init);
 
 MACHINE_START(SIMPAD, "Simpad")
 	/* Maintainer: Holger Freyther */
-	.boot_params	= 0xc0000100,
+	.atag_offset	= 0x100,
 	.map_io		= simpad_map_io,
 	.init_irq	= sa1100_init_irq,
 	.timer		= &sa1100_timer,
diff --git a/arch/arm/mach-shark/core.c b/arch/arm/mach-shark/core.c
index ac2873c8014..feda3ca7fc9 100644
--- a/arch/arm/mach-shark/core.c
+++ b/arch/arm/mach-shark/core.c
@@ -152,7 +152,7 @@ static struct sys_timer shark_timer = {
 
 MACHINE_START(SHARK, "Shark")
 	/* Maintainer: Alexander Schulz */
-	.boot_params	= 0x08003000,
+	.atag_offset	= 0x3000,
 	.map_io		= shark_map_io,
 	.init_irq	= shark_init_irq,
 	.timer		= &shark_timer,
diff --git a/arch/arm/mach-shmobile/board-ag5evm.c b/arch/arm/mach-shmobile/board-ag5evm.c
index cdfdd624d21..5fde49da399 100644
--- a/arch/arm/mach-shmobile/board-ag5evm.c
+++ b/arch/arm/mach-shmobile/board-ag5evm.c
@@ -37,6 +37,7 @@
 #include <linux/mmc/sh_mobile_sdhi.h>
 #include <linux/mfd/tmio.h>
 #include <linux/sh_clk.h>
+#include <linux/dma-mapping.h>
 #include <video/sh_mobile_lcdc.h>
 #include <video/sh_mipi_dsi.h>
 #include <sound/sh_fsi.h>
@@ -447,6 +448,8 @@ static struct map_desc ag5evm_io_desc[] __initdata = {
 static void __init ag5evm_map_io(void)
 {
 	iotable_init(ag5evm_io_desc, ARRAY_SIZE(ag5evm_io_desc));
+	/* DMA memory at 0xf6000000 - 0xffdfffff */
+	init_consistent_dma_size(158 << 20);
 
 	/* setup early devices and console here as well */
 	sh73a0_add_early_devices();
diff --git a/arch/arm/mach-shmobile/board-ap4evb.c b/arch/arm/mach-shmobile/board-ap4evb.c
index 523f608eb8c..b622d8d3ab7 100644
--- a/arch/arm/mach-shmobile/board-ap4evb.c
+++ b/arch/arm/mach-shmobile/board-ap4evb.c
@@ -42,6 +42,7 @@
 #include <linux/leds.h>
 #include <linux/input/sh_keysc.h>
 #include <linux/usb/r8a66597.h>
+#include <linux/dma-mapping.h>
 
 #include <media/sh_mobile_ceu.h>
 #include <media/sh_mobile_csi2.h>
@@ -1170,6 +1171,8 @@ static struct map_desc ap4evb_io_desc[] __initdata = {
 static void __init ap4evb_map_io(void)
 {
 	iotable_init(ap4evb_io_desc, ARRAY_SIZE(ap4evb_io_desc));
+	/* DMA memory at 0xf6000000 - 0xffdfffff */
+	init_consistent_dma_size(158 << 20);
 
 	/* setup early devices and console here as well */
 	sh7372_add_early_devices();
diff --git a/arch/arm/mach-shmobile/board-g3evm.c b/arch/arm/mach-shmobile/board-g3evm.c
index ef4613b993a..8b620bf0622 100644
--- a/arch/arm/mach-shmobile/board-g3evm.c
+++ b/arch/arm/mach-shmobile/board-g3evm.c
@@ -32,6 +32,7 @@
 #include <linux/gpio.h>
 #include <linux/input.h>
 #include <linux/input/sh_keysc.h>
+#include <linux/dma-mapping.h>
 #include <mach/sh7367.h>
 #include <mach/common.h>
 #include <asm/mach-types.h>
@@ -260,6 +261,8 @@ static struct map_desc g3evm_io_desc[] __initdata = {
 static void __init g3evm_map_io(void)
 {
 	iotable_init(g3evm_io_desc, ARRAY_SIZE(g3evm_io_desc));
+	/* DMA memory at 0xf6000000 - 0xffdfffff */
+	init_consistent_dma_size(158 << 20);
 
 	/* setup early devices and console here as well */
 	sh7367_add_early_devices();
diff --git a/arch/arm/mach-shmobile/board-g4evm.c b/arch/arm/mach-shmobile/board-g4evm.c
index 8e3c5559f27..7719ddc5f59 100644
--- a/arch/arm/mach-shmobile/board-g4evm.c
+++ b/arch/arm/mach-shmobile/board-g4evm.c
@@ -33,6 +33,7 @@
 #include <linux/mmc/host.h>
 #include <linux/mmc/sh_mobile_sdhi.h>
 #include <linux/gpio.h>
+#include <linux/dma-mapping.h>
 #include <mach/sh7377.h>
 #include <mach/common.h>
 #include <asm/mach-types.h>
@@ -274,6 +275,8 @@ static struct map_desc g4evm_io_desc[] __initdata = {
 static void __init g4evm_map_io(void)
 {
 	iotable_init(g4evm_io_desc, ARRAY_SIZE(g4evm_io_desc));
+	/* DMA memory at 0xf6000000 - 0xffdfffff */
+	init_consistent_dma_size(158 << 20);
 
 	/* setup early devices and console here as well */
 	sh7377_add_early_devices();
diff --git a/arch/arm/mach-shmobile/board-mackerel.c b/arch/arm/mach-shmobile/board-mackerel.c
index 17c19dc2560..de2253d7f15 100644
--- a/arch/arm/mach-shmobile/board-mackerel.c
+++ b/arch/arm/mach-shmobile/board-mackerel.c
@@ -45,6 +45,7 @@
 #include <linux/tca6416_keypad.h>
 #include <linux/usb/r8a66597.h>
 #include <linux/usb/renesas_usbhs.h>
+#include <linux/dma-mapping.h>
 
 #include <video/sh_mobile_hdmi.h>
 #include <video/sh_mobile_lcdc.h>
@@ -1381,6 +1382,8 @@ static struct map_desc mackerel_io_desc[] __initdata = {
 static void __init mackerel_map_io(void)
 {
 	iotable_init(mackerel_io_desc, ARRAY_SIZE(mackerel_io_desc));
+	/* DMA memory at 0xf6000000 - 0xffdfffff */
+	init_consistent_dma_size(158 << 20);
 
 	/* setup early devices and console here as well */
 	sh7372_add_early_devices();
diff --git a/arch/arm/mach-shmobile/include/mach/memory.h b/arch/arm/mach-shmobile/include/mach/memory.h
index ad00c3c258f..0ffbe8155c7 100644
--- a/arch/arm/mach-shmobile/include/mach/memory.h
+++ b/arch/arm/mach-shmobile/include/mach/memory.h
@@ -4,7 +4,4 @@
 #define PLAT_PHYS_OFFSET	UL(CONFIG_MEMORY_START)
 #define MEM_SIZE	UL(CONFIG_MEMORY_SIZE)
 
-/* DMA memory at 0xf6000000 - 0xffdfffff */
-#define CONSISTENT_DMA_SIZE (158 << 20)
-
 #endif /* __ASM_MACH_MEMORY_H */
diff --git a/arch/arm/mach-shmobile/platsmp.c b/arch/arm/mach-shmobile/platsmp.c
index 66f980625a3..e4e485fa253 100644
--- a/arch/arm/mach-shmobile/platsmp.c
+++ b/arch/arm/mach-shmobile/platsmp.c
@@ -56,6 +56,12 @@ void __init smp_init_cpus(void)
 	unsigned int ncores = shmobile_smp_get_core_count();
 	unsigned int i;
 
+	if (ncores > nr_cpu_ids) {
+		pr_warn("SMP: %u cores greater than maximum (%u), clipping\n",
+			ncores, nr_cpu_ids);
+		ncores = nr_cpu_ids;
+	}
+
 	for (i = 0; i < ncores; i++)
 		set_cpu_possible(i, true);
 
diff --git a/arch/arm/mach-spear3xx/spear300_evb.c b/arch/arm/mach-spear3xx/spear300_evb.c
index 69006f69422..a5ff98eed1d 100644
--- a/arch/arm/mach-spear3xx/spear300_evb.c
+++ b/arch/arm/mach-spear3xx/spear300_evb.c
@@ -64,7 +64,7 @@ static void __init spear300_evb_init(void)
 }
 
 MACHINE_START(SPEAR300, "ST-SPEAR300-EVB")
-	.boot_params	=	0x00000100,
+	.atag_offset	=	0x100,
 	.map_io		=	spear3xx_map_io,
 	.init_irq	=	spear3xx_init_irq,
 	.timer		=	&spear3xx_timer,
diff --git a/arch/arm/mach-spear3xx/spear310_evb.c b/arch/arm/mach-spear3xx/spear310_evb.c
index c8684ce1f9b..45d180d5936 100644
--- a/arch/arm/mach-spear3xx/spear310_evb.c
+++ b/arch/arm/mach-spear3xx/spear310_evb.c
@@ -70,7 +70,7 @@ static void __init spear310_evb_init(void)
 }
 
 MACHINE_START(SPEAR310, "ST-SPEAR310-EVB")
-	.boot_params	=	0x00000100,
+	.atag_offset	=	0x100,
 	.map_io		=	spear3xx_map_io,
 	.init_irq	=	spear3xx_init_irq,
 	.timer		=	&spear3xx_timer,
diff --git a/arch/arm/mach-spear3xx/spear320_evb.c b/arch/arm/mach-spear3xx/spear320_evb.c
index a12b353940d..22879848d73 100644
--- a/arch/arm/mach-spear3xx/spear320_evb.c
+++ b/arch/arm/mach-spear3xx/spear320_evb.c
@@ -68,7 +68,7 @@ static void __init spear320_evb_init(void)
 }
 
 MACHINE_START(SPEAR320, "ST-SPEAR320-EVB")
-	.boot_params	=	0x00000100,
+	.atag_offset	=	0x100,
 	.map_io		=	spear3xx_map_io,
 	.init_irq	=	spear3xx_init_irq,
 	.timer		=	&spear3xx_timer,
diff --git a/arch/arm/mach-spear6xx/spear600_evb.c b/arch/arm/mach-spear6xx/spear600_evb.c
index f19cefe91a2..8238fe38e71 100644
--- a/arch/arm/mach-spear6xx/spear600_evb.c
+++ b/arch/arm/mach-spear6xx/spear600_evb.c
@@ -43,7 +43,7 @@ static void __init spear600_evb_init(void)
 }
 
 MACHINE_START(SPEAR600, "ST-SPEAR600-EVB")
-	.boot_params	=	0x00000100,
+	.atag_offset	=	0x100,
 	.map_io		=	spear6xx_map_io,
 	.init_irq	=	spear6xx_init_irq,
 	.timer		=	&spear6xx_timer,
diff --git a/arch/arm/mach-tcc8k/board-tcc8000-sdk.c b/arch/arm/mach-tcc8k/board-tcc8000-sdk.c
index 4cb3c2dd905..777a5bb9eed 100644
--- a/arch/arm/mach-tcc8k/board-tcc8000-sdk.c
+++ b/arch/arm/mach-tcc8k/board-tcc8000-sdk.c
@@ -73,7 +73,7 @@ static void __init tcc8k_map_io(void)
 }
 
 MACHINE_START(TCC8000_SDK, "Telechips TCC8000-SDK Demo Board")
-	.boot_params	= PLAT_PHYS_OFFSET + 0x00000100,
+	.atag_offset	= 0x100,
 	.map_io		= tcc8k_map_io,
 	.init_irq	= tcc8k_init_irq,
 	.init_machine	= tcc8k_init,
diff --git a/arch/arm/mach-tegra/board-harmony.c b/arch/arm/mach-tegra/board-harmony.c
index 846cd7d69e3..a4d1980e697 100644
--- a/arch/arm/mach-tegra/board-harmony.c
+++ b/arch/arm/mach-tegra/board-harmony.c
@@ -179,7 +179,7 @@ static void __init tegra_harmony_init(void)
 }
 
 MACHINE_START(HARMONY, "harmony")
-	.boot_params  = 0x00000100,
+	.atag_offset	= 0x100,
 	.fixup		= tegra_harmony_fixup,
 	.map_io         = tegra_map_common_io,
 	.init_early	= tegra_init_early,
diff --git a/arch/arm/mach-tegra/board-paz00.c b/arch/arm/mach-tegra/board-paz00.c
index ea2f79c9879..3197c4cbaa7 100644
--- a/arch/arm/mach-tegra/board-paz00.c
+++ b/arch/arm/mach-tegra/board-paz00.c
@@ -127,7 +127,7 @@ static void __init tegra_paz00_init(void)
 }
 
 MACHINE_START(PAZ00, "Toshiba AC100 / Dynabook AZ")
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.fixup		= tegra_paz00_fixup,
 	.map_io         = tegra_map_common_io,
 	.init_early	= tegra_init_early,
diff --git a/arch/arm/mach-tegra/board-seaboard.c b/arch/arm/mach-tegra/board-seaboard.c
index 56cbabf6aa6..9e98ac706f4 100644
--- a/arch/arm/mach-tegra/board-seaboard.c
+++ b/arch/arm/mach-tegra/board-seaboard.c
@@ -201,7 +201,7 @@ static void __init tegra_wario_init(void)
 
 
 MACHINE_START(SEABOARD, "seaboard")
-	.boot_params    = 0x00000100,
+	.atag_offset    = 0x100,
 	.map_io         = tegra_map_common_io,
 	.init_early     = tegra_init_early,
 	.init_irq       = tegra_init_irq,
@@ -210,7 +210,7 @@ MACHINE_START(SEABOARD, "seaboard")
 MACHINE_END
 
 MACHINE_START(KAEN, "kaen")
-	.boot_params    = 0x00000100,
+	.atag_offset    = 0x100,
 	.map_io         = tegra_map_common_io,
 	.init_early     = tegra_init_early,
 	.init_irq       = tegra_init_irq,
@@ -219,7 +219,7 @@ MACHINE_START(KAEN, "kaen")
 MACHINE_END
 
 MACHINE_START(WARIO, "wario")
-	.boot_params    = 0x00000100,
+	.atag_offset    = 0x100,
 	.map_io         = tegra_map_common_io,
 	.init_early     = tegra_init_early,
 	.init_irq       = tegra_init_irq,
diff --git a/arch/arm/mach-tegra/board-trimslice.c b/arch/arm/mach-tegra/board-trimslice.c
index 89a6d2adc1d..8489aa8f515 100644
--- a/arch/arm/mach-tegra/board-trimslice.c
+++ b/arch/arm/mach-tegra/board-trimslice.c
@@ -171,7 +171,7 @@ static void __init tegra_trimslice_init(void)
 }
 
 MACHINE_START(TRIMSLICE, "trimslice")
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.fixup		= tegra_trimslice_fixup,
 	.map_io         = tegra_map_common_io,
 	.init_early	= tegra_init_early,
diff --git a/arch/arm/mach-tegra/platsmp.c b/arch/arm/mach-tegra/platsmp.c
index 0886cbccdde..7d2b5d03c1d 100644
--- a/arch/arm/mach-tegra/platsmp.c
+++ b/arch/arm/mach-tegra/platsmp.c
@@ -114,10 +114,10 @@ void __init smp_init_cpus(void)
 {
 	unsigned int i, ncores = scu_get_core_count(scu_base);
 
-	if (ncores > NR_CPUS) {
-		printk(KERN_ERR "Tegra: no. of cores (%u) greater than configured (%u), clipping\n",
-			ncores, NR_CPUS);
-		ncores = NR_CPUS;
+	if (ncores > nr_cpu_ids) {
+		pr_warn("SMP: %u cores greater than maximum (%u), clipping\n",
+			ncores, nr_cpu_ids);
+		ncores = nr_cpu_ids;
 	}
 
 	for (i = 0; i < ncores; i++)
diff --git a/arch/arm/mach-u300/core.c b/arch/arm/mach-u300/core.c
index 399c89f14df..376b6dfdfae 100644
--- a/arch/arm/mach-u300/core.c
+++ b/arch/arm/mach-u300/core.c
@@ -25,6 +25,7 @@
 #include <linux/err.h>
 #include <linux/mtd/nand.h>
 #include <linux/mtd/fsmc.h>
+#include <linux/dma-mapping.h>
 
 #include <asm/types.h>
 #include <asm/setup.h>
@@ -92,6 +93,8 @@ static struct map_desc u300_io_desc[] __initdata = {
 void __init u300_map_io(void)
 {
 	iotable_init(u300_io_desc, ARRAY_SIZE(u300_io_desc));
+	/* We enable a real big DMA buffer if need be. */
+	init_consistent_dma_size(SZ_4M);
 }
 
 /*
diff --git a/arch/arm/mach-u300/include/mach/memory.h b/arch/arm/mach-u300/include/mach/memory.h
index 888e2e351ee..7034bae95de 100644
--- a/arch/arm/mach-u300/include/mach/memory.h
+++ b/arch/arm/mach-u300/include/mach/memory.h
@@ -16,7 +16,7 @@
 #ifdef CONFIG_MACH_U300_DUAL_RAM
 
 #define PLAT_PHYS_OFFSET		UL(0x48000000)
-#define BOOT_PARAMS_OFFSET	(PHYS_OFFSET + 0x100)
+#define BOOT_PARAMS_OFFSET		0x100
 
 #else
 
@@ -24,19 +24,14 @@
 #define PLAT_PHYS_OFFSET (0x28000000 + \
 	     (CONFIG_MACH_U300_ACCESS_MEM_SIZE - \
 	     (CONFIG_MACH_U300_ACCESS_MEM_SIZE & 1))*1024*1024)
+#define BOOT_PARAMS_OFFSET (0x100 + \
+	     (CONFIG_MACH_U300_ACCESS_MEM_SIZE & 1)*1024*1024*2)
 #else
 #define PLAT_PHYS_OFFSET (0x28000000 + \
 	     (CONFIG_MACH_U300_ACCESS_MEM_SIZE +	\
 	     (CONFIG_MACH_U300_ACCESS_MEM_SIZE & 1))*1024*1024)
+#define BOOT_PARAMS_OFFSET 0x100
 #endif
-#define BOOT_PARAMS_OFFSET (0x28000000 + \
-	    (CONFIG_MACH_U300_ACCESS_MEM_SIZE +		\
-	    (CONFIG_MACH_U300_ACCESS_MEM_SIZE & 1))*1024*1024 + 0x100)
 #endif
 
-/*
- * We enable a real big DMA buffer if need be.
- */
-#define CONSISTENT_DMA_SIZE SZ_4M
-
 #endif
diff --git a/arch/arm/mach-u300/u300.c b/arch/arm/mach-u300/u300.c
index 48b3b7f3996..80e7305589c 100644
--- a/arch/arm/mach-u300/u300.c
+++ b/arch/arm/mach-u300/u300.c
@@ -61,7 +61,7 @@ static void __init u300_init_machine(void)
 
 MACHINE_START(U300, MACH_U300_STRING)
 	/* Maintainer: Linus Walleij <linus.walleij@stericsson.com> */
-	.boot_params	= BOOT_PARAMS_OFFSET,
+	.atag_offset	= BOOT_PARAMS_OFFSET,
 	.map_io		= u300_map_io,
 	.reserve	= u300_reserve,
 	.init_irq	= u300_init_irq,
diff --git a/arch/arm/mach-ux500/board-mop500.c b/arch/arm/mach-ux500/board-mop500.c
index 76211404481..e5f6fe8989b 100644
--- a/arch/arm/mach-ux500/board-mop500.c
+++ b/arch/arm/mach-ux500/board-mop500.c
@@ -1292,7 +1292,7 @@ static void __init mop500_init_machine(void)
 
 MACHINE_START(U8500, "ST-Ericsson MOP500 platform")
 	/* Maintainer: Srinidhi Kasagar <srinidhi.kasagar@stericsson.com> */
-	.boot_params	= 0x100,
+	.atag_offset	= 0x100,
 	.map_io		= u8500_map_io,
 	.init_irq	= ux500_init_irq,
 	/* we re-use nomadik timer here */
@@ -1301,7 +1301,7 @@ MACHINE_START(U8500, "ST-Ericsson MOP500 platform")
 MACHINE_END
 
 MACHINE_START(HREFV60, "ST-Ericsson U8500 Platform HREFv60+")
-	.boot_params	= 0x100,
+	.atag_offset	= 0x100,
 	.map_io		= u8500_map_io,
 	.init_irq	= ux500_init_irq,
 	.timer		= &ux500_timer,
@@ -1309,7 +1309,8 @@ MACHINE_START(HREFV60, "ST-Ericsson U8500 Platform HREFv60+")
 MACHINE_END
 
 MACHINE_START(SNOWBALL, "ST-Ericsson Snowball platform")
-	.boot_params	= 0x100,
+	.boot_params 	= 0x100,
+	.atag_offset	= 0x100,
 	.map_io		= u8500_map_io,
 	.init_irq	= ux500_init_irq,
 	/* we re-use nomadik timer here */
diff --git a/arch/arm/mach-ux500/board-u5500.c b/arch/arm/mach-ux500/board-u5500.c
index 7752f22d95e..2cc3477559c 100644
--- a/arch/arm/mach-ux500/board-u5500.c
+++ b/arch/arm/mach-ux500/board-u5500.c
@@ -662,7 +662,7 @@ static void __init u5500_init_machine(void)
 }
 
 MACHINE_START(U5500, "ST-Ericsson U5500 Platform")
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.map_io		= u5500_map_io,
 	.init_irq	= ux500_init_irq,
 	.timer		= &ux500_timer,
diff --git a/arch/arm/mach-ux500/cpu.c b/arch/arm/mach-ux500/cpu.c
index 7274ab2f90f..046c08d0696 100644
--- a/arch/arm/mach-ux500/cpu.c
+++ b/arch/arm/mach-ux500/cpu.c
@@ -128,7 +128,27 @@ static void ux500_l2x0_inv_all(void)
 	ux500_cache_sync();
 }
 
-static int ux500_l2x0_init(void)
+static int __init ux500_l2x0_unlock(void)
+{
+	int i;
+
+	/*
+	 * Unlock Data and Instruction Lock if locked. Ux500 U-Boot versions
+	 * apparently locks both caches before jumping to the kernel. The
+	 * l2x0 core will not touch the unlock registers if the l2x0 is
+	 * already enabled, so we do it right here instead. The PL310 has
+	 * 8 sets of registers, one per possible CPU.
+	 */
+	for (i = 0; i < 8; i++) {
+		writel_relaxed(0x0, l2x0_base + L2X0_LOCKDOWN_WAY_D_BASE +
+			       i * L2X0_LOCKDOWN_STRIDE);
+		writel_relaxed(0x0, l2x0_base + L2X0_LOCKDOWN_WAY_I_BASE +
+			       i * L2X0_LOCKDOWN_STRIDE);
+	}
+	return 0;
+}
+
+static int __init ux500_l2x0_init(void)
 {
 	if (cpu_is_u5500())
 		l2x0_base = __io_address(U5500_L2CC_BASE);
@@ -137,6 +157,9 @@ static int ux500_l2x0_init(void)
 	else
 		ux500_unknown_soc();
 
+	/* Unlock before init */
+	ux500_l2x0_unlock();
+
 	/* 64KB way size, 8 way associativity, force WA */
 	l2x0_init(l2x0_base, 0x3e060000, 0xc0000fff);
 
diff --git a/arch/arm/mach-ux500/platsmp.c b/arch/arm/mach-ux500/platsmp.c
index a33df5f4c27..eb5199102cf 100644
--- a/arch/arm/mach-ux500/platsmp.c
+++ b/arch/arm/mach-ux500/platsmp.c
@@ -156,12 +156,10 @@ void __init smp_init_cpus(void)
 	ncores = scu_base ? scu_get_core_count(scu_base) : 1;
 
 	/* sanity check */
-	if (ncores > NR_CPUS) {
-		printk(KERN_WARNING
-		       "U8500: no. of cores (%d) greater than configured "
-		       "maximum of %d - clipping\n",
-		       ncores, NR_CPUS);
-		ncores = NR_CPUS;
+	if (ncores > nr_cpu_ids) {
+		pr_warn("SMP: %u cores greater than maximum (%u), clipping\n",
+			ncores, nr_cpu_ids);
+		ncores = nr_cpu_ids;
 	}
 
 	for (i = 0; i < ncores; i++)
diff --git a/arch/arm/mach-versatile/Makefile.boot b/arch/arm/mach-versatile/Makefile.boot
index c7e75acfe6c..c08ab6da090 100644
--- a/arch/arm/mach-versatile/Makefile.boot
+++ b/arch/arm/mach-versatile/Makefile.boot
@@ -2,3 +2,5 @@
 params_phys-y	:= 0x00000100
 initrd_phys-y	:= 0x00800000
 
+dtb-$(CONFIG_MACH_VERSATILE_DT) += versatile-pb.dtb
+dtb-$(CONFIG_MACH_VERSATILE_DT) += versatile-ab.dtb
diff --git a/arch/arm/mach-versatile/versatile_ab.c b/arch/arm/mach-versatile/versatile_ab.c
index f8ae64b3eed..fda4866703c 100644
--- a/arch/arm/mach-versatile/versatile_ab.c
+++ b/arch/arm/mach-versatile/versatile_ab.c
@@ -35,7 +35,7 @@
 
 MACHINE_START(VERSATILE_AB, "ARM-Versatile AB")
 	/* Maintainer: ARM Ltd/Deep Blue Solutions Ltd */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.map_io		= versatile_map_io,
 	.init_early	= versatile_init_early,
 	.init_irq	= versatile_init_irq,
diff --git a/arch/arm/mach-versatile/versatile_pb.c b/arch/arm/mach-versatile/versatile_pb.c
index 37c23dfeefb..feaf9cbe60f 100644
--- a/arch/arm/mach-versatile/versatile_pb.c
+++ b/arch/arm/mach-versatile/versatile_pb.c
@@ -103,7 +103,7 @@ static void __init versatile_pb_init(void)
 
 MACHINE_START(VERSATILE_PB, "ARM-Versatile PB")
 	/* Maintainer: ARM Ltd/Deep Blue Solutions Ltd */
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.map_io		= versatile_map_io,
 	.init_early	= versatile_init_early,
 	.init_irq	= versatile_init_irq,
diff --git a/arch/arm/mach-vexpress/Makefile.boot b/arch/arm/mach-vexpress/Makefile.boot
index 07c2d9c457e..9920a1053e2 100644
--- a/arch/arm/mach-vexpress/Makefile.boot
+++ b/arch/arm/mach-vexpress/Makefile.boot
@@ -1,3 +1,5 @@
    zreladdr-y	:= 0x60008000
 params_phys-y	:= 0x60000100
 initrd_phys-y	:= 0x60800000
+
+dtb-$(CONFIG_ARCH_VEXPRESS_CA9X4) += vexpress.dtb
diff --git a/arch/arm/mach-vexpress/ct-ca9x4.c b/arch/arm/mach-vexpress/ct-ca9x4.c
index bfd32f52c2d..2b1e836a76e 100644
--- a/arch/arm/mach-vexpress/ct-ca9x4.c
+++ b/arch/arm/mach-vexpress/ct-ca9x4.c
@@ -221,6 +221,12 @@ static void ct_ca9x4_init_cpu_map(void)
 {
 	int i, ncores = scu_get_core_count(MMIO_P2V(A9_MPCORE_SCU));
 
+	if (ncores > nr_cpu_ids) {
+		pr_warn("SMP: %u cores greater than maximum (%u), clipping\n",
+			ncores, nr_cpu_ids);
+		ncores = nr_cpu_ids;
+	}
+
 	for (i = 0; i < ncores; ++i)
 		set_cpu_possible(i, true);
 
diff --git a/arch/arm/mach-vexpress/v2m.c b/arch/arm/mach-vexpress/v2m.c
index d0d267a8d3f..f9c47defaa8 100644
--- a/arch/arm/mach-vexpress/v2m.c
+++ b/arch/arm/mach-vexpress/v2m.c
@@ -442,11 +442,17 @@ static void __init v2m_init(void)
 	ct_desc->init_tile();
 }
 
+static const char *vexpress_dt_match[] __initdata = {
+	"arm,vexpress",
+	NULL,
+};
+
 MACHINE_START(VEXPRESS, "ARM-Versatile Express")
-	.boot_params	= PLAT_PHYS_OFFSET + 0x00000100,
+	.atag_offset	= 0x100,
 	.map_io		= v2m_map_io,
 	.init_early	= v2m_init_early,
 	.init_irq	= v2m_init_irq,
 	.timer		= &v2m_timer,
 	.init_machine	= v2m_init,
+	.dt_compat	= vexpress_dt_match,
 MACHINE_END
diff --git a/arch/arm/mach-vt8500/bv07.c b/arch/arm/mach-vt8500/bv07.c
index 94a261d86bf..a464c758441 100644
--- a/arch/arm/mach-vt8500/bv07.c
+++ b/arch/arm/mach-vt8500/bv07.c
@@ -68,7 +68,7 @@ void __init bv07_init(void)
 }
 
 MACHINE_START(BV07, "Benign BV07 Mini Netbook")
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.reserve	= vt8500_reserve_mem,
 	.map_io		= vt8500_map_io,
 	.init_irq	= vt8500_init_irq,
diff --git a/arch/arm/mach-vt8500/wm8505_7in.c b/arch/arm/mach-vt8500/wm8505_7in.c
index e73aadbcafd..cf910a95608 100644
--- a/arch/arm/mach-vt8500/wm8505_7in.c
+++ b/arch/arm/mach-vt8500/wm8505_7in.c
@@ -68,7 +68,7 @@ void __init wm8505_7in_init(void)
 }
 
 MACHINE_START(WM8505_7IN_NETBOOK, "WM8505 7-inch generic netbook")
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.reserve	= wm8505_reserve_mem,
 	.map_io		= wm8505_map_io,
 	.init_irq	= wm8505_init_irq,
diff --git a/arch/arm/mach-w90x900/mach-nuc910evb.c b/arch/arm/mach-w90x900/mach-nuc910evb.c
index 30fccde94fb..31c10901822 100644
--- a/arch/arm/mach-w90x900/mach-nuc910evb.c
+++ b/arch/arm/mach-w90x900/mach-nuc910evb.c
@@ -34,7 +34,6 @@ static void __init nuc910evb_init(void)
 
 MACHINE_START(W90P910EVB, "W90P910EVB")
 	/* Maintainer: Wan ZongShun */
-	.boot_params	= 0,
 	.map_io		= nuc910evb_map_io,
 	.init_irq	= nuc900_init_irq,
 	.init_machine	= nuc910evb_init,
diff --git a/arch/arm/mach-w90x900/mach-nuc950evb.c b/arch/arm/mach-w90x900/mach-nuc950evb.c
index 590c99b96dc..4062e55a57d 100644
--- a/arch/arm/mach-w90x900/mach-nuc950evb.c
+++ b/arch/arm/mach-w90x900/mach-nuc950evb.c
@@ -37,7 +37,6 @@ static void __init nuc950evb_init(void)
 
 MACHINE_START(W90P950EVB, "W90P950EVB")
 	/* Maintainer: Wan ZongShun */
-	.boot_params	= 0,
 	.map_io		= nuc950evb_map_io,
 	.init_irq	= nuc900_init_irq,
 	.init_machine	= nuc950evb_init,
diff --git a/arch/arm/mach-w90x900/mach-nuc960evb.c b/arch/arm/mach-w90x900/mach-nuc960evb.c
index e09c645d61b..0ab9995d5b5 100644
--- a/arch/arm/mach-w90x900/mach-nuc960evb.c
+++ b/arch/arm/mach-w90x900/mach-nuc960evb.c
@@ -34,7 +34,6 @@ static void __init nuc960evb_init(void)
 
 MACHINE_START(W90N960EVB, "W90N960EVB")
 	/* Maintainer: Wan ZongShun */
-	.boot_params	= 0,
 	.map_io		= nuc960evb_map_io,
 	.init_irq	= nuc900_init_irq,
 	.init_machine	= nuc960evb_init,
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 88633fe01a5..0e15dd9fbee 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -629,6 +629,23 @@ config IO_36
 
 comment "Processor Features"
 
+config ARM_LPAE
+	bool "Support for the Large Physical Address Extension"
+	depends on MMU && CPU_V7
+	help
+	  Say Y if you have an ARMv7 processor supporting the LPAE page
+	  table format and you would like to access memory beyond the
+	  4GB limit. The resulting kernel image will not run on
+	  processors without the LPA extension.
+
+	  If unsure, say N.
+
+config ARCH_PHYS_ADDR_T_64BIT
+	def_bool ARM_LPAE
+
+config ARCH_DMA_ADDR_T_64BIT
+	def_bool ARM_LPAE
+
 config ARM_THUMB
 	bool "Support Thumb user binaries"
 	depends on CPU_ARM720T || CPU_ARM740T || CPU_ARM920T || CPU_ARM922T || CPU_ARM925T || CPU_ARM926T || CPU_ARM940T || CPU_ARM946E || CPU_ARM1020 || CPU_ARM1020E || CPU_ARM1022 || CPU_ARM1026 || CPU_XSCALE || CPU_XSC3 || CPU_MOHAWK || CPU_V6 || CPU_V6K || CPU_V7 || CPU_FEROCEON
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index cfbcf8b9559..715eb1dbebb 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -968,7 +968,7 @@ static int __init alignment_init(void)
 		ai_usermode = safe_usermode(ai_usermode, false);
 	}
 
-	hook_fault_code(1, do_alignment, SIGBUS, BUS_ADRALN,
+	hook_fault_code(FAULT_CODE_ALIGNMENT, do_alignment, SIGBUS, BUS_ADRALN,
 			"alignment exception");
 
 	/*
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index 9ecfdb51195..3f9b9980478 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -16,9 +16,12 @@
  * along with this program; if not, write to the Free Software
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
  */
+#include <linux/err.h>
 #include <linux/init.h>
 #include <linux/spinlock.h>
 #include <linux/io.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
 
 #include <asm/cacheflush.h>
 #include <asm/hardware/cache-l2x0.h>
@@ -30,11 +33,19 @@ static DEFINE_SPINLOCK(l2x0_lock);
 static uint32_t l2x0_way_mask;	/* Bitmask of active ways */
 static uint32_t l2x0_size;
 
+struct l2x0_regs l2x0_saved_regs;
+
+struct l2x0_of_data {
+	void (*setup)(const struct device_node *, __u32 *, __u32 *);
+	void (*save)(void);
+	void (*resume)(void);
+};
+
 static inline void cache_wait_way(void __iomem *reg, unsigned long mask)
 {
 	/* wait for cache operation by line or way to complete */
 	while (readl_relaxed(reg) & mask)
-		;
+		cpu_relax();
 }
 
 #ifdef CONFIG_CACHE_PL310
@@ -277,7 +288,7 @@ static void l2x0_disable(void)
 	spin_unlock_irqrestore(&l2x0_lock, flags);
 }
 
-static void __init l2x0_unlock(__u32 cache_id)
+static void l2x0_unlock(__u32 cache_id)
 {
 	int lockregs;
 	int i;
@@ -353,6 +364,8 @@ void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask)
 		/* l2x0 controller is disabled */
 		writel_relaxed(aux, l2x0_base + L2X0_AUX_CTRL);
 
+		l2x0_saved_regs.aux_ctrl = aux;
+
 		l2x0_inv_all();
 
 		/* enable L2X0 */
@@ -372,3 +385,202 @@ void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask)
 	printk(KERN_INFO "l2x0: %d ways, CACHE_ID 0x%08x, AUX_CTRL 0x%08x, Cache size: %d B\n",
 			ways, cache_id, aux, l2x0_size);
 }
+
+#ifdef CONFIG_OF
+static void __init l2x0_of_setup(const struct device_node *np,
+				 __u32 *aux_val, __u32 *aux_mask)
+{
+	u32 data[2] = { 0, 0 };
+	u32 tag = 0;
+	u32 dirty = 0;
+	u32 val = 0, mask = 0;
+
+	of_property_read_u32(np, "arm,tag-latency", &tag);
+	if (tag) {
+		mask |= L2X0_AUX_CTRL_TAG_LATENCY_MASK;
+		val |= (tag - 1) << L2X0_AUX_CTRL_TAG_LATENCY_SHIFT;
+	}
+
+	of_property_read_u32_array(np, "arm,data-latency",
+				   data, ARRAY_SIZE(data));
+	if (data[0] && data[1]) {
+		mask |= L2X0_AUX_CTRL_DATA_RD_LATENCY_MASK |
+			L2X0_AUX_CTRL_DATA_WR_LATENCY_MASK;
+		val |= ((data[0] - 1) << L2X0_AUX_CTRL_DATA_RD_LATENCY_SHIFT) |
+		       ((data[1] - 1) << L2X0_AUX_CTRL_DATA_WR_LATENCY_SHIFT);
+	}
+
+	of_property_read_u32(np, "arm,dirty-latency", &dirty);
+	if (dirty) {
+		mask |= L2X0_AUX_CTRL_DIRTY_LATENCY_MASK;
+		val |= (dirty - 1) << L2X0_AUX_CTRL_DIRTY_LATENCY_SHIFT;
+	}
+
+	*aux_val &= ~mask;
+	*aux_val |= val;
+	*aux_mask &= ~mask;
+}
+
+static void __init pl310_of_setup(const struct device_node *np,
+				  __u32 *aux_val, __u32 *aux_mask)
+{
+	u32 data[3] = { 0, 0, 0 };
+	u32 tag[3] = { 0, 0, 0 };
+	u32 filter[2] = { 0, 0 };
+
+	of_property_read_u32_array(np, "arm,tag-latency", tag, ARRAY_SIZE(tag));
+	if (tag[0] && tag[1] && tag[2])
+		writel_relaxed(
+			((tag[0] - 1) << L2X0_LATENCY_CTRL_RD_SHIFT) |
+			((tag[1] - 1) << L2X0_LATENCY_CTRL_WR_SHIFT) |
+			((tag[2] - 1) << L2X0_LATENCY_CTRL_SETUP_SHIFT),
+			l2x0_base + L2X0_TAG_LATENCY_CTRL);
+
+	of_property_read_u32_array(np, "arm,data-latency",
+				   data, ARRAY_SIZE(data));
+	if (data[0] && data[1] && data[2])
+		writel_relaxed(
+			((data[0] - 1) << L2X0_LATENCY_CTRL_RD_SHIFT) |
+			((data[1] - 1) << L2X0_LATENCY_CTRL_WR_SHIFT) |
+			((data[2] - 1) << L2X0_LATENCY_CTRL_SETUP_SHIFT),
+			l2x0_base + L2X0_DATA_LATENCY_CTRL);
+
+	of_property_read_u32_array(np, "arm,filter-ranges",
+				   filter, ARRAY_SIZE(filter));
+	if (filter[1]) {
+		writel_relaxed(ALIGN(filter[0] + filter[1], SZ_1M),
+			       l2x0_base + L2X0_ADDR_FILTER_END);
+		writel_relaxed((filter[0] & ~(SZ_1M - 1)) | L2X0_ADDR_FILTER_EN,
+			       l2x0_base + L2X0_ADDR_FILTER_START);
+	}
+}
+
+static void __init pl310_save(void)
+{
+	u32 l2x0_revision = readl_relaxed(l2x0_base + L2X0_CACHE_ID) &
+		L2X0_CACHE_ID_RTL_MASK;
+
+	l2x0_saved_regs.tag_latency = readl_relaxed(l2x0_base +
+		L2X0_TAG_LATENCY_CTRL);
+	l2x0_saved_regs.data_latency = readl_relaxed(l2x0_base +
+		L2X0_DATA_LATENCY_CTRL);
+	l2x0_saved_regs.filter_end = readl_relaxed(l2x0_base +
+		L2X0_ADDR_FILTER_END);
+	l2x0_saved_regs.filter_start = readl_relaxed(l2x0_base +
+		L2X0_ADDR_FILTER_START);
+
+	if (l2x0_revision >= L2X0_CACHE_ID_RTL_R2P0) {
+		/*
+		 * From r2p0, there is Prefetch offset/control register
+		 */
+		l2x0_saved_regs.prefetch_ctrl = readl_relaxed(l2x0_base +
+			L2X0_PREFETCH_CTRL);
+		/*
+		 * From r3p0, there is Power control register
+		 */
+		if (l2x0_revision >= L2X0_CACHE_ID_RTL_R3P0)
+			l2x0_saved_regs.pwr_ctrl = readl_relaxed(l2x0_base +
+				L2X0_POWER_CTRL);
+	}
+}
+
+static void l2x0_resume(void)
+{
+	if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & 1)) {
+		/* restore aux ctrl and enable l2 */
+		l2x0_unlock(readl_relaxed(l2x0_base + L2X0_CACHE_ID));
+
+		writel_relaxed(l2x0_saved_regs.aux_ctrl, l2x0_base +
+			L2X0_AUX_CTRL);
+
+		l2x0_inv_all();
+
+		writel_relaxed(1, l2x0_base + L2X0_CTRL);
+	}
+}
+
+static void pl310_resume(void)
+{
+	u32 l2x0_revision;
+
+	if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & 1)) {
+		/* restore pl310 setup */
+		writel_relaxed(l2x0_saved_regs.tag_latency,
+			l2x0_base + L2X0_TAG_LATENCY_CTRL);
+		writel_relaxed(l2x0_saved_regs.data_latency,
+			l2x0_base + L2X0_DATA_LATENCY_CTRL);
+		writel_relaxed(l2x0_saved_regs.filter_end,
+			l2x0_base + L2X0_ADDR_FILTER_END);
+		writel_relaxed(l2x0_saved_regs.filter_start,
+			l2x0_base + L2X0_ADDR_FILTER_START);
+
+		l2x0_revision = readl_relaxed(l2x0_base + L2X0_CACHE_ID) &
+			L2X0_CACHE_ID_RTL_MASK;
+
+		if (l2x0_revision >= L2X0_CACHE_ID_RTL_R2P0) {
+			writel_relaxed(l2x0_saved_regs.prefetch_ctrl,
+				l2x0_base + L2X0_PREFETCH_CTRL);
+			if (l2x0_revision >= L2X0_CACHE_ID_RTL_R3P0)
+				writel_relaxed(l2x0_saved_regs.pwr_ctrl,
+					l2x0_base + L2X0_POWER_CTRL);
+		}
+	}
+
+	l2x0_resume();
+}
+
+static const struct l2x0_of_data pl310_data = {
+	pl310_of_setup,
+	pl310_save,
+	pl310_resume,
+};
+
+static const struct l2x0_of_data l2x0_data = {
+	l2x0_of_setup,
+	NULL,
+	l2x0_resume,
+};
+
+static const struct of_device_id l2x0_ids[] __initconst = {
+	{ .compatible = "arm,pl310-cache", .data = (void *)&pl310_data },
+	{ .compatible = "arm,l220-cache", .data = (void *)&l2x0_data },
+	{ .compatible = "arm,l210-cache", .data = (void *)&l2x0_data },
+	{}
+};
+
+int __init l2x0_of_init(__u32 aux_val, __u32 aux_mask)
+{
+	struct device_node *np;
+	struct l2x0_of_data *data;
+	struct resource res;
+
+	np = of_find_matching_node(NULL, l2x0_ids);
+	if (!np)
+		return -ENODEV;
+
+	if (of_address_to_resource(np, 0, &res))
+		return -ENODEV;
+
+	l2x0_base = ioremap(res.start, resource_size(&res));
+	if (!l2x0_base)
+		return -ENOMEM;
+
+	l2x0_saved_regs.phy_base = res.start;
+
+	data = of_match_node(l2x0_ids, np)->data;
+
+	/* L2 configuration can only be changed if the cache is disabled */
+	if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & 1)) {
+		if (data->setup)
+			data->setup(np, &aux_val, &aux_mask);
+	}
+
+	if (data->save)
+		data->save();
+
+	l2x0_init(l2x0_base, aux_val, aux_mask);
+
+	outer_cache.resume = data->resume;
+	return 0;
+}
+#endif
diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c
index b0ee9ba3cfa..fcdb1017cdc 100644
--- a/arch/arm/mm/context.c
+++ b/arch/arm/mm/context.c
@@ -22,6 +22,21 @@ unsigned int cpu_last_asid = ASID_FIRST_VERSION;
 DEFINE_PER_CPU(struct mm_struct *, current_mm);
 #endif
 
+#ifdef CONFIG_ARM_LPAE
+#define cpu_set_asid(asid) {						\
+	unsigned long ttbl, ttbh;					\
+	asm volatile(							\
+	"	mrrc	p15, 0, %0, %1, c2		@ read TTBR0\n"	\
+	"	mov	%1, %2, lsl #(48 - 32)		@ set ASID\n"	\
+	"	mcrr	p15, 0, %0, %1, c2		@ set TTBR0\n"	\
+	: "=&r" (ttbl), "=&r" (ttbh)					\
+	: "r" (asid & ~ASID_MASK));					\
+}
+#else
+#define cpu_set_asid(asid) \
+	asm("	mcr	p15, 0, %0, c13, c0, 1\n" : : "r" (asid))
+#endif
+
 /*
  * We fork()ed a process, and we need a new context for the child
  * to run in.  We reserve version 0 for initial tasks so we will
@@ -37,7 +52,7 @@ void __init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 static void flush_context(void)
 {
 	/* set the reserved ASID before flushing the TLB */
-	asm("mcr	p15, 0, %0, c13, c0, 1\n" : : "r" (0));
+	cpu_set_asid(0);
 	isb();
 	local_flush_tlb_all();
 	if (icache_is_vivt_asid_tagged()) {
@@ -99,7 +114,7 @@ static void reset_context(void *info)
 	set_mm_context(mm, asid);
 
 	/* set the new ASID */
-	asm("mcr	p15, 0, %0, c13, c0, 1\n" : : "r" (mm->context.id));
+	cpu_set_asid(mm->context.id);
 	isb();
 }
 
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index c3ff82f92d9..e4e7f6cba1a 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -18,12 +18,14 @@
 #include <linux/device.h>
 #include <linux/dma-mapping.h>
 #include <linux/highmem.h>
+#include <linux/slab.h>
 
 #include <asm/memory.h>
 #include <asm/highmem.h>
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
 #include <asm/sizes.h>
+#include <asm/mach/arch.h>
 
 #include "mm.h"
 
@@ -117,26 +119,36 @@ static void __dma_free_buffer(struct page *page, size_t size)
 }
 
 #ifdef CONFIG_MMU
-/* Sanity check size */
-#if (CONSISTENT_DMA_SIZE % SZ_2M)
-#error "CONSISTENT_DMA_SIZE must be multiple of 2MiB"
-#endif
 
-#define CONSISTENT_OFFSET(x)	(((unsigned long)(x) - CONSISTENT_BASE) >> PAGE_SHIFT)
-#define CONSISTENT_PTE_INDEX(x) (((unsigned long)(x) - CONSISTENT_BASE) >> PGDIR_SHIFT)
-#define NUM_CONSISTENT_PTES (CONSISTENT_DMA_SIZE >> PGDIR_SHIFT)
+#define CONSISTENT_OFFSET(x)	(((unsigned long)(x) - consistent_base) >> PAGE_SHIFT)
+#define CONSISTENT_PTE_INDEX(x) (((unsigned long)(x) - consistent_base) >> PMD_SHIFT)
 
 /*
  * These are the page tables (2MB each) covering uncached, DMA consistent allocations
  */
-static pte_t *consistent_pte[NUM_CONSISTENT_PTES];
+static pte_t **consistent_pte;
+
+#define DEFAULT_CONSISTENT_DMA_SIZE SZ_2M
+
+unsigned long consistent_base = CONSISTENT_END - DEFAULT_CONSISTENT_DMA_SIZE;
+
+void __init init_consistent_dma_size(unsigned long size)
+{
+	unsigned long base = CONSISTENT_END - ALIGN(size, SZ_2M);
+
+	BUG_ON(consistent_pte); /* Check we're called before DMA region init */
+	BUG_ON(base < VMALLOC_END);
+
+	/* Grow region to accommodate specified size  */
+	if (base < consistent_base)
+		consistent_base = base;
+}
 
 #include "vmregion.h"
 
 static struct arm_vmregion_head consistent_head = {
 	.vm_lock	= __SPIN_LOCK_UNLOCKED(&consistent_head.vm_lock),
 	.vm_list	= LIST_HEAD_INIT(consistent_head.vm_list),
-	.vm_start	= CONSISTENT_BASE,
 	.vm_end		= CONSISTENT_END,
 };
 
@@ -155,7 +167,17 @@ static int __init consistent_init(void)
 	pmd_t *pmd;
 	pte_t *pte;
 	int i = 0;
-	u32 base = CONSISTENT_BASE;
+	unsigned long base = consistent_base;
+	unsigned long num_ptes = (CONSISTENT_END - base) >> PGDIR_SHIFT;
+
+	consistent_pte = kmalloc(num_ptes * sizeof(pte_t), GFP_KERNEL);
+	if (!consistent_pte) {
+		pr_err("%s: no memory\n", __func__);
+		return -ENOMEM;
+	}
+
+	pr_debug("DMA memory: 0x%08lx - 0x%08lx:\n", base, CONSISTENT_END);
+	consistent_head.vm_start = base;
 
 	do {
 		pgd = pgd_offset(&init_mm, base);
@@ -183,7 +205,7 @@ static int __init consistent_init(void)
 		}
 
 		consistent_pte[i++] = pte;
-		base += (1 << PGDIR_SHIFT);
+		base += PMD_SIZE;
 	} while (base < CONSISTENT_END);
 
 	return ret;
@@ -198,7 +220,7 @@ __dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot)
 	size_t align;
 	int bit;
 
-	if (!consistent_pte[0]) {
+	if (!consistent_pte) {
 		printk(KERN_ERR "%s: not initialised\n", __func__);
 		dump_stack();
 		return NULL;
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index 3b5ea68acbb..0a7d73fc984 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -26,19 +26,6 @@
 
 #include "fault.h"
 
-/*
- * Fault status register encodings.  We steal bit 31 for our own purposes.
- */
-#define FSR_LNX_PF		(1 << 31)
-#define FSR_WRITE		(1 << 11)
-#define FSR_FS4			(1 << 10)
-#define FSR_FS3_0		(15)
-
-static inline int fsr_fs(unsigned int fsr)
-{
-	return (fsr & FSR_FS3_0) | (fsr & FSR_FS4) >> 6;
-}
-
 #ifdef CONFIG_MMU
 
 #ifdef CONFIG_KPROBES
@@ -122,8 +109,10 @@ void show_pte(struct mm_struct *mm, unsigned long addr)
 
 		pte = pte_offset_map(pmd, addr);
 		printk(", *pte=%08llx", (long long)pte_val(*pte));
+#ifndef CONFIG_ARM_LPAE
 		printk(", *ppte=%08llx",
 		       (long long)pte_val(pte[PTE_HWTABLE_PTRS]));
+#endif
 		pte_unmap(pte);
 	} while(0);
 
@@ -230,7 +219,7 @@ static inline bool access_error(unsigned int fsr, struct vm_area_struct *vma)
 
 static int __kprobes
 __do_page_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr,
-		struct task_struct *tsk)
+		unsigned int flags, struct task_struct *tsk)
 {
 	struct vm_area_struct *vma;
 	int fault;
@@ -252,18 +241,7 @@ good_area:
 		goto out;
 	}
 
-	/*
-	 * If for any reason at all we couldn't handle the fault, make
-	 * sure we exit gracefully rather than endlessly redo the fault.
-	 */
-	fault = handle_mm_fault(mm, vma, addr & PAGE_MASK, (fsr & FSR_WRITE) ? FAULT_FLAG_WRITE : 0);
-	if (unlikely(fault & VM_FAULT_ERROR))
-		return fault;
-	if (fault & VM_FAULT_MAJOR)
-		tsk->maj_flt++;
-	else
-		tsk->min_flt++;
-	return fault;
+	return handle_mm_fault(mm, vma, addr & PAGE_MASK, flags);
 
 check_stack:
 	if (vma->vm_flags & VM_GROWSDOWN && !expand_stack(vma, addr))
@@ -278,6 +256,9 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	struct task_struct *tsk;
 	struct mm_struct *mm;
 	int fault, sig, code;
+	int write = fsr & FSR_WRITE;
+	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
+				(write ? FAULT_FLAG_WRITE : 0);
 
 	if (notify_page_fault(regs, fsr))
 		return 0;
@@ -304,6 +285,7 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	if (!down_read_trylock(&mm->mmap_sem)) {
 		if (!user_mode(regs) && !search_exception_tables(regs->ARM_pc))
 			goto no_context;
+retry:
 		down_read(&mm->mmap_sem);
 	} else {
 		/*
@@ -319,14 +301,41 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 #endif
 	}
 
-	fault = __do_page_fault(mm, addr, fsr, tsk);
-	up_read(&mm->mmap_sem);
+	fault = __do_page_fault(mm, addr, fsr, flags, tsk);
+
+	/* If we need to retry but a fatal signal is pending, handle the
+	 * signal first. We do not need to release the mmap_sem because
+	 * it would already be released in __lock_page_or_retry in
+	 * mm/filemap.c. */
+	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+		return 0;
+
+	/*
+	 * Major/minor page fault accounting is only done on the
+	 * initial attempt. If we go through a retry, it is extremely
+	 * likely that the page will be found in page cache at that point.
+	 */
 
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
-	if (fault & VM_FAULT_MAJOR)
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, addr);
-	else if (fault & VM_FAULT_MINOR)
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, addr);
+	if (flags & FAULT_FLAG_ALLOW_RETRY) {
+		if (fault & VM_FAULT_MAJOR) {
+			tsk->maj_flt++;
+			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
+					regs, addr);
+		} else {
+			tsk->min_flt++;
+			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1,
+					regs, addr);
+		}
+		if (fault & VM_FAULT_RETRY) {
+			/* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
+			* of starvation. */
+			flags &= ~FAULT_FLAG_ALLOW_RETRY;
+			goto retry;
+		}
+	}
+
+	up_read(&mm->mmap_sem);
 
 	/*
 	 * Handle the "normal" case first - VM_FAULT_MAJOR / VM_FAULT_MINOR
@@ -440,6 +449,12 @@ do_translation_fault(unsigned long addr, unsigned int fsr,
 	pmd = pmd_offset(pud, addr);
 	pmd_k = pmd_offset(pud_k, addr);
 
+#ifdef CONFIG_ARM_LPAE
+	/*
+	 * Only one hardware entry per PMD with LPAE.
+	 */
+	index = 0;
+#else
 	/*
 	 * On ARM one Linux PGD entry contains two hardware entries (see page
 	 * tables layout in pgtable.h). We normally guarantee that we always
@@ -449,6 +464,7 @@ do_translation_fault(unsigned long addr, unsigned int fsr,
 	 * for the first of pair.
 	 */
 	index = (addr >> SECTION_SHIFT) & 1;
+#endif
 	if (pmd_none(pmd_k[index]))
 		goto bad_area;
 
@@ -488,55 +504,20 @@ do_bad(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	return 1;
 }
 
-static struct fsr_info {
+struct fsr_info {
 	int	(*fn)(unsigned long addr, unsigned int fsr, struct pt_regs *regs);
 	int	sig;
 	int	code;
 	const char *name;
-} fsr_info[] = {
-	/*
-	 * The following are the standard ARMv3 and ARMv4 aborts.  ARMv5
-	 * defines these to be "precise" aborts.
-	 */
-	{ do_bad,		SIGSEGV, 0,		"vector exception"		   },
-	{ do_bad,		SIGBUS,	 BUS_ADRALN,	"alignment exception"		   },
-	{ do_bad,		SIGKILL, 0,		"terminal exception"		   },
-	{ do_bad,		SIGBUS,	 BUS_ADRALN,	"alignment exception"		   },
-	{ do_bad,		SIGBUS,	 0,		"external abort on linefetch"	   },
-	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"section translation fault"	   },
-	{ do_bad,		SIGBUS,	 0,		"external abort on linefetch"	   },
-	{ do_page_fault,	SIGSEGV, SEGV_MAPERR,	"page translation fault"	   },
-	{ do_bad,		SIGBUS,	 0,		"external abort on non-linefetch"  },
-	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"section domain fault"		   },
-	{ do_bad,		SIGBUS,	 0,		"external abort on non-linefetch"  },
-	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"page domain fault"		   },
-	{ do_bad,		SIGBUS,	 0,		"external abort on translation"	   },
-	{ do_sect_fault,	SIGSEGV, SEGV_ACCERR,	"section permission fault"	   },
-	{ do_bad,		SIGBUS,	 0,		"external abort on translation"	   },
-	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"page permission fault"		   },
-	/*
-	 * The following are "imprecise" aborts, which are signalled by bit
-	 * 10 of the FSR, and may not be recoverable.  These are only
-	 * supported if the CPU abort handler supports bit 10.
-	 */
-	{ do_bad,		SIGBUS,  0,		"unknown 16"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 17"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 18"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 19"			   },
-	{ do_bad,		SIGBUS,  0,		"lock abort"			   }, /* xscale */
-	{ do_bad,		SIGBUS,  0,		"unknown 21"			   },
-	{ do_bad,		SIGBUS,  BUS_OBJERR,	"imprecise external abort"	   }, /* xscale */
-	{ do_bad,		SIGBUS,  0,		"unknown 23"			   },
-	{ do_bad,		SIGBUS,  0,		"dcache parity error"		   }, /* xscale */
-	{ do_bad,		SIGBUS,  0,		"unknown 25"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 26"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 27"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 28"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 29"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 30"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 31"			   }
 };
 
+/* FSR definition */
+#ifdef CONFIG_ARM_LPAE
+#include "fsr-3level.c"
+#else
+#include "fsr-2level.c"
+#endif
+
 void __init
 hook_fault_code(int nr, int (*fn)(unsigned long, unsigned int, struct pt_regs *),
 		int sig, int code, const char *name)
@@ -572,42 +553,6 @@ do_DataAbort(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	arm_notify_die("", regs, &info, fsr, 0);
 }
 
-
-static struct fsr_info ifsr_info[] = {
-	{ do_bad,		SIGBUS,  0,		"unknown 0"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 1"			   },
-	{ do_bad,		SIGBUS,  0,		"debug event"			   },
-	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"section access flag fault"	   },
-	{ do_bad,		SIGBUS,  0,		"unknown 4"			   },
-	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"section translation fault"	   },
-	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"page access flag fault"	   },
-	{ do_page_fault,	SIGSEGV, SEGV_MAPERR,	"page translation fault"	   },
-	{ do_bad,		SIGBUS,	 0,		"external abort on non-linefetch"  },
-	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"section domain fault"		   },
-	{ do_bad,		SIGBUS,  0,		"unknown 10"			   },
-	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"page domain fault"		   },
-	{ do_bad,		SIGBUS,	 0,		"external abort on translation"	   },
-	{ do_sect_fault,	SIGSEGV, SEGV_ACCERR,	"section permission fault"	   },
-	{ do_bad,		SIGBUS,	 0,		"external abort on translation"	   },
-	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"page permission fault"		   },
-	{ do_bad,		SIGBUS,  0,		"unknown 16"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 17"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 18"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 19"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 20"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 21"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 22"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 23"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 24"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 25"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 26"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 27"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 28"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 29"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 30"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 31"			   },
-};
-
 void __init
 hook_ifault_code(int nr, int (*fn)(unsigned long, unsigned int, struct pt_regs *),
 		 int sig, int code, const char *name)
@@ -640,6 +585,7 @@ do_PrefetchAbort(unsigned long addr, unsigned int ifsr, struct pt_regs *regs)
 	arm_notify_die("", regs, &info, ifsr, 0);
 }
 
+#ifndef CONFIG_ARM_LPAE
 static int __init exceptions_init(void)
 {
 	if (cpu_architecture() >= CPU_ARCH_ARMv6) {
@@ -662,3 +608,4 @@ static int __init exceptions_init(void)
 }
 
 arch_initcall(exceptions_init);
+#endif
diff --git a/arch/arm/mm/fault.h b/arch/arm/mm/fault.h
index 49e9e3804de..cf08bdfbe0d 100644
--- a/arch/arm/mm/fault.h
+++ b/arch/arm/mm/fault.h
@@ -1,3 +1,28 @@
-void do_bad_area(unsigned long addr, unsigned int fsr, struct pt_regs *regs);
+#ifndef __ARCH_ARM_FAULT_H
+#define __ARCH_ARM_FAULT_H
+
+/*
+ * Fault status register encodings.  We steal bit 31 for our own purposes.
+ */
+#define FSR_LNX_PF		(1 << 31)
+#define FSR_WRITE		(1 << 11)
+#define FSR_FS4			(1 << 10)
+#define FSR_FS3_0		(15)
+#define FSR_FS5_0		(0x3f)
+
+#ifdef CONFIG_ARM_LPAE
+static inline int fsr_fs(unsigned int fsr)
+{
+	return fsr & FSR_FS5_0;
+}
+#else
+static inline int fsr_fs(unsigned int fsr)
+{
+	return (fsr & FSR_FS3_0) | (fsr & FSR_FS4) >> 6;
+}
+#endif
 
+void do_bad_area(unsigned long addr, unsigned int fsr, struct pt_regs *regs);
 unsigned long search_exception_table(unsigned long addr);
+
+#endif	/* __ARCH_ARM_FAULT_H */
diff --git a/arch/arm/mm/fsr-2level.c b/arch/arm/mm/fsr-2level.c
new file mode 100644
index 00000000000..9260894e394
--- /dev/null
+++ b/arch/arm/mm/fsr-2level.c
@@ -0,0 +1,78 @@
+static struct fsr_info fsr_info[] = {
+	/*
+	 * The following are the standard ARMv3 and ARMv4 aborts.  ARMv5
+	 * defines these to be "precise" aborts.
+	 */
+	{ do_bad,		SIGSEGV, 0,		"vector exception"		   },
+	{ do_bad,		SIGBUS,	 BUS_ADRALN,	"alignment exception"		   },
+	{ do_bad,		SIGKILL, 0,		"terminal exception"		   },
+	{ do_bad,		SIGBUS,	 BUS_ADRALN,	"alignment exception"		   },
+	{ do_bad,		SIGBUS,	 0,		"external abort on linefetch"	   },
+	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"section translation fault"	   },
+	{ do_bad,		SIGBUS,	 0,		"external abort on linefetch"	   },
+	{ do_page_fault,	SIGSEGV, SEGV_MAPERR,	"page translation fault"	   },
+	{ do_bad,		SIGBUS,	 0,		"external abort on non-linefetch"  },
+	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"section domain fault"		   },
+	{ do_bad,		SIGBUS,	 0,		"external abort on non-linefetch"  },
+	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"page domain fault"		   },
+	{ do_bad,		SIGBUS,	 0,		"external abort on translation"	   },
+	{ do_sect_fault,	SIGSEGV, SEGV_ACCERR,	"section permission fault"	   },
+	{ do_bad,		SIGBUS,	 0,		"external abort on translation"	   },
+	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"page permission fault"		   },
+	/*
+	 * The following are "imprecise" aborts, which are signalled by bit
+	 * 10 of the FSR, and may not be recoverable.  These are only
+	 * supported if the CPU abort handler supports bit 10.
+	 */
+	{ do_bad,		SIGBUS,  0,		"unknown 16"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 17"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 18"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 19"			   },
+	{ do_bad,		SIGBUS,  0,		"lock abort"			   }, /* xscale */
+	{ do_bad,		SIGBUS,  0,		"unknown 21"			   },
+	{ do_bad,		SIGBUS,  BUS_OBJERR,	"imprecise external abort"	   }, /* xscale */
+	{ do_bad,		SIGBUS,  0,		"unknown 23"			   },
+	{ do_bad,		SIGBUS,  0,		"dcache parity error"		   }, /* xscale */
+	{ do_bad,		SIGBUS,  0,		"unknown 25"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 26"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 27"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 28"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 29"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 30"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 31"			   }
+};
+
+static struct fsr_info ifsr_info[] = {
+	{ do_bad,		SIGBUS,  0,		"unknown 0"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 1"			   },
+	{ do_bad,		SIGBUS,  0,		"debug event"			   },
+	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"section access flag fault"	   },
+	{ do_bad,		SIGBUS,  0,		"unknown 4"			   },
+	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"section translation fault"	   },
+	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"page access flag fault"	   },
+	{ do_page_fault,	SIGSEGV, SEGV_MAPERR,	"page translation fault"	   },
+	{ do_bad,		SIGBUS,	 0,		"external abort on non-linefetch"  },
+	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"section domain fault"		   },
+	{ do_bad,		SIGBUS,  0,		"unknown 10"			   },
+	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"page domain fault"		   },
+	{ do_bad,		SIGBUS,	 0,		"external abort on translation"	   },
+	{ do_sect_fault,	SIGSEGV, SEGV_ACCERR,	"section permission fault"	   },
+	{ do_bad,		SIGBUS,	 0,		"external abort on translation"	   },
+	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"page permission fault"		   },
+	{ do_bad,		SIGBUS,  0,		"unknown 16"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 17"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 18"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 19"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 20"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 21"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 22"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 23"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 24"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 25"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 26"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 27"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 28"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 29"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 30"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 31"			   },
+};
diff --git a/arch/arm/mm/fsr-3level.c b/arch/arm/mm/fsr-3level.c
new file mode 100644
index 00000000000..05a4e943183
--- /dev/null
+++ b/arch/arm/mm/fsr-3level.c
@@ -0,0 +1,68 @@
+static struct fsr_info fsr_info[] = {
+	{ do_bad,		SIGBUS,  0,		"unknown 0"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 1"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 2"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 3"			},
+	{ do_bad,		SIGBUS,  0,		"reserved translation fault"	},
+	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"level 1 translation fault"	},
+	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"level 2 translation fault"	},
+	{ do_page_fault,	SIGSEGV, SEGV_MAPERR,	"level 3 translation fault"	},
+	{ do_bad,		SIGBUS,  0,		"reserved access flag fault"	},
+	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"level 1 access flag fault"	},
+	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"level 2 access flag fault"	},
+	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 3 access flag fault"	},
+	{ do_bad,		SIGBUS,  0,		"reserved permission fault"	},
+	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"level 1 permission fault"	},
+	{ do_sect_fault,	SIGSEGV, SEGV_ACCERR,	"level 2 permission fault"	},
+	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 3 permission fault"	},
+	{ do_bad,		SIGBUS,  0,		"synchronous external abort"	},
+	{ do_bad,		SIGBUS,  0,		"asynchronous external abort"	},
+	{ do_bad,		SIGBUS,  0,		"unknown 18"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 19"			},
+	{ do_bad,		SIGBUS,  0,		"synchronous abort (translation table walk)" },
+	{ do_bad,		SIGBUS,  0,		"synchronous abort (translation table walk)" },
+	{ do_bad,		SIGBUS,  0,		"synchronous abort (translation table walk)" },
+	{ do_bad,		SIGBUS,  0,		"synchronous abort (translation table walk)" },
+	{ do_bad,		SIGBUS,  0,		"synchronous parity error"	},
+	{ do_bad,		SIGBUS,  0,		"asynchronous parity error"	},
+	{ do_bad,		SIGBUS,  0,		"unknown 26"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 27"			},
+	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk" },
+	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk" },
+	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk" },
+	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk" },
+	{ do_bad,		SIGBUS,  0,		"unknown 32"			},
+	{ do_bad,		SIGBUS,  BUS_ADRALN,	"alignment fault"		},
+	{ do_bad,		SIGBUS,  0,		"debug event"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 35"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 36"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 37"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 38"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 39"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 40"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 41"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 42"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 43"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 44"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 45"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 46"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 47"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 48"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 49"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 50"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 51"			},
+	{ do_bad,		SIGBUS,  0,		"implementation fault (lockdown abort)" },
+	{ do_bad,		SIGBUS,  0,		"unknown 53"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 54"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 55"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 56"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 57"			},
+	{ do_bad,		SIGBUS,  0,		"implementation fault (coprocessor abort)" },
+	{ do_bad,		SIGBUS,  0,		"unknown 59"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 60"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 61"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 62"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 63"			},
+};
+
+#define ifsr_info	fsr_info
diff --git a/arch/arm/mm/idmap.c b/arch/arm/mm/idmap.c
index 2be9139a4ef..24e06555bee 100644
--- a/arch/arm/mm/idmap.c
+++ b/arch/arm/mm/idmap.c
@@ -1,9 +1,36 @@
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 
 #include <asm/cputype.h>
 #include <asm/pgalloc.h>
 #include <asm/pgtable.h>
 
+#ifdef CONFIG_ARM_LPAE
+static void idmap_add_pmd(pud_t *pud, unsigned long addr, unsigned long end,
+	unsigned long prot)
+{
+	pmd_t *pmd;
+	unsigned long next;
+
+	if (pud_none_or_clear_bad(pud) || (pud_val(*pud) & L_PGD_SWAPPER)) {
+		pmd = pmd_alloc_one(NULL, addr);
+		if (!pmd) {
+			pr_warning("Failed to allocate identity pmd.\n");
+			return;
+		}
+		pud_populate(NULL, pud, pmd);
+		pmd += pmd_index(addr);
+	} else
+		pmd = pmd_offset(pud, addr);
+
+	do {
+		next = pmd_addr_end(addr, end);
+		*pmd = __pmd((addr & PMD_MASK) | prot);
+		flush_pmd_entry(pmd);
+	} while (pmd++, addr = next, addr != end);
+}
+#else	/* !CONFIG_ARM_LPAE */
 static void idmap_add_pmd(pud_t *pud, unsigned long addr, unsigned long end,
 	unsigned long prot)
 {
@@ -15,6 +42,7 @@ static void idmap_add_pmd(pud_t *pud, unsigned long addr, unsigned long end,
 	pmd[1] = __pmd(addr);
 	flush_pmd_entry(pmd);
 }
+#endif	/* CONFIG_ARM_LPAE */
 
 static void idmap_add_pud(pgd_t *pgd, unsigned long addr, unsigned long end,
 	unsigned long prot)
@@ -32,7 +60,7 @@ void identity_mapping_add(pgd_t *pgd, unsigned long addr, unsigned long end)
 {
 	unsigned long prot, next;
 
-	prot = PMD_TYPE_SECT | PMD_SECT_AP_WRITE;
+	prot = PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_SECT_AF;
 	if (cpu_architecture() <= CPU_ARCH_ARMv5TEJ && !cpu_is_xscale())
 		prot |= PMD_BIT4;
 
@@ -46,7 +74,11 @@ void identity_mapping_add(pgd_t *pgd, unsigned long addr, unsigned long end)
 #ifdef CONFIG_SMP
 static void idmap_del_pmd(pud_t *pud, unsigned long addr, unsigned long end)
 {
-	pmd_t *pmd = pmd_offset(pud, addr);
+	pmd_t *pmd;
+
+	if (pud_none_or_clear_bad(pud))
+		return;
+	pmd = pmd_offset(pud, addr);
 	pmd_clear(pmd);
 }
 
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index f8037ba338a..04e9a92bb47 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -660,9 +660,6 @@ void __init mem_init(void)
 			"    ITCM    : 0x%08lx - 0x%08lx   (%4ld kB)\n"
 #endif
 			"    fixmap  : 0x%08lx - 0x%08lx   (%4ld kB)\n"
-#ifdef CONFIG_MMU
-			"    DMA     : 0x%08lx - 0x%08lx   (%4ld MB)\n"
-#endif
 			"    vmalloc : 0x%08lx - 0x%08lx   (%4ld MB)\n"
 			"    lowmem  : 0x%08lx - 0x%08lx   (%4ld MB)\n"
 #ifdef CONFIG_HIGHMEM
@@ -681,9 +678,6 @@ void __init mem_init(void)
 			MLK(ITCM_OFFSET, (unsigned long) itcm_end),
 #endif
 			MLK(FIXADDR_START, FIXADDR_TOP),
-#ifdef CONFIG_MMU
-			MLM(CONSISTENT_BASE, CONSISTENT_END),
-#endif
 			MLM(VMALLOC_START, VMALLOC_END),
 			MLM(PAGE_OFFSET, (unsigned long)high_memory),
 #ifdef CONFIG_HIGHMEM
@@ -706,9 +700,6 @@ void __init mem_init(void)
 	 * be detected at build time already.
 	 */
 #ifdef CONFIG_MMU
-	BUILD_BUG_ON(VMALLOC_END			> CONSISTENT_BASE);
-	BUG_ON(VMALLOC_END				> CONSISTENT_BASE);
-
 	BUILD_BUG_ON(TASK_SIZE				> MODULES_VADDR);
 	BUG_ON(TASK_SIZE 				> MODULES_VADDR);
 #endif
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index ab506272b2d..645011bf8d4 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -64,7 +64,7 @@ void __check_kvm_seq(struct mm_struct *mm)
 	} while (seq != init_mm.context.kvm_seq);
 }
 
-#ifndef CONFIG_SMP
+#if !defined(CONFIG_SMP) && !defined(CONFIG_ARM_LPAE)
 /*
  * Section support is unsafe on SMP - If you iounmap and ioremap a region,
  * the other CPUs will not see this change until their next context switch.
@@ -79,13 +79,16 @@ static void unmap_area_sections(unsigned long virt, unsigned long size)
 {
 	unsigned long addr = virt, end = virt + (size & ~(SZ_1M - 1));
 	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmdp;
 
 	flush_cache_vunmap(addr, end);
 	pgd = pgd_offset_k(addr);
+	pud = pud_offset(pgd, addr);
+	pmdp = pmd_offset(pud, addr);
 	do {
-		pmd_t pmd, *pmdp = pmd_offset(pgd, addr);
+		pmd_t pmd = *pmdp;
 
-		pmd = *pmdp;
 		if (!pmd_none(pmd)) {
 			/*
 			 * Clear the PMD from the page table, and
@@ -104,8 +107,8 @@ static void unmap_area_sections(unsigned long virt, unsigned long size)
 				pte_free_kernel(&init_mm, pmd_page_vaddr(pmd));
 		}
 
-		addr += PGDIR_SIZE;
-		pgd++;
+		addr += PMD_SIZE;
+		pmdp += 2;
 	} while (addr < end);
 
 	/*
@@ -124,6 +127,8 @@ remap_area_sections(unsigned long virt, unsigned long pfn,
 {
 	unsigned long addr = virt, end = virt + size;
 	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;
 
 	/*
 	 * Remove and free any PTE-based mapping, and
@@ -132,17 +137,17 @@ remap_area_sections(unsigned long virt, unsigned long pfn,
 	unmap_area_sections(virt, size);
 
 	pgd = pgd_offset_k(addr);
+	pud = pud_offset(pgd, addr);
+	pmd = pmd_offset(pud, addr);
 	do {
-		pmd_t *pmd = pmd_offset(pgd, addr);
-
 		pmd[0] = __pmd(__pfn_to_phys(pfn) | type->prot_sect);
 		pfn += SZ_1M >> PAGE_SHIFT;
 		pmd[1] = __pmd(__pfn_to_phys(pfn) | type->prot_sect);
 		pfn += SZ_1M >> PAGE_SHIFT;
 		flush_pmd_entry(pmd);
 
-		addr += PGDIR_SIZE;
-		pgd++;
+		addr += PMD_SIZE;
+		pmd += 2;
 	} while (addr < end);
 
 	return 0;
@@ -154,6 +159,8 @@ remap_area_supersections(unsigned long virt, unsigned long pfn,
 {
 	unsigned long addr = virt, end = virt + size;
 	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;
 
 	/*
 	 * Remove and free any PTE-based mapping, and
@@ -162,6 +169,8 @@ remap_area_supersections(unsigned long virt, unsigned long pfn,
 	unmap_area_sections(virt, size);
 
 	pgd = pgd_offset_k(virt);
+	pud = pud_offset(pgd, addr);
+	pmd = pmd_offset(pud, addr);
 	do {
 		unsigned long super_pmd_val, i;
 
@@ -170,14 +179,12 @@ remap_area_supersections(unsigned long virt, unsigned long pfn,
 		super_pmd_val |= ((pfn >> (32 - PAGE_SHIFT)) & 0xf) << 20;
 
 		for (i = 0; i < 8; i++) {
-			pmd_t *pmd = pmd_offset(pgd, addr);
-
 			pmd[0] = __pmd(super_pmd_val);
 			pmd[1] = __pmd(super_pmd_val);
 			flush_pmd_entry(pmd);
 
-			addr += PGDIR_SIZE;
-			pgd++;
+			addr += PMD_SIZE;
+			pmd += 2;
 		}
 
 		pfn += SUPERSECTION_SIZE >> PAGE_SHIFT;
@@ -195,11 +202,13 @@ void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn,
 	unsigned long addr;
  	struct vm_struct * area;
 
+#ifndef CONFIG_ARM_LPAE
 	/*
 	 * High mappings must be supersection aligned
 	 */
 	if (pfn >= 0x100000 && (__pfn_to_phys(pfn) & ~SUPERSECTION_MASK))
 		return NULL;
+#endif
 
 	/*
 	 * Don't allow RAM to be mapped - this causes problems with ARMv6+
@@ -221,7 +230,7 @@ void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn,
  		return NULL;
  	addr = (unsigned long)area->addr;
 
-#ifndef CONFIG_SMP
+#if !defined(CONFIG_SMP) && !defined(CONFIG_ARM_LPAE)
 	if (DOMAIN_IO == 0 &&
 	    (((cpu_architecture() >= CPU_ARCH_ARMv6) && (get_cr() & CR_XP)) ||
 	       cpu_is_xsc3()) && pfn >= 0x100000 &&
@@ -292,7 +301,7 @@ EXPORT_SYMBOL(__arm_ioremap);
 void __iounmap(volatile void __iomem *io_addr)
 {
 	void *addr = (void *)(PAGE_MASK & (unsigned long)io_addr);
-#ifndef CONFIG_SMP
+#if !defined(CONFIG_SMP) && !defined(CONFIG_ARM_LPAE)
 	struct vm_struct **p, *tmp;
 
 	/*
diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h
index 010566799c8..ad7cce3bc43 100644
--- a/arch/arm/mm/mm.h
+++ b/arch/arm/mm/mm.h
@@ -12,8 +12,8 @@ static inline pmd_t *pmd_off_k(unsigned long virt)
 
 struct mem_type {
 	pteval_t prot_pte;
-	unsigned int prot_l1;
-	unsigned int prot_sect;
+	pmdval_t prot_l1;
+	pmdval_t prot_sect;
 	unsigned int domain;
 };
 
diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c
index 74be05f3e03..c2809d7990b 100644
--- a/arch/arm/mm/mmap.c
+++ b/arch/arm/mm/mmap.c
@@ -9,13 +9,51 @@
 #include <linux/io.h>
 #include <linux/personality.h>
 #include <linux/random.h>
-#include <asm/cputype.h>
-#include <asm/system.h>
+#include <asm/cachetype.h>
+
+static inline unsigned long COLOUR_ALIGN_DOWN(unsigned long addr,
+					      unsigned long pgoff)
+{
+	unsigned long base = addr & ~(SHMLBA-1);
+	unsigned long off = (pgoff << PAGE_SHIFT) & (SHMLBA-1);
+
+	if (base + off <= addr)
+		return base + off;
+
+	return base - off;
+}
 
 #define COLOUR_ALIGN(addr,pgoff)		\
 	((((addr)+SHMLBA-1)&~(SHMLBA-1)) +	\
 	 (((pgoff)<<PAGE_SHIFT) & (SHMLBA-1)))
 
+/* gap between mmap and stack */
+#define MIN_GAP (128*1024*1024UL)
+#define MAX_GAP ((TASK_SIZE)/6*5)
+
+static int mmap_is_legacy(void)
+{
+	if (current->personality & ADDR_COMPAT_LAYOUT)
+		return 1;
+
+	if (rlimit(RLIMIT_STACK) == RLIM_INFINITY)
+		return 1;
+
+	return sysctl_legacy_va_layout;
+}
+
+static unsigned long mmap_base(unsigned long rnd)
+{
+	unsigned long gap = rlimit(RLIMIT_STACK);
+
+	if (gap < MIN_GAP)
+		gap = MIN_GAP;
+	else if (gap > MAX_GAP)
+		gap = MAX_GAP;
+
+	return PAGE_ALIGN(TASK_SIZE - gap - rnd);
+}
+
 /*
  * We need to ensure that shared mappings are correctly aligned to
  * avoid aliasing issues with VIPT caches.  We need to ensure that
@@ -32,25 +70,15 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
 	unsigned long start_addr;
-#if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_V6K)
-	unsigned int cache_type;
-	int do_align = 0, aliasing = 0;
+	int do_align = 0;
+	int aliasing = cache_is_vipt_aliasing() || icache_is_vipt_aliasing();
 
 	/*
 	 * We only need to do colour alignment if either the I or D
-	 * caches alias.  This is indicated by bits 9 and 21 of the
-	 * cache type register.
+	 * caches alias.
 	 */
-	cache_type = read_cpuid_cachetype();
-	if (cache_type != read_cpuid_id()) {
-		aliasing = (cache_type | cache_type >> 12) & (1 << 11);
-		if (aliasing)
-			do_align = filp || flags & MAP_SHARED;
-	}
-#else
-#define do_align 0
-#define aliasing 0
-#endif
+	if (aliasing)
+		do_align = filp || (flags & MAP_SHARED);
 
 	/*
 	 * We enforce the MAP_FIXED case.
@@ -79,13 +107,9 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 	if (len > mm->cached_hole_size) {
 	        start_addr = addr = mm->free_area_cache;
 	} else {
-	        start_addr = addr = TASK_UNMAPPED_BASE;
+	        start_addr = addr = mm->mmap_base;
 	        mm->cached_hole_size = 0;
 	}
-	/* 8 bits of randomness in 20 address space bits */
-	if ((current->flags & PF_RANDOMIZE) &&
-	    !(current->personality & ADDR_NO_RANDOMIZE))
-		addr += (get_random_int() % (1 << 8)) << PAGE_SHIFT;
 
 full_search:
 	if (do_align)
@@ -122,6 +146,134 @@ full_search:
 	}
 }
 
+unsigned long
+arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
+			const unsigned long len, const unsigned long pgoff,
+			const unsigned long flags)
+{
+	struct vm_area_struct *vma;
+	struct mm_struct *mm = current->mm;
+	unsigned long addr = addr0;
+	int do_align = 0;
+	int aliasing = cache_is_vipt_aliasing() || icache_is_vipt_aliasing();
+
+	/*
+	 * We only need to do colour alignment if either the I or D
+	 * caches alias.
+	 */
+	if (aliasing)
+		do_align = filp || (flags & MAP_SHARED);
+
+	/* requested length too big for entire address space */
+	if (len > TASK_SIZE)
+		return -ENOMEM;
+
+	if (flags & MAP_FIXED) {
+		if (aliasing && flags & MAP_SHARED &&
+		    (addr - (pgoff << PAGE_SHIFT)) & (SHMLBA - 1))
+			return -EINVAL;
+		return addr;
+	}
+
+	/* requesting a specific address */
+	if (addr) {
+		if (do_align)
+			addr = COLOUR_ALIGN(addr, pgoff);
+		else
+			addr = PAGE_ALIGN(addr);
+		vma = find_vma(mm, addr);
+		if (TASK_SIZE - len >= addr &&
+				(!vma || addr + len <= vma->vm_start))
+			return addr;
+	}
+
+	/* check if free_area_cache is useful for us */
+	if (len <= mm->cached_hole_size) {
+		mm->cached_hole_size = 0;
+		mm->free_area_cache = mm->mmap_base;
+	}
+
+	/* either no address requested or can't fit in requested address hole */
+	addr = mm->free_area_cache;
+	if (do_align) {
+		unsigned long base = COLOUR_ALIGN_DOWN(addr - len, pgoff);
+		addr = base + len;
+	}
+
+	/* make sure it can fit in the remaining address space */
+	if (addr > len) {
+		vma = find_vma(mm, addr-len);
+		if (!vma || addr <= vma->vm_start)
+			/* remember the address as a hint for next time */
+			return (mm->free_area_cache = addr-len);
+	}
+
+	if (mm->mmap_base < len)
+		goto bottomup;
+
+	addr = mm->mmap_base - len;
+	if (do_align)
+		addr = COLOUR_ALIGN_DOWN(addr, pgoff);
+
+	do {
+		/*
+		 * Lookup failure means no vma is above this address,
+		 * else if new region fits below vma->vm_start,
+		 * return with success:
+		 */
+		vma = find_vma(mm, addr);
+		if (!vma || addr+len <= vma->vm_start)
+			/* remember the address as a hint for next time */
+			return (mm->free_area_cache = addr);
+
+		/* remember the largest hole we saw so far */
+		if (addr + mm->cached_hole_size < vma->vm_start)
+			mm->cached_hole_size = vma->vm_start - addr;
+
+		/* try just below the current vma->vm_start */
+		addr = vma->vm_start - len;
+		if (do_align)
+			addr = COLOUR_ALIGN_DOWN(addr, pgoff);
+	} while (len < vma->vm_start);
+
+bottomup:
+	/*
+	 * A failed mmap() very likely causes application failure,
+	 * so fall back to the bottom-up function here. This scenario
+	 * can happen with large stack limits and large mmap()
+	 * allocations.
+	 */
+	mm->cached_hole_size = ~0UL;
+	mm->free_area_cache = TASK_UNMAPPED_BASE;
+	addr = arch_get_unmapped_area(filp, addr0, len, pgoff, flags);
+	/*
+	 * Restore the topdown base:
+	 */
+	mm->free_area_cache = mm->mmap_base;
+	mm->cached_hole_size = ~0UL;
+
+	return addr;
+}
+
+void arch_pick_mmap_layout(struct mm_struct *mm)
+{
+	unsigned long random_factor = 0UL;
+
+	/* 8 bits of randomness in 20 address space bits */
+	if ((current->flags & PF_RANDOMIZE) &&
+	    !(current->personality & ADDR_NO_RANDOMIZE))
+		random_factor = (get_random_int() % (1 << 8)) << PAGE_SHIFT;
+
+	if (mmap_is_legacy()) {
+		mm->mmap_base = TASK_UNMAPPED_BASE + random_factor;
+		mm->get_unmapped_area = arch_get_unmapped_area;
+		mm->unmap_area = arch_unmap_area;
+	} else {
+		mm->mmap_base = mmap_base(random_factor);
+		mm->get_unmapped_area = arch_get_unmapped_area_topdown;
+		mm->unmap_area = arch_unmap_area_topdown;
+	}
+}
 
 /*
  * You really shouldn't be using read() or write() on /dev/mem.  This
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index df6ced286ea..8a92abfb0a2 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -60,7 +60,7 @@ EXPORT_SYMBOL(pgprot_kernel);
 struct cachepolicy {
 	const char	policy[16];
 	unsigned int	cr_mask;
-	unsigned int	pmd;
+	pmdval_t	pmd;
 	pteval_t	pte;
 };
 
@@ -150,6 +150,7 @@ static int __init early_nowrite(char *__unused)
 }
 early_param("nowb", early_nowrite);
 
+#ifndef CONFIG_ARM_LPAE
 static int __init early_ecc(char *p)
 {
 	if (memcmp(p, "on", 2) == 0)
@@ -159,6 +160,7 @@ static int __init early_ecc(char *p)
 	return 0;
 }
 early_param("ecc", early_ecc);
+#endif
 
 static int __init noalign_setup(char *__unused)
 {
@@ -228,10 +230,12 @@ static struct mem_type mem_types[] = {
 		.prot_sect = PMD_TYPE_SECT | PMD_SECT_XN,
 		.domain    = DOMAIN_KERNEL,
 	},
+#ifndef CONFIG_ARM_LPAE
 	[MT_MINICLEAN] = {
 		.prot_sect = PMD_TYPE_SECT | PMD_SECT_XN | PMD_SECT_MINICACHE,
 		.domain    = DOMAIN_KERNEL,
 	},
+#endif
 	[MT_LOW_VECTORS] = {
 		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
 				L_PTE_RDONLY,
@@ -287,6 +291,14 @@ static struct mem_type mem_types[] = {
 		.prot_sect      = PROT_SECT_DEVICE | PMD_SECT_S,
 		.domain         = DOMAIN_IO,
 	},
+	[MT_MEMORY_SO] = {
+		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
+				L_PTE_MT_UNCACHED,
+		.prot_l1   = PMD_TYPE_TABLE,
+		.prot_sect = PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_SECT_S |
+				PMD_SECT_UNCACHED | PMD_SECT_XN,
+		.domain    = DOMAIN_KERNEL,
+	},
 };
 
 const struct mem_type *get_mem_type(unsigned int type)
@@ -302,7 +314,7 @@ static void __init build_mem_type_table(void)
 {
 	struct cachepolicy *cp;
 	unsigned int cr = get_cr();
-	unsigned int user_pgprot, kern_pgprot, vecs_pgprot;
+	pteval_t user_pgprot, kern_pgprot, vecs_pgprot;
 	int cpu_arch = cpu_architecture();
 	int i;
 
@@ -435,6 +447,7 @@ static void __init build_mem_type_table(void)
 	 * ARMv6 and above have extended page tables.
 	 */
 	if (cpu_arch >= CPU_ARCH_ARMv6 && (cr & CR_XP)) {
+#ifndef CONFIG_ARM_LPAE
 		/*
 		 * Mark cache clean areas and XIP ROM read only
 		 * from SVC mode and no access from userspace.
@@ -442,6 +455,7 @@ static void __init build_mem_type_table(void)
 		mem_types[MT_ROM].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE;
 		mem_types[MT_MINICLEAN].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE;
 		mem_types[MT_CACHECLEAN].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE;
+#endif
 
 		if (is_smp()) {
 			/*
@@ -480,6 +494,18 @@ static void __init build_mem_type_table(void)
 		mem_types[MT_MEMORY_NONCACHED].prot_sect |= PMD_SECT_BUFFERABLE;
 	}
 
+#ifdef CONFIG_ARM_LPAE
+	/*
+	 * Do not generate access flag faults for the kernel mappings.
+	 */
+	for (i = 0; i < ARRAY_SIZE(mem_types); i++) {
+		mem_types[i].prot_pte |= PTE_EXT_AF;
+		mem_types[i].prot_sect |= PMD_SECT_AF;
+	}
+	kern_pgprot |= PTE_EXT_AF;
+	vecs_pgprot |= PTE_EXT_AF;
+#endif
+
 	for (i = 0; i < 16; i++) {
 		unsigned long v = pgprot_val(protection_map[i]);
 		protection_map[i] = __pgprot(v | user_pgprot);
@@ -578,8 +604,10 @@ static void __init alloc_init_section(pud_t *pud, unsigned long addr,
 	if (((addr | end | phys) & ~SECTION_MASK) == 0) {
 		pmd_t *p = pmd;
 
+#ifndef CONFIG_ARM_LPAE
 		if (addr & SECTION_SIZE)
 			pmd++;
+#endif
 
 		do {
 			*pmd = __pmd(phys | type->prot_sect);
@@ -609,6 +637,7 @@ static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end,
 	} while (pud++, addr = next, addr != end);
 }
 
+#ifndef CONFIG_ARM_LPAE
 static void __init create_36bit_mapping(struct map_desc *md,
 					const struct mem_type *type)
 {
@@ -668,6 +697,7 @@ static void __init create_36bit_mapping(struct map_desc *md,
 		pgd += SUPERSECTION_SIZE >> PGDIR_SHIFT;
 	} while (addr != end);
 }
+#endif	/* !CONFIG_ARM_LPAE */
 
 /*
  * Create the page directory entries and any necessary
@@ -699,6 +729,7 @@ static void __init create_mapping(struct map_desc *md)
 
 	type = &mem_types[md->type];
 
+#ifndef CONFIG_ARM_LPAE
 	/*
 	 * Catch 36-bit addresses
 	 */
@@ -706,6 +737,7 @@ static void __init create_mapping(struct map_desc *md)
 		create_36bit_mapping(md, type);
 		return;
 	}
+#endif
 
 	addr = md->virtual & PAGE_MASK;
 	phys = __pfn_to_phys(md->pfn);
@@ -781,6 +813,9 @@ void __init sanity_check_meminfo(void)
 		struct membank *bank = &meminfo.bank[j];
 		*bank = meminfo.bank[i];
 
+		if (bank->start > ULONG_MAX)
+			highmem = 1;
+
 #ifdef CONFIG_HIGHMEM
 		if (__va(bank->start) >= vmalloc_min ||
 		    __va(bank->start) < (void *)PAGE_OFFSET)
@@ -792,7 +827,7 @@ void __init sanity_check_meminfo(void)
 		 * Split those memory banks which are partially overlapping
 		 * the vmalloc area greatly simplifying things later.
 		 */
-		if (__va(bank->start) < vmalloc_min &&
+		if (!highmem && __va(bank->start) < vmalloc_min &&
 		    bank->size > vmalloc_min - __va(bank->start)) {
 			if (meminfo.nr_banks >= NR_BANKS) {
 				printk(KERN_CRIT "NR_BANKS too low, "
@@ -813,6 +848,17 @@ void __init sanity_check_meminfo(void)
 		bank->highmem = highmem;
 
 		/*
+		 * Highmem banks not allowed with !CONFIG_HIGHMEM.
+		 */
+		if (highmem) {
+			printk(KERN_NOTICE "Ignoring RAM at %.8llx-%.8llx "
+			       "(!CONFIG_HIGHMEM).\n",
+			       (unsigned long long)bank->start,
+			       (unsigned long long)bank->start + bank->size - 1);
+			continue;
+		}
+
+		/*
 		 * Check whether this memory bank would entirely overlap
 		 * the vmalloc area.
 		 */
@@ -877,14 +923,14 @@ static inline void prepare_page_table(void)
 	/*
 	 * Clear out all the mappings below the kernel image.
 	 */
-	for (addr = 0; addr < MODULES_VADDR; addr += PGDIR_SIZE)
+	for (addr = 0; addr < MODULES_VADDR; addr += PMD_SIZE)
 		pmd_clear(pmd_off_k(addr));
 
 #ifdef CONFIG_XIP_KERNEL
 	/* The XIP kernel is mapped in the module area -- skip over it */
-	addr = ((unsigned long)_etext + PGDIR_SIZE - 1) & PGDIR_MASK;
+	addr = ((unsigned long)_etext + PMD_SIZE - 1) & PMD_MASK;
 #endif
-	for ( ; addr < PAGE_OFFSET; addr += PGDIR_SIZE)
+	for ( ; addr < PAGE_OFFSET; addr += PMD_SIZE)
 		pmd_clear(pmd_off_k(addr));
 
 	/*
@@ -899,10 +945,18 @@ static inline void prepare_page_table(void)
 	 * memory bank, up to the end of the vmalloc region.
 	 */
 	for (addr = __phys_to_virt(end);
-	     addr < VMALLOC_END; addr += PGDIR_SIZE)
+	     addr < VMALLOC_END; addr += PMD_SIZE)
 		pmd_clear(pmd_off_k(addr));
 }
 
+#ifdef CONFIG_ARM_LPAE
+/* the first page is reserved for pgd */
+#define SWAPPER_PG_DIR_SIZE	(PAGE_SIZE + \
+				 PTRS_PER_PGD * PTRS_PER_PMD * sizeof(pmd_t))
+#else
+#define SWAPPER_PG_DIR_SIZE	(PTRS_PER_PGD * sizeof(pgd_t))
+#endif
+
 /*
  * Reserve the special regions of memory
  */
@@ -912,7 +966,7 @@ void __init arm_mm_memblock_reserve(void)
 	 * Reserve the page tables.  These are already in use,
 	 * and can only be in node 0.
 	 */
-	memblock_reserve(__pa(swapper_pg_dir), PTRS_PER_PGD * sizeof(pgd_t));
+	memblock_reserve(__pa(swapper_pg_dir), SWAPPER_PG_DIR_SIZE);
 
 #ifdef CONFIG_SA1111
 	/*
@@ -940,7 +994,7 @@ static void __init devicemaps_init(struct machine_desc *mdesc)
 	 */
 	vectors_page = early_alloc(PAGE_SIZE);
 
-	for (addr = VMALLOC_END; addr; addr += PGDIR_SIZE)
+	for (addr = VMALLOC_END; addr; addr += PMD_SIZE)
 		pmd_clear(pmd_off_k(addr));
 
 	/*
diff --git a/arch/arm/mm/pgd.c b/arch/arm/mm/pgd.c
index b2027c154b2..a3e78ccabd6 100644
--- a/arch/arm/mm/pgd.c
+++ b/arch/arm/mm/pgd.c
@@ -10,6 +10,7 @@
 #include <linux/mm.h>
 #include <linux/gfp.h>
 #include <linux/highmem.h>
+#include <linux/slab.h>
 
 #include <asm/pgalloc.h>
 #include <asm/page.h>
@@ -17,6 +18,14 @@
 
 #include "mm.h"
 
+#ifdef CONFIG_ARM_LPAE
+#define __pgd_alloc()	kmalloc(PTRS_PER_PGD * sizeof(pgd_t), GFP_KERNEL)
+#define __pgd_free(pgd)	kfree(pgd)
+#else
+#define __pgd_alloc()	(pgd_t *)__get_free_pages(GFP_KERNEL, 2)
+#define __pgd_free(pgd)	free_pages((unsigned long)pgd, 2)
+#endif
+
 /*
  * need to get a 16k page for level 1
  */
@@ -27,7 +36,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
 	pmd_t *new_pmd, *init_pmd;
 	pte_t *new_pte, *init_pte;
 
-	new_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL, 2);
+	new_pgd = __pgd_alloc();
 	if (!new_pgd)
 		goto no_pgd;
 
@@ -42,10 +51,25 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
 
 	clean_dcache_area(new_pgd, PTRS_PER_PGD * sizeof(pgd_t));
 
+#ifdef CONFIG_ARM_LPAE
+	/*
+	 * Allocate PMD table for modules and pkmap mappings.
+	 */
+	new_pud = pud_alloc(mm, new_pgd + pgd_index(MODULES_VADDR),
+			    MODULES_VADDR);
+	if (!new_pud)
+		goto no_pud;
+
+	new_pmd = pmd_alloc(mm, new_pud, 0);
+	if (!new_pmd)
+		goto no_pmd;
+#endif
+
 	if (!vectors_high()) {
 		/*
 		 * On ARM, first page must always be allocated since it
-		 * contains the machine vectors.
+		 * contains the machine vectors. The vectors are always high
+		 * with LPAE.
 		 */
 		new_pud = pud_alloc(mm, new_pgd, 0);
 		if (!new_pud)
@@ -74,7 +98,7 @@ no_pte:
 no_pmd:
 	pud_free(mm, new_pud);
 no_pud:
-	free_pages((unsigned long)new_pgd, 2);
+	__pgd_free(new_pgd);
 no_pgd:
 	return NULL;
 }
@@ -111,5 +135,24 @@ no_pud:
 	pgd_clear(pgd);
 	pud_free(mm, pud);
 no_pgd:
-	free_pages((unsigned long) pgd_base, 2);
+#ifdef CONFIG_ARM_LPAE
+	/*
+	 * Free modules/pkmap or identity pmd tables.
+	 */
+	for (pgd = pgd_base; pgd < pgd_base + PTRS_PER_PGD; pgd++) {
+		if (pgd_none_or_clear_bad(pgd))
+			continue;
+		if (pgd_val(*pgd) & L_PGD_SWAPPER)
+			continue;
+		pud = pud_offset(pgd, 0);
+		if (pud_none_or_clear_bad(pud))
+			continue;
+		pmd = pmd_offset(pud, 0);
+		pud_clear(pud);
+		pmd_free(mm, pmd);
+		pgd_clear(pgd);
+		pud_free(mm, pud);
+	}
+#endif
+	__pgd_free(pgd_base);
 }
diff --git a/arch/arm/mm/proc-arm920.S b/arch/arm/mm/proc-arm920.S
index 2e6849b41f6..88fb3d9e064 100644
--- a/arch/arm/mm/proc-arm920.S
+++ b/arch/arm/mm/proc-arm920.S
@@ -379,31 +379,26 @@ ENTRY(cpu_arm920_set_pte_ext)
 
 /* Suspend/resume support: taken from arch/arm/plat-s3c24xx/sleep.S */
 .globl	cpu_arm920_suspend_size
-.equ	cpu_arm920_suspend_size, 4 * 4
+.equ	cpu_arm920_suspend_size, 4 * 3
 #ifdef CONFIG_PM_SLEEP
 ENTRY(cpu_arm920_do_suspend)
-	stmfd	sp!, {r4 - r7, lr}
+	stmfd	sp!, {r4 - r6, lr}
 	mrc	p15, 0, r4, c13, c0, 0	@ PID
 	mrc	p15, 0, r5, c3, c0, 0	@ Domain ID
-	mrc	p15, 0, r6, c2, c0, 0	@ TTB address
-	mrc	p15, 0, r7, c1, c0, 0	@ Control register
-	stmia	r0, {r4 - r7}
-	ldmfd	sp!, {r4 - r7, pc}
+	mrc	p15, 0, r6, c1, c0, 0	@ Control register
+	stmia	r0, {r4 - r6}
+	ldmfd	sp!, {r4 - r6, pc}
 ENDPROC(cpu_arm920_do_suspend)
 
 ENTRY(cpu_arm920_do_resume)
 	mov	ip, #0
 	mcr	p15, 0, ip, c8, c7, 0	@ invalidate I+D TLBs
 	mcr	p15, 0, ip, c7, c7, 0	@ invalidate I+D caches
-	ldmia	r0, {r4 - r7}
+	ldmia	r0, {r4 - r6}
 	mcr	p15, 0, r4, c13, c0, 0	@ PID
 	mcr	p15, 0, r5, c3, c0, 0	@ Domain ID
-	mcr	p15, 0, r6, c2, c0, 0	@ TTB address
-	mov	r0, r7			@ control register
-	mov	r2, r6, lsr #14		@ get TTB0 base
-	mov	r2, r2, lsl #14
-	ldr	r3, =PMD_TYPE_SECT | PMD_SECT_BUFFERABLE | \
-		     PMD_SECT_CACHEABLE | PMD_BIT4 | PMD_SECT_AP_WRITE
+	mcr	p15, 0, r1, c2, c0, 0	@ TTB address
+	mov	r0, r6			@ control register
 	b	cpu_resume_mmu
 ENDPROC(cpu_arm920_do_resume)
 #endif
diff --git a/arch/arm/mm/proc-arm926.S b/arch/arm/mm/proc-arm926.S
index cd8f79c3a28..9f8fd91f918 100644
--- a/arch/arm/mm/proc-arm926.S
+++ b/arch/arm/mm/proc-arm926.S
@@ -394,31 +394,26 @@ ENTRY(cpu_arm926_set_pte_ext)
 
 /* Suspend/resume support: taken from arch/arm/plat-s3c24xx/sleep.S */
 .globl	cpu_arm926_suspend_size
-.equ	cpu_arm926_suspend_size, 4 * 4
+.equ	cpu_arm926_suspend_size, 4 * 3
 #ifdef CONFIG_PM_SLEEP
 ENTRY(cpu_arm926_do_suspend)
-	stmfd	sp!, {r4 - r7, lr}
+	stmfd	sp!, {r4 - r6, lr}
 	mrc	p15, 0, r4, c13, c0, 0	@ PID
 	mrc	p15, 0, r5, c3, c0, 0	@ Domain ID
-	mrc	p15, 0, r6, c2, c0, 0	@ TTB address
-	mrc	p15, 0, r7, c1, c0, 0	@ Control register
-	stmia	r0, {r4 - r7}
-	ldmfd	sp!, {r4 - r7, pc}
+	mrc	p15, 0, r6, c1, c0, 0	@ Control register
+	stmia	r0, {r4 - r6}
+	ldmfd	sp!, {r4 - r6, pc}
 ENDPROC(cpu_arm926_do_suspend)
 
 ENTRY(cpu_arm926_do_resume)
 	mov	ip, #0
 	mcr	p15, 0, ip, c8, c7, 0	@ invalidate I+D TLBs
 	mcr	p15, 0, ip, c7, c7, 0	@ invalidate I+D caches
-	ldmia	r0, {r4 - r7}
+	ldmia	r0, {r4 - r6}
 	mcr	p15, 0, r4, c13, c0, 0	@ PID
 	mcr	p15, 0, r5, c3, c0, 0	@ Domain ID
-	mcr	p15, 0, r6, c2, c0, 0	@ TTB address
-	mov	r0, r7			@ control register
-	mov	r2, r6, lsr #14		@ get TTB0 base
-	mov	r2, r2, lsl #14
-	ldr	r3, =PMD_TYPE_SECT | PMD_SECT_BUFFERABLE | \
-		     PMD_SECT_CACHEABLE | PMD_BIT4 | PMD_SECT_AP_WRITE
+	mcr	p15, 0, r1, c2, c0, 0	@ TTB address
+	mov	r0, r6			@ control register
 	b	cpu_resume_mmu
 ENDPROC(cpu_arm926_do_resume)
 #endif
diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S
index 411610d4973..518ab10fea5 100644
--- a/arch/arm/mm/proc-macros.S
+++ b/arch/arm/mm/proc-macros.S
@@ -91,8 +91,9 @@
 #if L_PTE_SHARED != PTE_EXT_SHARED
 #error PTE shared bit mismatch
 #endif
-#if (L_PTE_XN+L_PTE_USER+L_PTE_RDONLY+L_PTE_DIRTY+L_PTE_YOUNG+\
-     L_PTE_FILE+L_PTE_PRESENT) > L_PTE_SHARED
+#if !defined (CONFIG_ARM_LPAE) && \
+	(L_PTE_XN+L_PTE_USER+L_PTE_RDONLY+L_PTE_DIRTY+L_PTE_YOUNG+\
+	 L_PTE_FILE+L_PTE_PRESENT) > L_PTE_SHARED
 #error Invalid Linux PTE bit settings
 #endif
 #endif	/* CONFIG_MMU */
diff --git a/arch/arm/mm/proc-sa1100.S b/arch/arm/mm/proc-sa1100.S
index 69e7f2ef738..7d91545d089 100644
--- a/arch/arm/mm/proc-sa1100.S
+++ b/arch/arm/mm/proc-sa1100.S
@@ -168,20 +168,19 @@ ENTRY(cpu_sa1100_set_pte_ext)
 	mov	pc, lr
 
 .globl	cpu_sa1100_suspend_size
-.equ	cpu_sa1100_suspend_size, 4*4
+.equ	cpu_sa1100_suspend_size, 4 * 3
 #ifdef CONFIG_PM_SLEEP
 ENTRY(cpu_sa1100_do_suspend)
-	stmfd	sp!, {r4 - r7, lr}
+	stmfd	sp!, {r4 - r6, lr}
 	mrc	p15, 0, r4, c3, c0, 0		@ domain ID
-	mrc	p15, 0, r5, c2, c0, 0		@ translation table base addr
-	mrc	p15, 0, r6, c13, c0, 0		@ PID
-	mrc	p15, 0, r7, c1, c0, 0		@ control reg
-	stmia	r0, {r4 - r7}			@ store cp regs
-	ldmfd	sp!, {r4 - r7, pc}
+	mrc	p15, 0, r5, c13, c0, 0		@ PID
+	mrc	p15, 0, r6, c1, c0, 0		@ control reg
+	stmia	r0, {r4 - r6}			@ store cp regs
+	ldmfd	sp!, {r4 - r6, pc}
 ENDPROC(cpu_sa1100_do_suspend)
 
 ENTRY(cpu_sa1100_do_resume)
-	ldmia	r0, {r4 - r7}			@ load cp regs
+	ldmia	r0, {r4 - r6}			@ load cp regs
 	mov	ip, #0
 	mcr	p15, 0, ip, c8, c7, 0		@ flush I+D TLBs
 	mcr	p15, 0, ip, c7, c7, 0		@ flush I&D cache
@@ -189,13 +188,9 @@ ENTRY(cpu_sa1100_do_resume)
 	mcr	p15, 0, ip, c9, c0, 5		@ allow user space to use RB
 
 	mcr	p15, 0, r4, c3, c0, 0		@ domain ID
-	mcr	p15, 0, r5, c2, c0, 0		@ translation table base addr
-	mcr	p15, 0, r6, c13, c0, 0		@ PID
-	mov	r0, r7				@ control register
-	mov	r2, r5, lsr #14			@ get TTB0 base
-	mov	r2, r2, lsl #14
-	ldr	r3, =PMD_TYPE_SECT | PMD_SECT_BUFFERABLE | \
-		     PMD_SECT_CACHEABLE | PMD_SECT_AP_WRITE
+	mcr	p15, 0, r1, c2, c0, 0		@ translation table base addr
+	mcr	p15, 0, r5, c13, c0, 0		@ PID
+	mov	r0, r6				@ control register
 	b	cpu_resume_mmu
 ENDPROC(cpu_sa1100_do_resume)
 #endif
diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S
index a923aa0fd00..d061d2fa550 100644
--- a/arch/arm/mm/proc-v6.S
+++ b/arch/arm/mm/proc-v6.S
@@ -128,20 +128,18 @@ ENTRY(cpu_v6_set_pte_ext)
 
 /* Suspend/resume support: taken from arch/arm/mach-s3c64xx/sleep.S */
 .globl	cpu_v6_suspend_size
-.equ	cpu_v6_suspend_size, 4 * 8
+.equ	cpu_v6_suspend_size, 4 * 6
 #ifdef CONFIG_PM_SLEEP
 ENTRY(cpu_v6_do_suspend)
-	stmfd	sp!, {r4 - r11, lr}
+	stmfd	sp!, {r4 - r9, lr}
 	mrc	p15, 0, r4, c13, c0, 0	@ FCSE/PID
-	mrc	p15, 0, r5, c13, c0, 1	@ Context ID
-	mrc	p15, 0, r6, c3, c0, 0	@ Domain ID
-	mrc	p15, 0, r7, c2, c0, 0	@ Translation table base 0
-	mrc	p15, 0, r8, c2, c0, 1	@ Translation table base 1
-	mrc	p15, 0, r9, c1, c0, 1	@ auxiliary control register
-	mrc	p15, 0, r10, c1, c0, 2	@ co-processor access control
-	mrc	p15, 0, r11, c1, c0, 0	@ control register
-	stmia	r0, {r4 - r11}
-	ldmfd	sp!, {r4- r11, pc}
+	mrc	p15, 0, r5, c3, c0, 0	@ Domain ID
+	mrc	p15, 0, r6, c2, c0, 1	@ Translation table base 1
+	mrc	p15, 0, r7, c1, c0, 1	@ auxiliary control register
+	mrc	p15, 0, r8, c1, c0, 2	@ co-processor access control
+	mrc	p15, 0, r9, c1, c0, 0	@ control register
+	stmia	r0, {r4 - r9}
+	ldmfd	sp!, {r4- r9, pc}
 ENDPROC(cpu_v6_do_suspend)
 
 ENTRY(cpu_v6_do_resume)
@@ -150,25 +148,21 @@ ENTRY(cpu_v6_do_resume)
 	mcr	p15, 0, ip, c7, c5, 0	@ invalidate I cache
 	mcr	p15, 0, ip, c7, c15, 0	@ clean+invalidate cache
 	mcr	p15, 0, ip, c7, c10, 4	@ drain write buffer
-	ldmia	r0, {r4 - r11}
+	mcr	p15, 0, ip, c13, c0, 1	@ set reserved context ID
+	ldmia	r0, {r4 - r9}
 	mcr	p15, 0, r4, c13, c0, 0	@ FCSE/PID
-	mcr	p15, 0, r5, c13, c0, 1	@ Context ID
-	mcr	p15, 0, r6, c3, c0, 0	@ Domain ID
-	mcr	p15, 0, r7, c2, c0, 0	@ Translation table base 0
-	mcr	p15, 0, r8, c2, c0, 1	@ Translation table base 1
-	mcr	p15, 0, r9, c1, c0, 1	@ auxiliary control register
-	mcr	p15, 0, r10, c1, c0, 2	@ co-processor access control
+	mcr	p15, 0, r5, c3, c0, 0	@ Domain ID
+	ALT_SMP(orr	r1, r1, #TTB_FLAGS_SMP)
+	ALT_UP(orr	r1, r1, #TTB_FLAGS_UP)
+	mcr	p15, 0, r1, c2, c0, 0	@ Translation table base 0
+	mcr	p15, 0, r6, c2, c0, 1	@ Translation table base 1
+	mcr	p15, 0, r7, c1, c0, 1	@ auxiliary control register
+	mcr	p15, 0, r8, c1, c0, 2	@ co-processor access control
 	mcr	p15, 0, ip, c2, c0, 2	@ TTB control register
 	mcr	p15, 0, ip, c7, c5, 4	@ ISB
-	mov	r0, r11			@ control register
-	mov	r2, r7, lsr #14		@ get TTB0 base
-	mov	r2, r2, lsl #14
-	ldr	r3, cpu_resume_l1_flags
+	mov	r0, r9			@ control register
 	b	cpu_resume_mmu
 ENDPROC(cpu_v6_do_resume)
-cpu_resume_l1_flags:
-	ALT_SMP(.long PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_FLAGS_SMP)
-	ALT_UP(.long  PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_FLAGS_UP)
 #endif
 
 	string	cpu_v6_name, "ARMv6-compatible processor"
diff --git a/arch/arm/mm/proc-v7-2level.S b/arch/arm/mm/proc-v7-2level.S
new file mode 100644
index 00000000000..3a4b3e7b888
--- /dev/null
+++ b/arch/arm/mm/proc-v7-2level.S
@@ -0,0 +1,171 @@
+/*
+ * arch/arm/mm/proc-v7-2level.S
+ *
+ * Copyright (C) 2001 Deep Blue Solutions Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#define TTB_S		(1 << 1)
+#define TTB_RGN_NC	(0 << 3)
+#define TTB_RGN_OC_WBWA	(1 << 3)
+#define TTB_RGN_OC_WT	(2 << 3)
+#define TTB_RGN_OC_WB	(3 << 3)
+#define TTB_NOS		(1 << 5)
+#define TTB_IRGN_NC	((0 << 0) | (0 << 6))
+#define TTB_IRGN_WBWA	((0 << 0) | (1 << 6))
+#define TTB_IRGN_WT	((1 << 0) | (0 << 6))
+#define TTB_IRGN_WB	((1 << 0) | (1 << 6))
+
+/* PTWs cacheable, inner WB not shareable, outer WB not shareable */
+#define TTB_FLAGS_UP	TTB_IRGN_WB|TTB_RGN_OC_WB
+#define PMD_FLAGS_UP	PMD_SECT_WB
+
+/* PTWs cacheable, inner WBWA shareable, outer WBWA not shareable */
+#define TTB_FLAGS_SMP	TTB_IRGN_WBWA|TTB_S|TTB_NOS|TTB_RGN_OC_WBWA
+#define PMD_FLAGS_SMP	PMD_SECT_WBWA|PMD_SECT_S
+
+/*
+ *	cpu_v7_switch_mm(pgd_phys, tsk)
+ *
+ *	Set the translation table base pointer to be pgd_phys
+ *
+ *	- pgd_phys - physical address of new TTB
+ *
+ *	It is assumed that:
+ *	- we are not using split page tables
+ */
+ENTRY(cpu_v7_switch_mm)
+#ifdef CONFIG_MMU
+	mov	r2, #0
+	ldr	r1, [r1, #MM_CONTEXT_ID]	@ get mm->context.id
+	ALT_SMP(orr	r0, r0, #TTB_FLAGS_SMP)
+	ALT_UP(orr	r0, r0, #TTB_FLAGS_UP)
+#ifdef CONFIG_ARM_ERRATA_430973
+	mcr	p15, 0, r2, c7, c5, 6		@ flush BTAC/BTB
+#endif
+#ifdef CONFIG_ARM_ERRATA_754322
+	dsb
+#endif
+	mcr	p15, 0, r2, c13, c0, 1		@ set reserved context ID
+	isb
+1:	mcr	p15, 0, r0, c2, c0, 0		@ set TTB 0
+	isb
+#ifdef CONFIG_ARM_ERRATA_754322
+	dsb
+#endif
+	mcr	p15, 0, r1, c13, c0, 1		@ set context ID
+	isb
+#endif
+	mov	pc, lr
+ENDPROC(cpu_v7_switch_mm)
+
+/*
+ *	cpu_v7_set_pte_ext(ptep, pte)
+ *
+ *	Set a level 2 translation table entry.
+ *
+ *	- ptep  - pointer to level 2 translation table entry
+ *		  (hardware version is stored at +2048 bytes)
+ *	- pte   - PTE value to store
+ *	- ext	- value for extended PTE bits
+ */
+ENTRY(cpu_v7_set_pte_ext)
+#ifdef CONFIG_MMU
+	str	r1, [r0]			@ linux version
+
+	bic	r3, r1, #0x000003f0
+	bic	r3, r3, #PTE_TYPE_MASK
+	orr	r3, r3, r2
+	orr	r3, r3, #PTE_EXT_AP0 | 2
+
+	tst	r1, #1 << 4
+	orrne	r3, r3, #PTE_EXT_TEX(1)
+
+	eor	r1, r1, #L_PTE_DIRTY
+	tst	r1, #L_PTE_RDONLY | L_PTE_DIRTY
+	orrne	r3, r3, #PTE_EXT_APX
+
+	tst	r1, #L_PTE_USER
+	orrne	r3, r3, #PTE_EXT_AP1
+#ifdef CONFIG_CPU_USE_DOMAINS
+	@ allow kernel read/write access to read-only user pages
+	tstne	r3, #PTE_EXT_APX
+	bicne	r3, r3, #PTE_EXT_APX | PTE_EXT_AP0
+#endif
+
+	tst	r1, #L_PTE_XN
+	orrne	r3, r3, #PTE_EXT_XN
+
+	tst	r1, #L_PTE_YOUNG
+	tstne	r1, #L_PTE_PRESENT
+	moveq	r3, #0
+
+ ARM(	str	r3, [r0, #2048]! )
+ THUMB(	add	r0, r0, #2048 )
+ THUMB(	str	r3, [r0] )
+	mcr	p15, 0, r0, c7, c10, 1		@ flush_pte
+#endif
+	mov	pc, lr
+ENDPROC(cpu_v7_set_pte_ext)
+
+	/*
+	 * Memory region attributes with SCTLR.TRE=1
+	 *
+	 *   n = TEX[0],C,B
+	 *   TR = PRRR[2n+1:2n]		- memory type
+	 *   IR = NMRR[2n+1:2n]		- inner cacheable property
+	 *   OR = NMRR[2n+17:2n+16]	- outer cacheable property
+	 *
+	 *			n	TR	IR	OR
+	 *   UNCACHED		000	00
+	 *   BUFFERABLE		001	10	00	00
+	 *   WRITETHROUGH	010	10	10	10
+	 *   WRITEBACK		011	10	11	11
+	 *   reserved		110
+	 *   WRITEALLOC		111	10	01	01
+	 *   DEV_SHARED		100	01
+	 *   DEV_NONSHARED	100	01
+	 *   DEV_WC		001	10
+	 *   DEV_CACHED		011	10
+	 *
+	 * Other attributes:
+	 *
+	 *   DS0 = PRRR[16] = 0		- device shareable property
+	 *   DS1 = PRRR[17] = 1		- device shareable property
+	 *   NS0 = PRRR[18] = 0		- normal shareable property
+	 *   NS1 = PRRR[19] = 1		- normal shareable property
+	 *   NOS = PRRR[24+n] = 1	- not outer shareable
+	 */
+.equ	PRRR,	0xff0a81a8
+.equ	NMRR,	0x40e040e0
+
+	/*
+	 * Macro for setting up the TTBRx and TTBCR registers.
+	 * - \ttb0 and \ttb1 updated with the corresponding flags.
+	 */
+	.macro	v7_ttb_setup, zero, ttbr0, ttbr1, tmp
+	mcr	p15, 0, \zero, c2, c0, 2	@ TTB control register
+	ALT_SMP(orr	\ttbr0, \ttbr0, #TTB_FLAGS_SMP)
+	ALT_UP(orr	\ttbr0, \ttbr0, #TTB_FLAGS_UP)
+	ALT_SMP(orr	\ttbr1, \ttbr1, #TTB_FLAGS_SMP)
+	ALT_UP(orr	\ttbr1, \ttbr1, #TTB_FLAGS_UP)
+	mcr	p15, 0, \ttbr1, c2, c0, 1	@ load TTB1
+	.endm
+
+	__CPUINIT
+
+	/*   AT
+	 *  TFR   EV X F   I D LR    S
+	 * .EEE ..EE PUI. .T.T 4RVI ZWRS BLDP WCAM
+	 * rxxx rrxx xxx0 0101 xxxx xxxx x111 xxxx < forced
+	 *    1    0 110       0011 1100 .111 1101 < we want
+	 */
+	.align	2
+	.type	v7_crval, #object
+v7_crval:
+	crval	clear=0x0120c302, mmuset=0x10c03c7d, ucset=0x00c01c7c
+
+	.previous
diff --git a/arch/arm/mm/proc-v7-3level.S b/arch/arm/mm/proc-v7-3level.S
new file mode 100644
index 00000000000..79cad358ebe
--- /dev/null
+++ b/arch/arm/mm/proc-v7-3level.S
@@ -0,0 +1,149 @@
+/*
+ * arch/arm/mm/proc-v7-3level.S
+ *
+ * Copyright (C) 2001 Deep Blue Solutions Ltd.
+ * Copyright (C) 2011 ARM Ltd.
+ * Author: Catalin Marinas <catalin.marinas@arm.com>
+ *   based on arch/arm/mm/proc-v7-2level.S
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#define TTB_IRGN_NC	(0 << 8)
+#define TTB_IRGN_WBWA	(1 << 8)
+#define TTB_IRGN_WT	(2 << 8)
+#define TTB_IRGN_WB	(3 << 8)
+#define TTB_RGN_NC	(0 << 10)
+#define TTB_RGN_OC_WBWA	(1 << 10)
+#define TTB_RGN_OC_WT	(2 << 10)
+#define TTB_RGN_OC_WB	(3 << 10)
+#define TTB_S		(3 << 12)
+#define TTB_EAE		(1 << 31)
+
+/* PTWs cacheable, inner WB not shareable, outer WB not shareable */
+#define TTB_FLAGS_UP	(TTB_IRGN_WB|TTB_RGN_OC_WB)
+#define PMD_FLAGS_UP	(PMD_SECT_WB)
+
+/* PTWs cacheable, inner WBWA shareable, outer WBWA not shareable */
+#define TTB_FLAGS_SMP	(TTB_IRGN_WBWA|TTB_S|TTB_RGN_OC_WBWA)
+#define PMD_FLAGS_SMP	(PMD_SECT_WBWA|PMD_SECT_S)
+
+/*
+ * cpu_v7_switch_mm(pgd_phys, tsk)
+ *
+ * Set the translation table base pointer to be pgd_phys (physical address of
+ * the new TTB).
+ */
+ENTRY(cpu_v7_switch_mm)
+#ifdef CONFIG_MMU
+	ldr	r1, [r1, #MM_CONTEXT_ID]	@ get mm->context.id
+	mov	r2, #0
+	and	r3, r1, #0xff
+	mov	r3, r3, lsl #(48 - 32)		@ ASID
+	mcrr	p15, 0, r0, r3, c2		@ set TTB 0
+	isb
+#endif
+	mov	pc, lr
+ENDPROC(cpu_v7_switch_mm)
+
+/*
+ * cpu_v7_set_pte_ext(ptep, pte)
+ *
+ * Set a level 2 translation table entry.
+ * - ptep - pointer to level 3 translation table entry
+ * - pte - PTE value to store (64-bit in r2 and r3)
+ */
+ENTRY(cpu_v7_set_pte_ext)
+#ifdef CONFIG_MMU
+	tst	r2, #L_PTE_PRESENT
+	beq	1f
+	tst	r3, #1 << (55 - 32)		@ L_PTE_DIRTY
+	orreq	r2, #L_PTE_RDONLY
+1:	strd	r2, r3, [r0]
+	mcr	p15, 0, r0, c7, c10, 1		@ flush_pte
+#endif
+	mov	pc, lr
+ENDPROC(cpu_v7_set_pte_ext)
+
+	/*
+	 * Memory region attributes for LPAE (defined in pgtable-3level.h):
+	 *
+	 *   n = AttrIndx[2:0]
+	 *
+	 *			n	MAIR
+	 *   UNCACHED		000	00000000
+	 *   BUFFERABLE		001	01000100
+	 *   DEV_WC		001	01000100
+	 *   WRITETHROUGH	010	10101010
+	 *   WRITEBACK		011	11101110
+	 *   DEV_CACHED		011	11101110
+	 *   DEV_SHARED		100	00000100
+	 *   DEV_NONSHARED	100	00000100
+	 *   unused		101
+	 *   unused		110
+	 *   WRITEALLOC		111	11111111
+	 */
+.equ	PRRR,	0xeeaa4400			@ MAIR0
+.equ	NMRR,	0xff000004			@ MAIR1
+
+	/*
+	 * Macro for setting up the TTBRx and TTBCR registers.
+	 * - \ttbr1 updated.
+	 */
+	.macro	v7_ttb_setup, zero, ttbr0, ttbr1, tmp
+	mrc	p15, 0, \tmp, c2, c0, 2		@ TTB control register
+	orr	\tmp, \tmp, #TTB_EAE
+	ALT_SMP(orr	\tmp, \tmp, #TTB_FLAGS_SMP)
+	ALT_UP(orr	\tmp, \tmp, #TTB_FLAGS_UP)
+	ALT_SMP(orr	\tmp, \tmp, #TTB_FLAGS_SMP << 16)
+	ALT_UP(orr	\tmp, \tmp, #TTB_FLAGS_UP << 16)
+#if PHYS_OFFSET <= PAGE_OFFSET
+	/*
+	 * TTBR0/TTBR1 split (PAGE_OFFSET):
+	 *   0x40000000: T0SZ = 2, T1SZ = 0 (not used)
+	 *   0x80000000: T0SZ = 0, T1SZ = 1
+	 *   0xc0000000: T0SZ = 0, T1SZ = 2
+	 *
+	 * Only use this feature if PHYS_OFFSET <= PAGE_OFFSET, otherwise
+	 * booting secondary CPUs would end up using TTBR1 for the identity
+	 * mapping set up in TTBR0.
+	 */
+	orr	\tmp, \tmp, #(((PAGE_OFFSET >> 30) - 1) << 16) @ TTBCR.T1SZ
+#if defined CONFIG_VMSPLIT_2G
+	/* PAGE_OFFSET == 0x80000000, T1SZ == 1 */
+	add	\ttbr1, \ttbr1, #1 << 4		@ skip two L1 entries
+#elif defined CONFIG_VMSPLIT_3G
+	/* PAGE_OFFSET == 0xc0000000, T1SZ == 2 */
+	add	\ttbr1, \ttbr1, #4096 * (1 + 3)	@ only L2 used, skip pgd+3*pmd
+#endif
+#endif	/* PHYS_OFFSET <= PAGE_OFFSET */
+	mcr	p15, 0, \tmp, c2, c0, 2	@ TTB control register
+	mcrr	p15, 1, \ttbr1, \zero, c2	@ load TTBR1
+	.endm
+
+	__CPUINIT
+
+	/*
+	 *   AT
+	 *  TFR   EV X F   IHD LR    S
+	 * .EEE ..EE PUI. .TAT 4RVI ZWRS BLDP WCAM
+	 * rxxx rrxx xxx0 0101 xxxx xxxx x111 xxxx < forced
+	 *   11    0 110    1  0011 1100 .111 1101 < we want
+	 */
+	.align	2
+	.type	v7_crval, #object
+v7_crval:
+	crval	clear=0x0120c302, mmuset=0x30c23c7d, ucset=0x00c01c7c
+
+	.previous
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 2cd0273bc65..c3a3ecd804d 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -19,24 +19,11 @@
 
 #include "proc-macros.S"
 
-#define TTB_S		(1 << 1)
-#define TTB_RGN_NC	(0 << 3)
-#define TTB_RGN_OC_WBWA	(1 << 3)
-#define TTB_RGN_OC_WT	(2 << 3)
-#define TTB_RGN_OC_WB	(3 << 3)
-#define TTB_NOS		(1 << 5)
-#define TTB_IRGN_NC	((0 << 0) | (0 << 6))
-#define TTB_IRGN_WBWA	((0 << 0) | (1 << 6))
-#define TTB_IRGN_WT	((1 << 0) | (0 << 6))
-#define TTB_IRGN_WB	((1 << 0) | (1 << 6))
-
-/* PTWs cacheable, inner WB not shareable, outer WB not shareable */
-#define TTB_FLAGS_UP	TTB_IRGN_WB|TTB_RGN_OC_WB
-#define PMD_FLAGS_UP	PMD_SECT_WB
-
-/* PTWs cacheable, inner WBWA shareable, outer WBWA not shareable */
-#define TTB_FLAGS_SMP	TTB_IRGN_WBWA|TTB_S|TTB_NOS|TTB_RGN_OC_WBWA
-#define PMD_FLAGS_SMP	PMD_SECT_WBWA|PMD_SECT_S
+#ifdef CONFIG_ARM_LPAE
+#include "proc-v7-3level.S"
+#else
+#include "proc-v7-2level.S"
+#endif
 
 ENTRY(cpu_v7_proc_init)
 	mov	pc, lr
@@ -97,176 +84,58 @@ ENTRY(cpu_v7_dcache_clean_area)
 	mov	pc, lr
 ENDPROC(cpu_v7_dcache_clean_area)
 
-/*
- *	cpu_v7_switch_mm(pgd_phys, tsk)
- *
- *	Set the translation table base pointer to be pgd_phys
- *
- *	- pgd_phys - physical address of new TTB
- *
- *	It is assumed that:
- *	- we are not using split page tables
- */
-ENTRY(cpu_v7_switch_mm)
-#ifdef CONFIG_MMU
-	mov	r2, #0
-	ldr	r1, [r1, #MM_CONTEXT_ID]	@ get mm->context.id
-	ALT_SMP(orr	r0, r0, #TTB_FLAGS_SMP)
-	ALT_UP(orr	r0, r0, #TTB_FLAGS_UP)
-#ifdef CONFIG_ARM_ERRATA_430973
-	mcr	p15, 0, r2, c7, c5, 6		@ flush BTAC/BTB
-#endif
-#ifdef CONFIG_ARM_ERRATA_754322
-	dsb
-#endif
-	mcr	p15, 0, r2, c13, c0, 1		@ set reserved context ID
-	isb
-1:	mcr	p15, 0, r0, c2, c0, 0		@ set TTB 0
-	isb
-#ifdef CONFIG_ARM_ERRATA_754322
-	dsb
-#endif
-	mcr	p15, 0, r1, c13, c0, 1		@ set context ID
-	isb
-#endif
-	mov	pc, lr
-ENDPROC(cpu_v7_switch_mm)
-
-/*
- *	cpu_v7_set_pte_ext(ptep, pte)
- *
- *	Set a level 2 translation table entry.
- *
- *	- ptep  - pointer to level 2 translation table entry
- *		  (hardware version is stored at +2048 bytes)
- *	- pte   - PTE value to store
- *	- ext	- value for extended PTE bits
- */
-ENTRY(cpu_v7_set_pte_ext)
-#ifdef CONFIG_MMU
-	str	r1, [r0]			@ linux version
-
-	bic	r3, r1, #0x000003f0
-	bic	r3, r3, #PTE_TYPE_MASK
-	orr	r3, r3, r2
-	orr	r3, r3, #PTE_EXT_AP0 | 2
-
-	tst	r1, #1 << 4
-	orrne	r3, r3, #PTE_EXT_TEX(1)
-
-	eor	r1, r1, #L_PTE_DIRTY
-	tst	r1, #L_PTE_RDONLY | L_PTE_DIRTY
-	orrne	r3, r3, #PTE_EXT_APX
-
-	tst	r1, #L_PTE_USER
-	orrne	r3, r3, #PTE_EXT_AP1
-#ifdef CONFIG_CPU_USE_DOMAINS
-	@ allow kernel read/write access to read-only user pages
-	tstne	r3, #PTE_EXT_APX
-	bicne	r3, r3, #PTE_EXT_APX | PTE_EXT_AP0
-#endif
-
-	tst	r1, #L_PTE_XN
-	orrne	r3, r3, #PTE_EXT_XN
-
-	tst	r1, #L_PTE_YOUNG
-	tstne	r1, #L_PTE_PRESENT
-	moveq	r3, #0
-
- ARM(	str	r3, [r0, #2048]! )
- THUMB(	add	r0, r0, #2048 )
- THUMB(	str	r3, [r0] )
-	mcr	p15, 0, r0, c7, c10, 1		@ flush_pte
-#endif
-	mov	pc, lr
-ENDPROC(cpu_v7_set_pte_ext)
-
 	string	cpu_v7_name, "ARMv7 Processor"
 	.align
 
-	/*
-	 * Memory region attributes with SCTLR.TRE=1
-	 *
-	 *   n = TEX[0],C,B
-	 *   TR = PRRR[2n+1:2n]		- memory type
-	 *   IR = NMRR[2n+1:2n]		- inner cacheable property
-	 *   OR = NMRR[2n+17:2n+16]	- outer cacheable property
-	 *
-	 *			n	TR	IR	OR
-	 *   UNCACHED		000	00
-	 *   BUFFERABLE		001	10	00	00
-	 *   WRITETHROUGH	010	10	10	10
-	 *   WRITEBACK		011	10	11	11
-	 *   reserved		110
-	 *   WRITEALLOC		111	10	01	01
-	 *   DEV_SHARED		100	01
-	 *   DEV_NONSHARED	100	01
-	 *   DEV_WC		001	10
-	 *   DEV_CACHED		011	10
-	 *
-	 * Other attributes:
-	 *
-	 *   DS0 = PRRR[16] = 0		- device shareable property
-	 *   DS1 = PRRR[17] = 1		- device shareable property
-	 *   NS0 = PRRR[18] = 0		- normal shareable property
-	 *   NS1 = PRRR[19] = 1		- normal shareable property
-	 *   NOS = PRRR[24+n] = 1	- not outer shareable
-	 */
-.equ	PRRR,	0xff0a81a8
-.equ	NMRR,	0x40e040e0
-
 /* Suspend/resume support: derived from arch/arm/mach-s5pv210/sleep.S */
 .globl	cpu_v7_suspend_size
-.equ	cpu_v7_suspend_size, 4 * 9
+.equ	cpu_v7_suspend_size, 4 * 8
 #ifdef CONFIG_PM_SLEEP
 ENTRY(cpu_v7_do_suspend)
-	stmfd	sp!, {r4 - r11, lr}
+	stmfd	sp!, {r4 - r10, lr}
 	mrc	p15, 0, r4, c13, c0, 0	@ FCSE/PID
-	mrc	p15, 0, r5, c13, c0, 1	@ Context ID
-	mrc	p15, 0, r6, c13, c0, 3	@ User r/o thread ID
-	stmia	r0!, {r4 - r6}
+	mrc	p15, 0, r5, c13, c0, 3	@ User r/o thread ID
+	stmia	r0!, {r4 - r5}
 	mrc	p15, 0, r6, c3, c0, 0	@ Domain ID
-	mrc	p15, 0, r7, c2, c0, 0	@ TTB 0
-	mrc	p15, 0, r8, c2, c0, 1	@ TTB 1
-	mrc	p15, 0, r9, c1, c0, 0	@ Control register
-	mrc	p15, 0, r10, c1, c0, 1	@ Auxiliary control register
-	mrc	p15, 0, r11, c1, c0, 2	@ Co-processor access control
+	mrc	p15, 0, r7, c2, c0, 1	@ TTB 1
+	mrc	p15, 0, r11, c2, c0, 2	@ TTB control register
+	mrc	p15, 0, r8, c1, c0, 0	@ Control register
+	mrc	p15, 0, r9, c1, c0, 1	@ Auxiliary control register
+	mrc	p15, 0, r10, c1, c0, 2	@ Co-processor access control
 	stmia	r0, {r6 - r11}
-	ldmfd	sp!, {r4 - r11, pc}
+	ldmfd	sp!, {r4 - r10, pc}
 ENDPROC(cpu_v7_do_suspend)
 
 ENTRY(cpu_v7_do_resume)
 	mov	ip, #0
 	mcr	p15, 0, ip, c8, c7, 0	@ invalidate TLBs
 	mcr	p15, 0, ip, c7, c5, 0	@ invalidate I cache
-	ldmia	r0!, {r4 - r6}
+	mcr	p15, 0, ip, c13, c0, 1	@ set reserved context ID
+	ldmia	r0!, {r4 - r5}
 	mcr	p15, 0, r4, c13, c0, 0	@ FCSE/PID
-	mcr	p15, 0, r5, c13, c0, 1	@ Context ID
-	mcr	p15, 0, r6, c13, c0, 3	@ User r/o thread ID
+	mcr	p15, 0, r5, c13, c0, 3	@ User r/o thread ID
 	ldmia	r0, {r6 - r11}
 	mcr	p15, 0, r6, c3, c0, 0	@ Domain ID
-	mcr	p15, 0, r7, c2, c0, 0	@ TTB 0
-	mcr	p15, 0, r8, c2, c0, 1	@ TTB 1
-	mcr	p15, 0, ip, c2, c0, 2	@ TTB control register
+#ifndef CONFIG_ARM_LPAE
+	ALT_SMP(orr	r1, r1, #TTB_FLAGS_SMP)
+	ALT_UP(orr	r1, r1, #TTB_FLAGS_UP)
+#endif
+	mcr	p15, 0, r1, c2, c0, 0	@ TTB 0
+	mcr	p15, 0, r7, c2, c0, 1	@ TTB 1
+	mcr	p15, 0, r11, c2, c0, 2	@ TTB control register
 	mrc	p15, 0, r4, c1, c0, 1	@ Read Auxiliary control register
-	teq	r4, r10			@ Is it already set?
-	mcrne	p15, 0, r10, c1, c0, 1	@ No, so write it
-	mcr	p15, 0, r11, c1, c0, 2	@ Co-processor access control
+	teq	r4, r9			@ Is it already set?
+	mcrne	p15, 0, r9, c1, c0, 1	@ No, so write it
+	mcr	p15, 0, r10, c1, c0, 2	@ Co-processor access control
 	ldr	r4, =PRRR		@ PRRR
 	ldr	r5, =NMRR		@ NMRR
 	mcr	p15, 0, r4, c10, c2, 0	@ write PRRR
 	mcr	p15, 0, r5, c10, c2, 1	@ write NMRR
 	isb
 	dsb
-	mov	r0, r9			@ control register
-	mov	r2, r7, lsr #14		@ get TTB0 base
-	mov	r2, r2, lsl #14
-	ldr	r3, cpu_resume_l1_flags
+	mov	r0, r8			@ control register
 	b	cpu_resume_mmu
 ENDPROC(cpu_v7_do_resume)
-cpu_resume_l1_flags:
-	ALT_SMP(.long PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_FLAGS_SMP)
-	ALT_UP(.long  PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_FLAGS_UP)
 #endif
 
 	__CPUINIT
@@ -383,12 +252,7 @@ __v7_setup:
 	dsb
 #ifdef CONFIG_MMU
 	mcr	p15, 0, r10, c8, c7, 0		@ invalidate I + D TLBs
-	mcr	p15, 0, r10, c2, c0, 2		@ TTB control register
-	ALT_SMP(orr	r4, r4, #TTB_FLAGS_SMP)
-	ALT_UP(orr	r4, r4, #TTB_FLAGS_UP)
-	ALT_SMP(orr	r8, r8, #TTB_FLAGS_SMP)
-	ALT_UP(orr	r8, r8, #TTB_FLAGS_UP)
-	mcr	p15, 0, r8, c2, c0, 1		@ load TTB1
+	v7_ttb_setup r10, r4, r8, r5		@ TTBCR, TTBRx setup
 	ldr	r5, =PRRR			@ PRRR
 	ldr	r6, =NMRR			@ NMRR
 	mcr	p15, 0, r5, c10, c2, 0		@ write PRRR
@@ -410,16 +274,7 @@ __v7_setup:
 	mov	pc, lr				@ return to head.S:__ret
 ENDPROC(__v7_setup)
 
-	/*   AT
-	 *  TFR   EV X F   I D LR    S
-	 * .EEE ..EE PUI. .T.T 4RVI ZWRS BLDP WCAM
-	 * rxxx rrxx xxx0 0101 xxxx xxxx x111 xxxx < forced
-	 *    1    0 110       0011 1100 .111 1101 < we want
-	 */
-	.type	v7_crval, #object
-v7_crval:
-	crval	clear=0x0120c302, mmuset=0x10c03c7d, ucset=0x00c01c7c
-
+	.align	2
 __v7_setup_stack:
 	.space	4 * 11				@ 11 registers
 
@@ -441,11 +296,11 @@ __v7_setup_stack:
 	 */
 .macro __v7_proc initfunc, mm_mmuflags = 0, io_mmuflags = 0, hwcaps = 0
 	ALT_SMP(.long	PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_SECT_AP_READ | \
-			PMD_FLAGS_SMP | \mm_mmuflags)
+			PMD_SECT_AF | PMD_FLAGS_SMP | \mm_mmuflags)
 	ALT_UP(.long	PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_SECT_AP_READ | \
-			PMD_FLAGS_UP | \mm_mmuflags)
+			PMD_SECT_AF | PMD_FLAGS_UP | \mm_mmuflags)
 	.long	PMD_TYPE_SECT | PMD_SECT_XN | PMD_SECT_AP_WRITE | \
-		PMD_SECT_AP_READ | \io_mmuflags
+		PMD_SECT_AP_READ | PMD_SECT_AF | \io_mmuflags
 	W(b)	\initfunc
 	.long	cpu_arch_name
 	.long	cpu_elf_name
@@ -458,6 +313,7 @@ __v7_setup_stack:
 	.long	v7_cache_fns
 .endm
 
+#ifndef CONFIG_ARM_LPAE
 	/*
 	 * ARM Ltd. Cortex A5 processor.
 	 */
@@ -477,6 +333,7 @@ __v7_ca9mp_proc_info:
 	.long	0xff0ffff0
 	__v7_proc __v7_ca9mp_setup
 	.size	__v7_ca9mp_proc_info, . - __v7_ca9mp_proc_info
+#endif	/* CONFIG_ARM_LPAE */
 
 	/*
 	 * ARM Ltd. Cortex A15 processor.
diff --git a/arch/arm/mm/proc-xsc3.S b/arch/arm/mm/proc-xsc3.S
index 755e1bf2268..abf0507a08a 100644
--- a/arch/arm/mm/proc-xsc3.S
+++ b/arch/arm/mm/proc-xsc3.S
@@ -406,24 +406,23 @@ ENTRY(cpu_xsc3_set_pte_ext)
 	.align
 
 .globl	cpu_xsc3_suspend_size
-.equ	cpu_xsc3_suspend_size, 4 * 7
+.equ	cpu_xsc3_suspend_size, 4 * 6
 #ifdef CONFIG_PM_SLEEP
 ENTRY(cpu_xsc3_do_suspend)
-	stmfd	sp!, {r4 - r10, lr}
+	stmfd	sp!, {r4 - r9, lr}
 	mrc	p14, 0, r4, c6, c0, 0	@ clock configuration, for turbo mode
 	mrc	p15, 0, r5, c15, c1, 0	@ CP access reg
 	mrc	p15, 0, r6, c13, c0, 0	@ PID
 	mrc 	p15, 0, r7, c3, c0, 0	@ domain ID
-	mrc 	p15, 0, r8, c2, c0, 0	@ translation table base addr
-	mrc	p15, 0, r9, c1, c0, 1	@ auxiliary control reg
-	mrc 	p15, 0, r10, c1, c0, 0	@ control reg
+	mrc	p15, 0, r8, c1, c0, 1	@ auxiliary control reg
+	mrc 	p15, 0, r9, c1, c0, 0	@ control reg
 	bic	r4, r4, #2		@ clear frequency change bit
-	stmia	r0, {r4 - r10}		@ store cp regs
-	ldmia	sp!, {r4 - r10, pc}
+	stmia	r0, {r4 - r9}		@ store cp regs
+	ldmia	sp!, {r4 - r9, pc}
 ENDPROC(cpu_xsc3_do_suspend)
 
 ENTRY(cpu_xsc3_do_resume)
-	ldmia	r0, {r4 - r10}		@ load cp regs
+	ldmia	r0, {r4 - r9}		@ load cp regs
 	mov	ip, #0
 	mcr	p15, 0, ip, c7, c7, 0	@ invalidate I & D caches, BTB
 	mcr	p15, 0, ip, c7, c10, 4	@ drain write (&fill) buffer
@@ -433,15 +432,10 @@ ENTRY(cpu_xsc3_do_resume)
 	mcr	p15, 0, r5, c15, c1, 0	@ CP access reg
 	mcr	p15, 0, r6, c13, c0, 0	@ PID
 	mcr	p15, 0, r7, c3, c0, 0	@ domain ID
-	mcr	p15, 0, r8, c2, c0, 0	@ translation table base addr
-	mcr	p15, 0, r9, c1, c0, 1	@ auxiliary control reg
-
-	@ temporarily map resume_turn_on_mmu into the page table,
-	@ otherwise prefetch abort occurs after MMU is turned on
-	mov	r0, r10			@ control register
-	mov	r2, r8, lsr #14		@ get TTB0 base
-	mov	r2, r2, lsl #14
-	ldr	r3, =0x542e		@ section flags
+	orr	r1, r1, #0x18		@ cache the page table in L2
+	mcr	p15, 0, r1, c2, c0, 0	@ translation table base addr
+	mcr	p15, 0, r8, c1, c0, 1	@ auxiliary control reg
+	mov	r0, r9			@ control register
 	b	cpu_resume_mmu
 ENDPROC(cpu_xsc3_do_resume)
 #endif
diff --git a/arch/arm/mm/proc-xscale.S b/arch/arm/mm/proc-xscale.S
index fbc06e55b87..3277904beba 100644
--- a/arch/arm/mm/proc-xscale.S
+++ b/arch/arm/mm/proc-xscale.S
@@ -520,24 +520,23 @@ ENTRY(cpu_xscale_set_pte_ext)
 	.align
 
 .globl	cpu_xscale_suspend_size
-.equ	cpu_xscale_suspend_size, 4 * 7
+.equ	cpu_xscale_suspend_size, 4 * 6
 #ifdef CONFIG_PM_SLEEP
 ENTRY(cpu_xscale_do_suspend)
-	stmfd	sp!, {r4 - r10, lr}
+	stmfd	sp!, {r4 - r9, lr}
 	mrc	p14, 0, r4, c6, c0, 0	@ clock configuration, for turbo mode
 	mrc	p15, 0, r5, c15, c1, 0	@ CP access reg
 	mrc	p15, 0, r6, c13, c0, 0	@ PID
 	mrc	p15, 0, r7, c3, c0, 0	@ domain ID
-	mrc	p15, 0, r8, c2, c0, 0	@ translation table base addr
-	mrc	p15, 0, r9, c1, c1, 0	@ auxiliary control reg
-	mrc	p15, 0, r10, c1, c0, 0	@ control reg
+	mrc	p15, 0, r8, c1, c1, 0	@ auxiliary control reg
+	mrc	p15, 0, r9, c1, c0, 0	@ control reg
 	bic	r4, r4, #2		@ clear frequency change bit
-	stmia	r0, {r4 - r10}		@ store cp regs
-	ldmfd	sp!, {r4 - r10, pc}
+	stmia	r0, {r4 - r9}		@ store cp regs
+	ldmfd	sp!, {r4 - r9, pc}
 ENDPROC(cpu_xscale_do_suspend)
 
 ENTRY(cpu_xscale_do_resume)
-	ldmia	r0, {r4 - r10}		@ load cp regs
+	ldmia	r0, {r4 - r9}		@ load cp regs
 	mov	ip, #0
 	mcr	p15, 0, ip, c8, c7, 0	@ invalidate I & D TLBs
 	mcr	p15, 0, ip, c7, c7, 0	@ invalidate I & D caches, BTB
@@ -545,13 +544,9 @@ ENTRY(cpu_xscale_do_resume)
 	mcr	p15, 0, r5, c15, c1, 0	@ CP access reg
 	mcr	p15, 0, r6, c13, c0, 0	@ PID
 	mcr	p15, 0, r7, c3, c0, 0	@ domain ID
-	mcr	p15, 0, r8, c2, c0, 0	@ translation table base addr
-	mcr	p15, 0, r9, c1, c1, 0	@ auxiliary control reg
-	mov	r0, r10			@ control register
-	mov	r2, r8, lsr #14		@ get TTB0 base
-	mov	r2, r2, lsl #14
-	ldr	r3, =PMD_TYPE_SECT | PMD_SECT_BUFFERABLE | \
-		     PMD_SECT_CACHEABLE | PMD_SECT_AP_WRITE
+	mcr	p15, 0, r1, c2, c0, 0	@ translation table base addr
+	mcr	p15, 0, r8, c1, c1, 0	@ auxiliary control reg
+	mov	r0, r9			@ control register
 	b	cpu_resume_mmu
 ENDPROC(cpu_xscale_do_resume)
 #endif
diff --git a/arch/arm/oprofile/common.c b/arch/arm/oprofile/common.c
index c074e66ad22..4e0a371630b 100644
--- a/arch/arm/oprofile/common.c
+++ b/arch/arm/oprofile/common.c
@@ -116,7 +116,7 @@ int __init oprofile_arch_init(struct oprofile_operations *ops)
 	return oprofile_perf_init(ops);
 }
 
-void __exit oprofile_arch_exit(void)
+void oprofile_arch_exit(void)
 {
 	oprofile_perf_exit();
 }
diff --git a/arch/arm/plat-mxc/Makefile b/arch/arm/plat-mxc/Makefile
index d53c35fe2ea..8939f79e670 100644
--- a/arch/arm/plat-mxc/Makefile
+++ b/arch/arm/plat-mxc/Makefile
@@ -19,6 +19,7 @@ obj-$(CONFIG_ARCH_MXC_AUDMUX_V1) += audmux-v1.o
 obj-$(CONFIG_ARCH_MXC_AUDMUX_V2) += audmux-v2.o
 obj-$(CONFIG_MXC_DEBUG_BOARD) += 3ds_debugboard.o
 obj-$(CONFIG_CPU_FREQ_IMX)    += cpufreq.o
+obj-$(CONFIG_CPU_IDLE) += cpuidle.o
 ifdef CONFIG_SND_IMX_SOC
 obj-y += ssi-fiq.o
 obj-y += ssi-fiq-ksym.o
diff --git a/arch/arm/plat-mxc/cpuidle.c b/arch/arm/plat-mxc/cpuidle.c
new file mode 100644
index 00000000000..40c192420f4
--- /dev/null
+++ b/arch/arm/plat-mxc/cpuidle.c
@@ -0,0 +1,159 @@
+/*
+ * Copyright 2011 Freescale Semiconductor, Inc.
+ * Copyright 2011 Linaro Ltd.
+ *
+ * The code contained herein is licensed under the GNU General Public
+ * License. You may obtain a copy of the GNU General Public License
+ * Version 2 or later at the following locations:
+ *
+ * http://www.opensource.org/licenses/gpl-license.html
+ * http://www.gnu.org/copyleft/gpl.html
+ */
+
+#include <linux/kernel.h>
+#include <linux/io.h>
+#include <linux/cpuidle.h>
+#include <linux/err.h>
+#include <asm/proc-fns.h>
+#include <mach/cpuidle.h>
+
+static int (*mach_cpuidle)(struct cpuidle_device *dev,
+			       struct cpuidle_state *state);
+static struct cpuidle_driver *imx_cpuidle_driver;
+static struct cpuidle_device *device;
+
+static int imx_enter_idle(struct cpuidle_device *dev,
+			       struct cpuidle_state *state)
+{
+	struct timeval before, after;
+	int idle_time;
+
+	local_irq_disable();
+	local_fiq_disable();
+
+	do_gettimeofday(&before);
+
+	mach_cpuidle(dev, state);
+
+	do_gettimeofday(&after);
+
+	local_fiq_enable();
+	local_irq_enable();
+
+	idle_time = (after.tv_sec - before.tv_sec) * USEC_PER_SEC +
+		(after.tv_usec - before.tv_usec);
+
+	return idle_time;
+}
+
+static DEFINE_PER_CPU(struct cpuidle_device, imx_cpuidle_device);
+
+int __init imx_cpuidle_init(struct imx_cpuidle_data *cpuidle_data)
+{
+	int i, cpu_id;
+
+	if (cpuidle_data == NULL) {
+		pr_err("%s: cpuidle_data pointer NULL\n", __func__);
+		return -EINVAL;
+	}
+
+	if (cpuidle_data->mach_cpuidle == NULL) {
+		pr_err("%s: idle callback function NULL\n", __func__);
+		return -EINVAL;
+	}
+
+	imx_cpuidle_driver = cpuidle_data->imx_cpuidle_driver;
+
+	mach_cpuidle = cpuidle_data->mach_cpuidle;
+
+	/* register imx_cpuidle driver */
+	if (cpuidle_register_driver(imx_cpuidle_driver)) {
+		pr_err("%s: Failed to register cpuidle driver\n", __func__);
+		return -ENODEV;
+	}
+
+	/* if provided, initialize the mach level cpuidle functionality */
+	if (cpuidle_data->mach_cpuidle_init) {
+		if (cpuidle_data->mach_cpuidle_init(cpuidle_data)) {
+			pr_err("%s: Failed to register cpuidle driver\n",
+				 __func__);
+			cpuidle_unregister_driver(imx_cpuidle_driver);
+			return -ENODEV;
+		}
+	}
+
+	/* initialize state data for each cpuidle_device(one per present cpu)*/
+	for_each_cpu(cpu_id, cpu_present_mask) {
+
+		device = &per_cpu(imx_cpuidle_device, cpu_id);
+		device->cpu = cpu_id;
+
+		device->state_count = min((unsigned int) CPUIDLE_STATE_MAX,
+			cpuidle_data->num_states);
+
+		device->prepare = cpuidle_data->prepare;
+
+		for (i = 0; i < device->state_count; i++) {
+			strlcpy(device->states[i].name,
+				cpuidle_data->state_data[i].name,
+				CPUIDLE_NAME_LEN);
+
+			strlcpy(device->states[i].desc,
+				cpuidle_data->state_data[i].desc,
+				CPUIDLE_DESC_LEN);
+
+			device->states[i].driver_data =
+				(void *)cpuidle_data->
+				state_data[i].mach_cpu_pwr_state;
+
+			/*
+			 * Because the imx_enter_idle function measures
+			 * and returns a valid time for all imx SoCs,
+			 * we always set this flag.
+			 */
+			device->states[i].flags = CPUIDLE_FLAG_TIME_VALID;
+
+			device->states[i].exit_latency =
+				cpuidle_data->state_data[i].exit_latency;
+
+			device->states[i].power_usage =
+				cpuidle_data->state_data[i].power_usage;
+
+			device->states[i].target_residency =
+				cpuidle_data->state_data[i].target_residency;
+
+			device->states[i].enter = imx_enter_idle;
+		}
+	}
+
+	return 0;
+}
+
+int __init imx_cpuidle_dev_init(void)
+{
+	int cpu_id;
+
+	/*
+	 * Register online cpus.  If maxcpus is specified as a boot
+	 * argument and secondary cpus are brought online after boot,
+	 * this function can be called again to register a cpuidle
+	 * device for those secondary cpus.
+	 */
+	for_each_cpu(cpu_id, cpu_online_mask) {
+		device = &per_cpu(imx_cpuidle_device, cpu_id);
+		if (device == NULL) {
+			pr_err("%s: Failed to register (No device)\n",
+				__func__);
+			return -ENODEV;
+		}
+
+		if (!device->registered)
+			if (cpuidle_register_device(device)) {
+				pr_err("%s: Failed to register\n", __func__);
+				return -ENODEV;
+			}
+	}
+
+	return 0;
+}
+late_initcall(imx_cpuidle_dev_init);
diff --git a/arch/arm/plat-mxc/include/mach/cpuidle.h b/arch/arm/plat-mxc/include/mach/cpuidle.h
new file mode 100644
index 00000000000..2bb109e243b
--- /dev/null
+++ b/arch/arm/plat-mxc/include/mach/cpuidle.h
@@ -0,0 +1,56 @@
+/*
+ * Copyright 2011 Freescale Semiconductor, Inc.
+ * Copyright 2011 Linaro Ltd.
+ *
+ * The code contained herein is licensed under the GNU General Public
+ * License. You may obtain a copy of the GNU General Public License
+ * Version 2 or later at the following locations:
+ *
+ * http://www.opensource.org/licenses/gpl-license.html
+ * http://www.gnu.org/copyleft/gpl.html
+ */
+
+#ifndef __ARCH_ARM_PLAT_MXC_CPUIDLE_H__
+#define __ARCH_ARM_PLAT_MXC_CPUIDLE_H__
+
+#include <linux/cpuidle.h>
+#include <mach/hardware.h>
+
+/* for passing cpuidle state info to the cpuidle driver. */
+struct imx_cpuidle_state_data {
+	enum mxc_cpu_pwr_mode	mach_cpu_pwr_state;
+	char			*name;
+	char			*desc;
+	/* time in uS to exit this idle state */
+	unsigned int		exit_latency;
+	/* OPTIONAL - power usage of this idle state in mW */
+	unsigned int		power_usage;
+	/* OPTIONAL - in uS. See drivers/cpuidle/governors/menu.c for usage */
+	unsigned int		target_residency;
+};
+
+struct imx_cpuidle_data {
+	unsigned int num_states;
+	struct cpuidle_driver *imx_cpuidle_driver;
+	struct imx_cpuidle_state_data *state_data;
+	int (*mach_cpuidle)(struct cpuidle_device *dev,
+		struct cpuidle_state *state);
+
+	/* OPTIONAL - parameter of mach_cpuidle_init func below */
+	void *mach_init_data;
+	/* OPTIONAL - callback for mach level cpuidle initialization */
+	int (*mach_cpuidle_init)(void *mach_init_data);
+	/* OPTIONAL - Search drivers/cpuidle/cpuidle.c for usage */
+	int (*prepare)(struct cpuidle_device *dev);
+};
+
+#ifdef CONFIG_CPU_IDLE
+int imx_cpuidle_init(struct imx_cpuidle_data *cpuidle_data);
+#else
+static inline int imx_cpuidle_init(struct imx_cpuidle_data *cpuidle_data)
+{
+	return -EINVAL;
+}
+#endif /* CONFIG_CPU_IDLE */
+
+#endif /* __ARCH_ARM_PLAT_MXC_CPUIDLE_H__ */
diff --git a/arch/arm/plat-mxc/include/mach/iomux-v3.h b/arch/arm/plat-mxc/include/mach/iomux-v3.h
index ebbce33097a..45099566fec 100644
--- a/arch/arm/plat-mxc/include/mach/iomux-v3.h
+++ b/arch/arm/plat-mxc/include/mach/iomux-v3.h
@@ -89,11 +89,11 @@ typedef u64 iomux_v3_cfg_t;
 #define PAD_CTL_HYS			(1 << 8)
 
 #define PAD_CTL_PKE			(1 << 7)
-#define PAD_CTL_PUE			(1 << 6)
-#define PAD_CTL_PUS_100K_DOWN		(0 << 4)
-#define PAD_CTL_PUS_47K_UP		(1 << 4)
-#define PAD_CTL_PUS_100K_UP		(2 << 4)
-#define PAD_CTL_PUS_22K_UP		(3 << 4)
+#define PAD_CTL_PUE			(1 << 6 | PAD_CTL_PKE)
+#define PAD_CTL_PUS_100K_DOWN		(0 << 4 | PAD_CTL_PUE)
+#define PAD_CTL_PUS_47K_UP		(1 << 4 | PAD_CTL_PUE)
+#define PAD_CTL_PUS_100K_UP		(2 << 4 | PAD_CTL_PUE)
+#define PAD_CTL_PUS_22K_UP		(3 << 4 | PAD_CTL_PUE)
 
 #define PAD_CTL_ODE			(1 << 3)
 
diff --git a/arch/arm/plat-mxc/include/mach/memory.h b/arch/arm/plat-mxc/include/mach/memory.h
index 11be5cdbdd1..3ec84b90224 100644
--- a/arch/arm/plat-mxc/include/mach/memory.h
+++ b/arch/arm/plat-mxc/include/mach/memory.h
@@ -40,19 +40,4 @@
 # endif
 #endif
 
-#if defined(CONFIG_MX3_VIDEO)
-/*
- * Increase size of DMA-consistent memory region.
- * This is required for mx3 camera driver to capture at least two QXGA frames.
- */
-#define CONSISTENT_DMA_SIZE SZ_8M
-
-#elif defined(CONFIG_MX1_VIDEO) || defined(CONFIG_VIDEO_MX2_HOSTSUPPORT)
-/*
- * Increase size of DMA-consistent memory region.
- * This is required for i.MX camera driver to capture at least four VGA frames.
- */
-#define CONSISTENT_DMA_SIZE SZ_4M
-#endif /* CONFIG_MX1_VIDEO || CONFIG_VIDEO_MX2_HOSTSUPPORT */
-
 #endif /* __ASM_ARCH_MXC_MEMORY_H__ */
diff --git a/arch/arm/plat-omap/include/plat/io.h b/arch/arm/plat-omap/include/plat/io.h
index d72ec85c97e..ebe67ea8d06 100644
--- a/arch/arm/plat-omap/include/plat/io.h
+++ b/arch/arm/plat-omap/include/plat/io.h
@@ -309,6 +309,8 @@ extern void omap2_init_common_devices(struct omap_sdrc_params *sdrc_cs0,
 void __iomem *omap_ioremap(unsigned long phys, size_t size, unsigned int type);
 void omap_iounmap(volatile void __iomem *addr);
 
+extern void __init omap_init_consistent_dma_size(void);
+
 #endif
 
 #endif
diff --git a/arch/arm/plat-omap/include/plat/memory.h b/arch/arm/plat-omap/include/plat/memory.h
index e6720aa2d55..7f9df6f1e11 100644
--- a/arch/arm/plat-omap/include/plat/memory.h
+++ b/arch/arm/plat-omap/include/plat/memory.h
@@ -85,18 +85,5 @@
 
 #endif	/* CONFIG_ARCH_OMAP15XX */
 
-/* Override the ARM default */
-#ifdef CONFIG_FB_OMAP_CONSISTENT_DMA_SIZE
-
-#if (CONFIG_FB_OMAP_CONSISTENT_DMA_SIZE == 0)
-#undef CONFIG_FB_OMAP_CONSISTENT_DMA_SIZE
-#define CONFIG_FB_OMAP_CONSISTENT_DMA_SIZE 2
-#endif
-
-#define CONSISTENT_DMA_SIZE \
-	(((CONFIG_FB_OMAP_CONSISTENT_DMA_SIZE + 1) & ~1) * 1024 * 1024)
-
-#endif
-
 #endif
 
diff --git a/arch/arm/plat-omap/io.c b/arch/arm/plat-omap/io.c
index f1ecfa9fc61..e9b0e23edd0 100644
--- a/arch/arm/plat-omap/io.c
+++ b/arch/arm/plat-omap/io.c
@@ -12,6 +12,7 @@
 #include <linux/module.h>
 #include <linux/io.h>
 #include <linux/mm.h>
+#include <linux/dma-mapping.h>
 
 #include <plat/omap7xx.h>
 #include <plat/omap1510.h>
@@ -139,3 +140,10 @@ void omap_iounmap(volatile void __iomem *addr)
 		__iounmap(addr);
 }
 EXPORT_SYMBOL(omap_iounmap);
+
+void __init omap_init_consistent_dma_size(void)
+{
+#ifdef CONFIG_FB_OMAP_CONSISTENT_DMA_SIZE
+	init_consistent_dma_size(CONFIG_FB_OMAP_CONSISTENT_DMA_SIZE << 20);
+#endif
+}
diff --git a/arch/arm/plat-s5p/include/plat/exynos4.h b/arch/arm/plat-s5p/include/plat/exynos4.h
index 907caab53dc..d62f7f74a80 100644
--- a/arch/arm/plat-s5p/include/plat/exynos4.h
+++ b/arch/arm/plat-s5p/include/plat/exynos4.h
@@ -15,6 +15,7 @@
 extern void exynos4_common_init_uarts(struct s3c2410_uartcfg *cfg, int no);
 extern void exynos4_register_clocks(void);
 extern void exynos4_setup_clocks(void);
+extern int exynos4_subrev(void);
 
 #ifdef CONFIG_CPU_EXYNOS4210
 
diff --git a/arch/arm/plat-samsung/include/plat/devs.h b/arch/arm/plat-samsung/include/plat/devs.h
index 24ebb1e1de4..04380872048 100644
--- a/arch/arm/plat-samsung/include/plat/devs.h
+++ b/arch/arm/plat-samsung/include/plat/devs.h
@@ -148,6 +148,7 @@ extern struct platform_device s5p_device_mipi_csis1;
 extern struct platform_device s5p_device_ehci;
 
 extern struct platform_device exynos4_device_sysmmu;
+extern struct platform_device exynos4_device_tmu;
 
 /* s3c2440 specific devices */
 
diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index 79bcb431693..0cbd5a0a933 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -11,6 +11,7 @@
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/cpu.h>
+#include <linux/cpu_pm.h>
 #include <linux/kernel.h>
 #include <linux/notifier.h>
 #include <linux/signal.h>
@@ -68,7 +69,7 @@ static bool vfp_state_in_hw(unsigned int cpu, struct thread_info *thread)
 /*
  * Force a reload of the VFP context from the thread structure.  We do
  * this by ensuring that access to the VFP hardware is disabled, and
- * clear last_VFP_context.  Must be called from non-preemptible context.
+ * clear vfp_current_hw_state.  Must be called from non-preemptible context.
  */
 static void vfp_force_reload(unsigned int cpu, struct thread_info *thread)
 {
@@ -436,9 +437,7 @@ static void vfp_enable(void *unused)
 	set_copro_access(access | CPACC_FULL(10) | CPACC_FULL(11));
 }
 
-#ifdef CONFIG_PM
-#include <linux/syscore_ops.h>
-
+#ifdef CONFIG_CPU_PM
 static int vfp_pm_suspend(void)
 {
 	struct thread_info *ti = current_thread_info();
@@ -468,19 +467,33 @@ static void vfp_pm_resume(void)
 	fmxr(FPEXC, fmrx(FPEXC) & ~FPEXC_EN);
 }
 
-static struct syscore_ops vfp_pm_syscore_ops = {
-	.suspend	= vfp_pm_suspend,
-	.resume		= vfp_pm_resume,
+static int vfp_cpu_pm_notifier(struct notifier_block *self, unsigned long cmd,
+	void *v)
+{
+	switch (cmd) {
+	case CPU_PM_ENTER:
+		vfp_pm_suspend();
+		break;
+	case CPU_PM_ENTER_FAILED:
+	case CPU_PM_EXIT:
+		vfp_pm_resume();
+		break;
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block vfp_cpu_pm_notifier_block = {
+	.notifier_call = vfp_cpu_pm_notifier,
 };
 
 static void vfp_pm_init(void)
 {
-	register_syscore_ops(&vfp_pm_syscore_ops);
+	cpu_pm_register_notifier(&vfp_cpu_pm_notifier_block);
 }
 
 #else
 static inline void vfp_pm_init(void) { }
-#endif /* CONFIG_PM */
+#endif /* CONFIG_CPU_PM */
 
 /*
  * Ensure that the VFP state stored in 'thread->vfpstate' is up to date
diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h
index 6fbce725c71..a0f358d4a00 100644
--- a/arch/powerpc/include/asm/sections.h
+++ b/arch/powerpc/include/asm/sections.h
@@ -8,7 +8,7 @@
 
 #ifdef __powerpc64__
 
-extern char _end[];
+extern char __end_interrupts[];
 
 static inline int in_kernel_text(unsigned long addr)
 {
diff --git a/arch/powerpc/include/asm/sparsemem.h b/arch/powerpc/include/asm/sparsemem.h
index 54a47ea2c3a..0c5fa314561 100644
--- a/arch/powerpc/include/asm/sparsemem.h
+++ b/arch/powerpc/include/asm/sparsemem.h
@@ -16,7 +16,7 @@
 #endif /* CONFIG_SPARSEMEM */
 
 #ifdef CONFIG_MEMORY_HOTPLUG
-extern void create_section_mapping(unsigned long start, unsigned long end);
+extern int create_section_mapping(unsigned long start, unsigned long end);
 extern int remove_section_mapping(unsigned long start, unsigned long end);
 #ifdef CONFIG_NUMA
 extern int hot_add_scn_to_nid(unsigned long scn_addr);
diff --git a/arch/powerpc/include/asm/synch.h b/arch/powerpc/include/asm/synch.h
index d7cab44643c..87878c68d1c 100644
--- a/arch/powerpc/include/asm/synch.h
+++ b/arch/powerpc/include/asm/synch.h
@@ -13,6 +13,7 @@
 extern unsigned int __start___lwsync_fixup, __stop___lwsync_fixup;
 extern void do_lwsync_fixups(unsigned long value, void *fixup_start,
 			     void *fixup_end);
+extern void do_final_fixups(void);
 
 static inline void eieio(void)
 {
diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index b06bdae0406..ad892f7a757 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -131,7 +131,6 @@ static void kvm_patch_ins_b(u32 *inst, int addr)
 	/* On relocatable kernels interrupts handlers and our code
 	   can be in different regions, so we don't patch them */
 
-	extern u32 __end_interrupts;
 	if ((ulong)inst < (ulong)&__end_interrupts)
 		return;
 #endif
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index 209135af0a4..912c36a45f6 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -107,6 +107,8 @@ notrace unsigned long __init early_init(unsigned long dt_ptr)
 			 PTRRELOC(&__start___lwsync_fixup),
 			 PTRRELOC(&__stop___lwsync_fixup));
 
+	do_final_fixups();
+
 	return KERNELBASE + offset;
 }
 
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index aebef1320ed..e0f2031e23e 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -353,6 +353,7 @@ void __init setup_system(void)
 			  &__start___fw_ftr_fixup, &__stop___fw_ftr_fixup);
 	do_lwsync_fixups(cur_cpu_spec->cpu_features,
 			 &__start___lwsync_fixup, &__stop___lwsync_fixup);
+	do_final_fixups();
 
 	/*
 	 * Unflatten the device-tree passed by prom_init or kexec
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index cc0d7f1b19a..0e85639d48a 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -43,6 +43,7 @@
 #include <asm/processor.h>
 #include <asm/cputhreads.h>
 #include <asm/page.h>
+#include <asm/hvcall.h>
 #include <linux/gfp.h>
 #include <linux/sched.h>
 #include <linux/vmalloc.h>
diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c
index 0d08d017139..7a8a7487cee 100644
--- a/arch/powerpc/lib/feature-fixups.c
+++ b/arch/powerpc/lib/feature-fixups.c
@@ -18,6 +18,8 @@
 #include <linux/init.h>
 #include <asm/cputable.h>
 #include <asm/code-patching.h>
+#include <asm/page.h>
+#include <asm/sections.h>
 
 
 struct fixup_entry {
@@ -128,6 +130,27 @@ void do_lwsync_fixups(unsigned long value, void *fixup_start, void *fixup_end)
 	}
 }
 
+void do_final_fixups(void)
+{
+#if defined(CONFIG_PPC64) && defined(CONFIG_RELOCATABLE)
+	int *src, *dest;
+	unsigned long length;
+
+	if (PHYSICAL_START == 0)
+		return;
+
+	src = (int *)(KERNELBASE + PHYSICAL_START);
+	dest = (int *)KERNELBASE;
+	length = (__end_interrupts - _stext) / sizeof(int);
+
+	while (length--) {
+		patch_instruction(dest, *src);
+		src++;
+		dest++;
+	}
+#endif
+}
+
 #ifdef CONFIG_FTR_FIXUP_SELFTEST
 
 #define check(x)	\
diff --git a/arch/powerpc/mm/gup.c b/arch/powerpc/mm/gup.c
index fec13200868..d7efdbf640c 100644
--- a/arch/powerpc/mm/gup.c
+++ b/arch/powerpc/mm/gup.c
@@ -16,16 +16,6 @@
 
 #ifdef __HAVE_ARCH_PTE_SPECIAL
 
-static inline void get_huge_page_tail(struct page *page)
-{
-	/*
-	 * __split_huge_page_refcount() cannot run
-	 * from under us.
-	 */
-	VM_BUG_ON(atomic_read(&page->_count) < 0);
-	atomic_inc(&page->_count);
-}
-
 /*
  * The performance critical leaf functions are made noinline otherwise gcc
  * inlines everything into a single function which results in too much
@@ -57,8 +47,6 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
 			put_page(page);
 			return 0;
 		}
-		if (PageTail(page))
-			get_huge_page_tail(page);
 		pages[*nr] = page;
 		(*nr)++;
 
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 26b2872b3d0..07f9e9f0d87 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -534,11 +534,11 @@ static unsigned long __init htab_get_table_size(void)
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
-void create_section_mapping(unsigned long start, unsigned long end)
+int create_section_mapping(unsigned long start, unsigned long end)
 {
-	BUG_ON(htab_bolt_mapping(start, end, __pa(start),
+	return htab_bolt_mapping(start, end, __pa(start),
 				 pgprot_val(PAGE_KERNEL), mmu_linear_psize,
-				 mmu_kernel_ssize));
+				 mmu_kernel_ssize);
 }
 
 int remove_section_mapping(unsigned long start, unsigned long end)
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 0b9a5c1901b..da5eb388570 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -390,7 +390,7 @@ static noinline int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long add
 {
 	unsigned long mask;
 	unsigned long pte_end;
-	struct page *head, *page;
+	struct page *head, *page, *tail;
 	pte_t pte;
 	int refs;
 
@@ -413,6 +413,7 @@ static noinline int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long add
 	head = pte_page(pte);
 
 	page = head + ((addr & (sz-1)) >> PAGE_SHIFT);
+	tail = page;
 	do {
 		VM_BUG_ON(compound_head(page) != head);
 		pages[*nr] = page;
@@ -428,10 +429,20 @@ static noinline int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long add
 
 	if (unlikely(pte_val(pte) != pte_val(*ptep))) {
 		/* Could be optimized better */
-		while (*nr) {
-			put_page(page);
-			(*nr)--;
-		}
+		*nr -= refs;
+		while (refs--)
+			put_page(head);
+		return 0;
+	}
+
+	/*
+	 * Any tail page need their mapcount reference taken before we
+	 * return.
+	 */
+	while (refs--) {
+		if (PageTail(tail))
+			get_huge_page_tail(tail);
+		tail++;
 	}
 
 	return 1;
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index c781bbcf733..95985f286e3 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -123,7 +123,8 @@ int arch_add_memory(int nid, u64 start, u64 size)
 	pgdata = NODE_DATA(nid);
 
 	start = (unsigned long)__va(start);
-	create_section_mapping(start, start + size);
+	if (create_section_mapping(start, start + size))
+		return -EINVAL;
 
 	/* this should work for most non-highmem platforms */
 	zone = pgdata->node_zones;
diff --git a/arch/powerpc/mm/mmu_context_hash64.c b/arch/powerpc/mm/mmu_context_hash64.c
index 3bafc3deca6..4ff587e3825 100644
--- a/arch/powerpc/mm/mmu_context_hash64.c
+++ b/arch/powerpc/mm/mmu_context_hash64.c
@@ -136,8 +136,8 @@ int use_cop(unsigned long acop, struct mm_struct *mm)
 	if (!mm || !acop)
 		return -EINVAL;
 
-	/* We need to make sure mm_users doesn't change */
-	down_read(&mm->mmap_sem);
+	/* The page_table_lock ensures mm_users won't change under us */
+	spin_lock(&mm->page_table_lock);
 	spin_lock(mm->context.cop_lockp);
 
 	if (mm->context.cop_pid == COP_PID_NONE) {
@@ -164,7 +164,7 @@ int use_cop(unsigned long acop, struct mm_struct *mm)
 
 out:
 	spin_unlock(mm->context.cop_lockp);
-	up_read(&mm->mmap_sem);
+	spin_unlock(&mm->page_table_lock);
 
 	return ret;
 }
@@ -185,8 +185,8 @@ void drop_cop(unsigned long acop, struct mm_struct *mm)
 	if (WARN_ON_ONCE(!mm))
 		return;
 
-	/* We need to make sure mm_users doesn't change */
-	down_read(&mm->mmap_sem);
+	/* The page_table_lock ensures mm_users won't change under us */
+	spin_lock(&mm->page_table_lock);
 	spin_lock(mm->context.cop_lockp);
 
 	mm->context.acop &= ~acop;
@@ -213,7 +213,7 @@ void drop_cop(unsigned long acop, struct mm_struct *mm)
 	}
 
 	spin_unlock(mm->context.cop_lockp);
-	up_read(&mm->mmap_sem);
+	spin_unlock(&mm->page_table_lock);
 }
 EXPORT_SYMBOL_GPL(drop_cop);
 
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 2164006fe17..2c1ae7a5fb5 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -1214,11 +1214,12 @@ int hot_add_node_scn_to_nid(unsigned long scn_addr)
 			break;
 		}
 
-		of_node_put(memory);
 		if (nid >= 0)
 			break;
 	}
 
+	of_node_put(memory);
+
 	return nid;
 }
 
diff --git a/arch/powerpc/platforms/ps3/interrupt.c b/arch/powerpc/platforms/ps3/interrupt.c
index 600ed2c0ed5..1aa478b97aa 100644
--- a/arch/powerpc/platforms/ps3/interrupt.c
+++ b/arch/powerpc/platforms/ps3/interrupt.c
@@ -88,6 +88,7 @@ struct ps3_private {
 	struct ps3_bmp bmp __attribute__ ((aligned (PS3_BMP_MINALIGN)));
 	u64 ppe_id;
 	u64 thread_id;
+	unsigned long ipi_mask;
 };
 
 static DEFINE_PER_CPU(struct ps3_private, ps3_private);
@@ -144,7 +145,11 @@ static void ps3_chip_unmask(struct irq_data *d)
 static void ps3_chip_eoi(struct irq_data *d)
 {
 	const struct ps3_private *pd = irq_data_get_irq_chip_data(d);
-	lv1_end_of_interrupt_ext(pd->ppe_id, pd->thread_id, d->irq);
+
+	/* non-IPIs are EOIed here. */
+
+	if (!test_bit(63 - d->irq, &pd->ipi_mask))
+		lv1_end_of_interrupt_ext(pd->ppe_id, pd->thread_id, d->irq);
 }
 
 /**
@@ -691,6 +696,16 @@ void __init ps3_register_ipi_debug_brk(unsigned int cpu, unsigned int virq)
 		cpu, virq, pd->bmp.ipi_debug_brk_mask);
 }
 
+void __init ps3_register_ipi_irq(unsigned int cpu, unsigned int virq)
+{
+	struct ps3_private *pd = &per_cpu(ps3_private, cpu);
+
+	set_bit(63 - virq, &pd->ipi_mask);
+
+	DBG("%s:%d: cpu %u, virq %u, ipi_mask %lxh\n", __func__, __LINE__,
+		cpu, virq, pd->ipi_mask);
+}
+
 static unsigned int ps3_get_irq(void)
 {
 	struct ps3_private *pd = &__get_cpu_var(ps3_private);
@@ -720,6 +735,12 @@ static unsigned int ps3_get_irq(void)
 		BUG();
 	}
 #endif
+
+	/* IPIs are EOIed here. */
+
+	if (test_bit(63 - plug, &pd->ipi_mask))
+		lv1_end_of_interrupt_ext(pd->ppe_id, pd->thread_id, plug);
+
 	return plug;
 }
 
diff --git a/arch/powerpc/platforms/ps3/platform.h b/arch/powerpc/platforms/ps3/platform.h
index 9a196a88eda..1a633ed0fe9 100644
--- a/arch/powerpc/platforms/ps3/platform.h
+++ b/arch/powerpc/platforms/ps3/platform.h
@@ -43,6 +43,7 @@ void ps3_mm_shutdown(void);
 void ps3_init_IRQ(void);
 void ps3_shutdown_IRQ(int cpu);
 void __init ps3_register_ipi_debug_brk(unsigned int cpu, unsigned int virq);
+void __init ps3_register_ipi_irq(unsigned int cpu, unsigned int virq);
 
 /* smp */
 
diff --git a/arch/powerpc/platforms/ps3/smp.c b/arch/powerpc/platforms/ps3/smp.c
index 4c44794faac..f609345b6c3 100644
--- a/arch/powerpc/platforms/ps3/smp.c
+++ b/arch/powerpc/platforms/ps3/smp.c
@@ -94,6 +94,8 @@ static void __init ps3_smp_setup_cpu(int cpu)
 
 		if (result)
 			virqs[i] = NO_IRQ;
+		else
+			ps3_register_ipi_irq(cpu, virqs[i]);
 	}
 
 	ps3_register_ipi_debug_brk(cpu, virqs[PPC_MSG_DEBUGGER_BREAK]);
diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index e9be25bc571..0f1b706506e 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -112,6 +112,7 @@ void dlpar_free_cc_nodes(struct device_node *dn)
 	dlpar_free_one_cc_node(dn);
 }
 
+#define COMPLETE	0
 #define NEXT_SIBLING    1
 #define NEXT_CHILD      2
 #define NEXT_PROPERTY   3
@@ -158,6 +159,9 @@ struct device_node *dlpar_configure_connector(u32 drc_index)
 		spin_unlock(&rtas_data_buf_lock);
 
 		switch (rc) {
+		case COMPLETE:
+			break;
+
 		case NEXT_SIBLING:
 			dn = dlpar_parse_cc_node(ccwa);
 			if (!dn)
diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c
index ada6e07532e..d42f37d8a44 100644
--- a/arch/powerpc/platforms/pseries/eeh.c
+++ b/arch/powerpc/platforms/pseries/eeh.c
@@ -1338,7 +1338,7 @@ static const struct file_operations proc_eeh_operations = {
 static int __init eeh_init_proc(void)
 {
 	if (machine_is(pseries))
-		proc_create("ppc64/eeh", 0, NULL, &proc_eeh_operations);
+		proc_create("powerpc/eeh", 0, NULL, &proc_eeh_operations);
 	return 0;
 }
 __initcall(eeh_init_proc);
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 00ff00dfb24..123d72a15c0 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -47,7 +47,7 @@ struct sca_block {
 #define KVM_HPAGE_MASK(x)	(~(KVM_HPAGE_SIZE(x) - 1))
 #define KVM_PAGES_PER_HPAGE(x)	(KVM_HPAGE_SIZE(x) / PAGE_SIZE)
 
-#define CPUSTAT_HOST       0x80000000
+#define CPUSTAT_STOPPED    0x80000000
 #define CPUSTAT_WAIT       0x10000000
 #define CPUSTAT_ECALL_PEND 0x08000000
 #define CPUSTAT_STOP_INT   0x04000000
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index ef86ad24398..5804cfa7cba 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -47,29 +47,31 @@ enum s390_regset {
 
 void update_per_regs(struct task_struct *task)
 {
-	static const struct per_regs per_single_step = {
-		.control = PER_EVENT_IFETCH,
-		.start = 0,
-		.end = PSW_ADDR_INSN,
-	};
 	struct pt_regs *regs = task_pt_regs(task);
 	struct thread_struct *thread = &task->thread;
-	const struct per_regs *new;
-	struct per_regs old;
-
-	/* TIF_SINGLE_STEP overrides the user specified PER registers. */
-	new = test_tsk_thread_flag(task, TIF_SINGLE_STEP) ?
-		&per_single_step : &thread->per_user;
+	struct per_regs old, new;
+
+	/* Copy user specified PER registers */
+	new.control = thread->per_user.control;
+	new.start = thread->per_user.start;
+	new.end = thread->per_user.end;
+
+	/* merge TIF_SINGLE_STEP into user specified PER registers. */
+	if (test_tsk_thread_flag(task, TIF_SINGLE_STEP)) {
+		new.control |= PER_EVENT_IFETCH;
+		new.start = 0;
+		new.end = PSW_ADDR_INSN;
+	}
 
 	/* Take care of the PER enablement bit in the PSW. */
-	if (!(new->control & PER_EVENT_MASK)) {
+	if (!(new.control & PER_EVENT_MASK)) {
 		regs->psw.mask &= ~PSW_MASK_PER;
 		return;
 	}
 	regs->psw.mask |= PSW_MASK_PER;
 	__ctl_store(old, 9, 11);
-	if (memcmp(new, &old, sizeof(struct per_regs)) != 0)
-		__ctl_load(*new, 9, 11);
+	if (memcmp(&new, &old, sizeof(struct per_regs)) != 0)
+		__ctl_load(new, 9, 11);
 }
 
 void user_enable_single_step(struct task_struct *task)
@@ -895,6 +897,14 @@ static int s390_last_break_get(struct task_struct *target,
 	return 0;
 }
 
+static int s390_last_break_set(struct task_struct *target,
+			       const struct user_regset *regset,
+			       unsigned int pos, unsigned int count,
+			       const void *kbuf, const void __user *ubuf)
+{
+	return 0;
+}
+
 #endif
 
 static const struct user_regset s390_regsets[] = {
@@ -921,6 +931,7 @@ static const struct user_regset s390_regsets[] = {
 		.size = sizeof(long),
 		.align = sizeof(long),
 		.get = s390_last_break_get,
+		.set = s390_last_break_set,
 	},
 #endif
 };
@@ -1078,6 +1089,14 @@ static int s390_compat_last_break_get(struct task_struct *target,
 	return 0;
 }
 
+static int s390_compat_last_break_set(struct task_struct *target,
+				      const struct user_regset *regset,
+				      unsigned int pos, unsigned int count,
+				      const void *kbuf, const void __user *ubuf)
+{
+	return 0;
+}
+
 static const struct user_regset s390_compat_regsets[] = {
 	[REGSET_GENERAL] = {
 		.core_note_type = NT_PRSTATUS,
@@ -1101,6 +1120,7 @@ static const struct user_regset s390_compat_regsets[] = {
 		.size = sizeof(long),
 		.align = sizeof(long),
 		.get = s390_compat_last_break_get,
+		.set = s390_compat_last_break_set,
 	},
 	[REGSET_GENERAL_EXTENDED] = {
 		.core_note_type = NT_S390_HIGH_GPRS,
diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c
index 9e4c84187cf..5a5c084cc01 100644
--- a/arch/s390/kvm/diag.c
+++ b/arch/s390/kvm/diag.c
@@ -42,7 +42,7 @@ static int __diag_ipl_functions(struct kvm_vcpu *vcpu)
 		return -EOPNOTSUPP;
 	}
 
-	atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
+	atomic_set_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
 	vcpu->run->s390_reset_flags |= KVM_S390_RESET_SUBSYSTEM;
 	vcpu->run->s390_reset_flags |= KVM_S390_RESET_IPL;
 	vcpu->run->s390_reset_flags |= KVM_S390_RESET_CPU_INIT;
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index c7c51898984..02434543eab 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -132,7 +132,6 @@ static int handle_stop(struct kvm_vcpu *vcpu)
 	int rc = 0;
 
 	vcpu->stat.exit_stop_request++;
-	atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
 	spin_lock_bh(&vcpu->arch.local_int.lock);
 	if (vcpu->arch.local_int.action_bits & ACTION_STORE_ON_STOP) {
 		vcpu->arch.local_int.action_bits &= ~ACTION_STORE_ON_STOP;
@@ -149,6 +148,8 @@ static int handle_stop(struct kvm_vcpu *vcpu)
 	}
 
 	if (vcpu->arch.local_int.action_bits & ACTION_STOP_ON_STOP) {
+		atomic_set_mask(CPUSTAT_STOPPED,
+				&vcpu->arch.sie_block->cpuflags);
 		vcpu->arch.local_int.action_bits &= ~ACTION_STOP_ON_STOP;
 		VCPU_EVENT(vcpu, 3, "%s", "cpu stopped");
 		rc = -EOPNOTSUPP;
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index c9aeb4b4d0b..d4bd4c73faa 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -224,6 +224,7 @@ static void __do_deliver_interrupt(struct kvm_vcpu *vcpu,
 			offsetof(struct _lowcore, restart_psw), sizeof(psw_t));
 		if (rc == -EFAULT)
 			exception = 1;
+		atomic_clear_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
 		break;
 
 	case KVM_S390_PROGRAM_INT:
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index dc2b580e27b..8cdb1bd5856 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -265,10 +265,12 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	restore_fp_regs(&vcpu->arch.guest_fpregs);
 	restore_access_regs(vcpu->arch.guest_acrs);
 	gmap_enable(vcpu->arch.gmap);
+	atomic_set_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
 }
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
+	atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
 	gmap_disable(vcpu->arch.gmap);
 	save_fp_regs(&vcpu->arch.guest_fpregs);
 	save_access_regs(vcpu->arch.guest_acrs);
@@ -296,7 +298,9 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu)
 
 int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 {
-	atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH | CPUSTAT_SM);
+	atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH |
+						    CPUSTAT_SM |
+						    CPUSTAT_STOPPED);
 	vcpu->arch.sie_block->ecb   = 6;
 	vcpu->arch.sie_block->eca   = 0xC1002001U;
 	vcpu->arch.sie_block->fac   = (int) (long) facilities;
@@ -312,11 +316,17 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 				      unsigned int id)
 {
-	struct kvm_vcpu *vcpu = kzalloc(sizeof(struct kvm_vcpu), GFP_KERNEL);
-	int rc = -ENOMEM;
+	struct kvm_vcpu *vcpu;
+	int rc = -EINVAL;
+
+	if (id >= KVM_MAX_VCPUS)
+		goto out;
 
+	rc = -ENOMEM;
+
+	vcpu = kzalloc(sizeof(struct kvm_vcpu), GFP_KERNEL);
 	if (!vcpu)
-		goto out_nomem;
+		goto out;
 
 	vcpu->arch.sie_block = (struct kvm_s390_sie_block *)
 					get_zeroed_page(GFP_KERNEL);
@@ -352,7 +362,7 @@ out_free_sie_block:
 	free_page((unsigned long)(vcpu->arch.sie_block));
 out_free_cpu:
 	kfree(vcpu);
-out_nomem:
+out:
 	return ERR_PTR(rc);
 }
 
@@ -415,7 +425,7 @@ static int kvm_arch_vcpu_ioctl_set_initial_psw(struct kvm_vcpu *vcpu, psw_t psw)
 {
 	int rc = 0;
 
-	if (atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_RUNNING)
+	if (!(atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_STOPPED))
 		rc = -EBUSY;
 	else {
 		vcpu->run->psw_mask = psw.mask;
@@ -488,7 +498,7 @@ rerun_vcpu:
 	if (vcpu->sigset_active)
 		sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
 
-	atomic_set_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
+	atomic_clear_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
 
 	BUG_ON(vcpu->kvm->arch.float_int.local_int[vcpu->vcpu_id] == NULL);
 
diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c
index d6a50c1fb2e..2a129bf44b9 100644
--- a/arch/s390/kvm/sigp.c
+++ b/arch/s390/kvm/sigp.c
@@ -57,8 +57,8 @@ static int __sigp_sense(struct kvm_vcpu *vcpu, u16 cpu_addr,
 	spin_lock(&fi->lock);
 	if (fi->local_int[cpu_addr] == NULL)
 		rc = 3; /* not operational */
-	else if (atomic_read(fi->local_int[cpu_addr]->cpuflags)
-		 & CPUSTAT_RUNNING) {
+	else if (!(atomic_read(fi->local_int[cpu_addr]->cpuflags)
+		  & CPUSTAT_STOPPED)) {
 		*reg &= 0xffffffff00000000UL;
 		rc = 1; /* status stored */
 	} else {
@@ -212,7 +212,7 @@ static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address,
 
 	spin_lock_bh(&li->lock);
 	/* cpu must be in stopped state */
-	if (atomic_read(li->cpuflags) & CPUSTAT_RUNNING) {
+	if (!(atomic_read(li->cpuflags) & CPUSTAT_STOPPED)) {
 		rc = 1; /* incorrect state */
 		*reg &= SIGP_STAT_INCORRECT_STATE;
 		kfree(inti);
diff --git a/arch/s390/mm/gup.c b/arch/s390/mm/gup.c
index 45b405ca256..65cb06e2af4 100644
--- a/arch/s390/mm/gup.c
+++ b/arch/s390/mm/gup.c
@@ -52,7 +52,7 @@ static inline int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
 		unsigned long end, int write, struct page **pages, int *nr)
 {
 	unsigned long mask, result;
-	struct page *head, *page;
+	struct page *head, *page, *tail;
 	int refs;
 
 	result = write ? 0 : _SEGMENT_ENTRY_RO;
@@ -64,6 +64,7 @@ static inline int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
 	refs = 0;
 	head = pmd_page(pmd);
 	page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
+	tail = page;
 	do {
 		VM_BUG_ON(compound_head(page) != head);
 		pages[*nr] = page;
@@ -81,6 +82,17 @@ static inline int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
 		*nr -= refs;
 		while (refs--)
 			put_page(head);
+		return 0;
+	}
+
+	/*
+	 * Any tail page need their mapcount reference taken before we
+	 * return.
+	 */
+	while (refs--) {
+		if (PageTail(tail))
+			get_huge_page_tail(tail);
+		tail++;
 	}
 
 	return 1;
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 5d56c2b95b1..529a0883837 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -662,8 +662,9 @@ void page_table_free_rcu(struct mmu_gather *tlb, unsigned long *table)
 
 void __tlb_remove_table(void *_table)
 {
-	void *table = (void *)((unsigned long) _table & PAGE_MASK);
-	unsigned type = (unsigned long) _table & ~PAGE_MASK;
+	const unsigned long mask = (FRAG_MASK << 4) | FRAG_MASK;
+	void *table = (void *)((unsigned long) _table & ~mask);
+	unsigned type = (unsigned long) _table & mask;
 
 	if (type)
 		__page_table_free_rcu(table, type);
diff --git a/arch/sh/include/asm/page.h b/arch/sh/include/asm/page.h
index 822d6084195..abcc4dcc2d9 100644
--- a/arch/sh/include/asm/page.h
+++ b/arch/sh/include/asm/page.h
@@ -141,8 +141,13 @@ typedef struct page *pgtable_t;
 #endif /* !__ASSEMBLY__ */
 
 #ifdef CONFIG_UNCACHED_MAPPING
+#if defined(CONFIG_29BIT)
+#define UNCAC_ADDR(addr)	P2SEGADDR(addr)
+#define CAC_ADDR(addr)		P1SEGADDR(addr)
+#else
 #define UNCAC_ADDR(addr)	((addr) - PAGE_OFFSET + uncached_start)
 #define CAC_ADDR(addr)		((addr) - uncached_start + PAGE_OFFSET)
+#endif
 #else
 #define UNCAC_ADDR(addr)	((addr))
 #define CAC_ADDR(addr)		((addr))
diff --git a/arch/sparc/mm/gup.c b/arch/sparc/mm/gup.c
index a986b5d0571..42c55df3aec 100644
--- a/arch/sparc/mm/gup.c
+++ b/arch/sparc/mm/gup.c
@@ -56,6 +56,8 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
 			put_page(head);
 			return 0;
 		}
+		if (head != page)
+			get_huge_page_tail(page);
 
 		pages[*nr] = page;
 		(*nr)++;
diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index 620f5b70957..0491e40d696 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -513,8 +513,37 @@ __uml_exitcall(kill_io_thread);
 static inline int ubd_file_size(struct ubd *ubd_dev, __u64 *size_out)
 {
 	char *file;
+	int fd;
+	int err;
+
+	__u32 version;
+	__u32 align;
+	char *backing_file;
+	time_t mtime;
+	unsigned long long size;
+	int sector_size;
+	int bitmap_offset;
+
+	if (ubd_dev->file && ubd_dev->cow.file) {
+		file = ubd_dev->cow.file;
+
+		goto out;
+	}
 
-	file = ubd_dev->cow.file ? ubd_dev->cow.file : ubd_dev->file;
+	fd = os_open_file(ubd_dev->file, global_openflags, 0);
+	if (fd < 0)
+		return fd;
+
+	err = read_cow_header(file_reader, &fd, &version, &backing_file, \
+		&mtime, &size, &sector_size, &align, &bitmap_offset);
+	os_close_file(fd);
+
+	if(err == -EINVAL)
+		file = ubd_dev->file;
+	else
+		file = backing_file;
+
+out:
 	return os_file_size(file, size_out);
 }
 
diff --git a/arch/um/sys-x86_64/vdso/vma.c b/arch/um/sys-x86_64/vdso/vma.c
index 9495c8d0ce3..91f4ec9a0a5 100644
--- a/arch/um/sys-x86_64/vdso/vma.c
+++ b/arch/um/sys-x86_64/vdso/vma.c
@@ -28,7 +28,7 @@ static int __init init_vdso(void)
 
 	um_vdso_addr = task_size - PAGE_SIZE;
 
-	vdsop = kmalloc(GFP_KERNEL, sizeof(struct page *));
+	vdsop = kmalloc(sizeof(struct page *), GFP_KERNEL);
 	if (!vdsop)
 		goto oom;
 
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 7b3ca8324b6..9b7273cb219 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -495,7 +495,7 @@ static inline void default_wait_for_init_deassert(atomic_t *deassert)
 	return;
 }
 
-extern struct apic *generic_bigsmp_probe(void);
+extern void generic_bigsmp_probe(void);
 
 
 #ifdef CONFIG_X86_LOCAL_APIC
diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h
index fa7b9176b76..431793e5d48 100644
--- a/arch/x86/include/asm/timer.h
+++ b/arch/x86/include/asm/timer.h
@@ -32,6 +32,22 @@ extern int no_timer_check;
  *  (mathieu.desnoyers@polymtl.ca)
  *
  *			-johnstul@us.ibm.com "math is hard, lets go shopping!"
+ *
+ * In:
+ *
+ * ns = cycles * cyc2ns_scale / SC
+ *
+ * Although we may still have enough bits to store the value of ns,
+ * in some cases, we may not have enough bits to store cycles * cyc2ns_scale,
+ * leading to an incorrect result.
+ *
+ * To avoid this, we can decompose 'cycles' into quotient and remainder
+ * of division by SC.  Then,
+ *
+ * ns = (quot * SC + rem) * cyc2ns_scale / SC
+ *    = quot * cyc2ns_scale + (rem * cyc2ns_scale) / SC
+ *
+ *			- sqazi@google.com
  */
 
 DECLARE_PER_CPU(unsigned long, cyc2ns);
@@ -41,9 +57,14 @@ DECLARE_PER_CPU(unsigned long long, cyc2ns_offset);
 
 static inline unsigned long long __cycles_2_ns(unsigned long long cyc)
 {
+	unsigned long long quot;
+	unsigned long long rem;
 	int cpu = smp_processor_id();
 	unsigned long long ns = per_cpu(cyc2ns_offset, cpu);
-	ns += cyc * per_cpu(cyc2ns, cpu) >> CYC2NS_SCALE_FACTOR;
+	quot = (cyc >> CYC2NS_SCALE_FACTOR);
+	rem = cyc & ((1ULL << CYC2NS_SCALE_FACTOR) - 1);
+	ns += quot * per_cpu(cyc2ns, cpu) +
+		((rem * per_cpu(cyc2ns, cpu)) >> CYC2NS_SCALE_FACTOR);
 	return ns;
 }
 
diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index 37d369859c8..0c767a8e000 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -55,6 +55,7 @@
 #define UV_BAU_TUNABLES_DIR		"sgi_uv"
 #define UV_BAU_TUNABLES_FILE		"bau_tunables"
 #define WHITESPACE			" \t\n"
+#define uv_mmask			((1UL << uv_hub_info->m_val) - 1)
 #define uv_physnodeaddr(x)		((__pa((unsigned long)(x)) & uv_mmask))
 #define cpubit_isset(cpu, bau_local_cpumask) \
 	test_bit((cpu), (bau_local_cpumask).bits)
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index f26544a1521..54a13aaebc4 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -46,6 +46,13 @@
  *	PNODE   - the low N bits of the GNODE. The PNODE is the most useful variant
  *		  of the nasid for socket usage.
  *
+ *	GPA	- (global physical address) a socket physical address converted
+ *		  so that it can be used by the GRU as a global address. Socket
+ *		  physical addresses 1) need additional NASID (node) bits added
+ *		  to the high end of the address, and 2) unaliased if the
+ *		  partition does not have a physical address 0. In addition, on
+ *		  UV2 rev 1, GPAs need the gnode left shifted to bits 39 or 40.
+ *
  *
  *  NumaLink Global Physical Address Format:
  *  +--------------------------------+---------------------+
@@ -141,6 +148,8 @@ struct uv_hub_info_s {
 	unsigned int		gnode_extra;
 	unsigned char		hub_revision;
 	unsigned char		apic_pnode_shift;
+	unsigned char		m_shift;
+	unsigned char		n_lshift;
 	unsigned long		gnode_upper;
 	unsigned long		lowmem_remap_top;
 	unsigned long		lowmem_remap_base;
@@ -177,6 +186,16 @@ static inline int is_uv2_hub(void)
 	return uv_hub_info->hub_revision >= UV2_HUB_REVISION_BASE;
 }
 
+static inline int is_uv2_1_hub(void)
+{
+	return uv_hub_info->hub_revision == UV2_HUB_REVISION_BASE;
+}
+
+static inline int is_uv2_2_hub(void)
+{
+	return uv_hub_info->hub_revision == UV2_HUB_REVISION_BASE + 1;
+}
+
 union uvh_apicid {
     unsigned long       v;
     struct uvh_apicid_s {
@@ -276,7 +295,10 @@ static inline unsigned long uv_soc_phys_ram_to_gpa(unsigned long paddr)
 {
 	if (paddr < uv_hub_info->lowmem_remap_top)
 		paddr |= uv_hub_info->lowmem_remap_base;
-	return paddr | uv_hub_info->gnode_upper;
+	paddr |= uv_hub_info->gnode_upper;
+	paddr = ((paddr << uv_hub_info->m_shift) >> uv_hub_info->m_shift) |
+		((paddr >> uv_hub_info->m_val) << uv_hub_info->n_lshift);
+	return paddr;
 }
 
 
@@ -300,16 +322,19 @@ static inline unsigned long uv_gpa_to_soc_phys_ram(unsigned long gpa)
 	unsigned long remap_base = uv_hub_info->lowmem_remap_base;
 	unsigned long remap_top =  uv_hub_info->lowmem_remap_top;
 
+	gpa = ((gpa << uv_hub_info->m_shift) >> uv_hub_info->m_shift) |
+		((gpa >> uv_hub_info->n_lshift) << uv_hub_info->m_val);
+	gpa = gpa & uv_hub_info->gpa_mask;
 	if (paddr >= remap_base && paddr < remap_base + remap_top)
 		paddr -= remap_base;
 	return paddr;
 }
 
 
-/* gnode -> pnode */
+/* gpa -> pnode */
 static inline unsigned long uv_gpa_to_gnode(unsigned long gpa)
 {
-	return gpa >> uv_hub_info->m_val;
+	return gpa >> uv_hub_info->n_lshift;
 }
 
 /* gpa -> pnode */
@@ -320,6 +345,12 @@ static inline int uv_gpa_to_pnode(unsigned long gpa)
 	return uv_gpa_to_gnode(gpa) & n_mask;
 }
 
+/* gpa -> node offset*/
+static inline unsigned long uv_gpa_to_offset(unsigned long gpa)
+{
+	return (gpa << uv_hub_info->m_shift) >> uv_hub_info->m_shift;
+}
+
 /* pnode, offset --> socket virtual */
 static inline void *uv_pnode_offset_to_vaddr(int pnode, unsigned long offset)
 {
diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c
index efd737e827f..521bead0113 100644
--- a/arch/x86/kernel/apic/bigsmp_32.c
+++ b/arch/x86/kernel/apic/bigsmp_32.c
@@ -255,12 +255,24 @@ static struct apic apic_bigsmp = {
 	.x86_32_early_logical_apicid	= bigsmp_early_logical_apicid,
 };
 
-struct apic * __init generic_bigsmp_probe(void)
+void __init generic_bigsmp_probe(void)
 {
-	if (probe_bigsmp())
-		return &apic_bigsmp;
+	unsigned int cpu;
 
-	return NULL;
+	if (!probe_bigsmp())
+		return;
+
+	apic = &apic_bigsmp;
+
+	for_each_possible_cpu(cpu) {
+		if (early_per_cpu(x86_cpu_to_logical_apicid,
+				  cpu) == BAD_APICID)
+			continue;
+		early_per_cpu(x86_cpu_to_logical_apicid, cpu) =
+			bigsmp_early_logical_apicid(cpu);
+	}
+
+	pr_info("Overriding APIC driver with %s\n", apic_bigsmp.name);
 }
 
 apic_driver(apic_bigsmp);
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index b5254ad044a..0787bb3412f 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -200,14 +200,8 @@ void __init default_setup_apic_routing(void)
 	 * - we find more than 8 CPUs in acpi LAPIC listing with xAPIC support
 	 */
 
-	if (!cmdline_apic && apic == &apic_default) {
-		struct apic *bigsmp = generic_bigsmp_probe();
-		if (bigsmp) {
-			apic = bigsmp;
-			printk(KERN_INFO "Overriding APIC driver with %s\n",
-			       apic->name);
-		}
-	}
+	if (!cmdline_apic && apic == &apic_default)
+		generic_bigsmp_probe();
 #endif
 
 	if (apic->setup_apic_routing)
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 34b18594e72..cfeb978f49f 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -832,6 +832,10 @@ void __init uv_system_init(void)
 		uv_cpu_hub_info(cpu)->apic_pnode_shift = uvh_apicid.s.pnode_shift;
 		uv_cpu_hub_info(cpu)->hub_revision = uv_hub_info->hub_revision;
 
+		uv_cpu_hub_info(cpu)->m_shift = 64 - m_val;
+		uv_cpu_hub_info(cpu)->n_lshift = is_uv2_1_hub() ?
+				(m_val == 40 ? 40 : 39) : m_val;
+
 		pnode = uv_apicid_to_pnode(apicid);
 		blade = boot_pnode_to_blade(pnode);
 		lcpu = uv_blade_info[blade].nr_possible_cpus;
@@ -862,8 +866,7 @@ void __init uv_system_init(void)
 		if (uv_node_to_blade[nid] >= 0)
 			continue;
 		paddr = node_start_pfn(nid) << PAGE_SHIFT;
-		paddr = uv_soc_phys_ram_to_gpa(paddr);
-		pnode = (paddr >> m_val) & pnode_mask;
+		pnode = uv_gpa_to_pnode(uv_soc_phys_ram_to_gpa(paddr));
 		blade = boot_pnode_to_blade(pnode);
 		uv_node_to_blade[nid] = blade;
 	}
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 1b1ef3addcf..3213c52db76 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -508,6 +508,7 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
 	unsigned long from = cpuc->lbr_entries[0].from;
 	unsigned long old_to, to = cpuc->lbr_entries[0].to;
 	unsigned long ip = regs->ip;
+	int is_64bit = 0;
 
 	/*
 	 * We don't need to fixup if the PEBS assist is fault like
@@ -559,7 +560,10 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
 		} else
 			kaddr = (void *)to;
 
-		kernel_insn_init(&insn, kaddr);
+#ifdef CONFIG_X86_64
+		is_64bit = kernel_ip(to) || !test_thread_flag(TIF_IA32);
+#endif
+		insn_init(&insn, kaddr, is_64bit);
 		insn_get_length(&insn);
 		to += insn.length;
 	} while (to < ip);
diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c
index f1a6244d7d9..794bc95134c 100644
--- a/arch/x86/kernel/kprobes.c
+++ b/arch/x86/kernel/kprobes.c
@@ -75,8 +75,10 @@ DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
 	/*
 	 * Undefined/reserved opcodes, conditional jump, Opcode Extension
 	 * Groups, and some special opcodes can not boost.
+	 * This is non-const to keep gcc from statically optimizing it out, as
+	 * variable_test_bit makes gcc think only *(unsigned long*) is used.
 	 */
-static const u32 twobyte_is_boostable[256 / 32] = {
+static u32 twobyte_is_boostable[256 / 32] = {
 	/*      0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f          */
 	/*      ----------------------------------------------          */
 	W(0x00, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 0) | /* 00 */
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 9103b89c145..0741b062a30 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -95,8 +95,8 @@ static void __init MP_bus_info(struct mpc_bus *m)
 	}
 #endif
 
+	set_bit(m->busid, mp_bus_not_pci);
 	if (strncmp(str, BUSTYPE_ISA, sizeof(BUSTYPE_ISA) - 1) == 0) {
-		set_bit(m->busid, mp_bus_not_pci);
 #if defined(CONFIG_EISA) || defined(CONFIG_MCA)
 		mp_bus_id_to_type[m->busid] = MP_BUS_ISA;
 #endif
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 9242436e993..d4a705f2283 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -124,7 +124,7 @@ __setup("reboot=", reboot_setup);
  */
 
 /*
- * Some machines require the "reboot=b"  commandline option,
+ * Some machines require the "reboot=b" or "reboot=k"  commandline options,
  * this quirk makes that automatic.
  */
 static int __init set_bios_reboot(const struct dmi_system_id *d)
@@ -136,6 +136,15 @@ static int __init set_bios_reboot(const struct dmi_system_id *d)
 	return 0;
 }
 
+static int __init set_kbd_reboot(const struct dmi_system_id *d)
+{
+	if (reboot_type != BOOT_KBD) {
+		reboot_type = BOOT_KBD;
+		printk(KERN_INFO "%s series board detected. Selecting KBD-method for reboot.\n", d->ident);
+	}
+	return 0;
+}
+
 static struct dmi_system_id __initdata reboot_dmi_table[] = {
 	{	/* Handle problems with rebooting on Dell E520's */
 		.callback = set_bios_reboot,
@@ -295,7 +304,7 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
 		},
 	},
 	{ /* Handle reboot issue on Acer Aspire one */
-		.callback = set_bios_reboot,
+		.callback = set_kbd_reboot,
 		.ident = "Acer Aspire One A110",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
index dbe34b93137..ea305856151 100644
--- a/arch/x86/mm/gup.c
+++ b/arch/x86/mm/gup.c
@@ -108,16 +108,6 @@ static inline void get_head_page_multiple(struct page *page, int nr)
 	SetPageReferenced(page);
 }
 
-static inline void get_huge_page_tail(struct page *page)
-{
-	/*
-	 * __split_huge_page_refcount() cannot run
-	 * from under us.
-	 */
-	VM_BUG_ON(atomic_read(&page->_count) < 0);
-	atomic_inc(&page->_count);
-}
-
 static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr,
 		unsigned long end, int write, struct page **pages, int *nr)
 {
diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c
index b4996266210..f4f29b19fac 100644
--- a/arch/x86/mm/highmem_32.c
+++ b/arch/x86/mm/highmem_32.c
@@ -45,6 +45,7 @@ void *kmap_atomic_prot(struct page *page, pgprot_t prot)
 	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
 	BUG_ON(!pte_none(*(kmap_pte-idx)));
 	set_pte(kmap_pte-idx, mk_pte(page, prot));
+	arch_flush_lazy_mmu_mode();
 
 	return (void *)vaddr;
 }
@@ -88,6 +89,7 @@ void __kunmap_atomic(void *kvaddr)
 		 */
 		kpte_clear_flush(kmap_pte-idx, vaddr);
 		kmap_atomic_idx_pop();
+		arch_flush_lazy_mmu_mode();
 	}
 #ifdef CONFIG_DEBUG_HIGHMEM
 	else {
diff --git a/arch/x86/oprofile/init.c b/arch/x86/oprofile/init.c
index cdfe4c54dec..f148cf65267 100644
--- a/arch/x86/oprofile/init.c
+++ b/arch/x86/oprofile/init.c
@@ -21,6 +21,7 @@ extern int op_nmi_timer_init(struct oprofile_operations *ops);
 extern void op_nmi_exit(void);
 extern void x86_backtrace(struct pt_regs * const regs, unsigned int depth);
 
+static int nmi_timer;
 
 int __init oprofile_arch_init(struct oprofile_operations *ops)
 {
@@ -31,8 +32,9 @@ int __init oprofile_arch_init(struct oprofile_operations *ops)
 #ifdef CONFIG_X86_LOCAL_APIC
 	ret = op_nmi_init(ops);
 #endif
+	nmi_timer = (ret != 0);
 #ifdef CONFIG_X86_IO_APIC
-	if (ret < 0)
+	if (nmi_timer)
 		ret = op_nmi_timer_init(ops);
 #endif
 	ops->backtrace = x86_backtrace;
@@ -44,6 +46,7 @@ int __init oprofile_arch_init(struct oprofile_operations *ops)
 void oprofile_arch_exit(void)
 {
 #ifdef CONFIG_X86_LOCAL_APIC
-	op_nmi_exit();
+	if (!nmi_timer)
+		op_nmi_exit();
 #endif
 }
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index db8b915f54b..5b552198f77 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -115,9 +115,6 @@ early_param("nobau", setup_nobau);
 
 /* base pnode in this partition */
 static int uv_base_pnode __read_mostly;
-/* position of pnode (which is nasid>>1): */
-static int uv_nshift __read_mostly;
-static unsigned long uv_mmask __read_mostly;
 
 static DEFINE_PER_CPU(struct ptc_stats, ptcstats);
 static DEFINE_PER_CPU(struct bau_control, bau_control);
@@ -1435,7 +1432,7 @@ static void activation_descriptor_init(int node, int pnode, int base_pnode)
 {
 	int i;
 	int cpu;
-	unsigned long pa;
+	unsigned long gpa;
 	unsigned long m;
 	unsigned long n;
 	size_t dsize;
@@ -1451,9 +1448,9 @@ static void activation_descriptor_init(int node, int pnode, int base_pnode)
 	bau_desc = kmalloc_node(dsize, GFP_KERNEL, node);
 	BUG_ON(!bau_desc);
 
-	pa = uv_gpa(bau_desc); /* need the real nasid*/
-	n = pa >> uv_nshift;
-	m = pa & uv_mmask;
+	gpa = uv_gpa(bau_desc);
+	n = uv_gpa_to_gnode(gpa);
+	m = uv_gpa_to_offset(gpa);
 
 	/* the 14-bit pnode */
 	write_mmr_descriptor_base(pnode, (n << UV_DESC_PSHIFT | m));
@@ -1525,9 +1522,9 @@ static void pq_init(int node, int pnode)
 		bcp->queue_last		= pqp + (DEST_Q_SIZE - 1);
 	}
 	/*
-	 * need the pnode of where the memory was really allocated
+	 * need the gnode of where the memory was really allocated
 	 */
-	pn = uv_gpa(pqp) >> uv_nshift;
+	pn = uv_gpa_to_gnode(uv_gpa(pqp));
 	first = uv_physnodeaddr(pqp);
 	pn_first = ((unsigned long)pn << UV_PAYLOADQ_PNODE_SHIFT) | first;
 	last = uv_physnodeaddr(pqp + (DEST_Q_SIZE - 1));
@@ -1837,8 +1834,6 @@ static int __init uv_bau_init(void)
 		zalloc_cpumask_var_node(mask, GFP_KERNEL, cpu_to_node(cur_cpu));
 	}
 
-	uv_nshift = uv_hub_info->m_val;
-	uv_mmask = (1UL << uv_hub_info->m_val) - 1;
 	nuvhubs = uv_num_possible_blades();
 	spin_lock_init(&disable_lock);
 	congested_cycles = usec_2_cycles(congested_respns_us);
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 2d69617950f..46c8069ae98 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1355,7 +1355,7 @@ static int __cpuinit xen_hvm_cpu_notify(struct notifier_block *self,
 	int cpu = (long)hcpu;
 	switch (action) {
 	case CPU_UP_PREPARE:
-		per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu];
+		xen_vcpu_setup(cpu);
 		if (xen_have_vector_callback)
 			xen_init_lock_cpu(cpu);
 		break;
@@ -1385,7 +1385,6 @@ static void __init xen_hvm_guest_init(void)
 	xen_hvm_smp_init();
 	register_cpu_notifier(&xen_hvm_cpu_notifier);
 	xen_unplug_emulated_devices();
-	have_vcpu_info_placement = 0;
 	x86_init.irqs.intr_init = xen_init_IRQ;
 	xen_hvm_init_time_ops();
 	xen_hvm_init_mmu_ops();
diff --git a/block/blk-core.c b/block/blk-core.c
index d34433ae791..795154e54a7 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1725,6 +1725,8 @@ int blk_insert_cloned_request(struct request_queue *q, struct request *rq)
 		where = ELEVATOR_INSERT_FLUSH;
 
 	add_acct_request(q, rq, where);
+	if (where == ELEVATOR_INSERT_FLUSH)
+		__blk_run_queue(q);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 
 	return 0;
diff --git a/block/blk-flush.c b/block/blk-flush.c
index 491eb30a242..720ad607ff9 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -320,7 +320,7 @@ void blk_insert_flush(struct request *rq)
 		return;
 	}
 
-	BUG_ON(!rq->bio || rq->bio != rq->biotail);
+	BUG_ON(rq->bio != rq->biotail); /*assumes zero or single bio rq */
 
 	/*
 	 * If there's data but flush is not necessary, the request can be
@@ -330,7 +330,6 @@ void blk_insert_flush(struct request *rq)
 	if ((policy & REQ_FSEQ_DATA) &&
 	    !(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH))) {
 		list_add_tail(&rq->queuelist, &q->queue_head);
-		blk_run_queue_async(q);
 		return;
 	}
 
diff --git a/block/blk-map.c b/block/blk-map.c
index e663ac2d8e6..164cd005970 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -204,10 +204,11 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
 		if (!iov[i].iov_len)
 			return -EINVAL;
 
-		if (uaddr & queue_dma_alignment(q)) {
+		/*
+		 * Keep going so we check length of all segments
+		 */
+		if (uaddr & queue_dma_alignment(q))
 			unaligned = 1;
-			break;
-		}
 	}
 
 	if (unaligned || (q->dma_pad_mask & len) || map_data)
diff --git a/block/genhd.c b/block/genhd.c
index e2f67902dd0..d261b73b974 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -611,6 +611,12 @@ void add_disk(struct gendisk *disk)
 	register_disk(disk);
 	blk_register_queue(disk);
 
+	/*
+	 * Take an extra ref on queue which will be put on disk_release()
+	 * so that it sticks around as long as @disk is there.
+	 */
+	WARN_ON_ONCE(blk_get_queue(disk->queue));
+
 	retval = sysfs_create_link(&disk_to_dev(disk)->kobj, &bdi->dev->kobj,
 				   "bdi");
 	WARN_ON(retval);
@@ -1095,6 +1101,8 @@ static void disk_release(struct device *dev)
 	disk_replace_part_tbl(disk, NULL);
 	free_part_stats(&disk->part0);
 	free_part_info(&disk->part0);
+	if (disk->queue)
+		blk_put_queue(disk->queue);
 	kfree(disk);
 }
 struct class block_class = {
diff --git a/crypto/cryptd.c b/crypto/cryptd.c
index e46d21ae26b..671d4d6d14d 100644
--- a/crypto/cryptd.c
+++ b/crypto/cryptd.c
@@ -945,7 +945,7 @@ static void __exit cryptd_exit(void)
 	crypto_unregister_template(&cryptd_tmpl);
 }
 
-module_init(cryptd_init);
+subsys_initcall(cryptd_init);
 module_exit(cryptd_exit);
 
 MODULE_LICENSE("GPL");
diff --git a/drivers/acpi/atomicio.c b/drivers/acpi/atomicio.c
index 7489b89c300..f151afe61aa 100644
--- a/drivers/acpi/atomicio.c
+++ b/drivers/acpi/atomicio.c
@@ -76,7 +76,7 @@ static void __iomem *__acpi_ioremap_fast(phys_addr_t paddr,
 {
 	struct acpi_iomap *map;
 
-	map = __acpi_find_iomap(paddr, size);
+	map = __acpi_find_iomap(paddr, size/8);
 	if (map)
 		return map->vaddr + (paddr - map->paddr);
 	else
diff --git a/drivers/ata/ata_piix.c b/drivers/ata/ata_piix.c
index 43107e9415d..cc431d6bc97 100644
--- a/drivers/ata/ata_piix.c
+++ b/drivers/ata/ata_piix.c
@@ -113,6 +113,8 @@ enum {
 	PIIX_PATA_FLAGS		= ATA_FLAG_SLAVE_POSS,
 	PIIX_SATA_FLAGS		= ATA_FLAG_SATA | PIIX_FLAG_CHECKINTR,
 
+	PIIX_FLAG_PIO16		= (1 << 30), /*support 16bit PIO only*/
+
 	PIIX_80C_PRI		= (1 << 5) | (1 << 4),
 	PIIX_80C_SEC		= (1 << 7) | (1 << 6),
 
@@ -147,6 +149,7 @@ enum piix_controller_ids {
 	ich8m_apple_sata,	/* locks up on second port enable */
 	tolapai_sata,
 	piix_pata_vmw,			/* PIIX4 for VMware, spurious DMA_ERR */
+	ich8_sata_snb,
 };
 
 struct piix_map_db {
@@ -177,6 +180,7 @@ static int piix_sidpr_scr_write(struct ata_link *link,
 static int piix_sidpr_set_lpm(struct ata_link *link, enum ata_lpm_policy policy,
 			      unsigned hints);
 static bool piix_irq_check(struct ata_port *ap);
+static int piix_port_start(struct ata_port *ap);
 #ifdef CONFIG_PM
 static int piix_pci_device_suspend(struct pci_dev *pdev, pm_message_t mesg);
 static int piix_pci_device_resume(struct pci_dev *pdev);
@@ -298,21 +302,21 @@ static const struct pci_device_id piix_pci_tbl[] = {
 	/* SATA Controller IDE (PCH) */
 	{ 0x8086, 0x3b2e, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_sata },
 	/* SATA Controller IDE (CPT) */
-	{ 0x8086, 0x1c00, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_sata },
+	{ 0x8086, 0x1c00, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_sata_snb },
 	/* SATA Controller IDE (CPT) */
-	{ 0x8086, 0x1c01, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_sata },
+	{ 0x8086, 0x1c01, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_sata_snb },
 	/* SATA Controller IDE (CPT) */
 	{ 0x8086, 0x1c08, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata },
 	/* SATA Controller IDE (CPT) */
 	{ 0x8086, 0x1c09, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata },
 	/* SATA Controller IDE (PBG) */
-	{ 0x8086, 0x1d00, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_sata },
+	{ 0x8086, 0x1d00, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_sata_snb },
 	/* SATA Controller IDE (PBG) */
 	{ 0x8086, 0x1d08, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata },
 	/* SATA Controller IDE (Panther Point) */
-	{ 0x8086, 0x1e00, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_sata },
+	{ 0x8086, 0x1e00, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_sata_snb },
 	/* SATA Controller IDE (Panther Point) */
-	{ 0x8086, 0x1e01, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_sata },
+	{ 0x8086, 0x1e01, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_sata_snb },
 	/* SATA Controller IDE (Panther Point) */
 	{ 0x8086, 0x1e08, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata },
 	/* SATA Controller IDE (Panther Point) */
@@ -338,6 +342,7 @@ static struct scsi_host_template piix_sht = {
 static struct ata_port_operations piix_sata_ops = {
 	.inherits		= &ata_bmdma32_port_ops,
 	.sff_irq_check		= piix_irq_check,
+	.port_start		= piix_port_start,
 };
 
 static struct ata_port_operations piix_pata_ops = {
@@ -478,6 +483,7 @@ static const struct piix_map_db *piix_map_db_table[] = {
 	[ich8_2port_sata]	= &ich8_2port_map_db,
 	[ich8m_apple_sata]	= &ich8m_apple_map_db,
 	[tolapai_sata]		= &tolapai_map_db,
+	[ich8_sata_snb]		= &ich8_map_db,
 };
 
 static struct ata_port_info piix_port_info[] = {
@@ -606,6 +612,19 @@ static struct ata_port_info piix_port_info[] = {
 		.port_ops	= &piix_vmw_ops,
 	},
 
+	/*
+	 * some Sandybridge chipsets have broken 32 mode up to now,
+	 * see https://bugzilla.kernel.org/show_bug.cgi?id=40592
+	 */
+	[ich8_sata_snb] =
+	{
+		.flags		= PIIX_SATA_FLAGS | PIIX_FLAG_SIDPR | PIIX_FLAG_PIO16,
+		.pio_mask	= ATA_PIO4,
+		.mwdma_mask	= ATA_MWDMA2,
+		.udma_mask	= ATA_UDMA6,
+		.port_ops	= &piix_sata_ops,
+	},
+
 };
 
 static struct pci_bits piix_enable_bits[] = {
@@ -649,6 +668,14 @@ static const struct ich_laptop ich_laptop[] = {
 	{ 0, }
 };
 
+static int piix_port_start(struct ata_port *ap)
+{
+	if (!(ap->flags & PIIX_FLAG_PIO16))
+		ap->pflags |= ATA_PFLAG_PIO32 | ATA_PFLAG_PIO32CHANGE;
+
+	return ata_bmdma_port_start(ap);
+}
+
 /**
  *	ich_pata_cable_detect - Probe host controller cable detect info
  *	@ap: Port for which cable detect info is desired
diff --git a/drivers/base/core.c b/drivers/base/core.c
index bc8729d603a..78445f40c43 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -22,6 +22,7 @@
 #include <linux/kallsyms.h>
 #include <linux/mutex.h>
 #include <linux/async.h>
+#include <linux/pm_runtime.h>
 
 #include "base.h"
 #include "power/power.h"
@@ -1742,6 +1743,8 @@ void device_shutdown(void)
 		 */
 		list_del_init(&dev->kobj.entry);
 		spin_unlock(&devices_kset->list_lock);
+		/* Disable all device's runtime power management */
+		pm_runtime_disable(dev);
 
 		if (dev->bus && dev->bus->shutdown) {
 			dev_dbg(dev, "shutdown\n");
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 793f796c4da..5693ecee9a4 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -127,12 +127,13 @@ static ssize_t node_read_meminfo(struct sys_device * dev,
 		       nid, K(node_page_state(nid, NR_WRITEBACK)),
 		       nid, K(node_page_state(nid, NR_FILE_PAGES)),
 		       nid, K(node_page_state(nid, NR_FILE_MAPPED)),
-		       nid, K(node_page_state(nid, NR_ANON_PAGES)
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
+		       nid, K(node_page_state(nid, NR_ANON_PAGES)
 			+ node_page_state(nid, NR_ANON_TRANSPARENT_HUGEPAGES) *
-			HPAGE_PMD_NR
+			HPAGE_PMD_NR),
+#else
+		       nid, K(node_page_state(nid, NR_ANON_PAGES)),
 #endif
-		       ),
 		       nid, K(node_page_state(nid, NR_SHMEM)),
 		       nid, node_page_state(nid, NR_KERNEL_STACK) *
 				THREAD_SIZE / 1024,
@@ -143,13 +144,14 @@ static ssize_t node_read_meminfo(struct sys_device * dev,
 		       nid, K(node_page_state(nid, NR_SLAB_RECLAIMABLE) +
 				node_page_state(nid, NR_SLAB_UNRECLAIMABLE)),
 		       nid, K(node_page_state(nid, NR_SLAB_RECLAIMABLE)),
-		       nid, K(node_page_state(nid, NR_SLAB_UNRECLAIMABLE))
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
+		       nid, K(node_page_state(nid, NR_SLAB_UNRECLAIMABLE))
 			, nid,
 			K(node_page_state(nid, NR_ANON_TRANSPARENT_HUGEPAGES) *
-			HPAGE_PMD_NR)
+			HPAGE_PMD_NR));
+#else
+		       nid, K(node_page_state(nid, NR_SLAB_UNRECLAIMABLE)));
 #endif
-		       );
 	n += hugetlb_report_node_meminfo(nid, buf + n);
 	return n;
 }
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index acb3f83b807..6a7f7b06968 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -285,6 +285,9 @@ static int rpm_callback(int (*cb)(struct device *), struct device *dev)
  * If a deferred resume was requested while the callback was running then carry
  * it out; otherwise send an idle notification for the device (if the suspend
  * failed) or for its parent (if the suspend succeeded).
+ * If ->runtime_suspend failed with -EAGAIN or -EBUSY, and if the RPM_AUTO
+ * flag is set and the next autosuspend-delay expiration time is in the
+ * future, schedule another autosuspend attempt.
  *
  * This function must be called under dev->power.lock with interrupts disabled.
  */
@@ -396,10 +399,21 @@ static int rpm_suspend(struct device *dev, int rpmflags)
 	if (retval) {
 		__update_runtime_status(dev, RPM_ACTIVE);
 		dev->power.deferred_resume = false;
-		if (retval == -EAGAIN || retval == -EBUSY)
+		if (retval == -EAGAIN || retval == -EBUSY) {
 			dev->power.runtime_error = 0;
-		else
+
+			/*
+			 * If the callback routine failed an autosuspend, and
+			 * if the last_busy time has been updated so that there
+			 * is a new autosuspend expiration time, automatically
+			 * reschedule another autosuspend.
+			 */
+			if ((rpmflags & RPM_AUTO) &&
+			    pm_runtime_autosuspend_expiration(dev) != 0)
+				goto repeat;
+		} else {
 			pm_runtime_cancel_pending(dev);
+		}
 	} else {
  no_callback:
 		__update_runtime_status(dev, RPM_SUSPENDED);
diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c
index 8f4ef656a1a..c2f9b3e3dec 100644
--- a/drivers/block/cciss.c
+++ b/drivers/block/cciss.c
@@ -4533,6 +4533,13 @@ static int cciss_controller_hard_reset(struct pci_dev *pdev,
 		pmcsr &= ~PCI_PM_CTRL_STATE_MASK;
 		pmcsr |= PCI_D0;
 		pci_write_config_word(pdev, pos + PCI_PM_CTRL, pmcsr);
+
+		/*
+		 * The P600 requires a small delay when changing states.
+		 * Otherwise we may think the board did not reset and we bail.
+		 * This for kdump only and is particular to the P600.
+		 */
+		msleep(500);
 	}
 	return 0;
 }
diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c
index 2330a9ad5e9..2f01073ff55 100644
--- a/drivers/block/xen-blkback/blkback.c
+++ b/drivers/block/xen-blkback/blkback.c
@@ -685,7 +685,7 @@ static int dispatch_rw_block_io(struct xen_blkif *blkif,
 
 	if (operation == READ)
 		blkif->st_rd_sect += preq.nr_sects;
-	else if (operation == WRITE || operation == WRITE_FLUSH)
+	else if (operation & WRITE)
 		blkif->st_wr_sect += preq.nr_sects;
 
 	return 0;
diff --git a/drivers/cpufreq/exynos4210-cpufreq.c b/drivers/cpufreq/exynos4210-cpufreq.c
index b7c3a84c4cf..d263241b2d0 100644
--- a/drivers/cpufreq/exynos4210-cpufreq.c
+++ b/drivers/cpufreq/exynos4210-cpufreq.c
@@ -17,43 +17,55 @@
 #include <linux/slab.h>
 #include <linux/regulator/consumer.h>
 #include <linux/cpufreq.h>
+#include <linux/suspend.h>
+#include <linux/reboot.h>
 
 #include <mach/map.h>
 #include <mach/regs-clock.h>
 #include <mach/regs-mem.h>
+#include <mach/cpufreq.h>
 
 #include <plat/clock.h>
 #include <plat/pm.h>
 
+static bool exynos4_cpufreq_init_done;
+static DEFINE_MUTEX(set_freq_lock);
+static DEFINE_MUTEX(set_cpu_freq_lock);
+
 static struct clk *cpu_clk;
 static struct clk *moutcore;
 static struct clk *mout_mpll;
 static struct clk *mout_apll;
 
 static struct regulator *arm_regulator;
-static struct regulator *int_regulator;
 
 static struct cpufreq_freqs freqs;
-static unsigned int memtype;
 
-enum exynos4_memory_type {
-	DDR2 = 4,
-	LPDDR2,
-	DDR3,
+struct cpufreq_clkdiv {
+	unsigned int clkdiv;
 };
 
 enum cpufreq_level_index {
-	L0, L1, L2, L3, CPUFREQ_LEVEL_END,
+	L0, L1, L2, L3, L4, CPUFREQ_LEVEL_END,
 };
 
+static struct cpufreq_clkdiv exynos4_clkdiv_table[CPUFREQ_LEVEL_END];
+
 static struct cpufreq_frequency_table exynos4_freq_table[] = {
-	{L0, 1000*1000},
-	{L1, 800*1000},
-	{L2, 400*1000},
-	{L3, 100*1000},
+	{L0, 1200*1000},
+	{L1, 1000*1000},
+	{L2, 800*1000},
+	{L3, 500*1000},
+	{L4, 200*1000},
 	{0, CPUFREQ_TABLE_END},
 };
 
+/* This defines are for cpufreq lock */
+#define CPUFREQ_MIN_LEVEL	(CPUFREQ_LEVEL_END - 1)
+unsigned int cpufreq_lock_id;
+unsigned int cpufreq_lock_val[DVFS_LOCK_ID_END];
+unsigned int cpufreq_lock_level = CPUFREQ_MIN_LEVEL;
+
 static unsigned int clkdiv_cpu0[CPUFREQ_LEVEL_END][7] = {
 	/*
 	 * Clock divider value for following
@@ -61,17 +73,20 @@ static unsigned int clkdiv_cpu0[CPUFREQ_LEVEL_END][7] = {
 	 *		DIVATB, DIVPCLK_DBG, DIVAPLL }
 	 */
 
-	/* ARM L0: 1000MHz */
-	{ 0, 3, 7, 3, 3, 0, 1 },
+	/* ARM L0: 1200MHz */
+	{ 0, 3, 7, 3, 4, 1, 7 },
 
-	/* ARM L1: 800MHz */
-	{ 0, 3, 7, 3, 3, 0, 1 },
+	/* ARM L1: 1000MHz */
+	{ 0, 3, 7, 3, 4, 1, 7 },
 
-	/* ARM L2: 400MHz */
-	{ 0, 1, 3, 1, 3, 0, 1 },
+	/* ARM L2: 800MHz */
+	{ 0, 3, 7, 3, 3, 1, 7 },
 
-	/* ARM L3: 100MHz */
-	{ 0, 0, 1, 0, 3, 1, 1 },
+	/* ARM L3: 500MHz */
+	{ 0, 3, 7, 3, 3, 1, 7 },
+
+	/* ARM L4: 200MHz */
+	{ 0, 1, 3, 1, 3, 1, 0 },
 };
 
 static unsigned int clkdiv_cpu1[CPUFREQ_LEVEL_END][2] = {
@@ -80,115 +95,61 @@ static unsigned int clkdiv_cpu1[CPUFREQ_LEVEL_END][2] = {
 	 * { DIVCOPY, DIVHPM }
 	 */
 
-	 /* ARM L0: 1000MHz */
-	{ 3, 0 },
+	 /* ARM L0: 1200MHz */
+	{ 5, 0 },
 
-	/* ARM L1: 800MHz */
-	{ 3, 0 },
+	/* ARM L1: 1000MHz */
+	{ 4, 0 },
 
-	/* ARM L2: 400MHz */
+	/* ARM L2: 800MHz */
 	{ 3, 0 },
 
-	/* ARM L3: 100MHz */
+	/* ARM L3: 500MHz */
 	{ 3, 0 },
-};
-
-static unsigned int clkdiv_dmc0[CPUFREQ_LEVEL_END][8] = {
-	/*
-	 * Clock divider value for following
-	 * { DIVACP, DIVACP_PCLK, DIVDPHY, DIVDMC, DIVDMCD
-	 *		DIVDMCP, DIVCOPY2, DIVCORE_TIMERS }
-	 */
-
-	/* DMC L0: 400MHz */
-	{ 3, 1, 1, 1, 1, 1, 3, 1 },
-
-	/* DMC L1: 400MHz */
-	{ 3, 1, 1, 1, 1, 1, 3, 1 },
-
-	/* DMC L2: 266.7MHz */
-	{ 7, 1, 1, 2, 1, 1, 3, 1 },
-
-	/* DMC L3: 200MHz */
-	{ 7, 1, 1, 3, 1, 1, 3, 1 },
-};
-
-static unsigned int clkdiv_top[CPUFREQ_LEVEL_END][5] = {
-	/*
-	 * Clock divider value for following
-	 * { DIVACLK200, DIVACLK100, DIVACLK160, DIVACLK133, DIVONENAND }
-	 */
-
-	/* ACLK200 L0: 200MHz */
-	{ 3, 7, 4, 5, 1 },
-
-	/* ACLK200 L1: 200MHz */
-	{ 3, 7, 4, 5, 1 },
-
-	/* ACLK200 L2: 160MHz */
-	{ 4, 7, 5, 7, 1 },
 
-	/* ACLK200 L3: 133.3MHz */
-	{ 5, 7, 7, 7, 1 },
-};
-
-static unsigned int clkdiv_lr_bus[CPUFREQ_LEVEL_END][2] = {
-	/*
-	 * Clock divider value for following
-	 * { DIVGDL/R, DIVGPL/R }
-	 */
-
-	/* ACLK_GDL/R L0: 200MHz */
-	{ 3, 1 },
-
-	/* ACLK_GDL/R L1: 200MHz */
-	{ 3, 1 },
-
-	/* ACLK_GDL/R L2: 160MHz */
-	{ 4, 1 },
-
-	/* ACLK_GDL/R L3: 133.3MHz */
-	{ 5, 1 },
+	/* ARM L4: 200MHz */
+	{ 3, 0 },
 };
 
 struct cpufreq_voltage_table {
 	unsigned int	index;		/* any */
 	unsigned int	arm_volt;	/* uV */
-	unsigned int	int_volt;
 };
 
 static struct cpufreq_voltage_table exynos4_volt_table[CPUFREQ_LEVEL_END] = {
 	{
 		.index		= L0,
-		.arm_volt	= 1200000,
-		.int_volt	= 1100000,
+		.arm_volt	= 1350000,
 	}, {
 		.index		= L1,
-		.arm_volt	= 1100000,
-		.int_volt	= 1100000,
+		.arm_volt	= 1300000,
 	}, {
 		.index		= L2,
-		.arm_volt	= 1000000,
-		.int_volt	= 1000000,
+		.arm_volt	= 1200000,
 	}, {
 		.index		= L3,
-		.arm_volt	= 900000,
-		.int_volt	= 1000000,
+		.arm_volt	= 1100000,
+	}, {
+		.index		= L4,
+		.arm_volt	= 1050000,
 	},
 };
 
 static unsigned int exynos4_apll_pms_table[CPUFREQ_LEVEL_END] = {
-	/* APLL FOUT L0: 1000MHz */
+	/* APLL FOUT L0: 1200MHz */
+	((150 << 16) | (3 << 8) | 1),
+
+	/* APLL FOUT L1: 1000MHz */
 	((250 << 16) | (6 << 8) | 1),
 
-	/* APLL FOUT L1: 800MHz */
+	/* APLL FOUT L2: 800MHz */
 	((200 << 16) | (6 << 8) | 1),
 
-	/* APLL FOUT L2 : 400MHz */
-	((200 << 16) | (6 << 8) | 2),
+	/* APLL FOUT L3: 500MHz */
+	((250 << 16) | (6 << 8) | 2),
 
-	/* APLL FOUT L3: 100MHz */
-	((200 << 16) | (6 << 8) | 4),
+	/* APLL FOUT L4: 200MHz */
+	((200 << 16) | (6 << 8) | 3),
 };
 
 static int exynos4_verify_speed(struct cpufreq_policy *policy)
@@ -207,20 +168,7 @@ static void exynos4_set_clkdiv(unsigned int div_index)
 
 	/* Change Divider - CPU0 */
 
-	tmp = __raw_readl(S5P_CLKDIV_CPU);
-
-	tmp &= ~(S5P_CLKDIV_CPU0_CORE_MASK | S5P_CLKDIV_CPU0_COREM0_MASK |
-		S5P_CLKDIV_CPU0_COREM1_MASK | S5P_CLKDIV_CPU0_PERIPH_MASK |
-		S5P_CLKDIV_CPU0_ATB_MASK | S5P_CLKDIV_CPU0_PCLKDBG_MASK |
-		S5P_CLKDIV_CPU0_APLL_MASK);
-
-	tmp |= ((clkdiv_cpu0[div_index][0] << S5P_CLKDIV_CPU0_CORE_SHIFT) |
-		(clkdiv_cpu0[div_index][1] << S5P_CLKDIV_CPU0_COREM0_SHIFT) |
-		(clkdiv_cpu0[div_index][2] << S5P_CLKDIV_CPU0_COREM1_SHIFT) |
-		(clkdiv_cpu0[div_index][3] << S5P_CLKDIV_CPU0_PERIPH_SHIFT) |
-		(clkdiv_cpu0[div_index][4] << S5P_CLKDIV_CPU0_ATB_SHIFT) |
-		(clkdiv_cpu0[div_index][5] << S5P_CLKDIV_CPU0_PCLKDBG_SHIFT) |
-		(clkdiv_cpu0[div_index][6] << S5P_CLKDIV_CPU0_APLL_SHIFT));
+	tmp = exynos4_clkdiv_table[div_index].clkdiv;
 
 	__raw_writel(tmp, S5P_CLKDIV_CPU);
 
@@ -242,80 +190,6 @@ static void exynos4_set_clkdiv(unsigned int div_index)
 	do {
 		tmp = __raw_readl(S5P_CLKDIV_STATCPU1);
 	} while (tmp & 0x11);
-
-	/* Change Divider - DMC0 */
-
-	tmp = __raw_readl(S5P_CLKDIV_DMC0);
-
-	tmp &= ~(S5P_CLKDIV_DMC0_ACP_MASK | S5P_CLKDIV_DMC0_ACPPCLK_MASK |
-		S5P_CLKDIV_DMC0_DPHY_MASK | S5P_CLKDIV_DMC0_DMC_MASK |
-		S5P_CLKDIV_DMC0_DMCD_MASK | S5P_CLKDIV_DMC0_DMCP_MASK |
-		S5P_CLKDIV_DMC0_COPY2_MASK | S5P_CLKDIV_DMC0_CORETI_MASK);
-
-	tmp |= ((clkdiv_dmc0[div_index][0] << S5P_CLKDIV_DMC0_ACP_SHIFT) |
-		(clkdiv_dmc0[div_index][1] << S5P_CLKDIV_DMC0_ACPPCLK_SHIFT) |
-		(clkdiv_dmc0[div_index][2] << S5P_CLKDIV_DMC0_DPHY_SHIFT) |
-		(clkdiv_dmc0[div_index][3] << S5P_CLKDIV_DMC0_DMC_SHIFT) |
-		(clkdiv_dmc0[div_index][4] << S5P_CLKDIV_DMC0_DMCD_SHIFT) |
-		(clkdiv_dmc0[div_index][5] << S5P_CLKDIV_DMC0_DMCP_SHIFT) |
-		(clkdiv_dmc0[div_index][6] << S5P_CLKDIV_DMC0_COPY2_SHIFT) |
-		(clkdiv_dmc0[div_index][7] << S5P_CLKDIV_DMC0_CORETI_SHIFT));
-
-	__raw_writel(tmp, S5P_CLKDIV_DMC0);
-
-	do {
-		tmp = __raw_readl(S5P_CLKDIV_STAT_DMC0);
-	} while (tmp & 0x11111111);
-
-	/* Change Divider - TOP */
-
-	tmp = __raw_readl(S5P_CLKDIV_TOP);
-
-	tmp &= ~(S5P_CLKDIV_TOP_ACLK200_MASK | S5P_CLKDIV_TOP_ACLK100_MASK |
-		S5P_CLKDIV_TOP_ACLK160_MASK | S5P_CLKDIV_TOP_ACLK133_MASK |
-		S5P_CLKDIV_TOP_ONENAND_MASK);
-
-	tmp |= ((clkdiv_top[div_index][0] << S5P_CLKDIV_TOP_ACLK200_SHIFT) |
-		(clkdiv_top[div_index][1] << S5P_CLKDIV_TOP_ACLK100_SHIFT) |
-		(clkdiv_top[div_index][2] << S5P_CLKDIV_TOP_ACLK160_SHIFT) |
-		(clkdiv_top[div_index][3] << S5P_CLKDIV_TOP_ACLK133_SHIFT) |
-		(clkdiv_top[div_index][4] << S5P_CLKDIV_TOP_ONENAND_SHIFT));
-
-	__raw_writel(tmp, S5P_CLKDIV_TOP);
-
-	do {
-		tmp = __raw_readl(S5P_CLKDIV_STAT_TOP);
-	} while (tmp & 0x11111);
-
-	/* Change Divider - LEFTBUS */
-
-	tmp = __raw_readl(S5P_CLKDIV_LEFTBUS);
-
-	tmp &= ~(S5P_CLKDIV_BUS_GDLR_MASK | S5P_CLKDIV_BUS_GPLR_MASK);
-
-	tmp |= ((clkdiv_lr_bus[div_index][0] << S5P_CLKDIV_BUS_GDLR_SHIFT) |
-		(clkdiv_lr_bus[div_index][1] << S5P_CLKDIV_BUS_GPLR_SHIFT));
-
-	__raw_writel(tmp, S5P_CLKDIV_LEFTBUS);
-
-	do {
-		tmp = __raw_readl(S5P_CLKDIV_STAT_LEFTBUS);
-	} while (tmp & 0x11);
-
-	/* Change Divider - RIGHTBUS */
-
-	tmp = __raw_readl(S5P_CLKDIV_RIGHTBUS);
-
-	tmp &= ~(S5P_CLKDIV_BUS_GDLR_MASK | S5P_CLKDIV_BUS_GPLR_MASK);
-
-	tmp |= ((clkdiv_lr_bus[div_index][0] << S5P_CLKDIV_BUS_GDLR_SHIFT) |
-		(clkdiv_lr_bus[div_index][1] << S5P_CLKDIV_BUS_GPLR_SHIFT));
-
-	__raw_writel(tmp, S5P_CLKDIV_RIGHTBUS);
-
-	do {
-		tmp = __raw_readl(S5P_CLKDIV_STAT_RIGHTBUS);
-	} while (tmp & 0x11);
 }
 
 static void exynos4_set_apll(unsigned int index)
@@ -359,14 +233,12 @@ static void exynos4_set_frequency(unsigned int old_index, unsigned int new_index
 	unsigned int tmp;
 
 	if (old_index > new_index) {
-		/* The frequency changing to L0 needs to change apll */
-		if (freqs.new == exynos4_freq_table[L0].frequency) {
-			/* 1. Change the system clock divider values */
-			exynos4_set_clkdiv(new_index);
-
-			/* 2. Change the apll m,p,s value */
-			exynos4_set_apll(new_index);
-		} else {
+		/*
+		 * L1/L3, L2/L4 Level change require
+		 * to only change s divider value
+		 */
+		if (((old_index == L3) && (new_index == L1)) ||
+				((old_index == L4) && (new_index == L2))) {
 			/* 1. Change the system clock divider values */
 			exynos4_set_clkdiv(new_index);
 
@@ -375,18 +247,20 @@ static void exynos4_set_frequency(unsigned int old_index, unsigned int new_index
 			tmp &= ~(0x7 << 0);
 			tmp |= (exynos4_apll_pms_table[new_index] & 0x7);
 			__raw_writel(tmp, S5P_APLL_CON0);
-		}
-	}
-
-	else if (old_index < new_index) {
-		/* The frequency changing from L0 needs to change apll */
-		if (freqs.old == exynos4_freq_table[L0].frequency) {
-			/* 1. Change the apll m,p,s value */
-			exynos4_set_apll(new_index);
-
-			/* 2. Change the system clock divider values */
-			exynos4_set_clkdiv(new_index);
 		} else {
+			/* Clock Configuration Procedure */
+			/* 1. Change the system clock divider values */
+			exynos4_set_clkdiv(new_index);
+			/* 2. Change the apll m,p,s value */
+			exynos4_set_apll(new_index);
+		}
+	} else if (old_index < new_index) {
+		/*
+		 * L1/L3, L2/L4 Level change require
+		 * to only change s divider value
+		 */
+		if (((old_index == L1) && (new_index == L3)) ||
+				((old_index == L2) && (new_index == L4))) {
 			/* 1. Change just s value in apll m,p,s value */
 			tmp = __raw_readl(S5P_APLL_CON0);
 			tmp &= ~(0x7 << 0);
@@ -395,6 +269,12 @@ static void exynos4_set_frequency(unsigned int old_index, unsigned int new_index
 
 			/* 2. Change the system clock divider values */
 			exynos4_set_clkdiv(new_index);
+		} else {
+			/* Clock Configuration Procedure */
+			/* 1. Change the apll m,p,s value */
+			exynos4_set_apll(new_index);
+			/* 2. Change the system clock divider values */
+			exynos4_set_clkdiv(new_index);
 		}
 	}
 }
@@ -404,51 +284,145 @@ static int exynos4_target(struct cpufreq_policy *policy,
 			  unsigned int relation)
 {
 	unsigned int index, old_index;
-	unsigned int arm_volt, int_volt;
+	unsigned int arm_volt;
+	int ret = 0;
+
+	mutex_lock(&set_freq_lock);
 
 	freqs.old = exynos4_getspeed(policy->cpu);
 
 	if (cpufreq_frequency_table_target(policy, exynos4_freq_table,
-					   freqs.old, relation, &old_index))
-		return -EINVAL;
+					   freqs.old, relation, &old_index)) {
+		ret = -EINVAL;
+		goto out;
+	}
 
 	if (cpufreq_frequency_table_target(policy, exynos4_freq_table,
-					   target_freq, relation, &index))
-		return -EINVAL;
+					   target_freq, relation, &index)) {
+		ret = -EINVAL;
+		goto out;
+	}
 
 	freqs.new = exynos4_freq_table[index].frequency;
 	freqs.cpu = policy->cpu;
 
-	if (freqs.new == freqs.old)
-		return 0;
+	if (freqs.new == freqs.old) {
+		ret = -EINVAL;
+		goto out;
+	}
 
 	/* get the voltage value */
 	arm_volt = exynos4_volt_table[index].arm_volt;
-	int_volt = exynos4_volt_table[index].int_volt;
 
 	cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
 
 	/* control regulator */
-	if (freqs.new > freqs.old) {
+	if (freqs.new > freqs.old)
 		/* Voltage up */
 		regulator_set_voltage(arm_regulator, arm_volt, arm_volt);
-		regulator_set_voltage(int_regulator, int_volt, int_volt);
-	}
 
 	/* Clock Configuration Procedure */
 	exynos4_set_frequency(old_index, index);
 
+	cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
+
 	/* control regulator */
-	if (freqs.new < freqs.old) {
+	if (freqs.new < freqs.old)
 		/* Voltage down */
 		regulator_set_voltage(arm_regulator, arm_volt, arm_volt);
-		regulator_set_voltage(int_regulator, int_volt, int_volt);
+
+out:
+	mutex_unlock(&set_freq_lock);
+
+	return ret;
+}
+
+atomic_t exynos4_cpufreq_lock_count;
+
+int exynos4_cpufreq_lock(unsigned int id,
+		enum cpufreq_level_request cpufreq_level)
+{
+	int i, old_idx = 0;
+	unsigned int freq_old, freq_new, arm_volt;
+
+	if (!exynos4_cpufreq_init_done)
+		return 0;
+
+	if (cpufreq_lock_id & (1 << id)) {
+		printk(KERN_ERR "%s:Device [%d] already locked cpufreq\n",
+				__func__,  id);
+		return 0;
 	}
+	mutex_lock(&set_cpu_freq_lock);
+	cpufreq_lock_id |= (1 << id);
+	cpufreq_lock_val[id] = cpufreq_level;
 
-	cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
+	/* If the requested cpufreq is higher than current min frequency */
+	if (cpufreq_level < cpufreq_lock_level)
+		cpufreq_lock_level = cpufreq_level;
+
+	mutex_unlock(&set_cpu_freq_lock);
+
+	/*
+	 * If current frequency is lower than requested freq,
+	 * it needs to update
+	 */
+	mutex_lock(&set_freq_lock);
+	freq_old = exynos4_getspeed(0);
+	freq_new = exynos4_freq_table[cpufreq_level].frequency;
+	if (freq_old < freq_new) {
+		/* Find out current level index */
+		for (i = 0 ; i < CPUFREQ_LEVEL_END ; i++) {
+			if (freq_old == exynos4_freq_table[i].frequency) {
+				old_idx = exynos4_freq_table[i].index;
+				break;
+			} else if (i == (CPUFREQ_LEVEL_END - 1)) {
+				printk(KERN_ERR "%s: Level not found\n",
+						__func__);
+				mutex_unlock(&set_freq_lock);
+				return -EINVAL;
+			} else {
+				continue;
+			}
+		}
+		freqs.old = freq_old;
+		freqs.new = freq_new;
+		cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
+
+		/* get the voltage value */
+		arm_volt = exynos4_volt_table[cpufreq_level].arm_volt;
+		regulator_set_voltage(arm_regulator, arm_volt,
+				arm_volt);
+
+		exynos4_set_frequency(old_idx, cpufreq_level);
+		cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
+	}
+	mutex_unlock(&set_freq_lock);
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(exynos4_cpufreq_lock);
+
+void exynos4_cpufreq_lock_free(unsigned int id)
+{
+	int i;
+
+	if (!exynos4_cpufreq_init_done)
+		return;
+
+	mutex_lock(&set_cpu_freq_lock);
+	cpufreq_lock_id &= ~(1 << id);
+	cpufreq_lock_val[id] = CPUFREQ_MIN_LEVEL;
+	cpufreq_lock_level = CPUFREQ_MIN_LEVEL;
+	if (cpufreq_lock_id) {
+		for (i = 0; i < DVFS_LOCK_ID_END; i++) {
+			if (cpufreq_lock_val[i] < cpufreq_lock_level)
+				cpufreq_lock_level = cpufreq_lock_val[i];
+		}
+	}
+	mutex_unlock(&set_cpu_freq_lock);
+}
+EXPORT_SYMBOL_GPL(exynos4_cpufreq_lock_free);
 
 #ifdef CONFIG_PM
 static int exynos4_cpufreq_suspend(struct cpufreq_policy *policy)
@@ -462,6 +436,28 @@ static int exynos4_cpufreq_resume(struct cpufreq_policy *policy)
 }
 #endif
 
+static int exynos4_cpufreq_notifier_event(struct notifier_block *this,
+		unsigned long event, void *ptr)
+{
+	switch (event) {
+	case PM_SUSPEND_PREPARE:
+		if (exynos4_cpufreq_lock(DVFS_LOCK_ID_PM, CPU_L0))
+			return NOTIFY_BAD;
+		pr_debug("PM_SUSPEND_PREPARE for CPUFREQ\n");
+		return NOTIFY_OK;
+	case PM_POST_RESTORE:
+	case PM_POST_SUSPEND:
+		pr_debug("PM_POST_SUSPEND for CPUFREQ\n");
+		exynos4_cpufreq_lock_free(DVFS_LOCK_ID_PM);
+		return NOTIFY_OK;
+	}
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block exynos4_cpufreq_notifier = {
+	.notifier_call = exynos4_cpufreq_notifier_event,
+};
+
 static int exynos4_cpufreq_cpu_init(struct cpufreq_policy *policy)
 {
 	policy->cur = policy->min = policy->max = exynos4_getspeed(policy->cpu);
@@ -477,11 +473,30 @@ static int exynos4_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	 * Each cpu is bound to the same speed.
 	 * So the affected cpu is all of the cpus.
 	 */
-	cpumask_setall(policy->cpus);
+	if (!cpu_online(1)) {
+		cpumask_copy(policy->related_cpus, cpu_possible_mask);
+		cpumask_copy(policy->cpus, cpu_online_mask);
+	} else {
+		cpumask_setall(policy->cpus);
+	}
 
 	return cpufreq_frequency_table_cpuinfo(policy, exynos4_freq_table);
 }
 
+static int exynos4_cpufreq_reboot_notifier_call(struct notifier_block *this,
+		unsigned long code, void *_cmd)
+{
+	if (exynos4_cpufreq_lock(DVFS_LOCK_ID_PM, CPU_L0))
+		return NOTIFY_BAD;
+
+	printk(KERN_INFO "REBOOT Notifier for CPUFREQ\n");
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block exynos4_cpufreq_reboot_notifier = {
+	.notifier_call = exynos4_cpufreq_reboot_notifier_call,
+};
+
 static struct cpufreq_driver exynos4_driver = {
 	.flags		= CPUFREQ_STICKY,
 	.verify		= exynos4_verify_speed,
@@ -497,71 +512,88 @@ static struct cpufreq_driver exynos4_driver = {
 
 static int __init exynos4_cpufreq_init(void)
 {
+	int i;
+	unsigned int tmp;
+
 	cpu_clk = clk_get(NULL, "armclk");
 	if (IS_ERR(cpu_clk))
 		return PTR_ERR(cpu_clk);
 
 	moutcore = clk_get(NULL, "moutcore");
 	if (IS_ERR(moutcore))
-		goto out;
+		goto err_moutcore;
 
 	mout_mpll = clk_get(NULL, "mout_mpll");
 	if (IS_ERR(mout_mpll))
-		goto out;
+		goto err_mout_mpll;
 
 	mout_apll = clk_get(NULL, "mout_apll");
 	if (IS_ERR(mout_apll))
-		goto out;
+		goto err_mout_apll;
 
 	arm_regulator = regulator_get(NULL, "vdd_arm");
 	if (IS_ERR(arm_regulator)) {
 		printk(KERN_ERR "failed to get resource %s\n", "vdd_arm");
-		goto out;
+		goto err_vdd_arm;
 	}
 
-	int_regulator = regulator_get(NULL, "vdd_int");
-	if (IS_ERR(int_regulator)) {
-		printk(KERN_ERR "failed to get resource %s\n", "vdd_int");
-		goto out;
-	}
+	register_pm_notifier(&exynos4_cpufreq_notifier);
+	register_reboot_notifier(&exynos4_cpufreq_reboot_notifier);
 
-	/*
-	 * Check DRAM type.
-	 * Because DVFS level is different according to DRAM type.
-	 */
-	memtype = __raw_readl(S5P_VA_DMC0 + S5P_DMC0_MEMCON_OFFSET);
-	memtype = (memtype >> S5P_DMC0_MEMTYPE_SHIFT);
-	memtype &= S5P_DMC0_MEMTYPE_MASK;
+	exynos4_cpufreq_init_done = true;
 
-	if ((memtype < DDR2) && (memtype > DDR3)) {
-		printk(KERN_ERR "%s: wrong memtype= 0x%x\n", __func__, memtype);
-		goto out;
-	} else {
-		printk(KERN_DEBUG "%s: memtype= 0x%x\n", __func__, memtype);
-	}
+	tmp = __raw_readl(S5P_CLKDIV_CPU);
 
-	return cpufreq_register_driver(&exynos4_driver);
+	for (i = L0; i <  CPUFREQ_LEVEL_END; i++) {
+		tmp &= ~(S5P_CLKDIV_CPU0_CORE_MASK |
+			 S5P_CLKDIV_CPU0_COREM0_MASK |
+			 S5P_CLKDIV_CPU0_COREM1_MASK |
+			 S5P_CLKDIV_CPU0_PERIPH_MASK |
+			 S5P_CLKDIV_CPU0_ATB_MASK |
+			 S5P_CLKDIV_CPU0_PCLKDBG_MASK |
+			 S5P_CLKDIV_CPU0_APLL_MASK);
+
+		tmp |= ((clkdiv_cpu0[i][0] << S5P_CLKDIV_CPU0_CORE_SHIFT) |
+			(clkdiv_cpu0[i][1] << S5P_CLKDIV_CPU0_COREM0_SHIFT) |
+			(clkdiv_cpu0[i][2] << S5P_CLKDIV_CPU0_COREM1_SHIFT) |
+			(clkdiv_cpu0[i][3] << S5P_CLKDIV_CPU0_PERIPH_SHIFT) |
+			(clkdiv_cpu0[i][4] << S5P_CLKDIV_CPU0_ATB_SHIFT) |
+			(clkdiv_cpu0[i][5] << S5P_CLKDIV_CPU0_PCLKDBG_SHIFT) |
+			(clkdiv_cpu0[i][6] << S5P_CLKDIV_CPU0_APLL_SHIFT));
+
+		exynos4_clkdiv_table[i].clkdiv = tmp;
+	}
 
-out:
-	if (!IS_ERR(cpu_clk))
-		clk_put(cpu_clk);
+	if (cpufreq_register_driver(&exynos4_driver)) {
+		pr_err("failed to register cpufreq driver\n");
+		goto err_cpufreq;
+	}
 
-	if (!IS_ERR(moutcore))
-		clk_put(moutcore);
+	return 0;
+err_cpufreq:
+	unregister_reboot_notifier(&exynos4_cpufreq_reboot_notifier);
+	unregister_pm_notifier(&exynos4_cpufreq_notifier);
 
-	if (!IS_ERR(mout_mpll))
-		clk_put(mout_mpll);
+	if (!IS_ERR(arm_regulator))
+		regulator_put(arm_regulator);
 
+err_vdd_arm:
 	if (!IS_ERR(mout_apll))
 		clk_put(mout_apll);
 
-	if (!IS_ERR(arm_regulator))
-		regulator_put(arm_regulator);
+err_mout_apll:
+	if (!IS_ERR(mout_mpll))
+		clk_put(mout_mpll);
 
-	if (!IS_ERR(int_regulator))
-		regulator_put(int_regulator);
+err_mout_mpll:
+	if (!IS_ERR(moutcore))
+		clk_put(moutcore);
+
+err_moutcore:
+	if (!IS_ERR(cpu_clk))
+		clk_put(cpu_clk);
 
-	printk(KERN_ERR "%s: failed initialization\n", __func__);
+	pr_debug("%s: failed initialization\n", __func__);
 
 	return -EINVAL;
 }
diff --git a/drivers/crypto/mv_cesa.c b/drivers/crypto/mv_cesa.c
index 3cf303ee3fe..38a3297ae2b 100644
--- a/drivers/crypto/mv_cesa.c
+++ b/drivers/crypto/mv_cesa.c
@@ -342,11 +342,13 @@ static void mv_process_hash_current(int first_block)
 		else
 			op.config |= CFG_MID_FRAG;
 
-		writel(req_ctx->state[0], cpg->reg + DIGEST_INITIAL_VAL_A);
-		writel(req_ctx->state[1], cpg->reg + DIGEST_INITIAL_VAL_B);
-		writel(req_ctx->state[2], cpg->reg + DIGEST_INITIAL_VAL_C);
-		writel(req_ctx->state[3], cpg->reg + DIGEST_INITIAL_VAL_D);
-		writel(req_ctx->state[4], cpg->reg + DIGEST_INITIAL_VAL_E);
+		if (first_block) {
+			writel(req_ctx->state[0], cpg->reg + DIGEST_INITIAL_VAL_A);
+			writel(req_ctx->state[1], cpg->reg + DIGEST_INITIAL_VAL_B);
+			writel(req_ctx->state[2], cpg->reg + DIGEST_INITIAL_VAL_C);
+			writel(req_ctx->state[3], cpg->reg + DIGEST_INITIAL_VAL_D);
+			writel(req_ctx->state[4], cpg->reg + DIGEST_INITIAL_VAL_E);
+		}
 	}
 
 	memcpy(cpg->sram + SRAM_CONFIG, &op, sizeof(struct sec_accel_config));
diff --git a/drivers/firmware/sigma.c b/drivers/firmware/sigma.c
index f10fc521951..1eedb6f7fda 100644
--- a/drivers/firmware/sigma.c
+++ b/drivers/firmware/sigma.c
@@ -14,13 +14,34 @@
 #include <linux/module.h>
 #include <linux/sigma.h>
 
-/* Return: 0==OK, <0==error, =1 ==no more actions */
+static size_t sigma_action_size(struct sigma_action *sa)
+{
+	size_t payload = 0;
+
+	switch (sa->instr) {
+	case SIGMA_ACTION_WRITEXBYTES:
+	case SIGMA_ACTION_WRITESINGLE:
+	case SIGMA_ACTION_WRITESAFELOAD:
+		payload = sigma_action_len(sa);
+		break;
+	default:
+		break;
+	}
+
+	payload = ALIGN(payload, 2);
+
+	return payload + sizeof(struct sigma_action);
+}
+
+/*
+ * Returns a negative error value in case of an error, 0 if processing of
+ * the firmware should be stopped after this action, 1 otherwise.
+ */
 static int
-process_sigma_action(struct i2c_client *client, struct sigma_firmware *ssfw)
+process_sigma_action(struct i2c_client *client, struct sigma_action *sa)
 {
-	struct sigma_action *sa = (void *)(ssfw->fw->data + ssfw->pos);
 	size_t len = sigma_action_len(sa);
-	int ret = 0;
+	int ret;
 
 	pr_debug("%s: instr:%i addr:%#x len:%zu\n", __func__,
 		sa->instr, sa->addr, len);
@@ -29,44 +50,50 @@ process_sigma_action(struct i2c_client *client, struct sigma_firmware *ssfw)
 	case SIGMA_ACTION_WRITEXBYTES:
 	case SIGMA_ACTION_WRITESINGLE:
 	case SIGMA_ACTION_WRITESAFELOAD:
-		if (ssfw->fw->size < ssfw->pos + len)
-			return -EINVAL;
 		ret = i2c_master_send(client, (void *)&sa->addr, len);
 		if (ret < 0)
 			return -EINVAL;
 		break;
-
 	case SIGMA_ACTION_DELAY:
-		ret = 0;
 		udelay(len);
 		len = 0;
 		break;
-
 	case SIGMA_ACTION_END:
-		return 1;
-
+		return 0;
 	default:
 		return -EINVAL;
 	}
 
-	/* when arrive here ret=0 or sent data */
-	ssfw->pos += sigma_action_size(sa, len);
-	return ssfw->pos == ssfw->fw->size;
+	return 1;
 }
 
 static int
 process_sigma_actions(struct i2c_client *client, struct sigma_firmware *ssfw)
 {
-	pr_debug("%s: processing %p\n", __func__, ssfw);
+	struct sigma_action *sa;
+	size_t size;
+	int ret;
+
+	while (ssfw->pos + sizeof(*sa) <= ssfw->fw->size) {
+		sa = (struct sigma_action *)(ssfw->fw->data + ssfw->pos);
+
+		size = sigma_action_size(sa);
+		ssfw->pos += size;
+		if (ssfw->pos > ssfw->fw->size || size == 0)
+			break;
+
+		ret = process_sigma_action(client, sa);
 
-	while (1) {
-		int ret = process_sigma_action(client, ssfw);
 		pr_debug("%s: action returned %i\n", __func__, ret);
-		if (ret == 1)
-			return 0;
-		else if (ret)
+
+		if (ret <= 0)
 			return ret;
 	}
+
+	if (ssfw->pos != ssfw->fw->size)
+		return -EINVAL;
+
+	return 0;
 }
 
 int process_sigma_firmware(struct i2c_client *client, const char *name)
@@ -89,16 +116,24 @@ int process_sigma_firmware(struct i2c_client *client, const char *name)
 
 	/* then verify the header */
 	ret = -EINVAL;
-	if (fw->size < sizeof(*ssfw_head))
+
+	/*
+	 * Reject too small or unreasonable large files. The upper limit has been
+	 * chosen a bit arbitrarily, but it should be enough for all practical
+	 * purposes and having the limit makes it easier to avoid integer
+	 * overflows later in the loading process.
+	 */
+	if (fw->size < sizeof(*ssfw_head) || fw->size >= 0x4000000)
 		goto done;
 
 	ssfw_head = (void *)fw->data;
 	if (memcmp(ssfw_head->magic, SIGMA_MAGIC, ARRAY_SIZE(ssfw_head->magic)))
 		goto done;
 
-	crc = crc32(0, fw->data, fw->size);
+	crc = crc32(0, fw->data + sizeof(*ssfw_head),
+			fw->size - sizeof(*ssfw_head));
 	pr_debug("%s: crc=%x\n", __func__, crc);
-	if (crc != ssfw_head->crc)
+	if (crc != le32_to_cpu(ssfw_head->crc))
 		goto done;
 
 	ssfw.pos = sizeof(*ssfw_head);
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index fe738f05309..2410c4078f3 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -1868,6 +1868,10 @@ int drm_mode_dirtyfb_ioctl(struct drm_device *dev,
 	}
 
 	if (num_clips && clips_ptr) {
+		if (num_clips < 0 || num_clips > DRM_MODE_FB_DIRTY_MAX_CLIPS) {
+			ret = -EINVAL;
+			goto out_err1;
+		}
 		clips = kzalloc(num_clips * sizeof(*clips), GFP_KERNEL);
 		if (!clips) {
 			ret = -ENOMEM;
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index a546a71fb06..346d5574f0a 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1475,7 +1475,7 @@ i915_gem_mmap_gtt(struct drm_file *file,
 
 	if (obj->base.size > dev_priv->mm.gtt_mappable_end) {
 		ret = -E2BIG;
-		goto unlock;
+		goto out;
 	}
 
 	if (obj->madv != I915_MADV_WILLNEED) {
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 9cbb0cd8f46..73248d0ea17 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -822,6 +822,7 @@ static void i915_gem_record_fences(struct drm_device *dev,
 
 	/* Fences */
 	switch (INTEL_INFO(dev)->gen) {
+	case 7:
 	case 6:
 		for (i = 0; i < 16; i++)
 			error->fence[i] = I915_READ64(FENCE_REG_SANDYBRIDGE_0 + (i * 8));
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 542453f7498..ad381a236b3 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -2554,10 +2554,18 @@
 #define _CURBBASE		0x700c4
 #define _CURBPOS			0x700c8
 
+#define _CURBCNTR_IVB		0x71080
+#define _CURBBASE_IVB		0x71084
+#define _CURBPOS_IVB		0x71088
+
 #define CURCNTR(pipe) _PIPE(pipe, _CURACNTR, _CURBCNTR)
 #define CURBASE(pipe) _PIPE(pipe, _CURABASE, _CURBBASE)
 #define CURPOS(pipe) _PIPE(pipe, _CURAPOS, _CURBPOS)
 
+#define CURCNTR_IVB(pipe) _PIPE(pipe, _CURACNTR, _CURBCNTR_IVB)
+#define CURBASE_IVB(pipe) _PIPE(pipe, _CURABASE, _CURBBASE_IVB)
+#define CURPOS_IVB(pipe) _PIPE(pipe, _CURAPOS, _CURBPOS_IVB)
+
 /* Display A control */
 #define _DSPACNTR                0x70180
 #define   DISPLAY_PLANE_ENABLE			(1<<31)
@@ -3167,6 +3175,7 @@
 #define  FDI_LINK_TRAIN_NONE_IVB            (3<<8)
 
 /* both Tx and Rx */
+#define  FDI_COMPOSITE_SYNC		(1<<11)
 #define  FDI_LINK_TRAIN_AUTO		(1<<10)
 #define  FDI_SCRAMBLING_ENABLE          (0<<7)
 #define  FDI_SCRAMBLING_DISABLE         (1<<7)
@@ -3392,6 +3401,10 @@
 #define  GT_FIFO_FREE_ENTRIES			0x120008
 #define    GT_FIFO_NUM_RESERVED_ENTRIES		20
 
+#define GEN6_UCGCTL2				0x9404
+# define GEN6_RCPBUNIT_CLOCK_GATE_DISABLE		(1 << 12)
+# define GEN6_RCCUNIT_CLOCK_GATE_DISABLE		(1 << 11)
+
 #define GEN6_RPNSWREQ				0xA008
 #define   GEN6_TURBO_DISABLE			(1<<31)
 #define   GEN6_FREQUENCY(x)			((x)<<25)
diff --git a/drivers/gpu/drm/i915/i915_suspend.c b/drivers/gpu/drm/i915/i915_suspend.c
index f10742359ec..9c7706a4c71 100644
--- a/drivers/gpu/drm/i915/i915_suspend.c
+++ b/drivers/gpu/drm/i915/i915_suspend.c
@@ -370,6 +370,7 @@ static void i915_save_modeset_reg(struct drm_device *dev)
 
 	/* Fences */
 	switch (INTEL_INFO(dev)->gen) {
+	case 7:
 	case 6:
 		for (i = 0; i < 16; i++)
 			dev_priv->saveFENCE[i] = I915_READ64(FENCE_REG_SANDYBRIDGE_0 + (i * 8));
@@ -404,6 +405,7 @@ static void i915_restore_modeset_reg(struct drm_device *dev)
 
 	/* Fences */
 	switch (INTEL_INFO(dev)->gen) {
+	case 7:
 	case 6:
 		for (i = 0; i < 16; i++)
 			I915_WRITE64(FENCE_REG_SANDYBRIDGE_0 + (i * 8), dev_priv->saveFENCE[i]);
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 04411ad2e77..07e7cf38068 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -2600,6 +2600,7 @@ static void ivb_manual_fdi_link_train(struct drm_crtc *crtc)
 	temp |= FDI_LINK_TRAIN_PATTERN_1_IVB;
 	temp &= ~FDI_LINK_TRAIN_VOL_EMP_MASK;
 	temp |= FDI_LINK_TRAIN_400MV_0DB_SNB_B;
+	temp |= FDI_COMPOSITE_SYNC;
 	I915_WRITE(reg, temp | FDI_TX_ENABLE);
 
 	reg = FDI_RX_CTL(pipe);
@@ -2607,6 +2608,7 @@ static void ivb_manual_fdi_link_train(struct drm_crtc *crtc)
 	temp &= ~FDI_LINK_TRAIN_AUTO;
 	temp &= ~FDI_LINK_TRAIN_PATTERN_MASK_CPT;
 	temp |= FDI_LINK_TRAIN_PATTERN_1_CPT;
+	temp |= FDI_COMPOSITE_SYNC;
 	I915_WRITE(reg, temp | FDI_RX_ENABLE);
 
 	POSTING_READ(reg);
@@ -5758,6 +5760,31 @@ static void i9xx_update_cursor(struct drm_crtc *crtc, u32 base)
 	I915_WRITE(CURBASE(pipe), base);
 }
 
+static void ivb_update_cursor(struct drm_crtc *crtc, u32 base)
+{
+	struct drm_device *dev = crtc->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+	int pipe = intel_crtc->pipe;
+	bool visible = base != 0;
+
+	if (intel_crtc->cursor_visible != visible) {
+		uint32_t cntl = I915_READ(CURCNTR_IVB(pipe));
+		if (base) {
+			cntl &= ~CURSOR_MODE;
+			cntl |= CURSOR_MODE_64_ARGB_AX | MCURSOR_GAMMA_ENABLE;
+		} else {
+			cntl &= ~(CURSOR_MODE | MCURSOR_GAMMA_ENABLE);
+			cntl |= CURSOR_MODE_DISABLE;
+		}
+		I915_WRITE(CURCNTR_IVB(pipe), cntl);
+
+		intel_crtc->cursor_visible = visible;
+	}
+	/* and commit changes on next vblank */
+	I915_WRITE(CURBASE_IVB(pipe), base);
+}
+
 /* If no-part of the cursor is visible on the framebuffer, then the GPU may hang... */
 static void intel_crtc_update_cursor(struct drm_crtc *crtc,
 				     bool on)
@@ -5805,11 +5832,16 @@ static void intel_crtc_update_cursor(struct drm_crtc *crtc,
 	if (!visible && !intel_crtc->cursor_visible)
 		return;
 
-	I915_WRITE(CURPOS(pipe), pos);
-	if (IS_845G(dev) || IS_I865G(dev))
-		i845_update_cursor(crtc, base);
-	else
-		i9xx_update_cursor(crtc, base);
+	if (IS_IVYBRIDGE(dev)) {
+		I915_WRITE(CURPOS_IVB(pipe), pos);
+		ivb_update_cursor(crtc, base);
+	} else {
+		I915_WRITE(CURPOS(pipe), pos);
+		if (IS_845G(dev) || IS_I865G(dev))
+			i845_update_cursor(crtc, base);
+		else
+			i9xx_update_cursor(crtc, base);
+	}
 
 	if (visible)
 		intel_mark_busy(dev, to_intel_framebuffer(crtc->fb)->obj);
@@ -7850,6 +7882,20 @@ static void gen6_init_clock_gating(struct drm_device *dev)
 	I915_WRITE(WM2_LP_ILK, 0);
 	I915_WRITE(WM1_LP_ILK, 0);
 
+	/* According to the BSpec vol1g, bit 12 (RCPBUNIT) clock
+	 * gating disable must be set.  Failure to set it results in
+	 * flickering pixels due to Z write ordering failures after
+	 * some amount of runtime in the Mesa "fire" demo, and Unigine
+	 * Sanctuary and Tropics, and apparently anything else with
+	 * alpha test or pixel discard.
+	 *
+	 * According to the spec, bit 11 (RCCUNIT) must also be set,
+	 * but we didn't debug actual testcases to find it out.
+	 */
+	I915_WRITE(GEN6_UCGCTL2,
+		   GEN6_RCPBUNIT_CLOCK_GATE_DISABLE |
+		   GEN6_RCCUNIT_CLOCK_GATE_DISABLE);
+
 	/*
 	 * According to the spec the following bits should be
 	 * set in order to enable memory self-refresh and fbc:
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 44fef5e1c49..7c64db48c1c 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -1683,6 +1683,31 @@ g4x_dp_detect(struct intel_dp *intel_dp)
 	return intel_dp_detect_dpcd(intel_dp);
 }
 
+static struct edid *
+intel_dp_get_edid(struct drm_connector *connector, struct i2c_adapter *adapter)
+{
+	struct intel_dp *intel_dp = intel_attached_dp(connector);
+	struct edid	*edid;
+
+	ironlake_edp_panel_vdd_on(intel_dp);
+	edid = drm_get_edid(connector, adapter);
+	ironlake_edp_panel_vdd_off(intel_dp);
+	return edid;
+}
+
+static int
+intel_dp_get_edid_modes(struct drm_connector *connector, struct i2c_adapter *adapter)
+{
+	struct intel_dp *intel_dp = intel_attached_dp(connector);
+	int	ret;
+
+	ironlake_edp_panel_vdd_on(intel_dp);
+	ret = intel_ddc_get_modes(connector, adapter);
+	ironlake_edp_panel_vdd_off(intel_dp);
+	return ret;
+}
+
+
 /**
  * Uses CRT_HOTPLUG_EN and CRT_HOTPLUG_STAT to detect DP connection.
  *
@@ -1715,7 +1740,7 @@ intel_dp_detect(struct drm_connector *connector, bool force)
 	if (intel_dp->force_audio) {
 		intel_dp->has_audio = intel_dp->force_audio > 0;
 	} else {
-		edid = drm_get_edid(connector, &intel_dp->adapter);
+		edid = intel_dp_get_edid(connector, &intel_dp->adapter);
 		if (edid) {
 			intel_dp->has_audio = drm_detect_monitor_audio(edid);
 			connector->display_info.raw_edid = NULL;
@@ -1736,7 +1761,7 @@ static int intel_dp_get_modes(struct drm_connector *connector)
 	/* We should parse the EDID data and find out if it has an audio sink
 	 */
 
-	ret = intel_ddc_get_modes(connector, &intel_dp->adapter);
+	ret = intel_dp_get_edid_modes(connector, &intel_dp->adapter);
 	if (ret) {
 		if (is_edp(intel_dp) && !dev_priv->panel_fixed_mode) {
 			struct drm_display_mode *newmode;
@@ -1772,7 +1797,7 @@ intel_dp_detect_audio(struct drm_connector *connector)
 	struct edid *edid;
 	bool has_audio = false;
 
-	edid = drm_get_edid(connector, &intel_dp->adapter);
+	edid = intel_dp_get_edid(connector, &intel_dp->adapter);
 	if (edid) {
 		has_audio = drm_detect_monitor_audio(edid);
 
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index fe1099d8817..2480cfa7c0c 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -184,7 +184,7 @@ struct intel_crtc {
 #define DIP_VERSION_AVI 0x2
 #define DIP_LEN_AVI     13
 
-#define DIP_TYPE_SPD	0x3
+#define DIP_TYPE_SPD	0x83
 #define DIP_VERSION_SPD	0x1
 #define DIP_LEN_SPD	25
 #define DIP_SPD_UNKNOWN	0
diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c
index a9e0c7bcd31..007f6ca309d 100644
--- a/drivers/gpu/drm/i915/intel_panel.c
+++ b/drivers/gpu/drm/i915/intel_panel.c
@@ -226,7 +226,7 @@ static void intel_pch_panel_set_backlight(struct drm_device *dev, u32 level)
 	I915_WRITE(BLC_PWM_CPU_CTL, val | level);
 }
 
-void intel_panel_set_backlight(struct drm_device *dev, u32 level)
+static void intel_panel_actually_set_backlight(struct drm_device *dev, u32 level)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 tmp;
@@ -254,16 +254,21 @@ void intel_panel_set_backlight(struct drm_device *dev, u32 level)
 	I915_WRITE(BLC_PWM_CTL, tmp | level);
 }
 
-void intel_panel_disable_backlight(struct drm_device *dev)
+void intel_panel_set_backlight(struct drm_device *dev, u32 level)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	if (dev_priv->backlight_enabled) {
-		dev_priv->backlight_level = intel_panel_get_backlight(dev);
-		dev_priv->backlight_enabled = false;
-	}
+	dev_priv->backlight_level = level;
+	if (dev_priv->backlight_enabled)
+		intel_panel_actually_set_backlight(dev, level);
+}
 
-	intel_panel_set_backlight(dev, 0);
+void intel_panel_disable_backlight(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	dev_priv->backlight_enabled = false;
+	intel_panel_actually_set_backlight(dev, 0);
 }
 
 void intel_panel_enable_backlight(struct drm_device *dev)
@@ -273,8 +278,8 @@ void intel_panel_enable_backlight(struct drm_device *dev)
 	if (dev_priv->backlight_level == 0)
 		dev_priv->backlight_level = intel_panel_get_max_backlight(dev);
 
-	intel_panel_set_backlight(dev, dev_priv->backlight_level);
 	dev_priv->backlight_enabled = true;
+	intel_panel_actually_set_backlight(dev, dev_priv->backlight_level);
 }
 
 static void intel_panel_init_backlight(struct drm_device *dev)
@@ -321,7 +326,8 @@ static int intel_panel_update_status(struct backlight_device *bd)
 static int intel_panel_get_brightness(struct backlight_device *bd)
 {
 	struct drm_device *dev = bl_get_data(bd);
-	return intel_panel_get_backlight(dev);
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	return dev_priv->backlight_level;
 }
 
 static const struct backlight_ops intel_panel_bl_ops = {
diff --git a/drivers/gpu/drm/nouveau/nouveau_channel.c b/drivers/gpu/drm/nouveau/nouveau_channel.c
index b0d753f45bb..0e3241c39b8 100644
--- a/drivers/gpu/drm/nouveau/nouveau_channel.c
+++ b/drivers/gpu/drm/nouveau/nouveau_channel.c
@@ -158,6 +158,7 @@ nouveau_channel_alloc(struct drm_device *dev, struct nouveau_channel **chan_ret,
 	INIT_LIST_HEAD(&chan->nvsw.vbl_wait);
 	INIT_LIST_HEAD(&chan->nvsw.flip);
 	INIT_LIST_HEAD(&chan->fence.pending);
+	spin_lock_init(&chan->fence.lock);
 
 	/* setup channel's memory and vm */
 	ret = nouveau_gpuobj_channel_init(chan, vram_handle, gart_handle);
diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c
index c919cfc8f2f..ae22dfaa2a0 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.c
@@ -539,8 +539,6 @@ nouveau_fence_channel_init(struct nouveau_channel *chan)
 			return ret;
 	}
 
-	INIT_LIST_HEAD(&chan->fence.pending);
-	spin_lock_init(&chan->fence.lock);
 	atomic_set(&chan->fence.last_sequence_irq, 0);
 	return 0;
 }
diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c
index 79e8ebc0530..3b77ad60ed5 100644
--- a/drivers/gpu/drm/radeon/atombios_dp.c
+++ b/drivers/gpu/drm/radeon/atombios_dp.c
@@ -283,7 +283,7 @@ int radeon_dp_i2c_aux_ch(struct i2c_adapter *adapter, int mode,
 		}
 	}
 
-	DRM_ERROR("aux i2c too many retries, giving up\n");
+	DRM_DEBUG_KMS("aux i2c too many retries, giving up\n");
 	return -EREMOTEIO;
 }
 
@@ -553,6 +553,7 @@ static void radeon_dp_set_panel_mode(struct drm_encoder *encoder,
 {
 	struct drm_device *dev = encoder->dev;
 	struct radeon_device *rdev = dev->dev_private;
+	struct radeon_connector *radeon_connector = to_radeon_connector(connector);
 	int panel_mode = DP_PANEL_MODE_EXTERNAL_DP_MODE;
 
 	if (!ASIC_IS_DCE4(rdev))
@@ -560,10 +561,20 @@ static void radeon_dp_set_panel_mode(struct drm_encoder *encoder,
 
 	if (radeon_connector_encoder_is_dp_bridge(connector))
 		panel_mode = DP_PANEL_MODE_INTERNAL_DP1_MODE;
+	else if (connector->connector_type == DRM_MODE_CONNECTOR_eDP) {
+		u8 tmp = radeon_read_dpcd_reg(radeon_connector, DP_EDP_CONFIGURATION_CAP);
+		if (tmp & 1)
+			panel_mode = DP_PANEL_MODE_INTERNAL_DP2_MODE;
+	}
 
 	atombios_dig_encoder_setup(encoder,
 				   ATOM_ENCODER_CMD_SETUP_PANEL_MODE,
 				   panel_mode);
+
+	if ((connector->connector_type == DRM_MODE_CONNECTOR_eDP) &&
+	    (panel_mode == DP_PANEL_MODE_INTERNAL_DP2_MODE)) {
+		radeon_write_dpcd_reg(radeon_connector, DP_EDP_CONFIGURATION_SET, 1);
+	}
 }
 
 void radeon_dp_set_link_config(struct drm_connector *connector,
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index c4ffa14fb2f..d4ee6f0d3c7 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -82,6 +82,7 @@ u32 evergreen_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base)
 {
 	struct radeon_crtc *radeon_crtc = rdev->mode_info.crtcs[crtc_id];
 	u32 tmp = RREG32(EVERGREEN_GRPH_UPDATE + radeon_crtc->crtc_offset);
+	int i;
 
 	/* Lock the graphics update lock */
 	tmp |= EVERGREEN_GRPH_UPDATE_LOCK;
@@ -99,7 +100,11 @@ u32 evergreen_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base)
 	       (u32)crtc_base);
 
 	/* Wait for update_pending to go high. */
-	while (!(RREG32(EVERGREEN_GRPH_UPDATE + radeon_crtc->crtc_offset) & EVERGREEN_GRPH_SURFACE_UPDATE_PENDING));
+	for (i = 0; i < rdev->usec_timeout; i++) {
+		if (RREG32(EVERGREEN_GRPH_UPDATE + radeon_crtc->crtc_offset) & EVERGREEN_GRPH_SURFACE_UPDATE_PENDING)
+			break;
+		udelay(1);
+	}
 	DRM_DEBUG("Update pending now high. Unlocking vupdate_lock.\n");
 
 	/* Unlock the lock, so double-buffering can take place inside vblank */
@@ -353,6 +358,7 @@ void evergreen_hpd_init(struct radeon_device *rdev)
 		default:
 			break;
 		}
+		radeon_hpd_set_polarity(rdev, radeon_connector->hpd.hpd);
 	}
 	if (rdev->irq.installed)
 		evergreen_irq_set(rdev);
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index 7fcdbbbf297..b94d871487e 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -84,13 +84,18 @@ u32 r100_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base)
 {
 	struct radeon_crtc *radeon_crtc = rdev->mode_info.crtcs[crtc_id];
 	u32 tmp = ((u32)crtc_base) | RADEON_CRTC_OFFSET__OFFSET_LOCK;
+	int i;
 
 	/* Lock the graphics update lock */
 	/* update the scanout addresses */
 	WREG32(RADEON_CRTC_OFFSET + radeon_crtc->crtc_offset, tmp);
 
 	/* Wait for update_pending to go high. */
-	while (!(RREG32(RADEON_CRTC_OFFSET + radeon_crtc->crtc_offset) & RADEON_CRTC_OFFSET__GUI_TRIG_OFFSET));
+	for (i = 0; i < rdev->usec_timeout; i++) {
+		if (RREG32(RADEON_CRTC_OFFSET + radeon_crtc->crtc_offset) & RADEON_CRTC_OFFSET__GUI_TRIG_OFFSET)
+			break;
+		udelay(1);
+	}
 	DRM_DEBUG("Update pending now high. Unlocking vupdate_lock.\n");
 
 	/* Unlock the lock, so double-buffering can take place inside vblank */
@@ -434,6 +439,7 @@ void r100_hpd_init(struct radeon_device *rdev)
 		default:
 			break;
 		}
+		radeon_hpd_set_polarity(rdev, radeon_connector->hpd.hpd);
 	}
 	if (rdev->irq.installed)
 		r100_irq_set(rdev);
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 720dd99163f..9b62a97742a 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -762,13 +762,14 @@ void r600_hpd_init(struct radeon_device *rdev)
 	struct drm_device *dev = rdev->ddev;
 	struct drm_connector *connector;
 
-	if (ASIC_IS_DCE3(rdev)) {
-		u32 tmp = DC_HPDx_CONNECTION_TIMER(0x9c4) | DC_HPDx_RX_INT_TIMER(0xfa);
-		if (ASIC_IS_DCE32(rdev))
-			tmp |= DC_HPDx_EN;
+	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
+		struct radeon_connector *radeon_connector = to_radeon_connector(connector);
+
+		if (ASIC_IS_DCE3(rdev)) {
+			u32 tmp = DC_HPDx_CONNECTION_TIMER(0x9c4) | DC_HPDx_RX_INT_TIMER(0xfa);
+			if (ASIC_IS_DCE32(rdev))
+				tmp |= DC_HPDx_EN;
 
-		list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
-			struct radeon_connector *radeon_connector = to_radeon_connector(connector);
 			switch (radeon_connector->hpd.hpd) {
 			case RADEON_HPD_1:
 				WREG32(DC_HPD1_CONTROL, tmp);
@@ -798,10 +799,7 @@ void r600_hpd_init(struct radeon_device *rdev)
 			default:
 				break;
 			}
-		}
-	} else {
-		list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
-			struct radeon_connector *radeon_connector = to_radeon_connector(connector);
+		} else {
 			switch (radeon_connector->hpd.hpd) {
 			case RADEON_HPD_1:
 				WREG32(DC_HOT_PLUG_DETECT1_CONTROL, DC_HOT_PLUG_DETECTx_EN);
@@ -819,6 +817,7 @@ void r600_hpd_init(struct radeon_device *rdev)
 				break;
 			}
 		}
+		radeon_hpd_set_polarity(rdev, radeon_connector->hpd.hpd);
 	}
 	if (rdev->irq.installed)
 		r600_irq_set(rdev);
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index c1e056b35b2..184628c7e02 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -93,6 +93,7 @@ extern int radeon_audio;
 extern int radeon_disp_priority;
 extern int radeon_hw_i2c;
 extern int radeon_pcie_gen2;
+extern int radeon_msi;
 
 /*
  * Copy from radeon_drv.h so we don't have to include both and have conflicting
diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c
index bf2b61584cd..285acc4f1e1 100644
--- a/drivers/gpu/drm/radeon/radeon_atombios.c
+++ b/drivers/gpu/drm/radeon/radeon_atombios.c
@@ -85,6 +85,18 @@ static inline struct radeon_i2c_bus_rec radeon_lookup_i2c_gpio(struct radeon_dev
 		for (i = 0; i < num_indices; i++) {
 			gpio = &i2c_info->asGPIO_Info[i];
 
+			/* r4xx mask is technically not used by the hw, so patch in the legacy mask bits */
+			if ((rdev->family == CHIP_R420) ||
+			    (rdev->family == CHIP_R423) ||
+			    (rdev->family == CHIP_RV410)) {
+				if ((le16_to_cpu(gpio->usClkMaskRegisterIndex) == 0x0018) ||
+				    (le16_to_cpu(gpio->usClkMaskRegisterIndex) == 0x0019) ||
+				    (le16_to_cpu(gpio->usClkMaskRegisterIndex) == 0x001a)) {
+					gpio->ucClkMaskShift = 0x19;
+					gpio->ucDataMaskShift = 0x18;
+				}
+			}
+
 			/* some evergreen boards have bad data for this entry */
 			if (ASIC_IS_DCE4(rdev)) {
 				if ((i == 7) &&
@@ -169,6 +181,18 @@ void radeon_atombios_i2c_init(struct radeon_device *rdev)
 			gpio = &i2c_info->asGPIO_Info[i];
 			i2c.valid = false;
 
+			/* r4xx mask is technically not used by the hw, so patch in the legacy mask bits */
+			if ((rdev->family == CHIP_R420) ||
+			    (rdev->family == CHIP_R423) ||
+			    (rdev->family == CHIP_RV410)) {
+				if ((le16_to_cpu(gpio->usClkMaskRegisterIndex) == 0x0018) ||
+				    (le16_to_cpu(gpio->usClkMaskRegisterIndex) == 0x0019) ||
+				    (le16_to_cpu(gpio->usClkMaskRegisterIndex) == 0x001a)) {
+					gpio->ucClkMaskShift = 0x19;
+					gpio->ucDataMaskShift = 0x18;
+				}
+			}
+
 			/* some evergreen boards have bad data for this entry */
 			if (ASIC_IS_DCE4(rdev)) {
 				if ((i == 7) &&
diff --git a/drivers/gpu/drm/radeon/radeon_combios.c b/drivers/gpu/drm/radeon/radeon_combios.c
index 63675241c7f..8bf83c4b414 100644
--- a/drivers/gpu/drm/radeon/radeon_combios.c
+++ b/drivers/gpu/drm/radeon/radeon_combios.c
@@ -620,8 +620,8 @@ static struct radeon_i2c_bus_rec combios_setup_i2c_bus(struct radeon_device *rde
 		i2c.y_data_mask = 0x80;
 	} else {
 		/* default masks for ddc pads */
-		i2c.mask_clk_mask = RADEON_GPIO_EN_1;
-		i2c.mask_data_mask = RADEON_GPIO_EN_0;
+		i2c.mask_clk_mask = RADEON_GPIO_MASK_1;
+		i2c.mask_data_mask = RADEON_GPIO_MASK_0;
 		i2c.a_clk_mask = RADEON_GPIO_A_1;
 		i2c.a_data_mask = RADEON_GPIO_A_0;
 		i2c.en_clk_mask = RADEON_GPIO_EN_1;
diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c
index 449c3d8c683..ff6a2e0d9a2 100644
--- a/drivers/gpu/drm/radeon/radeon_connectors.c
+++ b/drivers/gpu/drm/radeon/radeon_connectors.c
@@ -724,6 +724,7 @@ radeon_vga_detect(struct drm_connector *connector, bool force)
 		dret = radeon_ddc_probe(radeon_connector,
 					radeon_connector->requires_extended_probe);
 	if (dret) {
+		radeon_connector->detected_by_load = false;
 		if (radeon_connector->edid) {
 			kfree(radeon_connector->edid);
 			radeon_connector->edid = NULL;
@@ -750,12 +751,21 @@ radeon_vga_detect(struct drm_connector *connector, bool force)
 	} else {
 
 		/* if we aren't forcing don't do destructive polling */
-		if (!force)
-			return connector->status;
+		if (!force) {
+			/* only return the previous status if we last
+			 * detected a monitor via load.
+			 */
+			if (radeon_connector->detected_by_load)
+				return connector->status;
+			else
+				return ret;
+		}
 
 		if (radeon_connector->dac_load_detect && encoder) {
 			encoder_funcs = encoder->helper_private;
 			ret = encoder_funcs->detect(encoder, connector);
+			if (ret != connector_status_disconnected)
+				radeon_connector->detected_by_load = true;
 		}
 	}
 
@@ -897,6 +907,7 @@ radeon_dvi_detect(struct drm_connector *connector, bool force)
 		dret = radeon_ddc_probe(radeon_connector,
 					radeon_connector->requires_extended_probe);
 	if (dret) {
+		radeon_connector->detected_by_load = false;
 		if (radeon_connector->edid) {
 			kfree(radeon_connector->edid);
 			radeon_connector->edid = NULL;
@@ -959,8 +970,18 @@ radeon_dvi_detect(struct drm_connector *connector, bool force)
 	if ((ret == connector_status_connected) && (radeon_connector->use_digital == true))
 		goto out;
 
+	/* DVI-D and HDMI-A are digital only */
+	if ((connector->connector_type == DRM_MODE_CONNECTOR_DVID) ||
+	    (connector->connector_type == DRM_MODE_CONNECTOR_HDMIA))
+		goto out;
+
+	/* if we aren't forcing don't do destructive polling */
 	if (!force) {
-		ret = connector->status;
+		/* only return the previous status if we last
+		 * detected a monitor via load.
+		 */
+		if (radeon_connector->detected_by_load)
+			ret = connector->status;
 		goto out;
 	}
 
@@ -985,6 +1006,8 @@ radeon_dvi_detect(struct drm_connector *connector, bool force)
 					if (ret == connector_status_connected) {
 						radeon_connector->use_digital = false;
 					}
+					if (ret != connector_status_disconnected)
+						radeon_connector->detected_by_load = true;
 				}
 				break;
 			}
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index e71d2ed7fa1..c12b0775d68 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -118,6 +118,7 @@ int radeon_audio = 0;
 int radeon_disp_priority = 0;
 int radeon_hw_i2c = 0;
 int radeon_pcie_gen2 = 0;
+int radeon_msi = -1;
 
 MODULE_PARM_DESC(no_wb, "Disable AGP writeback for scratch registers");
 module_param_named(no_wb, radeon_no_wb, int, 0444);
@@ -164,6 +165,9 @@ module_param_named(hw_i2c, radeon_hw_i2c, int, 0444);
 MODULE_PARM_DESC(pcie_gen2, "PCIE Gen2 mode (1 = enable)");
 module_param_named(pcie_gen2, radeon_pcie_gen2, int, 0444);
 
+MODULE_PARM_DESC(msi, "MSI support (1 = enable, 0 = disable, -1 = auto)");
+module_param_named(msi, radeon_msi, int, 0444);
+
 static int radeon_suspend(struct drm_device *dev, pm_message_t state)
 {
 	drm_radeon_private_t *dev_priv = dev->dev_private;
diff --git a/drivers/gpu/drm/radeon/radeon_irq_kms.c b/drivers/gpu/drm/radeon/radeon_irq_kms.c
index 9ec830c77af..fecc1aae382 100644
--- a/drivers/gpu/drm/radeon/radeon_irq_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_irq_kms.c
@@ -108,6 +108,46 @@ void radeon_driver_irq_uninstall_kms(struct drm_device *dev)
 	radeon_irq_set(rdev);
 }
 
+static bool radeon_msi_ok(struct radeon_device *rdev)
+{
+	/* RV370/RV380 was first asic with MSI support */
+	if (rdev->family < CHIP_RV380)
+		return false;
+
+	/* MSIs don't work on AGP */
+	if (rdev->flags & RADEON_IS_AGP)
+		return false;
+
+	/* force MSI on */
+	if (radeon_msi == 1)
+		return true;
+	else if (radeon_msi == 0)
+		return false;
+
+	/* Quirks */
+	/* HP RS690 only seems to work with MSIs. */
+	if ((rdev->pdev->device == 0x791f) &&
+	    (rdev->pdev->subsystem_vendor == 0x103c) &&
+	    (rdev->pdev->subsystem_device == 0x30c2))
+		return true;
+
+	/* Dell RS690 only seems to work with MSIs. */
+	if ((rdev->pdev->device == 0x791f) &&
+	    (rdev->pdev->subsystem_vendor == 0x1028) &&
+	    (rdev->pdev->subsystem_device == 0x01fd))
+		return true;
+
+	if (rdev->flags & RADEON_IS_IGP) {
+		/* APUs work fine with MSIs */
+		if (rdev->family >= CHIP_PALM)
+			return true;
+		/* lots of IGPs have problems with MSIs */
+		return false;
+	}
+
+	return true;
+}
+
 int radeon_irq_kms_init(struct radeon_device *rdev)
 {
 	int i;
@@ -124,12 +164,8 @@ int radeon_irq_kms_init(struct radeon_device *rdev)
 	}
 	/* enable msi */
 	rdev->msi_enabled = 0;
-	/* MSIs don't seem to work reliably on all IGP
-	 * chips.  Disable MSI on them for now.
-	 */
-	if ((rdev->family >= CHIP_RV380) &&
-	    ((!(rdev->flags & RADEON_IS_IGP)) || (rdev->family >= CHIP_PALM)) &&
-	    (!(rdev->flags & RADEON_IS_AGP))) {
+
+	if (radeon_msi_ok(rdev)) {
 		int ret = pci_enable_msi(rdev->pdev);
 		if (!ret) {
 			rdev->msi_enabled = 1;
diff --git a/drivers/gpu/drm/radeon/radeon_mode.h b/drivers/gpu/drm/radeon/radeon_mode.h
index 68820f5f630..ed0178f0323 100644
--- a/drivers/gpu/drm/radeon/radeon_mode.h
+++ b/drivers/gpu/drm/radeon/radeon_mode.h
@@ -447,6 +447,7 @@ struct radeon_connector {
 	struct edid *edid;
 	void *con_priv;
 	bool dac_load_detect;
+	bool detected_by_load; /* if the connection status was determined by load */
 	uint16_t connector_object_id;
 	struct radeon_hpd hpd;
 	struct radeon_router router;
diff --git a/drivers/gpu/drm/radeon/rs600.c b/drivers/gpu/drm/radeon/rs600.c
index 4b5d0e6974a..0e89a9b885e 100644
--- a/drivers/gpu/drm/radeon/rs600.c
+++ b/drivers/gpu/drm/radeon/rs600.c
@@ -62,6 +62,7 @@ u32 rs600_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base)
 {
 	struct radeon_crtc *radeon_crtc = rdev->mode_info.crtcs[crtc_id];
 	u32 tmp = RREG32(AVIVO_D1GRPH_UPDATE + radeon_crtc->crtc_offset);
+	int i;
 
 	/* Lock the graphics update lock */
 	tmp |= AVIVO_D1GRPH_UPDATE_LOCK;
@@ -74,7 +75,11 @@ u32 rs600_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base)
 	       (u32)crtc_base);
 
 	/* Wait for update_pending to go high. */
-	while (!(RREG32(AVIVO_D1GRPH_UPDATE + radeon_crtc->crtc_offset) & AVIVO_D1GRPH_SURFACE_UPDATE_PENDING));
+	for (i = 0; i < rdev->usec_timeout; i++) {
+		if (RREG32(AVIVO_D1GRPH_UPDATE + radeon_crtc->crtc_offset) & AVIVO_D1GRPH_SURFACE_UPDATE_PENDING)
+			break;
+		udelay(1);
+	}
 	DRM_DEBUG("Update pending now high. Unlocking vupdate_lock.\n");
 
 	/* Unlock the lock, so double-buffering can take place inside vblank */
@@ -287,6 +292,7 @@ void rs600_hpd_init(struct radeon_device *rdev)
 		default:
 			break;
 		}
+		radeon_hpd_set_polarity(rdev, radeon_connector->hpd.hpd);
 	}
 	if (rdev->irq.installed)
 		rs600_irq_set(rdev);
diff --git a/drivers/gpu/drm/radeon/rv770.c b/drivers/gpu/drm/radeon/rv770.c
index b13c2eedc32..ddc206a1f61 100644
--- a/drivers/gpu/drm/radeon/rv770.c
+++ b/drivers/gpu/drm/radeon/rv770.c
@@ -47,6 +47,7 @@ u32 rv770_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base)
 {
 	struct radeon_crtc *radeon_crtc = rdev->mode_info.crtcs[crtc_id];
 	u32 tmp = RREG32(AVIVO_D1GRPH_UPDATE + radeon_crtc->crtc_offset);
+	int i;
 
 	/* Lock the graphics update lock */
 	tmp |= AVIVO_D1GRPH_UPDATE_LOCK;
@@ -66,7 +67,11 @@ u32 rv770_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base)
 	       (u32)crtc_base);
 
 	/* Wait for update_pending to go high. */
-	while (!(RREG32(AVIVO_D1GRPH_UPDATE + radeon_crtc->crtc_offset) & AVIVO_D1GRPH_SURFACE_UPDATE_PENDING));
+	for (i = 0; i < rdev->usec_timeout; i++) {
+		if (RREG32(AVIVO_D1GRPH_UPDATE + radeon_crtc->crtc_offset) & AVIVO_D1GRPH_SURFACE_UPDATE_PENDING)
+			break;
+		udelay(1);
+	}
 	DRM_DEBUG("Update pending now high. Unlocking vupdate_lock.\n");
 
 	/* Unlock the lock, so double-buffering can take place inside vblank */
diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig
index 1130a898712..7978c55db84 100644
--- a/drivers/hid/Kconfig
+++ b/drivers/hid/Kconfig
@@ -69,7 +69,7 @@ config HID_ACRUX
 	Say Y here if you want to enable support for ACRUX game controllers.
 
 config HID_ACRUX_FF
-	tristate "ACRUX force feedback support"
+	bool "ACRUX force feedback support"
 	depends on HID_ACRUX
 	select INPUT_FF_MEMLESS
 	---help---
@@ -328,6 +328,7 @@ config HID_MULTITOUCH
 	  - Hanvon dual touch panels
 	  - Ilitek dual touch panels
 	  - IrTouch Infrared USB panels
+	  - LG Display panels (Dell ST2220Tc)
 	  - Lumio CrystalTouch panels
 	  - MosArt dual-touch panels
 	  - PenMount dual touch panels
diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c
index 18b3bc646bf..299d2387112 100644
--- a/drivers/hid/hid-apple.c
+++ b/drivers/hid/hid-apple.c
@@ -455,6 +455,9 @@ static const struct hid_device_id apple_devices[] = {
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_ISO),
 		.driver_data = APPLE_NUMLOCK_EMULATION | APPLE_HAS_FN |
 			APPLE_ISO_KEYBOARD },
+	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ISO),
+		.driver_data = APPLE_NUMLOCK_EMULATION | APPLE_HAS_FN |
+			APPLE_ISO_KEYBOARD },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_JIS),
 		.driver_data = APPLE_NUMLOCK_EMULATION | APPLE_HAS_FN },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING_ANSI),
@@ -493,6 +496,24 @@ static const struct hid_device_id apple_devices[] = {
 		.driver_data = APPLE_HAS_FN | APPLE_ISO_KEYBOARD },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING5_JIS),
 		.driver_data = APPLE_HAS_FN | APPLE_RDESC_JIS },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING6_ANSI),
+		.driver_data = APPLE_HAS_FN },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING6_ISO),
+		.driver_data = APPLE_HAS_FN | APPLE_ISO_KEYBOARD },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING6_JIS),
+		.driver_data = APPLE_HAS_FN | APPLE_RDESC_JIS },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING6A_ANSI),
+		.driver_data = APPLE_HAS_FN },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING6A_ISO),
+		.driver_data = APPLE_HAS_FN | APPLE_ISO_KEYBOARD },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING6A_JIS),
+		.driver_data = APPLE_HAS_FN | APPLE_RDESC_JIS },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING5A_ANSI),
+		.driver_data = APPLE_HAS_FN },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING5A_ISO),
+		.driver_data = APPLE_HAS_FN | APPLE_ISO_KEYBOARD },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING5A_JIS),
+		.driver_data = APPLE_HAS_FN | APPLE_RDESC_JIS },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ANSI),
 		.driver_data = APPLE_NUMLOCK_EMULATION | APPLE_HAS_FN },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ISO),
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index 242353df3dc..f26ae3176a3 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -1340,12 +1340,22 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING5_ANSI) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING5_ISO) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING5_JIS) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING5A_ANSI) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING5A_ISO) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING5A_JIS) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING6_ANSI) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING6_ISO) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING6_JIS) },
+ 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING6A_ANSI) },
+ 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING6A_ISO) },
+ 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING6A_JIS) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_REVB_ANSI) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_REVB_ISO) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_REVB_JIS) },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ANSI) },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ISO) },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_JIS) },
+	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ISO) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_FOUNTAIN_TP_ONLY) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_GEYSER1_TP_ONLY) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ASUS, USB_DEVICE_ID_ASUS_T91MT) },
@@ -1399,6 +1409,7 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_ERGO_525V) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LABTEC, USB_DEVICE_ID_LABTEC_WIRELESS_KEYBOARD) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LCPOWER, USB_DEVICE_ID_LCPOWER_LC1000 ) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_LG, USB_DEVICE_ID_LG_MULTITOUCH) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_MX3000_RECEIVER) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_S510_RECEIVER) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_S510_RECEIVER_2) },
@@ -1717,8 +1728,8 @@ static const struct hid_device_id hid_ignore_list[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ESSENTIAL_REALITY, USB_DEVICE_ID_ESSENTIAL_REALITY_P5) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ETT, USB_DEVICE_ID_TC5UH) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ETT, USB_DEVICE_ID_TC4UM) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_GENERAL_TOUCH, 0x0001) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_GENERAL_TOUCH, 0x0002) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_GENERAL_TOUCH, 0x0003) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_GENERAL_TOUCH, 0x0004) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_GLAB, USB_DEVICE_ID_4_PHIDGETSERVO_30) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_GLAB, USB_DEVICE_ID_1_PHIDGETSERVO_30) },
@@ -1892,6 +1903,9 @@ static const struct hid_device_id hid_mouse_ignore_list[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING5_ANSI) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING5_ISO) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING5_JIS) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING5A_ANSI) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING5A_ISO) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING5A_JIS) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_FOUNTAIN_TP_ONLY) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_GEYSER1_TP_ONLY) },
 	{ }
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 7484e1b6724..53c4634fed3 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -109,12 +109,22 @@
 #define USB_DEVICE_ID_APPLE_WELLSPRING5_ANSI	0x0245
 #define USB_DEVICE_ID_APPLE_WELLSPRING5_ISO	0x0246
 #define USB_DEVICE_ID_APPLE_WELLSPRING5_JIS	0x0247
+#define USB_DEVICE_ID_APPLE_WELLSPRING6A_ANSI	0x0249
+#define USB_DEVICE_ID_APPLE_WELLSPRING6A_ISO	0x024a
+#define USB_DEVICE_ID_APPLE_WELLSPRING6A_JIS	0x024b
+#define USB_DEVICE_ID_APPLE_WELLSPRING6_ANSI	0x024c
+#define USB_DEVICE_ID_APPLE_WELLSPRING6_ISO	0x024d
+#define USB_DEVICE_ID_APPLE_WELLSPRING6_JIS	0x024e
 #define USB_DEVICE_ID_APPLE_ALU_REVB_ANSI	0x024f
 #define USB_DEVICE_ID_APPLE_ALU_REVB_ISO	0x0250
 #define USB_DEVICE_ID_APPLE_ALU_REVB_JIS	0x0251
+#define USB_DEVICE_ID_APPLE_WELLSPRING5A_ANSI	0x0252
+#define USB_DEVICE_ID_APPLE_WELLSPRING5A_ISO	0x0253
+#define USB_DEVICE_ID_APPLE_WELLSPRING5A_JIS	0x0254
 #define USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ANSI  0x0239
 #define USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ISO   0x023a
 #define USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_JIS   0x023b
+#define USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ISO   0x0256
 #define USB_DEVICE_ID_APPLE_FOUNTAIN_TP_ONLY	0x030a
 #define USB_DEVICE_ID_APPLE_GEYSER1_TP_ONLY	0x030b
 #define USB_DEVICE_ID_APPLE_ATV_IRCONTROL	0x8241
@@ -256,7 +266,7 @@
 #define USB_DEVICE_ID_GAMERON_DUAL_PCS_ADAPTOR	0x0002
 
 #define USB_VENDOR_ID_GENERAL_TOUCH	0x0dfc
-#define USB_DEVICE_ID_GENERAL_TOUCH_WIN7_TWOFINGERS 0x0001
+#define USB_DEVICE_ID_GENERAL_TOUCH_WIN7_TWOFINGERS 0x0003
 
 #define USB_VENDOR_ID_GLAB		0x06c2
 #define USB_DEVICE_ID_4_PHIDGETSERVO_30	0x0038
@@ -423,6 +433,9 @@
 #define USB_DEVICE_ID_LD_HYBRID		0x2090
 #define USB_DEVICE_ID_LD_HEATCONTROL	0x20A0
 
+#define USB_VENDOR_ID_LG		0x1fd2
+#define USB_DEVICE_ID_LG_MULTITOUCH	0x0064
+
 #define USB_VENDOR_ID_LOGITECH		0x046d
 #define USB_DEVICE_ID_LOGITECH_RECEIVER	0xc101
 #define USB_DEVICE_ID_LOGITECH_HARMONY_FIRST  0xc110
diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index 58d0e7aaf08..9fc15e1f627 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -672,6 +672,11 @@ static const struct hid_device_id mt_devices[] = {
 		HID_USB_DEVICE(USB_VENDOR_ID_IRTOUCHSYSTEMS,
 			USB_DEVICE_ID_IRTOUCH_INFRARED_USB) },
 
+	/* LG Display panels */
+	{ .driver_data = MT_CLS_DEFAULT,
+		HID_USB_DEVICE(USB_VENDOR_ID_LG,
+			USB_DEVICE_ID_LG_MULTITOUCH) },
+
 	/* Lumio panels */
 	{ .driver_data = MT_CLS_CONFIDENCE_MINUS_ONE,
 		HID_USB_DEVICE(USB_VENDOR_ID_LUMIO,
diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig
index f3472276160..5f1bf12268c 100644
--- a/drivers/hwmon/Kconfig
+++ b/drivers/hwmon/Kconfig
@@ -341,6 +341,16 @@ config SENSORS_DS1621
 	  This driver can also be built as a module.  If so, the module
 	  will be called ds1621.
 
+config SENSORS_EXYNOS4_TMU
+	tristate "Temperature sensor on Samsung EXYNOS4"
+	depends on EXYNOS4_DEV_TMU
+	help
+	  If you say yes here you get support for TMU (Thermal Managment
+	  Unit) on SAMSUNG EXYNOS4 series of SoC.
+
+	  This driver can also be built as a module. If so, the module
+	  will be called exynos4-tmu.
+
 config SENSORS_I5K_AMB
 	tristate "FB-DIMM AMB temperature sensor on Intel 5000 series chipsets"
 	depends on PCI && EXPERIMENTAL
diff --git a/drivers/hwmon/Makefile b/drivers/hwmon/Makefile
index cc0371f7406..439e1ef3924 100644
--- a/drivers/hwmon/Makefile
+++ b/drivers/hwmon/Makefile
@@ -50,6 +50,7 @@ obj-$(CONFIG_SENSORS_DS1621)	+= ds1621.o
 obj-$(CONFIG_SENSORS_EMC1403)	+= emc1403.o
 obj-$(CONFIG_SENSORS_EMC2103)	+= emc2103.o
 obj-$(CONFIG_SENSORS_EMC6W201)	+= emc6w201.o
+obj-$(CONFIG_SENSORS_EXYNOS4_TMU)	+= exynos4_tmu.o
 obj-$(CONFIG_SENSORS_F71805F)	+= f71805f.o
 obj-$(CONFIG_SENSORS_F71882FG)	+= f71882fg.o
 obj-$(CONFIG_SENSORS_F75375S)	+= f75375s.o
diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c
index 93238378664..62800ded941 100644
--- a/drivers/hwmon/coretemp.c
+++ b/drivers/hwmon/coretemp.c
@@ -60,14 +60,13 @@ MODULE_PARM_DESC(tjmax, "TjMax value in degrees Celsius");
 #ifdef CONFIG_SMP
 #define TO_PHYS_ID(cpu)		cpu_data(cpu).phys_proc_id
 #define TO_CORE_ID(cpu)		cpu_data(cpu).cpu_core_id
-#define TO_ATTR_NO(cpu)		(TO_CORE_ID(cpu) + BASE_SYSFS_ATTR_NO)
 #define for_each_sibling(i, cpu)	for_each_cpu(i, cpu_sibling_mask(cpu))
 #else
 #define TO_PHYS_ID(cpu)		(cpu)
 #define TO_CORE_ID(cpu)		(cpu)
-#define TO_ATTR_NO(cpu)		(cpu)
 #define for_each_sibling(i, cpu)	for (i = 0; false; )
 #endif
+#define TO_ATTR_NO(cpu)		(TO_CORE_ID(cpu) + BASE_SYSFS_ATTR_NO)
 
 /*
  * Per-Core Temperature Data
diff --git a/drivers/hwmon/exynos4_tmu.c b/drivers/hwmon/exynos4_tmu.c
new file mode 100644
index 00000000000..0d964b5b37c
--- /dev/null
+++ b/drivers/hwmon/exynos4_tmu.c
@@ -0,0 +1,553 @@
+/*
+ * exynos4_tmu.c - Samsung EXYNOS4 TMU (Thermal Management Unit)
+ *
+ *  Copyright (C) 2011 Samsung Electronics
+ *  Donggeun Kim <dg77.kim@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/platform_device.h>
+#include <linux/interrupt.h>
+#include <linux/clk.h>
+#include <linux/workqueue.h>
+#include <linux/sysfs.h>
+#include <linux/kobject.h>
+#include <linux/io.h>
+#include <linux/mutex.h>
+
+#include <linux/hwmon.h>
+#include <linux/hwmon-sysfs.h>
+
+#include <linux/platform_data/exynos4_tmu.h>
+#ifdef CONFIG_SAMSUNG_THERMAL_INTERFACE
+#include <linux/exynos_thermal.h>
+#endif
+
+#define EXYNOS4_TMU_REG_TRIMINFO	0x0
+#define EXYNOS4_TMU_REG_CONTROL		0x20
+#define EXYNOS4_TMU_REG_STATUS		0x28
+#define EXYNOS4_TMU_REG_CURRENT_TEMP	0x40
+#define EXYNOS4_TMU_REG_THRESHOLD_TEMP	0x44
+#define EXYNOS4_TMU_REG_TRIG_LEVEL0	0x50
+#define EXYNOS4_TMU_REG_TRIG_LEVEL1	0x54
+#define EXYNOS4_TMU_REG_TRIG_LEVEL2	0x58
+#define EXYNOS4_TMU_REG_TRIG_LEVEL3	0x5C
+#define EXYNOS4_TMU_REG_PAST_TEMP0	0x60
+#define EXYNOS4_TMU_REG_PAST_TEMP1	0x64
+#define EXYNOS4_TMU_REG_PAST_TEMP2	0x68
+#define EXYNOS4_TMU_REG_PAST_TEMP3	0x6C
+#define EXYNOS4_TMU_REG_INTEN		0x70
+#define EXYNOS4_TMU_REG_INTSTAT		0x74
+#define EXYNOS4_TMU_REG_INTCLEAR	0x78
+
+#define EXYNOS4_TMU_GAIN_SHIFT		8
+#define EXYNOS4_TMU_REF_VOLTAGE_SHIFT	24
+
+#define EXYNOS4_TMU_TRIM_TEMP_MASK	0xff
+#define EXYNOS4_TMU_CORE_ON	3
+#define EXYNOS4_TMU_CORE_OFF	2
+#define EXYNOS4_TMU_DEF_CODE_TO_TEMP_OFFSET	50
+#define EXYNOS4_TMU_TRIG_LEVEL0_MASK	0x1
+#define EXYNOS4_TMU_TRIG_LEVEL1_MASK	0x10
+#define EXYNOS4_TMU_TRIG_LEVEL2_MASK	0x100
+#define EXYNOS4_TMU_TRIG_LEVEL3_MASK	0x1000
+#define EXYNOS4_TMU_INTCLEAR_VAL	0x1111
+
+struct exynos4_tmu_data {
+	struct exynos4_tmu_platform_data *pdata;
+	struct device *hwmon_dev;
+	struct resource *mem;
+	void __iomem *base;
+	int irq;
+	struct work_struct irq_work;
+	struct mutex lock;
+	struct clk *clk;
+	u8 temp_error1, temp_error2;
+};
+
+/*
+ * TMU treats temperature as a mapped temperature code.
+ * The temperature is converted differently depending on the calibration type.
+ */
+static int temp_to_code(struct exynos4_tmu_data *data, u8 temp)
+{
+	struct exynos4_tmu_platform_data *pdata = data->pdata;
+	int temp_code;
+
+	/* temp should range between 25 and 125 */
+	if (temp < 25 || temp > 125) {
+		temp_code = -EINVAL;
+		goto out;
+	}
+
+	switch (pdata->cal_type) {
+	case TYPE_TWO_POINT_TRIMMING:
+		temp_code = (temp - 25) *
+		    (data->temp_error2 - data->temp_error1) /
+		    (85 - 25) + data->temp_error1;
+		break;
+	case TYPE_ONE_POINT_TRIMMING:
+		temp_code = temp + data->temp_error1 - 25;
+		break;
+	default:
+		temp_code = temp + EXYNOS4_TMU_DEF_CODE_TO_TEMP_OFFSET;
+		break;
+	}
+out:
+	return temp_code;
+}
+
+/*
+ * Calculate a temperature value from a temperature code.
+ * The unit of the temperature is degree Celsius.
+ */
+static int code_to_temp(struct exynos4_tmu_data *data, u8 temp_code)
+{
+	struct exynos4_tmu_platform_data *pdata = data->pdata;
+	int temp;
+
+	/* temp_code should range between 75 and 175 */
+	if (temp_code < 75 || temp_code > 175) {
+		temp = -ENODATA;
+		goto out;
+	}
+
+	switch (pdata->cal_type) {
+	case TYPE_TWO_POINT_TRIMMING:
+		temp = (temp_code - data->temp_error1) * (85 - 25) /
+		    (data->temp_error2 - data->temp_error1) + 25;
+		break;
+	case TYPE_ONE_POINT_TRIMMING:
+		temp = temp_code - data->temp_error1 + 25;
+		break;
+	default:
+		temp = temp_code - EXYNOS4_TMU_DEF_CODE_TO_TEMP_OFFSET;
+		break;
+	}
+out:
+	return temp;
+}
+
+static int exynos4_tmu_initialize(struct platform_device *pdev)
+{
+	struct exynos4_tmu_data *data = platform_get_drvdata(pdev);
+	struct exynos4_tmu_platform_data *pdata = data->pdata;
+	unsigned int status, trim_info;
+	int ret = 0, threshold_code;
+
+	mutex_lock(&data->lock);
+	clk_enable(data->clk);
+
+	status = readb(data->base + EXYNOS4_TMU_REG_STATUS);
+	if (!status) {
+		ret = -EBUSY;
+		goto out;
+	}
+
+	/* Save trimming info in order to perform calibration */
+	trim_info = readl(data->base + EXYNOS4_TMU_REG_TRIMINFO);
+	data->temp_error1 = trim_info & EXYNOS4_TMU_TRIM_TEMP_MASK;
+	data->temp_error2 = ((trim_info >> 8) & EXYNOS4_TMU_TRIM_TEMP_MASK);
+
+	/* Write temperature code for threshold */
+	threshold_code = temp_to_code(data, pdata->threshold);
+	if (threshold_code < 0) {
+		ret = threshold_code;
+		goto out;
+	}
+	writeb(threshold_code,
+		data->base + EXYNOS4_TMU_REG_THRESHOLD_TEMP);
+
+	writeb(pdata->trigger_levels[0],
+		data->base + EXYNOS4_TMU_REG_TRIG_LEVEL0);
+	writeb(pdata->trigger_levels[1],
+		data->base + EXYNOS4_TMU_REG_TRIG_LEVEL1);
+	writeb(pdata->trigger_levels[2],
+		data->base + EXYNOS4_TMU_REG_TRIG_LEVEL2);
+	writeb(pdata->trigger_levels[3],
+		data->base + EXYNOS4_TMU_REG_TRIG_LEVEL3);
+
+	writel(EXYNOS4_TMU_INTCLEAR_VAL,
+		data->base + EXYNOS4_TMU_REG_INTCLEAR);
+out:
+	clk_disable(data->clk);
+	mutex_unlock(&data->lock);
+
+	return ret;
+}
+
+static void exynos4_tmu_control(struct platform_device *pdev, bool on)
+{
+	struct exynos4_tmu_data *data = platform_get_drvdata(pdev);
+	struct exynos4_tmu_platform_data *pdata = data->pdata;
+	unsigned int con, interrupt_en;
+
+	mutex_lock(&data->lock);
+	clk_enable(data->clk);
+
+	con = pdata->reference_voltage << EXYNOS4_TMU_REF_VOLTAGE_SHIFT |
+		pdata->gain << EXYNOS4_TMU_GAIN_SHIFT;
+	if (on) {
+		con |= EXYNOS4_TMU_CORE_ON;
+		interrupt_en = pdata->trigger_level3_en << 12 |
+			pdata->trigger_level2_en << 8 |
+			pdata->trigger_level1_en << 4 |
+			pdata->trigger_level0_en;
+	} else {
+		con |= EXYNOS4_TMU_CORE_OFF;
+		interrupt_en = 0; /* Disable all interrupts */
+	}
+	writel(interrupt_en, data->base + EXYNOS4_TMU_REG_INTEN);
+	writel(con, data->base + EXYNOS4_TMU_REG_CONTROL);
+
+	clk_disable(data->clk);
+	mutex_unlock(&data->lock);
+}
+
+static int exynos4_tmu_read(struct exynos4_tmu_data *data)
+{
+	u8 temp_code;
+	int temp;
+
+	mutex_lock(&data->lock);
+	clk_enable(data->clk);
+
+	temp_code = readb(data->base + EXYNOS4_TMU_REG_CURRENT_TEMP);
+	temp = code_to_temp(data, temp_code);
+
+	clk_disable(data->clk);
+	mutex_unlock(&data->lock);
+
+	return temp;
+}
+
+static void exynos4_tmu_work(struct work_struct *work)
+{
+	struct exynos4_tmu_data *data = container_of(work,
+			struct exynos4_tmu_data, irq_work);
+
+	mutex_lock(&data->lock);
+	clk_enable(data->clk);
+
+	writel(EXYNOS4_TMU_INTCLEAR_VAL, data->base + EXYNOS4_TMU_REG_INTCLEAR);
+
+	kobject_uevent(&data->hwmon_dev->kobj, KOBJ_CHANGE);
+
+
+	clk_disable(data->clk);
+	mutex_unlock(&data->lock);
+#ifdef CONFIG_SAMSUNG_THERMAL_INTERFACE
+	exynos4_report_trigger();
+#endif
+	enable_irq(data->irq);
+}
+
+static irqreturn_t exynos4_tmu_irq(int irq, void *id)
+{
+	struct exynos4_tmu_data *data = id;
+
+	disable_irq_nosync(irq);
+	schedule_work(&data->irq_work);
+
+	return IRQ_HANDLED;
+}
+
+#ifndef CONFIG_SAMSUNG_THERMAL_INTERFACE
+static ssize_t exynos4_tmu_show_name(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "exynos4-tmu\n");
+}
+
+static ssize_t exynos4_tmu_show_temp(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct exynos4_tmu_data *data = dev_get_drvdata(dev);
+	int ret;
+
+	ret = exynos4_tmu_read(data);
+	if (ret < 0)
+		return ret;
+
+	/* convert from degree Celsius to millidegree Celsius */
+	return sprintf(buf, "%d\n", ret * 1000);
+}
+
+static ssize_t exynos4_tmu_show_alarm(struct device *dev,
+		struct device_attribute *devattr, char *buf)
+{
+	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
+	struct exynos4_tmu_data *data = dev_get_drvdata(dev);
+	struct exynos4_tmu_platform_data *pdata = data->pdata;
+	int temp;
+	unsigned int trigger_level;
+
+	temp = exynos4_tmu_read(data);
+	if (temp < 0)
+		return temp;
+
+	trigger_level = pdata->threshold + pdata->trigger_levels[attr->index];
+
+	return sprintf(buf, "%d\n", !!(temp > trigger_level));
+}
+
+static ssize_t exynos4_tmu_show_level(struct device *dev,
+		struct device_attribute *devattr, char *buf)
+{
+	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
+	struct exynos4_tmu_data *data = dev_get_drvdata(dev);
+	struct exynos4_tmu_platform_data *pdata = data->pdata;
+	unsigned int temp = pdata->threshold +
+			pdata->trigger_levels[attr->index];
+
+	return sprintf(buf, "%u\n", temp * 1000);
+}
+
+static DEVICE_ATTR(name, S_IRUGO, exynos4_tmu_show_name, NULL);
+static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO, exynos4_tmu_show_temp, NULL, 0);
+
+static SENSOR_DEVICE_ATTR(temp1_max_alarm, S_IRUGO,
+		exynos4_tmu_show_alarm, NULL, 1);
+static SENSOR_DEVICE_ATTR(temp1_crit_alarm, S_IRUGO,
+		exynos4_tmu_show_alarm, NULL, 2);
+static SENSOR_DEVICE_ATTR(temp1_emergency_alarm, S_IRUGO,
+		exynos4_tmu_show_alarm, NULL, 3);
+
+static SENSOR_DEVICE_ATTR(temp1_max, S_IRUGO, exynos4_tmu_show_level, NULL, 1);
+static SENSOR_DEVICE_ATTR(temp1_crit, S_IRUGO, exynos4_tmu_show_level, NULL, 2);
+static SENSOR_DEVICE_ATTR(temp1_emergency, S_IRUGO,
+		exynos4_tmu_show_level, NULL, 3);
+
+static struct attribute *exynos4_tmu_attributes[] = {
+	&dev_attr_name.attr,
+	&sensor_dev_attr_temp1_input.dev_attr.attr,
+	&sensor_dev_attr_temp1_max_alarm.dev_attr.attr,
+	&sensor_dev_attr_temp1_crit_alarm.dev_attr.attr,
+	&sensor_dev_attr_temp1_emergency_alarm.dev_attr.attr,
+	&sensor_dev_attr_temp1_max.dev_attr.attr,
+	&sensor_dev_attr_temp1_crit.dev_attr.attr,
+	&sensor_dev_attr_temp1_emergency.dev_attr.attr,
+	NULL,
+};
+
+static const struct attribute_group exynos4_tmu_attr_group = {
+	.attrs = exynos4_tmu_attributes,
+};
+#endif
+/*CONFIG_SAMSUNG_THERMAL_INTERFACE*/
+
+#ifdef CONFIG_SAMSUNG_THERMAL_INTERFACE
+static struct thermal_sensor_info exynos4_sensor_info = {
+	.name			= "exynos4-tmu",
+	.read_temperature	= (int (*)(void *))exynos4_tmu_read,
+};
+#endif
+/*CONFIG_SAMSUNG_THERMAL_INTERFACE*/
+
+static int __devinit exynos4_tmu_probe(struct platform_device *pdev)
+{
+	struct exynos4_tmu_data *data;
+	struct exynos4_tmu_platform_data *pdata = pdev->dev.platform_data;
+	int ret;
+
+	if (!pdata) {
+		dev_err(&pdev->dev, "No platform init data supplied.\n");
+		return -ENODEV;
+	}
+
+	data = kzalloc(sizeof(struct exynos4_tmu_data), GFP_KERNEL);
+	if (!data) {
+		dev_err(&pdev->dev, "Failed to allocate driver structure\n");
+		return -ENOMEM;
+	}
+
+	data->irq = platform_get_irq(pdev, 0);
+	if (data->irq < 0) {
+		ret = data->irq;
+		dev_err(&pdev->dev, "Failed to get platform irq\n");
+		goto err_free;
+	}
+
+	INIT_WORK(&data->irq_work, exynos4_tmu_work);
+
+	data->mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!data->mem) {
+		ret = -ENOENT;
+		dev_err(&pdev->dev, "Failed to get platform resource\n");
+		goto err_free;
+	}
+
+	data->mem = request_mem_region(data->mem->start,
+			resource_size(data->mem), pdev->name);
+	if (!data->mem) {
+		ret = -ENODEV;
+		dev_err(&pdev->dev, "Failed to request memory region\n");
+		goto err_free;
+	}
+
+	data->base = ioremap(data->mem->start, resource_size(data->mem));
+	if (!data->base) {
+		ret = -ENODEV;
+		dev_err(&pdev->dev, "Failed to ioremap memory\n");
+		goto err_mem_region;
+	}
+
+	ret = request_irq(data->irq, exynos4_tmu_irq,
+		IRQF_TRIGGER_RISING,
+		"exynos4-tmu", data);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to request irq: %d\n", data->irq);
+		goto err_io_remap;
+	}
+
+	data->clk = clk_get(NULL, "tmu_apbif");
+	if (IS_ERR(data->clk)) {
+		ret = PTR_ERR(data->clk);
+		dev_err(&pdev->dev, "Failed to get clock\n");
+		goto err_irq;
+	}
+
+	data->pdata = pdata;
+	platform_set_drvdata(pdev, data);
+	mutex_init(&data->lock);
+
+	ret = exynos4_tmu_initialize(pdev);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to initialize TMU\n");
+		goto err_clk;
+	}
+
+#ifndef CONFIG_SAMSUNG_THERMAL_INTERFACE
+	ret = sysfs_create_group(&pdev->dev.kobj, &exynos4_tmu_attr_group);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to create sysfs group\n");
+		goto err_clk;
+	}
+#endif
+/*CONFIG_SAMSUNG_THERMAL_INTERFACE*/
+
+	data->hwmon_dev = hwmon_device_register(&pdev->dev);
+	if (IS_ERR(data->hwmon_dev)) {
+		ret = PTR_ERR(data->hwmon_dev);
+		dev_err(&pdev->dev, "Failed to register hwmon device\n");
+		goto err_create_group;
+	}
+
+	exynos4_tmu_control(pdev, true);
+#ifdef CONFIG_SAMSUNG_THERMAL_INTERFACE
+	(&exynos4_sensor_info)->private_data = data;
+	(&exynos4_sensor_info)->sensor_data = pdata;
+	exynos4_register_temp_sensor(&exynos4_sensor_info);
+#endif
+
+	return 0;
+
+err_create_group:
+#ifndef CONFIG_SAMSUNG_THERMAL_INTERFACE
+	sysfs_remove_group(&pdev->dev.kobj, &exynos4_tmu_attr_group);
+#endif
+err_clk:
+	platform_set_drvdata(pdev, NULL);
+	clk_put(data->clk);
+err_irq:
+	free_irq(data->irq, data);
+err_io_remap:
+	iounmap(data->base);
+err_mem_region:
+	release_mem_region(data->mem->start, resource_size(data->mem));
+err_free:
+	kfree(data);
+
+	return ret;
+}
+
+static int __devexit exynos4_tmu_remove(struct platform_device *pdev)
+{
+	struct exynos4_tmu_data *data = platform_get_drvdata(pdev);
+
+	exynos4_tmu_control(pdev, false);
+
+	hwmon_device_unregister(data->hwmon_dev);
+#ifndef CONFIG_SAMSUNG_THERMAL_INTERFACE
+	sysfs_remove_group(&pdev->dev.kobj, &exynos4_tmu_attr_group);
+#endif
+
+	clk_put(data->clk);
+
+	free_irq(data->irq, data);
+
+	iounmap(data->base);
+	release_mem_region(data->mem->start, resource_size(data->mem));
+
+	platform_set_drvdata(pdev, NULL);
+
+	kfree(data);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM
+static int exynos4_tmu_suspend(struct platform_device *pdev, pm_message_t state)
+{
+	exynos4_tmu_control(pdev, false);
+
+	return 0;
+}
+
+static int exynos4_tmu_resume(struct platform_device *pdev)
+{
+	exynos4_tmu_initialize(pdev);
+	exynos4_tmu_control(pdev, true);
+
+	return 0;
+}
+#else
+#define exynos4_tmu_suspend NULL
+#define exynos4_tmu_resume NULL
+#endif
+
+static struct platform_driver exynos4_tmu_driver = {
+	.driver = {
+		.name   = "exynos4-tmu",
+		.owner  = THIS_MODULE,
+	},
+	.probe = exynos4_tmu_probe,
+	.remove	= __devexit_p(exynos4_tmu_remove),
+	.suspend = exynos4_tmu_suspend,
+	.resume = exynos4_tmu_resume,
+};
+
+static int __init exynos4_tmu_driver_init(void)
+{
+	return platform_driver_register(&exynos4_tmu_driver);
+}
+module_init(exynos4_tmu_driver_init);
+
+static void __exit exynos4_tmu_driver_exit(void)
+{
+	platform_driver_unregister(&exynos4_tmu_driver);
+}
+module_exit(exynos4_tmu_driver_exit);
+
+MODULE_DESCRIPTION("EXYNOS4 TMU Driver");
+MODULE_AUTHOR("Donggeun Kim <dg77.kim@samsung.com>");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:exynos4-tmu");
diff --git a/drivers/hwmon/w83627ehf.c b/drivers/hwmon/w83627ehf.c
index 36d7f270b14..4b2fc50c84f 100644
--- a/drivers/hwmon/w83627ehf.c
+++ b/drivers/hwmon/w83627ehf.c
@@ -1756,7 +1756,17 @@ static inline void __devinit w83627ehf_init_device(struct w83627ehf_data *data,
 		diode = 0x70;
 	}
 	for (i = 0; i < 3; i++) {
-		if ((tmp & (0x02 << i)))
+		const char *label = NULL;
+
+		if (data->temp_label)
+			label = data->temp_label[data->temp_src[i]];
+
+		/* Digital source overrides analog type */
+		if (label && strncmp(label, "PECI", 4) == 0)
+			data->temp_type[i] = 6;
+		else if (label && strncmp(label, "AMD", 3) == 0)
+			data->temp_type[i] = 5;
+		else if ((tmp & (0x02 << i)))
 			data->temp_type[i] = (diode & (0x10 << i)) ? 1 : 3;
 		else
 			data->temp_type[i] = 4; /* thermistor */
diff --git a/drivers/hwspinlock/hwspinlock_core.c b/drivers/hwspinlock/hwspinlock_core.c
index 43a62714b4f..12f7c8300c7 100644
--- a/drivers/hwspinlock/hwspinlock_core.c
+++ b/drivers/hwspinlock/hwspinlock_core.c
@@ -26,6 +26,7 @@
 #include <linux/radix-tree.h>
 #include <linux/hwspinlock.h>
 #include <linux/pm_runtime.h>
+#include <linux/mutex.h>
 
 #include "hwspinlock_internal.h"
 
@@ -52,10 +53,12 @@
 static RADIX_TREE(hwspinlock_tree, GFP_KERNEL);
 
 /*
- * Synchronization of access to the tree is achieved using this spinlock,
+ * Synchronization of access to the tree is achieved using this mutex,
  * as the radix-tree API requires that users provide all synchronisation.
+ * A mutex is needed because we're using non-atomic radix tree allocations.
  */
-static DEFINE_SPINLOCK(hwspinlock_tree_lock);
+static DEFINE_MUTEX(hwspinlock_tree_lock);
+
 
 /**
  * __hwspin_trylock() - attempt to lock a specific hwspinlock
@@ -261,8 +264,7 @@ EXPORT_SYMBOL_GPL(__hwspin_unlock);
  * This function should be called from the underlying platform-specific
  * implementation, to register a new hwspinlock instance.
  *
- * Can be called from an atomic context (will not sleep) but not from
- * within interrupt context.
+ * Should be called from a process context (might sleep)
  *
  * Returns 0 on success, or an appropriate error code on failure
  */
@@ -279,7 +281,7 @@ int hwspin_lock_register(struct hwspinlock *hwlock)
 
 	spin_lock_init(&hwlock->lock);
 
-	spin_lock(&hwspinlock_tree_lock);
+	mutex_lock(&hwspinlock_tree_lock);
 
 	ret = radix_tree_insert(&hwspinlock_tree, hwlock->id, hwlock);
 	if (ret)
@@ -293,7 +295,7 @@ int hwspin_lock_register(struct hwspinlock *hwlock)
 	WARN_ON(tmp != hwlock);
 
 out:
-	spin_unlock(&hwspinlock_tree_lock);
+	mutex_unlock(&hwspinlock_tree_lock);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(hwspin_lock_register);
@@ -305,8 +307,7 @@ EXPORT_SYMBOL_GPL(hwspin_lock_register);
  * This function should be called from the underlying platform-specific
  * implementation, to unregister an existing (and unused) hwspinlock.
  *
- * Can be called from an atomic context (will not sleep) but not from
- * within interrupt context.
+ * Should be called from a process context (might sleep)
  *
  * Returns the address of hwspinlock @id on success, or NULL on failure
  */
@@ -315,7 +316,7 @@ struct hwspinlock *hwspin_lock_unregister(unsigned int id)
 	struct hwspinlock *hwlock = NULL;
 	int ret;
 
-	spin_lock(&hwspinlock_tree_lock);
+	mutex_lock(&hwspinlock_tree_lock);
 
 	/* make sure the hwspinlock is not in use (tag is set) */
 	ret = radix_tree_tag_get(&hwspinlock_tree, id, HWSPINLOCK_UNUSED);
@@ -331,7 +332,7 @@ struct hwspinlock *hwspin_lock_unregister(unsigned int id)
 	}
 
 out:
-	spin_unlock(&hwspinlock_tree_lock);
+	mutex_unlock(&hwspinlock_tree_lock);
 	return hwlock;
 }
 EXPORT_SYMBOL_GPL(hwspin_lock_unregister);
@@ -400,9 +401,7 @@ EXPORT_SYMBOL_GPL(hwspin_lock_get_id);
  * to the remote core before it can be used for synchronization (to get the
  * id of a given hwlock, use hwspin_lock_get_id()).
  *
- * Can be called from an atomic context (will not sleep) but not from
- * within interrupt context (simply because there is no use case for
- * that yet).
+ * Should be called from a process context (might sleep)
  *
  * Returns the address of the assigned hwspinlock, or NULL on error
  */
@@ -411,7 +410,7 @@ struct hwspinlock *hwspin_lock_request(void)
 	struct hwspinlock *hwlock;
 	int ret;
 
-	spin_lock(&hwspinlock_tree_lock);
+	mutex_lock(&hwspinlock_tree_lock);
 
 	/* look for an unused lock */
 	ret = radix_tree_gang_lookup_tag(&hwspinlock_tree, (void **)&hwlock,
@@ -431,7 +430,7 @@ struct hwspinlock *hwspin_lock_request(void)
 		hwlock = NULL;
 
 out:
-	spin_unlock(&hwspinlock_tree_lock);
+	mutex_unlock(&hwspinlock_tree_lock);
 	return hwlock;
 }
 EXPORT_SYMBOL_GPL(hwspin_lock_request);
@@ -445,9 +444,7 @@ EXPORT_SYMBOL_GPL(hwspin_lock_request);
  * Usually early board code will be calling this function in order to
  * reserve specific hwspinlock ids for predefined purposes.
  *
- * Can be called from an atomic context (will not sleep) but not from
- * within interrupt context (simply because there is no use case for
- * that yet).
+ * Should be called from a process context (might sleep)
  *
  * Returns the address of the assigned hwspinlock, or NULL on error
  */
@@ -456,7 +453,7 @@ struct hwspinlock *hwspin_lock_request_specific(unsigned int id)
 	struct hwspinlock *hwlock;
 	int ret;
 
-	spin_lock(&hwspinlock_tree_lock);
+	mutex_lock(&hwspinlock_tree_lock);
 
 	/* make sure this hwspinlock exists */
 	hwlock = radix_tree_lookup(&hwspinlock_tree, id);
@@ -482,7 +479,7 @@ struct hwspinlock *hwspin_lock_request_specific(unsigned int id)
 		hwlock = NULL;
 
 out:
-	spin_unlock(&hwspinlock_tree_lock);
+	mutex_unlock(&hwspinlock_tree_lock);
 	return hwlock;
 }
 EXPORT_SYMBOL_GPL(hwspin_lock_request_specific);
@@ -495,9 +492,7 @@ EXPORT_SYMBOL_GPL(hwspin_lock_request_specific);
  * Should only be called with an @hwlock that was retrieved from
  * an earlier call to omap_hwspin_lock_request{_specific}.
  *
- * Can be called from an atomic context (will not sleep) but not from
- * within interrupt context (simply because there is no use case for
- * that yet).
+ * Should be called from a process context (might sleep)
  *
  * Returns 0 on success, or an appropriate error code on failure
  */
@@ -511,7 +506,7 @@ int hwspin_lock_free(struct hwspinlock *hwlock)
 		return -EINVAL;
 	}
 
-	spin_lock(&hwspinlock_tree_lock);
+	mutex_lock(&hwspinlock_tree_lock);
 
 	/* make sure the hwspinlock is used */
 	ret = radix_tree_tag_get(&hwspinlock_tree, hwlock->id,
@@ -538,7 +533,7 @@ int hwspin_lock_free(struct hwspinlock *hwlock)
 	module_put(hwlock->owner);
 
 out:
-	spin_unlock(&hwspinlock_tree_lock);
+	mutex_unlock(&hwspinlock_tree_lock);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(hwspin_lock_free);
diff --git a/drivers/i2c/algos/i2c-algo-bit.c b/drivers/i2c/algos/i2c-algo-bit.c
index d6d58684712..eca3bcc4599 100644
--- a/drivers/i2c/algos/i2c-algo-bit.c
+++ b/drivers/i2c/algos/i2c-algo-bit.c
@@ -486,7 +486,7 @@ static int bit_doAddress(struct i2c_adapter *i2c_adap, struct i2c_msg *msg)
 
 	if (flags & I2C_M_TEN) {
 		/* a ten bit address */
-		addr = 0xf0 | ((msg->addr >> 7) & 0x03);
+		addr = 0xf0 | ((msg->addr >> 7) & 0x06);
 		bit_dbg(2, &i2c_adap->dev, "addr0: %d\n", addr);
 		/* try extended address code...*/
 		ret = try_address(i2c_adap, addr, retries);
@@ -496,7 +496,7 @@ static int bit_doAddress(struct i2c_adapter *i2c_adap, struct i2c_msg *msg)
 			return -EREMOTEIO;
 		}
 		/* the remaining 8 bit address */
-		ret = i2c_outb(i2c_adap, msg->addr & 0x7f);
+		ret = i2c_outb(i2c_adap, msg->addr & 0xff);
 		if ((ret != 1) && !nak_ok) {
 			/* the chip did not ack / xmission error occurred */
 			dev_err(&i2c_adap->dev, "died at 2nd address code\n");
diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index 236ad9a89c0..f2a84c6f854 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -215,7 +215,9 @@ static int addr4_resolve(struct sockaddr_in *src_in,
 
 	neigh = neigh_lookup(&arp_tbl, &rt->rt_gateway, rt->dst.dev);
 	if (!neigh || !(neigh->nud_state & NUD_VALID)) {
+		rcu_read_lock();
 		neigh_event_send(dst_get_neighbour(&rt->dst), NULL);
+		rcu_read_unlock();
 		ret = -ENODATA;
 		if (neigh)
 			goto release;
@@ -273,15 +275,16 @@ static int addr6_resolve(struct sockaddr_in6 *src_in,
 		goto put;
 	}
 
+	rcu_read_lock();
 	neigh = dst_get_neighbour(dst);
 	if (!neigh || !(neigh->nud_state & NUD_VALID)) {
 		if (neigh)
 			neigh_event_send(neigh, NULL);
 		ret = -ENODATA;
-		goto put;
+	} else {
+		ret = rdma_copy_addr(addr, dst->dev, neigh->ha);
 	}
-
-	ret = rdma_copy_addr(addr, dst->dev, neigh->ha);
+	rcu_read_unlock();
 put:
 	dst_release(dst);
 	return ret;
diff --git a/drivers/infiniband/hw/cxgb3/iwch_cm.c b/drivers/infiniband/hw/cxgb3/iwch_cm.c
index 6cd642aaa4d..e55ce7a428b 100644
--- a/drivers/infiniband/hw/cxgb3/iwch_cm.c
+++ b/drivers/infiniband/hw/cxgb3/iwch_cm.c
@@ -1365,8 +1365,10 @@ static int pass_accept_req(struct t3cdev *tdev, struct sk_buff *skb, void *ctx)
 		goto reject;
 	}
 	dst = &rt->dst;
+	rcu_read_lock();
 	neigh = dst_get_neighbour(dst);
 	l2t = t3_l2t_get(tdev, neigh, neigh->dev);
+	rcu_read_unlock();
 	if (!l2t) {
 		printk(KERN_ERR MOD "%s - failed to allocate l2t entry!\n",
 		       __func__);
@@ -1936,10 +1938,12 @@ int iwch_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 	}
 	ep->dst = &rt->dst;
 
+	rcu_read_lock();
 	neigh = dst_get_neighbour(ep->dst);
 
 	/* get a l2t entry */
 	ep->l2t = t3_l2t_get(ep->com.tdev, neigh, neigh->dev);
+	rcu_read_unlock();
 	if (!ep->l2t) {
 		printk(KERN_ERR MOD "%s - cannot alloc l2e.\n", __func__);
 		err = -ENOMEM;
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index 77f769d9227..daa93e942e1 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -1358,6 +1358,7 @@ static int pass_accept_req(struct c4iw_dev *dev, struct sk_buff *skb)
 		goto reject;
 	}
 	dst = &rt->dst;
+	rcu_read_lock();
 	neigh = dst_get_neighbour(dst);
 	if (neigh->dev->flags & IFF_LOOPBACK) {
 		pdev = ip_dev_find(&init_net, peer_ip);
@@ -1384,6 +1385,7 @@ static int pass_accept_req(struct c4iw_dev *dev, struct sk_buff *skb)
 		rss_qid = dev->rdev.lldi.rxq_ids[
 			  cxgb4_port_idx(neigh->dev) * step];
 	}
+	rcu_read_unlock();
 	if (!l2t) {
 		printk(KERN_ERR MOD "%s - failed to allocate l2t entry!\n",
 		       __func__);
@@ -1909,6 +1911,7 @@ int c4iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 	}
 	ep->dst = &rt->dst;
 
+	rcu_read_lock();
 	neigh = dst_get_neighbour(ep->dst);
 
 	/* get a l2t entry */
@@ -1945,6 +1948,7 @@ int c4iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 		ep->rss_qid = ep->com.dev->rdev.lldi.rxq_ids[
 			      cxgb4_port_idx(neigh->dev) * step];
 	}
+	rcu_read_unlock();
 	if (!ep->l2t) {
 		printk(KERN_ERR MOD "%s - cannot alloc l2e.\n", __func__);
 		err = -ENOMEM;
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 3a91d9d8dc5..5c22514b871 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -1309,7 +1309,7 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_send_wr *wr,
 	int is_eth;
 	int is_vlan = 0;
 	int is_grh;
-	u16 vlan;
+	u16 vlan = 0;
 
 	send_size = 0;
 	for (i = 0; i < wr->num_sge; ++i)
diff --git a/drivers/infiniband/hw/nes/nes_cm.c b/drivers/infiniband/hw/nes/nes_cm.c
index c118663e443..a237547330b 100644
--- a/drivers/infiniband/hw/nes/nes_cm.c
+++ b/drivers/infiniband/hw/nes/nes_cm.c
@@ -1150,9 +1150,11 @@ static int nes_addr_resolve_neigh(struct nes_vnic *nesvnic, u32 dst_ip, int arpi
 		neigh_release(neigh);
 	}
 
-	if ((neigh == NULL) || (!(neigh->nud_state & NUD_VALID)))
+	if ((neigh == NULL) || (!(neigh->nud_state & NUD_VALID))) {
+		rcu_read_lock();
 		neigh_event_send(dst_get_neighbour(&rt->dst), NULL);
-
+		rcu_read_unlock();
+	}
 	ip_rt_put(rt);
 	return rc;
 }
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index fe89c4660d5..a98c414978e 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -555,6 +555,7 @@ static int path_rec_start(struct net_device *dev,
 	return 0;
 }
 
+/* called with rcu_read_lock */
 static void neigh_add_path(struct sk_buff *skb, struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
@@ -636,6 +637,7 @@ err_drop:
 	spin_unlock_irqrestore(&priv->lock, flags);
 }
 
+/* called with rcu_read_lock */
 static void ipoib_path_lookup(struct sk_buff *skb, struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(skb->dev);
@@ -720,13 +722,14 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct neighbour *n = NULL;
 	unsigned long flags;
 
+	rcu_read_lock();
 	if (likely(skb_dst(skb)))
 		n = dst_get_neighbour(skb_dst(skb));
 
 	if (likely(n)) {
 		if (unlikely(!*to_ipoib_neigh(n))) {
 			ipoib_path_lookup(skb, dev);
-			return NETDEV_TX_OK;
+			goto unlock;
 		}
 
 		neigh = *to_ipoib_neigh(n);
@@ -749,17 +752,17 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
 			ipoib_neigh_free(dev, neigh);
 			spin_unlock_irqrestore(&priv->lock, flags);
 			ipoib_path_lookup(skb, dev);
-			return NETDEV_TX_OK;
+			goto unlock;
 		}
 
 		if (ipoib_cm_get(neigh)) {
 			if (ipoib_cm_up(neigh)) {
 				ipoib_cm_send(dev, skb, ipoib_cm_get(neigh));
-				return NETDEV_TX_OK;
+				goto unlock;
 			}
 		} else if (neigh->ah) {
 			ipoib_send(dev, skb, neigh->ah, IPOIB_QPN(n->ha));
-			return NETDEV_TX_OK;
+			goto unlock;
 		}
 
 		if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) {
@@ -793,13 +796,14 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
 					   phdr->hwaddr + 4);
 				dev_kfree_skb_any(skb);
 				++dev->stats.tx_dropped;
-				return NETDEV_TX_OK;
+				goto unlock;
 			}
 
 			unicast_arp_send(skb, dev, phdr);
 		}
 	}
-
+unlock:
+	rcu_read_unlock();
 	return NETDEV_TX_OK;
 }
 
@@ -837,7 +841,7 @@ static int ipoib_hard_header(struct sk_buff *skb,
 	dst = skb_dst(skb);
 	n = NULL;
 	if (dst)
-		n = dst_get_neighbour(dst);
+		n = dst_get_neighbour_raw(dst);
 	if ((!dst || !n) && daddr) {
 		struct ipoib_pseudoheader *phdr =
 			(struct ipoib_pseudoheader *) skb_push(skb, sizeof *phdr);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index ecea4fe1ed0..a8d2a891b84 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -265,7 +265,7 @@ static int ipoib_mcast_join_finish(struct ipoib_mcast *mcast,
 
 		skb->dev = dev;
 		if (dst)
-			n = dst_get_neighbour(dst);
+			n = dst_get_neighbour_raw(dst);
 		if (!dst || !n) {
 			/* put pseudoheader back on for next time */
 			skb_push(skb, sizeof (struct ipoib_pseudoheader));
@@ -721,6 +721,8 @@ out:
 	if (mcast && mcast->ah) {
 		struct dst_entry *dst = skb_dst(skb);
 		struct neighbour *n = NULL;
+
+		rcu_read_lock();
 		if (dst)
 			n = dst_get_neighbour(dst);
 		if (n && !*to_ipoib_neigh(n)) {
@@ -733,7 +735,7 @@ out:
 				list_add_tail(&neigh->list, &mcast->neigh_list);
 			}
 		}
-
+		rcu_read_unlock();
 		spin_unlock_irqrestore(&priv->lock, flags);
 		ipoib_send(dev, skb, mcast->ah, IB_MULTICAST_QPN);
 		return;
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 0e4227f457a..cc79045bc52 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -1283,7 +1283,7 @@ static int alloc_new_range(struct dma_ops_domain *dma_dom,
 		if (!pte || !IOMMU_PTE_PRESENT(*pte))
 			continue;
 
-		dma_ops_reserve_addresses(dma_dom, i << PAGE_SHIFT, 1);
+		dma_ops_reserve_addresses(dma_dom, i >> PAGE_SHIFT, 1);
 	}
 
 	update_domain(&dma_dom->domain);
diff --git a/drivers/leds/led-class.c b/drivers/leds/led-class.c
index dc3d3d83191..6d5628bb060 100644
--- a/drivers/leds/led-class.c
+++ b/drivers/leds/led-class.c
@@ -267,6 +267,8 @@ void led_blink_set(struct led_classdev *led_cdev,
 		   unsigned long *delay_on,
 		   unsigned long *delay_off)
 {
+	del_timer_sync(&led_cdev->blink_timer);
+
 	if (led_cdev->blink_set &&
 	    !led_cdev->blink_set(led_cdev, delay_on, delay_off))
 		return;
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 0cd9672cf9c..1d44228530a 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1337,7 +1337,7 @@ static int raid10_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
 		mirror_info_t *p = &conf->mirrors[mirror];
 		if (p->recovery_disabled == mddev->recovery_disabled)
 			continue;
-		if (!p->rdev)
+		if (p->rdev)
 			continue;
 
 		disk_stack_limits(mddev->gendisk, rdev->bdev,
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index ac5e8b57e50..b6200c3935c 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -3069,7 +3069,7 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
 			}
 		} else if (test_bit(In_sync, &rdev->flags))
 			set_bit(R5_Insync, &dev->flags);
-		else {
+		else if (!test_bit(Faulty, &rdev->flags)) {
 			/* in sync if before recovery_offset */
 			if (sh->sector + STRIPE_SECTORS <= rdev->recovery_offset)
 				set_bit(R5_Insync, &dev->flags);
@@ -3116,7 +3116,7 @@ static void handle_stripe(struct stripe_head *sh)
 	struct r5dev *pdev, *qdev;
 
 	clear_bit(STRIPE_HANDLE, &sh->state);
-	if (test_and_set_bit(STRIPE_ACTIVE, &sh->state)) {
+	if (test_and_set_bit_lock(STRIPE_ACTIVE, &sh->state)) {
 		/* already being handled, ensure it gets handled
 		 * again when current action finishes */
 		set_bit(STRIPE_HANDLE, &sh->state);
@@ -3165,10 +3165,14 @@ static void handle_stripe(struct stripe_head *sh)
 	/* check if the array has lost more than max_degraded devices and,
 	 * if so, some requests might need to be failed.
 	 */
-	if (s.failed > conf->max_degraded && s.to_read+s.to_write+s.written)
-		handle_failed_stripe(conf, sh, &s, disks, &s.return_bi);
-	if (s.failed > conf->max_degraded && s.syncing)
-		handle_failed_sync(conf, sh, &s);
+	if (s.failed > conf->max_degraded) {
+		sh->check_state = 0;
+		sh->reconstruct_state = 0;
+		if (s.to_read+s.to_write+s.written)
+			handle_failed_stripe(conf, sh, &s, disks, &s.return_bi);
+		if (s.syncing)
+			handle_failed_sync(conf, sh, &s);
+	}
 
 	/*
 	 * might be able to return some write requests if the parity blocks
@@ -3377,7 +3381,7 @@ finish:
 
 	return_io(s.return_bi);
 
-	clear_bit(STRIPE_ACTIVE, &sh->state);
+	clear_bit_unlock(STRIPE_ACTIVE, &sh->state);
 }
 
 static void raid5_activate_delayed(raid5_conf_t *conf)
diff --git a/drivers/media/dvb/dvb-usb/dib0700_core.c b/drivers/media/dvb/dvb-usb/dib0700_core.c
index 5eb91b4f8fd..a224e94325b 100644
--- a/drivers/media/dvb/dvb-usb/dib0700_core.c
+++ b/drivers/media/dvb/dvb-usb/dib0700_core.c
@@ -30,6 +30,11 @@ int dib0700_get_version(struct dvb_usb_device *d, u32 *hwversion,
 	struct dib0700_state *st = d->priv;
 	int ret;
 
+	if (mutex_lock_interruptible(&d->usb_mutex) < 0) {
+		deb_info("could not acquire lock");
+		return 0;
+	}
+
 	ret = usb_control_msg(d->udev, usb_rcvctrlpipe(d->udev, 0),
 				  REQUEST_GET_VERSION,
 				  USB_TYPE_VENDOR | USB_DIR_IN, 0, 0,
@@ -46,6 +51,7 @@ int dib0700_get_version(struct dvb_usb_device *d, u32 *hwversion,
 	if (fwtype != NULL)
 		*fwtype     = (st->buf[12] << 24) | (st->buf[13] << 16) |
 			(st->buf[14] << 8) | st->buf[15];
+	mutex_unlock(&d->usb_mutex);
 	return ret;
 }
 
@@ -108,7 +114,12 @@ int dib0700_ctrl_rd(struct dvb_usb_device *d, u8 *tx, u8 txlen, u8 *rx, u8 rxlen
 int dib0700_set_gpio(struct dvb_usb_device *d, enum dib07x0_gpios gpio, u8 gpio_dir, u8 gpio_val)
 {
 	struct dib0700_state *st = d->priv;
-	s16 ret;
+	int ret;
+
+	if (mutex_lock_interruptible(&d->usb_mutex) < 0) {
+		deb_info("could not acquire lock");
+		return 0;
+	}
 
 	st->buf[0] = REQUEST_SET_GPIO;
 	st->buf[1] = gpio;
@@ -116,6 +127,7 @@ int dib0700_set_gpio(struct dvb_usb_device *d, enum dib07x0_gpios gpio, u8 gpio_
 
 	ret = dib0700_ctrl_wr(d, st->buf, 3);
 
+	mutex_unlock(&d->usb_mutex);
 	return ret;
 }
 
@@ -125,6 +137,11 @@ static int dib0700_set_usb_xfer_len(struct dvb_usb_device *d, u16 nb_ts_packets)
 	int ret;
 
 	if (st->fw_version >= 0x10201) {
+		if (mutex_lock_interruptible(&d->usb_mutex) < 0) {
+			deb_info("could not acquire lock");
+			return 0;
+		}
+
 		st->buf[0] = REQUEST_SET_USB_XFER_LEN;
 		st->buf[1] = (nb_ts_packets >> 8) & 0xff;
 		st->buf[2] = nb_ts_packets & 0xff;
@@ -132,6 +149,7 @@ static int dib0700_set_usb_xfer_len(struct dvb_usb_device *d, u16 nb_ts_packets)
 		deb_info("set the USB xfer len to %i Ts packet\n", nb_ts_packets);
 
 		ret = dib0700_ctrl_wr(d, st->buf, 3);
+		mutex_unlock(&d->usb_mutex);
 	} else {
 		deb_info("this firmware does not allow to change the USB xfer len\n");
 		ret = -EIO;
@@ -208,6 +226,10 @@ static int dib0700_i2c_xfer_new(struct i2c_adapter *adap, struct i2c_msg *msg,
 
 		} else {
 			/* Write request */
+			if (mutex_lock_interruptible(&d->usb_mutex) < 0) {
+				deb_info("could not acquire lock");
+				return 0;
+			}
 			st->buf[0] = REQUEST_NEW_I2C_WRITE;
 			st->buf[1] = msg[i].addr << 1;
 			st->buf[2] = (en_start << 7) | (en_stop << 6) |
@@ -227,6 +249,7 @@ static int dib0700_i2c_xfer_new(struct i2c_adapter *adap, struct i2c_msg *msg,
 						 USB_TYPE_VENDOR | USB_DIR_OUT,
 						 0, 0, st->buf, msg[i].len + 4,
 						 USB_CTRL_GET_TIMEOUT);
+			mutex_unlock(&d->usb_mutex);
 			if (result < 0) {
 				deb_info("i2c write error (status = %d)\n", result);
 				break;
@@ -249,6 +272,10 @@ static int dib0700_i2c_xfer_legacy(struct i2c_adapter *adap,
 
 	if (mutex_lock_interruptible(&d->i2c_mutex) < 0)
 		return -EAGAIN;
+	if (mutex_lock_interruptible(&d->usb_mutex) < 0) {
+		deb_info("could not acquire lock");
+		return 0;
+	}
 
 	for (i = 0; i < num; i++) {
 		/* fill in the address */
@@ -279,6 +306,7 @@ static int dib0700_i2c_xfer_legacy(struct i2c_adapter *adap,
 				break;
 		}
 	}
+	mutex_unlock(&d->usb_mutex);
 	mutex_unlock(&d->i2c_mutex);
 
 	return i;
@@ -337,7 +365,12 @@ static int dib0700_set_clock(struct dvb_usb_device *d, u8 en_pll,
 	u16 pll_loopdiv, u16 free_div, u16 dsuScaler)
 {
 	struct dib0700_state *st = d->priv;
-	s16 ret;
+	int ret;
+
+	if (mutex_lock_interruptible(&d->usb_mutex) < 0) {
+		deb_info("could not acquire lock");
+		return 0;
+	}
 
 	st->buf[0] = REQUEST_SET_CLOCK;
 	st->buf[1] = (en_pll << 7) | (pll_src << 6) |
@@ -352,6 +385,7 @@ static int dib0700_set_clock(struct dvb_usb_device *d, u8 en_pll,
 	st->buf[9] =  dsuScaler         & 0xff; /* LSB */
 
 	ret = dib0700_ctrl_wr(d, st->buf, 10);
+	mutex_unlock(&d->usb_mutex);
 
 	return ret;
 }
@@ -360,10 +394,16 @@ int dib0700_set_i2c_speed(struct dvb_usb_device *d, u16 scl_kHz)
 {
 	struct dib0700_state *st = d->priv;
 	u16 divider;
+	int ret;
 
 	if (scl_kHz == 0)
 		return -EINVAL;
 
+	if (mutex_lock_interruptible(&d->usb_mutex) < 0) {
+		deb_info("could not acquire lock");
+		return 0;
+	}
+
 	st->buf[0] = REQUEST_SET_I2C_PARAM;
 	divider = (u16) (30000 / scl_kHz);
 	st->buf[1] = 0;
@@ -379,7 +419,11 @@ int dib0700_set_i2c_speed(struct dvb_usb_device *d, u16 scl_kHz)
 	deb_info("setting I2C speed: %04x %04x %04x (%d kHz).",
 		(st->buf[2] << 8) | (st->buf[3]), (st->buf[4] << 8) |
 		st->buf[5], (st->buf[6] << 8) | st->buf[7], scl_kHz);
-	return dib0700_ctrl_wr(d, st->buf, 8);
+
+	ret = dib0700_ctrl_wr(d, st->buf, 8);
+	mutex_unlock(&d->usb_mutex);
+
+	return ret;
 }
 
 
@@ -515,6 +559,11 @@ int dib0700_streaming_ctrl(struct dvb_usb_adapter *adap, int onoff)
 		}
 	}
 
+	if (mutex_lock_interruptible(&adap->dev->usb_mutex) < 0) {
+		deb_info("could not acquire lock");
+		return 0;
+	}
+
 	st->buf[0] = REQUEST_ENABLE_VIDEO;
 	/* this bit gives a kind of command,
 	 * rather than enabling something or not */
@@ -548,7 +597,10 @@ int dib0700_streaming_ctrl(struct dvb_usb_adapter *adap, int onoff)
 
 	deb_info("data for streaming: %x %x\n", st->buf[1], st->buf[2]);
 
-	return dib0700_ctrl_wr(adap->dev, st->buf, 4);
+	ret = dib0700_ctrl_wr(adap->dev, st->buf, 4);
+	mutex_unlock(&adap->dev->usb_mutex);
+
+	return ret;
 }
 
 int dib0700_change_protocol(struct rc_dev *rc, u64 rc_type)
@@ -557,6 +609,11 @@ int dib0700_change_protocol(struct rc_dev *rc, u64 rc_type)
 	struct dib0700_state *st = d->priv;
 	int new_proto, ret;
 
+	if (mutex_lock_interruptible(&d->usb_mutex) < 0) {
+		deb_info("could not acquire lock");
+		return 0;
+	}
+
 	st->buf[0] = REQUEST_SET_RC;
 	st->buf[1] = 0;
 	st->buf[2] = 0;
@@ -567,23 +624,29 @@ int dib0700_change_protocol(struct rc_dev *rc, u64 rc_type)
 	else if (rc_type == RC_TYPE_NEC)
 		new_proto = 0;
 	else if (rc_type == RC_TYPE_RC6) {
-		if (st->fw_version < 0x10200)
-			return -EINVAL;
+		if (st->fw_version < 0x10200) {
+			ret = -EINVAL;
+			goto out;
+		}
 
 		new_proto = 2;
-	} else
-		return -EINVAL;
+	} else {
+		ret = -EINVAL;
+		goto out;
+	}
 
 	st->buf[1] = new_proto;
 
 	ret = dib0700_ctrl_wr(d, st->buf, 3);
 	if (ret < 0) {
 		err("ir protocol setup failed");
-		return ret;
+		goto out;
 	}
 
 	d->props.rc.core.protocol = rc_type;
 
+out:
+	mutex_unlock(&d->usb_mutex);
 	return ret;
 }
 
diff --git a/drivers/media/dvb/frontends/dib0070.c b/drivers/media/dvb/frontends/dib0070.c
index 1d47d4da7d4..dc1cb17a6ea 100644
--- a/drivers/media/dvb/frontends/dib0070.c
+++ b/drivers/media/dvb/frontends/dib0070.c
@@ -27,6 +27,7 @@
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/i2c.h>
+#include <linux/mutex.h>
 
 #include "dvb_frontend.h"
 
@@ -78,10 +79,18 @@ struct dib0070_state {
 	struct i2c_msg msg[2];
 	u8 i2c_write_buffer[3];
 	u8 i2c_read_buffer[2];
+	struct mutex i2c_buffer_lock;
 };
 
-static uint16_t dib0070_read_reg(struct dib0070_state *state, u8 reg)
+static u16 dib0070_read_reg(struct dib0070_state *state, u8 reg)
 {
+	u16 ret;
+
+	if (mutex_lock_interruptible(&state->i2c_buffer_lock) < 0) {
+		dprintk("could not acquire lock");
+		return 0;
+	}
+
 	state->i2c_write_buffer[0] = reg;
 
 	memset(state->msg, 0, 2 * sizeof(struct i2c_msg));
@@ -96,13 +105,23 @@ static uint16_t dib0070_read_reg(struct dib0070_state *state, u8 reg)
 
 	if (i2c_transfer(state->i2c, state->msg, 2) != 2) {
 		printk(KERN_WARNING "DiB0070 I2C read failed\n");
-		return 0;
-	}
-	return (state->i2c_read_buffer[0] << 8) | state->i2c_read_buffer[1];
+		ret = 0;
+	} else
+		ret = (state->i2c_read_buffer[0] << 8)
+			| state->i2c_read_buffer[1];
+
+	mutex_unlock(&state->i2c_buffer_lock);
+	return ret;
 }
 
 static int dib0070_write_reg(struct dib0070_state *state, u8 reg, u16 val)
 {
+	int ret;
+
+	if (mutex_lock_interruptible(&state->i2c_buffer_lock) < 0) {
+		dprintk("could not acquire lock");
+		return -EINVAL;
+	}
 	state->i2c_write_buffer[0] = reg;
 	state->i2c_write_buffer[1] = val >> 8;
 	state->i2c_write_buffer[2] = val & 0xff;
@@ -115,9 +134,12 @@ static int dib0070_write_reg(struct dib0070_state *state, u8 reg, u16 val)
 
 	if (i2c_transfer(state->i2c, state->msg, 1) != 1) {
 		printk(KERN_WARNING "DiB0070 I2C write failed\n");
-		return -EREMOTEIO;
-	}
-	return 0;
+		ret = -EREMOTEIO;
+	} else
+		ret = 0;
+
+	mutex_unlock(&state->i2c_buffer_lock);
+	return ret;
 }
 
 #define HARD_RESET(state) do { \
@@ -734,6 +756,7 @@ struct dvb_frontend *dib0070_attach(struct dvb_frontend *fe, struct i2c_adapter
 	state->cfg = cfg;
 	state->i2c = i2c;
 	state->fe  = fe;
+	mutex_init(&state->i2c_buffer_lock);
 	fe->tuner_priv = state;
 
 	if (dib0070_reset(fe) != 0)
diff --git a/drivers/media/dvb/frontends/dib0090.c b/drivers/media/dvb/frontends/dib0090.c
index c9c935ae41e..b174d1c7858 100644
--- a/drivers/media/dvb/frontends/dib0090.c
+++ b/drivers/media/dvb/frontends/dib0090.c
@@ -27,6 +27,7 @@
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/i2c.h>
+#include <linux/mutex.h>
 
 #include "dvb_frontend.h"
 
@@ -196,6 +197,7 @@ struct dib0090_state {
 	struct i2c_msg msg[2];
 	u8 i2c_write_buffer[3];
 	u8 i2c_read_buffer[2];
+	struct mutex i2c_buffer_lock;
 };
 
 struct dib0090_fw_state {
@@ -208,10 +210,18 @@ struct dib0090_fw_state {
 	struct i2c_msg msg;
 	u8 i2c_write_buffer[2];
 	u8 i2c_read_buffer[2];
+	struct mutex i2c_buffer_lock;
 };
 
 static u16 dib0090_read_reg(struct dib0090_state *state, u8 reg)
 {
+	u16 ret;
+
+	if (mutex_lock_interruptible(&state->i2c_buffer_lock) < 0) {
+		dprintk("could not acquire lock");
+		return 0;
+	}
+
 	state->i2c_write_buffer[0] = reg;
 
 	memset(state->msg, 0, 2 * sizeof(struct i2c_msg));
@@ -226,14 +236,24 @@ static u16 dib0090_read_reg(struct dib0090_state *state, u8 reg)
 
 	if (i2c_transfer(state->i2c, state->msg, 2) != 2) {
 		printk(KERN_WARNING "DiB0090 I2C read failed\n");
-		return 0;
-	}
+		ret = 0;
+	} else
+		ret = (state->i2c_read_buffer[0] << 8)
+			| state->i2c_read_buffer[1];
 
-	return (state->i2c_read_buffer[0] << 8) | state->i2c_read_buffer[1];
+	mutex_unlock(&state->i2c_buffer_lock);
+	return ret;
 }
 
 static int dib0090_write_reg(struct dib0090_state *state, u32 reg, u16 val)
 {
+	int ret;
+
+	if (mutex_lock_interruptible(&state->i2c_buffer_lock) < 0) {
+		dprintk("could not acquire lock");
+		return -EINVAL;
+	}
+
 	state->i2c_write_buffer[0] = reg & 0xff;
 	state->i2c_write_buffer[1] = val >> 8;
 	state->i2c_write_buffer[2] = val & 0xff;
@@ -246,13 +266,23 @@ static int dib0090_write_reg(struct dib0090_state *state, u32 reg, u16 val)
 
 	if (i2c_transfer(state->i2c, state->msg, 1) != 1) {
 		printk(KERN_WARNING "DiB0090 I2C write failed\n");
-		return -EREMOTEIO;
-	}
-	return 0;
+		ret = -EREMOTEIO;
+	} else
+		ret = 0;
+
+	mutex_unlock(&state->i2c_buffer_lock);
+	return ret;
 }
 
 static u16 dib0090_fw_read_reg(struct dib0090_fw_state *state, u8 reg)
 {
+	u16 ret;
+
+	if (mutex_lock_interruptible(&state->i2c_buffer_lock) < 0) {
+		dprintk("could not acquire lock");
+		return 0;
+	}
+
 	state->i2c_write_buffer[0] = reg;
 
 	memset(&state->msg, 0, sizeof(struct i2c_msg));
@@ -262,13 +292,24 @@ static u16 dib0090_fw_read_reg(struct dib0090_fw_state *state, u8 reg)
 	state->msg.len = 2;
 	if (i2c_transfer(state->i2c, &state->msg, 1) != 1) {
 		printk(KERN_WARNING "DiB0090 I2C read failed\n");
-		return 0;
-	}
-	return (state->i2c_read_buffer[0] << 8) | state->i2c_read_buffer[1];
+		ret = 0;
+	} else
+		ret = (state->i2c_read_buffer[0] << 8)
+			| state->i2c_read_buffer[1];
+
+	mutex_unlock(&state->i2c_buffer_lock);
+	return ret;
 }
 
 static int dib0090_fw_write_reg(struct dib0090_fw_state *state, u8 reg, u16 val)
 {
+	int ret;
+
+	if (mutex_lock_interruptible(&state->i2c_buffer_lock) < 0) {
+		dprintk("could not acquire lock");
+		return -EINVAL;
+	}
+
 	state->i2c_write_buffer[0] = val >> 8;
 	state->i2c_write_buffer[1] = val & 0xff;
 
@@ -279,9 +320,12 @@ static int dib0090_fw_write_reg(struct dib0090_fw_state *state, u8 reg, u16 val)
 	state->msg.len = 2;
 	if (i2c_transfer(state->i2c, &state->msg, 1) != 1) {
 		printk(KERN_WARNING "DiB0090 I2C write failed\n");
-		return -EREMOTEIO;
-	}
-	return 0;
+		ret = -EREMOTEIO;
+	} else
+		ret = 0;
+
+	mutex_unlock(&state->i2c_buffer_lock);
+	return ret;
 }
 
 #define HARD_RESET(state) do {  if (cfg->reset) {  if (cfg->sleep) cfg->sleep(fe, 0); msleep(10);  cfg->reset(fe, 1); msleep(10);  cfg->reset(fe, 0); msleep(10);  }  } while (0)
@@ -2440,6 +2484,7 @@ struct dvb_frontend *dib0090_register(struct dvb_frontend *fe, struct i2c_adapte
 	st->config = config;
 	st->i2c = i2c;
 	st->fe = fe;
+	mutex_init(&st->i2c_buffer_lock);
 	fe->tuner_priv = st;
 
 	if (config->wbd == NULL)
@@ -2471,6 +2516,7 @@ struct dvb_frontend *dib0090_fw_register(struct dvb_frontend *fe, struct i2c_ada
 	st->config = config;
 	st->i2c = i2c;
 	st->fe = fe;
+	mutex_init(&st->i2c_buffer_lock);
 	fe->tuner_priv = st;
 
 	if (dib0090_fw_reset_digital(fe, st->config) != 0)
diff --git a/drivers/media/dvb/frontends/dib7000m.c b/drivers/media/dvb/frontends/dib7000m.c
index 79cb1c20df2..dbb76d75c93 100644
--- a/drivers/media/dvb/frontends/dib7000m.c
+++ b/drivers/media/dvb/frontends/dib7000m.c
@@ -11,6 +11,7 @@
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/i2c.h>
+#include <linux/mutex.h>
 
 #include "dvb_frontend.h"
 
@@ -55,6 +56,7 @@ struct dib7000m_state {
 	struct i2c_msg msg[2];
 	u8 i2c_write_buffer[4];
 	u8 i2c_read_buffer[2];
+	struct mutex i2c_buffer_lock;
 };
 
 enum dib7000m_power_mode {
@@ -69,6 +71,13 @@ enum dib7000m_power_mode {
 
 static u16 dib7000m_read_word(struct dib7000m_state *state, u16 reg)
 {
+	u16 ret;
+
+	if (mutex_lock_interruptible(&state->i2c_buffer_lock) < 0) {
+		dprintk("could not acquire lock");
+		return 0;
+	}
+
 	state->i2c_write_buffer[0] = (reg >> 8) | 0x80;
 	state->i2c_write_buffer[1] = reg & 0xff;
 
@@ -85,11 +94,21 @@ static u16 dib7000m_read_word(struct dib7000m_state *state, u16 reg)
 	if (i2c_transfer(state->i2c_adap, state->msg, 2) != 2)
 		dprintk("i2c read error on %d",reg);
 
-	return (state->i2c_read_buffer[0] << 8) | state->i2c_read_buffer[1];
+	ret = (state->i2c_read_buffer[0] << 8) | state->i2c_read_buffer[1];
+	mutex_unlock(&state->i2c_buffer_lock);
+
+	return ret;
 }
 
 static int dib7000m_write_word(struct dib7000m_state *state, u16 reg, u16 val)
 {
+	int ret;
+
+	if (mutex_lock_interruptible(&state->i2c_buffer_lock) < 0) {
+		dprintk("could not acquire lock");
+		return -EINVAL;
+	}
+
 	state->i2c_write_buffer[0] = (reg >> 8) & 0xff;
 	state->i2c_write_buffer[1] = reg & 0xff;
 	state->i2c_write_buffer[2] = (val >> 8) & 0xff;
@@ -101,7 +120,10 @@ static int dib7000m_write_word(struct dib7000m_state *state, u16 reg, u16 val)
 	state->msg[0].buf = state->i2c_write_buffer;
 	state->msg[0].len = 4;
 
-	return i2c_transfer(state->i2c_adap, state->msg, 1) != 1 ? -EREMOTEIO : 0;
+	ret = (i2c_transfer(state->i2c_adap, state->msg, 1) != 1 ?
+			-EREMOTEIO : 0);
+	mutex_unlock(&state->i2c_buffer_lock);
+	return ret;
 }
 static void dib7000m_write_tab(struct dib7000m_state *state, u16 *buf)
 {
@@ -1385,6 +1407,7 @@ struct dvb_frontend * dib7000m_attach(struct i2c_adapter *i2c_adap, u8 i2c_addr,
 	demod                   = &st->demod;
 	demod->demodulator_priv = st;
 	memcpy(&st->demod.ops, &dib7000m_ops, sizeof(struct dvb_frontend_ops));
+	mutex_init(&st->i2c_buffer_lock);
 
 	st->timf_default = cfg->bw->timf;
 
diff --git a/drivers/media/dvb/frontends/dib7000p.c b/drivers/media/dvb/frontends/dib7000p.c
index a64a538ba36..4eb9c2b49cd 100644
--- a/drivers/media/dvb/frontends/dib7000p.c
+++ b/drivers/media/dvb/frontends/dib7000p.c
@@ -10,6 +10,7 @@
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/i2c.h>
+#include <linux/mutex.h>
 
 #include "dvb_math.h"
 #include "dvb_frontend.h"
@@ -68,6 +69,7 @@ struct dib7000p_state {
 	struct i2c_msg msg[2];
 	u8 i2c_write_buffer[4];
 	u8 i2c_read_buffer[2];
+	struct mutex i2c_buffer_lock;
 };
 
 enum dib7000p_power_mode {
@@ -81,6 +83,13 @@ static int dib7090_set_diversity_in(struct dvb_frontend *fe, int onoff);
 
 static u16 dib7000p_read_word(struct dib7000p_state *state, u16 reg)
 {
+	u16 ret;
+
+	if (mutex_lock_interruptible(&state->i2c_buffer_lock) < 0) {
+		dprintk("could not acquire lock");
+		return 0;
+	}
+
 	state->i2c_write_buffer[0] = reg >> 8;
 	state->i2c_write_buffer[1] = reg & 0xff;
 
@@ -97,11 +106,20 @@ static u16 dib7000p_read_word(struct dib7000p_state *state, u16 reg)
 	if (i2c_transfer(state->i2c_adap, state->msg, 2) != 2)
 		dprintk("i2c read error on %d", reg);
 
-	return (state->i2c_read_buffer[0] << 8) | state->i2c_read_buffer[1];
+	ret = (state->i2c_read_buffer[0] << 8) | state->i2c_read_buffer[1];
+	mutex_unlock(&state->i2c_buffer_lock);
+	return ret;
 }
 
 static int dib7000p_write_word(struct dib7000p_state *state, u16 reg, u16 val)
 {
+	int ret;
+
+	if (mutex_lock_interruptible(&state->i2c_buffer_lock) < 0) {
+		dprintk("could not acquire lock");
+		return -EINVAL;
+	}
+
 	state->i2c_write_buffer[0] = (reg >> 8) & 0xff;
 	state->i2c_write_buffer[1] = reg & 0xff;
 	state->i2c_write_buffer[2] = (val >> 8) & 0xff;
@@ -113,7 +131,10 @@ static int dib7000p_write_word(struct dib7000p_state *state, u16 reg, u16 val)
 	state->msg[0].buf = state->i2c_write_buffer;
 	state->msg[0].len = 4;
 
-	return i2c_transfer(state->i2c_adap, state->msg, 1) != 1 ? -EREMOTEIO : 0;
+	ret = (i2c_transfer(state->i2c_adap, state->msg, 1) != 1 ?
+			-EREMOTEIO : 0);
+	mutex_unlock(&state->i2c_buffer_lock);
+	return ret;
 }
 
 static void dib7000p_write_tab(struct dib7000p_state *state, u16 * buf)
@@ -1646,6 +1667,7 @@ int dib7000p_i2c_enumeration(struct i2c_adapter *i2c, int no_of_demods, u8 defau
 		return -ENOMEM;
 
 	dpst->i2c_adap = i2c;
+	mutex_init(&dpst->i2c_buffer_lock);
 
 	for (k = no_of_demods - 1; k >= 0; k--) {
 		dpst->cfg = cfg[k];
@@ -2324,6 +2346,7 @@ struct dvb_frontend *dib7000p_attach(struct i2c_adapter *i2c_adap, u8 i2c_addr,
 	demod = &st->demod;
 	demod->demodulator_priv = st;
 	memcpy(&st->demod.ops, &dib7000p_ops, sizeof(struct dvb_frontend_ops));
+	mutex_init(&st->i2c_buffer_lock);
 
 	dib7000p_write_word(st, 1287, 0x0003);	/* sram lead in, rdy */
 
@@ -2333,8 +2356,9 @@ struct dvb_frontend *dib7000p_attach(struct i2c_adapter *i2c_adap, u8 i2c_addr,
 	st->version = dib7000p_read_word(st, 897);
 
 	/* FIXME: make sure the dev.parent field is initialized, or else
-		request_firmware() will hit an OOPS (this should be moved somewhere
-		more common) */
+	   request_firmware() will hit an OOPS (this should be moved somewhere
+	   more common) */
+	st->i2c_master.gated_tuner_i2c_adap.dev.parent = i2c_adap->dev.parent;
 
 	/* FIXME: make sure the dev.parent field is initialized, or else
 	   request_firmware() will hit an OOPS (this should be moved somewhere
diff --git a/drivers/media/dvb/frontends/dib8000.c b/drivers/media/dvb/frontends/dib8000.c
index 7d2ea112ae2..fe284d5292f 100644
--- a/drivers/media/dvb/frontends/dib8000.c
+++ b/drivers/media/dvb/frontends/dib8000.c
@@ -10,6 +10,8 @@
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/i2c.h>
+#include <linux/mutex.h>
+
 #include "dvb_math.h"
 
 #include "dvb_frontend.h"
@@ -37,6 +39,7 @@ struct i2c_device {
 	u8 addr;
 	u8 *i2c_write_buffer;
 	u8 *i2c_read_buffer;
+	struct mutex *i2c_buffer_lock;
 };
 
 struct dib8000_state {
@@ -77,6 +80,7 @@ struct dib8000_state {
 	struct i2c_msg msg[2];
 	u8 i2c_write_buffer[4];
 	u8 i2c_read_buffer[2];
+	struct mutex i2c_buffer_lock;
 };
 
 enum dib8000_power_mode {
@@ -86,24 +90,39 @@ enum dib8000_power_mode {
 
 static u16 dib8000_i2c_read16(struct i2c_device *i2c, u16 reg)
 {
+	u16 ret;
 	struct i2c_msg msg[2] = {
-		{.addr = i2c->addr >> 1, .flags = 0,
-			.buf = i2c->i2c_write_buffer, .len = 2},
-		{.addr = i2c->addr >> 1, .flags = I2C_M_RD,
-			.buf = i2c->i2c_read_buffer, .len = 2},
+		{.addr = i2c->addr >> 1, .flags = 0, .len = 2},
+		{.addr = i2c->addr >> 1, .flags = I2C_M_RD, .len = 2},
 	};
 
+	if (mutex_lock_interruptible(i2c->i2c_buffer_lock) < 0) {
+		dprintk("could not acquire lock");
+		return 0;
+	}
+
+	msg[0].buf    = i2c->i2c_write_buffer;
 	msg[0].buf[0] = reg >> 8;
 	msg[0].buf[1] = reg & 0xff;
+	msg[1].buf    = i2c->i2c_read_buffer;
 
 	if (i2c_transfer(i2c->adap, msg, 2) != 2)
 		dprintk("i2c read error on %d", reg);
 
-	return (msg[1].buf[0] << 8) | msg[1].buf[1];
+	ret = (msg[1].buf[0] << 8) | msg[1].buf[1];
+	mutex_unlock(i2c->i2c_buffer_lock);
+	return ret;
 }
 
 static u16 dib8000_read_word(struct dib8000_state *state, u16 reg)
 {
+	u16 ret;
+
+	if (mutex_lock_interruptible(&state->i2c_buffer_lock) < 0) {
+		dprintk("could not acquire lock");
+		return 0;
+	}
+
 	state->i2c_write_buffer[0] = reg >> 8;
 	state->i2c_write_buffer[1] = reg & 0xff;
 
@@ -120,7 +139,10 @@ static u16 dib8000_read_word(struct dib8000_state *state, u16 reg)
 	if (i2c_transfer(state->i2c.adap, state->msg, 2) != 2)
 		dprintk("i2c read error on %d", reg);
 
-	return (state->i2c_read_buffer[0] << 8) | state->i2c_read_buffer[1];
+	ret = (state->i2c_read_buffer[0] << 8) | state->i2c_read_buffer[1];
+	mutex_unlock(&state->i2c_buffer_lock);
+
+	return ret;
 }
 
 static u32 dib8000_read32(struct dib8000_state *state, u16 reg)
@@ -135,22 +157,35 @@ static u32 dib8000_read32(struct dib8000_state *state, u16 reg)
 
 static int dib8000_i2c_write16(struct i2c_device *i2c, u16 reg, u16 val)
 {
-	struct i2c_msg msg = {.addr = i2c->addr >> 1, .flags = 0,
-		.buf = i2c->i2c_write_buffer, .len = 4};
+	struct i2c_msg msg = {.addr = i2c->addr >> 1, .flags = 0, .len = 4};
 	int ret = 0;
 
+	if (mutex_lock_interruptible(i2c->i2c_buffer_lock) < 0) {
+		dprintk("could not acquire lock");
+		return -EINVAL;
+	}
+
+	msg.buf    = i2c->i2c_write_buffer;
 	msg.buf[0] = (reg >> 8) & 0xff;
 	msg.buf[1] = reg & 0xff;
 	msg.buf[2] = (val >> 8) & 0xff;
 	msg.buf[3] = val & 0xff;
 
 	ret = i2c_transfer(i2c->adap, &msg, 1) != 1 ? -EREMOTEIO : 0;
+	mutex_unlock(i2c->i2c_buffer_lock);
 
 	return ret;
 }
 
 static int dib8000_write_word(struct dib8000_state *state, u16 reg, u16 val)
 {
+	int ret;
+
+	if (mutex_lock_interruptible(&state->i2c_buffer_lock) < 0) {
+		dprintk("could not acquire lock");
+		return -EINVAL;
+	}
+
 	state->i2c_write_buffer[0] = (reg >> 8) & 0xff;
 	state->i2c_write_buffer[1] = reg & 0xff;
 	state->i2c_write_buffer[2] = (val >> 8) & 0xff;
@@ -162,7 +197,11 @@ static int dib8000_write_word(struct dib8000_state *state, u16 reg, u16 val)
 	state->msg[0].buf = state->i2c_write_buffer;
 	state->msg[0].len = 4;
 
-	return i2c_transfer(state->i2c.adap, state->msg, 1) != 1 ? -EREMOTEIO : 0;
+	ret = (i2c_transfer(state->i2c.adap, state->msg, 1) != 1 ?
+			-EREMOTEIO : 0);
+	mutex_unlock(&state->i2c_buffer_lock);
+
+	return ret;
 }
 
 static const s16 coeff_2k_sb_1seg_dqpsk[8] = {
@@ -2434,8 +2473,15 @@ int dib8000_i2c_enumeration(struct i2c_adapter *host, int no_of_demods, u8 defau
 	if (!client.i2c_read_buffer) {
 		dprintk("%s: not enough memory", __func__);
 		ret = -ENOMEM;
-		goto error_memory;
+		goto error_memory_read;
+	}
+	client.i2c_buffer_lock = kzalloc(sizeof(struct mutex), GFP_KERNEL);
+	if (!client.i2c_buffer_lock) {
+		dprintk("%s: not enough memory", __func__);
+		ret = -ENOMEM;
+		goto error_memory_lock;
 	}
+	mutex_init(client.i2c_buffer_lock);
 
 	for (k = no_of_demods - 1; k >= 0; k--) {
 		/* designated i2c address */
@@ -2476,8 +2522,10 @@ int dib8000_i2c_enumeration(struct i2c_adapter *host, int no_of_demods, u8 defau
 	}
 
 error:
+	kfree(client.i2c_buffer_lock);
+error_memory_lock:
 	kfree(client.i2c_read_buffer);
-error_memory:
+error_memory_read:
 	kfree(client.i2c_write_buffer);
 
 	return ret;
@@ -2581,6 +2629,8 @@ struct dvb_frontend *dib8000_attach(struct i2c_adapter *i2c_adap, u8 i2c_addr, s
 	state->i2c.addr = i2c_addr;
 	state->i2c.i2c_write_buffer = state->i2c_write_buffer;
 	state->i2c.i2c_read_buffer = state->i2c_read_buffer;
+	mutex_init(&state->i2c_buffer_lock);
+	state->i2c.i2c_buffer_lock = &state->i2c_buffer_lock;
 	state->gpio_val = cfg->gpio_val;
 	state->gpio_dir = cfg->gpio_dir;
 
diff --git a/drivers/media/dvb/frontends/dib9000.c b/drivers/media/dvb/frontends/dib9000.c
index a0855883b5c..b931074a952 100644
--- a/drivers/media/dvb/frontends/dib9000.c
+++ b/drivers/media/dvb/frontends/dib9000.c
@@ -38,6 +38,15 @@ struct i2c_device {
 #define DibInitLock(lock) mutex_init(lock)
 #define DibFreeLock(lock)
 
+struct dib9000_pid_ctrl {
+#define DIB9000_PID_FILTER_CTRL 0
+#define DIB9000_PID_FILTER      1
+	u8 cmd;
+	u8 id;
+	u16 pid;
+	u8 onoff;
+};
+
 struct dib9000_state {
 	struct i2c_device i2c;
 
@@ -99,6 +108,10 @@ struct dib9000_state {
 	struct i2c_msg msg[2];
 	u8 i2c_write_buffer[255];
 	u8 i2c_read_buffer[255];
+	DIB_LOCK demod_lock;
+	u8 get_frontend_internal;
+	struct dib9000_pid_ctrl pid_ctrl[10];
+	s8 pid_ctrl_index; /* -1: empty list; -2: do not use the list */
 };
 
 static const u32 fe_info[44] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
@@ -1743,19 +1756,56 @@ EXPORT_SYMBOL(dib9000_set_gpio);
 int dib9000_fw_pid_filter_ctrl(struct dvb_frontend *fe, u8 onoff)
 {
 	struct dib9000_state *state = fe->demodulator_priv;
-	u16 val = dib9000_read_word(state, 294 + 1) & 0xffef;
+	u16 val;
+	int ret;
+
+	if ((state->pid_ctrl_index != -2) && (state->pid_ctrl_index < 9)) {
+		/* postpone the pid filtering cmd */
+		dprintk("pid filter cmd postpone");
+		state->pid_ctrl_index++;
+		state->pid_ctrl[state->pid_ctrl_index].cmd = DIB9000_PID_FILTER_CTRL;
+		state->pid_ctrl[state->pid_ctrl_index].onoff = onoff;
+		return 0;
+	}
+
+	DibAcquireLock(&state->demod_lock);
+
+	val = dib9000_read_word(state, 294 + 1) & 0xffef;
 	val |= (onoff & 0x1) << 4;
 
 	dprintk("PID filter enabled %d", onoff);
-	return dib9000_write_word(state, 294 + 1, val);
+	ret = dib9000_write_word(state, 294 + 1, val);
+	DibReleaseLock(&state->demod_lock);
+	return ret;
+
 }
 EXPORT_SYMBOL(dib9000_fw_pid_filter_ctrl);
 
 int dib9000_fw_pid_filter(struct dvb_frontend *fe, u8 id, u16 pid, u8 onoff)
 {
 	struct dib9000_state *state = fe->demodulator_priv;
+	int ret;
+
+	if (state->pid_ctrl_index != -2) {
+		/* postpone the pid filtering cmd */
+		dprintk("pid filter postpone");
+		if (state->pid_ctrl_index < 9) {
+			state->pid_ctrl_index++;
+			state->pid_ctrl[state->pid_ctrl_index].cmd = DIB9000_PID_FILTER;
+			state->pid_ctrl[state->pid_ctrl_index].id = id;
+			state->pid_ctrl[state->pid_ctrl_index].pid = pid;
+			state->pid_ctrl[state->pid_ctrl_index].onoff = onoff;
+		} else
+			dprintk("can not add any more pid ctrl cmd");
+		return 0;
+	}
+
+	DibAcquireLock(&state->demod_lock);
 	dprintk("Index %x, PID %d, OnOff %d", id, pid, onoff);
-	return dib9000_write_word(state, 300 + 1 + id, onoff ? (1 << 13) | pid : 0);
+	ret = dib9000_write_word(state, 300 + 1 + id,
+			onoff ? (1 << 13) | pid : 0);
+	DibReleaseLock(&state->demod_lock);
+	return ret;
 }
 EXPORT_SYMBOL(dib9000_fw_pid_filter);
 
@@ -1778,6 +1828,7 @@ static void dib9000_release(struct dvb_frontend *demod)
 	DibFreeLock(&state->platform.risc.mbx_lock);
 	DibFreeLock(&state->platform.risc.mem_lock);
 	DibFreeLock(&state->platform.risc.mem_mbx_lock);
+	DibFreeLock(&state->demod_lock);
 	dibx000_exit_i2c_master(&st->i2c_master);
 
 	i2c_del_adapter(&st->tuner_adap);
@@ -1795,14 +1846,19 @@ static int dib9000_sleep(struct dvb_frontend *fe)
 {
 	struct dib9000_state *state = fe->demodulator_priv;
 	u8 index_frontend;
-	int ret;
+	int ret = 0;
 
+	DibAcquireLock(&state->demod_lock);
 	for (index_frontend = 1; (index_frontend < MAX_NUMBER_OF_FRONTENDS) && (state->fe[index_frontend] != NULL); index_frontend++) {
 		ret = state->fe[index_frontend]->ops.sleep(state->fe[index_frontend]);
 		if (ret < 0)
-			return ret;
+			goto error;
 	}
-	return dib9000_mbx_send(state, OUT_MSG_FE_SLEEP, NULL, 0);
+	ret = dib9000_mbx_send(state, OUT_MSG_FE_SLEEP, NULL, 0);
+
+error:
+	DibReleaseLock(&state->demod_lock);
+	return ret;
 }
 
 static int dib9000_fe_get_tune_settings(struct dvb_frontend *fe, struct dvb_frontend_tune_settings *tune)
@@ -1816,7 +1872,10 @@ static int dib9000_get_frontend(struct dvb_frontend *fe, struct dvb_frontend_par
 	struct dib9000_state *state = fe->demodulator_priv;
 	u8 index_frontend, sub_index_frontend;
 	fe_status_t stat;
-	int ret;
+	int ret = 0;
+
+	if (state->get_frontend_internal == 0)
+		DibAcquireLock(&state->demod_lock);
 
 	for (index_frontend = 1; (index_frontend < MAX_NUMBER_OF_FRONTENDS) && (state->fe[index_frontend] != NULL); index_frontend++) {
 		state->fe[index_frontend]->ops.read_status(state->fe[index_frontend], &stat);
@@ -1846,14 +1905,15 @@ static int dib9000_get_frontend(struct dvb_frontend *fe, struct dvb_frontend_par
 					    state->fe[index_frontend]->dtv_property_cache.rolloff;
 				}
 			}
-			return 0;
+			ret = 0;
+			goto return_value;
 		}
 	}
 
 	/* get the channel from master chip */
 	ret = dib9000_fw_get_channel(fe, fep);
 	if (ret != 0)
-		return ret;
+		goto return_value;
 
 	/* synchronize the cache with the other frontends */
 	for (index_frontend = 1; (index_frontend < MAX_NUMBER_OF_FRONTENDS) && (state->fe[index_frontend] != NULL); index_frontend++) {
@@ -1866,8 +1926,12 @@ static int dib9000_get_frontend(struct dvb_frontend *fe, struct dvb_frontend_par
 		state->fe[index_frontend]->dtv_property_cache.code_rate_LP = fe->dtv_property_cache.code_rate_LP;
 		state->fe[index_frontend]->dtv_property_cache.rolloff = fe->dtv_property_cache.rolloff;
 	}
+	ret = 0;
 
-	return 0;
+return_value:
+	if (state->get_frontend_internal == 0)
+		DibReleaseLock(&state->demod_lock);
+	return ret;
 }
 
 static int dib9000_set_tune_state(struct dvb_frontend *fe, enum frontend_tune_state tune_state)
@@ -1912,6 +1976,10 @@ static int dib9000_set_frontend(struct dvb_frontend *fe, struct dvb_frontend_par
 		dprintk("dib9000: must specify bandwidth ");
 		return 0;
 	}
+
+	state->pid_ctrl_index = -1; /* postpone the pid filtering cmd */
+	DibAcquireLock(&state->demod_lock);
+
 	fe->dtv_property_cache.delivery_system = SYS_DVBT;
 
 	/* set the master status */
@@ -1974,13 +2042,18 @@ static int dib9000_set_frontend(struct dvb_frontend *fe, struct dvb_frontend_par
 	/* check the tune result */
 	if (exit_condition == 1) {	/* tune failed */
 		dprintk("tune failed");
+		DibReleaseLock(&state->demod_lock);
+		/* tune failed; put all the pid filtering cmd to junk */
+		state->pid_ctrl_index = -1;
 		return 0;
 	}
 
 	dprintk("tune success on frontend%i", index_frontend_success);
 
 	/* synchronize all the channel cache */
+	state->get_frontend_internal = 1;
 	dib9000_get_frontend(state->fe[0], fep);
+	state->get_frontend_internal = 0;
 
 	/* retune the other frontends with the found channel */
 	channel_status.status = CHANNEL_STATUS_PARAMETERS_SET;
@@ -2025,6 +2098,28 @@ static int dib9000_set_frontend(struct dvb_frontend *fe, struct dvb_frontend_par
 	/* turn off the diversity for the last frontend */
 	dib9000_fw_set_diversity_in(state->fe[index_frontend - 1], 0);
 
+	DibReleaseLock(&state->demod_lock);
+	if (state->pid_ctrl_index >= 0) {
+		u8 index_pid_filter_cmd;
+		u8 pid_ctrl_index = state->pid_ctrl_index;
+
+		state->pid_ctrl_index = -2;
+		for (index_pid_filter_cmd = 0;
+				index_pid_filter_cmd <= pid_ctrl_index;
+				index_pid_filter_cmd++) {
+			if (state->pid_ctrl[index_pid_filter_cmd].cmd == DIB9000_PID_FILTER_CTRL)
+				dib9000_fw_pid_filter_ctrl(state->fe[0],
+						state->pid_ctrl[index_pid_filter_cmd].onoff);
+			else if (state->pid_ctrl[index_pid_filter_cmd].cmd == DIB9000_PID_FILTER)
+				dib9000_fw_pid_filter(state->fe[0],
+						state->pid_ctrl[index_pid_filter_cmd].id,
+						state->pid_ctrl[index_pid_filter_cmd].pid,
+						state->pid_ctrl[index_pid_filter_cmd].onoff);
+		}
+	}
+	/* do not postpone any more the pid filtering */
+	state->pid_ctrl_index = -2;
+
 	return 0;
 }
 
@@ -2041,6 +2136,7 @@ static int dib9000_read_status(struct dvb_frontend *fe, fe_status_t * stat)
 	u8 index_frontend;
 	u16 lock = 0, lock_slave = 0;
 
+	DibAcquireLock(&state->demod_lock);
 	for (index_frontend = 1; (index_frontend < MAX_NUMBER_OF_FRONTENDS) && (state->fe[index_frontend] != NULL); index_frontend++)
 		lock_slave |= dib9000_read_lock(state->fe[index_frontend]);
 
@@ -2059,6 +2155,8 @@ static int dib9000_read_status(struct dvb_frontend *fe, fe_status_t * stat)
 	if ((lock & 0x0008) || (lock_slave & 0x0008))
 		*stat |= FE_HAS_LOCK;
 
+	DibReleaseLock(&state->demod_lock);
+
 	return 0;
 }
 
@@ -2066,10 +2164,14 @@ static int dib9000_read_ber(struct dvb_frontend *fe, u32 * ber)
 {
 	struct dib9000_state *state = fe->demodulator_priv;
 	u16 *c;
+	int ret = 0;
 
+	DibAcquireLock(&state->demod_lock);
 	DibAcquireLock(&state->platform.risc.mem_mbx_lock);
-	if (dib9000_fw_memmbx_sync(state, FE_SYNC_CHANNEL) < 0)
-		return -EIO;
+	if (dib9000_fw_memmbx_sync(state, FE_SYNC_CHANNEL) < 0) {
+		ret = -EIO;
+		goto error;
+	}
 	dib9000_risc_mem_read(state, FE_MM_R_FE_MONITOR,
 			state->i2c_read_buffer, 16 * 2);
 	DibReleaseLock(&state->platform.risc.mem_mbx_lock);
@@ -2077,7 +2179,10 @@ static int dib9000_read_ber(struct dvb_frontend *fe, u32 * ber)
 	c = (u16 *)state->i2c_read_buffer;
 
 	*ber = c[10] << 16 | c[11];
-	return 0;
+
+error:
+	DibReleaseLock(&state->demod_lock);
+	return ret;
 }
 
 static int dib9000_read_signal_strength(struct dvb_frontend *fe, u16 * strength)
@@ -2086,7 +2191,9 @@ static int dib9000_read_signal_strength(struct dvb_frontend *fe, u16 * strength)
 	u8 index_frontend;
 	u16 *c = (u16 *)state->i2c_read_buffer;
 	u16 val;
+	int ret = 0;
 
+	DibAcquireLock(&state->demod_lock);
 	*strength = 0;
 	for (index_frontend = 1; (index_frontend < MAX_NUMBER_OF_FRONTENDS) && (state->fe[index_frontend] != NULL); index_frontend++) {
 		state->fe[index_frontend]->ops.read_signal_strength(state->fe[index_frontend], &val);
@@ -2097,8 +2204,10 @@ static int dib9000_read_signal_strength(struct dvb_frontend *fe, u16 * strength)
 	}
 
 	DibAcquireLock(&state->platform.risc.mem_mbx_lock);
-	if (dib9000_fw_memmbx_sync(state, FE_SYNC_CHANNEL) < 0)
-		return -EIO;
+	if (dib9000_fw_memmbx_sync(state, FE_SYNC_CHANNEL) < 0) {
+		ret = -EIO;
+		goto error;
+	}
 	dib9000_risc_mem_read(state, FE_MM_R_FE_MONITOR, (u8 *) c, 16 * 2);
 	DibReleaseLock(&state->platform.risc.mem_mbx_lock);
 
@@ -2107,7 +2216,10 @@ static int dib9000_read_signal_strength(struct dvb_frontend *fe, u16 * strength)
 		*strength = 65535;
 	else
 		*strength += val;
-	return 0;
+
+error:
+	DibReleaseLock(&state->demod_lock);
+	return ret;
 }
 
 static u32 dib9000_get_snr(struct dvb_frontend *fe)
@@ -2151,6 +2263,7 @@ static int dib9000_read_snr(struct dvb_frontend *fe, u16 * snr)
 	u8 index_frontend;
 	u32 snr_master;
 
+	DibAcquireLock(&state->demod_lock);
 	snr_master = dib9000_get_snr(fe);
 	for (index_frontend = 1; (index_frontend < MAX_NUMBER_OF_FRONTENDS) && (state->fe[index_frontend] != NULL); index_frontend++)
 		snr_master += dib9000_get_snr(state->fe[index_frontend]);
@@ -2161,6 +2274,8 @@ static int dib9000_read_snr(struct dvb_frontend *fe, u16 * snr)
 	} else
 		*snr = 0;
 
+	DibReleaseLock(&state->demod_lock);
+
 	return 0;
 }
 
@@ -2168,15 +2283,22 @@ static int dib9000_read_unc_blocks(struct dvb_frontend *fe, u32 * unc)
 {
 	struct dib9000_state *state = fe->demodulator_priv;
 	u16 *c = (u16 *)state->i2c_read_buffer;
+	int ret = 0;
 
+	DibAcquireLock(&state->demod_lock);
 	DibAcquireLock(&state->platform.risc.mem_mbx_lock);
-	if (dib9000_fw_memmbx_sync(state, FE_SYNC_CHANNEL) < 0)
-		return -EIO;
+	if (dib9000_fw_memmbx_sync(state, FE_SYNC_CHANNEL) < 0) {
+		ret = -EIO;
+		goto error;
+	}
 	dib9000_risc_mem_read(state, FE_MM_R_FE_MONITOR, (u8 *) c, 16 * 2);
 	DibReleaseLock(&state->platform.risc.mem_mbx_lock);
 
 	*unc = c[12];
-	return 0;
+
+error:
+	DibReleaseLock(&state->demod_lock);
+	return ret;
 }
 
 int dib9000_i2c_enumeration(struct i2c_adapter *i2c, int no_of_demods, u8 default_addr, u8 first_addr)
@@ -2322,6 +2444,10 @@ struct dvb_frontend *dib9000_attach(struct i2c_adapter *i2c_adap, u8 i2c_addr, c
 	DibInitLock(&st->platform.risc.mbx_lock);
 	DibInitLock(&st->platform.risc.mem_lock);
 	DibInitLock(&st->platform.risc.mem_mbx_lock);
+	DibInitLock(&st->demod_lock);
+	st->get_frontend_internal = 0;
+
+	st->pid_ctrl_index = -2;
 
 	st->fe[0] = fe;
 	fe->demodulator_priv = st;
diff --git a/drivers/media/dvb/frontends/dibx000_common.c b/drivers/media/dvb/frontends/dibx000_common.c
index dc5d17a6757..774d507b66c 100644
--- a/drivers/media/dvb/frontends/dibx000_common.c
+++ b/drivers/media/dvb/frontends/dibx000_common.c
@@ -1,4 +1,5 @@
 #include <linux/i2c.h>
+#include <linux/mutex.h>
 
 #include "dibx000_common.h"
 
@@ -10,6 +11,13 @@ MODULE_PARM_DESC(debug, "turn on debugging (default: 0)");
 
 static int dibx000_write_word(struct dibx000_i2c_master *mst, u16 reg, u16 val)
 {
+	int ret;
+
+	if (mutex_lock_interruptible(&mst->i2c_buffer_lock) < 0) {
+		dprintk("could not acquire lock");
+		return -EINVAL;
+	}
+
 	mst->i2c_write_buffer[0] = (reg >> 8) & 0xff;
 	mst->i2c_write_buffer[1] = reg & 0xff;
 	mst->i2c_write_buffer[2] = (val >> 8) & 0xff;
@@ -21,11 +29,21 @@ static int dibx000_write_word(struct dibx000_i2c_master *mst, u16 reg, u16 val)
 	mst->msg[0].buf = mst->i2c_write_buffer;
 	mst->msg[0].len = 4;
 
-	return i2c_transfer(mst->i2c_adap, mst->msg, 1) != 1 ? -EREMOTEIO : 0;
+	ret = i2c_transfer(mst->i2c_adap, mst->msg, 1) != 1 ? -EREMOTEIO : 0;
+	mutex_unlock(&mst->i2c_buffer_lock);
+
+	return ret;
 }
 
 static u16 dibx000_read_word(struct dibx000_i2c_master *mst, u16 reg)
 {
+	u16 ret;
+
+	if (mutex_lock_interruptible(&mst->i2c_buffer_lock) < 0) {
+		dprintk("could not acquire lock");
+		return 0;
+	}
+
 	mst->i2c_write_buffer[0] = reg >> 8;
 	mst->i2c_write_buffer[1] = reg & 0xff;
 
@@ -42,7 +60,10 @@ static u16 dibx000_read_word(struct dibx000_i2c_master *mst, u16 reg)
 	if (i2c_transfer(mst->i2c_adap, mst->msg, 2) != 2)
 		dprintk("i2c read error on %d", reg);
 
-	return (mst->i2c_read_buffer[0] << 8) | mst->i2c_read_buffer[1];
+	ret = (mst->i2c_read_buffer[0] << 8) | mst->i2c_read_buffer[1];
+	mutex_unlock(&mst->i2c_buffer_lock);
+
+	return ret;
 }
 
 static int dibx000_is_i2c_done(struct dibx000_i2c_master *mst)
@@ -257,6 +278,7 @@ static int dibx000_i2c_gated_gpio67_xfer(struct i2c_adapter *i2c_adap,
 					struct i2c_msg msg[], int num)
 {
 	struct dibx000_i2c_master *mst = i2c_get_adapdata(i2c_adap);
+	int ret;
 
 	if (num > 32) {
 		dprintk("%s: too much I2C message to be transmitted (%i).\
@@ -264,10 +286,15 @@ static int dibx000_i2c_gated_gpio67_xfer(struct i2c_adapter *i2c_adap,
 		return -ENOMEM;
 	}
 
-	memset(mst->msg, 0, sizeof(struct i2c_msg) * (2 + num));
-
 	dibx000_i2c_select_interface(mst, DIBX000_I2C_INTERFACE_GPIO_6_7);
 
+	if (mutex_lock_interruptible(&mst->i2c_buffer_lock) < 0) {
+		dprintk("could not acquire lock");
+		return -EINVAL;
+	}
+
+	memset(mst->msg, 0, sizeof(struct i2c_msg) * (2 + num));
+
 	/* open the gate */
 	dibx000_i2c_gate_ctrl(mst, &mst->i2c_write_buffer[0], msg[0].addr, 1);
 	mst->msg[0].addr = mst->i2c_addr;
@@ -282,7 +309,11 @@ static int dibx000_i2c_gated_gpio67_xfer(struct i2c_adapter *i2c_adap,
 	mst->msg[num + 1].buf = &mst->i2c_write_buffer[4];
 	mst->msg[num + 1].len = 4;
 
-	return i2c_transfer(mst->i2c_adap, mst->msg, 2 + num) == 2 + num ? num : -EIO;
+	ret = (i2c_transfer(mst->i2c_adap, mst->msg, 2 + num) == 2 + num ?
+			num : -EIO);
+
+	mutex_unlock(&mst->i2c_buffer_lock);
+	return ret;
 }
 
 static struct i2c_algorithm dibx000_i2c_gated_gpio67_algo = {
@@ -294,6 +325,7 @@ static int dibx000_i2c_gated_tuner_xfer(struct i2c_adapter *i2c_adap,
 					struct i2c_msg msg[], int num)
 {
 	struct dibx000_i2c_master *mst = i2c_get_adapdata(i2c_adap);
+	int ret;
 
 	if (num > 32) {
 		dprintk("%s: too much I2C message to be transmitted (%i).\
@@ -301,10 +333,14 @@ static int dibx000_i2c_gated_tuner_xfer(struct i2c_adapter *i2c_adap,
 		return -ENOMEM;
 	}
 
-	memset(mst->msg, 0, sizeof(struct i2c_msg) * (2 + num));
-
 	dibx000_i2c_select_interface(mst, DIBX000_I2C_INTERFACE_TUNER);
 
+	if (mutex_lock_interruptible(&mst->i2c_buffer_lock) < 0) {
+		dprintk("could not acquire lock");
+		return -EINVAL;
+	}
+	memset(mst->msg, 0, sizeof(struct i2c_msg) * (2 + num));
+
 	/* open the gate */
 	dibx000_i2c_gate_ctrl(mst, &mst->i2c_write_buffer[0], msg[0].addr, 1);
 	mst->msg[0].addr = mst->i2c_addr;
@@ -319,7 +355,10 @@ static int dibx000_i2c_gated_tuner_xfer(struct i2c_adapter *i2c_adap,
 	mst->msg[num + 1].buf = &mst->i2c_write_buffer[4];
 	mst->msg[num + 1].len = 4;
 
-	return i2c_transfer(mst->i2c_adap, mst->msg, 2 + num) == 2 + num ? num : -EIO;
+	ret = (i2c_transfer(mst->i2c_adap, mst->msg, 2 + num) == 2 + num ?
+			num : -EIO);
+	mutex_unlock(&mst->i2c_buffer_lock);
+	return ret;
 }
 
 static struct i2c_algorithm dibx000_i2c_gated_tuner_algo = {
@@ -390,8 +429,18 @@ static int i2c_adapter_init(struct i2c_adapter *i2c_adap,
 int dibx000_init_i2c_master(struct dibx000_i2c_master *mst, u16 device_rev,
 				struct i2c_adapter *i2c_adap, u8 i2c_addr)
 {
-	u8 tx[4];
-	struct i2c_msg m = {.addr = i2c_addr >> 1,.buf = tx,.len = 4 };
+	int ret;
+
+	mutex_init(&mst->i2c_buffer_lock);
+	if (mutex_lock_interruptible(&mst->i2c_buffer_lock) < 0) {
+		dprintk("could not acquire lock");
+		return -EINVAL;
+	}
+	memset(mst->msg, 0, sizeof(struct i2c_msg));
+	mst->msg[0].addr = i2c_addr >> 1;
+	mst->msg[0].flags = 0;
+	mst->msg[0].buf = mst->i2c_write_buffer;
+	mst->msg[0].len = 4;
 
 	mst->device_rev = device_rev;
 	mst->i2c_adap = i2c_adap;
@@ -431,9 +480,12 @@ int dibx000_init_i2c_master(struct dibx000_i2c_master *mst, u16 device_rev,
 				"DiBX000: could not initialize the master i2c_adapter\n");
 
 	/* initialize the i2c-master by closing the gate */
-	dibx000_i2c_gate_ctrl(mst, tx, 0, 0);
+	dibx000_i2c_gate_ctrl(mst, mst->i2c_write_buffer, 0, 0);
+
+	ret = (i2c_transfer(i2c_adap, mst->msg, 1) == 1);
+	mutex_unlock(&mst->i2c_buffer_lock);
 
-	return i2c_transfer(i2c_adap, &m, 1) == 1;
+	return ret;
 }
 
 EXPORT_SYMBOL(dibx000_init_i2c_master);
diff --git a/drivers/media/dvb/frontends/dibx000_common.h b/drivers/media/dvb/frontends/dibx000_common.h
index f031165c045..5e011474be4 100644
--- a/drivers/media/dvb/frontends/dibx000_common.h
+++ b/drivers/media/dvb/frontends/dibx000_common.h
@@ -33,6 +33,7 @@ struct dibx000_i2c_master {
 	struct i2c_msg msg[34];
 	u8 i2c_write_buffer[8];
 	u8 i2c_read_buffer[2];
+	struct mutex i2c_buffer_lock;
 };
 
 extern int dibx000_init_i2c_master(struct dibx000_i2c_master *mst,
diff --git a/drivers/media/video/cx23885/cx23885-dvb.c b/drivers/media/video/cx23885/cx23885-dvb.c
index aa83f07b1b0..bcb45be44bb 100644
--- a/drivers/media/video/cx23885/cx23885-dvb.c
+++ b/drivers/media/video/cx23885/cx23885-dvb.c
@@ -844,7 +844,7 @@ static int dvb_register(struct cx23885_tsport *port)
 			static struct xc2028_ctrl ctl = {
 				.fname   = XC3028L_DEFAULT_FIRMWARE,
 				.max_len = 64,
-				.demod   = 5000,
+				.demod   = XC3028_FE_DIBCOM52,
 				/* This is true for all demods with
 					v36 firmware? */
 				.type    = XC2028_D2633,
diff --git a/drivers/media/video/saa7164/saa7164-cards.c b/drivers/media/video/saa7164/saa7164-cards.c
index 69822a4e727..c71369173fa 100644
--- a/drivers/media/video/saa7164/saa7164-cards.c
+++ b/drivers/media/video/saa7164/saa7164-cards.c
@@ -203,6 +203,66 @@ struct saa7164_board saa7164_boards[] = {
 			.i2c_reg_len	= REGLEN_8bit,
 		} },
 	},
+	[SAA7164_BOARD_HAUPPAUGE_HVR2200_4] = {
+		.name		= "Hauppauge WinTV-HVR2200",
+		.porta		= SAA7164_MPEG_DVB,
+		.portb		= SAA7164_MPEG_DVB,
+		.portc		= SAA7164_MPEG_ENCODER,
+		.portd		= SAA7164_MPEG_ENCODER,
+		.porte		= SAA7164_MPEG_VBI,
+		.portf		= SAA7164_MPEG_VBI,
+		.chiprev	= SAA7164_CHIP_REV3,
+		.unit		= {{
+			.id		= 0x1d,
+			.type		= SAA7164_UNIT_EEPROM,
+			.name		= "4K EEPROM",
+			.i2c_bus_nr	= SAA7164_I2C_BUS_0,
+			.i2c_bus_addr	= 0xa0 >> 1,
+			.i2c_reg_len	= REGLEN_8bit,
+		}, {
+			.id		= 0x04,
+			.type		= SAA7164_UNIT_TUNER,
+			.name		= "TDA18271-1",
+			.i2c_bus_nr	= SAA7164_I2C_BUS_1,
+			.i2c_bus_addr	= 0xc0 >> 1,
+			.i2c_reg_len	= REGLEN_8bit,
+		}, {
+			.id		= 0x05,
+			.type		= SAA7164_UNIT_ANALOG_DEMODULATOR,
+			.name		= "TDA8290-1",
+			.i2c_bus_nr	= SAA7164_I2C_BUS_1,
+			.i2c_bus_addr	= 0x84 >> 1,
+			.i2c_reg_len	= REGLEN_8bit,
+		}, {
+			.id		= 0x1b,
+			.type		= SAA7164_UNIT_TUNER,
+			.name		= "TDA18271-2",
+			.i2c_bus_nr	= SAA7164_I2C_BUS_2,
+			.i2c_bus_addr	= 0xc0 >> 1,
+			.i2c_reg_len	= REGLEN_8bit,
+		}, {
+			.id		= 0x1c,
+			.type		= SAA7164_UNIT_ANALOG_DEMODULATOR,
+			.name		= "TDA8290-2",
+			.i2c_bus_nr	= SAA7164_I2C_BUS_2,
+			.i2c_bus_addr	= 0x84 >> 1,
+			.i2c_reg_len	= REGLEN_8bit,
+		}, {
+			.id		= 0x1e,
+			.type		= SAA7164_UNIT_DIGITAL_DEMODULATOR,
+			.name		= "TDA10048-1",
+			.i2c_bus_nr	= SAA7164_I2C_BUS_1,
+			.i2c_bus_addr	= 0x10 >> 1,
+			.i2c_reg_len	= REGLEN_8bit,
+		}, {
+			.id		= 0x1f,
+			.type		= SAA7164_UNIT_DIGITAL_DEMODULATOR,
+			.name		= "TDA10048-2",
+			.i2c_bus_nr	= SAA7164_I2C_BUS_2,
+			.i2c_bus_addr	= 0x12 >> 1,
+			.i2c_reg_len	= REGLEN_8bit,
+		} },
+	},
 	[SAA7164_BOARD_HAUPPAUGE_HVR2250] = {
 		.name		= "Hauppauge WinTV-HVR2250",
 		.porta		= SAA7164_MPEG_DVB,
@@ -426,6 +486,10 @@ struct saa7164_subid saa7164_subids[] = {
 		.subvendor = 0x0070,
 		.subdevice = 0x8851,
 		.card      = SAA7164_BOARD_HAUPPAUGE_HVR2250_2,
+	}, {
+		.subvendor = 0x0070,
+		.subdevice = 0x8940,
+		.card      = SAA7164_BOARD_HAUPPAUGE_HVR2200_4,
 	},
 };
 const unsigned int saa7164_idcount = ARRAY_SIZE(saa7164_subids);
@@ -469,6 +533,7 @@ void saa7164_gpio_setup(struct saa7164_dev *dev)
 	case SAA7164_BOARD_HAUPPAUGE_HVR2200:
 	case SAA7164_BOARD_HAUPPAUGE_HVR2200_2:
 	case SAA7164_BOARD_HAUPPAUGE_HVR2200_3:
+	case SAA7164_BOARD_HAUPPAUGE_HVR2200_4:
 	case SAA7164_BOARD_HAUPPAUGE_HVR2250:
 	case SAA7164_BOARD_HAUPPAUGE_HVR2250_2:
 	case SAA7164_BOARD_HAUPPAUGE_HVR2250_3:
@@ -549,6 +614,7 @@ void saa7164_card_setup(struct saa7164_dev *dev)
 	case SAA7164_BOARD_HAUPPAUGE_HVR2200:
 	case SAA7164_BOARD_HAUPPAUGE_HVR2200_2:
 	case SAA7164_BOARD_HAUPPAUGE_HVR2200_3:
+	case SAA7164_BOARD_HAUPPAUGE_HVR2200_4:
 	case SAA7164_BOARD_HAUPPAUGE_HVR2250:
 	case SAA7164_BOARD_HAUPPAUGE_HVR2250_2:
 	case SAA7164_BOARD_HAUPPAUGE_HVR2250_3:
diff --git a/drivers/media/video/saa7164/saa7164-dvb.c b/drivers/media/video/saa7164/saa7164-dvb.c
index f65eab63ca8..d3779379197 100644
--- a/drivers/media/video/saa7164/saa7164-dvb.c
+++ b/drivers/media/video/saa7164/saa7164-dvb.c
@@ -475,6 +475,7 @@ int saa7164_dvb_register(struct saa7164_port *port)
 	case SAA7164_BOARD_HAUPPAUGE_HVR2200:
 	case SAA7164_BOARD_HAUPPAUGE_HVR2200_2:
 	case SAA7164_BOARD_HAUPPAUGE_HVR2200_3:
+	case SAA7164_BOARD_HAUPPAUGE_HVR2200_4:
 		i2c_bus = &dev->i2c_bus[port->nr + 1];
 		switch (port->nr) {
 		case 0:
diff --git a/drivers/media/video/saa7164/saa7164.h b/drivers/media/video/saa7164/saa7164.h
index 6678bf1e781..35b64306ba9 100644
--- a/drivers/media/video/saa7164/saa7164.h
+++ b/drivers/media/video/saa7164/saa7164.h
@@ -82,6 +82,7 @@
 #define SAA7164_BOARD_HAUPPAUGE_HVR2200_3	6
 #define SAA7164_BOARD_HAUPPAUGE_HVR2250_2	7
 #define SAA7164_BOARD_HAUPPAUGE_HVR2250_3	8
+#define SAA7164_BOARD_HAUPPAUGE_HVR2200_4	9
 
 #define SAA7164_MAX_UNITS		8
 #define SAA7164_TS_NUMBER_OF_LINES	312
diff --git a/drivers/mfd/twl-core.c b/drivers/mfd/twl-core.c
index 01ecfeee652..b8eef462737 100644
--- a/drivers/mfd/twl-core.c
+++ b/drivers/mfd/twl-core.c
@@ -109,7 +109,7 @@
 #define twl_has_watchdog()        false
 #endif
 
-#if defined(CONFIG_TWL4030_CODEC) || defined(CONFIG_TWL4030_CODEC_MODULE) ||\
+#if defined(CONFIG_MFD_TWL4030_AUDIO) || defined(CONFIG_MFD_TWL4030_AUDIO_MODULE) ||\
 	defined(CONFIG_TWL6040_CORE) || defined(CONFIG_TWL6040_CORE_MODULE)
 #define twl_has_codec()	true
 #else
diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig
index af32071da7b..59d8b33ba3c 100644
--- a/drivers/misc/Kconfig
+++ b/drivers/misc/Kconfig
@@ -495,7 +495,7 @@ config DISPDEV
 	  userspace buffers to be used with the overlay.
 
 config PCH_PHUB
-	tristate "Intel EG20T PCH / OKI SEMICONDUCTOR IOH(ML7213/ML7223) PHUB"
+	tristate "Intel EG20T PCH/LAPIS Semicon IOH(ML7213/ML7223/ML7831) PHUB"
 	depends on PCI
 	help
 	  This driver is for PCH(Platform controller Hub) PHUB(Packet Hub) of
@@ -503,12 +503,13 @@ config PCH_PHUB
 	  processor. The Topcliff has MAC address and Option ROM data in SROM.
 	  This driver can access MAC address and Option ROM data in SROM.
 
-	  This driver also can be used for OKI SEMICONDUCTOR IOH(Input/
-	  Output Hub), ML7213 and ML7223.
-	  ML7213 IOH is for IVI(In-Vehicle Infotainment) use and ML7223 IOH is
-	  for MP(Media Phone) use.
-	  ML7213/ML7223 is companion chip for Intel Atom E6xx series.
-	  ML7213/ML7223 is completely compatible for Intel EG20T PCH.
+	  This driver also can be used for LAPIS Semiconductor's IOH,
+	  ML7213/ML7223/ML7831.
+	  ML7213 which is for IVI(In-Vehicle Infotainment) use.
+	  ML7223 IOH is for MP(Media Phone) use.
+	  ML7831 IOH is for general purpose use.
+	  ML7213/ML7223/ML7831 is companion chip for Intel Atom E6xx series.
+	  ML7213/ML7223/ML7831 is completely compatible for Intel EG20T PCH.
 
 	  To compile this driver as a module, choose M here: the module will
 	  be called pch_phub.
diff --git a/drivers/misc/pch_phub.c b/drivers/misc/pch_phub.c
index 0fd7e77bee2..ba276ba5a82 100644
--- a/drivers/misc/pch_phub.c
+++ b/drivers/misc/pch_phub.c
@@ -73,6 +73,9 @@
 #define PCI_DEVICE_ID_ROHM_ML7223_mPHUB	0x8012 /* for Bus-m */
 #define PCI_DEVICE_ID_ROHM_ML7223_nPHUB	0x8002 /* for Bus-n */
 
+/* Macros for ML7831 */
+#define PCI_DEVICE_ID_ROHM_ML7831_PHUB 0x8801
+
 /* SROM ACCESS Macro */
 #define PCH_WORD_ADDR_MASK (~((1 << 2) - 1))
 
@@ -464,7 +467,7 @@ static int pch_phub_write_gbe_mac_addr(struct pch_phub_reg *chip, u8 *data)
 	int retval;
 	int i;
 
-	if (chip->ioh_type == 1) /* EG20T */
+	if ((chip->ioh_type == 1) || (chip->ioh_type == 5)) /* EG20T or ML7831*/
 		retval = pch_phub_gbe_serial_rom_conf(chip);
 	else	/* ML7223 */
 		retval = pch_phub_gbe_serial_rom_conf_mp(chip);
@@ -757,6 +760,22 @@ static int __devinit pch_phub_probe(struct pci_dev *pdev,
 		chip->pch_opt_rom_start_address =\
 						 PCH_PHUB_ROM_START_ADDR_ML7223;
 		chip->pch_mac_start_address = PCH_PHUB_MAC_START_ADDR_ML7223;
+	} else if (id->driver_data == 5) { /* ML7831 */
+		retval = sysfs_create_file(&pdev->dev.kobj,
+					   &dev_attr_pch_mac.attr);
+		if (retval)
+			goto err_sysfs_create;
+
+		retval = sysfs_create_bin_file(&pdev->dev.kobj, &pch_bin_attr);
+		if (retval)
+			goto exit_bin_attr;
+
+		/* set the prefech value */
+		iowrite32(0x000affaa, chip->pch_phub_base_address + 0x14);
+		/* set the interrupt delay value */
+		iowrite32(0x25, chip->pch_phub_base_address + 0x44);
+		chip->pch_opt_rom_start_address = PCH_PHUB_ROM_START_ADDR_EG20T;
+		chip->pch_mac_start_address = PCH_PHUB_MAC_START_ADDR_EG20T;
 	}
 
 	chip->ioh_type = id->driver_data;
@@ -841,6 +860,7 @@ static struct pci_device_id pch_phub_pcidev_id[] = {
 	{ PCI_VDEVICE(ROHM, PCI_DEVICE_ID_ROHM_ML7213_PHUB), 2,  },
 	{ PCI_VDEVICE(ROHM, PCI_DEVICE_ID_ROHM_ML7223_mPHUB), 3,  },
 	{ PCI_VDEVICE(ROHM, PCI_DEVICE_ID_ROHM_ML7223_nPHUB), 4,  },
+	{ PCI_VDEVICE(ROHM, PCI_DEVICE_ID_ROHM_ML7831_PHUB), 5,  },
 	{ }
 };
 MODULE_DEVICE_TABLE(pci, pch_phub_pcidev_id);
diff --git a/drivers/misc/spear13xx_pcie_gadget.c b/drivers/misc/spear13xx_pcie_gadget.c
index cfbddbef11d..43d073bc1d9 100644
--- a/drivers/misc/spear13xx_pcie_gadget.c
+++ b/drivers/misc/spear13xx_pcie_gadget.c
@@ -903,6 +903,6 @@ static void __exit spear_pcie_gadget_exit(void)
 }
 module_exit(spear_pcie_gadget_exit);
 
-MODULE_ALIAS("pcie-gadget-spear");
+MODULE_ALIAS("platform:pcie-gadget-spear");
 MODULE_AUTHOR("Pratyush Anand");
 MODULE_LICENSE("GPL");
diff --git a/drivers/mtd/mtdchar.c b/drivers/mtd/mtdchar.c
index f1af2228a1b..49e20a49708 100644
--- a/drivers/mtd/mtdchar.c
+++ b/drivers/mtd/mtdchar.c
@@ -320,6 +320,7 @@ static ssize_t mtd_write(struct file *file, const char __user *buf, size_t count
 			ops.mode = MTD_OOB_RAW;
 			ops.datbuf = kbuf;
 			ops.oobbuf = NULL;
+			ops.ooboffs = 0;
 			ops.len = len;
 
 			ret = mtd->write_oob(mtd, *ppos, &ops);
diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c
index a46e9bb847b..86f05f45780 100644
--- a/drivers/mtd/nand/nand_base.c
+++ b/drivers/mtd/nand/nand_base.c
@@ -2097,14 +2097,22 @@ static int nand_write_page(struct mtd_info *mtd, struct nand_chip *chip,
 
 /**
  * nand_fill_oob - [Internal] Transfer client buffer to oob
- * @chip:	nand chip structure
+ * @mtd:	MTD device structure
  * @oob:	oob data buffer
  * @len:	oob data write length
  * @ops:	oob ops structure
  */
-static uint8_t *nand_fill_oob(struct nand_chip *chip, uint8_t *oob, size_t len,
-						struct mtd_oob_ops *ops)
+static uint8_t *nand_fill_oob(struct mtd_info *mtd, uint8_t *oob, size_t len,
+			      struct mtd_oob_ops *ops)
 {
+	struct nand_chip *chip = mtd->priv;
+
+	/*
+	 * Initialise to all 0xFF, to avoid the possibility of left over OOB
+	 * data from a previous OOB read.
+	 */
+	memset(chip->oob_poi, 0xff, mtd->oobsize);
+
 	switch (ops->mode) {
 
 	case MTD_OOB_PLACE:
@@ -2201,10 +2209,6 @@ static int nand_do_write_ops(struct mtd_info *mtd, loff_t to,
 	    (chip->pagebuf << chip->page_shift) < (to + ops->len))
 		chip->pagebuf = -1;
 
-	/* If we're not given explicit OOB data, let it be 0xFF */
-	if (likely(!oob))
-		memset(chip->oob_poi, 0xff, mtd->oobsize);
-
 	/* Don't allow multipage oob writes with offset */
 	if (oob && ops->ooboffs && (ops->ooboffs + ops->ooblen > oobmaxlen))
 		return -EINVAL;
@@ -2226,8 +2230,11 @@ static int nand_do_write_ops(struct mtd_info *mtd, loff_t to,
 
 		if (unlikely(oob)) {
 			size_t len = min(oobwritelen, oobmaxlen);
-			oob = nand_fill_oob(chip, oob, len, ops);
+			oob = nand_fill_oob(mtd, oob, len, ops);
 			oobwritelen -= len;
+		} else {
+			/* We still need to erase leftover OOB data */
+			memset(chip->oob_poi, 0xff, mtd->oobsize);
 		}
 
 		ret = chip->write_page(mtd, chip, wbuf, page, cached,
@@ -2401,10 +2408,8 @@ static int nand_do_write_oob(struct mtd_info *mtd, loff_t to,
 	if (page == chip->pagebuf)
 		chip->pagebuf = -1;
 
-	memset(chip->oob_poi, 0xff, mtd->oobsize);
-	nand_fill_oob(chip, ops->oobbuf, ops->ooblen, ops);
+	nand_fill_oob(mtd, ops->oobbuf, ops->ooblen, ops);
 	status = chip->ecc.write_oob(mtd, chip, page & chip->pagemask);
-	memset(chip->oob_poi, 0xff, mtd->oobsize);
 
 	if (status)
 		return status;
diff --git a/drivers/mtd/nand/pxa3xx_nand.c b/drivers/mtd/nand/pxa3xx_nand.c
index 1fb3b3a8058..30689cc2b3c 100644
--- a/drivers/mtd/nand/pxa3xx_nand.c
+++ b/drivers/mtd/nand/pxa3xx_nand.c
@@ -685,6 +685,8 @@ static int pxa3xx_nand_read_page_hwecc(struct mtd_info *mtd,
 		 * OOB, ignore such double bit errors
 		 */
 		if (is_buf_blank(buf, mtd->writesize))
+			info->retcode = ERR_NONE;
+		else
 			mtd->ecc_stats.failed++;
 	}
 
@@ -813,7 +815,7 @@ static int pxa3xx_nand_detect_config(struct pxa3xx_nand_info *info)
 	info->page_size = ndcr & NDCR_PAGE_SZ ? 2048 : 512;
 	/* set info fields needed to read id */
 	info->read_id_bytes = (info->page_size == 2048) ? 4 : 2;
-	info->reg_ndcr = ndcr;
+	info->reg_ndcr = ndcr & ~NDCR_INT_MASK;
 	info->cmdset = &default_cmdset;
 
 	info->ndtr0cs0 = nand_readl(info, NDTR0CS0);
@@ -882,7 +884,7 @@ static int pxa3xx_nand_scan(struct mtd_info *mtd)
 	struct pxa3xx_nand_info *info = mtd->priv;
 	struct platform_device *pdev = info->pdev;
 	struct pxa3xx_nand_platform_data *pdata = pdev->dev.platform_data;
-	struct nand_flash_dev pxa3xx_flash_ids[2] = { {NULL,}, {NULL,} };
+	struct nand_flash_dev pxa3xx_flash_ids[2], *def = NULL;
 	const struct pxa3xx_nand_flash *f = NULL;
 	struct nand_chip *chip = mtd->priv;
 	uint32_t id = -1;
@@ -942,8 +944,10 @@ static int pxa3xx_nand_scan(struct mtd_info *mtd)
 	pxa3xx_flash_ids[0].erasesize = f->page_size * f->page_per_block;
 	if (f->flash_width == 16)
 		pxa3xx_flash_ids[0].options = NAND_BUSWIDTH_16;
+	pxa3xx_flash_ids[1].name = NULL;
+	def = pxa3xx_flash_ids;
 KEEP_CONFIG:
-	if (nand_scan_ident(mtd, 1, pxa3xx_flash_ids))
+	if (nand_scan_ident(mtd, 1, def))
 		return -ENODEV;
 	/* calculate addressing information */
 	info->col_addr_cycles = (mtd->writesize >= 2048) ? 2 : 1;
@@ -954,9 +958,9 @@ KEEP_CONFIG:
 		info->row_addr_cycles = 2;
 	mtd->name = mtd_names[0];
 	chip->ecc.mode = NAND_ECC_HW;
-	chip->ecc.size = f->page_size;
+	chip->ecc.size = info->page_size;
 
-	chip->options = (f->flash_width == 16) ? NAND_BUSWIDTH_16 : 0;
+	chip->options = (info->reg_ndcr & NDCR_DWIDTH_M) ? NAND_BUSWIDTH_16 : 0;
 	chip->options |= NAND_NO_AUTOINCR;
 	chip->options |= NAND_NO_READRDY;
 
diff --git a/drivers/mtd/redboot.c b/drivers/mtd/redboot.c
index 7a87d07cd79..4938bd0b024 100644
--- a/drivers/mtd/redboot.c
+++ b/drivers/mtd/redboot.c
@@ -297,6 +297,9 @@ static struct mtd_part_parser redboot_parser = {
 	.name = "RedBoot",
 };
 
+/* mtd parsers will request the module by parser name */
+MODULE_ALIAS("RedBoot");
+
 static int __init redboot_parser_init(void)
 {
 	return register_mtd_parser(&redboot_parser);
diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index edd7304773e..dc44b73f907 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -875,6 +875,7 @@ static void dp83640_remove(struct phy_device *phydev)
 	struct dp83640_clock *clock;
 	struct list_head *this, *next;
 	struct dp83640_private *tmp, *dp83640 = phydev->priv;
+	struct sk_buff *skb;
 
 	if (phydev->addr == BROADCAST_ADDR)
 		return;
@@ -882,6 +883,12 @@ static void dp83640_remove(struct phy_device *phydev)
 	enable_status_frames(phydev, false);
 	cancel_work_sync(&dp83640->ts_work);
 
+	while ((skb = skb_dequeue(&dp83640->rx_queue)) != NULL)
+		kfree_skb(skb);
+
+	while ((skb = skb_dequeue(&dp83640->tx_queue)) != NULL)
+		skb_complete_tx_timestamp(skb, NULL);
+
 	clock = dp83640_clock_get(dp83640->clock);
 
 	if (dp83640 == clock->chosen) {
@@ -1060,7 +1067,7 @@ static void dp83640_txtstamp(struct phy_device *phydev,
 	struct dp83640_private *dp83640 = phydev->priv;
 
 	if (!dp83640->hwts_tx_en) {
-		kfree_skb(skb);
+		skb_complete_tx_timestamp(skb, NULL);
 		return;
 	}
 	skb_queue_tail(&dp83640->tx_queue, skb);
diff --git a/drivers/net/rionet.c b/drivers/net/rionet.c
index 3bb13113703..7145714a5ec 100644
--- a/drivers/net/rionet.c
+++ b/drivers/net/rionet.c
@@ -88,8 +88,8 @@ static struct rio_dev **rionet_active;
 #define dev_rionet_capable(dev) \
 	is_rionet_capable(dev->src_ops, dev->dst_ops)
 
-#define RIONET_MAC_MATCH(x)	(*(u32 *)x == 0x00010001)
-#define RIONET_GET_DESTID(x)	(*(u16 *)(x + 4))
+#define RIONET_MAC_MATCH(x)	(!memcmp((x), "\00\01\00\01", 4))
+#define RIONET_GET_DESTID(x)	((*((u8 *)x + 4) << 8) | *((u8 *)x + 5))
 
 static int rionet_rx_clean(struct net_device *ndev)
 {
diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c
index c11a2b8327f..d469004704a 100644
--- a/drivers/net/tg3.c
+++ b/drivers/net/tg3.c
@@ -6029,12 +6029,12 @@ static void tg3_tx_skb_unmap(struct tg3_napi *tnapi, u32 entry, int last)
 
 /* Workaround 4GB and 40-bit hardware DMA bugs. */
 static int tigon3_dma_hwbug_workaround(struct tg3_napi *tnapi,
-				       struct sk_buff *skb,
+				       struct sk_buff **pskb,
 				       u32 *entry, u32 *budget,
 				       u32 base_flags, u32 mss, u32 vlan)
 {
 	struct tg3 *tp = tnapi->tp;
-	struct sk_buff *new_skb;
+	struct sk_buff *new_skb, *skb = *pskb;
 	dma_addr_t new_addr = 0;
 	int ret = 0;
 
@@ -6076,7 +6076,7 @@ static int tigon3_dma_hwbug_workaround(struct tg3_napi *tnapi,
 	}
 
 	dev_kfree_skb(skb);
-
+	*pskb = new_skb;
 	return ret;
 }
 
@@ -6305,7 +6305,7 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		 */
 		entry = tnapi->tx_prod;
 		budget = tg3_tx_avail(tnapi);
-		if (tigon3_dma_hwbug_workaround(tnapi, skb, &entry, &budget,
+		if (tigon3_dma_hwbug_workaround(tnapi, &skb, &entry, &budget,
 						base_flags, mss, vlan))
 			goto out_unlock;
 	}
diff --git a/drivers/net/wireless/ath/ath9k/ani.c b/drivers/net/wireless/ath/ath9k/ani.c
index bfb6481f01f..4e4e7c3dcdd 100644
--- a/drivers/net/wireless/ath/ath9k/ani.c
+++ b/drivers/net/wireless/ath/ath9k/ani.c
@@ -502,9 +502,6 @@ static void ath9k_ani_reset_old(struct ath_hw *ah, bool is_scanning)
 		ath9k_hw_ani_control(ah, ATH9K_ANI_CCK_WEAK_SIGNAL_THR,
 				     ATH9K_ANI_CCK_WEAK_SIG_THR);
 
-		ath9k_hw_setrxfilter(ah, ath9k_hw_getrxfilter(ah) |
-				     ATH9K_RX_FILTER_PHYERR);
-
 		ath9k_ani_restart(ah);
 		return;
 	}
@@ -525,8 +522,6 @@ static void ath9k_ani_reset_old(struct ath_hw *ah, bool is_scanning)
 		ath9k_hw_ani_control(ah, ATH9K_ANI_FIRSTEP_LEVEL,
 				     aniState->firstepLevel);
 
-	ath9k_hw_setrxfilter(ah, ath9k_hw_getrxfilter(ah) &
-			     ~ATH9K_RX_FILTER_PHYERR);
 	ath9k_ani_restart(ah);
 
 	ENABLE_REGWRITE_BUFFER(ah);
diff --git a/drivers/net/wireless/ath/ath9k/ar9003_calib.c b/drivers/net/wireless/ath/ath9k/ar9003_calib.c
index f48051c5009..7c2aaad24ed 100644
--- a/drivers/net/wireless/ath/ath9k/ar9003_calib.c
+++ b/drivers/net/wireless/ath/ath9k/ar9003_calib.c
@@ -643,8 +643,9 @@ static void ar9003_hw_detect_outlier(int *mp_coeff, int nmeasurement,
 			outlier_idx = max_idx;
 		else
 			outlier_idx = min_idx;
+
+		mp_coeff[outlier_idx] = mp_avg;
 	}
-	mp_coeff[outlier_idx] = mp_avg;
 }
 
 static void ar9003_hw_tx_iqcal_load_avg_2_passes(struct ath_hw *ah,
diff --git a/drivers/net/wireless/ath/ath9k/ar9003_mac.c b/drivers/net/wireless/ath/ath9k/ar9003_mac.c
index 8ff0b88a29b..048f6afea19 100644
--- a/drivers/net/wireless/ath/ath9k/ar9003_mac.c
+++ b/drivers/net/wireless/ath/ath9k/ar9003_mac.c
@@ -253,8 +253,6 @@ static int ar9003_hw_proc_txdesc(struct ath_hw *ah, void *ds,
 		return -EIO;
 	}
 
-	if (status & AR_TxOpExceeded)
-		ts->ts_status |= ATH9K_TXERR_XTXOP;
 	ts->ts_rateindex = MS(status, AR_FinalTxIdx);
 	ts->ts_seqnum = MS(status, AR_SeqNum);
 	ts->tid = MS(status, AR_TxTid);
@@ -264,6 +262,8 @@ static int ar9003_hw_proc_txdesc(struct ath_hw *ah, void *ds,
 	ts->ts_status = 0;
 	ts->ts_flags  = 0;
 
+	if (status & AR_TxOpExceeded)
+		ts->ts_status |= ATH9K_TXERR_XTXOP;
 	status = ACCESS_ONCE(ads->status2);
 	ts->ts_rssi_ctl0 = MS(status, AR_TxRSSIAnt00);
 	ts->ts_rssi_ctl1 = MS(status, AR_TxRSSIAnt01);
diff --git a/drivers/net/wireless/ath/ath9k/ar9003_phy.h b/drivers/net/wireless/ath/ath9k/ar9003_phy.h
index 5c590429f12..32ac05f1877 100644
--- a/drivers/net/wireless/ath/ath9k/ar9003_phy.h
+++ b/drivers/net/wireless/ath/ath9k/ar9003_phy.h
@@ -572,12 +572,12 @@
 
 #define AR_PHY_TXGAIN_TABLE      (AR_SM_BASE + 0x300)
 
-#define AR_PHY_TX_IQCAL_CONTROL_1   (AR_SM_BASE + AR_SREV_9485(ah) ? \
-						 0x3c8 : 0x448)
-#define AR_PHY_TX_IQCAL_START       (AR_SM_BASE + AR_SREV_9485(ah) ? \
-						 0x3c4 : 0x440)
-#define AR_PHY_TX_IQCAL_STATUS_B0   (AR_SM_BASE + AR_SREV_9485(ah) ? \
-						 0x3f0 : 0x48c)
+#define AR_PHY_TX_IQCAL_CONTROL_1   (AR_SM_BASE + (AR_SREV_9485(ah) ? \
+						 0x3c8 : 0x448))
+#define AR_PHY_TX_IQCAL_START       (AR_SM_BASE + (AR_SREV_9485(ah) ? \
+						 0x3c4 : 0x440))
+#define AR_PHY_TX_IQCAL_STATUS_B0   (AR_SM_BASE + (AR_SREV_9485(ah) ? \
+						 0x3f0 : 0x48c))
 #define AR_PHY_TX_IQCAL_CORR_COEFF_B0(_i)    (AR_SM_BASE + \
 					     (AR_SREV_9485(ah) ? \
 					      0x3d0 : 0x450) + ((_i) << 2))
diff --git a/drivers/net/wireless/ath/ath9k/ar9485_initvals.h b/drivers/net/wireless/ath/ath9k/ar9485_initvals.h
index 611ea6ce850..d16d029f81a 100644
--- a/drivers/net/wireless/ath/ath9k/ar9485_initvals.h
+++ b/drivers/net/wireless/ath/ath9k/ar9485_initvals.h
@@ -521,7 +521,7 @@ static const u32 ar9485_1_1_radio_postamble[][2] = {
 	{0x000160ac, 0x24611800},
 	{0x000160b0, 0x03284f3e},
 	{0x0001610c, 0x00170000},
-	{0x00016140, 0x10804008},
+	{0x00016140, 0x50804008},
 };
 
 static const u32 ar9485_1_1_mac_postamble[][5] = {
@@ -603,7 +603,7 @@ static const u32 ar9485_1_1_radio_core[][2] = {
 
 static const u32 ar9485_1_1_pcie_phy_pll_on_clkreq_enable_L1[][2] = {
 	/* Addr        allmodes */
-	{0x00018c00, 0x10052e5e},
+	{0x00018c00, 0x18052e5e},
 	{0x00018c04, 0x000801d8},
 	{0x00018c08, 0x0000080c},
 };
@@ -776,7 +776,7 @@ static const u32 ar9485_modes_green_ob_db_tx_gain_1_1[][5] = {
 
 static const u32 ar9485_1_1_pcie_phy_clkreq_disable_L1[][2] = {
 	/* Addr        allmodes */
-	{0x00018c00, 0x10013e5e},
+	{0x00018c00, 0x18013e5e},
 	{0x00018c04, 0x000801d8},
 	{0x00018c08, 0x0000080c},
 };
@@ -882,7 +882,7 @@ static const u32 ar9485_fast_clock_1_1_baseband_postamble[][3] = {
 
 static const u32 ar9485_1_1_pcie_phy_pll_on_clkreq_disable_L1[][2] = {
 	/* Addr        allmodes  */
-	{0x00018c00, 0x10012e5e},
+	{0x00018c00, 0x18012e5e},
 	{0x00018c04, 0x000801d8},
 	{0x00018c08, 0x0000080c},
 };
@@ -1021,7 +1021,7 @@ static const u32 ar9485_common_rx_gain_1_1[][2] = {
 
 static const u32 ar9485_1_1_pcie_phy_clkreq_enable_L1[][2] = {
 	/* Addr        allmodes */
-	{0x00018c00, 0x10053e5e},
+	{0x00018c00, 0x18053e5e},
 	{0x00018c04, 0x000801d8},
 	{0x00018c08, 0x0000080c},
 };
diff --git a/drivers/net/wireless/ath/ath9k/hif_usb.c b/drivers/net/wireless/ath/ath9k/hif_usb.c
index d3f4a59cd45..77c8ded8de5 100644
--- a/drivers/net/wireless/ath/ath9k/hif_usb.c
+++ b/drivers/net/wireless/ath/ath9k/hif_usb.c
@@ -38,6 +38,7 @@ static struct usb_device_id ath9k_hif_usb_ids[] = {
 	{ USB_DEVICE(0x04CA, 0x4605) }, /* Liteon */
 	{ USB_DEVICE(0x040D, 0x3801) }, /* VIA */
 	{ USB_DEVICE(0x0cf3, 0xb003) }, /* Ubiquiti WifiStation Ext */
+	{ USB_DEVICE(0x057c, 0x8403) }, /* AVM FRITZ!WLAN 11N v2 USB */
 
 	{ USB_DEVICE(0x0cf3, 0x7015),
 	  .driver_info = AR9287_USB },  /* Atheros */
diff --git a/drivers/net/wireless/ath/ath9k/hw.c b/drivers/net/wireless/ath/ath9k/hw.c
index 8dcefe74f4c..0be84b1714c 100644
--- a/drivers/net/wireless/ath/ath9k/hw.c
+++ b/drivers/net/wireless/ath/ath9k/hw.c
@@ -2101,6 +2101,10 @@ int ath9k_hw_fill_cap_info(struct ath_hw *ah)
 		pCap->num_gpio_pins = AR9271_NUM_GPIO;
 	else if (AR_DEVID_7010(ah))
 		pCap->num_gpio_pins = AR7010_NUM_GPIO;
+	else if (AR_SREV_9300_20_OR_LATER(ah))
+		pCap->num_gpio_pins = AR9300_NUM_GPIO;
+	else if (AR_SREV_9287_11_OR_LATER(ah))
+		pCap->num_gpio_pins = AR9287_NUM_GPIO;
 	else if (AR_SREV_9285_12_OR_LATER(ah))
 		pCap->num_gpio_pins = AR9285_NUM_GPIO;
 	else if (AR_SREV_9280_20_OR_LATER(ah))
diff --git a/drivers/net/wireless/ath/ath9k/recv.c b/drivers/net/wireless/ath/ath9k/recv.c
index 4c21f8cbdeb..60a3bb2a8af 100644
--- a/drivers/net/wireless/ath/ath9k/recv.c
+++ b/drivers/net/wireless/ath/ath9k/recv.c
@@ -433,12 +433,9 @@ void ath_rx_cleanup(struct ath_softc *sc)
 
 u32 ath_calcrxfilter(struct ath_softc *sc)
 {
-#define	RX_FILTER_PRESERVE (ATH9K_RX_FILTER_PHYERR | ATH9K_RX_FILTER_PHYRADAR)
-
 	u32 rfilt;
 
-	rfilt = (ath9k_hw_getrxfilter(sc->sc_ah) & RX_FILTER_PRESERVE)
-		| ATH9K_RX_FILTER_UCAST | ATH9K_RX_FILTER_BCAST
+	rfilt = ATH9K_RX_FILTER_UCAST | ATH9K_RX_FILTER_BCAST
 		| ATH9K_RX_FILTER_MCAST;
 
 	if (sc->rx.rxfilter & FIF_PROBE_REQ)
diff --git a/drivers/net/wireless/b43/main.c b/drivers/net/wireless/b43/main.c
index e293a7921bf..fdb4df2dd2a 100644
--- a/drivers/net/wireless/b43/main.c
+++ b/drivers/net/wireless/b43/main.c
@@ -2508,6 +2508,13 @@ static int b43_upload_microcode(struct b43_wldev *dev)
 		b43_print_fw_helptext(dev->wl, 1);
 		err = -EOPNOTSUPP;
 		goto error;
+	} else if (fwrev >= 598) {
+		b43err(dev->wl, "YOUR FIRMWARE IS TOO NEW. Support for "
+		       "firmware 598 and up requires kernel 3.2 or newer. You "
+		       "have to install older firmware or upgrade kernel.\n");
+		b43_print_fw_helptext(dev->wl, 1);
+		err = -EOPNOTSUPP;
+		goto error;
 	}
 	dev->fw.rev = fwrev;
 	dev->fw.patch = fwpatch;
diff --git a/drivers/net/wireless/iwlwifi/iwl-agn-rxon.c b/drivers/net/wireless/iwlwifi/iwl-agn-rxon.c
index d42ef1763a7..eabbf1a128e 100644
--- a/drivers/net/wireless/iwlwifi/iwl-agn-rxon.c
+++ b/drivers/net/wireless/iwlwifi/iwl-agn-rxon.c
@@ -295,8 +295,8 @@ static int iwlagn_rxon_connect(struct iwl_priv *priv,
 		return ret;
 	}
 
-	if ((ctx->vif && ctx->vif->type == NL80211_IFTYPE_STATION) &&
-	    priv->cfg->ht_params->smps_mode)
+	if (ctx->vif && ctx->vif->type == NL80211_IFTYPE_STATION &&
+	    priv->cfg->ht_params && priv->cfg->ht_params->smps_mode)
 		ieee80211_request_smps(ctx->vif,
 				       priv->cfg->ht_params->smps_mode);
 
@@ -542,6 +542,24 @@ int iwlagn_commit_rxon(struct iwl_priv *priv, struct iwl_rxon_context *ctx)
 	return 0;
 }
 
+void iwlagn_config_ht40(struct ieee80211_conf *conf,
+	struct iwl_rxon_context *ctx)
+{
+	if (conf_is_ht40_minus(conf)) {
+		ctx->ht.extension_chan_offset =
+			IEEE80211_HT_PARAM_CHA_SEC_BELOW;
+		ctx->ht.is_40mhz = true;
+	} else if (conf_is_ht40_plus(conf)) {
+		ctx->ht.extension_chan_offset =
+			IEEE80211_HT_PARAM_CHA_SEC_ABOVE;
+		ctx->ht.is_40mhz = true;
+	} else {
+		ctx->ht.extension_chan_offset =
+			IEEE80211_HT_PARAM_CHA_SEC_NONE;
+		ctx->ht.is_40mhz = false;
+	}
+}
+
 int iwlagn_mac_config(struct ieee80211_hw *hw, u32 changed)
 {
 	struct iwl_priv *priv = hw->priv;
@@ -600,19 +618,11 @@ int iwlagn_mac_config(struct ieee80211_hw *hw, u32 changed)
 				ctx->ht.enabled = conf_is_ht(conf);
 
 			if (ctx->ht.enabled) {
-				if (conf_is_ht40_minus(conf)) {
-					ctx->ht.extension_chan_offset =
-						IEEE80211_HT_PARAM_CHA_SEC_BELOW;
-					ctx->ht.is_40mhz = true;
-				} else if (conf_is_ht40_plus(conf)) {
-					ctx->ht.extension_chan_offset =
-						IEEE80211_HT_PARAM_CHA_SEC_ABOVE;
-					ctx->ht.is_40mhz = true;
-				} else {
-					ctx->ht.extension_chan_offset =
-						IEEE80211_HT_PARAM_CHA_SEC_NONE;
-					ctx->ht.is_40mhz = false;
-				}
+				/* if HT40 is used, it should not change
+				 * after associated except channel switch */
+				if (iwl_is_associated_ctx(ctx) &&
+				     !ctx->ht.is_40mhz)
+					iwlagn_config_ht40(conf, ctx);
 			} else
 				ctx->ht.is_40mhz = false;
 
diff --git a/drivers/net/wireless/iwlwifi/iwl-agn-sta.c b/drivers/net/wireless/iwlwifi/iwl-agn-sta.c
index 37e624095e4..211a5ad6a4f 100644
--- a/drivers/net/wireless/iwlwifi/iwl-agn-sta.c
+++ b/drivers/net/wireless/iwlwifi/iwl-agn-sta.c
@@ -440,9 +440,6 @@ int iwl_set_dynamic_key(struct iwl_priv *priv,
 
 	switch (keyconf->cipher) {
 	case WLAN_CIPHER_SUITE_TKIP:
-		keyconf->flags |= IEEE80211_KEY_FLAG_GENERATE_MMIC;
-		keyconf->flags |= IEEE80211_KEY_FLAG_GENERATE_IV;
-
 		if (sta)
 			addr = sta->addr;
 		else /* station mode case only */
@@ -455,8 +452,6 @@ int iwl_set_dynamic_key(struct iwl_priv *priv,
 					  seq.tkip.iv32, p1k, CMD_SYNC);
 		break;
 	case WLAN_CIPHER_SUITE_CCMP:
-		keyconf->flags |= IEEE80211_KEY_FLAG_GENERATE_IV;
-		/* fall through */
 	case WLAN_CIPHER_SUITE_WEP40:
 	case WLAN_CIPHER_SUITE_WEP104:
 		ret = iwlagn_send_sta_key(priv, keyconf, sta_id,
diff --git a/drivers/net/wireless/iwlwifi/iwl-agn-ucode.c b/drivers/net/wireless/iwlwifi/iwl-agn-ucode.c
index 56211006a18..a5c5a0accd5 100644
--- a/drivers/net/wireless/iwlwifi/iwl-agn-ucode.c
+++ b/drivers/net/wireless/iwlwifi/iwl-agn-ucode.c
@@ -113,13 +113,8 @@ static int iwlagn_load_section(struct iwl_priv *priv, const char *name,
 		FH_TCSR_TX_CONFIG_REG_VAL_CIRQ_HOST_ENDTFD);
 
 	IWL_DEBUG_FW(priv, "%s uCode section being loaded...\n", name);
-	ret = wait_event_interruptible_timeout(priv->wait_command_queue,
-					priv->ucode_write_complete, 5 * HZ);
-	if (ret == -ERESTARTSYS) {
-		IWL_ERR(priv, "Could not load the %s uCode section due "
-			"to interrupt\n", name);
-		return ret;
-	}
+	ret = wait_event_timeout(priv->wait_command_queue,
+				 priv->ucode_write_complete, 5 * HZ);
 	if (!ret) {
 		IWL_ERR(priv, "Could not load the %s uCode section\n",
 			name);
diff --git a/drivers/net/wireless/iwlwifi/iwl-agn.c b/drivers/net/wireless/iwlwifi/iwl-agn.c
index f9c3cd95d61..f473c019c64 100644
--- a/drivers/net/wireless/iwlwifi/iwl-agn.c
+++ b/drivers/net/wireless/iwlwifi/iwl-agn.c
@@ -2793,6 +2793,17 @@ static int iwlagn_mac_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 		return -EOPNOTSUPP;
 	}
 
+	switch (key->cipher) {
+	case WLAN_CIPHER_SUITE_TKIP:
+		key->flags |= IEEE80211_KEY_FLAG_GENERATE_MMIC;
+		/* fall through */
+	case WLAN_CIPHER_SUITE_CCMP:
+		key->flags |= IEEE80211_KEY_FLAG_GENERATE_IV;
+		break;
+	default:
+		break;
+	}
+
 	/*
 	 * We could program these keys into the hardware as well, but we
 	 * don't expect much multicast traffic in IBSS and having keys
@@ -3075,21 +3086,9 @@ static void iwlagn_mac_channel_switch(struct ieee80211_hw *hw,
 
 	/* Configure HT40 channels */
 	ctx->ht.enabled = conf_is_ht(conf);
-	if (ctx->ht.enabled) {
-		if (conf_is_ht40_minus(conf)) {
-			ctx->ht.extension_chan_offset =
-				IEEE80211_HT_PARAM_CHA_SEC_BELOW;
-			ctx->ht.is_40mhz = true;
-		} else if (conf_is_ht40_plus(conf)) {
-			ctx->ht.extension_chan_offset =
-				IEEE80211_HT_PARAM_CHA_SEC_ABOVE;
-			ctx->ht.is_40mhz = true;
-		} else {
-			ctx->ht.extension_chan_offset =
-				IEEE80211_HT_PARAM_CHA_SEC_NONE;
-			ctx->ht.is_40mhz = false;
-		}
-	} else
+	if (ctx->ht.enabled)
+		iwlagn_config_ht40(conf, ctx);
+	else
 		ctx->ht.is_40mhz = false;
 
 	if ((le16_to_cpu(ctx->staging.channel) != ch))
diff --git a/drivers/net/wireless/iwlwifi/iwl-agn.h b/drivers/net/wireless/iwlwifi/iwl-agn.h
index d941c4c98e4..e172f6baad3 100644
--- a/drivers/net/wireless/iwlwifi/iwl-agn.h
+++ b/drivers/net/wireless/iwlwifi/iwl-agn.h
@@ -135,6 +135,8 @@ void iwlagn_bss_info_changed(struct ieee80211_hw *hw,
 			     struct ieee80211_vif *vif,
 			     struct ieee80211_bss_conf *bss_conf,
 			     u32 changes);
+void iwlagn_config_ht40(struct ieee80211_conf *conf,
+			struct iwl_rxon_context *ctx);
 
 /* uCode */
 void iwlagn_rx_calib_result(struct iwl_priv *priv,
diff --git a/drivers/net/wireless/iwlwifi/iwl-core.c b/drivers/net/wireless/iwlwifi/iwl-core.c
index cf376f62b2f..d652778253a 100644
--- a/drivers/net/wireless/iwlwifi/iwl-core.c
+++ b/drivers/net/wireless/iwlwifi/iwl-core.c
@@ -867,7 +867,7 @@ void iwlagn_fw_error(struct iwl_priv *priv, bool ondemand)
 	 * commands by clearing the ready bit */
 	clear_bit(STATUS_READY, &priv->status);
 
-	wake_up_interruptible(&priv->wait_command_queue);
+	wake_up(&priv->wait_command_queue);
 
 	if (!ondemand) {
 		/*
@@ -918,7 +918,7 @@ void iwl_irq_handle_error(struct iwl_priv *priv)
 		 */
 		clear_bit(STATUS_READY, &priv->status);
 		clear_bit(STATUS_HCMD_ACTIVE, &priv->status);
-		wake_up_interruptible(&priv->wait_command_queue);
+		wake_up(&priv->wait_command_queue);
 		IWL_ERR(priv, "RF is used by WiMAX\n");
 		return;
 	}
diff --git a/drivers/net/wireless/iwlwifi/iwl-pci.c b/drivers/net/wireless/iwlwifi/iwl-pci.c
index 2fdbffa079c..32d64e71861 100644
--- a/drivers/net/wireless/iwlwifi/iwl-pci.c
+++ b/drivers/net/wireless/iwlwifi/iwl-pci.c
@@ -442,10 +442,9 @@ static int iwl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	pci_write_config_byte(pdev, PCI_CFG_RETRY_TIMEOUT, 0x00);
 
 	err = pci_enable_msi(pdev);
-	if (err) {
-		dev_printk(KERN_ERR, &pdev->dev, "pci_enable_msi failed");
-		goto out_iounmap;
-	}
+	if (err)
+		dev_printk(KERN_ERR, &pdev->dev,
+			"pci_enable_msi failed(0X%x)", err);
 
 	/* TODO: Move this away, not needed if not MSI */
 	/* enable rfkill interrupt: hw bug w/a */
@@ -466,7 +465,6 @@ static int iwl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 out_disable_msi:
 	pci_disable_msi(pdev);
-out_iounmap:
 	pci_iounmap(pdev, pci_bus->hw_base);
 out_pci_release_regions:
 	pci_set_drvdata(pdev, NULL);
diff --git a/drivers/net/wireless/iwlwifi/iwl-rx.c b/drivers/net/wireless/iwlwifi/iwl-rx.c
index 8e314003b63..732f01b565d 100644
--- a/drivers/net/wireless/iwlwifi/iwl-rx.c
+++ b/drivers/net/wireless/iwlwifi/iwl-rx.c
@@ -561,7 +561,7 @@ static void iwl_rx_card_state_notif(struct iwl_priv *priv,
 		wiphy_rfkill_set_hw_state(priv->hw->wiphy,
 			test_bit(STATUS_RF_KILL_HW, &priv->status));
 	else
-		wake_up_interruptible(&priv->wait_command_queue);
+		wake_up(&priv->wait_command_queue);
 }
 
 static void iwl_rx_missed_beacon_notif(struct iwl_priv *priv,
diff --git a/drivers/net/wireless/iwlwifi/iwl-trans-rx-pcie.c b/drivers/net/wireless/iwlwifi/iwl-trans-rx-pcie.c
index 47486029040..f9f0df0cecb 100644
--- a/drivers/net/wireless/iwlwifi/iwl-trans-rx-pcie.c
+++ b/drivers/net/wireless/iwlwifi/iwl-trans-rx-pcie.c
@@ -671,7 +671,7 @@ void iwl_irq_tasklet(struct iwl_priv *priv)
 		handled |= CSR_INT_BIT_FH_TX;
 		/* Wake up uCode load routine, now that load is complete */
 		priv->ucode_write_complete = 1;
-		wake_up_interruptible(&priv->wait_command_queue);
+		wake_up(&priv->wait_command_queue);
 	}
 
 	if (inta & ~handled) {
diff --git a/drivers/net/wireless/iwlwifi/iwl-trans-tx-pcie.c b/drivers/net/wireless/iwlwifi/iwl-trans-tx-pcie.c
index 222d410c586..2bf3107be93 100644
--- a/drivers/net/wireless/iwlwifi/iwl-trans-tx-pcie.c
+++ b/drivers/net/wireless/iwlwifi/iwl-trans-tx-pcie.c
@@ -790,7 +790,7 @@ void iwl_tx_cmd_complete(struct iwl_priv *priv, struct iwl_rx_mem_buffer *rxb)
 		clear_bit(STATUS_HCMD_ACTIVE, &priv->status);
 		IWL_DEBUG_INFO(priv, "Clearing HCMD_ACTIVE for command %s\n",
 			       get_cmd_string(cmd->hdr.cmd));
-		wake_up_interruptible(&priv->wait_command_queue);
+		wake_up(&priv->wait_command_queue);
 	}
 
 	meta->flags = 0;
@@ -957,7 +957,7 @@ static int iwl_send_cmd_sync(struct iwl_priv *priv, struct iwl_host_cmd *cmd)
 		return ret;
 	}
 
-	ret = wait_event_interruptible_timeout(priv->wait_command_queue,
+	ret = wait_event_timeout(priv->wait_command_queue,
 			!test_bit(STATUS_HCMD_ACTIVE, &priv->status),
 			HOST_COMPLETE_TIMEOUT);
 	if (!ret) {
diff --git a/drivers/net/wireless/libertas/if_spi.c b/drivers/net/wireless/libertas/if_spi.c
index e0286cfbc91..7be8b051aab 100644
--- a/drivers/net/wireless/libertas/if_spi.c
+++ b/drivers/net/wireless/libertas/if_spi.c
@@ -999,6 +999,7 @@ static int if_spi_host_to_card(struct lbs_private *priv,
 		spin_unlock_irqrestore(&card->buffer_lock, flags);
 		break;
 	default:
+		kfree(packet);
 		netdev_err(priv->dev, "can't transfer buffer of type %d\n",
 			   type);
 		err = -EINVAL;
diff --git a/drivers/net/wireless/p54/p54spi.c b/drivers/net/wireless/p54/p54spi.c
index 6d9204fef90..b33ceb1c066 100644
--- a/drivers/net/wireless/p54/p54spi.c
+++ b/drivers/net/wireless/p54/p54spi.c
@@ -589,8 +589,6 @@ static void p54spi_op_stop(struct ieee80211_hw *dev)
 
 	WARN_ON(priv->fw_state != FW_STATE_READY);
 
-	cancel_work_sync(&priv->work);
-
 	p54spi_power_off(priv);
 	spin_lock_irqsave(&priv->tx_lock, flags);
 	INIT_LIST_HEAD(&priv->tx_pending);
@@ -598,6 +596,8 @@ static void p54spi_op_stop(struct ieee80211_hw *dev)
 
 	priv->fw_state = FW_STATE_OFF;
 	mutex_unlock(&priv->mutex);
+
+	cancel_work_sync(&priv->work);
 }
 
 static int __devinit p54spi_probe(struct spi_device *spi)
@@ -657,6 +657,7 @@ static int __devinit p54spi_probe(struct spi_device *spi)
 	init_completion(&priv->fw_comp);
 	INIT_LIST_HEAD(&priv->tx_pending);
 	mutex_init(&priv->mutex);
+	spin_lock_init(&priv->tx_lock);
 	SET_IEEE80211_DEV(hw, &spi->dev);
 	priv->common.open = p54spi_op_start;
 	priv->common.stop = p54spi_op_stop;
diff --git a/drivers/net/wireless/rt2x00/rt2800lib.c b/drivers/net/wireless/rt2x00/rt2800lib.c
index 0019dfd8fb0..c6ad97f6daa 100644
--- a/drivers/net/wireless/rt2x00/rt2800lib.c
+++ b/drivers/net/wireless/rt2x00/rt2800lib.c
@@ -3699,7 +3699,7 @@ static void rt2800_efuse_read(struct rt2x00_dev *rt2x00dev, unsigned int i)
 	/* Apparently the data is read from end to start */
 	rt2800_register_read_lock(rt2x00dev, EFUSE_DATA3, &reg);
 	/* The returned value is in CPU order, but eeprom is le */
-	rt2x00dev->eeprom[i] = cpu_to_le32(reg);
+	*(u32 *)&rt2x00dev->eeprom[i] = cpu_to_le32(reg);
 	rt2800_register_read_lock(rt2x00dev, EFUSE_DATA2, &reg);
 	*(u32 *)&rt2x00dev->eeprom[i + 2] = cpu_to_le32(reg);
 	rt2800_register_read_lock(rt2x00dev, EFUSE_DATA1, &reg);
diff --git a/drivers/net/wireless/rt2x00/rt2x00.h b/drivers/net/wireless/rt2x00/rt2x00.h
index f82bfeb79eb..0415e470ddd 100644
--- a/drivers/net/wireless/rt2x00/rt2x00.h
+++ b/drivers/net/wireless/rt2x00/rt2x00.h
@@ -923,6 +923,7 @@ struct rt2x00_dev {
 	 * Powersaving work
 	 */
 	struct delayed_work autowakeup_work;
+	struct work_struct sleep_work;
 
 	/*
 	 * Data queue arrays for RX, TX, Beacon and ATIM.
diff --git a/drivers/net/wireless/rt2x00/rt2x00dev.c b/drivers/net/wireless/rt2x00/rt2x00dev.c
index 0955c941317..9d05f871a98 100644
--- a/drivers/net/wireless/rt2x00/rt2x00dev.c
+++ b/drivers/net/wireless/rt2x00/rt2x00dev.c
@@ -449,6 +449,23 @@ static u8 *rt2x00lib_find_ie(u8 *data, unsigned int len, u8 ie)
 	return NULL;
 }
 
+static void rt2x00lib_sleep(struct work_struct *work)
+{
+	struct rt2x00_dev *rt2x00dev =
+	    container_of(work, struct rt2x00_dev, sleep_work);
+
+	if (!test_bit(DEVICE_STATE_PRESENT, &rt2x00dev->flags))
+		return;
+
+	/*
+	 * Check again is powersaving is enabled, to prevent races from delayed
+	 * work execution.
+	 */
+	if (!test_bit(CONFIG_POWERSAVING, &rt2x00dev->flags))
+		rt2x00lib_config(rt2x00dev, &rt2x00dev->hw->conf,
+				 IEEE80211_CONF_CHANGE_PS);
+}
+
 static void rt2x00lib_rxdone_check_ps(struct rt2x00_dev *rt2x00dev,
 				      struct sk_buff *skb,
 				      struct rxdone_entry_desc *rxdesc)
@@ -496,8 +513,7 @@ static void rt2x00lib_rxdone_check_ps(struct rt2x00_dev *rt2x00dev,
 	cam |= (tim_ie->bitmap_ctrl & 0x01);
 
 	if (!cam && !test_bit(CONFIG_POWERSAVING, &rt2x00dev->flags))
-		rt2x00lib_config(rt2x00dev, &rt2x00dev->hw->conf,
-				 IEEE80211_CONF_CHANGE_PS);
+		queue_work(rt2x00dev->workqueue, &rt2x00dev->sleep_work);
 }
 
 static int rt2x00lib_rxdone_read_signal(struct rt2x00_dev *rt2x00dev,
@@ -1121,6 +1137,7 @@ int rt2x00lib_probe_dev(struct rt2x00_dev *rt2x00dev)
 
 	INIT_WORK(&rt2x00dev->intf_work, rt2x00lib_intf_scheduled);
 	INIT_DELAYED_WORK(&rt2x00dev->autowakeup_work, rt2x00lib_autowakeup);
+	INIT_WORK(&rt2x00dev->sleep_work, rt2x00lib_sleep);
 
 	/*
 	 * Let the driver probe the device to detect the capabilities.
@@ -1177,6 +1194,7 @@ void rt2x00lib_remove_dev(struct rt2x00_dev *rt2x00dev)
 	 */
 	cancel_work_sync(&rt2x00dev->intf_work);
 	cancel_delayed_work_sync(&rt2x00dev->autowakeup_work);
+	cancel_work_sync(&rt2x00dev->sleep_work);
 	if (rt2x00_is_usb(rt2x00dev)) {
 		del_timer_sync(&rt2x00dev->txstatus_timer);
 		cancel_work_sync(&rt2x00dev->rxdone_work);
diff --git a/drivers/net/wireless/rtlwifi/ps.c b/drivers/net/wireless/rtlwifi/ps.c
index a693feffbe7..0b04b2e7b59 100644
--- a/drivers/net/wireless/rtlwifi/ps.c
+++ b/drivers/net/wireless/rtlwifi/ps.c
@@ -394,7 +394,7 @@ void rtl_lps_enter(struct ieee80211_hw *hw)
 	if (mac->link_state != MAC80211_LINKED)
 		return;
 
-	spin_lock(&rtlpriv->locks.lps_lock);
+	spin_lock_irq(&rtlpriv->locks.lps_lock);
 
 	/* Idle for a while if we connect to AP a while ago. */
 	if (mac->cnt_after_linked >= 2) {
@@ -406,7 +406,7 @@ void rtl_lps_enter(struct ieee80211_hw *hw)
 		}
 	}
 
-	spin_unlock(&rtlpriv->locks.lps_lock);
+	spin_unlock_irq(&rtlpriv->locks.lps_lock);
 }
 
 /*Leave the leisure power save mode.*/
@@ -415,8 +415,9 @@ void rtl_lps_leave(struct ieee80211_hw *hw)
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_ps_ctl *ppsc = rtl_psc(rtl_priv(hw));
 	struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw));
+	unsigned long flags;
 
-	spin_lock(&rtlpriv->locks.lps_lock);
+	spin_lock_irqsave(&rtlpriv->locks.lps_lock, flags);
 
 	if (ppsc->fwctrl_lps) {
 		if (ppsc->dot11_psmode != EACTIVE) {
@@ -437,7 +438,7 @@ void rtl_lps_leave(struct ieee80211_hw *hw)
 			rtl_lps_set_psmode(hw, EACTIVE);
 		}
 	}
-	spin_unlock(&rtlpriv->locks.lps_lock);
+	spin_unlock_irqrestore(&rtlpriv->locks.lps_lock, flags);
 }
 
 /* For sw LPS*/
@@ -538,9 +539,9 @@ void rtl_swlps_rf_awake(struct ieee80211_hw *hw)
 		RT_CLEAR_PS_LEVEL(ppsc, RT_PS_LEVEL_ASPM);
 	}
 
-	spin_lock(&rtlpriv->locks.lps_lock);
+	spin_lock_irq(&rtlpriv->locks.lps_lock);
 	rtl_ps_set_rf_state(hw, ERFON, RF_CHANGE_BY_PS);
-	spin_unlock(&rtlpriv->locks.lps_lock);
+	spin_unlock_irq(&rtlpriv->locks.lps_lock);
 }
 
 void rtl_swlps_rfon_wq_callback(void *data)
@@ -573,9 +574,9 @@ void rtl_swlps_rf_sleep(struct ieee80211_hw *hw)
 	if (rtlpriv->link_info.busytraffic)
 		return;
 
-	spin_lock(&rtlpriv->locks.lps_lock);
+	spin_lock_irq(&rtlpriv->locks.lps_lock);
 	rtl_ps_set_rf_state(hw, ERFSLEEP, RF_CHANGE_BY_PS);
-	spin_unlock(&rtlpriv->locks.lps_lock);
+	spin_unlock_irq(&rtlpriv->locks.lps_lock);
 
 	if (ppsc->reg_rfps_level & RT_RF_OFF_LEVL_ASPM &&
 		!RT_IN_PS_LEVEL(ppsc, RT_PS_LEVEL_ASPM)) {
diff --git a/drivers/net/wireless/wl12xx/scan.c b/drivers/net/wireless/wl12xx/scan.c
index edfe01c321c..afb7356bd48 100644
--- a/drivers/net/wireless/wl12xx/scan.c
+++ b/drivers/net/wireless/wl12xx/scan.c
@@ -83,14 +83,18 @@ static int wl1271_get_scan_channels(struct wl1271 *wl,
 	for (i = 0, j = 0;
 	     i < req->n_channels && j < WL1271_SCAN_MAX_CHANNELS;
 	     i++) {
-
 		flags = req->channels[i]->flags;
 
 		if (!test_bit(i, wl->scan.scanned_ch) &&
 		    !(flags & IEEE80211_CHAN_DISABLED) &&
-		    ((!!(flags & IEEE80211_CHAN_PASSIVE_SCAN)) == passive) &&
-		    (req->channels[i]->band == band)) {
-
+		    (req->channels[i]->band == band) &&
+		    /*
+		     * In passive scans, we scan all remaining
+		     * channels, even if not marked as such.
+		     * In active scans, we only scan channels not
+		     * marked as passive.
+		     */
+		    (passive || !(flags & IEEE80211_CHAN_PASSIVE_SCAN))) {
 			wl1271_debug(DEBUG_SCAN, "band %d, center_freq %d ",
 				     req->channels[i]->band,
 				     req->channels[i]->center_freq);
@@ -142,6 +146,10 @@ static int wl1271_scan_send(struct wl1271 *wl, enum ieee80211_band band,
 	int ret;
 	u16 scan_options = 0;
 
+	/* skip active scans if we don't have SSIDs */
+	if (!passive && wl->scan.req->n_ssids == 0)
+		return WL1271_NOTHING_TO_SCAN;
+
 	cmd = kzalloc(sizeof(*cmd), GFP_KERNEL);
 	trigger = kzalloc(sizeof(*trigger), GFP_KERNEL);
 	if (!cmd || !trigger) {
@@ -152,8 +160,7 @@ static int wl1271_scan_send(struct wl1271 *wl, enum ieee80211_band band,
 	/* We always use high priority scans */
 	scan_options = WL1271_SCAN_OPT_PRIORITY_HIGH;
 
-	/* No SSIDs means that we have a forced passive scan */
-	if (passive || wl->scan.req->n_ssids == 0)
+	if (passive)
 		scan_options |= WL1271_SCAN_OPT_PASSIVE;
 
 	cmd->params.scan_options = cpu_to_le16(scan_options);
diff --git a/drivers/of/base.c b/drivers/of/base.c
index 3ff22e32b60..b970562e011 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -17,14 +17,39 @@
  *      as published by the Free Software Foundation; either version
  *      2 of the License, or (at your option) any later version.
  */
+#include <linux/ctype.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/spinlock.h>
 #include <linux/slab.h>
 #include <linux/proc_fs.h>
 
+/**
+ * struct alias_prop - Alias property in 'aliases' node
+ * @link:	List node to link the structure in aliases_lookup list
+ * @alias:	Alias property name
+ * @np:		Pointer to device_node that the alias stands for
+ * @id:		Index value from end of alias name
+ * @stem:	Alias string without the index
+ *
+ * The structure represents one alias property of 'aliases' node as
+ * an entry in aliases_lookup list.
+ */
+struct alias_prop {
+	struct list_head link;
+	const char *alias;
+	struct device_node *np;
+	int id;
+	char stem[0];
+};
+
+static LIST_HEAD(aliases_lookup);
+
 struct device_node *allnodes;
 struct device_node *of_chosen;
+struct device_node *of_aliases;
+
+static DEFINE_MUTEX(of_aliases_mutex);
 
 /* use when traversing tree through the allnext, child, sibling,
  * or parent members of struct device_node.
@@ -632,6 +657,35 @@ int of_property_read_u32_array(const struct device_node *np,
 EXPORT_SYMBOL_GPL(of_property_read_u32_array);
 
 /**
+ * of_property_read_u64 - Find and read a 64 bit integer from a property
+ * @np:		device node from which the property value is to be read.
+ * @propname:	name of the property to be searched.
+ * @out_value:	pointer to return value, modified only if return value is 0.
+ *
+ * Search for a property in a device node and read a 64-bit value from
+ * it. Returns 0 on success, -EINVAL if the property does not exist,
+ * -ENODATA if property does not have a value, and -EOVERFLOW if the
+ * property data isn't large enough.
+ *
+ * The out_value is modified only if a valid u64 value can be decoded.
+ */
+int of_property_read_u64(const struct device_node *np, const char *propname,
+			 u64 *out_value)
+{
+	struct property *prop = of_find_property(np, propname, NULL);
+
+	if (!prop)
+		return -EINVAL;
+	if (!prop->value)
+		return -ENODATA;
+	if (sizeof(*out_value) > prop->length)
+		return -EOVERFLOW;
+	*out_value = of_read_number(prop->value, 2);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(of_property_read_u64);
+
+/**
  * of_property_read_string - Find and read a string from a property
  * @np:		device node from which the property value is to be read.
  * @propname:	name of the property to be searched.
@@ -988,3 +1042,99 @@ out_unlock:
 }
 #endif /* defined(CONFIG_OF_DYNAMIC) */
 
+static void of_alias_add(struct alias_prop *ap, struct device_node *np,
+			 int id, const char *stem, int stem_len)
+{
+	ap->np = np;
+	ap->id = id;
+	strncpy(ap->stem, stem, stem_len);
+	ap->stem[stem_len] = 0;
+	list_add_tail(&ap->link, &aliases_lookup);
+	pr_debug("adding DT alias:%s: stem=%s id=%i node=%s\n",
+		 ap->alias, ap->stem, ap->id, np ? np->full_name : NULL);
+}
+
+/**
+ * of_alias_scan - Scan all properties of 'aliases' node
+ *
+ * The function scans all the properties of 'aliases' node and populate
+ * the the global lookup table with the properties.  It returns the
+ * number of alias_prop found, or error code in error case.
+ *
+ * @dt_alloc:	An allocator that provides a virtual address to memory
+ *		for the resulting tree
+ */
+void of_alias_scan(void * (*dt_alloc)(u64 size, u64 align))
+{
+	struct property *pp;
+
+	of_chosen = of_find_node_by_path("/chosen");
+	if (of_chosen == NULL)
+		of_chosen = of_find_node_by_path("/chosen@0");
+	of_aliases = of_find_node_by_path("/aliases");
+	if (!of_aliases)
+		return;
+
+	for_each_property(pp, of_aliases->properties) {
+		const char *start = pp->name;
+		const char *end = start + strlen(start);
+		struct device_node *np;
+		struct alias_prop *ap;
+		int id, len;
+
+		/* Skip those we do not want to proceed */
+		if (!strcmp(pp->name, "name") ||
+		    !strcmp(pp->name, "phandle") ||
+		    !strcmp(pp->name, "linux,phandle"))
+			continue;
+
+		np = of_find_node_by_path(pp->value);
+		if (!np)
+			continue;
+
+		/* walk the alias backwards to extract the id and work out
+		 * the 'stem' string */
+		while (isdigit(*(end-1)) && end > start)
+			end--;
+		len = end - start;
+
+		if (kstrtoint(end, 10, &id) < 0)
+			continue;
+
+		/* Allocate an alias_prop with enough space for the stem */
+		ap = dt_alloc(sizeof(*ap) + len + 1, 4);
+		if (!ap)
+			continue;
+		ap->alias = start;
+		of_alias_add(ap, np, id, start, len);
+	}
+}
+
+/**
+ * of_alias_get_id - Get alias id for the given device_node
+ * @np:		Pointer to the given device_node
+ * @stem:	Alias stem of the given device_node
+ *
+ * The function travels the lookup table to get alias id for the given
+ * device_node and alias stem.  It returns the alias id if find it.
+ */
+int of_alias_get_id(struct device_node *np, const char *stem)
+{
+	struct alias_prop *app;
+	int id = -ENODEV;
+
+	mutex_lock(&of_aliases_mutex);
+	list_for_each_entry(app, &aliases_lookup, link) {
+		if (strcmp(app->stem, stem) != 0)
+			continue;
+
+		if (np == app->np) {
+			id = app->id;
+			break;
+		}
+	}
+	mutex_unlock(&of_aliases_mutex);
+
+	return id;
+}
+EXPORT_SYMBOL_GPL(of_alias_get_id);
diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index 65200af29c5..aeec35bc378 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -707,10 +707,8 @@ void __init unflatten_device_tree(void)
 	__unflatten_device_tree(initial_boot_params, &allnodes,
 				early_init_dt_alloc_memory_arch);
 
-	/* Get pointer to OF "/chosen" node for use everywhere */
-	of_chosen = of_find_node_by_path("/chosen");
-	if (of_chosen == NULL)
-		of_chosen = of_find_node_by_path("/chosen@0");
+	/* Get pointer to "/chosen" and "/aliasas" nodes for use everywhere */
+	of_alias_scan(early_init_dt_alloc_memory_arch);
 }
 
 #endif /* CONFIG_OF_EARLY_FLATTREE */
diff --git a/drivers/of/irq.c b/drivers/of/irq.c
index 9f689f1da0f..6a5b5e777dd 100644
--- a/drivers/of/irq.c
+++ b/drivers/of/irq.c
@@ -58,27 +58,27 @@ EXPORT_SYMBOL_GPL(irq_of_parse_and_map);
  */
 struct device_node *of_irq_find_parent(struct device_node *child)
 {
-	struct device_node *p;
+	struct device_node *p, *c = child;
 	const __be32 *parp;
 
-	if (!of_node_get(child))
+	if (!of_node_get(c))
 		return NULL;
 
 	do {
-		parp = of_get_property(child, "interrupt-parent", NULL);
+		parp = of_get_property(c, "interrupt-parent", NULL);
 		if (parp == NULL)
-			p = of_get_parent(child);
+			p = of_get_parent(c);
 		else {
 			if (of_irq_workarounds & OF_IMAP_NO_PHANDLE)
 				p = of_node_get(of_irq_dflt_pic);
 			else
 				p = of_find_node_by_phandle(be32_to_cpup(parp));
 		}
-		of_node_put(child);
-		child = p;
+		of_node_put(c);
+		c = p;
 	} while (p && of_get_property(p, "#interrupt-cells", NULL) == NULL);
 
-	return p;
+	return (p == child) ? NULL : p;
 }
 
 /**
diff --git a/drivers/of/pdt.c b/drivers/of/pdt.c
index 4d87b5dc928..bc5b3990f6e 100644
--- a/drivers/of/pdt.c
+++ b/drivers/of/pdt.c
@@ -229,6 +229,11 @@ static struct device_node * __init of_pdt_build_tree(struct device_node *parent,
 	return ret;
 }
 
+static void *kernel_tree_alloc(u64 size, u64 align)
+{
+	return prom_early_alloc(size);
+}
+
 void __init of_pdt_build_devicetree(phandle root_node, struct of_pdt_ops *ops)
 {
 	struct device_node **nextp;
@@ -245,4 +250,7 @@ void __init of_pdt_build_devicetree(phandle root_node, struct of_pdt_ops *ops)
 	nextp = &allnodes->allnext;
 	allnodes->child = of_pdt_build_tree(allnodes,
 			of_pdt_prom_ops->getchild(allnodes->phandle), &nextp);
+
+	/* Get pointer to "/chosen" and "/aliasas" nodes for use everywhere */
+	of_alias_scan(kernel_tree_alloc);
 }
diff --git a/drivers/of/platform.c b/drivers/of/platform.c
index ed5a6d3c26a..b22f8873a41 100644
--- a/drivers/of/platform.c
+++ b/drivers/of/platform.c
@@ -345,6 +345,7 @@ static int of_platform_bus_create(struct device_node *bus,
 	struct platform_device *dev;
 	const char *bus_id = NULL;
 	void *platform_data = NULL;
+	int id = -1;
 	int rc = 0;
 
 	/* Make sure it has a compatible property */
@@ -357,6 +358,7 @@ static int of_platform_bus_create(struct device_node *bus,
 	auxdata = of_dev_lookup(lookup, bus);
 	if (auxdata) {
 		bus_id = auxdata->name;
+		id = auxdata->id;
 		platform_data = auxdata->platform_data;
 	}
 
@@ -366,6 +368,11 @@ static int of_platform_bus_create(struct device_node *bus,
 	}
 
 	dev = of_platform_device_create_pdata(bus, bus_id, platform_data, parent);
+
+	/* override the id if auxdata gives an id */
+	if (id != -1)
+		dev->id = id;
+
 	if (!dev || !of_match_node(matches, bus))
 		return 0;
 
diff --git a/drivers/oprofile/oprof.c b/drivers/oprofile/oprof.c
index dccd8636095..f8c752e408a 100644
--- a/drivers/oprofile/oprof.c
+++ b/drivers/oprofile/oprof.c
@@ -239,26 +239,45 @@ int oprofile_set_ulong(unsigned long *addr, unsigned long val)
 	return err;
 }
 
+static int timer_mode;
+
 static int __init oprofile_init(void)
 {
 	int err;
 
+	/* always init architecture to setup backtrace support */
 	err = oprofile_arch_init(&oprofile_ops);
-	if (err < 0 || timer) {
-		printk(KERN_INFO "oprofile: using timer interrupt.\n");
+
+	timer_mode = err || timer;	/* fall back to timer mode on errors */
+	if (timer_mode) {
+		if (!err)
+			oprofile_arch_exit();
 		err = oprofile_timer_init(&oprofile_ops);
 		if (err)
 			return err;
 	}
-	return oprofilefs_register();
+
+	err = oprofilefs_register();
+	if (!err)
+		return 0;
+
+	/* failed */
+	if (timer_mode)
+		oprofile_timer_exit();
+	else
+		oprofile_arch_exit();
+
+	return err;
 }
 
 
 static void __exit oprofile_exit(void)
 {
-	oprofile_timer_exit();
 	oprofilefs_unregister();
-	oprofile_arch_exit();
+	if (timer_mode)
+		oprofile_timer_exit();
+	else
+		oprofile_arch_exit();
 }
 
 
diff --git a/drivers/oprofile/timer_int.c b/drivers/oprofile/timer_int.c
index 3ef44624f51..878fba12658 100644
--- a/drivers/oprofile/timer_int.c
+++ b/drivers/oprofile/timer_int.c
@@ -110,6 +110,7 @@ int oprofile_timer_init(struct oprofile_operations *ops)
 	ops->start = oprofile_hrtimer_start;
 	ops->stop = oprofile_hrtimer_stop;
 	ops->cpu_type = "timer";
+	printk(KERN_INFO "oprofile: using timer interrupt.\n");
 	return 0;
 }
 
diff --git a/drivers/pci/hotplug/shpchp_core.c b/drivers/pci/hotplug/shpchp_core.c
index aca972bbfb4..dd7e0c51a33 100644
--- a/drivers/pci/hotplug/shpchp_core.c
+++ b/drivers/pci/hotplug/shpchp_core.c
@@ -278,8 +278,8 @@ static int get_adapter_status (struct hotplug_slot *hotplug_slot, u8 *value)
 
 static int is_shpc_capable(struct pci_dev *dev)
 {
-	if ((dev->vendor == PCI_VENDOR_ID_AMD) || (dev->device ==
-						PCI_DEVICE_ID_AMD_GOLAM_7450))
+	if (dev->vendor == PCI_VENDOR_ID_AMD &&
+	    dev->device == PCI_DEVICE_ID_AMD_GOLAM_7450)
 		return 1;
 	if (!pci_find_capability(dev, PCI_CAP_ID_SHPC))
 		return 0;
diff --git a/drivers/pci/hotplug/shpchp_hpc.c b/drivers/pci/hotplug/shpchp_hpc.c
index 36547f0ce30..75ba2311b54 100644
--- a/drivers/pci/hotplug/shpchp_hpc.c
+++ b/drivers/pci/hotplug/shpchp_hpc.c
@@ -944,8 +944,8 @@ int shpc_init(struct controller *ctrl, struct pci_dev *pdev)
 	ctrl->pci_dev = pdev;  /* pci_dev of the P2P bridge */
 	ctrl_dbg(ctrl, "Hotplug Controller:\n");
 
-	if ((pdev->vendor == PCI_VENDOR_ID_AMD) || (pdev->device ==
-				PCI_DEVICE_ID_AMD_GOLAM_7450)) {
+	if (pdev->vendor == PCI_VENDOR_ID_AMD &&
+	    pdev->device == PCI_DEVICE_ID_AMD_GOLAM_7450) {
 		/* amd shpc driver doesn't use Base Offset; assume 0 */
 		ctrl->mmio_base = pci_resource_start(pdev, 0);
 		ctrl->mmio_size = pci_resource_len(pdev, 0);
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 1196f61a4ab..cec46292731 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -2745,20 +2745,6 @@ static void ricoh_mmc_fixup_r5c832(struct pci_dev *dev)
 	/* disable must be done via function #0 */
 	if (PCI_FUNC(dev->devfn))
 		return;
-
-	pci_read_config_byte(dev, 0xCB, &disable);
-
-	if (disable & 0x02)
-		return;
-
-	pci_read_config_byte(dev, 0xCA, &write_enable);
-	pci_write_config_byte(dev, 0xCA, 0x57);
-	pci_write_config_byte(dev, 0xCB, disable | 0x02);
-	pci_write_config_byte(dev, 0xCA, write_enable);
-
-	dev_notice(&dev->dev, "proprietary Ricoh MMC controller disabled (via firewire function)\n");
-	dev_notice(&dev->dev, "MMC cards are now supported by standard SDHCI controller\n");
-
 	/*
 	 * RICOH 0xe823 SD/MMC card reader fails to recognize
 	 * certain types of SD/MMC cards. Lowering the SD base
@@ -2781,6 +2767,20 @@ static void ricoh_mmc_fixup_r5c832(struct pci_dev *dev)
 
 		dev_notice(&dev->dev, "MMC controller base frequency changed to 50Mhz.\n");
 	}
+
+	pci_read_config_byte(dev, 0xCB, &disable);
+
+	if (disable & 0x02)
+		return;
+
+	pci_read_config_byte(dev, 0xCA, &write_enable);
+	pci_write_config_byte(dev, 0xCA, 0x57);
+	pci_write_config_byte(dev, 0xCB, disable | 0x02);
+	pci_write_config_byte(dev, 0xCA, write_enable);
+
+	dev_notice(&dev->dev, "proprietary Ricoh MMC controller disabled (via firewire function)\n");
+	dev_notice(&dev->dev, "MMC cards are now supported by standard SDHCI controller\n");
+
 }
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_RICOH, PCI_DEVICE_ID_RICOH_R5C832, ricoh_mmc_fixup_r5c832);
 DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_RICOH, PCI_DEVICE_ID_RICOH_R5C832, ricoh_mmc_fixup_r5c832);
diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c
index 6fa215a3861..90832a95599 100644
--- a/drivers/pci/xen-pcifront.c
+++ b/drivers/pci/xen-pcifront.c
@@ -400,9 +400,8 @@ static int pcifront_claim_resource(struct pci_dev *dev, void *data)
 			dev_info(&pdev->xdev->dev, "claiming resource %s/%d\n",
 				pci_name(dev), i);
 			if (pci_claim_resource(dev, i)) {
-				dev_err(&pdev->xdev->dev, "Could not claim "
-					"resource %s/%d! Device offline. Try "
-					"giving less than 4GB to domain.\n",
+				dev_err(&pdev->xdev->dev, "Could not claim resource %s/%d! "
+					"Device offline. Try using e820_host=1 in the guest config.\n",
 					pci_name(dev), i);
 			}
 		}
diff --git a/drivers/platform/x86/samsung-laptop.c b/drivers/platform/x86/samsung-laptop.c
index 35916301104..59ac26c6a2a 100644
--- a/drivers/platform/x86/samsung-laptop.c
+++ b/drivers/platform/x86/samsung-laptop.c
@@ -370,15 +370,17 @@ static u8 read_brightness(void)
 				  &sretval);
 	if (!retval) {
 		user_brightness = sretval.retval[0];
-		if (user_brightness != 0)
+		if (user_brightness > sabi_config->min_brightness)
 			user_brightness -= sabi_config->min_brightness;
+		else
+			user_brightness = 0;
 	}
 	return user_brightness;
 }
 
 static void set_brightness(u8 user_brightness)
 {
-	u8 user_level = user_brightness - sabi_config->min_brightness;
+	u8 user_level = user_brightness + sabi_config->min_brightness;
 
 	sabi_set_command(sabi_config->commands.set_brightness, user_level);
 }
@@ -641,6 +643,15 @@ static struct dmi_system_id __initdata samsung_dmi_table[] = {
 		.callback = dmi_check_cb,
 	},
 	{
+		.ident = "R700",
+		.matches = {
+		      DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."),
+		      DMI_MATCH(DMI_PRODUCT_NAME, "SR700"),
+		      DMI_MATCH(DMI_BOARD_NAME, "SR700"),
+		},
+		.callback = dmi_check_cb,
+	},
+	{
 		.ident = "R530/R730",
 		.matches = {
 		      DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."),
@@ -686,6 +697,24 @@ static struct dmi_system_id __initdata samsung_dmi_table[] = {
 		},
 		.callback = dmi_check_cb,
 	},
+		{
+		.ident = "X520",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "X520"),
+			DMI_MATCH(DMI_BOARD_NAME, "X520"),
+		},
+		.callback = dmi_check_cb,
+	},
+	{
+		.ident = "R528/R728",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "R528/R728"),
+			DMI_MATCH(DMI_BOARD_NAME, "R528/R728"),
+		},
+		.callback = dmi_check_cb,
+	},
 	{ },
 };
 MODULE_DEVICE_TABLE(dmi, samsung_dmi_table);
@@ -770,7 +799,7 @@ static int __init samsung_init(void)
 	sabi_iface = ioremap_nocache(ifaceP, 16);
 	if (!sabi_iface) {
 		pr_err("Can't remap %x\n", ifaceP);
-		goto exit;
+		goto error_no_signature;
 	}
 	if (debug) {
 		printk(KERN_DEBUG "ifaceP = 0x%08x\n", ifaceP);
@@ -802,7 +831,8 @@ static int __init samsung_init(void)
 	/* create a backlight device to talk to this one */
 	memset(&props, 0, sizeof(struct backlight_properties));
 	props.type = BACKLIGHT_PLATFORM;
-	props.max_brightness = sabi_config->max_brightness;
+	props.max_brightness = sabi_config->max_brightness -
+				sabi_config->min_brightness;
 	backlight_device = backlight_device_register("samsung", &sdev->dev,
 						     NULL, &backlight_ops,
 						     &props);
@@ -821,7 +851,6 @@ static int __init samsung_init(void)
 	if (retval)
 		goto error_file_create;
 
-exit:
 	return 0;
 
 error_file_create:
diff --git a/drivers/platform/x86/wmi.c b/drivers/platform/x86/wmi.c
index f23d5a84e7b..9b88be42b6c 100644
--- a/drivers/platform/x86/wmi.c
+++ b/drivers/platform/x86/wmi.c
@@ -754,9 +754,13 @@ static void wmi_free_devices(void)
 	struct wmi_block *wblock, *next;
 
 	/* Delete devices for all the GUIDs */
-	list_for_each_entry_safe(wblock, next, &wmi_block_list, list)
+	list_for_each_entry_safe(wblock, next, &wmi_block_list, list) {
+		list_del(&wblock->list);
 		if (wblock->dev.class)
 			device_unregister(&wblock->dev);
+		else
+			kfree(wblock);
+	}
 }
 
 static bool guid_already_parsed(const char *guid_string)
diff --git a/drivers/power/ds2780_battery.c b/drivers/power/ds2780_battery.c
index 1fefe82e12e..91a783d7236 100644
--- a/drivers/power/ds2780_battery.c
+++ b/drivers/power/ds2780_battery.c
@@ -39,6 +39,7 @@ struct ds2780_device_info {
 	struct device *dev;
 	struct power_supply bat;
 	struct device *w1_dev;
+	struct task_struct *mutex_holder;
 };
 
 enum current_types {
@@ -49,8 +50,8 @@ enum current_types {
 static const char model[] = "DS2780";
 static const char manufacturer[] = "Maxim/Dallas";
 
-static inline struct ds2780_device_info *to_ds2780_device_info(
-	struct power_supply *psy)
+static inline struct ds2780_device_info *
+to_ds2780_device_info(struct power_supply *psy)
 {
 	return container_of(psy, struct ds2780_device_info, bat);
 }
@@ -60,17 +61,28 @@ static inline struct power_supply *to_power_supply(struct device *dev)
 	return dev_get_drvdata(dev);
 }
 
-static inline int ds2780_read8(struct device *dev, u8 *val, int addr)
+static inline int ds2780_battery_io(struct ds2780_device_info *dev_info,
+	char *buf, int addr, size_t count, int io)
 {
-	return w1_ds2780_io(dev, val, addr, sizeof(u8), 0);
+	if (dev_info->mutex_holder == current)
+		return w1_ds2780_io_nolock(dev_info->w1_dev, buf, addr, count, io);
+	else
+		return w1_ds2780_io(dev_info->w1_dev, buf, addr, count, io);
+}
+
+static inline int ds2780_read8(struct ds2780_device_info *dev_info, u8 *val,
+	int addr)
+{
+	return ds2780_battery_io(dev_info, val, addr, sizeof(u8), 0);
 }
 
-static int ds2780_read16(struct device *dev, s16 *val, int addr)
+static int ds2780_read16(struct ds2780_device_info *dev_info, s16 *val,
+	int addr)
 {
 	int ret;
 	u8 raw[2];
 
-	ret = w1_ds2780_io(dev, raw, addr, sizeof(u8) * 2, 0);
+	ret = ds2780_battery_io(dev_info, raw, addr, sizeof(raw), 0);
 	if (ret < 0)
 		return ret;
 
@@ -79,16 +91,16 @@ static int ds2780_read16(struct device *dev, s16 *val, int addr)
 	return 0;
 }
 
-static inline int ds2780_read_block(struct device *dev, u8 *val, int addr,
-	size_t count)
+static inline int ds2780_read_block(struct ds2780_device_info *dev_info,
+	u8 *val, int addr, size_t count)
 {
-	return w1_ds2780_io(dev, val, addr, count, 0);
+	return ds2780_battery_io(dev_info, val, addr, count, 0);
 }
 
-static inline int ds2780_write(struct device *dev, u8 *val, int addr,
-	size_t count)
+static inline int ds2780_write(struct ds2780_device_info *dev_info, u8 *val,
+	int addr, size_t count)
 {
-	return w1_ds2780_io(dev, val, addr, count, 1);
+	return ds2780_battery_io(dev_info, val, addr, count, 1);
 }
 
 static inline int ds2780_store_eeprom(struct device *dev, int addr)
@@ -122,7 +134,7 @@ static int ds2780_set_sense_register(struct ds2780_device_info *dev_info,
 {
 	int ret;
 
-	ret = ds2780_write(dev_info->w1_dev, &conductance,
+	ret = ds2780_write(dev_info, &conductance,
 				DS2780_RSNSP_REG, sizeof(u8));
 	if (ret < 0)
 		return ret;
@@ -134,7 +146,7 @@ static int ds2780_set_sense_register(struct ds2780_device_info *dev_info,
 static int ds2780_get_rsgain_register(struct ds2780_device_info *dev_info,
 	u16 *rsgain)
 {
-	return ds2780_read16(dev_info->w1_dev, rsgain, DS2780_RSGAIN_MSB_REG);
+	return ds2780_read16(dev_info, rsgain, DS2780_RSGAIN_MSB_REG);
 }
 
 /* Set RSGAIN value from 0 to 1.999 in steps of 0.001 */
@@ -144,8 +156,8 @@ static int ds2780_set_rsgain_register(struct ds2780_device_info *dev_info,
 	int ret;
 	u8 raw[] = {rsgain >> 8, rsgain & 0xFF};
 
-	ret = ds2780_write(dev_info->w1_dev, raw,
-				DS2780_RSGAIN_MSB_REG, sizeof(u8) * 2);
+	ret = ds2780_write(dev_info, raw,
+				DS2780_RSGAIN_MSB_REG, sizeof(raw));
 	if (ret < 0)
 		return ret;
 
@@ -167,7 +179,7 @@ static int ds2780_get_voltage(struct ds2780_device_info *dev_info,
 	 * Bits 2 - 0 of the voltage value are in bits 7 - 5 of the
 	 * voltage LSB register
 	 */
-	ret = ds2780_read16(dev_info->w1_dev, &voltage_raw,
+	ret = ds2780_read16(dev_info, &voltage_raw,
 				DS2780_VOLT_MSB_REG);
 	if (ret < 0)
 		return ret;
@@ -196,7 +208,7 @@ static int ds2780_get_temperature(struct ds2780_device_info *dev_info,
 	 * Bits 2 - 0 of the temperature value are in bits 7 - 5 of the
 	 * temperature LSB register
 	 */
-	ret = ds2780_read16(dev_info->w1_dev, &temperature_raw,
+	ret = ds2780_read16(dev_info, &temperature_raw,
 				DS2780_TEMP_MSB_REG);
 	if (ret < 0)
 		return ret;
@@ -222,13 +234,13 @@ static int ds2780_get_current(struct ds2780_device_info *dev_info,
 	 * The units of measurement for current are dependent on the value of
 	 * the sense resistor.
 	 */
-	ret = ds2780_read8(dev_info->w1_dev, &sense_res_raw, DS2780_RSNSP_REG);
+	ret = ds2780_read8(dev_info, &sense_res_raw, DS2780_RSNSP_REG);
 	if (ret < 0)
 		return ret;
 
 	if (sense_res_raw == 0) {
 		dev_err(dev_info->dev, "sense resistor value is 0\n");
-		return -ENXIO;
+		return -EINVAL;
 	}
 	sense_res = 1000 / sense_res_raw;
 
@@ -248,7 +260,7 @@ static int ds2780_get_current(struct ds2780_device_info *dev_info,
 	 * Bits 7 - 0 of the current value are in bits 7 - 0 of the current
 	 * LSB register
 	 */
-	ret = ds2780_read16(dev_info->w1_dev, &current_raw, reg_msb);
+	ret = ds2780_read16(dev_info, &current_raw, reg_msb);
 	if (ret < 0)
 		return ret;
 
@@ -267,7 +279,7 @@ static int ds2780_get_accumulated_current(struct ds2780_device_info *dev_info,
 	 * The units of measurement for accumulated current are dependent on
 	 * the value of the sense resistor.
 	 */
-	ret = ds2780_read8(dev_info->w1_dev, &sense_res_raw, DS2780_RSNSP_REG);
+	ret = ds2780_read8(dev_info, &sense_res_raw, DS2780_RSNSP_REG);
 	if (ret < 0)
 		return ret;
 
@@ -285,7 +297,7 @@ static int ds2780_get_accumulated_current(struct ds2780_device_info *dev_info,
 	 * Bits 7 - 0 of the ACR value are in bits 7 - 0 of the ACR
 	 * LSB register
 	 */
-	ret = ds2780_read16(dev_info->w1_dev, &current_raw, DS2780_ACR_MSB_REG);
+	ret = ds2780_read16(dev_info, &current_raw, DS2780_ACR_MSB_REG);
 	if (ret < 0)
 		return ret;
 
@@ -299,7 +311,7 @@ static int ds2780_get_capacity(struct ds2780_device_info *dev_info,
 	int ret;
 	u8 raw;
 
-	ret = ds2780_read8(dev_info->w1_dev, &raw, DS2780_RARC_REG);
+	ret = ds2780_read8(dev_info, &raw, DS2780_RARC_REG);
 	if (ret < 0)
 		return ret;
 
@@ -345,7 +357,7 @@ static int ds2780_get_charge_now(struct ds2780_device_info *dev_info,
 	 * Bits 7 - 0 of the RAAC value are in bits 7 - 0 of the RAAC
 	 * LSB register
 	 */
-	ret = ds2780_read16(dev_info->w1_dev, &charge_raw, DS2780_RAAC_MSB_REG);
+	ret = ds2780_read16(dev_info, &charge_raw, DS2780_RAAC_MSB_REG);
 	if (ret < 0)
 		return ret;
 
@@ -356,7 +368,7 @@ static int ds2780_get_charge_now(struct ds2780_device_info *dev_info,
 static int ds2780_get_control_register(struct ds2780_device_info *dev_info,
 	u8 *control_reg)
 {
-	return ds2780_read8(dev_info->w1_dev, control_reg, DS2780_CONTROL_REG);
+	return ds2780_read8(dev_info, control_reg, DS2780_CONTROL_REG);
 }
 
 static int ds2780_set_control_register(struct ds2780_device_info *dev_info,
@@ -364,7 +376,7 @@ static int ds2780_set_control_register(struct ds2780_device_info *dev_info,
 {
 	int ret;
 
-	ret = ds2780_write(dev_info->w1_dev, &control_reg,
+	ret = ds2780_write(dev_info, &control_reg,
 				DS2780_CONTROL_REG, sizeof(u8));
 	if (ret < 0)
 		return ret;
@@ -503,7 +515,7 @@ static ssize_t ds2780_get_sense_resistor_value(struct device *dev,
 	struct power_supply *psy = to_power_supply(dev);
 	struct ds2780_device_info *dev_info = to_ds2780_device_info(psy);
 
-	ret = ds2780_read8(dev_info->w1_dev, &sense_resistor, DS2780_RSNSP_REG);
+	ret = ds2780_read8(dev_info, &sense_resistor, DS2780_RSNSP_REG);
 	if (ret < 0)
 		return ret;
 
@@ -584,7 +596,7 @@ static ssize_t ds2780_get_pio_pin(struct device *dev,
 	struct power_supply *psy = to_power_supply(dev);
 	struct ds2780_device_info *dev_info = to_ds2780_device_info(psy);
 
-	ret = ds2780_read8(dev_info->w1_dev, &sfr, DS2780_SFR_REG);
+	ret = ds2780_read8(dev_info, &sfr, DS2780_SFR_REG);
 	if (ret < 0)
 		return ret;
 
@@ -611,7 +623,7 @@ static ssize_t ds2780_set_pio_pin(struct device *dev,
 		return -EINVAL;
 	}
 
-	ret = ds2780_write(dev_info->w1_dev, &new_setting,
+	ret = ds2780_write(dev_info, &new_setting,
 				DS2780_SFR_REG, sizeof(u8));
 	if (ret < 0)
 		return ret;
@@ -632,7 +644,7 @@ static ssize_t ds2780_read_param_eeprom_bin(struct file *filp,
 		DS2780_EEPROM_BLOCK1_END -
 		DS2780_EEPROM_BLOCK1_START + 1 - off);
 
-	return ds2780_read_block(dev_info->w1_dev, buf,
+	return ds2780_read_block(dev_info, buf,
 				DS2780_EEPROM_BLOCK1_START + off, count);
 }
 
@@ -650,7 +662,7 @@ static ssize_t ds2780_write_param_eeprom_bin(struct file *filp,
 		DS2780_EEPROM_BLOCK1_END -
 		DS2780_EEPROM_BLOCK1_START + 1 - off);
 
-	ret = ds2780_write(dev_info->w1_dev, buf,
+	ret = ds2780_write(dev_info, buf,
 				DS2780_EEPROM_BLOCK1_START + off, count);
 	if (ret < 0)
 		return ret;
@@ -685,9 +697,8 @@ static ssize_t ds2780_read_user_eeprom_bin(struct file *filp,
 		DS2780_EEPROM_BLOCK0_END -
 		DS2780_EEPROM_BLOCK0_START + 1 - off);
 
-	return ds2780_read_block(dev_info->w1_dev, buf,
+	return ds2780_read_block(dev_info, buf,
 				DS2780_EEPROM_BLOCK0_START + off, count);
-
 }
 
 static ssize_t ds2780_write_user_eeprom_bin(struct file *filp,
@@ -704,7 +715,7 @@ static ssize_t ds2780_write_user_eeprom_bin(struct file *filp,
 		DS2780_EEPROM_BLOCK0_END -
 		DS2780_EEPROM_BLOCK0_START + 1 - off);
 
-	ret = ds2780_write(dev_info->w1_dev, buf,
+	ret = ds2780_write(dev_info, buf,
 				DS2780_EEPROM_BLOCK0_START + off, count);
 	if (ret < 0)
 		return ret;
@@ -768,6 +779,7 @@ static int __devinit ds2780_battery_probe(struct platform_device *pdev)
 	dev_info->bat.properties	= ds2780_battery_props;
 	dev_info->bat.num_properties	= ARRAY_SIZE(ds2780_battery_props);
 	dev_info->bat.get_property	= ds2780_battery_get_property;
+	dev_info->mutex_holder		= current;
 
 	ret = power_supply_register(&pdev->dev, &dev_info->bat);
 	if (ret) {
@@ -797,6 +809,8 @@ static int __devinit ds2780_battery_probe(struct platform_device *pdev)
 		goto fail_remove_bin_file;
 	}
 
+	dev_info->mutex_holder = NULL;
+
 	return 0;
 
 fail_remove_bin_file:
@@ -816,6 +830,8 @@ static int __devexit ds2780_battery_remove(struct platform_device *pdev)
 {
 	struct ds2780_device_info *dev_info = platform_get_drvdata(pdev);
 
+	dev_info->mutex_holder = current;
+
 	/* remove attributes */
 	sysfs_remove_group(&dev_info->bat.dev->kobj, &ds2780_attr_group);
 
diff --git a/drivers/regulator/aat2870-regulator.c b/drivers/regulator/aat2870-regulator.c
index cd4104542f0..11d1ab4abef 100644
--- a/drivers/regulator/aat2870-regulator.c
+++ b/drivers/regulator/aat2870-regulator.c
@@ -159,7 +159,7 @@ static struct aat2870_regulator *aat2870_get_regulator(int id)
 			break;
 	}
 
-	if (!ri)
+	if (i == ARRAY_SIZE(aat2870_regulators))
 		return NULL;
 
 	ri->enable_addr = AAT2870_LDO_EN;
diff --git a/drivers/regulator/twl-regulator.c b/drivers/regulator/twl-regulator.c
index ee8747f4fa0..11cc308d66e 100644
--- a/drivers/regulator/twl-regulator.c
+++ b/drivers/regulator/twl-regulator.c
@@ -71,6 +71,7 @@ struct twlreg_info {
 #define VREG_TYPE		1
 #define VREG_REMAP		2
 #define VREG_DEDICATED		3	/* LDO control */
+#define VREG_VOLTAGE_SMPS_4030	9
 /* TWL6030 register offsets */
 #define VREG_TRANS		1
 #define VREG_STATE		2
@@ -514,6 +515,32 @@ static struct regulator_ops twl4030ldo_ops = {
 	.get_status	= twl4030reg_get_status,
 };
 
+static int
+twl4030smps_set_voltage(struct regulator_dev *rdev, int min_uV, int max_uV,
+			unsigned *selector)
+{
+	struct twlreg_info *info = rdev_get_drvdata(rdev);
+	int vsel = DIV_ROUND_UP(min_uV - 600000, 12500);
+
+	twlreg_write(info, TWL_MODULE_PM_RECEIVER, VREG_VOLTAGE_SMPS_4030,
+		vsel);
+	return 0;
+}
+
+static int twl4030smps_get_voltage(struct regulator_dev *rdev)
+{
+	struct twlreg_info *info = rdev_get_drvdata(rdev);
+	int vsel = twlreg_read(info, TWL_MODULE_PM_RECEIVER,
+		VREG_VOLTAGE_SMPS_4030);
+
+	return vsel * 12500 + 600000;
+}
+
+static struct regulator_ops twl4030smps_ops = {
+	.set_voltage	= twl4030smps_set_voltage,
+	.get_voltage	= twl4030smps_get_voltage,
+};
+
 static int twl6030ldo_list_voltage(struct regulator_dev *rdev, unsigned index)
 {
 	struct twlreg_info	*info = rdev_get_drvdata(rdev);
@@ -856,6 +883,21 @@ static struct regulator_ops twlsmps_ops = {
 		}, \
 	}
 
+#define TWL4030_ADJUSTABLE_SMPS(label, offset, num, turnon_delay, remap_conf) \
+	{ \
+	.base = offset, \
+	.id = num, \
+	.delay = turnon_delay, \
+	.remap = remap_conf, \
+	.desc = { \
+		.name = #label, \
+		.id = TWL4030_REG_##label, \
+		.ops = &twl4030smps_ops, \
+		.type = REGULATOR_VOLTAGE, \
+		.owner = THIS_MODULE, \
+		}, \
+	}
+
 #define TWL6030_ADJUSTABLE_LDO(label, offset, min_mVolts, max_mVolts) { \
 	.base = offset, \
 	.min_mV = min_mVolts, \
@@ -947,8 +989,8 @@ static struct twlreg_info twl_regs[] = {
 	TWL4030_ADJUSTABLE_LDO(VINTANA2, 0x43, 12, 100, 0x08),
 	TWL4030_FIXED_LDO(VINTDIG, 0x47, 1500, 13, 100, 0x08),
 	TWL4030_ADJUSTABLE_LDO(VIO, 0x4b, 14, 1000, 0x08),
-	TWL4030_ADJUSTABLE_LDO(VDD1, 0x55, 15, 1000, 0x08),
-	TWL4030_ADJUSTABLE_LDO(VDD2, 0x63, 16, 1000, 0x08),
+	TWL4030_ADJUSTABLE_SMPS(VDD1, 0x55, 15, 1000, 0x08),
+	TWL4030_ADJUSTABLE_SMPS(VDD2, 0x63, 16, 1000, 0x08),
 	TWL4030_FIXED_LDO(VUSB1V5, 0x71, 1500, 17, 100, 0x08),
 	TWL4030_FIXED_LDO(VUSB1V8, 0x74, 1800, 18, 100, 0x08),
 	TWL4030_FIXED_LDO(VUSB3V1, 0x77, 3100, 19, 150, 0x08),
diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c
index 01a7df5317c..b82a1554cdc 100644
--- a/drivers/rtc/class.c
+++ b/drivers/rtc/class.c
@@ -66,7 +66,7 @@ static int rtc_suspend(struct device *dev, pm_message_t mesg)
 	 */
 	delta = timespec_sub(old_system, old_rtc);
 	delta_delta = timespec_sub(delta, old_delta);
-	if (abs(delta_delta.tv_sec)  >= 2) {
+	if (delta_delta.tv_sec < -2 || delta_delta.tv_sec >= 2) {
 		/*
 		 * if delta_delta is too large, assume time correction
 		 * has occured and set old_delta to the current delta.
@@ -100,9 +100,8 @@ static int rtc_resume(struct device *dev)
 	rtc_tm_to_time(&tm, &new_rtc.tv_sec);
 	new_rtc.tv_nsec = 0;
 
-	if (new_rtc.tv_sec <= old_rtc.tv_sec) {
-		if (new_rtc.tv_sec < old_rtc.tv_sec)
-			pr_debug("%s:  time travel!\n", dev_name(&rtc->dev));
+	if (new_rtc.tv_sec < old_rtc.tv_sec) {
+		pr_debug("%s:  time travel!\n", dev_name(&rtc->dev));
 		return 0;
 	}
 
@@ -119,7 +118,8 @@ static int rtc_resume(struct device *dev)
 	sleep_time = timespec_sub(sleep_time,
 			timespec_sub(new_system, old_system));
 
-	timekeeping_inject_sleeptime(&sleep_time);
+	if (sleep_time.tv_sec >= 0)
+		timekeeping_inject_sleeptime(&sleep_time);
 	return 0;
 }
 
diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c
index 44e91e598f8..3d9d2b97656 100644
--- a/drivers/rtc/interface.c
+++ b/drivers/rtc/interface.c
@@ -318,6 +318,20 @@ int rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm)
 }
 EXPORT_SYMBOL_GPL(rtc_read_alarm);
 
+static int ___rtc_set_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm)
+{
+	int err;
+
+	if (!rtc->ops)
+		err = -ENODEV;
+	else if (!rtc->ops->set_alarm)
+		err = -EINVAL;
+	else
+		err = rtc->ops->set_alarm(rtc->dev.parent, alarm);
+
+	return err;
+}
+
 static int __rtc_set_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm)
 {
 	struct rtc_time tm;
@@ -341,14 +355,7 @@ static int __rtc_set_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm)
 	 * over right here, before we set the alarm.
 	 */
 
-	if (!rtc->ops)
-		err = -ENODEV;
-	else if (!rtc->ops->set_alarm)
-		err = -EINVAL;
-	else
-		err = rtc->ops->set_alarm(rtc->dev.parent, alarm);
-
-	return err;
+	return ___rtc_set_alarm(rtc, alarm);
 }
 
 int rtc_set_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm)
@@ -762,6 +769,20 @@ static int rtc_timer_enqueue(struct rtc_device *rtc, struct rtc_timer *timer)
 	return 0;
 }
 
+static void rtc_alarm_disable(struct rtc_device *rtc)
+{
+	struct rtc_wkalrm alarm;
+	struct rtc_time tm;
+
+	__rtc_read_time(rtc, &tm);
+
+	alarm.time = rtc_ktime_to_tm(ktime_add(rtc_tm_to_ktime(tm),
+				     ktime_set(300, 0)));
+	alarm.enabled = 0;
+
+	___rtc_set_alarm(rtc, &alarm);
+}
+
 /**
  * rtc_timer_remove - Removes a rtc_timer from the rtc_device timerqueue
  * @rtc rtc device
@@ -783,8 +804,10 @@ static void rtc_timer_remove(struct rtc_device *rtc, struct rtc_timer *timer)
 		struct rtc_wkalrm alarm;
 		int err;
 		next = timerqueue_getnext(&rtc->timerqueue);
-		if (!next)
+		if (!next) {
+			rtc_alarm_disable(rtc);
 			return;
+		}
 		alarm.time = rtc_ktime_to_tm(next->expires);
 		alarm.enabled = 1;
 		err = __rtc_set_alarm(rtc, &alarm);
@@ -846,7 +869,8 @@ again:
 		err = __rtc_set_alarm(rtc, &alarm);
 		if (err == -ETIME)
 			goto again;
-	}
+	} else
+		rtc_alarm_disable(rtc);
 
 	mutex_unlock(&rtc->ops_lock);
 }
diff --git a/drivers/s390/cio/ccwgroup.c b/drivers/s390/cio/ccwgroup.c
index 5c567414c4b..cda9bd6e48e 100644
--- a/drivers/s390/cio/ccwgroup.c
+++ b/drivers/s390/cio/ccwgroup.c
@@ -87,6 +87,12 @@ static void __ccwgroup_remove_cdev_refs(struct ccwgroup_device *gdev)
 	}
 }
 
+static ssize_t ccwgroup_online_store(struct device *dev,
+				     struct device_attribute *attr,
+				     const char *buf, size_t count);
+static ssize_t ccwgroup_online_show(struct device *dev,
+				    struct device_attribute *attr,
+				    char *buf);
 /*
  * Provide an 'ungroup' attribute so the user can remove group devices no
  * longer needed or accidentially created. Saves memory :)
@@ -134,6 +140,20 @@ out:
 }
 
 static DEVICE_ATTR(ungroup, 0200, NULL, ccwgroup_ungroup_store);
+static DEVICE_ATTR(online, 0644, ccwgroup_online_show, ccwgroup_online_store);
+
+static struct attribute *ccwgroup_attrs[] = {
+	&dev_attr_online.attr,
+	&dev_attr_ungroup.attr,
+	NULL,
+};
+static struct attribute_group ccwgroup_attr_group = {
+	.attrs = ccwgroup_attrs,
+};
+static const struct attribute_group *ccwgroup_attr_groups[] = {
+	&ccwgroup_attr_group,
+	NULL,
+};
 
 static void
 ccwgroup_release (struct device *dev)
@@ -293,25 +313,17 @@ int ccwgroup_create_from_string(struct device *root, unsigned int creator_id,
 	}
 
 	dev_set_name(&gdev->dev, "%s", dev_name(&gdev->cdev[0]->dev));
-
+	gdev->dev.groups = ccwgroup_attr_groups;
 	rc = device_add(&gdev->dev);
 	if (rc)
 		goto error;
 	get_device(&gdev->dev);
-	rc = device_create_file(&gdev->dev, &dev_attr_ungroup);
-
-	if (rc) {
-		device_unregister(&gdev->dev);
-		goto error;
-	}
-
 	rc = __ccwgroup_create_symlinks(gdev);
 	if (!rc) {
 		mutex_unlock(&gdev->reg_mutex);
 		put_device(&gdev->dev);
 		return 0;
 	}
-	device_remove_file(&gdev->dev, &dev_attr_ungroup);
 	device_unregister(&gdev->dev);
 error:
 	for (i = 0; i < num_devices; i++)
@@ -423,7 +435,7 @@ ccwgroup_online_store (struct device *dev, struct device_attribute *attr, const
 	int ret;
 
 	if (!dev->driver)
-		return -ENODEV;
+		return -EINVAL;
 
 	gdev = to_ccwgroupdev(dev);
 	gdrv = to_ccwgroupdrv(dev->driver);
@@ -456,8 +468,6 @@ ccwgroup_online_show (struct device *dev, struct device_attribute *attr, char *b
 	return sprintf(buf, online ? "1\n" : "0\n");
 }
 
-static DEVICE_ATTR(online, 0644, ccwgroup_online_show, ccwgroup_online_store);
-
 static int
 ccwgroup_probe (struct device *dev)
 {
@@ -469,12 +479,7 @@ ccwgroup_probe (struct device *dev)
 	gdev = to_ccwgroupdev(dev);
 	gdrv = to_ccwgroupdrv(dev->driver);
 
-	if ((ret = device_create_file(dev, &dev_attr_online)))
-		return ret;
-
 	ret = gdrv->probe ? gdrv->probe(gdev) : -ENODEV;
-	if (ret)
-		device_remove_file(dev, &dev_attr_online);
 
 	return ret;
 }
@@ -485,9 +490,6 @@ ccwgroup_remove (struct device *dev)
 	struct ccwgroup_device *gdev;
 	struct ccwgroup_driver *gdrv;
 
-	device_remove_file(dev, &dev_attr_online);
-	device_remove_file(dev, &dev_attr_ungroup);
-
 	if (!dev->driver)
 		return 0;
 
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index fafb8c29954..c74e8670fab 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -2740,11 +2740,13 @@ int inline qeth_l3_get_cast_type(struct qeth_card *card, struct sk_buff *skb)
 	struct neighbour *n = NULL;
 	struct dst_entry *dst;
 
+	rcu_read_lock();
 	dst = skb_dst(skb);
 	if (dst)
 		n = dst_get_neighbour(dst);
 	if (n) {
 		cast_type = n->type;
+		rcu_read_unlock();
 		if ((cast_type == RTN_BROADCAST) ||
 		    (cast_type == RTN_MULTICAST) ||
 		    (cast_type == RTN_ANYCAST))
@@ -2752,6 +2754,8 @@ int inline qeth_l3_get_cast_type(struct qeth_card *card, struct sk_buff *skb)
 		else
 			return RTN_UNSPEC;
 	}
+	rcu_read_unlock();
+
 	/* try something else */
 	if (skb->protocol == ETH_P_IPV6)
 		return (skb_network_header(skb)[24] == 0xff) ?
@@ -2807,6 +2811,8 @@ static void qeth_l3_fill_header(struct qeth_card *card, struct qeth_hdr *hdr,
 	}
 
 	hdr->hdr.l3.length = skb->len - sizeof(struct qeth_hdr);
+
+	rcu_read_lock();
 	dst = skb_dst(skb);
 	if (dst)
 		n = dst_get_neighbour(dst);
@@ -2853,6 +2859,7 @@ static void qeth_l3_fill_header(struct qeth_card *card, struct qeth_hdr *hdr,
 				QETH_CAST_UNICAST | QETH_HDR_PASSTHRU;
 		}
 	}
+	rcu_read_unlock();
 }
 
 static inline void qeth_l3_hdr_csum(struct qeth_card *card,
diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c
index 3382475dc22..c7b6fed8873 100644
--- a/drivers/scsi/aacraid/linit.c
+++ b/drivers/scsi/aacraid/linit.c
@@ -38,6 +38,7 @@
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/pci.h>
+#include <linux/pci-aspm.h>
 #include <linux/slab.h>
 #include <linux/mutex.h>
 #include <linux/spinlock.h>
@@ -1108,6 +1109,9 @@ static int __devinit aac_probe_one(struct pci_dev *pdev,
 		unique_id++;
 	}
 
+	pci_disable_link_state(pdev, PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1 |
+			       PCIE_LINK_STATE_CLKPM);
+
 	error = pci_enable_device(pdev);
 	if (error)
 		goto out;
diff --git a/drivers/scsi/device_handler/scsi_dh.c b/drivers/scsi/device_handler/scsi_dh.c
index 0119b814779..d973325ded2 100644
--- a/drivers/scsi/device_handler/scsi_dh.c
+++ b/drivers/scsi/device_handler/scsi_dh.c
@@ -398,7 +398,15 @@ int scsi_dh_activate(struct request_queue *q, activate_complete fn, void *data)
 
 	spin_lock_irqsave(q->queue_lock, flags);
 	sdev = q->queuedata;
-	if (sdev && sdev->scsi_dh_data)
+	if (!sdev) {
+		spin_unlock_irqrestore(q->queue_lock, flags);
+		err = SCSI_DH_NOSYS;
+		if (fn)
+			fn(data, err);
+		return err;
+	}
+
+	if (sdev->scsi_dh_data)
 		scsi_dh = sdev->scsi_dh_data->scsi_dh;
 	dev = get_device(&sdev->sdev_gendev);
 	if (!scsi_dh || !dev ||
diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c
index 4f7a5829ea4..351dc0b86fa 100644
--- a/drivers/scsi/hosts.c
+++ b/drivers/scsi/hosts.c
@@ -286,6 +286,7 @@ static void scsi_host_dev_release(struct device *dev)
 {
 	struct Scsi_Host *shost = dev_to_shost(dev);
 	struct device *parent = dev->parent;
+	struct request_queue *q;
 
 	scsi_proc_hostdir_rm(shost->hostt);
 
@@ -293,9 +294,11 @@ static void scsi_host_dev_release(struct device *dev)
 		kthread_stop(shost->ehandler);
 	if (shost->work_q)
 		destroy_workqueue(shost->work_q);
-	if (shost->uspace_req_q) {
-		kfree(shost->uspace_req_q->queuedata);
-		scsi_free_queue(shost->uspace_req_q);
+	q = shost->uspace_req_q;
+	if (q) {
+		kfree(q->queuedata);
+		q->queuedata = NULL;
+		scsi_free_queue(q);
 	}
 
 	scsi_destroy_command_freelist(shost);
diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c
index b200b736b00..418ce83694a 100644
--- a/drivers/scsi/hpsa.c
+++ b/drivers/scsi/hpsa.c
@@ -23,6 +23,7 @@
 #include <linux/interrupt.h>
 #include <linux/types.h>
 #include <linux/pci.h>
+#include <linux/pci-aspm.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/delay.h>
@@ -3300,6 +3301,13 @@ static int hpsa_controller_hard_reset(struct pci_dev *pdev,
 		pmcsr &= ~PCI_PM_CTRL_STATE_MASK;
 		pmcsr |= PCI_D0;
 		pci_write_config_word(pdev, pos + PCI_PM_CTRL, pmcsr);
+
+		/*
+		 * The P600 requires a small delay when changing states.
+		 * Otherwise we may think the board did not reset and we bail.
+		 * This for kdump only and is particular to the P600.
+		 */
+		msleep(500);
 	}
 	return 0;
 }
@@ -3880,6 +3888,10 @@ static int __devinit hpsa_pci_init(struct ctlr_info *h)
 		dev_warn(&h->pdev->dev, "controller appears to be disabled\n");
 		return -ENODEV;
 	}
+
+	pci_disable_link_state(h->pdev, PCIE_LINK_STATE_L0S |
+			       PCIE_LINK_STATE_L1 | PCIE_LINK_STATE_CLKPM);
+
 	err = pci_enable_device(h->pdev);
 	if (err) {
 		dev_warn(&h->pdev->dev, "unable to enable PCI device\n");
diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index 8d636301e32..acbb9241262 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -8812,7 +8812,7 @@ static int __devinit ipr_probe_ioa(struct pci_dev *pdev,
 	uproc = readl(ioa_cfg->regs.sense_uproc_interrupt_reg32);
 	if ((mask & IPR_PCII_HRRQ_UPDATED) == 0 || (uproc & IPR_UPROCI_RESET_ALERT))
 		ioa_cfg->needs_hard_reset = 1;
-	if (interrupts & IPR_PCII_ERROR_INTERRUPTS)
+	if ((interrupts & IPR_PCII_ERROR_INTERRUPTS) || reset_devices)
 		ioa_cfg->needs_hard_reset = 1;
 	if (interrupts & IPR_PCII_IOA_UNIT_CHECKED)
 		ioa_cfg->ioa_unit_checked = 1;
diff --git a/drivers/scsi/isci/isci.h b/drivers/scsi/isci/isci.h
index d1de63312e7..8efeb6b0832 100644
--- a/drivers/scsi/isci/isci.h
+++ b/drivers/scsi/isci/isci.h
@@ -97,7 +97,7 @@
 #define SCU_MAX_COMPLETION_QUEUE_SHIFT	  (ilog2(SCU_MAX_COMPLETION_QUEUE_ENTRIES))
 
 #define SCU_ABSOLUTE_MAX_UNSOLICITED_FRAMES (4096)
-#define SCU_UNSOLICITED_FRAME_BUFFER_SIZE   (1024)
+#define SCU_UNSOLICITED_FRAME_BUFFER_SIZE   (1024U)
 #define SCU_INVALID_FRAME_INDEX             (0xFFFF)
 
 #define SCU_IO_REQUEST_MAX_SGE_SIZE         (0x00FFFFFF)
diff --git a/drivers/scsi/isci/port_config.c b/drivers/scsi/isci/port_config.c
index 486b113c634..38a99d28114 100644
--- a/drivers/scsi/isci/port_config.c
+++ b/drivers/scsi/isci/port_config.c
@@ -678,7 +678,7 @@ static void apc_agent_timeout(unsigned long data)
 	configure_phy_mask = ~port_agent->phy_configured_mask & port_agent->phy_ready_mask;
 
 	if (!configure_phy_mask)
-		return;
+		goto done;
 
 	for (index = 0; index < SCI_MAX_PHYS; index++) {
 		if ((configure_phy_mask & (1 << index)) == 0)
diff --git a/drivers/scsi/isci/request.c b/drivers/scsi/isci/request.c
index b5d3a8c4d32..225b196800a 100644
--- a/drivers/scsi/isci/request.c
+++ b/drivers/scsi/isci/request.c
@@ -1490,29 +1490,30 @@ sci_io_request_frame_handler(struct isci_request *ireq,
 		return SCI_SUCCESS;
 
 	case SCI_REQ_SMP_WAIT_RESP: {
-		struct smp_resp *rsp_hdr = &ireq->smp.rsp;
-		void *frame_header;
+		struct sas_task *task = isci_request_access_task(ireq);
+		struct scatterlist *sg = &task->smp_task.smp_resp;
+		void *frame_header, *kaddr;
+		u8 *rsp;
 
 		sci_unsolicited_frame_control_get_header(&ihost->uf_control,
-							      frame_index,
-							      &frame_header);
-
-		/* byte swap the header. */
-		word_cnt = SMP_RESP_HDR_SZ / sizeof(u32);
-		sci_swab32_cpy(rsp_hdr, frame_header, word_cnt);
+							 frame_index,
+							 &frame_header);
+		kaddr = kmap_atomic(sg_page(sg), KM_IRQ0);
+		rsp = kaddr + sg->offset;
+		sci_swab32_cpy(rsp, frame_header, 1);
 
-		if (rsp_hdr->frame_type == SMP_RESPONSE) {
+		if (rsp[0] == SMP_RESPONSE) {
 			void *smp_resp;
 
 			sci_unsolicited_frame_control_get_buffer(&ihost->uf_control,
-								      frame_index,
-								      &smp_resp);
+								 frame_index,
+								 &smp_resp);
 
-			word_cnt = (sizeof(struct smp_resp) - SMP_RESP_HDR_SZ) /
-				sizeof(u32);
-
-			sci_swab32_cpy(((u8 *) rsp_hdr) + SMP_RESP_HDR_SZ,
-				       smp_resp, word_cnt);
+			word_cnt = (sg->length/4)-1;
+			if (word_cnt > 0)
+				word_cnt = min_t(unsigned int, word_cnt,
+						 SCU_UNSOLICITED_FRAME_BUFFER_SIZE/4);
+			sci_swab32_cpy(rsp + 4, smp_resp, word_cnt);
 
 			ireq->scu_status = SCU_TASK_DONE_GOOD;
 			ireq->sci_status = SCI_SUCCESS;
@@ -1528,12 +1529,13 @@ sci_io_request_frame_handler(struct isci_request *ireq,
 				__func__,
 				ireq,
 				frame_index,
-				rsp_hdr->frame_type);
+				rsp[0]);
 
 			ireq->scu_status = SCU_TASK_DONE_SMP_FRM_TYPE_ERR;
 			ireq->sci_status = SCI_FAILURE_CONTROLLER_SPECIFIC_IO_ERR;
 			sci_change_state(&ireq->sm, SCI_REQ_COMPLETED);
 		}
+		kunmap_atomic(kaddr, KM_IRQ0);
 
 		sci_controller_release_frame(ihost, frame_index);
 
@@ -2603,18 +2605,7 @@ static void isci_request_io_request_complete(struct isci_host *ihost,
 			status   = SAM_STAT_GOOD;
 			set_bit(IREQ_COMPLETE_IN_TARGET, &request->flags);
 
-			if (task->task_proto == SAS_PROTOCOL_SMP) {
-				void *rsp = &request->smp.rsp;
-
-				dev_dbg(&ihost->pdev->dev,
-					"%s: SMP protocol completion\n",
-					__func__);
-
-				sg_copy_from_buffer(
-					&task->smp_task.smp_resp, 1,
-					rsp, sizeof(struct smp_resp));
-			} else if (completion_status
-				   == SCI_IO_SUCCESS_IO_DONE_EARLY) {
+			if (completion_status == SCI_IO_SUCCESS_IO_DONE_EARLY) {
 
 				/* This was an SSP / STP / SATA transfer.
 				 * There is a possibility that less data than
diff --git a/drivers/scsi/isci/request.h b/drivers/scsi/isci/request.h
index 7a1d5a9778e..58d70b6606e 100644
--- a/drivers/scsi/isci/request.h
+++ b/drivers/scsi/isci/request.h
@@ -174,9 +174,6 @@ struct isci_request {
 			};
 		} ssp;
 		struct {
-			struct smp_resp rsp;
-		} smp;
-		struct {
 			struct isci_stp_request req;
 			struct host_to_dev_fis cmd;
 			struct dev_to_host_fis rsp;
diff --git a/drivers/scsi/isci/sas.h b/drivers/scsi/isci/sas.h
index 462b15174d3..dc26b4aea99 100644
--- a/drivers/scsi/isci/sas.h
+++ b/drivers/scsi/isci/sas.h
@@ -204,8 +204,6 @@ struct smp_req {
 	u8 req_data[0];
 }  __packed;
 
-#define SMP_RESP_HDR_SZ	4
-
 /*
  * struct sci_sas_address - This structure depicts how a SAS address is
  *    represented by SCI.
diff --git a/drivers/scsi/libsas/sas_expander.c b/drivers/scsi/libsas/sas_expander.c
index 16ad97df5ba..37cbe4d3bb9 100644
--- a/drivers/scsi/libsas/sas_expander.c
+++ b/drivers/scsi/libsas/sas_expander.c
@@ -199,6 +199,8 @@ static void sas_set_ex_phy(struct domain_device *dev, int phy_id,
 	phy->virtual = dr->virtual;
 	phy->last_da_index = -1;
 
+	phy->phy->identify.sas_address = SAS_ADDR(phy->attached_sas_addr);
+	phy->phy->identify.device_type = phy->attached_dev_type;
 	phy->phy->identify.initiator_port_protocols = phy->attached_iproto;
 	phy->phy->identify.target_port_protocols = phy->attached_tproto;
 	phy->phy->identify.phy_identifier = phy_id;
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index 776d0198866..839ad7ba32f 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -1907,7 +1907,6 @@ static int megasas_generic_reset(struct scsi_cmnd *scmd)
 static enum
 blk_eh_timer_return megasas_reset_timer(struct scsi_cmnd *scmd)
 {
-	struct megasas_cmd *cmd = (struct megasas_cmd *)scmd->SCp.ptr;
 	struct megasas_instance *instance;
 	unsigned long flags;
 
@@ -1916,7 +1915,7 @@ blk_eh_timer_return megasas_reset_timer(struct scsi_cmnd *scmd)
 		return BLK_EH_NOT_HANDLED;
 	}
 
-	instance = cmd->instance;
+	instance = (struct megasas_instance *)scmd->device->host->hostdata;
 	if (!(instance->flag & MEGASAS_FW_BUSY)) {
 		/* FW is busy, throttle IO */
 		spin_lock_irqsave(instance->host->host_lock, flags);
diff --git a/drivers/scsi/mpt2sas/mpt2sas_scsih.c b/drivers/scsi/mpt2sas/mpt2sas_scsih.c
index 6abd2fcc43e..97aac82eef3 100644
--- a/drivers/scsi/mpt2sas/mpt2sas_scsih.c
+++ b/drivers/scsi/mpt2sas/mpt2sas_scsih.c
@@ -7461,22 +7461,27 @@ _scsih_probe_sas(struct MPT2SAS_ADAPTER *ioc)
 	/* SAS Device List */
 	list_for_each_entry_safe(sas_device, next, &ioc->sas_device_init_list,
 	    list) {
-		spin_lock_irqsave(&ioc->sas_device_lock, flags);
-		list_move_tail(&sas_device->list, &ioc->sas_device_list);
-		spin_unlock_irqrestore(&ioc->sas_device_lock, flags);
 
 		if (ioc->hide_drives)
 			continue;
 
 		if (!mpt2sas_transport_port_add(ioc, sas_device->handle,
 		    sas_device->sas_address_parent)) {
-			_scsih_sas_device_remove(ioc, sas_device);
+			list_del(&sas_device->list);
+			kfree(sas_device);
+			continue;
 		} else if (!sas_device->starget) {
 			mpt2sas_transport_port_remove(ioc,
 			    sas_device->sas_address,
 			    sas_device->sas_address_parent);
-			_scsih_sas_device_remove(ioc, sas_device);
+			list_del(&sas_device->list);
+			kfree(sas_device);
+			continue;
+
 		}
+		spin_lock_irqsave(&ioc->sas_device_lock, flags);
+		list_move_tail(&sas_device->list, &ioc->sas_device_list);
+		spin_unlock_irqrestore(&ioc->sas_device_lock, flags);
 	}
 }
 
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index fc3f168decb..6d219e48d62 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1408,6 +1408,8 @@ static void scsi_kill_request(struct request *req, struct request_queue *q)
 
 	blk_start_request(req);
 
+	scmd_printk(KERN_INFO, cmd, "killing request\n");
+
 	sdev = cmd->device;
 	starget = scsi_target(sdev);
 	shost = sdev->host;
@@ -1489,7 +1491,6 @@ static void scsi_request_fn(struct request_queue *q)
 	struct request *req;
 
 	if (!sdev) {
-		printk("scsi: killing requests for dead queue\n");
 		while ((req = blk_peek_request(q)) != NULL)
 			scsi_kill_request(req, q);
 		return;
@@ -1698,6 +1699,15 @@ struct request_queue *scsi_alloc_queue(struct scsi_device *sdev)
 
 void scsi_free_queue(struct request_queue *q)
 {
+	unsigned long flags;
+
+	WARN_ON(q->queuedata);
+
+	/* cause scsi_request_fn() to kill all non-finished requests */
+	spin_lock_irqsave(q->queue_lock, flags);
+	q->request_fn(q);
+	spin_unlock_irqrestore(q->queue_lock, flags);
+
 	blk_cleanup_queue(q);
 }
 
diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index 44e8ca398ef..b3c6d957fbd 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -319,10 +319,7 @@ static struct scsi_device *scsi_alloc_sdev(struct scsi_target *starget,
 	return sdev;
 
 out_device_destroy:
-	scsi_device_set_state(sdev, SDEV_DEL);
-	transport_destroy_device(&sdev->sdev_gendev);
-	put_device(&sdev->sdev_dev);
-	put_device(&sdev->sdev_gendev);
+	__scsi_remove_device(sdev);
 out:
 	if (display_failure_msg)
 		printk(ALLOC_FAILURE_MSG, __func__);
diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index 1871b8ae83a..9b28f39bac2 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -462,14 +462,16 @@ static void st_scsi_execute_end(struct request *req, int uptodate)
 {
 	struct st_request *SRpnt = req->end_io_data;
 	struct scsi_tape *STp = SRpnt->stp;
+	struct bio *tmp;
 
 	STp->buffer->cmdstat.midlevel_result = SRpnt->result = req->errors;
 	STp->buffer->cmdstat.residual = req->resid_len;
 
+	tmp = SRpnt->bio;
 	if (SRpnt->waiting)
 		complete(SRpnt->waiting);
 
-	blk_rq_unmap_user(SRpnt->bio);
+	blk_rq_unmap_user(tmp);
 	__blk_put_request(req->q, req);
 }
 
diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c
index fde3a2d4f12..322be7aea8b 100644
--- a/drivers/spi/spi-omap2-mcspi.c
+++ b/drivers/spi/spi-omap2-mcspi.c
@@ -1116,15 +1116,16 @@ static int __init omap2_mcspi_probe(struct platform_device *pdev)
 		status = -ENODEV;
 		goto err1;
 	}
+
+	r->start += pdata->regs_offset;
+	r->end += pdata->regs_offset;
+	mcspi->phys = r->start;
 	if (!request_mem_region(r->start, resource_size(r),
 				dev_name(&pdev->dev))) {
 		status = -EBUSY;
 		goto err1;
 	}
 
-	r->start += pdata->regs_offset;
-	r->end += pdata->regs_offset;
-	mcspi->phys = r->start;
 	mcspi->base = ioremap(r->start, resource_size(r));
 	if (!mcspi->base) {
 		dev_dbg(&pdev->dev, "can't ioremap MCSPI\n");
diff --git a/drivers/staging/brcm80211/brcmsmac/mac80211_if.c b/drivers/staging/brcm80211/brcmsmac/mac80211_if.c
index d6de44e430d..3cb92fc0391 100644
--- a/drivers/staging/brcm80211/brcmsmac/mac80211_if.c
+++ b/drivers/staging/brcm80211/brcmsmac/mac80211_if.c
@@ -975,6 +975,10 @@ static struct ieee80211_channel brcms_5ghz_nphy_chantable[] = {
 	.hw_value = (rate100m / 5), \
 }
 
+/*
+ * The rate table is used for both 2.4G and 5G rates. The
+ * latter being a subset as it does not support CCK rates.
+ */
 static struct ieee80211_rate legacy_ratetable[] = {
 	RATE(10, 0),
 	RATE(20, IEEE80211_RATE_SHORT_PREAMBLE),
@@ -1016,8 +1020,9 @@ static struct ieee80211_supported_band brcms_band_5GHz_nphy = {
 	.band = IEEE80211_BAND_5GHZ,
 	.channels = brcms_5ghz_nphy_chantable,
 	.n_channels = ARRAY_SIZE(brcms_5ghz_nphy_chantable),
-	.bitrates = legacy_ratetable + 4,
-	.n_bitrates = ARRAY_SIZE(legacy_ratetable) - 4,
+	.bitrates = legacy_ratetable + BRCMS_LEGACY_5G_RATE_OFFSET,
+	.n_bitrates = ARRAY_SIZE(legacy_ratetable) -
+			BRCMS_LEGACY_5G_RATE_OFFSET,
 	.ht_cap = {
 		   /* use IEEE80211_HT_CAP_* from include/linux/ieee80211.h */
 		   .cap = IEEE80211_HT_CAP_GRN_FLD | IEEE80211_HT_CAP_SGI_20 | IEEE80211_HT_CAP_SGI_40 | IEEE80211_HT_CAP_40MHZ_INTOLERANT,	/* No 40 mhz yet */
diff --git a/drivers/staging/brcm80211/brcmsmac/mac80211_if.h b/drivers/staging/brcm80211/brcmsmac/mac80211_if.h
index 40e3d375ea9..3be8655c57e 100644
--- a/drivers/staging/brcm80211/brcmsmac/mac80211_if.h
+++ b/drivers/staging/brcm80211/brcmsmac/mac80211_if.h
@@ -20,6 +20,12 @@
 #include <linux/timer.h>
 #include <linux/interrupt.h>
 
+/*
+ * Starting index for 5G rates in the
+ * legacy rate table.
+ */
+#define BRCMS_LEGACY_5G_RATE_OFFSET	4
+
 /* softmac ioctl definitions */
 #define BRCMS_SET_SHORTSLOT_OVERRIDE		146
 
diff --git a/drivers/staging/brcm80211/brcmsmac/main.c b/drivers/staging/brcm80211/brcmsmac/main.c
index 1763c4535cd..96541630aad 100644
--- a/drivers/staging/brcm80211/brcmsmac/main.c
+++ b/drivers/staging/brcm80211/brcmsmac/main.c
@@ -4608,6 +4608,14 @@ prep_mac80211_status(struct brcms_c_info *wlc, struct d11rxhdr *rxh,
 			wiphy_err(wlc->wiphy, "%s: Unknown rate\n", __func__);
 		}
 
+		/*
+		 * For 5GHz, we should decrease the index as it is
+		 * a subset of the 2.4G rates. See bitrates field
+		 * of brcms_band_5GHz_nphy (in mac80211_if.c).
+		 */
+		if (rx_status->band == IEEE80211_BAND_5GHZ)
+			rx_status->rate_idx -= BRCMS_LEGACY_5G_RATE_OFFSET;
+
 		/* Determine short preamble and rate_idx */
 		preamble = 0;
 		if (IS_CCK(rspec)) {
diff --git a/drivers/staging/comedi/comedi_fops.c b/drivers/staging/comedi/comedi_fops.c
index e90e3cceb5f..b347cda3ca9 100644
--- a/drivers/staging/comedi/comedi_fops.c
+++ b/drivers/staging/comedi/comedi_fops.c
@@ -1432,7 +1432,21 @@ static int do_cancel(struct comedi_device *dev, struct comedi_subdevice *s)
 	return ret;
 }
 
-static void comedi_unmap(struct vm_area_struct *area)
+
+static void comedi_vm_open(struct vm_area_struct *area)
+{
+	struct comedi_async *async;
+	struct comedi_device *dev;
+
+	async = area->vm_private_data;
+	dev = async->subdevice->device;
+
+	mutex_lock(&dev->mutex);
+	async->mmap_count++;
+	mutex_unlock(&dev->mutex);
+}
+
+static void comedi_vm_close(struct vm_area_struct *area)
 {
 	struct comedi_async *async;
 	struct comedi_device *dev;
@@ -1446,15 +1460,13 @@ static void comedi_unmap(struct vm_area_struct *area)
 }
 
 static struct vm_operations_struct comedi_vm_ops = {
-	.close = comedi_unmap,
+	.open = comedi_vm_open,
+	.close = comedi_vm_close,
 };
 
 static int comedi_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	const unsigned minor = iminor(file->f_dentry->d_inode);
-	struct comedi_device_file_info *dev_file_info =
-	    comedi_get_device_file_info(minor);
-	struct comedi_device *dev = dev_file_info->device;
 	struct comedi_async *async = NULL;
 	unsigned long start = vma->vm_start;
 	unsigned long size;
@@ -1462,6 +1474,15 @@ static int comedi_mmap(struct file *file, struct vm_area_struct *vma)
 	int i;
 	int retval;
 	struct comedi_subdevice *s;
+	struct comedi_device_file_info *dev_file_info;
+	struct comedi_device *dev;
+
+	dev_file_info = comedi_get_device_file_info(minor);
+	if (dev_file_info == NULL)
+	        return -ENODEV;
+	dev = dev_file_info->device;
+	if (dev == NULL)
+	        return -ENODEV;
 
 	mutex_lock(&dev->mutex);
 	if (!dev->attached) {
@@ -1528,11 +1549,17 @@ static unsigned int comedi_poll(struct file *file, poll_table * wait)
 {
 	unsigned int mask = 0;
 	const unsigned minor = iminor(file->f_dentry->d_inode);
-	struct comedi_device_file_info *dev_file_info =
-	    comedi_get_device_file_info(minor);
-	struct comedi_device *dev = dev_file_info->device;
 	struct comedi_subdevice *read_subdev;
 	struct comedi_subdevice *write_subdev;
+	struct comedi_device_file_info *dev_file_info;
+	struct comedi_device *dev;
+	dev_file_info = comedi_get_device_file_info(minor);
+
+	if (dev_file_info == NULL)
+	        return -ENODEV;
+	dev = dev_file_info->device;
+	if (dev == NULL)
+	        return -ENODEV;
 
 	mutex_lock(&dev->mutex);
 	if (!dev->attached) {
@@ -1578,9 +1605,15 @@ static ssize_t comedi_write(struct file *file, const char __user *buf,
 	int n, m, count = 0, retval = 0;
 	DECLARE_WAITQUEUE(wait, current);
 	const unsigned minor = iminor(file->f_dentry->d_inode);
-	struct comedi_device_file_info *dev_file_info =
-	    comedi_get_device_file_info(minor);
-	struct comedi_device *dev = dev_file_info->device;
+	struct comedi_device_file_info *dev_file_info;
+	struct comedi_device *dev;
+	dev_file_info = comedi_get_device_file_info(minor);
+
+	if (dev_file_info == NULL)
+	        return -ENODEV;
+	dev = dev_file_info->device;
+	if (dev == NULL)
+	        return -ENODEV;
 
 	if (!dev->attached) {
 		DPRINTK("no driver configured on comedi%i\n", dev->minor);
@@ -1640,11 +1673,11 @@ static ssize_t comedi_write(struct file *file, const char __user *buf,
 				retval = -EAGAIN;
 				break;
 			}
+			schedule();
 			if (signal_pending(current)) {
 				retval = -ERESTARTSYS;
 				break;
 			}
-			schedule();
 			if (!s->busy)
 				break;
 			if (s->busy != file) {
@@ -1683,9 +1716,15 @@ static ssize_t comedi_read(struct file *file, char __user *buf, size_t nbytes,
 	int n, m, count = 0, retval = 0;
 	DECLARE_WAITQUEUE(wait, current);
 	const unsigned minor = iminor(file->f_dentry->d_inode);
-	struct comedi_device_file_info *dev_file_info =
-	    comedi_get_device_file_info(minor);
-	struct comedi_device *dev = dev_file_info->device;
+	struct comedi_device_file_info *dev_file_info;
+	struct comedi_device *dev;
+	dev_file_info = comedi_get_device_file_info(minor);
+
+	if (dev_file_info == NULL)
+	        return -ENODEV;
+	dev = dev_file_info->device;
+	if (dev == NULL)
+	        return -ENODEV;
 
 	if (!dev->attached) {
 		DPRINTK("no driver configured on comedi%i\n", dev->minor);
@@ -1741,11 +1780,11 @@ static ssize_t comedi_read(struct file *file, char __user *buf, size_t nbytes,
 				retval = -EAGAIN;
 				break;
 			}
+			schedule();
 			if (signal_pending(current)) {
 				retval = -ERESTARTSYS;
 				break;
 			}
-			schedule();
 			if (!s->busy) {
 				retval = 0;
 				break;
@@ -1885,11 +1924,17 @@ ok:
 static int comedi_close(struct inode *inode, struct file *file)
 {
 	const unsigned minor = iminor(inode);
-	struct comedi_device_file_info *dev_file_info =
-	    comedi_get_device_file_info(minor);
-	struct comedi_device *dev = dev_file_info->device;
 	struct comedi_subdevice *s = NULL;
 	int i;
+	struct comedi_device_file_info *dev_file_info;
+	struct comedi_device *dev;
+	dev_file_info = comedi_get_device_file_info(minor);
+
+	if (dev_file_info == NULL)
+	        return -ENODEV;
+	dev = dev_file_info->device;
+	if (dev == NULL)
+	        return -ENODEV;
 
 	mutex_lock(&dev->mutex);
 
@@ -1923,10 +1968,15 @@ static int comedi_close(struct inode *inode, struct file *file)
 static int comedi_fasync(int fd, struct file *file, int on)
 {
 	const unsigned minor = iminor(file->f_dentry->d_inode);
-	struct comedi_device_file_info *dev_file_info =
-	    comedi_get_device_file_info(minor);
+	struct comedi_device_file_info *dev_file_info;
+	struct comedi_device *dev;
+	dev_file_info = comedi_get_device_file_info(minor);
 
-	struct comedi_device *dev = dev_file_info->device;
+	if (dev_file_info == NULL)
+	        return -ENODEV;
+	dev = dev_file_info->device;
+	if (dev == NULL)
+	        return -ENODEV;
 
 	return fasync_helper(fd, file, on, &dev->async_queue);
 }
diff --git a/drivers/staging/hv/hyperv_storage.h b/drivers/staging/hv/hyperv_storage.h
index a01f9a07c98..5af82f4235b 100644
--- a/drivers/staging/hv/hyperv_storage.h
+++ b/drivers/staging/hv/hyperv_storage.h
@@ -218,6 +218,7 @@ struct vstor_packet {
 #define STORVSC_MAX_LUNS_PER_TARGET			64
 #define STORVSC_MAX_TARGETS				1
 #define STORVSC_MAX_CHANNELS				1
+#define STORVSC_MAX_CMD_LEN				16
 
 struct hv_storvsc_request;
 
diff --git a/drivers/staging/hv/netvsc_drv.c b/drivers/staging/hv/netvsc_drv.c
index 61989f0d9f0..88d519359e6 100644
--- a/drivers/staging/hv/netvsc_drv.c
+++ b/drivers/staging/hv/netvsc_drv.c
@@ -217,8 +217,8 @@ void netvsc_linkstatus_callback(struct hv_device *device_obj,
 	if (status == 1) {
 		netif_carrier_on(net);
 		netif_wake_queue(net);
-		netif_notify_peers(net);
 		ndev_ctx = netdev_priv(net);
+		schedule_delayed_work(&ndev_ctx->dwork, 0);
 		schedule_delayed_work(&ndev_ctx->dwork, msecs_to_jiffies(20));
 	} else {
 		netif_carrier_off(net);
diff --git a/drivers/staging/hv/storvsc_drv.c b/drivers/staging/hv/storvsc_drv.c
index 7effaf32e25..26983ac1ae4 100644
--- a/drivers/staging/hv/storvsc_drv.c
+++ b/drivers/staging/hv/storvsc_drv.c
@@ -701,6 +701,8 @@ static int storvsc_probe(struct hv_device *device)
 	host->max_id = STORVSC_MAX_TARGETS;
 	/* max # of channels */
 	host->max_channel = STORVSC_MAX_CHANNELS - 1;
+	/* max cmd length */
+	host->max_cmd_len = STORVSC_MAX_CMD_LEN;
 
 	/* Register the HBA and start the scsi bus scan */
 	ret = scsi_add_host(host, &device->device);
diff --git a/drivers/staging/quatech_usb2/quatech_usb2.c b/drivers/staging/quatech_usb2/quatech_usb2.c
index ca098cabc2b..02fafecd477 100644
--- a/drivers/staging/quatech_usb2/quatech_usb2.c
+++ b/drivers/staging/quatech_usb2/quatech_usb2.c
@@ -916,9 +916,10 @@ static int qt2_ioctl(struct tty_struct *tty,
 		dbg("%s() port %d, cmd == TIOCMIWAIT enter",
 			__func__, port->number);
 		prev_msr_value = port_extra->shadowMSR  & QT2_SERIAL_MSR_MASK;
+		barrier();
+		__set_current_state(TASK_INTERRUPTIBLE);
 		while (1) {
 			add_wait_queue(&port_extra->wait, &wait);
-			set_current_state(TASK_INTERRUPTIBLE);
 			schedule();
 			dbg("%s(): port %d, cmd == TIOCMIWAIT here\n",
 				__func__, port->number);
@@ -926,9 +927,12 @@ static int qt2_ioctl(struct tty_struct *tty,
 			/* see if a signal woke us up */
 			if (signal_pending(current))
 				return -ERESTARTSYS;
+			set_current_state(TASK_INTERRUPTIBLE);
 			msr_value = port_extra->shadowMSR & QT2_SERIAL_MSR_MASK;
-			if (msr_value == prev_msr_value)
+			if (msr_value == prev_msr_value) {
+				__set_current_state(TASK_RUNNING);
 				return -EIO;  /* no change - error */
+			}
 			if ((arg & TIOCM_RNG &&
 				((prev_msr_value & QT2_SERIAL_MSR_RI) ==
 					(msr_value & QT2_SERIAL_MSR_RI))) ||
@@ -941,6 +945,7 @@ static int qt2_ioctl(struct tty_struct *tty,
 				(arg & TIOCM_CTS &&
 				((prev_msr_value & QT2_SERIAL_MSR_CTS) ==
 					(msr_value & QT2_SERIAL_MSR_CTS)))) {
+				__set_current_state(TASK_RUNNING);
 				return 0;
 			}
 		} /* end inifinite while */
diff --git a/drivers/staging/rts_pstor/rtsx.c b/drivers/staging/rts_pstor/rtsx.c
index 16c73fbff51..890e6cce6d3 100644
--- a/drivers/staging/rts_pstor/rtsx.c
+++ b/drivers/staging/rts_pstor/rtsx.c
@@ -1015,6 +1015,7 @@ static int __devinit rtsx_probe(struct pci_dev *pci, const struct pci_device_id
 	th = kthread_create(rtsx_scan_thread, dev, "rtsx-scan");
 	if (IS_ERR(th)) {
 		printk(KERN_ERR "Unable to start the device-scanning thread\n");
+		complete(&dev->scanning_done);
 		quiesce_and_remove_host(dev);
 		err = PTR_ERR(th);
 		goto errout;
diff --git a/drivers/staging/serqt_usb2/serqt_usb2.c b/drivers/staging/serqt_usb2/serqt_usb2.c
index 12f5eba0355..48aa61eb9c7 100644
--- a/drivers/staging/serqt_usb2/serqt_usb2.c
+++ b/drivers/staging/serqt_usb2/serqt_usb2.c
@@ -24,7 +24,6 @@ static int debug;
 #define DRIVER_DESC "Quatech USB to Serial Driver"
 
 #define	USB_VENDOR_ID_QUATECH			0x061d	/* Quatech VID */
-#define QUATECH_SSU100	0xC020	/* SSU100 */
 #define QUATECH_SSU200	0xC030	/* SSU200 */
 #define QUATECH_DSU100	0xC040	/* DSU100 */
 #define QUATECH_DSU200	0xC050	/* DSU200 */
@@ -127,7 +126,6 @@ static int debug;
 #define RS232_MODE          0x00
 
 static const struct usb_device_id serqt_id_table[] = {
-	{USB_DEVICE(USB_VENDOR_ID_QUATECH, QUATECH_SSU100)},
 	{USB_DEVICE(USB_VENDOR_ID_QUATECH, QUATECH_SSU200)},
 	{USB_DEVICE(USB_VENDOR_ID_QUATECH, QUATECH_DSU100)},
 	{USB_DEVICE(USB_VENDOR_ID_QUATECH, QUATECH_DSU200)},
@@ -775,7 +773,6 @@ static int qt_startup(struct usb_serial *serial)
 	}
 
 	switch (serial->dev->descriptor.idProduct) {
-	case QUATECH_SSU100:
 	case QUATECH_DSU100:
 	case QUATECH_QSU100:
 	case QUATECH_ESU100A:
diff --git a/drivers/staging/usbip/usbip_common.h b/drivers/staging/usbip/usbip_common.h
index 074ac4267d3..be216175ae8 100644
--- a/drivers/staging/usbip/usbip_common.h
+++ b/drivers/staging/usbip/usbip_common.h
@@ -126,12 +126,12 @@ extern struct device_attribute dev_attr_usbip_debug;
  *
  */
 #define USBIP_CMD_SUBMIT	0x0001
-#define USBIP_RET_SUBMIT	0x0002
-#define USBIP_CMD_UNLINK	0x0003
+#define USBIP_CMD_UNLINK	0x0002
+#define USBIP_RET_SUBMIT	0x0003
 #define USBIP_RET_UNLINK	0x0004
 
-#define USBIP_DIR_IN	0x00
-#define USBIP_DIR_OUT	0x01
+#define USBIP_DIR_OUT	0x00
+#define USBIP_DIR_IN	0x01
 
 /**
  * struct usbip_header_basic - data pertinent to every request
diff --git a/drivers/staging/usbip/vhci_rx.c b/drivers/staging/usbip/vhci_rx.c
index 09c44abb89e..3872b8cccdc 100644
--- a/drivers/staging/usbip/vhci_rx.c
+++ b/drivers/staging/usbip/vhci_rx.c
@@ -68,6 +68,7 @@ static void vhci_recv_ret_submit(struct vhci_device *vdev,
 {
 	struct usbip_device *ud = &vdev->ud;
 	struct urb *urb;
+	unsigned long flags;
 
 	spin_lock(&vdev->priv_lock);
 	urb = pickup_urb_and_free_priv(vdev, pdu->base.seqnum);
@@ -101,9 +102,9 @@ static void vhci_recv_ret_submit(struct vhci_device *vdev,
 
 	usbip_dbg_vhci_rx("now giveback urb %p\n", urb);
 
-	spin_lock(&the_controller->lock);
+	spin_lock_irqsave(&the_controller->lock, flags);
 	usb_hcd_unlink_urb_from_ep(vhci_to_hcd(the_controller), urb);
-	spin_unlock(&the_controller->lock);
+	spin_unlock_irqrestore(&the_controller->lock, flags);
 
 	usb_hcd_giveback_urb(vhci_to_hcd(the_controller), urb, urb->status);
 
@@ -141,6 +142,7 @@ static void vhci_recv_ret_unlink(struct vhci_device *vdev,
 {
 	struct vhci_unlink *unlink;
 	struct urb *urb;
+	unsigned long flags;
 
 	usbip_dump_header(pdu);
 
@@ -170,9 +172,9 @@ static void vhci_recv_ret_unlink(struct vhci_device *vdev,
 		urb->status = pdu->u.ret_unlink.status;
 		pr_info("urb->status %d\n", urb->status);
 
-		spin_lock(&the_controller->lock);
+		spin_lock_irqsave(&the_controller->lock, flags);
 		usb_hcd_unlink_urb_from_ep(vhci_to_hcd(the_controller), urb);
-		spin_unlock(&the_controller->lock);
+		spin_unlock_irqrestore(&the_controller->lock, flags);
 
 		usb_hcd_giveback_urb(vhci_to_hcd(the_controller), urb,
 				     urb->status);
diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index 6a4ea29c2f3..26a5d8b94ba 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -1079,7 +1079,9 @@ attach_cmd:
 	 */
 	if (!cmd->immediate_data) {
 		cmdsn_ret = iscsit_sequence_cmd(conn, cmd, hdr->cmdsn);
-		if (cmdsn_ret == CMDSN_ERROR_CANNOT_RECOVER)
+		if (cmdsn_ret == CMDSN_LOWER_THAN_EXP)
+			return 0;
+		else if (cmdsn_ret == CMDSN_ERROR_CANNOT_RECOVER)
 			return iscsit_add_reject_from_cmd(
 				ISCSI_REASON_PROTOCOL_ERROR,
 				1, 0, buf, cmd);
@@ -1819,17 +1821,16 @@ attach:
 		int cmdsn_ret = iscsit_sequence_cmd(conn, cmd, hdr->cmdsn);
 		if (cmdsn_ret == CMDSN_HIGHER_THAN_EXP)
 			out_of_order_cmdsn = 1;
-		else if (cmdsn_ret == CMDSN_LOWER_THAN_EXP) {
+		else if (cmdsn_ret == CMDSN_LOWER_THAN_EXP)
 			return 0;
-		} else { /* (cmdsn_ret == CMDSN_ERROR_CANNOT_RECOVER) */
+		else if (cmdsn_ret == CMDSN_ERROR_CANNOT_RECOVER)
 			return iscsit_add_reject_from_cmd(
 					ISCSI_REASON_PROTOCOL_ERROR,
 					1, 0, buf, cmd);
-		}
 	}
 	iscsit_ack_from_expstatsn(conn, hdr->exp_statsn);
 
-	if (out_of_order_cmdsn)
+	if (out_of_order_cmdsn || !(hdr->opcode & ISCSI_OP_IMMEDIATE))
 		return 0;
 	/*
 	 * Found the referenced task, send to transport for processing.
diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c
index aa2d6799723..fb85b35bd2f 100644
--- a/drivers/target/loopback/tcm_loop.c
+++ b/drivers/target/loopback/tcm_loop.c
@@ -174,6 +174,24 @@ static int tcm_loop_new_cmd_map(struct se_cmd *se_cmd)
 		sgl_bidi = sdb->table.sgl;
 		sgl_bidi_count = sdb->table.nents;
 	}
+	/*
+	 * Because some userspace code via scsi-generic do not memset their
+	 * associated read buffers, go ahead and do that here for type
+	 * SCF_SCSI_CONTROL_SG_IO_CDB.  Also note that this is currently
+	 * guaranteed to be a single SGL for SCF_SCSI_CONTROL_SG_IO_CDB
+	 * by target core in transport_generic_allocate_tasks() ->
+	 * transport_generic_cmd_sequencer().
+	 */
+	if (se_cmd->se_cmd_flags & SCF_SCSI_CONTROL_SG_IO_CDB &&
+	    se_cmd->data_direction == DMA_FROM_DEVICE) {
+		struct scatterlist *sg = scsi_sglist(sc);
+		unsigned char *buf = kmap(sg_page(sg)) + sg->offset;
+
+		if (buf != NULL) {
+			memset(buf, 0, sg->length);
+			kunmap(sg_page(sg));
+		}
+	}
 
 	/* Tell the core about our preallocated memory */
 	ret = transport_generic_map_mem_to_cmd(se_cmd, scsi_sglist(sc),
diff --git a/drivers/target/target_core_alua.c b/drivers/target/target_core_alua.c
index 98c98a3a025..8badcb46943 100644
--- a/drivers/target/target_core_alua.c
+++ b/drivers/target/target_core_alua.c
@@ -68,6 +68,15 @@ int core_emulate_report_target_port_groups(struct se_cmd *cmd)
 	unsigned char *buf;
 	u32 rd_len = 0, off = 4; /* Skip over RESERVED area to first
 				    Target port group descriptor */
+	/*
+	 * Need at least 4 bytes of response data or else we can't
+	 * even fit the return data length.
+	 */
+	if (cmd->data_length < 4) {
+		pr_warn("REPORT TARGET PORT GROUPS allocation length %u"
+			" too small\n", cmd->data_length);
+		return -EINVAL;
+	}
 
 	buf = transport_kmap_first_data_page(cmd);
 
@@ -75,6 +84,17 @@ int core_emulate_report_target_port_groups(struct se_cmd *cmd)
 	list_for_each_entry(tg_pt_gp, &su_dev->t10_alua.tg_pt_gps_list,
 			tg_pt_gp_list) {
 		/*
+		 * Check if the Target port group and Target port descriptor list
+		 * based on tg_pt_gp_members count will fit into the response payload.
+		 * Otherwise, bump rd_len to let the initiator know we have exceeded
+		 * the allocation length and the response is truncated.
+		 */
+		if ((off + 8 + (tg_pt_gp->tg_pt_gp_members * 4)) >
+		     cmd->data_length) {
+			rd_len += 8 + (tg_pt_gp->tg_pt_gp_members * 4);
+			continue;
+		}
+		/*
 		 * PREF: Preferred target port bit, determine if this
 		 * bit should be set for port group.
 		 */
diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c
index 27d4925e51c..5c1b8c599f6 100644
--- a/drivers/target/target_core_tmr.c
+++ b/drivers/target/target_core_tmr.c
@@ -67,15 +67,16 @@ void core_tmr_release_req(
 	struct se_tmr_req *tmr)
 {
 	struct se_device *dev = tmr->tmr_dev;
+	unsigned long flags;
 
 	if (!dev) {
 		kmem_cache_free(se_tmr_req_cache, tmr);
 		return;
 	}
 
-	spin_lock_irq(&dev->se_tmr_lock);
+	spin_lock_irqsave(&dev->se_tmr_lock, flags);
 	list_del(&tmr->tmr_list);
-	spin_unlock_irq(&dev->se_tmr_lock);
+	spin_unlock_irqrestore(&dev->se_tmr_lock, flags);
 
 	kmem_cache_free(se_tmr_req_cache, tmr);
 }
@@ -100,54 +101,20 @@ static void core_tmr_handle_tas_abort(
 	transport_cmd_finish_abort(cmd, 0);
 }
 
-int core_tmr_lun_reset(
+static void core_tmr_drain_tmr_list(
 	struct se_device *dev,
 	struct se_tmr_req *tmr,
-	struct list_head *preempt_and_abort_list,
-	struct se_cmd *prout_cmd)
+	struct list_head *preempt_and_abort_list)
 {
-	struct se_cmd *cmd, *tcmd;
-	struct se_node_acl *tmr_nacl = NULL;
-	struct se_portal_group *tmr_tpg = NULL;
-	struct se_queue_obj *qobj = &dev->dev_queue_obj;
+	LIST_HEAD(drain_tmr_list);
 	struct se_tmr_req *tmr_p, *tmr_pp;
-	struct se_task *task, *task_tmp;
+	struct se_cmd *cmd;
 	unsigned long flags;
-	int fe_count, tas;
-	/*
-	 * TASK_ABORTED status bit, this is configurable via ConfigFS
-	 * struct se_device attributes.  spc4r17 section 7.4.6 Control mode page
-	 *
-	 * A task aborted status (TAS) bit set to zero specifies that aborted
-	 * tasks shall be terminated by the device server without any response
-	 * to the application client. A TAS bit set to one specifies that tasks
-	 * aborted by the actions of an I_T nexus other than the I_T nexus on
-	 * which the command was received shall be completed with TASK ABORTED
-	 * status (see SAM-4).
-	 */
-	tas = dev->se_sub_dev->se_dev_attrib.emulate_tas;
-	/*
-	 * Determine if this se_tmr is coming from a $FABRIC_MOD
-	 * or struct se_device passthrough..
-	 */
-	if (tmr && tmr->task_cmd && tmr->task_cmd->se_sess) {
-		tmr_nacl = tmr->task_cmd->se_sess->se_node_acl;
-		tmr_tpg = tmr->task_cmd->se_sess->se_tpg;
-		if (tmr_nacl && tmr_tpg) {
-			pr_debug("LUN_RESET: TMR caller fabric: %s"
-				" initiator port %s\n",
-				tmr_tpg->se_tpg_tfo->get_fabric_name(),
-				tmr_nacl->initiatorname);
-		}
-	}
-	pr_debug("LUN_RESET: %s starting for [%s], tas: %d\n",
-		(preempt_and_abort_list) ? "Preempt" : "TMR",
-		dev->transport->name, tas);
 	/*
 	 * Release all pending and outgoing TMRs aside from the received
 	 * LUN_RESET tmr..
 	 */
-	spin_lock_irq(&dev->se_tmr_lock);
+	spin_lock_irqsave(&dev->se_tmr_lock, flags);
 	list_for_each_entry_safe(tmr_p, tmr_pp, &dev->dev_tmr_list, tmr_list) {
 		/*
 		 * Allow the received TMR to return with FUNCTION_COMPLETE.
@@ -169,29 +136,48 @@ int core_tmr_lun_reset(
 		    (core_scsi3_check_cdb_abort_and_preempt(
 					preempt_and_abort_list, cmd) != 0))
 			continue;
-		spin_unlock_irq(&dev->se_tmr_lock);
 
-		spin_lock_irqsave(&cmd->t_state_lock, flags);
+		spin_lock(&cmd->t_state_lock);
 		if (!atomic_read(&cmd->t_transport_active)) {
-			spin_unlock_irqrestore(&cmd->t_state_lock, flags);
-			spin_lock_irq(&dev->se_tmr_lock);
+			spin_unlock(&cmd->t_state_lock);
 			continue;
 		}
 		if (cmd->t_state == TRANSPORT_ISTATE_PROCESSING) {
-			spin_unlock_irqrestore(&cmd->t_state_lock, flags);
-			spin_lock_irq(&dev->se_tmr_lock);
+			spin_unlock(&cmd->t_state_lock);
 			continue;
 		}
+		spin_unlock(&cmd->t_state_lock);
+
+		list_move_tail(&tmr_p->tmr_list, &drain_tmr_list);
+	}
+	spin_unlock_irqrestore(&dev->se_tmr_lock, flags);
+
+	while (!list_empty(&drain_tmr_list)) {
+		tmr = list_entry(drain_tmr_list.next, struct se_tmr_req, tmr_list);
+		list_del(&tmr->tmr_list);
+		cmd = tmr->task_cmd;
+
 		pr_debug("LUN_RESET: %s releasing TMR %p Function: 0x%02x,"
 			" Response: 0x%02x, t_state: %d\n",
-			(preempt_and_abort_list) ? "Preempt" : "", tmr_p,
-			tmr_p->function, tmr_p->response, cmd->t_state);
-		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+			(preempt_and_abort_list) ? "Preempt" : "", tmr,
+			tmr->function, tmr->response, cmd->t_state);
 
 		transport_cmd_finish_abort_tmr(cmd);
-		spin_lock_irq(&dev->se_tmr_lock);
 	}
-	spin_unlock_irq(&dev->se_tmr_lock);
+}
+
+static void core_tmr_drain_task_list(
+	struct se_device *dev,
+	struct se_cmd *prout_cmd,
+	struct se_node_acl *tmr_nacl,
+	int tas,
+	struct list_head *preempt_and_abort_list)
+{
+	LIST_HEAD(drain_task_list);
+	struct se_cmd *cmd;
+	struct se_task *task, *task_tmp;
+	unsigned long flags;
+	int fe_count;
 	/*
 	 * Complete outstanding struct se_task CDBs with TASK_ABORTED SAM status.
 	 * This is following sam4r17, section 5.6 Aborting commands, Table 38
@@ -236,9 +222,23 @@ int core_tmr_lun_reset(
 		if (prout_cmd == cmd)
 			continue;
 
-		list_del(&task->t_state_list);
+		list_move_tail(&task->t_state_list, &drain_task_list);
 		atomic_set(&task->task_state_active, 0);
-		spin_unlock_irqrestore(&dev->execute_task_lock, flags);
+		/*
+		 * Remove from task execute list before processing drain_task_list
+		 */
+		if (atomic_read(&task->task_execute_queue) != 0) {
+			list_del(&task->t_execute_list);
+			atomic_set(&task->task_execute_queue, 0);
+			atomic_dec(&dev->execute_tasks);
+		}
+	}
+	spin_unlock_irqrestore(&dev->execute_task_lock, flags);
+
+	while (!list_empty(&drain_task_list)) {
+		task = list_entry(drain_task_list.next, struct se_task, t_state_list);
+		list_del(&task->t_state_list);
+		cmd = task->task_se_cmd;
 
 		spin_lock_irqsave(&cmd->t_state_lock, flags);
 		pr_debug("LUN_RESET: %s cmd: %p task: %p"
@@ -275,20 +275,14 @@ int core_tmr_lun_reset(
 
 			atomic_set(&task->task_active, 0);
 			atomic_set(&task->task_stop, 0);
-		} else {
-			if (atomic_read(&task->task_execute_queue) != 0)
-				transport_remove_task_from_execute_queue(task, dev);
 		}
 		__transport_stop_task_timer(task, &flags);
 
 		if (!atomic_dec_and_test(&cmd->t_task_cdbs_ex_left)) {
-			spin_unlock_irqrestore(
-					&cmd->t_state_lock, flags);
+			spin_unlock_irqrestore(&cmd->t_state_lock, flags);
 			pr_debug("LUN_RESET: Skipping task: %p, dev: %p for"
 				" t_task_cdbs_ex_left: %d\n", task, dev,
 				atomic_read(&cmd->t_task_cdbs_ex_left));
-
-			spin_lock_irqsave(&dev->execute_task_lock, flags);
 			continue;
 		}
 		fe_count = atomic_read(&cmd->t_fe_count);
@@ -298,22 +292,31 @@ int core_tmr_lun_reset(
 				" task: %p, t_fe_count: %d dev: %p\n", task,
 				fe_count, dev);
 			atomic_set(&cmd->t_transport_aborted, 1);
-			spin_unlock_irqrestore(&cmd->t_state_lock,
-						flags);
-			core_tmr_handle_tas_abort(tmr_nacl, cmd, tas, fe_count);
+			spin_unlock_irqrestore(&cmd->t_state_lock, flags);
 
-			spin_lock_irqsave(&dev->execute_task_lock, flags);
+			core_tmr_handle_tas_abort(tmr_nacl, cmd, tas, fe_count);
 			continue;
 		}
 		pr_debug("LUN_RESET: Got t_transport_active = 0 for task: %p,"
 			" t_fe_count: %d dev: %p\n", task, fe_count, dev);
 		atomic_set(&cmd->t_transport_aborted, 1);
 		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
-		core_tmr_handle_tas_abort(tmr_nacl, cmd, tas, fe_count);
 
-		spin_lock_irqsave(&dev->execute_task_lock, flags);
+		core_tmr_handle_tas_abort(tmr_nacl, cmd, tas, fe_count);
 	}
-	spin_unlock_irqrestore(&dev->execute_task_lock, flags);
+}
+
+static void core_tmr_drain_cmd_list(
+	struct se_device *dev,
+	struct se_cmd *prout_cmd,
+	struct se_node_acl *tmr_nacl,
+	int tas,
+	struct list_head *preempt_and_abort_list)
+{
+	LIST_HEAD(drain_cmd_list);
+	struct se_queue_obj *qobj = &dev->dev_queue_obj;
+	struct se_cmd *cmd, *tcmd;
+	unsigned long flags;
 	/*
 	 * Release all commands remaining in the struct se_device cmd queue.
 	 *
@@ -337,11 +340,26 @@ int core_tmr_lun_reset(
 		 */
 		if (prout_cmd == cmd)
 			continue;
+		/*
+		 * Skip direct processing of TRANSPORT_FREE_CMD_INTR for
+		 * HW target mode fabrics.
+		 */
+		spin_lock(&cmd->t_state_lock);
+		if (cmd->t_state == TRANSPORT_FREE_CMD_INTR) {
+			spin_unlock(&cmd->t_state_lock);
+			continue;
+		}
+		spin_unlock(&cmd->t_state_lock);
 
-		atomic_dec(&cmd->t_transport_queue_active);
+		atomic_set(&cmd->t_transport_queue_active, 0);
 		atomic_dec(&qobj->queue_cnt);
-		list_del(&cmd->se_queue_node);
-		spin_unlock_irqrestore(&qobj->cmd_queue_lock, flags);
+		list_move_tail(&cmd->se_queue_node, &drain_cmd_list);
+	}
+	spin_unlock_irqrestore(&qobj->cmd_queue_lock, flags);
+
+	while (!list_empty(&drain_cmd_list)) {
+		cmd = list_entry(drain_cmd_list.next, struct se_cmd, se_queue_node);
+		list_del_init(&cmd->se_queue_node);
 
 		pr_debug("LUN_RESET: %s from Device Queue: cmd: %p t_state:"
 			" %d t_fe_count: %d\n", (preempt_and_abort_list) ?
@@ -354,9 +372,53 @@ int core_tmr_lun_reset(
 
 		core_tmr_handle_tas_abort(tmr_nacl, cmd, tas,
 				atomic_read(&cmd->t_fe_count));
-		spin_lock_irqsave(&qobj->cmd_queue_lock, flags);
 	}
-	spin_unlock_irqrestore(&qobj->cmd_queue_lock, flags);
+}
+
+int core_tmr_lun_reset(
+        struct se_device *dev,
+        struct se_tmr_req *tmr,
+        struct list_head *preempt_and_abort_list,
+        struct se_cmd *prout_cmd)
+{
+	struct se_node_acl *tmr_nacl = NULL;
+	struct se_portal_group *tmr_tpg = NULL;
+	int tas;
+        /*
+	 * TASK_ABORTED status bit, this is configurable via ConfigFS
+	 * struct se_device attributes.  spc4r17 section 7.4.6 Control mode page
+	 *
+	 * A task aborted status (TAS) bit set to zero specifies that aborted
+	 * tasks shall be terminated by the device server without any response
+	 * to the application client. A TAS bit set to one specifies that tasks
+	 * aborted by the actions of an I_T nexus other than the I_T nexus on
+	 * which the command was received shall be completed with TASK ABORTED
+	 * status (see SAM-4).
+	 */
+	tas = dev->se_sub_dev->se_dev_attrib.emulate_tas;
+	/*
+	 * Determine if this se_tmr is coming from a $FABRIC_MOD
+	 * or struct se_device passthrough..
+	 */
+	if (tmr && tmr->task_cmd && tmr->task_cmd->se_sess) {
+		tmr_nacl = tmr->task_cmd->se_sess->se_node_acl;
+		tmr_tpg = tmr->task_cmd->se_sess->se_tpg;
+		if (tmr_nacl && tmr_tpg) {
+			pr_debug("LUN_RESET: TMR caller fabric: %s"
+				" initiator port %s\n",
+				tmr_tpg->se_tpg_tfo->get_fabric_name(),
+				tmr_nacl->initiatorname);
+		}
+	}
+	pr_debug("LUN_RESET: %s starting for [%s], tas: %d\n",
+		(preempt_and_abort_list) ? "Preempt" : "TMR",
+		dev->transport->name, tas);
+
+	core_tmr_drain_tmr_list(dev, tmr, preempt_and_abort_list);
+	core_tmr_drain_task_list(dev, prout_cmd, tmr_nacl, tas,
+				preempt_and_abort_list);
+	core_tmr_drain_cmd_list(dev, prout_cmd, tmr_nacl, tas,
+				preempt_and_abort_list);
 	/*
 	 * Clear any legacy SPC-2 reservation when called during
 	 * LOGICAL UNIT RESET
@@ -379,3 +441,4 @@ int core_tmr_lun_reset(
 			dev->transport->name);
 	return 0;
 }
+
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index a4b0a8d27f2..013c1006adf 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -594,13 +594,14 @@ check_lun:
 
 void transport_cmd_finish_abort(struct se_cmd *cmd, int remove)
 {
-	transport_remove_cmd_from_queue(cmd, &cmd->se_dev->dev_queue_obj);
 	transport_lun_remove_cmd(cmd);
 
 	if (transport_cmd_check_stop_to_fabric(cmd))
 		return;
-	if (remove)
+	if (remove) {
+		transport_remove_cmd_from_queue(cmd, &cmd->se_dev->dev_queue_obj);
 		transport_generic_remove(cmd, 0);
+	}
 }
 
 void transport_cmd_finish_abort_tmr(struct se_cmd *cmd)
@@ -621,8 +622,6 @@ static void transport_add_cmd_to_queue(
 	struct se_queue_obj *qobj = &dev->dev_queue_obj;
 	unsigned long flags;
 
-	INIT_LIST_HEAD(&cmd->se_queue_node);
-
 	if (t_state) {
 		spin_lock_irqsave(&cmd->t_state_lock, flags);
 		cmd->t_state = t_state;
@@ -631,15 +630,21 @@ static void transport_add_cmd_to_queue(
 	}
 
 	spin_lock_irqsave(&qobj->cmd_queue_lock, flags);
+
+	/* If the cmd is already on the list, remove it before we add it */
+	if (!list_empty(&cmd->se_queue_node))
+		list_del(&cmd->se_queue_node);
+	else
+		atomic_inc(&qobj->queue_cnt);
+
 	if (cmd->se_cmd_flags & SCF_EMULATE_QUEUE_FULL) {
 		cmd->se_cmd_flags &= ~SCF_EMULATE_QUEUE_FULL;
 		list_add(&cmd->se_queue_node, &qobj->qobj_list);
 	} else
 		list_add_tail(&cmd->se_queue_node, &qobj->qobj_list);
-	atomic_inc(&cmd->t_transport_queue_active);
+	atomic_set(&cmd->t_transport_queue_active, 1);
 	spin_unlock_irqrestore(&qobj->cmd_queue_lock, flags);
 
-	atomic_inc(&qobj->queue_cnt);
 	wake_up_interruptible(&qobj->thread_wq);
 }
 
@@ -656,9 +661,9 @@ transport_get_cmd_from_queue(struct se_queue_obj *qobj)
 	}
 	cmd = list_first_entry(&qobj->qobj_list, struct se_cmd, se_queue_node);
 
-	atomic_dec(&cmd->t_transport_queue_active);
+	atomic_set(&cmd->t_transport_queue_active, 0);
 
-	list_del(&cmd->se_queue_node);
+	list_del_init(&cmd->se_queue_node);
 	atomic_dec(&qobj->queue_cnt);
 	spin_unlock_irqrestore(&qobj->cmd_queue_lock, flags);
 
@@ -668,7 +673,6 @@ transport_get_cmd_from_queue(struct se_queue_obj *qobj)
 static void transport_remove_cmd_from_queue(struct se_cmd *cmd,
 		struct se_queue_obj *qobj)
 {
-	struct se_cmd *t;
 	unsigned long flags;
 
 	spin_lock_irqsave(&qobj->cmd_queue_lock, flags);
@@ -676,14 +680,9 @@ static void transport_remove_cmd_from_queue(struct se_cmd *cmd,
 		spin_unlock_irqrestore(&qobj->cmd_queue_lock, flags);
 		return;
 	}
-
-	list_for_each_entry(t, &qobj->qobj_list, se_queue_node)
-		if (t == cmd) {
-			atomic_dec(&cmd->t_transport_queue_active);
-			atomic_dec(&qobj->queue_cnt);
-			list_del(&cmd->se_queue_node);
-			break;
-		}
+	atomic_set(&cmd->t_transport_queue_active, 0);
+	atomic_dec(&qobj->queue_cnt);
+	list_del_init(&cmd->se_queue_node);
 	spin_unlock_irqrestore(&qobj->cmd_queue_lock, flags);
 
 	if (atomic_read(&cmd->t_transport_queue_active)) {
@@ -1067,7 +1066,7 @@ static void transport_release_all_cmds(struct se_device *dev)
 	list_for_each_entry_safe(cmd, tcmd, &dev->dev_queue_obj.qobj_list,
 				se_queue_node) {
 		t_state = cmd->t_state;
-		list_del(&cmd->se_queue_node);
+		list_del_init(&cmd->se_queue_node);
 		spin_unlock_irqrestore(&dev->dev_queue_obj.cmd_queue_lock,
 				flags);
 
@@ -1598,6 +1597,7 @@ void transport_init_se_cmd(
 	INIT_LIST_HEAD(&cmd->se_delayed_node);
 	INIT_LIST_HEAD(&cmd->se_ordered_node);
 	INIT_LIST_HEAD(&cmd->se_qf_node);
+	INIT_LIST_HEAD(&cmd->se_queue_node);
 
 	INIT_LIST_HEAD(&cmd->t_task_list);
 	init_completion(&cmd->transport_lun_fe_stop_comp);
@@ -4920,6 +4920,15 @@ EXPORT_SYMBOL(transport_check_aborted_status);
 
 void transport_send_task_abort(struct se_cmd *cmd)
 {
+	unsigned long flags;
+
+	spin_lock_irqsave(&cmd->t_state_lock, flags);
+	if (cmd->se_cmd_flags & SCF_SENT_CHECK_CONDITION) {
+		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+		return;
+	}
+	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+
 	/*
 	 * If there are still expected incoming fabric WRITEs, we wait
 	 * until until they have completed before sending a TASK_ABORTED
diff --git a/drivers/thermal/Kconfig b/drivers/thermal/Kconfig
index f7f71b2d310..938953fd1c2 100644
--- a/drivers/thermal/Kconfig
+++ b/drivers/thermal/Kconfig
@@ -18,3 +18,22 @@ config THERMAL_HWMON
 	depends on THERMAL
 	depends on HWMON=y || HWMON=THERMAL
 	default y
+
+config CPU_THERMAL
+	bool "generic cpu cooling support"
+	depends on THERMAL
+	help
+	  This implements the generic cpu cooling mechanism through frequency
+	  reduction, cpu hotplug and any other ways of reducing temperature. An
+	  ACPI version of this already exists(drivers/acpi/processor_thermal.c).
+	  This will be useful for platforms using the generic thermal interface
+	  and not the ACPI interface.
+	  If you want this support, you should say Y or M here.
+
+menuconfig SAMSUNG_THERMAL_INTERFACE
+	bool "Samsung Thermal support"
+	depends on THERMAL && CPU_THERMAL
+	help
+	  This is a samsung thermal interface which will be used as
+	  a link between sensors and cooling devices with linux thermal
+	  framework.
diff --git a/drivers/thermal/Makefile b/drivers/thermal/Makefile
index 31108a01c22..c67b6b222be 100644
--- a/drivers/thermal/Makefile
+++ b/drivers/thermal/Makefile
@@ -3,3 +3,5 @@
 #
 
 obj-$(CONFIG_THERMAL)		+= thermal_sys.o
+obj-$(CONFIG_CPU_THERMAL)	+= cpu_cooling.o
+obj-$(CONFIG_SAMSUNG_THERMAL_INTERFACE)	+= exynos_thermal.o
diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c
new file mode 100644
index 00000000000..cdd148c0036
--- /dev/null
+++ b/drivers/thermal/cpu_cooling.c
@@ -0,0 +1,302 @@
+/*
+ *  linux/drivers/thermal/cpu_cooling.c
+ *
+ *  Copyright (C) 2011	Samsung Electronics Co., Ltd(http://www.samsung.com)
+ *  Copyright (C) 2011  Amit Daniel <amit.kachhap@linaro.org>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; version 2 of the License.
+ *
+ *  This program is distributed in the hope that it will be useful, but
+ *  WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License along
+ *  with this program; if not, write to the Free Software Foundation, Inc.,
+ *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/thermal.h>
+#include <linux/platform_device.h>
+#include <linux/cpufreq.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+#include <linux/cpu.h>
+#include <linux/cpu_cooling.h>
+
+#ifdef CONFIG_CPU_FREQ
+struct cpufreq_cooling_device {
+	struct thermal_cooling_device *cool_dev;
+	struct freq_pctg_table *tab_ptr;
+	unsigned int tab_size;
+	unsigned int cpufreq_state;
+	const struct cpumask *allowed_cpus;
+};
+
+static struct cpufreq_cooling_device *cpufreq_device;
+
+/*Below codes defines functions to be used for cpufreq as cooling device*/
+static bool is_cpufreq_valid(int cpu)
+{
+	struct cpufreq_policy policy;
+	if (!cpufreq_get_policy(&policy, cpu))
+		return true;
+	return false;
+}
+
+static int cpufreq_apply_cooling(int cooling_state)
+{
+	int cpuid, this_cpu = smp_processor_id();
+
+	if (!is_cpufreq_valid(this_cpu))
+		return 0;
+
+	if (cooling_state > cpufreq_device->tab_size)
+		return -EINVAL;
+
+	/*Check if last cooling level is same as current cooling level*/
+	if (cpufreq_device->cpufreq_state == cooling_state)
+		return 0;
+
+	cpufreq_device->cpufreq_state = cooling_state;
+
+	for_each_cpu(cpuid, cpufreq_device->allowed_cpus) {
+		if (is_cpufreq_valid(cpuid))
+			cpufreq_update_policy(cpuid);
+	}
+
+	return 0;
+}
+
+static int thermal_cpufreq_notifier(struct notifier_block *nb,
+					unsigned long event, void *data)
+{
+	struct cpufreq_policy *policy = data;
+	struct freq_pctg_table *th_table;
+	unsigned long max_freq = 0;
+	unsigned int cpu = policy->cpu, th_pctg = 0, level;
+
+	if (event != CPUFREQ_ADJUST)
+		return 0;
+
+	level = cpufreq_device->cpufreq_state;
+
+	if (level > 0) {
+		th_table =
+			&(cpufreq_device->tab_ptr[level - 1]);
+		th_pctg = th_table->freq_clip_pctg[cpu];
+	}
+
+	max_freq =
+		(policy->cpuinfo.max_freq * (100 - th_pctg)) / 100;
+
+	cpufreq_verify_within_limits(policy, 0, max_freq);
+
+	return 0;
+}
+
+/*
+ * cpufreq cooling device callback functions
+ */
+static int cpufreq_get_max_state(struct thermal_cooling_device *cdev,
+				 unsigned long *state)
+{
+	*state = cpufreq_device->tab_size;
+	return 0;
+}
+
+static int cpufreq_get_cur_state(struct thermal_cooling_device *cdev,
+				 unsigned long *state)
+{
+	*state = cpufreq_device->cpufreq_state;
+	return 0;
+}
+
+/*This cooling may be as PASSIVE/STATE_ACTIVE type*/
+static int cpufreq_set_cur_state(struct thermal_cooling_device *cdev,
+				 unsigned long state)
+{
+	cpufreq_apply_cooling(state);
+	return 0;
+}
+
+/* bind cpufreq callbacks to cpufreq cooling device */
+static struct thermal_cooling_device_ops cpufreq_cooling_ops = {
+	.get_max_state = cpufreq_get_max_state,
+	.get_cur_state = cpufreq_get_cur_state,
+	.set_cur_state = cpufreq_set_cur_state,
+};
+
+static struct notifier_block thermal_cpufreq_notifier_block = {
+	.notifier_call = thermal_cpufreq_notifier,
+};
+
+struct thermal_cooling_device *cpufreq_cooling_register(
+	struct freq_pctg_table *tab_ptr, unsigned int tab_size,
+	const struct cpumask *mask_val)
+{
+	struct thermal_cooling_device *cool_dev;
+
+	if (tab_ptr == NULL || tab_size == 0)
+		return ERR_PTR(-EINVAL);
+
+	cpufreq_device =
+		kzalloc(sizeof(struct cpufreq_cooling_device), GFP_KERNEL);
+
+	if (!cpufreq_device)
+		return ERR_PTR(-ENOMEM);
+
+	cool_dev = thermal_cooling_device_register("thermal-cpufreq", NULL,
+						&cpufreq_cooling_ops);
+	if (!cool_dev) {
+		kfree(cpufreq_device);
+		return ERR_PTR(-EINVAL);
+	}
+
+	cpufreq_device->tab_ptr = tab_ptr;
+	cpufreq_device->tab_size = tab_size;
+	cpufreq_device->cool_dev = cool_dev;
+	cpufreq_device->allowed_cpus = mask_val;
+
+	cpufreq_register_notifier(&thermal_cpufreq_notifier_block,
+						CPUFREQ_POLICY_NOTIFIER);
+	return cool_dev;
+}
+EXPORT_SYMBOL(cpufreq_cooling_register);
+
+void cpufreq_cooling_unregister(void)
+{
+	cpufreq_unregister_notifier(&thermal_cpufreq_notifier_block,
+						CPUFREQ_POLICY_NOTIFIER);
+	thermal_cooling_device_unregister(cpufreq_device->cool_dev);
+	kfree(cpufreq_device);
+}
+EXPORT_SYMBOL(cpufreq_cooling_unregister);
+#else /*!CONFIG_CPU_FREQ*/
+struct thermal_cooling_device *cpufreq_cooling_register(
+	struct freq_pctg_table *tab_ptr, unsigned int tab_size)
+{
+	return NULL;
+}
+EXPORT_SYMBOL(cpufreq_cooling_register);
+void cpufreq_cooling_unregister(void)
+{
+	return;
+}
+EXPORT_SYMBOL(cpufreq_cooling_unregister);
+#endif /*CONFIG_CPU_FREQ*/
+
+#ifdef CONFIG_HOTPLUG_CPU
+
+struct hotplug_cooling_device {
+	struct thermal_cooling_device *cool_dev;
+	unsigned int hotplug_state;
+	const struct cpumask *allowed_cpus;
+};
+static struct hotplug_cooling_device *hotplug_device;
+
+/*
+ * cpu hotplug cooling device callback functions
+ */
+static int cpuhotplug_get_max_state(struct thermal_cooling_device *cdev,
+				 unsigned long *state)
+{
+	*state = 1;
+	return 0;
+}
+
+static int cpuhotplug_get_cur_state(struct thermal_cooling_device *cdev,
+				 unsigned long *state)
+{
+	/*This cooling device may be of type ACTIVE, so state field
+	can be 0 or 1*/
+	*state = hotplug_device->hotplug_state;
+	return 0;
+}
+
+/*This cooling may be as PASSIVE/STATE_ACTIVE type*/
+static int cpuhotplug_set_cur_state(struct thermal_cooling_device *cdev,
+				 unsigned long state)
+{
+	int cpuid, this_cpu = smp_processor_id();
+
+	if (hotplug_device->hotplug_state == state)
+		return 0;
+
+	/*This cooling device may be of type ACTIVE, so state field
+	can be 0 or 1*/
+	if (state == 1) {
+		for_each_cpu(cpuid, hotplug_device->allowed_cpus) {
+			if (cpu_online(cpuid) && (cpuid != this_cpu))
+				cpu_down(cpuid);
+		}
+	} else if (state == 0) {
+		for_each_cpu(cpuid, hotplug_device->allowed_cpus) {
+			if (!cpu_online(cpuid) && (cpuid != this_cpu))
+				cpu_up(cpuid);
+		}
+	} else
+		return -EINVAL;
+
+	hotplug_device->hotplug_state = state;
+
+	return 0;
+}
+/* bind hotplug callbacks to cpu hotplug cooling device */
+static struct thermal_cooling_device_ops cpuhotplug_cooling_ops = {
+	.get_max_state = cpuhotplug_get_max_state,
+	.get_cur_state = cpuhotplug_get_cur_state,
+	.set_cur_state = cpuhotplug_set_cur_state,
+};
+
+struct thermal_cooling_device *cpuhotplug_cooling_register(
+	const struct cpumask *mask_val)
+{
+	struct thermal_cooling_device *cool_dev;
+
+	hotplug_device =
+		kzalloc(sizeof(struct hotplug_cooling_device), GFP_KERNEL);
+
+	if (!hotplug_device)
+		return ERR_PTR(-ENOMEM);
+
+	cool_dev = thermal_cooling_device_register("thermal-cpuhotplug", NULL,
+						&cpuhotplug_cooling_ops);
+	if (!cool_dev) {
+		kfree(hotplug_device);
+		return ERR_PTR(-EINVAL);
+	}
+
+	hotplug_device->cool_dev = cool_dev;
+	hotplug_device->hotplug_state = 0;
+	hotplug_device->allowed_cpus = mask_val;
+
+	return cool_dev;
+}
+EXPORT_SYMBOL(cpuhotplug_cooling_register);
+
+void cpuhotplug_cooling_unregister(void)
+{
+	thermal_cooling_device_unregister(hotplug_device->cool_dev);
+	kfree(hotplug_device);
+}
+EXPORT_SYMBOL(cpuhotplug_cooling_unregister);
+#else /*!CONFIG_HOTPLUG_CPU*/
+struct thermal_cooling_device *cpuhotplug_cooling_register(
+	const struct cpumask *mask_val)
+{
+	return NULL;
+}
+EXPORT_SYMBOL(cpuhotplug_cooling_register);
+void cpuhotplug_cooling_unregister(void)
+{
+	return;
+}
+EXPORT_SYMBOL(cpuhotplug_cooling_unregister);
+#endif /*CONFIG_HOTPLUG_CPU*/
diff --git a/drivers/thermal/exynos_thermal.c b/drivers/thermal/exynos_thermal.c
new file mode 100644
index 00000000000..ff189b145ad
--- /dev/null
+++ b/drivers/thermal/exynos_thermal.c
@@ -0,0 +1,334 @@
+/* linux/drivers/staging/thermal_exynos4/thermal_interface.c
+ *
+ * Copyright (c) 2010-2011 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+*/
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/thermal.h>
+#include <linux/platform_device.h>
+#include <linux/cpufreq.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+#include <linux/cpu_cooling.h>
+#include <linux/platform_data/exynos4_tmu.h>
+#include <linux/exynos_thermal.h>
+
+static unsigned int verbose;
+
+struct exynos4_thermal_zone {
+	unsigned int idle_interval;
+	unsigned int active_interval;
+	struct thermal_zone_device *therm_dev;
+	struct thermal_cooling_device *cool_dev;
+	struct platform_device *exynos4_dev;
+	struct exynos4_tmu_platform_data *sensor_data;
+};
+static struct thermal_sensor_info *exynos4_sensor_info;
+
+static struct exynos4_thermal_zone *th_zone;
+
+static int exynos4_get_mode(struct thermal_zone_device *thermal,
+			    enum thermal_device_mode *mode)
+{
+	if (exynos4_sensor_info) {
+		pr_info("Temperature sensor not initialised\n");
+		*mode = THERMAL_DEVICE_DISABLED;
+	} else
+		*mode = THERMAL_DEVICE_ENABLED;
+	return 0;
+}
+
+/*
+ * set operation mode;
+ * enabled: the thermal layer of the kernel takes care about
+ *          the temperature.
+ * disabled: temperature sensor is not enabled.
+ */
+static int exynos4_set_mode(struct thermal_zone_device *thermal,
+			    enum thermal_device_mode mode)
+{
+	if (!th_zone->therm_dev) {
+		pr_notice("thermal zone not registered\n");
+		return 0;
+	}
+	if (mode == THERMAL_DEVICE_ENABLED)
+		th_zone->therm_dev->polling_delay =
+				th_zone->active_interval*1000;
+	else
+		th_zone->therm_dev->polling_delay =
+				th_zone->idle_interval*1000;
+
+	thermal_zone_device_update(th_zone->therm_dev);
+	pr_info("thermal polling set for duration=%d sec\n",
+				th_zone->therm_dev->polling_delay/1000);
+	return 0;
+}
+
+/*This may be called from interrupt based temperature sensor*/
+void exynos4_report_trigger(void)
+{
+	unsigned int th_temp = th_zone->sensor_data->threshold;
+	unsigned int monitor_temp = th_temp +
+			th_zone->sensor_data->trigger_levels[1];
+
+	thermal_zone_device_update(th_zone->therm_dev);
+
+	if (th_zone->therm_dev->last_temperature > monitor_temp)
+		th_zone->therm_dev->polling_delay =
+					th_zone->active_interval*1000;
+	else
+		th_zone->therm_dev->polling_delay =
+					th_zone->idle_interval*1000;
+}
+
+static int exynos4_get_trip_type(struct thermal_zone_device *thermal, int trip,
+				 enum thermal_trip_type *type)
+{
+	if (verbose)
+		pr_info("%s, trip no=%d\n", __func__, trip);
+	if (trip == 0 || trip == 1)
+		*type = THERMAL_TRIP_STATE_ACTIVE;
+	else if (trip == 2)
+		*type = THERMAL_TRIP_CRITICAL;
+	else
+		return -EINVAL;
+
+	return 0;
+}
+
+static int exynos4_get_trip_temp(struct thermal_zone_device *thermal, int trip,
+				 unsigned long *temp)
+{
+	unsigned int th_temp = th_zone->sensor_data->threshold;
+
+	/*Monitor zone*/
+	if (trip == 0)
+		*temp = th_temp + th_zone->sensor_data->trigger_levels[1];
+	/*Warn zone*/
+	else if (trip == 1)
+		*temp = th_temp + th_zone->sensor_data->trigger_levels[2];
+	/*Panic zone*/
+	else if (trip == 2)
+		*temp = th_temp + th_zone->sensor_data->trigger_levels[3];
+	else
+		return -EINVAL;
+
+	return 0;
+}
+
+static int exynos4_get_crit_temp(struct thermal_zone_device *thermal,
+				 unsigned long *temp)
+{
+	unsigned int th_temp = th_zone->sensor_data->threshold;
+	/*Panic zone*/
+	*temp = th_temp + th_zone->sensor_data->trigger_levels[3];
+	return 0;
+}
+
+static int exynos4_bind(struct thermal_zone_device *thermal,
+			struct thermal_cooling_device *cdev)
+{
+	/* if the cooling device is the one from exynos4 bind it */
+	if (cdev != th_zone->cool_dev)
+		return 0;
+
+	if (thermal_zone_bind_cooling_device(thermal, 0, cdev)) {
+		pr_err("error binding cooling dev\n");
+		return -EINVAL;
+	}
+	if (thermal_zone_bind_cooling_device(thermal, 1, cdev)) {
+		pr_err("error binding cooling dev\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int exynos4_unbind(struct thermal_zone_device *thermal,
+			  struct thermal_cooling_device *cdev)
+{
+	if (cdev != th_zone->cool_dev)
+		return 0;
+	if (thermal_zone_unbind_cooling_device(thermal, 0, cdev)) {
+		pr_err("error unbinding cooling dev\n");
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int exynos4_get_temp(struct thermal_zone_device *thermal,
+			       unsigned long *t)
+{
+	int temp = 0;
+	void *data;
+
+	if (!exynos4_sensor_info) {
+		pr_info("Temperature sensor not initialised\n");
+		return -EINVAL;
+	}
+	data = exynos4_sensor_info->private_data;
+	temp = exynos4_sensor_info->read_temperature(data);
+
+	if (verbose)
+		pr_notice("temp %d\n", temp);
+
+	*t = temp;
+	return 0;
+}
+
+/* bind callback functions to thermalzone */
+static struct thermal_zone_device_ops exynos4_dev_ops = {
+	.bind = exynos4_bind,
+	.unbind = exynos4_unbind,
+	.get_temp = exynos4_get_temp,
+	.get_mode = exynos4_get_mode,
+	.set_mode = exynos4_set_mode,
+	.get_trip_type = exynos4_get_trip_type,
+	.get_trip_temp = exynos4_get_trip_temp,
+	.get_crit_temp = exynos4_get_crit_temp,
+};
+
+int exynos4_register_temp_sensor(struct thermal_sensor_info *sensor_info)
+{
+	exynos4_sensor_info = sensor_info;
+	return 0;
+}
+
+
+static int __devinit exynos4_probe(struct platform_device *device)
+{
+	return 0;
+}
+
+static int exynos4_remove(struct platform_device *device)
+{
+	return 0;
+}
+
+static struct platform_driver exynos4_driver = {
+	.driver = {
+		.name  = "exynos4",
+		.owner = THIS_MODULE,
+	},
+	.probe = exynos4_probe,
+	.remove = exynos4_remove,
+};
+
+static int exynos4_register_platform(void)
+{
+	int err = 0;
+
+	th_zone = kzalloc(sizeof(struct exynos4_thermal_zone), GFP_KERNEL);
+	if (!th_zone)
+		return -ENOMEM;
+
+	err = platform_driver_register(&exynos4_driver);
+	if (err)
+		return err;
+
+	th_zone->exynos4_dev = platform_device_alloc("exynos4", -1);
+	if (!th_zone->exynos4_dev) {
+		err = -ENOMEM;
+		goto err_device_alloc;
+	}
+	err = platform_device_add(th_zone->exynos4_dev);
+	if (err)
+		goto err_device_add;
+
+	return 0;
+
+err_device_add:
+	platform_device_put(th_zone->exynos4_dev);
+err_device_alloc:
+	platform_driver_unregister(&exynos4_driver);
+	return err;
+}
+
+static void exynos4_unregister_platform(void)
+{
+	platform_device_unregister(th_zone->exynos4_dev);
+	platform_driver_unregister(&exynos4_driver);
+	kfree(th_zone);
+}
+
+static int exynos4_register_thermal(void)
+{
+	if (!exynos4_sensor_info) {
+		pr_info("Temperature sensor not initialised\n");
+		return -EINVAL;
+	}
+
+	th_zone->sensor_data = exynos4_sensor_info->sensor_data;
+	if (!th_zone->sensor_data) {
+		pr_info("Temperature sensor data not initialised\n");
+		return -EINVAL;
+	}
+
+	th_zone->cool_dev = cpufreq_cooling_register(
+		(struct freq_pctg_table *)th_zone->sensor_data->freq_tab,
+		th_zone->sensor_data->level_count);
+
+	if (IS_ERR(th_zone->cool_dev))
+		return -EINVAL;
+
+	th_zone->therm_dev = thermal_zone_device_register("exynos4-therm",
+				3, NULL, &exynos4_dev_ops, 0, 0, 0, 1000);
+	if (IS_ERR(th_zone->therm_dev))
+		return -EINVAL;
+
+	th_zone->active_interval = 1;
+	th_zone->idle_interval = 10;
+	exynos4_set_mode(th_zone->therm_dev, THERMAL_DEVICE_DISABLED);
+
+	return 0;
+}
+
+static void exynos4_unregister_thermal(void)
+{
+	if (th_zone->cool_dev)
+		cpufreq_cooling_unregister();
+
+	if (th_zone->therm_dev)
+		thermal_zone_device_unregister(th_zone->therm_dev);
+}
+
+static int __init exynos4_thermal_init(void)
+{
+	int err = 0;
+
+	err = exynos4_register_platform();
+	if (err)
+		goto out_err;
+
+	err = exynos4_register_thermal();
+	if (err)
+		goto err_unreg;
+
+	return 0;
+
+err_unreg:
+	exynos4_unregister_thermal();
+	exynos4_unregister_platform();
+
+out_err:
+	return err;
+}
+
+static void __exit exynos4_thermal_exit(void)
+{
+	exynos4_unregister_thermal();
+	exynos4_unregister_platform();
+}
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Amit Daniel <amit.kachhap@linaro.org>");
+MODULE_DESCRIPTION("samsung Exynos4 thermal monitor driver");
+
+module_init(exynos4_thermal_init);
+module_exit(exynos4_thermal_exit);
diff --git a/drivers/thermal/thermal_sys.c b/drivers/thermal/thermal_sys.c
index 708f8e92771..2a42296a1f6 100644
--- a/drivers/thermal/thermal_sys.c
+++ b/drivers/thermal/thermal_sys.c
@@ -192,6 +192,8 @@ trip_point_type_show(struct device *dev, struct device_attribute *attr,
 		return sprintf(buf, "passive\n");
 	case THERMAL_TRIP_ACTIVE:
 		return sprintf(buf, "active\n");
+	case THERMAL_TRIP_STATE_ACTIVE:
+		return sprintf(buf, "state-active\n");
 	default:
 		return sprintf(buf, "unknown\n");
 	}
@@ -1035,7 +1037,7 @@ EXPORT_SYMBOL(thermal_cooling_device_unregister);
 void thermal_zone_device_update(struct thermal_zone_device *tz)
 {
 	int count, ret = 0;
-	long temp, trip_temp;
+	long temp, trip_temp, max_state, last_trip_change = 0;
 	enum thermal_trip_type trip_type;
 	struct thermal_cooling_device_instance *instance;
 	struct thermal_cooling_device *cdev;
@@ -1086,6 +1088,29 @@ void thermal_zone_device_update(struct thermal_zone_device *tz)
 					cdev->ops->set_cur_state(cdev, 0);
 			}
 			break;
+		case THERMAL_TRIP_STATE_ACTIVE:
+			list_for_each_entry(instance, &tz->cooling_devices,
+					    node) {
+				if (instance->trip != count)
+					continue;
+
+				if (temp <= last_trip_change)
+					continue;
+
+				cdev = instance->cdev;
+				cdev->ops->get_max_state(cdev, &max_state);
+
+				if ((temp >= trip_temp) &&
+						((count + 1) <= max_state))
+					cdev->ops->set_cur_state(cdev,
+								count + 1);
+				else if ((temp < trip_temp) &&
+							(count <= max_state))
+					cdev->ops->set_cur_state(cdev, count);
+
+				last_trip_change = trip_temp;
+			}
+			break;
 		case THERMAL_TRIP_PASSIVE:
 			if (temp >= trip_temp || tz->passive)
 				thermal_zone_device_passive(tz, temp,
diff --git a/drivers/tty/hvc/hvc_dcc.c b/drivers/tty/hvc/hvc_dcc.c
index 435f6facbc2..44fbebab507 100644
--- a/drivers/tty/hvc/hvc_dcc.c
+++ b/drivers/tty/hvc/hvc_dcc.c
@@ -46,6 +46,7 @@ static inline char __dcc_getchar(void)
 
 	asm volatile("mrc p14, 0, %0, c0, c5, 0	@ read comms data reg"
 		: "=r" (__c));
+	isb();
 
 	return __c;
 }
@@ -55,6 +56,7 @@ static inline void __dcc_putchar(char c)
 	asm volatile("mcr p14, 0, %0, c0, c5, 0	@ write a char"
 		: /* no output register */
 		: "r" (c));
+	isb();
 }
 
 static int hvc_dcc_put_chars(uint32_t vt, const char *buf, int count)
diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c
index e809e9d4683..e18604b3fc7 100644
--- a/drivers/tty/pty.c
+++ b/drivers/tty/pty.c
@@ -670,12 +670,18 @@ static int ptmx_open(struct inode *inode, struct file *filp)
 
 	nonseekable_open(inode, filp);
 
+	retval = tty_alloc_file(filp);
+	if (retval)
+		return retval;
+
 	/* find a device that is not in use. */
 	tty_lock();
 	index = devpts_new_index(inode);
 	tty_unlock();
-	if (index < 0)
-		return index;
+	if (index < 0) {
+		retval = index;
+		goto err_file;
+	}
 
 	mutex_lock(&tty_mutex);
 	tty_lock();
@@ -689,27 +695,27 @@ static int ptmx_open(struct inode *inode, struct file *filp)
 
 	set_bit(TTY_PTY_LOCK, &tty->flags); /* LOCK THE SLAVE */
 
-	retval = tty_add_file(tty, filp);
-	if (retval)
-		goto out;
+	tty_add_file(tty, filp);
 
 	retval = devpts_pty_new(inode, tty->link);
 	if (retval)
-		goto out1;
+		goto err_release;
 
 	retval = ptm_driver->ops->open(tty, filp);
 	if (retval)
-		goto out2;
-out1:
+		goto err_release;
+
 	tty_unlock();
-	return retval;
-out2:
+	return 0;
+err_release:
 	tty_unlock();
 	tty_release(inode, filp);
 	return retval;
 out:
 	devpts_kill_index(inode, index);
 	tty_unlock();
+err_file:
+	tty_free_file(filp);
 	return retval;
 }
 
diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig
index 6deb387415e..9c3f4c4b99a 100644
--- a/drivers/tty/serial/Kconfig
+++ b/drivers/tty/serial/Kconfig
@@ -1578,7 +1578,7 @@ config SERIAL_IFX6X60
 	  Support for the IFX6x60 modem devices on Intel MID platforms.
 
 config SERIAL_PCH_UART
-	tristate "Intel EG20T PCH / OKI SEMICONDUCTOR IOH(ML7213/ML7223) UART"
+	tristate "Intel EG20T PCH/LAPIS Semicon IOH(ML7213/ML7223/ML7831) UART"
 	depends on PCI
 	select SERIAL_CORE
 	help
@@ -1586,12 +1586,12 @@ config SERIAL_PCH_UART
 	  which is an IOH(Input/Output Hub) for x86 embedded processor.
 	  Enabling PCH_DMA, this PCH UART works as DMA mode.
 
-	  This driver also can be used for OKI SEMICONDUCTOR IOH(Input/
-	  Output Hub), ML7213 and ML7223.
-	  ML7213 IOH is for IVI(In-Vehicle Infotainment) use and ML7223 IOH is
-	  for MP(Media Phone) use.
-	  ML7213/ML7223 is companion chip for Intel Atom E6xx series.
-	  ML7213/ML7223 is completely compatible for Intel EG20T PCH.
+	  This driver also can be used for LAPIS Semiconductor IOH(Input/
+	  Output Hub), ML7213, ML7223 and ML7831.
+	  ML7213 IOH is for IVI(In-Vehicle Infotainment) use, ML7223 IOH is
+	  for MP(Media Phone) use and ML7831 IOH is for general purpose use.
+	  ML7213/ML7223/ML7831 is companion chip for Intel Atom E6xx series.
+	  ML7213/ML7223/ML7831 is completely compatible for Intel EG20T PCH.
 
 config SERIAL_MSM_SMD
 	bool "Enable tty device interface for some SMD ports"
diff --git a/drivers/tty/serial/altera_jtaguart.c b/drivers/tty/serial/altera_jtaguart.c
index 60e049b041a..af46c56080d 100644
--- a/drivers/tty/serial/altera_jtaguart.c
+++ b/drivers/tty/serial/altera_jtaguart.c
@@ -18,6 +18,7 @@
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/console.h>
+#include <linux/of.h>
 #include <linux/tty.h>
 #include <linux/tty_flip.h>
 #include <linux/serial.h>
@@ -472,8 +473,6 @@ static struct of_device_id altera_jtaguart_match[] = {
 	{},
 };
 MODULE_DEVICE_TABLE(of, altera_jtaguart_match);
-#else
-#define altera_jtaguart_match NULL
 #endif /* CONFIG_OF */
 
 static struct platform_driver altera_jtaguart_platform_driver = {
@@ -482,7 +481,7 @@ static struct platform_driver altera_jtaguart_platform_driver = {
 	.driver	= {
 		.name		= DRV_NAME,
 		.owner		= THIS_MODULE,
-		.of_match_table	= altera_jtaguart_match,
+		.of_match_table	= of_match_ptr(altera_jtaguart_match),
 	},
 };
 
diff --git a/drivers/tty/serial/altera_uart.c b/drivers/tty/serial/altera_uart.c
index 50bc5a5ac65..0abd31d2361 100644
--- a/drivers/tty/serial/altera_uart.c
+++ b/drivers/tty/serial/altera_uart.c
@@ -616,8 +616,6 @@ static struct of_device_id altera_uart_match[] = {
 	{},
 };
 MODULE_DEVICE_TABLE(of, altera_uart_match);
-#else
-#define altera_uart_match NULL
 #endif /* CONFIG_OF */
 
 static struct platform_driver altera_uart_platform_driver = {
@@ -626,7 +624,7 @@ static struct platform_driver altera_uart_platform_driver = {
 	.driver	= {
 		.name		= DRV_NAME,
 		.owner		= THIS_MODULE,
-		.of_match_table	= altera_uart_match,
+		.of_match_table	= of_match_ptr(altera_uart_match),
 	},
 };
 
diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c
index 7e91b3d368c..99898773706 100644
--- a/drivers/tty/serial/imx.c
+++ b/drivers/tty/serial/imx.c
@@ -1286,17 +1286,20 @@ static int serial_imx_resume(struct platform_device *dev)
 static int serial_imx_probe_dt(struct imx_port *sport,
 		struct platform_device *pdev)
 {
-	static int portnum = 0;
 	struct device_node *np = pdev->dev.of_node;
 	const struct of_device_id *of_id =
 			of_match_device(imx_uart_dt_ids, &pdev->dev);
+	int ret;
 
 	if (!np)
 		return -ENODEV;
 
-	sport->port.line = portnum++;
-	if (sport->port.line >= UART_NR)
-		return -EINVAL;
+	ret = of_alias_get_id(np, "serial");
+	if (ret < 0) {
+		dev_err(&pdev->dev, "failed to get alias id, errno %d\n", ret);
+		return -ENODEV;
+	}
+	sport->port.line = ret;
 
 	if (of_get_property(np, "fsl,uart-has-rtscts", NULL))
 		sport->have_rtscts = 1;
diff --git a/drivers/tty/serial/jsm/jsm.h b/drivers/tty/serial/jsm/jsm.h
index b704c8ce0d7..5b837e749c1 100644
--- a/drivers/tty/serial/jsm/jsm.h
+++ b/drivers/tty/serial/jsm/jsm.h
@@ -183,10 +183,8 @@ struct jsm_board
 /* Our Read/Error/Write queue sizes */
 #define RQUEUEMASK	0x1FFF		/* 8 K - 1 */
 #define EQUEUEMASK	0x1FFF		/* 8 K - 1 */
-#define WQUEUEMASK	0x0FFF		/* 4 K - 1 */
 #define RQUEUESIZE	(RQUEUEMASK + 1)
 #define EQUEUESIZE	RQUEUESIZE
-#define WQUEUESIZE	(WQUEUEMASK + 1)
 
 
 /************************************************************************
@@ -226,10 +224,6 @@ struct jsm_channel {
 	u16		ch_e_head;	/* Head location of the error queue */
 	u16		ch_e_tail;	/* Tail location of the error queue */
 
-	u8		*ch_wqueue;	/* Our write queue buffer - malloc'ed */
-	u16		ch_w_head;	/* Head location of the write queue */
-	u16		ch_w_tail;	/* Tail location of the write queue */
-
 	u64		ch_rxcount;	/* total of data received so far */
 	u64		ch_txcount;	/* total of data transmitted so far */
 
@@ -378,7 +372,6 @@ extern int	jsm_debug;
  * Prototypes for non-static functions used in more than one module
  *
  *************************************************************************/
-int jsm_tty_write(struct uart_port *port);
 int jsm_tty_init(struct jsm_board *);
 int jsm_uart_port_init(struct jsm_board *);
 int jsm_remove_uart_port(struct jsm_board *);
diff --git a/drivers/tty/serial/jsm/jsm_driver.c b/drivers/tty/serial/jsm/jsm_driver.c
index 96da17868cf..2aaafa9c58a 100644
--- a/drivers/tty/serial/jsm/jsm_driver.c
+++ b/drivers/tty/serial/jsm/jsm_driver.c
@@ -211,7 +211,6 @@ static void __devexit jsm_remove_one(struct pci_dev *pdev)
 		if (brd->channels[i]) {
 			kfree(brd->channels[i]->ch_rqueue);
 			kfree(brd->channels[i]->ch_equeue);
-			kfree(brd->channels[i]->ch_wqueue);
 			kfree(brd->channels[i]);
 		}
 	}
diff --git a/drivers/tty/serial/jsm/jsm_neo.c b/drivers/tty/serial/jsm/jsm_neo.c
index 4538c3e3646..bd6e84699e1 100644
--- a/drivers/tty/serial/jsm/jsm_neo.c
+++ b/drivers/tty/serial/jsm/jsm_neo.c
@@ -496,12 +496,15 @@ static void neo_copy_data_from_queue_to_uart(struct jsm_channel *ch)
 	int s;
 	int qlen;
 	u32 len_written = 0;
+	struct circ_buf *circ;
 
 	if (!ch)
 		return;
 
+	circ = &ch->uart_port.state->xmit;
+
 	/* No data to write to the UART */
-	if (ch->ch_w_tail == ch->ch_w_head)
+	if (uart_circ_empty(circ))
 		return;
 
 	/* If port is "stopped", don't send any data to the UART */
@@ -517,11 +520,10 @@ static void neo_copy_data_from_queue_to_uart(struct jsm_channel *ch)
 		if (ch->ch_cached_lsr & UART_LSR_THRE) {
 			ch->ch_cached_lsr &= ~(UART_LSR_THRE);
 
-			writeb(ch->ch_wqueue[ch->ch_w_tail], &ch->ch_neo_uart->txrx);
+			writeb(circ->buf[circ->tail], &ch->ch_neo_uart->txrx);
 			jsm_printk(WRITE, INFO, &ch->ch_bd->pci_dev,
-					"Tx data: %x\n", ch->ch_wqueue[ch->ch_w_head]);
-			ch->ch_w_tail++;
-			ch->ch_w_tail &= WQUEUEMASK;
+					"Tx data: %x\n", circ->buf[circ->head]);
+			circ->tail = (circ->tail + 1) & (UART_XMIT_SIZE - 1);
 			ch->ch_txcount++;
 		}
 		return;
@@ -536,36 +538,36 @@ static void neo_copy_data_from_queue_to_uart(struct jsm_channel *ch)
 	n = UART_17158_TX_FIFOSIZE - ch->ch_t_tlevel;
 
 	/* cache head and tail of queue */
-	head = ch->ch_w_head & WQUEUEMASK;
-	tail = ch->ch_w_tail & WQUEUEMASK;
-	qlen = (head - tail) & WQUEUEMASK;
+	head = circ->head & (UART_XMIT_SIZE - 1);
+	tail = circ->tail & (UART_XMIT_SIZE - 1);
+	qlen = uart_circ_chars_pending(circ);
 
 	/* Find minimum of the FIFO space, versus queue length */
 	n = min(n, qlen);
 
 	while (n > 0) {
 
-		s = ((head >= tail) ? head : WQUEUESIZE) - tail;
+		s = ((head >= tail) ? head : UART_XMIT_SIZE) - tail;
 		s = min(s, n);
 
 		if (s <= 0)
 			break;
 
-		memcpy_toio(&ch->ch_neo_uart->txrxburst, ch->ch_wqueue + tail, s);
+		memcpy_toio(&ch->ch_neo_uart->txrxburst, circ->buf + tail, s);
 		/* Add and flip queue if needed */
-		tail = (tail + s) & WQUEUEMASK;
+		tail = (tail + s) & (UART_XMIT_SIZE - 1);
 		n -= s;
 		ch->ch_txcount += s;
 		len_written += s;
 	}
 
 	/* Update the final tail */
-	ch->ch_w_tail = tail & WQUEUEMASK;
+	circ->tail = tail & (UART_XMIT_SIZE - 1);
 
 	if (len_written >= ch->ch_t_tlevel)
 		ch->ch_flags &= ~(CH_TX_FIFO_EMPTY | CH_TX_FIFO_LWM);
 
-	if (!jsm_tty_write(&ch->uart_port))
+	if (uart_circ_empty(circ))
 		uart_write_wakeup(&ch->uart_port);
 }
 
@@ -946,7 +948,6 @@ static void neo_param(struct jsm_channel *ch)
 	if ((ch->ch_c_cflag & (CBAUD)) == 0) {
 		ch->ch_r_head = ch->ch_r_tail = 0;
 		ch->ch_e_head = ch->ch_e_tail = 0;
-		ch->ch_w_head = ch->ch_w_tail = 0;
 
 		neo_flush_uart_write(ch);
 		neo_flush_uart_read(ch);
diff --git a/drivers/tty/serial/jsm/jsm_tty.c b/drivers/tty/serial/jsm/jsm_tty.c
index 7a4a914ecff..434bd881fca 100644
--- a/drivers/tty/serial/jsm/jsm_tty.c
+++ b/drivers/tty/serial/jsm/jsm_tty.c
@@ -118,6 +118,19 @@ static void jsm_tty_set_mctrl(struct uart_port *port, unsigned int mctrl)
 	udelay(10);
 }
 
+/*
+ * jsm_tty_write()
+ *
+ * Take data from the user or kernel and send it out to the FEP.
+ * In here exists all the Transparent Print magic as well.
+ */
+static void jsm_tty_write(struct uart_port *port)
+{
+	struct jsm_channel *channel;
+	channel = container_of(port, struct jsm_channel, uart_port);
+	channel->ch_bd->bd_ops->copy_data_from_queue_to_uart(channel);
+}
+
 static void jsm_tty_start_tx(struct uart_port *port)
 {
 	struct jsm_channel *channel = (struct jsm_channel *)port;
@@ -216,14 +229,6 @@ static int jsm_tty_open(struct uart_port *port)
 			return -ENOMEM;
 		}
 	}
-	if (!channel->ch_wqueue) {
-		channel->ch_wqueue = kzalloc(WQUEUESIZE, GFP_KERNEL);
-		if (!channel->ch_wqueue) {
-			jsm_printk(INIT, ERR, &channel->ch_bd->pci_dev,
-				"unable to allocate write queue buf");
-			return -ENOMEM;
-		}
-	}
 
 	channel->ch_flags &= ~(CH_OPENING);
 	/*
@@ -237,7 +242,6 @@ static int jsm_tty_open(struct uart_port *port)
 	 */
 	channel->ch_r_head = channel->ch_r_tail = 0;
 	channel->ch_e_head = channel->ch_e_tail = 0;
-	channel->ch_w_head = channel->ch_w_tail = 0;
 
 	brd->bd_ops->flush_uart_write(channel);
 	brd->bd_ops->flush_uart_read(channel);
@@ -836,75 +840,3 @@ void jsm_check_queue_flow_control(struct jsm_channel *ch)
 		}
 	}
 }
-
-/*
- * jsm_tty_write()
- *
- * Take data from the user or kernel and send it out to the FEP.
- * In here exists all the Transparent Print magic as well.
- */
-int jsm_tty_write(struct uart_port *port)
-{
-	int bufcount;
-	int data_count = 0,data_count1 =0;
-	u16 head;
-	u16 tail;
-	u16 tmask;
-	u32 remain;
-	int temp_tail = port->state->xmit.tail;
-	struct jsm_channel *channel = (struct jsm_channel *)port;
-
-	tmask = WQUEUEMASK;
-	head = (channel->ch_w_head) & tmask;
-	tail = (channel->ch_w_tail) & tmask;
-
-	if ((bufcount = tail - head - 1) < 0)
-		bufcount += WQUEUESIZE;
-
-	bufcount = min(bufcount, 56);
-	remain = WQUEUESIZE - head;
-
-	data_count = 0;
-	if (bufcount >= remain) {
-		bufcount -= remain;
-		while ((port->state->xmit.head != temp_tail) &&
-		(data_count < remain)) {
-			channel->ch_wqueue[head++] =
-			port->state->xmit.buf[temp_tail];
-
-			temp_tail++;
-			temp_tail &= (UART_XMIT_SIZE - 1);
-			data_count++;
-		}
-		if (data_count == remain) head = 0;
-	}
-
-	data_count1 = 0;
-	if (bufcount > 0) {
-		remain = bufcount;
-		while ((port->state->xmit.head != temp_tail) &&
-			(data_count1 < remain)) {
-			channel->ch_wqueue[head++] =
-				port->state->xmit.buf[temp_tail];
-
-			temp_tail++;
-			temp_tail &= (UART_XMIT_SIZE - 1);
-			data_count1++;
-
-		}
-	}
-
-	port->state->xmit.tail = temp_tail;
-
-	data_count += data_count1;
-	if (data_count) {
-		head &= tmask;
-		channel->ch_w_head = head;
-	}
-
-	if (data_count) {
-		channel->ch_bd->bd_ops->copy_data_from_queue_to_uart(channel);
-	}
-
-	return data_count;
-}
diff --git a/drivers/tty/serial/pch_uart.c b/drivers/tty/serial/pch_uart.c
index b46218d679e..f913ed054c1 100644
--- a/drivers/tty/serial/pch_uart.c
+++ b/drivers/tty/serial/pch_uart.c
@@ -256,6 +256,8 @@ enum pch_uart_num_t {
 	pch_ml7213_uart2,
 	pch_ml7223_uart0,
 	pch_ml7223_uart1,
+	pch_ml7831_uart0,
+	pch_ml7831_uart1,
 };
 
 static struct pch_uart_driver_data drv_dat[] = {
@@ -268,6 +270,8 @@ static struct pch_uart_driver_data drv_dat[] = {
 	[pch_ml7213_uart2] = {PCH_UART_2LINE, 2},
 	[pch_ml7223_uart0] = {PCH_UART_8LINE, 0},
 	[pch_ml7223_uart1] = {PCH_UART_2LINE, 1},
+	[pch_ml7831_uart0] = {PCH_UART_8LINE, 0},
+	[pch_ml7831_uart1] = {PCH_UART_2LINE, 1},
 };
 
 static unsigned int default_baud = 9600;
@@ -626,6 +630,7 @@ static void pch_request_dma(struct uart_port *port)
 		dev_err(priv->port.dev, "%s:dma_request_channel FAILS(Rx)\n",
 			__func__);
 		dma_release_channel(priv->chan_tx);
+		priv->chan_tx = NULL;
 		return;
 	}
 
@@ -1213,8 +1218,7 @@ static void pch_uart_shutdown(struct uart_port *port)
 		dev_err(priv->port.dev,
 			"pch_uart_hal_set_fifo Failed(ret=%d)\n", ret);
 
-	if (priv->use_dma_flag)
-		pch_free_dma(port);
+	pch_free_dma(port);
 
 	free_irq(priv->port.irq, priv);
 }
@@ -1278,6 +1282,7 @@ static void pch_uart_set_termios(struct uart_port *port,
 	if (rtn)
 		goto out;
 
+	pch_uart_set_mctrl(&priv->port, priv->port.mctrl);
 	/* Don't rewrite B0 */
 	if (tty_termios_baud_rate(termios))
 		tty_termios_encode_baud_rate(termios, baud, baud);
@@ -1550,6 +1555,10 @@ static DEFINE_PCI_DEVICE_TABLE(pch_uart_pci_id) = {
 	 .driver_data = pch_ml7223_uart0},
 	{PCI_DEVICE(PCI_VENDOR_ID_ROHM, 0x800D),
 	 .driver_data = pch_ml7223_uart1},
+	{PCI_DEVICE(PCI_VENDOR_ID_ROHM, 0x8811),
+	 .driver_data = pch_ml7831_uart0},
+	{PCI_DEVICE(PCI_VENDOR_ID_ROHM, 0x8812),
+	 .driver_data = pch_ml7831_uart1},
 	{0,},
 };
 
diff --git a/drivers/tty/serial/pxa.c b/drivers/tty/serial/pxa.c
index 531931c1b25..5c8e3bba6c8 100644
--- a/drivers/tty/serial/pxa.c
+++ b/drivers/tty/serial/pxa.c
@@ -100,6 +100,16 @@ static inline void receive_chars(struct uart_pxa_port *up, int *status)
 	int max_count = 256;
 
 	do {
+		/* work around Errata #20 according to
+		 * Intel(R) PXA27x Processor Family
+		 * Specification Update (May 2005)
+		 *
+		 * Step 2
+		 * Disable the Reciever Time Out Interrupt via IER[RTOEI]
+		 */
+		up->ier &= ~UART_IER_RTOIE;
+		serial_out(up, UART_IER, up->ier);
+
 		ch = serial_in(up, UART_RX);
 		flag = TTY_NORMAL;
 		up->port.icount.rx++;
@@ -156,6 +166,16 @@ static inline void receive_chars(struct uart_pxa_port *up, int *status)
 		*status = serial_in(up, UART_LSR);
 	} while ((*status & UART_LSR_DR) && (max_count-- > 0));
 	tty_flip_buffer_push(tty);
+
+	/* work around Errata #20 according to
+	 * Intel(R) PXA27x Processor Family
+	 * Specification Update (May 2005)
+	 *
+	 * Step 6:
+	 * No more data in FIFO: Re-enable RTO interrupt via IER[RTOIE]
+	 */
+	up->ier |= UART_IER_RTOIE;
+	serial_out(up, UART_IER, up->ier);
 }
 
 static void transmit_chars(struct uart_pxa_port *up)
diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index a3efbea5dbb..25f3094ec74 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -2008,6 +2008,8 @@ int uart_resume_port(struct uart_driver *drv, struct uart_port *uport)
 		if (port->tty && port->tty->termios && termios.c_cflag == 0)
 			termios = *(port->tty->termios);
 
+		if (console_suspend_enabled)
+			uart_change_pm(state, 0);
 		uport->ops->set_termios(uport, &termios, NULL);
 		if (console_suspend_enabled)
 			console_start(uport->cons);
diff --git a/drivers/tty/serial/uartlite.c b/drivers/tty/serial/uartlite.c
index 8af1ed83a4c..0aed022d21b 100644
--- a/drivers/tty/serial/uartlite.c
+++ b/drivers/tty/serial/uartlite.c
@@ -568,8 +568,6 @@ static struct of_device_id ulite_of_match[] __devinitdata = {
 	{}
 };
 MODULE_DEVICE_TABLE(of, ulite_of_match);
-#else /* CONFIG_OF */
-#define ulite_of_match NULL
 #endif /* CONFIG_OF */
 
 static int __devinit ulite_probe(struct platform_device *pdev)
@@ -609,7 +607,7 @@ static struct platform_driver ulite_platform_driver = {
 	.driver = {
 		.owner = THIS_MODULE,
 		.name  = "uartlite",
-		.of_match_table = ulite_of_match,
+		.of_match_table = of_match_ptr(ulite_of_match),
 	},
 };
 
diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 4f1fc81112e..1a890e270be 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -194,8 +194,7 @@ static inline struct tty_struct *file_tty(struct file *file)
 	return ((struct tty_file_private *)file->private_data)->tty;
 }
 
-/* Associate a new file with the tty structure */
-int tty_add_file(struct tty_struct *tty, struct file *file)
+int tty_alloc_file(struct file *file)
 {
 	struct tty_file_private *priv;
 
@@ -203,15 +202,36 @@ int tty_add_file(struct tty_struct *tty, struct file *file)
 	if (!priv)
 		return -ENOMEM;
 
+	file->private_data = priv;
+
+	return 0;
+}
+
+/* Associate a new file with the tty structure */
+void tty_add_file(struct tty_struct *tty, struct file *file)
+{
+	struct tty_file_private *priv = file->private_data;
+
 	priv->tty = tty;
 	priv->file = file;
-	file->private_data = priv;
 
 	spin_lock(&tty_files_lock);
 	list_add(&priv->list, &tty->tty_files);
 	spin_unlock(&tty_files_lock);
+}
 
-	return 0;
+/**
+ * tty_free_file - free file->private_data
+ *
+ * This shall be used only for fail path handling when tty_add_file was not
+ * called yet.
+ */
+void tty_free_file(struct file *file)
+{
+	struct tty_file_private *priv = file->private_data;
+
+	file->private_data = NULL;
+	kfree(priv);
 }
 
 /* Delete file from its tty */
@@ -222,8 +242,7 @@ void tty_del_file(struct file *file)
 	spin_lock(&tty_files_lock);
 	list_del(&priv->list);
 	spin_unlock(&tty_files_lock);
-	file->private_data = NULL;
-	kfree(priv);
+	tty_free_file(file);
 }
 
 
@@ -1811,6 +1830,10 @@ static int tty_open(struct inode *inode, struct file *filp)
 	nonseekable_open(inode, filp);
 
 retry_open:
+	retval = tty_alloc_file(filp);
+	if (retval)
+		return -ENOMEM;
+
 	noctty = filp->f_flags & O_NOCTTY;
 	index  = -1;
 	retval = 0;
@@ -1823,6 +1846,7 @@ retry_open:
 		if (!tty) {
 			tty_unlock();
 			mutex_unlock(&tty_mutex);
+			tty_free_file(filp);
 			return -ENXIO;
 		}
 		driver = tty_driver_kref_get(tty->driver);
@@ -1855,6 +1879,7 @@ retry_open:
 		}
 		tty_unlock();
 		mutex_unlock(&tty_mutex);
+		tty_free_file(filp);
 		return -ENODEV;
 	}
 
@@ -1862,6 +1887,7 @@ retry_open:
 	if (!driver) {
 		tty_unlock();
 		mutex_unlock(&tty_mutex);
+		tty_free_file(filp);
 		return -ENODEV;
 	}
 got_driver:
@@ -1872,6 +1898,8 @@ got_driver:
 		if (IS_ERR(tty)) {
 			tty_unlock();
 			mutex_unlock(&tty_mutex);
+			tty_driver_kref_put(driver);
+			tty_free_file(filp);
 			return PTR_ERR(tty);
 		}
 	}
@@ -1887,15 +1915,11 @@ got_driver:
 	tty_driver_kref_put(driver);
 	if (IS_ERR(tty)) {
 		tty_unlock();
+		tty_free_file(filp);
 		return PTR_ERR(tty);
 	}
 
-	retval = tty_add_file(tty, filp);
-	if (retval) {
-		tty_unlock();
-		tty_release(inode, filp);
-		return retval;
-	}
+	tty_add_file(tty, filp);
 
 	check_tty_count(tty, "tty_open");
 	if (tty->driver->type == TTY_DRIVER_TYPE_PTY &&
diff --git a/drivers/tty/tty_ldisc.c b/drivers/tty/tty_ldisc.c
index ef925d58171..a76c808afad 100644
--- a/drivers/tty/tty_ldisc.c
+++ b/drivers/tty/tty_ldisc.c
@@ -36,6 +36,7 @@
 
 #include <linux/kmod.h>
 #include <linux/nsproxy.h>
+#include <linux/ratelimit.h>
 
 /*
  *	This guards the refcounted line discipline lists. The lock
@@ -548,15 +549,16 @@ static void tty_ldisc_flush_works(struct tty_struct *tty)
 /**
  *	tty_ldisc_wait_idle	-	wait for the ldisc to become idle
  *	@tty: tty to wait for
+ *	@timeout: for how long to wait at most
  *
  *	Wait for the line discipline to become idle. The discipline must
  *	have been halted for this to guarantee it remains idle.
  */
-static int tty_ldisc_wait_idle(struct tty_struct *tty)
+static int tty_ldisc_wait_idle(struct tty_struct *tty, long timeout)
 {
-	int ret;
+	long ret;
 	ret = wait_event_timeout(tty_ldisc_idle,
-			atomic_read(&tty->ldisc->users) == 1, 5 * HZ);
+			atomic_read(&tty->ldisc->users) == 1, timeout);
 	if (ret < 0)
 		return ret;
 	return ret > 0 ? 0 : -EBUSY;
@@ -666,7 +668,7 @@ int tty_set_ldisc(struct tty_struct *tty, int ldisc)
 
 	tty_ldisc_flush_works(tty);
 
-	retval = tty_ldisc_wait_idle(tty);
+	retval = tty_ldisc_wait_idle(tty, 5 * HZ);
 
 	tty_lock();
 	mutex_lock(&tty->ldisc_mutex);
@@ -763,8 +765,6 @@ static int tty_ldisc_reinit(struct tty_struct *tty, int ldisc)
 	if (IS_ERR(ld))
 		return -1;
 
-	WARN_ON_ONCE(tty_ldisc_wait_idle(tty));
-
 	tty_ldisc_close(tty, tty->ldisc);
 	tty_ldisc_put(tty->ldisc);
 	tty->ldisc = NULL;
@@ -839,7 +839,7 @@ void tty_ldisc_hangup(struct tty_struct *tty)
 	tty_unlock();
 	cancel_work_sync(&tty->buf.work);
 	mutex_unlock(&tty->ldisc_mutex);
-
+retry:
 	tty_lock();
 	mutex_lock(&tty->ldisc_mutex);
 
@@ -848,6 +848,22 @@ void tty_ldisc_hangup(struct tty_struct *tty)
 	   it means auditing a lot of other paths so this is
 	   a FIXME */
 	if (tty->ldisc) {	/* Not yet closed */
+		if (atomic_read(&tty->ldisc->users) != 1) {
+			char cur_n[TASK_COMM_LEN], tty_n[64];
+			long timeout = 3 * HZ;
+			tty_unlock();
+
+			while (tty_ldisc_wait_idle(tty, timeout) == -EBUSY) {
+				timeout = MAX_SCHEDULE_TIMEOUT;
+				printk_ratelimited(KERN_WARNING
+					"%s: waiting (%s) for %s took too long, but we keep waiting...\n",
+					__func__, get_task_comm(cur_n, current),
+					tty_name(tty, tty_n));
+			}
+			mutex_unlock(&tty->ldisc_mutex);
+			goto retry;
+		}
+
 		if (reset == 0) {
 
 			if (!tty_ldisc_reinit(tty, tty->termios->c_line))
diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index dac7676ce21..2ffcaa0b0b7 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -539,7 +539,6 @@ static void acm_port_down(struct acm *acm)
 {
 	int i;
 
-	mutex_lock(&open_mutex);
 	if (acm->dev) {
 		usb_autopm_get_interface(acm->control);
 		acm_set_control(acm, acm->ctrlout = 0);
@@ -551,14 +550,15 @@ static void acm_port_down(struct acm *acm)
 		acm->control->needs_remote_wakeup = 0;
 		usb_autopm_put_interface(acm->control);
 	}
-	mutex_unlock(&open_mutex);
 }
 
 static void acm_tty_hangup(struct tty_struct *tty)
 {
 	struct acm *acm = tty->driver_data;
 	tty_port_hangup(&acm->port);
+	mutex_lock(&open_mutex);
 	acm_port_down(acm);
+	mutex_unlock(&open_mutex);
 }
 
 static void acm_tty_close(struct tty_struct *tty, struct file *filp)
@@ -569,8 +569,9 @@ static void acm_tty_close(struct tty_struct *tty, struct file *filp)
 	   shutdown */
 	if (!acm)
 		return;
+
+	mutex_lock(&open_mutex);
 	if (tty_port_close_start(&acm->port, tty, filp) == 0) {
-		mutex_lock(&open_mutex);
 		if (!acm->dev) {
 			tty_port_tty_set(&acm->port, NULL);
 			acm_tty_unregister(acm);
@@ -582,6 +583,7 @@ static void acm_tty_close(struct tty_struct *tty, struct file *filp)
 	acm_port_down(acm);
 	tty_port_close_end(&acm->port, tty);
 	tty_port_tty_set(&acm->port, NULL);
+	mutex_unlock(&open_mutex);
 }
 
 static int acm_tty_write(struct tty_struct *tty,
@@ -1534,6 +1536,9 @@ static const struct usb_device_id acm_ids[] = {
 	{ NOKIA_PCSUITE_ACM_INFO(0x03cd), }, /* Nokia C7 */
 	{ SAMSUNG_PCSUITE_ACM_INFO(0x6651), }, /* Samsung GTi8510 (INNOV8) */
 
+	/* Support for Owen devices */
+	{ USB_DEVICE(0x03eb, 0x0030), }, /* Owen SI30 */
+
 	/* NOTE: non-Nokia COMM/ACM/0xff is likely MSFT RNDIS... NOT a modem! */
 
 	/* Support Lego NXT using pbLua firmware */
diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c
index 37518dfdeb9..0ca54e22d31 100644
--- a/drivers/usb/core/devio.c
+++ b/drivers/usb/core/devio.c
@@ -407,7 +407,7 @@ static void async_completed(struct urb *urb)
 		sinfo.si_errno = as->status;
 		sinfo.si_code = SI_ASYNCIO;
 		sinfo.si_addr = as->userurb;
-		pid = as->pid;
+		pid = get_pid(as->pid);
 		uid = as->uid;
 		euid = as->euid;
 		secid = as->secid;
@@ -422,9 +422,11 @@ static void async_completed(struct urb *urb)
 		cancel_bulk_urbs(ps, as->bulk_addr);
 	spin_unlock(&ps->lock);
 
-	if (signr)
+	if (signr) {
 		kill_pid_info_as_uid(sinfo.si_signo, &sinfo, pid, uid,
 				      euid, secid);
+		put_pid(pid);
+	}
 
 	wake_up(&ps->wait);
 }
@@ -607,9 +609,10 @@ static int findintfep(struct usb_device *dev, unsigned int ep)
 }
 
 static int check_ctrlrecip(struct dev_state *ps, unsigned int requesttype,
-			   unsigned int index)
+			   unsigned int request, unsigned int index)
 {
 	int ret = 0;
+	struct usb_host_interface *alt_setting;
 
 	if (ps->dev->state != USB_STATE_UNAUTHENTICATED
 	 && ps->dev->state != USB_STATE_ADDRESS
@@ -618,6 +621,19 @@ static int check_ctrlrecip(struct dev_state *ps, unsigned int requesttype,
 	if (USB_TYPE_VENDOR == (USB_TYPE_MASK & requesttype))
 		return 0;
 
+	/*
+	 * check for the special corner case 'get_device_id' in the printer
+	 * class specification, where wIndex is (interface << 8 | altsetting)
+	 * instead of just interface
+	 */
+	if (requesttype == 0xa1 && request == 0) {
+		alt_setting = usb_find_alt_setting(ps->dev->actconfig,
+						   index >> 8, index & 0xff);
+		if (alt_setting
+		 && alt_setting->desc.bInterfaceClass == USB_CLASS_PRINTER)
+			index >>= 8;
+	}
+
 	index &= 0xff;
 	switch (requesttype & USB_RECIP_MASK) {
 	case USB_RECIP_ENDPOINT:
@@ -770,7 +786,8 @@ static int proc_control(struct dev_state *ps, void __user *arg)
 
 	if (copy_from_user(&ctrl, arg, sizeof(ctrl)))
 		return -EFAULT;
-	ret = check_ctrlrecip(ps, ctrl.bRequestType, ctrl.wIndex);
+	ret = check_ctrlrecip(ps, ctrl.bRequestType, ctrl.bRequest,
+			      ctrl.wIndex);
 	if (ret)
 		return ret;
 	wLength = ctrl.wLength;		/* To suppress 64k PAGE_SIZE warning */
@@ -1100,7 +1117,7 @@ static int proc_do_submiturb(struct dev_state *ps, struct usbdevfs_urb *uurb,
 			kfree(dr);
 			return -EINVAL;
 		}
-		ret = check_ctrlrecip(ps, dr->bRequestType,
+		ret = check_ctrlrecip(ps, dr->bRequestType, dr->bRequest,
 				      le16_to_cpup(&dr->wIndex));
 		if (ret) {
 			kfree(dr);
diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c
index 34e3da5aa72..75b4bc03e2e 100644
--- a/drivers/usb/core/driver.c
+++ b/drivers/usb/core/driver.c
@@ -1583,7 +1583,7 @@ int usb_autopm_get_interface_async(struct usb_interface *intf)
 	dev_vdbg(&intf->dev, "%s: cnt %d -> %d\n",
 			__func__, atomic_read(&intf->dev.power.usage_count),
 			status);
-	if (status > 0)
+	if (status > 0 || status == -EINPROGRESS)
 		status = 0;
 	return status;
 }
@@ -1668,6 +1668,11 @@ int usb_runtime_suspend(struct device *dev)
 		return -EAGAIN;
 
 	status = usb_suspend_both(udev, PMSG_AUTO_SUSPEND);
+
+	/* Allow a retry if autosuspend failed temporarily */
+	if (status == -EAGAIN || status == -EBUSY)
+		usb_mark_last_busy(udev);
+
 	/* The PM core reacts badly unless the return code is 0,
 	 * -EAGAIN, or -EBUSY, so always return -EBUSY on an error.
 	 */
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 98801cf4c18..bcda835815d 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -819,6 +819,12 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type)
 					USB_PORT_FEAT_C_PORT_LINK_STATE);
 		}
 
+		if ((portchange & USB_PORT_STAT_C_BH_RESET) &&
+				hub_is_superspeed(hub->hdev)) {
+			need_debounce_delay = true;
+			clear_port_feature(hub->hdev, port1,
+					USB_PORT_FEAT_C_BH_PORT_RESET);
+		}
 		/* We can forget about a "removed" device when there's a
 		 * physical disconnect or the connect status changes.
 		 */
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 81ce6a8e1d9..ecf12e15a7e 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -38,6 +38,54 @@ static const struct usb_device_id usb_quirk_list[] = {
 	/* Creative SB Audigy 2 NX */
 	{ USB_DEVICE(0x041e, 0x3020), .driver_info = USB_QUIRK_RESET_RESUME },
 
+	/* Logitech Webcam C200 */
+	{ USB_DEVICE(0x046d, 0x0802), .driver_info = USB_QUIRK_RESET_RESUME },
+
+	/* Logitech Webcam C250 */
+	{ USB_DEVICE(0x046d, 0x0804), .driver_info = USB_QUIRK_RESET_RESUME },
+
+	/* Logitech Webcam C300 */
+	{ USB_DEVICE(0x046d, 0x0805), .driver_info = USB_QUIRK_RESET_RESUME },
+
+	/* Logitech Webcam B/C500 */
+	{ USB_DEVICE(0x046d, 0x0807), .driver_info = USB_QUIRK_RESET_RESUME },
+
+	/* Logitech Webcam C600 */
+	{ USB_DEVICE(0x046d, 0x0808), .driver_info = USB_QUIRK_RESET_RESUME },
+
+	/* Logitech Webcam Pro 9000 */
+	{ USB_DEVICE(0x046d, 0x0809), .driver_info = USB_QUIRK_RESET_RESUME },
+
+	/* Logitech Webcam C905 */
+	{ USB_DEVICE(0x046d, 0x080a), .driver_info = USB_QUIRK_RESET_RESUME },
+
+	/* Logitech Webcam C210 */
+	{ USB_DEVICE(0x046d, 0x0819), .driver_info = USB_QUIRK_RESET_RESUME },
+
+	/* Logitech Webcam C260 */
+	{ USB_DEVICE(0x046d, 0x081a), .driver_info = USB_QUIRK_RESET_RESUME },
+
+	/* Logitech Webcam C310 */
+	{ USB_DEVICE(0x046d, 0x081b), .driver_info = USB_QUIRK_RESET_RESUME },
+
+	/* Logitech Webcam C910 */
+	{ USB_DEVICE(0x046d, 0x0821), .driver_info = USB_QUIRK_RESET_RESUME },
+
+	/* Logitech Webcam C160 */
+	{ USB_DEVICE(0x046d, 0x0824), .driver_info = USB_QUIRK_RESET_RESUME },
+
+	/* Logitech Webcam C270 */
+	{ USB_DEVICE(0x046d, 0x0825), .driver_info = USB_QUIRK_RESET_RESUME },
+
+	/* Logitech Quickcam Pro 9000 */
+	{ USB_DEVICE(0x046d, 0x0990), .driver_info = USB_QUIRK_RESET_RESUME },
+
+	/* Logitech Quickcam E3500 */
+	{ USB_DEVICE(0x046d, 0x09a4), .driver_info = USB_QUIRK_RESET_RESUME },
+
+	/* Logitech Quickcam Vision Pro */
+	{ USB_DEVICE(0x046d, 0x09a6), .driver_info = USB_QUIRK_RESET_RESUME },
+
 	/* Logitech Harmony 700-series */
 	{ USB_DEVICE(0x046d, 0xc122), .driver_info = USB_QUIRK_DELAY_INIT },
 
@@ -69,6 +117,9 @@ static const struct usb_device_id usb_quirk_list[] = {
 	{ USB_DEVICE(0x06a3, 0x0006), .driver_info =
 			USB_QUIRK_CONFIG_INTF_STRINGS },
 
+	/* Guillemot Webcam Hercules Dualpix Exchange*/
+	{ USB_DEVICE(0x06f8, 0x0804), .driver_info = USB_QUIRK_RESET_RESUME },
+
 	/* M-Systems Flash Disk Pioneers */
 	{ USB_DEVICE(0x08ec, 0x1000), .driver_info = USB_QUIRK_RESET_RESUME },
 
diff --git a/drivers/usb/gadget/Kconfig b/drivers/usb/gadget/Kconfig
index 5a084b9cfa3..6f5049156e1 100644
--- a/drivers/usb/gadget/Kconfig
+++ b/drivers/usb/gadget/Kconfig
@@ -442,7 +442,7 @@ config USB_LANGWELL
 	   gadget drivers to also be dynamically linked.
 
 config USB_EG20T
-	tristate "Intel EG20T PCH/OKI SEMICONDUCTOR ML7213 IOH UDC"
+	tristate "Intel EG20T PCH/LAPIS Semiconductor IOH(ML7213/ML7831) UDC"
 	depends on PCI
 	select USB_GADGET_DUALSPEED
 	help
@@ -458,10 +458,11 @@ config USB_EG20T
 	  This driver dose not support interrupt transfer or isochronous
 	  transfer modes.
 
-	  This driver also can be used for OKI SEMICONDUCTOR's ML7213 which is
+	  This driver also can be used for LAPIS Semiconductor's ML7213 which is
 	  for IVI(In-Vehicle Infotainment) use.
-	  ML7213 is companion chip for Intel Atom E6xx series.
-	  ML7213 is completely compatible for Intel EG20T PCH.
+	  ML7831 is for general purpose use.
+	  ML7213/ML7831 is companion chip for Intel Atom E6xx series.
+	  ML7213/ML7831 is completely compatible for Intel EG20T PCH.
 
 config USB_CI13XXX_MSM
 	tristate "MIPS USB CI13xxx for MSM"
diff --git a/drivers/usb/gadget/pch_udc.c b/drivers/usb/gadget/pch_udc.c
index f96615ab6b7..06c40b164b2 100644
--- a/drivers/usb/gadget/pch_udc.c
+++ b/drivers/usb/gadget/pch_udc.c
@@ -363,6 +363,7 @@ struct pch_udc_dev {
 #define PCI_DEVICE_ID_INTEL_EG20T_UDC	0x8808
 #define PCI_VENDOR_ID_ROHM		0x10DB
 #define PCI_DEVICE_ID_ML7213_IOH_UDC	0x801D
+#define PCI_DEVICE_ID_ML7831_IOH_UDC	0x8808
 
 static const char	ep0_string[] = "ep0in";
 static DEFINE_SPINLOCK(udc_stall_spinlock);	/* stall spin lock */
@@ -2979,6 +2980,11 @@ static DEFINE_PCI_DEVICE_TABLE(pch_udc_pcidev_id) = {
 		.class = (PCI_CLASS_SERIAL_USB << 8) | 0xfe,
 		.class_mask = 0xffffffff,
 	},
+	{
+		PCI_DEVICE(PCI_VENDOR_ID_ROHM, PCI_DEVICE_ID_ML7831_IOH_UDC),
+		.class = (PCI_CLASS_SERIAL_USB << 8) | 0xfe,
+		.class_mask = 0xffffffff,
+	},
 	{ 0 },
 };
 
diff --git a/drivers/usb/gadget/printer.c b/drivers/usb/gadget/printer.c
index a341dde6f9c..0c06d8000ef 100644
--- a/drivers/usb/gadget/printer.c
+++ b/drivers/usb/gadget/printer.c
@@ -1611,7 +1611,7 @@ cleanup(void)
 	if (status)
 		ERROR(dev, "usb_gadget_unregister_driver %x\n", status);
 
-	unregister_chrdev_region(g_printer_devno, 2);
+	unregister_chrdev_region(g_printer_devno, 1);
 	class_destroy(usb_gadget_class);
 	mutex_unlock(&usb_printer_gadget.lock_printer_io);
 }
diff --git a/drivers/usb/host/ehci-dbg.c b/drivers/usb/host/ehci-dbg.c
index 40a844c1dbb..3e2ccb0dd25 100644
--- a/drivers/usb/host/ehci-dbg.c
+++ b/drivers/usb/host/ehci-dbg.c
@@ -808,7 +808,7 @@ static ssize_t fill_registers_buffer(struct debug_buffer *buf)
 	next += temp;
 
 	temp = scnprintf (next, size, "uframe %04x\n",
-			ehci_readl(ehci, &ehci->regs->frame_index));
+			ehci_read_frame_index(ehci));
 	size -= temp;
 	next += temp;
 
diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c
index f72ae0b6ee7..d7318e32170 100644
--- a/drivers/usb/host/ehci-hcd.c
+++ b/drivers/usb/host/ehci-hcd.c
@@ -768,6 +768,35 @@ static int ehci_run (struct usb_hcd *hcd)
 	return 0;
 }
 
+static int __maybe_unused ehci_setup (struct usb_hcd *hcd)
+{
+	struct ehci_hcd *ehci = hcd_to_ehci(hcd);
+	int retval;
+
+	ehci->regs = (void __iomem *)ehci->caps +
+	    HC_LENGTH(ehci, ehci_readl(ehci, &ehci->caps->hc_capbase));
+	dbg_hcs_params(ehci, "reset");
+	dbg_hcc_params(ehci, "reset");
+
+	/* cache this readonly data; minimize chip reads */
+	ehci->hcs_params = ehci_readl(ehci, &ehci->caps->hcs_params);
+
+	ehci->sbrn = HCD_USB2;
+
+	retval = ehci_halt(ehci);
+	if (retval)
+		return retval;
+
+	/* data structure init */
+	retval = ehci_init(hcd);
+	if (retval)
+		return retval;
+
+	ehci_reset(ehci);
+
+	return 0;
+}
+
 /*-------------------------------------------------------------------------*/
 
 static irqreturn_t ehci_irq (struct usb_hcd *hcd)
@@ -1166,8 +1195,7 @@ ehci_endpoint_reset(struct usb_hcd *hcd, struct usb_host_endpoint *ep)
 static int ehci_get_frame (struct usb_hcd *hcd)
 {
 	struct ehci_hcd		*ehci = hcd_to_ehci (hcd);
-	return (ehci_readl(ehci, &ehci->regs->frame_index) >> 3) %
-		ehci->periodic_size;
+	return (ehci_read_frame_index(ehci) >> 3) % ehci->periodic_size;
 }
 
 /*-------------------------------------------------------------------------*/
diff --git a/drivers/usb/host/ehci-pci.c b/drivers/usb/host/ehci-pci.c
index 1102ce65a3a..1d1caa6a33f 100644
--- a/drivers/usb/host/ehci-pci.c
+++ b/drivers/usb/host/ehci-pci.c
@@ -224,6 +224,11 @@ static int ehci_pci_setup(struct usb_hcd *hcd)
 			pci_dev_put(p_smbus);
 		}
 		break;
+	case PCI_VENDOR_ID_NETMOS:
+		/* MosChip frame-index-register bug */
+		ehci_info(ehci, "applying MosChip frame-index workaround\n");
+		ehci->frame_index_bug = 1;
+		break;
 	}
 
 	/* optional debug port, normally in the first BAR */
diff --git a/drivers/usb/host/ehci-q.c b/drivers/usb/host/ehci-q.c
index 0917e3a3246..b7f9496e4f0 100644
--- a/drivers/usb/host/ehci-q.c
+++ b/drivers/usb/host/ehci-q.c
@@ -995,6 +995,12 @@ static void qh_link_async (struct ehci_hcd *ehci, struct ehci_qh *qh)
 	head->qh_next.qh = qh;
 	head->hw->hw_next = dma;
 
+	/*
+	 * flush qh descriptor into memory immediately,
+	 * see comments in qh_append_tds.
+	 */
+	ehci_sync_mem();
+
 	qh_get(qh);
 	qh->xacterrs = 0;
 	qh->qh_state = QH_STATE_LINKED;
@@ -1082,6 +1088,18 @@ static struct ehci_qh *qh_append_tds (
 			wmb ();
 			dummy->hw_token = token;
 
+			/*
+			 * Writing to dma coherent buffer on ARM may
+			 * be delayed to reach memory, so HC may not see
+			 * hw_token of dummy qtd in time, which can cause
+			 * the qtd transaction to be executed very late,
+			 * and degrade performance a lot. ehci_sync_mem
+			 * is added to flush 'token' immediatelly into
+			 * memory, so that ehci can execute the transaction
+			 * ASAP.
+			 */
+			ehci_sync_mem();
+
 			urb->hcpriv = qh_get (qh);
 		}
 	}
diff --git a/drivers/usb/host/ehci-sched.c b/drivers/usb/host/ehci-sched.c
index 2abf8543f08..c787af2ba4b 100644
--- a/drivers/usb/host/ehci-sched.c
+++ b/drivers/usb/host/ehci-sched.c
@@ -36,6 +36,27 @@
 
 static int ehci_get_frame (struct usb_hcd *hcd);
 
+#ifdef CONFIG_PCI
+
+static unsigned ehci_read_frame_index(struct ehci_hcd *ehci)
+{
+	unsigned uf;
+
+	/*
+	 * The MosChip MCS9990 controller updates its microframe counter
+	 * a little before the frame counter, and occasionally we will read
+	 * the invalid intermediate value.  Avoid problems by checking the
+	 * microframe number (the low-order 3 bits); if they are 0 then
+	 * re-read the register to get the correct value.
+	 */
+	uf = ehci_readl(ehci, &ehci->regs->frame_index);
+	if (unlikely(ehci->frame_index_bug && ((uf & 7) == 0)))
+		uf = ehci_readl(ehci, &ehci->regs->frame_index);
+	return uf;
+}
+
+#endif
+
 /*-------------------------------------------------------------------------*/
 
 /*
@@ -482,7 +503,7 @@ static int enable_periodic (struct ehci_hcd *ehci)
 	ehci_to_hcd(ehci)->state = HC_STATE_RUNNING;
 
 	/* make sure ehci_work scans these */
-	ehci->next_uframe = ehci_readl(ehci, &ehci->regs->frame_index)
+	ehci->next_uframe = ehci_read_frame_index(ehci)
 		% (ehci->periodic_size << 3);
 	if (unlikely(ehci->broken_periodic))
 		ehci->last_periodic_enable = ktime_get_real();
@@ -1409,7 +1430,7 @@ iso_stream_schedule (
 		goto fail;
 	}
 
-	now = ehci_readl(ehci, &ehci->regs->frame_index) & (mod - 1);
+	now = ehci_read_frame_index(ehci) & (mod - 1);
 
 	/* Typical case: reuse current schedule, stream is still active.
 	 * Hopefully there are no gaps from the host falling behind
@@ -1455,30 +1476,36 @@ iso_stream_schedule (
 	 * jump until after the queue is primed.
 	 */
 	else {
+		int done = 0;
 		start = SCHEDULE_SLOP + (now & ~0x07);
 
 		/* NOTE:  assumes URB_ISO_ASAP, to limit complexity/bugs */
 
-		/* find a uframe slot with enough bandwidth */
-		next = start + period;
-		for (; start < next; start++) {
-
+		/* find a uframe slot with enough bandwidth.
+		 * Early uframes are more precious because full-speed
+		 * iso IN transfers can't use late uframes,
+		 * and therefore they should be allocated last.
+		 */
+		next = start;
+		start += period;
+		do {
+			start--;
 			/* check schedule: enough space? */
 			if (stream->highspeed) {
 				if (itd_slot_ok(ehci, mod, start,
 						stream->usecs, period))
-					break;
+					done = 1;
 			} else {
 				if ((start % 8) >= 6)
 					continue;
 				if (sitd_slot_ok(ehci, mod, stream,
 						start, sched, period))
-					break;
+					done = 1;
 			}
-		}
+		} while (start > next && !done);
 
 		/* no room in the schedule */
-		if (start == next) {
+		if (!done) {
 			ehci_dbg(ehci, "iso resched full %p (now %d max %d)\n",
 				urb, now, now + mod);
 			status = -ENOSPC;
@@ -2276,7 +2303,7 @@ scan_periodic (struct ehci_hcd *ehci)
 	 */
 	now_uframe = ehci->next_uframe;
 	if (HC_IS_RUNNING(ehci_to_hcd(ehci)->state)) {
-		clock = ehci_readl(ehci, &ehci->regs->frame_index);
+		clock = ehci_read_frame_index(ehci);
 		clock_frame = (clock >> 3) & (ehci->periodic_size - 1);
 	} else  {
 		clock = now_uframe + mod - 1;
@@ -2455,8 +2482,7 @@ restart:
 					|| ehci->periodic_sched == 0)
 				break;
 			ehci->next_uframe = now_uframe;
-			now = ehci_readl(ehci, &ehci->regs->frame_index) &
-					(mod - 1);
+			now = ehci_read_frame_index(ehci) & (mod - 1);
 			if (now_uframe == now)
 				break;
 
diff --git a/drivers/usb/host/ehci.h b/drivers/usb/host/ehci.h
index cc7d337ec35..395382f40a2 100644
--- a/drivers/usb/host/ehci.h
+++ b/drivers/usb/host/ehci.h
@@ -139,6 +139,7 @@ struct ehci_hcd {			/* one per controller */
 	unsigned		fs_i_thresh:1;	/* Intel iso scheduling */
 	unsigned		use_dummy_qh:1;	/* AMD Frame List table quirk*/
 	unsigned		has_synopsys_hc_bug:1; /* Synopsys HC */
+	unsigned		frame_index_bug:1; /* MosChip (AKA NetMos) */
 
 	/* required for usb32 quirk */
 	#define OHCI_CTRL_HCFS          (3 << 6)
@@ -738,6 +739,39 @@ static inline u32 hc32_to_cpup (const struct ehci_hcd *ehci, const __hc32 *x)
 
 #endif
 
+/*
+ * Writing to dma coherent memory on ARM may be delayed via L2
+ * writing buffer, so introduce the helper which can flush L2 writing
+ * buffer into memory immediately, especially used to flush ehci
+ * descriptor to memory.
+ */
+#ifdef	CONFIG_ARM_DMA_MEM_BUFFERABLE
+static inline void ehci_sync_mem()
+{
+	mb();
+}
+#else
+static inline void ehci_sync_mem()
+{
+}
+#endif
+
+/*-------------------------------------------------------------------------*/
+
+#ifdef CONFIG_PCI
+
+/* For working around the MosChip frame-index-register bug */
+static unsigned ehci_read_frame_index(struct ehci_hcd *ehci);
+
+#else
+
+static inline unsigned ehci_read_frame_index(struct ehci_hcd *ehci)
+{
+	return ehci_readl(ehci, &ehci->regs->frame_index);
+}
+
+#endif
+
 /*-------------------------------------------------------------------------*/
 
 #ifndef DEBUG
diff --git a/drivers/usb/host/fhci-sched.c b/drivers/usb/host/fhci-sched.c
index a42ef380e91..2df851b4bc7 100644
--- a/drivers/usb/host/fhci-sched.c
+++ b/drivers/usb/host/fhci-sched.c
@@ -1,7 +1,7 @@
 /*
  * Freescale QUICC Engine USB Host Controller Driver
  *
- * Copyright (c) Freescale Semicondutor, Inc. 2006.
+ * Copyright (c) Freescale Semicondutor, Inc. 2006, 2011.
  *               Shlomi Gridish <gridish@freescale.com>
  *               Jerry Huang <Chang-Ming.Huang@freescale.com>
  * Copyright (c) Logic Product Development, Inc. 2007
@@ -810,9 +810,11 @@ void fhci_queue_urb(struct fhci_hcd *fhci, struct urb *urb)
 		ed->dev_addr = usb_pipedevice(urb->pipe);
 		ed->max_pkt_size = usb_maxpacket(urb->dev, urb->pipe,
 			usb_pipeout(urb->pipe));
+		/* setup stage */
 		td = fhci_td_fill(fhci, urb, urb_priv, ed, cnt++, FHCI_TA_SETUP,
 			USB_TD_TOGGLE_DATA0, urb->setup_packet, 8, 0, 0, true);
 
+		/* data stage */
 		if (data_len > 0) {
 			td = fhci_td_fill(fhci, urb, urb_priv, ed, cnt++,
 				usb_pipeout(urb->pipe) ? FHCI_TA_OUT :
@@ -820,9 +822,18 @@ void fhci_queue_urb(struct fhci_hcd *fhci, struct urb *urb)
 				USB_TD_TOGGLE_DATA1, data, data_len, 0, 0,
 				true);
 		}
-		td = fhci_td_fill(fhci, urb, urb_priv, ed, cnt++,
-			usb_pipeout(urb->pipe) ? FHCI_TA_IN : FHCI_TA_OUT,
-			USB_TD_TOGGLE_DATA1, data, 0, 0, 0, true);
+
+		/* status stage */
+		if (data_len > 0)
+			td = fhci_td_fill(fhci, urb, urb_priv, ed, cnt++,
+				(usb_pipeout(urb->pipe) ? FHCI_TA_IN :
+							  FHCI_TA_OUT),
+				USB_TD_TOGGLE_DATA1, data, 0, 0, 0, true);
+		else
+			 td = fhci_td_fill(fhci, urb, urb_priv, ed, cnt++,
+				FHCI_TA_IN,
+				USB_TD_TOGGLE_DATA1, data, 0, 0, 0, true);
+
 		urb_state = US_CTRL_SETUP;
 		break;
 	case FHCI_TF_ISO:
diff --git a/drivers/usb/host/ohci-hub.c b/drivers/usb/host/ohci-hub.c
index 9154615292d..2f00040fc40 100644
--- a/drivers/usb/host/ohci-hub.c
+++ b/drivers/usb/host/ohci-hub.c
@@ -356,10 +356,7 @@ static void ohci_finish_controller_resume(struct usb_hcd *hcd)
 		msleep(20);
 	}
 
-	/* Does the root hub have a port wakeup pending? */
-	if (ohci_readl(ohci, &ohci->regs->intrstatus) &
-			(OHCI_INTR_RD | OHCI_INTR_RHSC))
-		usb_hcd_resume_root_hub(hcd);
+	usb_hcd_resume_root_hub(hcd);
 }
 
 /* Carry out polling-, autostop-, and autoresume-related state changes */
diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c
index 629a96813fd..a495d489918 100644
--- a/drivers/usb/host/pci-quirks.c
+++ b/drivers/usb/host/pci-quirks.c
@@ -626,7 +626,7 @@ static void __devinit quirk_usb_disable_ehci(struct pci_dev *pdev)
 	void __iomem *base, *op_reg_base;
 	u32	hcc_params, cap, val;
 	u8	offset, cap_length;
-	int	wait_time, delta, count = 256/4;
+	int	wait_time, count = 256/4;
 
 	if (!mmio_resource_enabled(pdev, 0))
 		return;
@@ -672,11 +672,10 @@ static void __devinit quirk_usb_disable_ehci(struct pci_dev *pdev)
 		writel(val, op_reg_base + EHCI_USBCMD);
 
 		wait_time = 2000;
-		delta = 100;
 		do {
 			writel(0x3f, op_reg_base + EHCI_USBSTS);
-			udelay(delta);
-			wait_time -= delta;
+			udelay(100);
+			wait_time -= 100;
 			val = readl(op_reg_base + EHCI_USBSTS);
 			if ((val == ~(u32)0) || (val & EHCI_USBSTS_HALTED)) {
 				break;
diff --git a/drivers/usb/host/whci/qset.c b/drivers/usb/host/whci/qset.c
index d6e17542861..a403b53e86b 100644
--- a/drivers/usb/host/whci/qset.c
+++ b/drivers/usb/host/whci/qset.c
@@ -124,7 +124,7 @@ void qset_clear(struct whc *whc, struct whc_qset *qset)
 {
 	qset->td_start = qset->td_end = qset->ntds = 0;
 
-	qset->qh.link = cpu_to_le32(QH_LINK_NTDS(8) | QH_LINK_T);
+	qset->qh.link = cpu_to_le64(QH_LINK_NTDS(8) | QH_LINK_T);
 	qset->qh.status = qset->qh.status & QH_STATUS_SEQ_MASK;
 	qset->qh.err_count = 0;
 	qset->qh.scratch[0] = 0;
diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c
index 723f8231193..ce9f974dac0 100644
--- a/drivers/usb/host/xhci-hub.c
+++ b/drivers/usb/host/xhci-hub.c
@@ -392,6 +392,20 @@ static int xhci_get_ports(struct usb_hcd *hcd, __le32 __iomem ***port_array)
 	return max_ports;
 }
 
+/* Test and clear port RWC bit */
+void xhci_test_and_clear_bit(struct xhci_hcd *xhci, __le32 __iomem **port_array,
+				int port_id, u32 port_bit)
+{
+	u32 temp;
+
+	temp = xhci_readl(xhci, port_array[port_id]);
+	if (temp & port_bit) {
+		temp = xhci_port_state_to_neutral(temp);
+		temp |= port_bit;
+		xhci_writel(xhci, temp, port_array[port_id]);
+	}
+}
+
 int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 		u16 wIndex, char *buf, u16 wLength)
 {
@@ -938,12 +952,8 @@ int xhci_bus_resume(struct usb_hcd *hcd)
 			spin_lock_irqsave(&xhci->lock, flags);
 
 			/* Clear PLC */
-			temp = xhci_readl(xhci, port_array[port_index]);
-			if (temp & PORT_PLC) {
-				temp = xhci_port_state_to_neutral(temp);
-				temp |= PORT_PLC;
-				xhci_writel(xhci, temp, port_array[port_index]);
-			}
+			xhci_test_and_clear_bit(xhci, port_array, port_index,
+						PORT_PLC);
 
 			slot_id = xhci_find_slot_id_by_port(hcd,
 					xhci, port_index + 1);
diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index d446886b22b..d718033dc53 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -81,7 +81,7 @@ static void xhci_segment_free(struct xhci_hcd *xhci, struct xhci_segment *seg)
  * related flags, such as End TRB, Toggle Cycle, and no snoop.
  */
 static void xhci_link_segments(struct xhci_hcd *xhci, struct xhci_segment *prev,
-		struct xhci_segment *next, bool link_trbs)
+		struct xhci_segment *next, bool link_trbs, bool isoc)
 {
 	u32 val;
 
@@ -97,7 +97,9 @@ static void xhci_link_segments(struct xhci_hcd *xhci, struct xhci_segment *prev,
 		val &= ~TRB_TYPE_BITMASK;
 		val |= TRB_TYPE(TRB_LINK);
 		/* Always set the chain bit with 0.95 hardware */
-		if (xhci_link_trb_quirk(xhci))
+		/* Set chain bit for isoc rings on AMD 0.96 host */
+		if (xhci_link_trb_quirk(xhci) ||
+				(isoc && (xhci->quirks & XHCI_AMD_0x96_HOST)))
 			val |= TRB_CHAIN;
 		prev->trbs[TRBS_PER_SEGMENT-1].link.control = cpu_to_le32(val);
 	}
@@ -112,18 +114,20 @@ void xhci_ring_free(struct xhci_hcd *xhci, struct xhci_ring *ring)
 	struct xhci_segment *seg;
 	struct xhci_segment *first_seg;
 
-	if (!ring || !ring->first_seg)
+	if (!ring)
 		return;
-	first_seg = ring->first_seg;
-	seg = first_seg->next;
-	xhci_dbg(xhci, "Freeing ring at %p\n", ring);
-	while (seg != first_seg) {
-		struct xhci_segment *next = seg->next;
-		xhci_segment_free(xhci, seg);
-		seg = next;
+	if (ring->first_seg) {
+		first_seg = ring->first_seg;
+		seg = first_seg->next;
+		xhci_dbg(xhci, "Freeing ring at %p\n", ring);
+		while (seg != first_seg) {
+			struct xhci_segment *next = seg->next;
+			xhci_segment_free(xhci, seg);
+			seg = next;
+		}
+		xhci_segment_free(xhci, first_seg);
+		ring->first_seg = NULL;
 	}
-	xhci_segment_free(xhci, first_seg);
-	ring->first_seg = NULL;
 	kfree(ring);
 }
 
@@ -152,7 +156,7 @@ static void xhci_initialize_ring_info(struct xhci_ring *ring)
  * See section 4.9.1 and figures 15 and 16.
  */
 static struct xhci_ring *xhci_ring_alloc(struct xhci_hcd *xhci,
-		unsigned int num_segs, bool link_trbs, gfp_t flags)
+		unsigned int num_segs, bool link_trbs, bool isoc, gfp_t flags)
 {
 	struct xhci_ring	*ring;
 	struct xhci_segment	*prev;
@@ -178,12 +182,12 @@ static struct xhci_ring *xhci_ring_alloc(struct xhci_hcd *xhci,
 		next = xhci_segment_alloc(xhci, flags);
 		if (!next)
 			goto fail;
-		xhci_link_segments(xhci, prev, next, link_trbs);
+		xhci_link_segments(xhci, prev, next, link_trbs, isoc);
 
 		prev = next;
 		num_segs--;
 	}
-	xhci_link_segments(xhci, prev, ring->first_seg, link_trbs);
+	xhci_link_segments(xhci, prev, ring->first_seg, link_trbs, isoc);
 
 	if (link_trbs) {
 		/* See section 4.9.2.1 and 6.4.4.1 */
@@ -229,14 +233,14 @@ void xhci_free_or_cache_endpoint_ring(struct xhci_hcd *xhci,
  * pointers to the beginning of the ring.
  */
 static void xhci_reinit_cached_ring(struct xhci_hcd *xhci,
-		struct xhci_ring *ring)
+		struct xhci_ring *ring, bool isoc)
 {
 	struct xhci_segment	*seg = ring->first_seg;
 	do {
 		memset(seg->trbs, 0,
 				sizeof(union xhci_trb)*TRBS_PER_SEGMENT);
 		/* All endpoint rings have link TRBs */
-		xhci_link_segments(xhci, seg, seg->next, 1);
+		xhci_link_segments(xhci, seg, seg->next, 1, isoc);
 		seg = seg->next;
 	} while (seg != ring->first_seg);
 	xhci_initialize_ring_info(ring);
@@ -540,7 +544,7 @@ struct xhci_stream_info *xhci_alloc_stream_info(struct xhci_hcd *xhci,
 	 */
 	for (cur_stream = 1; cur_stream < num_streams; cur_stream++) {
 		stream_info->stream_rings[cur_stream] =
-			xhci_ring_alloc(xhci, 1, true, mem_flags);
+			xhci_ring_alloc(xhci, 1, true, false, mem_flags);
 		cur_ring = stream_info->stream_rings[cur_stream];
 		if (!cur_ring)
 			goto cleanup_rings;
@@ -765,7 +769,7 @@ int xhci_alloc_virt_device(struct xhci_hcd *xhci, int slot_id,
 	}
 
 	/* Allocate endpoint 0 ring */
-	dev->eps[0].ring = xhci_ring_alloc(xhci, 1, true, flags);
+	dev->eps[0].ring = xhci_ring_alloc(xhci, 1, true, false, flags);
 	if (!dev->eps[0].ring)
 		goto fail;
 
@@ -871,7 +875,6 @@ int xhci_setup_addressable_virt_dev(struct xhci_hcd *xhci, struct usb_device *ud
 	struct xhci_virt_device *dev;
 	struct xhci_ep_ctx	*ep0_ctx;
 	struct xhci_slot_ctx    *slot_ctx;
-	struct xhci_input_control_ctx *ctrl_ctx;
 	u32			port_num;
 	struct usb_device *top_dev;
 
@@ -883,12 +886,8 @@ int xhci_setup_addressable_virt_dev(struct xhci_hcd *xhci, struct usb_device *ud
 		return -EINVAL;
 	}
 	ep0_ctx = xhci_get_ep_ctx(xhci, dev->in_ctx, 0);
-	ctrl_ctx = xhci_get_input_control_ctx(xhci, dev->in_ctx);
 	slot_ctx = xhci_get_slot_ctx(xhci, dev->in_ctx);
 
-	/* 2) New slot context and endpoint 0 context are valid*/
-	ctrl_ctx->add_flags = cpu_to_le32(SLOT_FLAG | EP0_FLAG);
-
 	/* 3) Only the control endpoint is valid - one endpoint context */
 	slot_ctx->dev_info |= cpu_to_le32(LAST_CTX(1) | udev->route);
 	switch (udev->speed) {
@@ -1175,10 +1174,10 @@ int xhci_endpoint_init(struct xhci_hcd *xhci,
 	 */
 	if (usb_endpoint_xfer_isoc(&ep->desc))
 		virt_dev->eps[ep_index].new_ring =
-			xhci_ring_alloc(xhci, 8, true, mem_flags);
+			xhci_ring_alloc(xhci, 8, true, true, mem_flags);
 	else
 		virt_dev->eps[ep_index].new_ring =
-			xhci_ring_alloc(xhci, 1, true, mem_flags);
+			xhci_ring_alloc(xhci, 1, true, false, mem_flags);
 	if (!virt_dev->eps[ep_index].new_ring) {
 		/* Attempt to use the ring cache */
 		if (virt_dev->num_rings_cached == 0)
@@ -1187,7 +1186,8 @@ int xhci_endpoint_init(struct xhci_hcd *xhci,
 			virt_dev->ring_cache[virt_dev->num_rings_cached];
 		virt_dev->ring_cache[virt_dev->num_rings_cached] = NULL;
 		virt_dev->num_rings_cached--;
-		xhci_reinit_cached_ring(xhci, virt_dev->eps[ep_index].new_ring);
+		xhci_reinit_cached_ring(xhci, virt_dev->eps[ep_index].new_ring,
+			usb_endpoint_xfer_isoc(&ep->desc) ? true : false);
 	}
 	virt_dev->eps[ep_index].skip = false;
 	ep_ring = virt_dev->eps[ep_index].new_ring;
@@ -2001,7 +2001,7 @@ int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags)
 		goto fail;
 
 	/* Set up the command ring to have one segments for now. */
-	xhci->cmd_ring = xhci_ring_alloc(xhci, 1, true, flags);
+	xhci->cmd_ring = xhci_ring_alloc(xhci, 1, true, false, flags);
 	if (!xhci->cmd_ring)
 		goto fail;
 	xhci_dbg(xhci, "Allocated command ring at %p\n", xhci->cmd_ring);
@@ -2032,7 +2032,8 @@ int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags)
 	 * the event ring segment table (ERST).  Section 4.9.3.
 	 */
 	xhci_dbg(xhci, "// Allocating event ring\n");
-	xhci->event_ring = xhci_ring_alloc(xhci, ERST_NUM_SEGS, false, flags);
+	xhci->event_ring = xhci_ring_alloc(xhci, ERST_NUM_SEGS, false, false,
+						flags);
 	if (!xhci->event_ring)
 		goto fail;
 	if (xhci_check_trb_in_td_math(xhci, flags) < 0)
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index cb16de213f6..50e7156a7d8 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -128,6 +128,9 @@ static int xhci_pci_setup(struct usb_hcd *hcd)
 	if (pdev->vendor == PCI_VENDOR_ID_NEC)
 		xhci->quirks |= XHCI_NEC_HOST;
 
+	if (pdev->vendor == PCI_VENDOR_ID_AMD && xhci->hci_version == 0x96)
+		xhci->quirks |= XHCI_AMD_0x96_HOST;
+
 	/* AMD PLL quirk */
 	if (pdev->vendor == PCI_VENDOR_ID_AMD && usb_amd_find_chipset_info())
 		xhci->quirks |= XHCI_AMD_PLL_FIX;
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index 952e2ded61a..2c07fffe8db 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -185,7 +185,7 @@ static void inc_deq(struct xhci_hcd *xhci, struct xhci_ring *ring, bool consumer
  *			prepare_transfer()?
  */
 static void inc_enq(struct xhci_hcd *xhci, struct xhci_ring *ring,
-		bool consumer, bool more_trbs_coming)
+		bool consumer, bool more_trbs_coming, bool isoc)
 {
 	u32 chain;
 	union xhci_trb *next;
@@ -212,11 +212,13 @@ static void inc_enq(struct xhci_hcd *xhci, struct xhci_ring *ring,
 				if (!chain && !more_trbs_coming)
 					break;
 
-				/* If we're not dealing with 0.95 hardware,
+				/* If we're not dealing with 0.95 hardware or
+				 * isoc rings on AMD 0.96 host,
 				 * carry over the chain bit of the previous TRB
 				 * (which may mean the chain bit is cleared).
 				 */
-				if (!xhci_link_trb_quirk(xhci)) {
+				if (!(isoc && (xhci->quirks & XHCI_AMD_0x96_HOST))
+						&& !xhci_link_trb_quirk(xhci)) {
 					next->link.control &=
 						cpu_to_le32(~TRB_CHAIN);
 					next->link.control |=
@@ -814,23 +816,24 @@ void xhci_stop_endpoint_command_watchdog(unsigned long arg)
 	struct xhci_ring *ring;
 	struct xhci_td *cur_td;
 	int ret, i, j;
+	unsigned long flags;
 
 	ep = (struct xhci_virt_ep *) arg;
 	xhci = ep->xhci;
 
-	spin_lock(&xhci->lock);
+	spin_lock_irqsave(&xhci->lock, flags);
 
 	ep->stop_cmds_pending--;
 	if (xhci->xhc_state & XHCI_STATE_DYING) {
 		xhci_dbg(xhci, "Stop EP timer ran, but another timer marked "
 				"xHCI as DYING, exiting.\n");
-		spin_unlock(&xhci->lock);
+		spin_unlock_irqrestore(&xhci->lock, flags);
 		return;
 	}
 	if (!(ep->stop_cmds_pending == 0 && (ep->ep_state & EP_HALT_PENDING))) {
 		xhci_dbg(xhci, "Stop EP timer ran, but no command pending, "
 				"exiting.\n");
-		spin_unlock(&xhci->lock);
+		spin_unlock_irqrestore(&xhci->lock, flags);
 		return;
 	}
 
@@ -842,11 +845,11 @@ void xhci_stop_endpoint_command_watchdog(unsigned long arg)
 	xhci->xhc_state |= XHCI_STATE_DYING;
 	/* Disable interrupts from the host controller and start halting it */
 	xhci_quiesce(xhci);
-	spin_unlock(&xhci->lock);
+	spin_unlock_irqrestore(&xhci->lock, flags);
 
 	ret = xhci_halt(xhci);
 
-	spin_lock(&xhci->lock);
+	spin_lock_irqsave(&xhci->lock, flags);
 	if (ret < 0) {
 		/* This is bad; the host is not responding to commands and it's
 		 * not allowing itself to be halted.  At least interrupts are
@@ -894,7 +897,7 @@ void xhci_stop_endpoint_command_watchdog(unsigned long arg)
 			}
 		}
 	}
-	spin_unlock(&xhci->lock);
+	spin_unlock_irqrestore(&xhci->lock, flags);
 	xhci_dbg(xhci, "Calling usb_hc_died()\n");
 	usb_hc_died(xhci_to_hcd(xhci)->primary_hcd);
 	xhci_dbg(xhci, "xHCI host controller is dead.\n");
@@ -1342,10 +1345,8 @@ static void handle_port_status(struct xhci_hcd *xhci,
 			xhci_ring_device(xhci, slot_id);
 			xhci_dbg(xhci, "resume SS port %d finished\n", port_id);
 			/* Clear PORT_PLC */
-			temp = xhci_readl(xhci, port_array[faked_port_index]);
-			temp = xhci_port_state_to_neutral(temp);
-			temp |= PORT_PLC;
-			xhci_writel(xhci, temp, port_array[faked_port_index]);
+			xhci_test_and_clear_bit(xhci, port_array,
+						faked_port_index, PORT_PLC);
 		} else {
 			xhci_dbg(xhci, "resume HS port %d\n", port_id);
 			bus_state->resume_done[faked_port_index] = jiffies +
@@ -1356,6 +1357,10 @@ static void handle_port_status(struct xhci_hcd *xhci,
 		}
 	}
 
+	if (hcd->speed != HCD_USB3)
+		xhci_test_and_clear_bit(xhci, port_array, faked_port_index,
+					PORT_PLC);
+
 cleanup:
 	/* Update event ring dequeue pointer before dropping the lock */
 	inc_deq(xhci, xhci->event_ring, true);
@@ -2409,7 +2414,7 @@ irqreturn_t xhci_msi_irq(int irq, struct usb_hcd *hcd)
  *			prepare_transfer()?
  */
 static void queue_trb(struct xhci_hcd *xhci, struct xhci_ring *ring,
-		bool consumer, bool more_trbs_coming,
+		bool consumer, bool more_trbs_coming, bool isoc,
 		u32 field1, u32 field2, u32 field3, u32 field4)
 {
 	struct xhci_generic_trb *trb;
@@ -2419,7 +2424,7 @@ static void queue_trb(struct xhci_hcd *xhci, struct xhci_ring *ring,
 	trb->field[1] = cpu_to_le32(field2);
 	trb->field[2] = cpu_to_le32(field3);
 	trb->field[3] = cpu_to_le32(field4);
-	inc_enq(xhci, ring, consumer, more_trbs_coming);
+	inc_enq(xhci, ring, consumer, more_trbs_coming, isoc);
 }
 
 /*
@@ -2427,7 +2432,7 @@ static void queue_trb(struct xhci_hcd *xhci, struct xhci_ring *ring,
  * FIXME allocate segments if the ring is full.
  */
 static int prepare_ring(struct xhci_hcd *xhci, struct xhci_ring *ep_ring,
-		u32 ep_state, unsigned int num_trbs, gfp_t mem_flags)
+		u32 ep_state, unsigned int num_trbs, bool isoc, gfp_t mem_flags)
 {
 	/* Make sure the endpoint has been added to xHC schedule */
 	switch (ep_state) {
@@ -2469,10 +2474,11 @@ static int prepare_ring(struct xhci_hcd *xhci, struct xhci_ring *ep_ring,
 		next = ring->enqueue;
 
 		while (last_trb(xhci, ring, ring->enq_seg, next)) {
-			/* If we're not dealing with 0.95 hardware,
-			 * clear the chain bit.
+			/* If we're not dealing with 0.95 hardware or isoc rings
+			 * on AMD 0.96 host, clear the chain bit.
 			 */
-			if (!xhci_link_trb_quirk(xhci))
+			if (!xhci_link_trb_quirk(xhci) && !(isoc &&
+					(xhci->quirks & XHCI_AMD_0x96_HOST)))
 				next->link.control &= cpu_to_le32(~TRB_CHAIN);
 			else
 				next->link.control |= cpu_to_le32(TRB_CHAIN);
@@ -2505,6 +2511,7 @@ static int prepare_transfer(struct xhci_hcd *xhci,
 		unsigned int num_trbs,
 		struct urb *urb,
 		unsigned int td_index,
+		bool isoc,
 		gfp_t mem_flags)
 {
 	int ret;
@@ -2522,7 +2529,7 @@ static int prepare_transfer(struct xhci_hcd *xhci,
 
 	ret = prepare_ring(xhci, ep_ring,
 			   le32_to_cpu(ep_ctx->ep_info) & EP_STATE_MASK,
-			   num_trbs, mem_flags);
+			   num_trbs, isoc, mem_flags);
 	if (ret)
 		return ret;
 
@@ -2745,7 +2752,7 @@ static int queue_bulk_sg_tx(struct xhci_hcd *xhci, gfp_t mem_flags,
 
 	trb_buff_len = prepare_transfer(xhci, xhci->devs[slot_id],
 			ep_index, urb->stream_id,
-			num_trbs, urb, 0, mem_flags);
+			num_trbs, urb, 0, false, mem_flags);
 	if (trb_buff_len < 0)
 		return trb_buff_len;
 
@@ -2840,7 +2847,7 @@ static int queue_bulk_sg_tx(struct xhci_hcd *xhci, gfp_t mem_flags,
 			more_trbs_coming = true;
 		else
 			more_trbs_coming = false;
-		queue_trb(xhci, ep_ring, false, more_trbs_coming,
+		queue_trb(xhci, ep_ring, false, more_trbs_coming, false,
 				lower_32_bits(addr),
 				upper_32_bits(addr),
 				length_field,
@@ -2931,7 +2938,7 @@ int xhci_queue_bulk_tx(struct xhci_hcd *xhci, gfp_t mem_flags,
 
 	ret = prepare_transfer(xhci, xhci->devs[slot_id],
 			ep_index, urb->stream_id,
-			num_trbs, urb, 0, mem_flags);
+			num_trbs, urb, 0, false, mem_flags);
 	if (ret < 0)
 		return ret;
 
@@ -3003,7 +3010,7 @@ int xhci_queue_bulk_tx(struct xhci_hcd *xhci, gfp_t mem_flags,
 			more_trbs_coming = true;
 		else
 			more_trbs_coming = false;
-		queue_trb(xhci, ep_ring, false, more_trbs_coming,
+		queue_trb(xhci, ep_ring, false, more_trbs_coming, false,
 				lower_32_bits(addr),
 				upper_32_bits(addr),
 				length_field,
@@ -3063,7 +3070,7 @@ int xhci_queue_ctrl_tx(struct xhci_hcd *xhci, gfp_t mem_flags,
 		num_trbs++;
 	ret = prepare_transfer(xhci, xhci->devs[slot_id],
 			ep_index, urb->stream_id,
-			num_trbs, urb, 0, mem_flags);
+			num_trbs, urb, 0, false, mem_flags);
 	if (ret < 0)
 		return ret;
 
@@ -3096,7 +3103,7 @@ int xhci_queue_ctrl_tx(struct xhci_hcd *xhci, gfp_t mem_flags,
 		}
 	}
 
-	queue_trb(xhci, ep_ring, false, true,
+	queue_trb(xhci, ep_ring, false, true, false,
 		  setup->bRequestType | setup->bRequest << 8 | le16_to_cpu(setup->wValue) << 16,
 		  le16_to_cpu(setup->wIndex) | le16_to_cpu(setup->wLength) << 16,
 		  TRB_LEN(8) | TRB_INTR_TARGET(0),
@@ -3116,7 +3123,7 @@ int xhci_queue_ctrl_tx(struct xhci_hcd *xhci, gfp_t mem_flags,
 	if (urb->transfer_buffer_length > 0) {
 		if (setup->bRequestType & USB_DIR_IN)
 			field |= TRB_DIR_IN;
-		queue_trb(xhci, ep_ring, false, true,
+		queue_trb(xhci, ep_ring, false, true, false,
 				lower_32_bits(urb->transfer_dma),
 				upper_32_bits(urb->transfer_dma),
 				length_field,
@@ -3132,7 +3139,7 @@ int xhci_queue_ctrl_tx(struct xhci_hcd *xhci, gfp_t mem_flags,
 		field = 0;
 	else
 		field = TRB_DIR_IN;
-	queue_trb(xhci, ep_ring, false, false,
+	queue_trb(xhci, ep_ring, false, false, false,
 			0,
 			0,
 			TRB_INTR_TARGET(0),
@@ -3281,7 +3288,8 @@ static int xhci_queue_isoc_tx(struct xhci_hcd *xhci, gfp_t mem_flags,
 		trbs_per_td = count_isoc_trbs_needed(xhci, urb, i);
 
 		ret = prepare_transfer(xhci, xhci->devs[slot_id], ep_index,
-				urb->stream_id, trbs_per_td, urb, i, mem_flags);
+				urb->stream_id, trbs_per_td, urb, i, true,
+				mem_flags);
 		if (ret < 0) {
 			if (i == 0)
 				return ret;
@@ -3351,7 +3359,7 @@ static int xhci_queue_isoc_tx(struct xhci_hcd *xhci, gfp_t mem_flags,
 				remainder |
 				TRB_INTR_TARGET(0);
 
-			queue_trb(xhci, ep_ring, false, more_trbs_coming,
+			queue_trb(xhci, ep_ring, false, more_trbs_coming, true,
 				lower_32_bits(addr),
 				upper_32_bits(addr),
 				length_field,
@@ -3433,7 +3441,7 @@ int xhci_queue_isoc_tx_prepare(struct xhci_hcd *xhci, gfp_t mem_flags,
 	 * Do not insert any td of the urb to the ring if the check failed.
 	 */
 	ret = prepare_ring(xhci, ep_ring, le32_to_cpu(ep_ctx->ep_info) & EP_STATE_MASK,
-			   num_trbs, mem_flags);
+			   num_trbs, true, mem_flags);
 	if (ret)
 		return ret;
 
@@ -3492,7 +3500,7 @@ static int queue_command(struct xhci_hcd *xhci, u32 field1, u32 field2,
 		reserved_trbs++;
 
 	ret = prepare_ring(xhci, xhci->cmd_ring, EP_STATE_RUNNING,
-			reserved_trbs, GFP_ATOMIC);
+			reserved_trbs, false, GFP_ATOMIC);
 	if (ret < 0) {
 		xhci_err(xhci, "ERR: No room for command on command ring\n");
 		if (command_must_succeed)
@@ -3500,8 +3508,8 @@ static int queue_command(struct xhci_hcd *xhci, u32 field1, u32 field2,
 					"unfailable commands failed.\n");
 		return ret;
 	}
-	queue_trb(xhci, xhci->cmd_ring, false, false, field1, field2, field3,
-			field4 | xhci->cmd_ring->cycle_state);
+	queue_trb(xhci, xhci->cmd_ring, false, false, false, field1, field2,
+			field3,	field4 | xhci->cmd_ring->cycle_state);
 	return 0;
 }
 
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 3a0f695138f..10dc1bdf3a7 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -657,7 +657,10 @@ static void xhci_clear_command_ring(struct xhci_hcd *xhci)
 	ring = xhci->cmd_ring;
 	seg = ring->deq_seg;
 	do {
-		memset(seg->trbs, 0, SEGMENT_SIZE);
+		memset(seg->trbs, 0,
+			sizeof(union xhci_trb) * (TRBS_PER_SEGMENT - 1));
+		seg->trbs[TRBS_PER_SEGMENT - 1].link.control &=
+			cpu_to_le32(~TRB_CYCLE);
 		seg = seg->next;
 	} while (seg != ring->deq_seg);
 
@@ -749,7 +752,7 @@ int xhci_resume(struct xhci_hcd *xhci, bool hibernated)
 	u32			command, temp = 0;
 	struct usb_hcd		*hcd = xhci_to_hcd(xhci);
 	struct usb_hcd		*secondary_hcd;
-	int			retval;
+	int			retval = 0;
 
 	/* Wait a bit if either of the roothubs need to settle from the
 	 * transition into bus suspend.
@@ -759,6 +762,9 @@ int xhci_resume(struct xhci_hcd *xhci, bool hibernated)
 				xhci->bus_state[1].next_statechange))
 		msleep(100);
 
+	set_bit(HCD_FLAG_HW_ACCESSIBLE, &hcd->flags);
+	set_bit(HCD_FLAG_HW_ACCESSIBLE, &xhci->shared_hcd->flags);
+
 	spin_lock_irq(&xhci->lock);
 	if (xhci->quirks & XHCI_RESET_ON_RESUME)
 		hibernated = true;
@@ -828,20 +834,13 @@ int xhci_resume(struct xhci_hcd *xhci, bool hibernated)
 			return retval;
 		xhci_dbg(xhci, "Start the primary HCD\n");
 		retval = xhci_run(hcd->primary_hcd);
-		if (retval)
-			goto failed_restart;
-
-		xhci_dbg(xhci, "Start the secondary HCD\n");
-		retval = xhci_run(secondary_hcd);
 		if (!retval) {
-			set_bit(HCD_FLAG_HW_ACCESSIBLE, &hcd->flags);
-			set_bit(HCD_FLAG_HW_ACCESSIBLE,
-					&xhci->shared_hcd->flags);
+			xhci_dbg(xhci, "Start the secondary HCD\n");
+			retval = xhci_run(secondary_hcd);
 		}
-failed_restart:
 		hcd->state = HC_STATE_SUSPENDED;
 		xhci->shared_hcd->state = HC_STATE_SUSPENDED;
-		return retval;
+		goto done;
 	}
 
 	/* step 4: set Run/Stop bit */
@@ -860,11 +859,14 @@ failed_restart:
 	 * Running endpoints by ringing their doorbells
 	 */
 
-	set_bit(HCD_FLAG_HW_ACCESSIBLE, &hcd->flags);
-	set_bit(HCD_FLAG_HW_ACCESSIBLE, &xhci->shared_hcd->flags);
-
 	spin_unlock_irq(&xhci->lock);
-	return 0;
+
+ done:
+	if (retval == 0) {
+		usb_hcd_resume_root_hub(hcd);
+		usb_hcd_resume_root_hub(xhci->shared_hcd);
+	}
+	return retval;
 }
 #endif	/* CONFIG_PM */
 
@@ -1888,6 +1890,12 @@ int xhci_check_bandwidth(struct usb_hcd *hcd, struct usb_device *udev)
 	ctrl_ctx->add_flags |= cpu_to_le32(SLOT_FLAG);
 	ctrl_ctx->add_flags &= cpu_to_le32(~EP0_FLAG);
 	ctrl_ctx->drop_flags &= cpu_to_le32(~(SLOT_FLAG | EP0_FLAG));
+
+	/* Don't issue the command if there's no endpoints to update. */
+	if (ctrl_ctx->add_flags == cpu_to_le32(SLOT_FLAG) &&
+			ctrl_ctx->drop_flags == 0)
+		return 0;
+
 	xhci_dbg(xhci, "New Input Control Context:\n");
 	slot_ctx = xhci_get_slot_ctx(xhci, virt_dev->in_ctx);
 	xhci_dbg_ctx(xhci, virt_dev->in_ctx,
@@ -2867,6 +2875,10 @@ int xhci_address_device(struct usb_hcd *hcd, struct usb_device *udev)
 	/* Otherwise, update the control endpoint ring enqueue pointer. */
 	else
 		xhci_copy_ep0_dequeue_into_input_ctx(xhci, udev);
+	ctrl_ctx = xhci_get_input_control_ctx(xhci, virt_dev->in_ctx);
+	ctrl_ctx->add_flags = cpu_to_le32(SLOT_FLAG | EP0_FLAG);
+	ctrl_ctx->drop_flags = 0;
+
 	xhci_dbg(xhci, "Slot ID %d Input Context:\n", udev->slot_id);
 	xhci_dbg_ctx(xhci, virt_dev->in_ctx, 2);
 
@@ -2948,7 +2960,6 @@ int xhci_address_device(struct usb_hcd *hcd, struct usb_device *udev)
 	virt_dev->address = (le32_to_cpu(slot_ctx->dev_state) & DEV_ADDR_MASK)
 		+ 1;
 	/* Zero the input context control for later use */
-	ctrl_ctx = xhci_get_input_control_ctx(xhci, virt_dev->in_ctx);
 	ctrl_ctx->add_flags = 0;
 	ctrl_ctx->drop_flags = 0;
 
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index cae8e23308b..1fb0549b771 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -1318,6 +1318,7 @@ struct xhci_hcd {
 #define XHCI_EP_LIMIT_QUIRK	(1 << 5)
 #define XHCI_BROKEN_MSI		(1 << 6)
 #define XHCI_RESET_ON_RESUME	(1 << 7)
+#define XHCI_AMD_0x96_HOST	(1 << 9)
 	unsigned int		num_active_eps;
 	unsigned int		limit_active_eps;
 	/* There are two roothubs to keep track of bus suspend info for */
@@ -1572,6 +1573,8 @@ void xhci_ring_ep_doorbell(struct xhci_hcd *xhci, unsigned int slot_id,
 		unsigned int ep_index, unsigned int stream_id);
 
 /* xHCI roothub code */
+void xhci_test_and_clear_bit(struct xhci_hcd *xhci, __le32 __iomem **port_array,
+				int port_id, u32 port_bit);
 int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue, u16 wIndex,
 		char *buf, u16 wLength);
 int xhci_hub_status_data(struct usb_hcd *hcd, char *buf);
diff --git a/drivers/usb/mon/mon_bin.c b/drivers/usb/mon/mon_bin.c
index a09dbd243eb..a04b2ff9dd8 100644
--- a/drivers/usb/mon/mon_bin.c
+++ b/drivers/usb/mon/mon_bin.c
@@ -1101,7 +1101,7 @@ static long mon_bin_ioctl(struct file *file, unsigned int cmd, unsigned long arg
 		nevents = mon_bin_queued(rp);
 
 		sp = (struct mon_bin_stats __user *)arg;
-		if (put_user(rp->cnt_lost, &sp->dropped))
+		if (put_user(ndropped, &sp->dropped))
 			return -EFAULT;
 		if (put_user(nevents, &sp->queued))
 			return -EFAULT;
diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c
index 698f24a4e94..f00ca33a03b 100644
--- a/drivers/usb/musb/musb_core.c
+++ b/drivers/usb/musb/musb_core.c
@@ -2370,18 +2370,12 @@ static int musb_suspend(struct device *dev)
 		 */
 	}
 
-	musb_save_context(musb);
-
 	spin_unlock_irqrestore(&musb->lock, flags);
 	return 0;
 }
 
 static int musb_resume(struct device *dev)
 {
-	struct musb	*musb = dev_to_musb(dev);
-
-	musb_restore_context(musb);
-
 	/* for static cmos like DaVinci, register values were preserved
 	 * unless for some reason the whole soc powered down or the USB
 	 * module got reset through the PSC (vs just being disabled).
diff --git a/drivers/usb/serial/ark3116.c b/drivers/usb/serial/ark3116.c
index 5cdb9d91227..18e875b92e0 100644
--- a/drivers/usb/serial/ark3116.c
+++ b/drivers/usb/serial/ark3116.c
@@ -42,7 +42,7 @@ static int debug;
  * Version information
  */
 
-#define DRIVER_VERSION "v0.6"
+#define DRIVER_VERSION "v0.7"
 #define DRIVER_AUTHOR "Bart Hartgers <bart.hartgers+ark3116@gmail.com>"
 #define DRIVER_DESC "USB ARK3116 serial/IrDA driver"
 #define DRIVER_DEV_DESC "ARK3116 RS232/IrDA"
@@ -380,10 +380,6 @@ static int ark3116_open(struct tty_struct *tty, struct usb_serial_port *port)
 		goto err_out;
 	}
 
-	/* setup termios */
-	if (tty)
-		ark3116_set_termios(tty, port, NULL);
-
 	/* remove any data still left: also clears error state */
 	ark3116_read_reg(serial, UART_RX, buf);
 
@@ -406,6 +402,10 @@ static int ark3116_open(struct tty_struct *tty, struct usb_serial_port *port)
 	/* enable DMA */
 	ark3116_write_reg(port->serial, UART_FCR, UART_FCR_DMA_SELECT);
 
+	/* setup termios */
+	if (tty)
+		ark3116_set_termios(tty, port, NULL);
+
 err_out:
 	kfree(buf);
 	return result;
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index 5fc13e71791..bbd2cdd669a 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -207,6 +207,8 @@ static struct usb_device_id id_table_combined [] = {
 	{ USB_DEVICE(FTDI_VID, FTDI_XF_640_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_XF_642_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_DSS20_PID) },
+	{ USB_DEVICE(FTDI_VID, FTDI_URBAN_0_PID) },
+	{ USB_DEVICE(FTDI_VID, FTDI_URBAN_1_PID) },
 	{ USB_DEVICE(FTDI_NF_RIC_VID, FTDI_NF_RIC_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_VNHCPCUSB_D_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_MTXORB_0_PID) },
@@ -733,6 +735,7 @@ static struct usb_device_id id_table_combined [] = {
 	{ USB_DEVICE(TML_VID, TML_USB_SERIAL_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_ELSTER_UNICOM_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_PROPOX_JTAGCABLEII_PID) },
+	{ USB_DEVICE(FTDI_VID, FTDI_PROPOX_ISPCABLEIII_PID) },
 	{ USB_DEVICE(OLIMEX_VID, OLIMEX_ARM_USB_OCD_PID),
 		.driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
 	{ USB_DEVICE(OLIMEX_VID, OLIMEX_ARM_USB_OCD_H_PID),
@@ -745,6 +748,8 @@ static struct usb_device_id id_table_combined [] = {
 		.driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
 	{ USB_DEVICE(FTDI_VID, LMI_LM3S_EVAL_BOARD_PID),
 		.driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
+	{ USB_DEVICE(FTDI_VID, LMI_LM3S_ICDI_BOARD_PID),
+		.driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
 	{ USB_DEVICE(FTDI_VID, FTDI_TURTELIZER_PID),
 		.driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
 	{ USB_DEVICE(RATOC_VENDOR_ID, RATOC_PRODUCT_ID_USB60F) },
@@ -2079,13 +2084,19 @@ static void ftdi_set_termios(struct tty_struct *tty,
 
 	cflag = termios->c_cflag;
 
-	/* FIXME -For this cut I don't care if the line is really changing or
-	   not  - so just do the change regardless  - should be able to
-	   compare old_termios and tty->termios */
+	if (old_termios->c_cflag == termios->c_cflag
+	    && old_termios->c_ispeed == termios->c_ispeed
+	    && old_termios->c_ospeed == termios->c_ospeed)
+		goto no_c_cflag_changes;
+
 	/* NOTE These routines can get interrupted by
 	   ftdi_sio_read_bulk_callback  - need to examine what this means -
 	   don't see any problems yet */
 
+	if ((old_termios->c_cflag & (CSIZE|PARODD|PARENB|CMSPAR|CSTOPB)) ==
+	    (termios->c_cflag & (CSIZE|PARODD|PARENB|CMSPAR|CSTOPB)))
+		goto no_data_parity_stop_changes;
+
 	/* Set number of data bits, parity, stop bits */
 
 	urb_value = 0;
@@ -2126,6 +2137,7 @@ static void ftdi_set_termios(struct tty_struct *tty,
 	}
 
 	/* Now do the baudrate */
+no_data_parity_stop_changes:
 	if ((cflag & CBAUD) == B0) {
 		/* Disable flow control */
 		if (usb_control_msg(dev, usb_sndctrlpipe(dev, 0),
@@ -2153,6 +2165,7 @@ static void ftdi_set_termios(struct tty_struct *tty,
 
 	/* Set flow control */
 	/* Note device also supports DTR/CD (ugh) and Xon/Xoff in hardware */
+no_c_cflag_changes:
 	if (cflag & CRTSCTS) {
 		dbg("%s Setting to CRTSCTS flow control", __func__);
 		if (usb_control_msg(dev,
diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h
index bf5227ad3ef..055b64ef0bb 100644
--- a/drivers/usb/serial/ftdi_sio_ids.h
+++ b/drivers/usb/serial/ftdi_sio_ids.h
@@ -54,6 +54,7 @@
 /* FTDI 2332C Dual channel device, side A=245 FIFO (JTAG), Side B=RS232 UART */
 #define LMI_LM3S_DEVEL_BOARD_PID	0xbcd8
 #define LMI_LM3S_EVAL_BOARD_PID		0xbcd9
+#define LMI_LM3S_ICDI_BOARD_PID		0xbcda
 
 #define FTDI_TURTELIZER_PID	0xBDC8 /* JTAG/RS-232 adapter by egnite GmbH */
 
@@ -111,6 +112,7 @@
 
 /* Propox devices */
 #define FTDI_PROPOX_JTAGCABLEII_PID	0xD738
+#define FTDI_PROPOX_ISPCABLEIII_PID	0xD739
 
 /* Lenz LI-USB Computer Interface. */
 #define FTDI_LENZ_LIUSB_PID	0xD780
@@ -420,9 +422,11 @@
 #define PROTEGO_SPECIAL_4	0xFC73	/* special/unknown device */
 
 /*
- * DSS-20 Sync Station for Sony Ericsson P800
+ * Sony Ericsson product ids
  */
-#define FTDI_DSS20_PID          0xFC82
+#define FTDI_DSS20_PID		0xFC82	/* DSS-20 Sync Station for Sony Ericsson P800 */
+#define FTDI_URBAN_0_PID	0xFC8A	/* Sony Ericsson Urban, uart #0 */
+#define FTDI_URBAN_1_PID	0xFC8B	/* Sony Ericsson Urban, uart #1 */
 
 /* www.irtrans.de device */
 #define FTDI_IRTRANS_PID 0xFC60 /* Product Id */
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index fe22e90bc87..e98a1e1e508 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -156,6 +156,7 @@ static void option_instat_callback(struct urb *urb);
 #define HUAWEI_PRODUCT_K4511			0x14CC
 #define HUAWEI_PRODUCT_ETS1220			0x1803
 #define HUAWEI_PRODUCT_E353			0x1506
+#define HUAWEI_PRODUCT_E173S			0x1C05
 
 #define QUANTA_VENDOR_ID			0x0408
 #define QUANTA_PRODUCT_Q101			0xEA02
@@ -316,6 +317,9 @@ static void option_instat_callback(struct urb *urb);
 #define ZTE_PRODUCT_AC8710			0xfff1
 #define ZTE_PRODUCT_AC2726			0xfff5
 #define ZTE_PRODUCT_AC8710T			0xffff
+#define ZTE_PRODUCT_MC2718			0xffe8
+#define ZTE_PRODUCT_AD3812			0xffeb
+#define ZTE_PRODUCT_MC2716			0xffed
 
 #define BENQ_VENDOR_ID				0x04a5
 #define BENQ_PRODUCT_H10			0x4068
@@ -475,31 +479,66 @@ enum option_blacklist_reason {
 		OPTION_BLACKLIST_RESERVED_IF = 2
 };
 
+#define MAX_BL_NUM  8
 struct option_blacklist_info {
-	const u32 infolen;	/* number of interface numbers on blacklist */
-	const u8  *ifaceinfo;	/* pointer to the array holding the numbers */
-	enum option_blacklist_reason reason;
+	/* bitfield of interface numbers for OPTION_BLACKLIST_SENDSETUP */
+	const unsigned long sendsetup;
+	/* bitfield of interface numbers for OPTION_BLACKLIST_RESERVED_IF */
+	const unsigned long reserved;
 };
 
-static const u8 four_g_w14_no_sendsetup[] = { 0, 1 };
 static const struct option_blacklist_info four_g_w14_blacklist = {
-	.infolen = ARRAY_SIZE(four_g_w14_no_sendsetup),
-	.ifaceinfo = four_g_w14_no_sendsetup,
-	.reason = OPTION_BLACKLIST_SENDSETUP
+	.sendsetup = BIT(0) | BIT(1),
 };
 
-static const u8 alcatel_x200_no_sendsetup[] = { 0, 1 };
 static const struct option_blacklist_info alcatel_x200_blacklist = {
-	.infolen = ARRAY_SIZE(alcatel_x200_no_sendsetup),
-	.ifaceinfo = alcatel_x200_no_sendsetup,
-	.reason = OPTION_BLACKLIST_SENDSETUP
+	.sendsetup = BIT(0) | BIT(1),
+};
+
+static const struct option_blacklist_info zte_0037_blacklist = {
+	.sendsetup = BIT(0) | BIT(1),
 };
 
-static const u8 zte_k3765_z_no_sendsetup[] = { 0, 1, 2 };
 static const struct option_blacklist_info zte_k3765_z_blacklist = {
-	.infolen = ARRAY_SIZE(zte_k3765_z_no_sendsetup),
-	.ifaceinfo = zte_k3765_z_no_sendsetup,
-	.reason = OPTION_BLACKLIST_SENDSETUP
+	.sendsetup = BIT(0) | BIT(1) | BIT(2),
+	.reserved = BIT(4),
+};
+
+static const struct option_blacklist_info zte_ad3812_z_blacklist = {
+	.sendsetup = BIT(0) | BIT(1) | BIT(2),
+};
+
+static const struct option_blacklist_info zte_mc2718_z_blacklist = {
+	.sendsetup = BIT(1) | BIT(2) | BIT(3) | BIT(4),
+};
+
+static const struct option_blacklist_info zte_mc2716_z_blacklist = {
+	.sendsetup = BIT(1) | BIT(2) | BIT(3),
+};
+
+static const struct option_blacklist_info huawei_cdc12_blacklist = {
+	.reserved = BIT(1) | BIT(2),
+};
+
+static const struct option_blacklist_info net_intf1_blacklist = {
+	.reserved = BIT(1),
+};
+
+static const struct option_blacklist_info net_intf3_blacklist = {
+	.reserved = BIT(3),
+};
+
+static const struct option_blacklist_info net_intf4_blacklist = {
+	.reserved = BIT(4),
+};
+
+static const struct option_blacklist_info net_intf5_blacklist = {
+	.reserved = BIT(5),
+};
+
+static const struct option_blacklist_info zte_mf626_blacklist = {
+	.sendsetup = BIT(0) | BIT(1),
+	.reserved = BIT(4),
 };
 
 static const struct usb_device_id option_ids[] = {
@@ -599,12 +638,16 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E143D, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E143E, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E143F, 0xff, 0xff, 0xff) },
-	{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_K4505, 0xff, 0xff, 0xff) },
-	{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_K3765, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E173S, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_K4505, 0xff, 0xff, 0xff),
+		.driver_info = (kernel_ulong_t) &huawei_cdc12_blacklist },
+	{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_K3765, 0xff, 0xff, 0xff),
+		.driver_info = (kernel_ulong_t) &huawei_cdc12_blacklist },
 	{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_ETS1220, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E14AC, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_K3806, 0xff, 0xff, 0xff) },
-	{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_K4605, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_K4605, 0xff, 0xff, 0xff),
+		.driver_info = (kernel_ulong_t) &huawei_cdc12_blacklist },
 	{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_K3770, 0xff, 0x02, 0x31) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_K3770, 0xff, 0x02, 0x32) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_K3771, 0xff, 0x02, 0x31) },
@@ -614,6 +657,9 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_K4511, 0xff, 0x01, 0x31) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_K4511, 0xff, 0x01, 0x32) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E353, 0xff, 0x01, 0x01) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E353, 0xff, 0x01, 0x02) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E353, 0xff, 0x01, 0x03) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E353, 0xff, 0x01, 0x08) },
 	{ USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_V640) },
 	{ USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_V620) },
 	{ USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_V740) },
@@ -700,12 +746,14 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE(KYOCERA_VENDOR_ID, KYOCERA_PRODUCT_KPC680) },
 	{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x6000)}, /* ZTE AC8700 */
 	{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x6613)}, /* Onda H600/ZTE MF330 */
+	{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x9000)}, /* SIMCom SIM5218 */
 	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6280) }, /* BP3-USB & BP3-EXT HSDPA */
 	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6008) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_UC864E) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_UC864G) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MF622, 0xff, 0xff, 0xff) }, /* ZTE WCDMA products */
-	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0002, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0002, 0xff, 0xff, 0xff),
+		.driver_info = (kernel_ulong_t)&net_intf1_blacklist },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0003, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0004, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0005, 0xff, 0xff, 0xff) },
@@ -720,51 +768,62 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x000f, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0010, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0011, 0xff, 0xff, 0xff) },
-	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0012, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0012, 0xff, 0xff, 0xff),
+		.driver_info = (kernel_ulong_t)&net_intf1_blacklist },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0013, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0014, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MF628, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0016, 0xff, 0xff, 0xff) },
-	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0017, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0017, 0xff, 0xff, 0xff),
+		.driver_info = (kernel_ulong_t)&net_intf3_blacklist },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0018, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0019, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0020, 0xff, 0xff, 0xff) },
-	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0021, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0021, 0xff, 0xff, 0xff),
+		.driver_info = (kernel_ulong_t)&net_intf4_blacklist },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0022, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0023, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0024, 0xff, 0xff, 0xff) },
-	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0025, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0025, 0xff, 0xff, 0xff),
+		.driver_info = (kernel_ulong_t)&net_intf1_blacklist },
 	/* { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0026, 0xff, 0xff, 0xff) }, */
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0028, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0029, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0030, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MF626, 0xff,
-	  0xff, 0xff), .driver_info = (kernel_ulong_t)&four_g_w14_blacklist },
+	  0xff, 0xff), .driver_info = (kernel_ulong_t)&zte_mf626_blacklist },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0032, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0033, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0034, 0xff, 0xff, 0xff) },
-	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0037, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0037, 0xff, 0xff, 0xff),
+		.driver_info = (kernel_ulong_t)&zte_0037_blacklist },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0038, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0039, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0040, 0xff, 0xff, 0xff) },
-	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0042, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0042, 0xff, 0xff, 0xff),
+		.driver_info = (kernel_ulong_t)&net_intf4_blacklist },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0043, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0044, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0048, 0xff, 0xff, 0xff) },
-	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0049, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0049, 0xff, 0xff, 0xff),
+		.driver_info = (kernel_ulong_t)&net_intf5_blacklist },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0050, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0051, 0xff, 0xff, 0xff) },
-	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0052, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0052, 0xff, 0xff, 0xff),
+		.driver_info = (kernel_ulong_t)&net_intf4_blacklist },
 	/* { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0053, 0xff, 0xff, 0xff) }, */
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0054, 0xff, 0xff, 0xff) },
-	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0055, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0055, 0xff, 0xff, 0xff),
+		.driver_info = (kernel_ulong_t)&net_intf1_blacklist },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0056, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0057, 0xff, 0xff, 0xff) },
-	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0058, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0058, 0xff, 0xff, 0xff),
+		.driver_info = (kernel_ulong_t)&net_intf4_blacklist },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0059, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0061, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0062, 0xff, 0xff, 0xff) },
-	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0063, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0063, 0xff, 0xff, 0xff),
+		.driver_info = (kernel_ulong_t)&net_intf4_blacklist },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0064, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0065, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0066, 0xff, 0xff, 0xff) },
@@ -779,11 +838,13 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0083, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0086, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0087, 0xff, 0xff, 0xff) },
-	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0104, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0104, 0xff, 0xff, 0xff),
+		.driver_info = (kernel_ulong_t)&net_intf4_blacklist },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0105, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0106, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0108, 0xff, 0xff, 0xff) },
-	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0113, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0113, 0xff, 0xff, 0xff),
+		.driver_info = (kernel_ulong_t)&net_intf5_blacklist },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0117, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0118, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0121, 0xff, 0xff, 0xff) },
@@ -1003,6 +1064,12 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_AC8710, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_AC2726, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_AC8710T, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MC2718, 0xff, 0xff, 0xff),
+	 .driver_info = (kernel_ulong_t)&zte_mc2718_z_blacklist },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_AD3812, 0xff, 0xff, 0xff),
+	 .driver_info = (kernel_ulong_t)&zte_ad3812_z_blacklist },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MC2716, 0xff, 0xff, 0xff),
+	 .driver_info = (kernel_ulong_t)&zte_mc2716_z_blacklist },
 	{ USB_DEVICE(BENQ_VENDOR_ID, BENQ_PRODUCT_H10) },
 	{ USB_DEVICE(DLINK_VENDOR_ID, DLINK_PRODUCT_DWM_652) },
 	{ USB_DEVICE(ALINK_VENDOR_ID, DLINK_PRODUCT_DWM_652_U5) }, /* Yes, ALINK_VENDOR_ID */
@@ -1214,10 +1281,35 @@ static void __exit option_exit(void)
 module_init(option_init);
 module_exit(option_exit);
 
+static bool is_blacklisted(const u8 ifnum, enum option_blacklist_reason reason,
+			   const struct option_blacklist_info *blacklist)
+{
+	unsigned long num;
+	const unsigned long *intf_list;
+
+	if (blacklist) {
+		if (reason == OPTION_BLACKLIST_SENDSETUP)
+			intf_list = &blacklist->sendsetup;
+		else if (reason == OPTION_BLACKLIST_RESERVED_IF)
+			intf_list = &blacklist->reserved;
+		else {
+			BUG_ON(reason);
+			return false;
+		}
+
+		for_each_set_bit(num, intf_list, MAX_BL_NUM + 1) {
+			if (num == ifnum)
+				return true;
+		}
+	}
+	return false;
+}
+
 static int option_probe(struct usb_serial *serial,
 			const struct usb_device_id *id)
 {
 	struct usb_wwan_intf_private *data;
+
 	/* D-Link DWM 652 still exposes CD-Rom emulation interface in modem mode */
 	if (serial->dev->descriptor.idVendor == DLINK_VENDOR_ID &&
 		serial->dev->descriptor.idProduct == DLINK_PRODUCT_DWM_652 &&
@@ -1230,14 +1322,14 @@ static int option_probe(struct usb_serial *serial,
 		serial->interface->cur_altsetting->desc.bInterfaceClass != 0xff)
 		return -ENODEV;
 
-	/* Don't bind network interfaces on Huawei K3765, K4505 & K4605 */
-	if (serial->dev->descriptor.idVendor == HUAWEI_VENDOR_ID &&
-		(serial->dev->descriptor.idProduct == HUAWEI_PRODUCT_K3765 ||
-			serial->dev->descriptor.idProduct == HUAWEI_PRODUCT_K4505 ||
-			serial->dev->descriptor.idProduct == HUAWEI_PRODUCT_K4605) &&
-		(serial->interface->cur_altsetting->desc.bInterfaceNumber == 1 ||
-			serial->interface->cur_altsetting->desc.bInterfaceNumber == 2))
-		return -ENODEV;
+	/* Don't bind reserved interfaces (like network ones) which often have
+	 * the same class/subclass/protocol as the serial interfaces.  Look at
+	 * the Windows driver .INF files for reserved interface numbers.
+	 */
+	if (is_blacklisted(
+		serial->interface->cur_altsetting->desc.bInterfaceNumber,
+		OPTION_BLACKLIST_RESERVED_IF,
+		(const struct option_blacklist_info *) id->driver_info))
 
 	/* Don't bind network interface on Samsung GT-B3730, it is handled by a separate module */
 	if (serial->dev->descriptor.idVendor == SAMSUNG_VENDOR_ID &&
@@ -1246,7 +1338,6 @@ static int option_probe(struct usb_serial *serial,
 		return -ENODEV;
 
 	data = serial->private = kzalloc(sizeof(struct usb_wwan_intf_private), GFP_KERNEL);
-
 	if (!data)
 		return -ENOMEM;
 	data->send_setup = option_send_setup;
@@ -1255,23 +1346,6 @@ static int option_probe(struct usb_serial *serial,
 	return 0;
 }
 
-static enum option_blacklist_reason is_blacklisted(const u8 ifnum,
-				const struct option_blacklist_info *blacklist)
-{
-	const u8  *info;
-	int i;
-
-	if (blacklist) {
-		info = blacklist->ifaceinfo;
-
-		for (i = 0; i < blacklist->infolen; i++) {
-			if (info[i] == ifnum)
-				return blacklist->reason;
-		}
-	}
-	return OPTION_BLACKLIST_NONE;
-}
-
 static void option_instat_callback(struct urb *urb)
 {
 	int err;
@@ -1343,9 +1417,8 @@ static int option_send_setup(struct usb_serial_port *port)
 	int val = 0;
 	dbg("%s", __func__);
 
-	if (is_blacklisted(ifNum,
-			   (struct option_blacklist_info *) intfdata->private)
-	    == OPTION_BLACKLIST_SENDSETUP) {
+	if (is_blacklisted(ifNum, OPTION_BLACKLIST_SENDSETUP,
+			(struct option_blacklist_info *) intfdata->private)) {
 		dbg("No send_setup on blacklisted interface #%d\n", ifNum);
 		return -EIO;
 	}
diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c
index 1d33260de01..d44c669cc48 100644
--- a/drivers/usb/serial/pl2303.c
+++ b/drivers/usb/serial/pl2303.c
@@ -91,7 +91,7 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(SONY_VENDOR_ID, SONY_QN3USB_PRODUCT_ID) },
 	{ USB_DEVICE(SANWA_VENDOR_ID, SANWA_PRODUCT_ID) },
 	{ USB_DEVICE(ADLINK_VENDOR_ID, ADLINK_ND6530_PRODUCT_ID) },
-	{ USB_DEVICE(WINCHIPHEAD_VENDOR_ID, WINCHIPHEAD_USBSER_PRODUCT_ID) },
+	{ USB_DEVICE(SMART_VENDOR_ID, SMART_PRODUCT_ID) },
 	{ }					/* Terminating entry */
 };
 
diff --git a/drivers/usb/serial/pl2303.h b/drivers/usb/serial/pl2303.h
index ca0d237683b..c38b8c00c06 100644
--- a/drivers/usb/serial/pl2303.h
+++ b/drivers/usb/serial/pl2303.h
@@ -145,6 +145,7 @@
 #define ADLINK_VENDOR_ID		0x0b63
 #define ADLINK_ND6530_PRODUCT_ID	0x6530
 
-/* WinChipHead USB->RS 232 adapter */
-#define WINCHIPHEAD_VENDOR_ID		0x4348
-#define WINCHIPHEAD_USBSER_PRODUCT_ID	0x5523
+/* SMART USB Serial Adapter */
+#define SMART_VENDOR_ID	0x0b8c
+#define SMART_PRODUCT_ID	0x2303
+
diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c
index aeccc7f0a93..b9bb24729c9 100644
--- a/drivers/usb/serial/qcserial.c
+++ b/drivers/usb/serial/qcserial.c
@@ -28,6 +28,7 @@ static const struct usb_device_id id_table[] = {
 	{USB_DEVICE(0x05c6, 0x9212)},	/* Acer Gobi Modem Device */
 	{USB_DEVICE(0x03f0, 0x1f1d)},	/* HP un2400 Gobi Modem Device */
 	{USB_DEVICE(0x03f0, 0x201d)},	/* HP un2400 Gobi QDL Device */
+	{USB_DEVICE(0x03f0, 0x371d)},	/* HP un2430 Mobile Broadband Module */
 	{USB_DEVICE(0x04da, 0x250d)},	/* Panasonic Gobi Modem device */
 	{USB_DEVICE(0x04da, 0x250c)},	/* Panasonic Gobi QDL device */
 	{USB_DEVICE(0x413c, 0x8172)},	/* Dell Gobi Modem device */
@@ -84,6 +85,7 @@ static const struct usb_device_id id_table[] = {
 	{USB_DEVICE(0x16d8, 0x8002)},	/* CMDTech Gobi 2000 Modem device (VU922) */
 	{USB_DEVICE(0x05c6, 0x9204)},	/* Gobi 2000 QDL device */
 	{USB_DEVICE(0x05c6, 0x9205)},	/* Gobi 2000 Modem device */
+	{USB_DEVICE(0x1199, 0x9013)},	/* Sierra Wireless Gobi 3000 Modem device (MC8355) */
 	{ }				/* Terminating entry */
 };
 MODULE_DEVICE_TABLE(usb, id_table);
diff --git a/drivers/usb/storage/Kconfig b/drivers/usb/storage/Kconfig
index bedc4b9f2ac..fe2d803a634 100644
--- a/drivers/usb/storage/Kconfig
+++ b/drivers/usb/storage/Kconfig
@@ -42,7 +42,7 @@ config USB_STORAGE_REALTEK
 
 config REALTEK_AUTOPM
 	bool "Realtek Card Reader autosuspend support"
-	depends on USB_STORAGE_REALTEK && CONFIG_PM_RUNTIME
+	depends on USB_STORAGE_REALTEK && PM_RUNTIME
 	default y
 
 config USB_STORAGE_DATAFAB
diff --git a/drivers/usb/storage/protocol.c b/drivers/usb/storage/protocol.c
index fc310f75ead..0fded39e3b3 100644
--- a/drivers/usb/storage/protocol.c
+++ b/drivers/usb/storage/protocol.c
@@ -58,7 +58,9 @@
 
 void usb_stor_pad12_command(struct scsi_cmnd *srb, struct us_data *us)
 {
-	/* Pad the SCSI command with zeros out to 12 bytes
+	/*
+	 * Pad the SCSI command with zeros out to 12 bytes.  If the
+	 * command already is 12 bytes or longer, leave it alone.
 	 *
 	 * NOTE: This only works because a scsi_cmnd struct field contains
 	 * a unsigned char cmnd[16], so we know we have storage available
@@ -66,9 +68,6 @@ void usb_stor_pad12_command(struct scsi_cmnd *srb, struct us_data *us)
 	for (; srb->cmd_len<12; srb->cmd_len++)
 		srb->cmnd[srb->cmd_len] = 0;
 
-	/* set command length to 12 bytes */
-	srb->cmd_len = 12;
-
 	/* send the command to the transport layer */
 	usb_stor_invoke_transport(srb, us);
 }
diff --git a/drivers/usb/storage/realtek_cr.c b/drivers/usb/storage/realtek_cr.c
index 34adc4b42ce..232167ad478 100644
--- a/drivers/usb/storage/realtek_cr.c
+++ b/drivers/usb/storage/realtek_cr.c
@@ -320,6 +320,11 @@ static int rts51x_read_mem(struct us_data *us, u16 addr, u8 *data, u16 len)
 {
 	int retval;
 	u8 cmnd[12] = { 0 };
+	u8 *buf;
+
+	buf = kmalloc(len, GFP_NOIO);
+	if (buf == NULL)
+		return USB_STOR_TRANSPORT_ERROR;
 
 	US_DEBUGP("%s, addr = 0x%x, len = %d\n", __func__, addr, len);
 
@@ -331,10 +336,14 @@ static int rts51x_read_mem(struct us_data *us, u16 addr, u8 *data, u16 len)
 	cmnd[5] = (u8) len;
 
 	retval = rts51x_bulk_transport(us, 0, cmnd, 12,
-				       data, len, DMA_FROM_DEVICE, NULL);
-	if (retval != USB_STOR_TRANSPORT_GOOD)
+				       buf, len, DMA_FROM_DEVICE, NULL);
+	if (retval != USB_STOR_TRANSPORT_GOOD) {
+		kfree(buf);
 		return -EIO;
+	}
 
+	memcpy(data, buf, len);
+	kfree(buf);
 	return 0;
 }
 
@@ -342,6 +351,12 @@ static int rts51x_write_mem(struct us_data *us, u16 addr, u8 *data, u16 len)
 {
 	int retval;
 	u8 cmnd[12] = { 0 };
+	u8 *buf;
+
+	buf = kmalloc(len, GFP_NOIO);
+	if (buf == NULL)
+		return USB_STOR_TRANSPORT_ERROR;
+	memcpy(buf, data, len);
 
 	US_DEBUGP("%s, addr = 0x%x, len = %d\n", __func__, addr, len);
 
@@ -353,7 +368,8 @@ static int rts51x_write_mem(struct us_data *us, u16 addr, u8 *data, u16 len)
 	cmnd[5] = (u8) len;
 
 	retval = rts51x_bulk_transport(us, 0, cmnd, 12,
-				       data, len, DMA_TO_DEVICE, NULL);
+				       buf, len, DMA_TO_DEVICE, NULL);
+	kfree(buf);
 	if (retval != USB_STOR_TRANSPORT_GOOD)
 		return -EIO;
 
@@ -365,6 +381,11 @@ static int rts51x_read_status(struct us_data *us,
 {
 	int retval;
 	u8 cmnd[12] = { 0 };
+	u8 *buf;
+
+	buf = kmalloc(len, GFP_NOIO);
+	if (buf == NULL)
+		return USB_STOR_TRANSPORT_ERROR;
 
 	US_DEBUGP("%s, lun = %d\n", __func__, lun);
 
@@ -372,10 +393,14 @@ static int rts51x_read_status(struct us_data *us,
 	cmnd[1] = 0x09;
 
 	retval = rts51x_bulk_transport(us, lun, cmnd, 12,
-				       status, len, DMA_FROM_DEVICE, actlen);
-	if (retval != USB_STOR_TRANSPORT_GOOD)
+				       buf, len, DMA_FROM_DEVICE, actlen);
+	if (retval != USB_STOR_TRANSPORT_GOOD) {
+		kfree(buf);
 		return -EIO;
+	}
 
+	memcpy(status, buf, len);
+	kfree(buf);
 	return 0;
 }
 
diff --git a/drivers/usb/storage/transport.c b/drivers/usb/storage/transport.c
index e8ae21b2d38..ff32390d61e 100644
--- a/drivers/usb/storage/transport.c
+++ b/drivers/usb/storage/transport.c
@@ -691,6 +691,9 @@ void usb_stor_invoke_transport(struct scsi_cmnd *srb, struct us_data *us)
 		int temp_result;
 		struct scsi_eh_save ses;
 		int sense_size = US_SENSE_SIZE;
+		struct scsi_sense_hdr sshdr;
+		const u8 *scdd;
+		u8 fm_ili;
 
 		/* device supports and needs bigger sense buffer */
 		if (us->fflags & US_FL_SANE_SENSE)
@@ -774,32 +777,30 @@ Retry_Sense:
 			srb->sense_buffer[7] = (US_SENSE_SIZE - 8);
 		}
 
+		scsi_normalize_sense(srb->sense_buffer, SCSI_SENSE_BUFFERSIZE,
+				     &sshdr);
+
 		US_DEBUGP("-- Result from auto-sense is %d\n", temp_result);
 		US_DEBUGP("-- code: 0x%x, key: 0x%x, ASC: 0x%x, ASCQ: 0x%x\n",
-			  srb->sense_buffer[0],
-			  srb->sense_buffer[2] & 0xf,
-			  srb->sense_buffer[12], 
-			  srb->sense_buffer[13]);
+			  sshdr.response_code, sshdr.sense_key,
+			  sshdr.asc, sshdr.ascq);
 #ifdef CONFIG_USB_STORAGE_DEBUG
-		usb_stor_show_sense(
-			  srb->sense_buffer[2] & 0xf,
-			  srb->sense_buffer[12], 
-			  srb->sense_buffer[13]);
+		usb_stor_show_sense(sshdr.sense_key, sshdr.asc, sshdr.ascq);
 #endif
 
 		/* set the result so the higher layers expect this data */
 		srb->result = SAM_STAT_CHECK_CONDITION;
 
+		scdd = scsi_sense_desc_find(srb->sense_buffer,
+					    SCSI_SENSE_BUFFERSIZE, 4);
+		fm_ili = (scdd ? scdd[3] : srb->sense_buffer[2]) & 0xA0;
+
 		/* We often get empty sense data.  This could indicate that
 		 * everything worked or that there was an unspecified
 		 * problem.  We have to decide which.
 		 */
-		if (	/* Filemark 0, ignore EOM, ILI 0, no sense */
-				(srb->sense_buffer[2] & 0xaf) == 0 &&
-			/* No ASC or ASCQ */
-				srb->sense_buffer[12] == 0 &&
-				srb->sense_buffer[13] == 0) {
-
+		if (sshdr.sense_key == 0 && sshdr.asc == 0 && sshdr.ascq == 0 &&
+		    fm_ili == 0) {
 			/* If things are really okay, then let's show that.
 			 * Zero out the sense buffer so the higher layers
 			 * won't realize we did an unsolicited auto-sense.
@@ -814,7 +815,10 @@ Retry_Sense:
 			 */
 			} else {
 				srb->result = DID_ERROR << 16;
-				srb->sense_buffer[2] = HARDWARE_ERROR;
+				if ((sshdr.response_code & 0x72) == 0x72)
+					srb->sense_buffer[1] = HARDWARE_ERROR;
+				else
+					srb->sense_buffer[2] = HARDWARE_ERROR;
 			}
 		}
 	}
diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h
index 3041a974faf..24caba79d72 100644
--- a/drivers/usb/storage/unusual_devs.h
+++ b/drivers/usb/storage/unusual_devs.h
@@ -1854,6 +1854,13 @@ UNUSUAL_DEV(  0x1370, 0x6828, 0x0110, 0x0110,
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_IGNORE_RESIDUE ),
 
+/* Reported by Qinglin Ye <yestyle@gmail.com> */
+UNUSUAL_DEV(  0x13fe, 0x3600, 0x0100, 0x0100,
+		"Kingston",
+		"DT 101 G2",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_BULK_IGNORE_TAG ),
+
 /* Reported by Francesco Foresti <frafore@tiscali.it> */
 UNUSUAL_DEV(  0x14cd, 0x6600, 0x0201, 0x0201,
 		"Super Top",
diff --git a/drivers/usb/storage/usb.c b/drivers/usb/storage/usb.c
index 0ca095820f3..c325e69415a 100644
--- a/drivers/usb/storage/usb.c
+++ b/drivers/usb/storage/usb.c
@@ -831,12 +831,22 @@ static int usb_stor_scan_thread(void * __us)
 
 	dev_dbg(dev, "device found\n");
 
-	set_freezable();
-	/* Wait for the timeout to expire or for a disconnect */
+	set_freezable_with_signal();
+	/*
+	 * Wait for the timeout to expire or for a disconnect
+	 *
+	 * We can't freeze in this thread or we risk causing khubd to
+	 * fail to freeze, but we can't be non-freezable either. Nor can
+	 * khubd freeze while waiting for scanning to complete as it may
+	 * hold the device lock, causing a hang when suspending devices.
+	 * So we request a fake signal when freezing and use
+	 * interruptible sleep to kick us out of our wait early when
+	 * freezing happens.
+	 */
 	if (delay_use > 0) {
 		dev_dbg(dev, "waiting for device to settle "
 				"before scanning\n");
-		wait_event_freezable_timeout(us->delay_wait,
+		wait_event_interruptible_timeout(us->delay_wait,
 				test_bit(US_FLIDX_DONT_SCAN, &us->dflags),
 				delay_use * HZ);
 	}
diff --git a/drivers/video/carminefb.c b/drivers/video/carminefb.c
index caaa27d4a46..cb09aa1fa13 100644
--- a/drivers/video/carminefb.c
+++ b/drivers/video/carminefb.c
@@ -32,11 +32,11 @@
 #define CARMINEFB_DEFAULT_VIDEO_MODE	1
 
 static unsigned int fb_mode = CARMINEFB_DEFAULT_VIDEO_MODE;
-module_param(fb_mode, uint, 444);
+module_param(fb_mode, uint, 0444);
 MODULE_PARM_DESC(fb_mode, "Initial video mode as integer.");
 
 static char *fb_mode_str;
-module_param(fb_mode_str, charp, 444);
+module_param(fb_mode_str, charp, 0444);
 MODULE_PARM_DESC(fb_mode_str, "Initial video mode in characters.");
 
 /*
@@ -46,7 +46,7 @@ MODULE_PARM_DESC(fb_mode_str, "Initial video mode in characters.");
  * 0b010 Display 1
  */
 static int fb_displays = CARMINE_USE_DISPLAY0 | CARMINE_USE_DISPLAY1;
-module_param(fb_displays, int, 444);
+module_param(fb_displays, int, 0444);
 MODULE_PARM_DESC(fb_displays, "Bit mode, which displays are used");
 
 struct carmine_hw {
diff --git a/drivers/video/fbmem.c b/drivers/video/fbmem.c
index 5aac00eb183..ad936295d8f 100644
--- a/drivers/video/fbmem.c
+++ b/drivers/video/fbmem.c
@@ -1738,8 +1738,6 @@ void fb_set_suspend(struct fb_info *info, int state)
 {
 	struct fb_event event;
 
-	if (!lock_fb_info(info))
-		return;
 	event.info = info;
 	if (state) {
 		fb_notifier_call_chain(FB_EVENT_SUSPEND, &event);
@@ -1748,7 +1746,6 @@ void fb_set_suspend(struct fb_info *info, int state)
 		info->state = FBINFO_STATE_RUNNING;
 		fb_notifier_call_chain(FB_EVENT_RESUME, &event);
 	}
-	unlock_fb_info(info);
 }
 
 /**
diff --git a/drivers/video/fbsysfs.c b/drivers/video/fbsysfs.c
index 04251ce8918..67afa9c2289 100644
--- a/drivers/video/fbsysfs.c
+++ b/drivers/video/fbsysfs.c
@@ -399,9 +399,12 @@ static ssize_t store_fbstate(struct device *device,
 
 	state = simple_strtoul(buf, &last, 0);
 
+	if (!lock_fb_info(fb_info))
+		return -ENODEV;
 	console_lock();
 	fb_set_suspend(fb_info, (int)state);
 	console_unlock();
+	unlock_fb_info(fb_info);
 
 	return count;
 }
diff --git a/drivers/video/sh_mobile_hdmi.c b/drivers/video/sh_mobile_hdmi.c
index 7d54e2c612f..647ba984f00 100644
--- a/drivers/video/sh_mobile_hdmi.c
+++ b/drivers/video/sh_mobile_hdmi.c
@@ -1111,6 +1111,7 @@ static long sh_hdmi_clk_configure(struct sh_hdmi *hdmi, unsigned long hdmi_rate,
 static void sh_hdmi_edid_work_fn(struct work_struct *work)
 {
 	struct sh_hdmi *hdmi = container_of(work, struct sh_hdmi, edid_work.work);
+	struct fb_info *info;
 	struct sh_mobile_hdmi_info *pdata = hdmi->dev->platform_data;
 	struct sh_mobile_lcdc_chan *ch;
 	int ret;
@@ -1123,8 +1124,9 @@ static void sh_hdmi_edid_work_fn(struct work_struct *work)
 
 	mutex_lock(&hdmi->mutex);
 
+	info = hdmi->info;
+
 	if (hdmi->hp_state == HDMI_HOTPLUG_CONNECTED) {
-		struct fb_info *info = hdmi->info;
 		unsigned long parent_rate = 0, hdmi_rate;
 
 		ret = sh_hdmi_read_edid(hdmi, &hdmi_rate, &parent_rate);
@@ -1148,42 +1150,45 @@ static void sh_hdmi_edid_work_fn(struct work_struct *work)
 
 		ch = info->par;
 
-		console_lock();
+		if (lock_fb_info(info)) {
+			console_lock();
 
-		/* HDMI plug in */
-		if (!sh_hdmi_must_reconfigure(hdmi) &&
-		    info->state == FBINFO_STATE_RUNNING) {
-			/*
-			 * First activation with the default monitor - just turn
-			 * on, if we run a resume here, the logo disappears
-			 */
-			if (lock_fb_info(info)) {
+			/* HDMI plug in */
+			if (!sh_hdmi_must_reconfigure(hdmi) &&
+			    info->state == FBINFO_STATE_RUNNING) {
+				/*
+				 * First activation with the default monitor - just turn
+				 * on, if we run a resume here, the logo disappears
+				 */
 				info->var.width = hdmi->var.width;
 				info->var.height = hdmi->var.height;
 				sh_hdmi_display_on(hdmi, info);
-				unlock_fb_info(info);
+			} else {
+				/* New monitor or have to wake up */
+				fb_set_suspend(info, 0);
 			}
-		} else {
-			/* New monitor or have to wake up */
-			fb_set_suspend(info, 0);
-		}
 
-		console_unlock();
+			console_unlock();
+			unlock_fb_info(info);
+		}
 	} else {
 		ret = 0;
-		if (!hdmi->info)
+		if (!info)
 			goto out;
 
 		hdmi->monspec.modedb_len = 0;
 		fb_destroy_modedb(hdmi->monspec.modedb);
 		hdmi->monspec.modedb = NULL;
 
-		console_lock();
+		if (lock_fb_info(info)) {
+			console_lock();
 
-		/* HDMI disconnect */
-		fb_set_suspend(hdmi->info, 1);
+			/* HDMI disconnect */
+			fb_set_suspend(info, 1);
 
-		console_unlock();
+			console_unlock();
+			unlock_fb_info(info);
+		}
 	}
 
 out:
diff --git a/drivers/video/via/share.h b/drivers/video/via/share.h
index 61b0bd596b8..1603023e3aa 100644
--- a/drivers/video/via/share.h
+++ b/drivers/video/via/share.h
@@ -557,8 +557,8 @@
 #define M1200X720_R60_VSP       POSITIVE
 
 /* 1200x900@60 Sync Polarity (DCON) */
-#define M1200X900_R60_HSP       NEGATIVE
-#define M1200X900_R60_VSP       NEGATIVE
+#define M1200X900_R60_HSP       POSITIVE
+#define M1200X900_R60_VSP       POSITIVE
 
 /* 1280x600@60 Sync Polarity (GTF Mode) */
 #define M1280x600_R60_HSP       NEGATIVE
diff --git a/drivers/video/via/via_modesetting.h b/drivers/video/via/via_modesetting.h
index ae35cfdeb37..013884543e9 100644
--- a/drivers/video/via/via_modesetting.h
+++ b/drivers/video/via/via_modesetting.h
@@ -28,6 +28,11 @@
 
 #include <linux/types.h>
 
+
+#define VIA_PITCH_SIZE	(1<<3)
+#define VIA_PITCH_MAX	0x3FF8
+
+
 void via_set_primary_address(u32 addr);
 void via_set_secondary_address(u32 addr);
 void via_set_primary_pitch(u32 pitch);
diff --git a/drivers/video/via/viafbdev.c b/drivers/video/via/viafbdev.c
index 53aa4430d86..09fa57cea84 100644
--- a/drivers/video/via/viafbdev.c
+++ b/drivers/video/via/viafbdev.c
@@ -151,7 +151,8 @@ static void viafb_update_fix(struct fb_info *info)
 
 	info->fix.visual =
 		bpp == 8 ? FB_VISUAL_PSEUDOCOLOR : FB_VISUAL_TRUECOLOR;
-	info->fix.line_length = (info->var.xres_virtual * bpp / 8 + 7) & ~7;
+	info->fix.line_length = ALIGN(info->var.xres_virtual * bpp / 8,
+		VIA_PITCH_SIZE);
 }
 
 static void viafb_setup_fixinfo(struct fb_fix_screeninfo *fix,
@@ -238,8 +239,12 @@ static int viafb_check_var(struct fb_var_screeninfo *var,
 		depth = 24;
 
 	viafb_fill_var_color_info(var, depth);
-	line = (var->xres_virtual * var->bits_per_pixel / 8 + 7) & ~7;
-	if (line * var->yres_virtual > ppar->memsize)
+	if (var->xres_virtual < var->xres)
+		var->xres_virtual = var->xres;
+
+	line = ALIGN(var->xres_virtual * var->bits_per_pixel / 8,
+		VIA_PITCH_SIZE);
+	if (line > VIA_PITCH_MAX || line * var->yres_virtual > ppar->memsize)
 		return -EINVAL;
 
 	/* Based on var passed in to calculate the refresh,
@@ -348,8 +353,9 @@ static int viafb_pan_display(struct fb_var_screeninfo *var,
 	struct fb_info *info)
 {
 	struct viafb_par *viapar = info->par;
-	u32 vram_addr = (var->yoffset * var->xres_virtual + var->xoffset)
-		* (var->bits_per_pixel / 8) + viapar->vram_addr;
+	u32 vram_addr = viapar->vram_addr
+		+ var->yoffset * info->fix.line_length
+		+ var->xoffset * info->var.bits_per_pixel / 8;
 
 	DEBUG_MSG(KERN_DEBUG "viafb_pan_display, address = %d\n", vram_addr);
 	if (!viafb_dual_fb) {
diff --git a/drivers/virtio/virtio_pci.c b/drivers/virtio/virtio_pci.c
index 4bcc8b82640..ecb925411e0 100644
--- a/drivers/virtio/virtio_pci.c
+++ b/drivers/virtio/virtio_pci.c
@@ -590,11 +590,11 @@ static struct virtio_config_ops virtio_pci_config_ops = {
 
 static void virtio_pci_release_dev(struct device *_d)
 {
-	struct virtio_device *dev = container_of(_d, struct virtio_device,
-						 dev);
-	struct virtio_pci_device *vp_dev = to_vp_device(dev);
-
-	kfree(vp_dev);
+	/*
+	 * No need for a release method as we allocate/free
+	 * all devices together with the pci devices.
+	 * Provide an empty one to avoid getting a warning from core.
+	 */
 }
 
 /* the PCI probing function */
@@ -682,6 +682,7 @@ static void __devexit virtio_pci_remove(struct pci_dev *pci_dev)
 	pci_iounmap(pci_dev, vp_dev->ioaddr);
 	pci_release_regions(pci_dev);
 	pci_disable_device(pci_dev);
+	kfree(vp_dev);
 }
 
 #ifdef CONFIG_PM
diff --git a/drivers/w1/slaves/w1_ds2780.c b/drivers/w1/slaves/w1_ds2780.c
index 274c8f38303..505b17d8c67 100644
--- a/drivers/w1/slaves/w1_ds2780.c
+++ b/drivers/w1/slaves/w1_ds2780.c
@@ -26,20 +26,14 @@
 #include "../w1_family.h"
 #include "w1_ds2780.h"
 
-int w1_ds2780_io(struct device *dev, char *buf, int addr, size_t count,
-			int io)
+static int w1_ds2780_do_io(struct device *dev, char *buf, int addr,
+			size_t count, int io)
 {
 	struct w1_slave *sl = container_of(dev, struct w1_slave, dev);
 
-	if (!dev)
-		return -ENODEV;
+	if (addr > DS2780_DATA_SIZE || addr < 0)
+		return 0;
 
-	mutex_lock(&sl->master->mutex);
-
-	if (addr > DS2780_DATA_SIZE || addr < 0) {
-		count = 0;
-		goto out;
-	}
 	count = min_t(int, count, DS2780_DATA_SIZE - addr);
 
 	if (w1_reset_select_slave(sl) == 0) {
@@ -47,7 +41,6 @@ int w1_ds2780_io(struct device *dev, char *buf, int addr, size_t count,
 			w1_write_8(sl->master, W1_DS2780_WRITE_DATA);
 			w1_write_8(sl->master, addr);
 			w1_write_block(sl->master, buf, count);
-			/* XXX w1_write_block returns void, not n_written */
 		} else {
 			w1_write_8(sl->master, W1_DS2780_READ_DATA);
 			w1_write_8(sl->master, addr);
@@ -55,13 +48,42 @@ int w1_ds2780_io(struct device *dev, char *buf, int addr, size_t count,
 		}
 	}
 
-out:
+	return count;
+}
+
+int w1_ds2780_io(struct device *dev, char *buf, int addr, size_t count,
+			int io)
+{
+	struct w1_slave *sl = container_of(dev, struct w1_slave, dev);
+	int ret;
+
+	if (!dev)
+		return -ENODEV;
+
+	mutex_lock(&sl->master->mutex);
+
+	ret = w1_ds2780_do_io(dev, buf, addr, count, io);
+
 	mutex_unlock(&sl->master->mutex);
 
-	return count;
+	return ret;
 }
 EXPORT_SYMBOL(w1_ds2780_io);
 
+int w1_ds2780_io_nolock(struct device *dev, char *buf, int addr, size_t count,
+			int io)
+{
+	int ret;
+
+	if (!dev)
+		return -ENODEV;
+
+	ret = w1_ds2780_do_io(dev, buf, addr, count, io);
+
+	return ret;
+}
+EXPORT_SYMBOL(w1_ds2780_io_nolock);
+
 int w1_ds2780_eeprom_cmd(struct device *dev, int addr, int cmd)
 {
 	struct w1_slave *sl = container_of(dev, struct w1_slave, dev);
diff --git a/drivers/w1/slaves/w1_ds2780.h b/drivers/w1/slaves/w1_ds2780.h
index a1fba79eb1b..73737936502 100644
--- a/drivers/w1/slaves/w1_ds2780.h
+++ b/drivers/w1/slaves/w1_ds2780.h
@@ -124,6 +124,8 @@
 
 extern int w1_ds2780_io(struct device *dev, char *buf, int addr, size_t count,
 			int io);
+extern int w1_ds2780_io_nolock(struct device *dev, char *buf, int addr,
+			size_t count, int io);
 extern int w1_ds2780_eeprom_cmd(struct device *dev, int addr, int cmd);
 
 #endif /* !_W1_DS2780_H */
diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index 7523719bf8a..44490de5aec 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -1021,7 +1021,7 @@ int bind_ipi_to_irqhandler(enum ipi_vector ipi,
 	if (irq < 0)
 		return irq;
 
-	irqflags |= IRQF_NO_SUSPEND | IRQF_FORCE_RESUME;
+	irqflags |= IRQF_NO_SUSPEND | IRQF_FORCE_RESUME | IRQF_EARLY_RESUME;
 	retval = request_irq(irq, handler, irqflags, devname, dev_id);
 	if (retval != 0) {
 		unbind_from_irq(irq);
diff --git a/drivers/xen/gntalloc.c b/drivers/xen/gntalloc.c
index f6832f46aea..e1c4c6e5b46 100644
--- a/drivers/xen/gntalloc.c
+++ b/drivers/xen/gntalloc.c
@@ -135,7 +135,7 @@ static int add_grefs(struct ioctl_gntalloc_alloc_gref *op,
 		/* Grant foreign access to the page. */
 		gref->gref_id = gnttab_grant_foreign_access(op->domid,
 			pfn_to_mfn(page_to_pfn(gref->page)), readonly);
-		if (gref->gref_id < 0) {
+		if ((int)gref->gref_id < 0) {
 			rc = gref->gref_id;
 			goto undo;
 		}
@@ -280,7 +280,7 @@ static long gntalloc_ioctl_alloc(struct gntalloc_file_private_data *priv,
 		goto out;
 	}
 
-	gref_ids = kzalloc(sizeof(gref_ids[0]) * op.count, GFP_TEMPORARY);
+	gref_ids = kcalloc(op.count, sizeof(gref_ids[0]), GFP_TEMPORARY);
 	if (!gref_ids) {
 		rc = -ENOMEM;
 		goto out;
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 6e8c15a2320..84f317e0cc2 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -278,9 +278,10 @@ dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
 	/*
 	 * Ensure that the address returned is DMA'ble
 	 */
-	if (!dma_capable(dev, dev_addr, size))
-		panic("map_single: bounce buffer is not DMA'ble");
-
+	if (!dma_capable(dev, dev_addr, size)) {
+		swiotlb_tbl_unmap_single(dev, map, size, dir);
+		dev_addr = 0;
+	}
 	return dev_addr;
 }
 EXPORT_SYMBOL_GPL(xen_swiotlb_map_page);
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index dd0fdfc56d3..21ac5ee4b43 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -795,7 +795,16 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs)
 			 * might try to exec.  This is because the brk will
 			 * follow the loader, and is not movable.  */
 #if defined(CONFIG_X86) || defined(CONFIG_ARM)
-			load_bias = 0;
+			/* Memory randomization might have been switched off
+			 * in runtime via sysctl.
+			 * If that is the case, retain the original non-zero
+			 * load_bias value in order to establish proper
+			 * non-randomized mappings.
+			 */
+			if (current->flags & PF_RANDOMIZE)
+				load_bias = 0;
+			else
+				load_bias = ELF_PAGESTART(ELF_ET_DYN_BASE - vaddr);
 #else
 			load_bias = ELF_PAGESTART(ELF_ET_DYN_BASE - vaddr);
 #endif
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 95f786ec7f0..1c44b8d5450 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1085,6 +1085,7 @@ static int __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part);
 static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 {
 	struct gendisk *disk;
+	struct module *owner;
 	int ret;
 	int partno;
 	int perm = 0;
@@ -1110,6 +1111,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 	disk = get_gendisk(bdev->bd_dev, &partno);
 	if (!disk)
 		goto out;
+	owner = disk->fops->owner;
 
 	disk_block_events(disk);
 	mutex_lock_nested(&bdev->bd_mutex, for_part);
@@ -1137,8 +1139,8 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 					bdev->bd_disk = NULL;
 					mutex_unlock(&bdev->bd_mutex);
 					disk_unblock_events(disk);
-					module_put(disk->fops->owner);
 					put_disk(disk);
+					module_put(owner);
 					goto restart;
 				}
 			}
@@ -1194,8 +1196,8 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 				goto out_unlock_bdev;
 		}
 		/* only one opener holds refs to the module and disk */
-		module_put(disk->fops->owner);
 		put_disk(disk);
+		module_put(owner);
 	}
 	bdev->bd_openers++;
 	if (for_part)
@@ -1215,8 +1217,8 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
  out_unlock_bdev:
 	mutex_unlock(&bdev->bd_mutex);
 	disk_unblock_events(disk);
-	module_put(disk->fops->owner);
 	put_disk(disk);
+	module_put(owner);
  out:
 	bdput(bdev);
 
@@ -1442,14 +1444,15 @@ static int __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
 	if (!bdev->bd_openers) {
 		struct module *owner = disk->fops->owner;
 
-		put_disk(disk);
-		module_put(owner);
 		disk_put_part(bdev->bd_part);
 		bdev->bd_part = NULL;
 		bdev->bd_disk = NULL;
 		if (bdev != bdev->bd_contains)
 			victim = bdev->bd_contains;
 		bdev->bd_contains = NULL;
+
+		put_disk(disk);
+		module_put(owner);
 	}
 	mutex_unlock(&bdev->bd_mutex);
 	bdput(bdev);
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 71beb020197..28bba5791d9 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -2807,10 +2807,10 @@ void cifs_setup_cifs_sb(struct smb_vol *pvolume_info,
 
 /*
  * When the server doesn't allow large posix writes, only allow a wsize of
- * 128k minus the size of the WRITE_AND_X header. That allows for a write up
+ * 2^17-1 minus the size of the WRITE_AND_X header. That allows for a write up
  * to the maximum size described by RFC1002.
  */
-#define CIFS_MAX_RFC1002_WSIZE (128 * 1024 - sizeof(WRITE_REQ) + 4)
+#define CIFS_MAX_RFC1002_WSIZE ((1<<17) - 1 - sizeof(WRITE_REQ) + 4)
 
 /*
  * The default wsize is 1M. find_get_pages seems to return a maximum of 256
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index a7b2dcd4a53..745e5cdca8f 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -562,7 +562,16 @@ int cifs_get_file_info(struct file *filp)
 
 	xid = GetXid();
 	rc = CIFSSMBQFileInfo(xid, tcon, cfile->netfid, &find_data);
-	if (rc == -EOPNOTSUPP || rc == -EINVAL) {
+	switch (rc) {
+	case 0:
+		cifs_all_info_to_fattr(&fattr, &find_data, cifs_sb, false);
+		break;
+	case -EREMOTE:
+		cifs_create_dfs_fattr(&fattr, inode->i_sb);
+		rc = 0;
+		break;
+	case -EOPNOTSUPP:
+	case -EINVAL:
 		/*
 		 * FIXME: legacy server -- fall back to path-based call?
 		 * for now, just skip revalidating and mark inode for
@@ -570,18 +579,14 @@ int cifs_get_file_info(struct file *filp)
 		 */
 		rc = 0;
 		CIFS_I(inode)->time = 0;
+	default:
 		goto cgfi_exit;
-	} else if (rc == -EREMOTE) {
-		cifs_create_dfs_fattr(&fattr, inode->i_sb);
-		rc = 0;
-	} else if (rc)
-		goto cgfi_exit;
+	}
 
 	/*
 	 * don't bother with SFU junk here -- just mark inode as needing
 	 * revalidation.
 	 */
-	cifs_all_info_to_fattr(&fattr, &find_data, cifs_sb, false);
 	fattr.cf_uniqueid = CIFS_I(inode)->uniqueid;
 	fattr.cf_flags |= CIFS_FATTR_NEED_REVAL;
 	cifs_fattr_to_inode(inode, &fattr);
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index 58609bde3b9..2a834255c75 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -967,7 +967,7 @@ static void ecryptfs_set_default_crypt_stat_vals(
 
 /**
  * ecryptfs_new_file_context
- * @ecryptfs_dentry: The eCryptfs dentry
+ * @ecryptfs_inode: The eCryptfs inode
  *
  * If the crypto context for the file has not yet been established,
  * this is where we do that.  Establishing a new crypto context
@@ -984,13 +984,13 @@ static void ecryptfs_set_default_crypt_stat_vals(
  *
  * Returns zero on success; non-zero otherwise
  */
-int ecryptfs_new_file_context(struct dentry *ecryptfs_dentry)
+int ecryptfs_new_file_context(struct inode *ecryptfs_inode)
 {
 	struct ecryptfs_crypt_stat *crypt_stat =
-	    &ecryptfs_inode_to_private(ecryptfs_dentry->d_inode)->crypt_stat;
+	    &ecryptfs_inode_to_private(ecryptfs_inode)->crypt_stat;
 	struct ecryptfs_mount_crypt_stat *mount_crypt_stat =
 	    &ecryptfs_superblock_to_private(
-		    ecryptfs_dentry->d_sb)->mount_crypt_stat;
+		    ecryptfs_inode->i_sb)->mount_crypt_stat;
 	int cipher_name_len;
 	int rc = 0;
 
@@ -1299,12 +1299,12 @@ static int ecryptfs_write_headers_virt(char *page_virt, size_t max,
 }
 
 static int
-ecryptfs_write_metadata_to_contents(struct dentry *ecryptfs_dentry,
+ecryptfs_write_metadata_to_contents(struct inode *ecryptfs_inode,
 				    char *virt, size_t virt_len)
 {
 	int rc;
 
-	rc = ecryptfs_write_lower(ecryptfs_dentry->d_inode, virt,
+	rc = ecryptfs_write_lower(ecryptfs_inode, virt,
 				  0, virt_len);
 	if (rc < 0)
 		printk(KERN_ERR "%s: Error attempting to write header "
@@ -1338,7 +1338,8 @@ static unsigned long ecryptfs_get_zeroed_pages(gfp_t gfp_mask,
 
 /**
  * ecryptfs_write_metadata
- * @ecryptfs_dentry: The eCryptfs dentry
+ * @ecryptfs_dentry: The eCryptfs dentry, which should be negative
+ * @ecryptfs_inode: The newly created eCryptfs inode
  *
  * Write the file headers out.  This will likely involve a userspace
  * callout, in which the session key is encrypted with one or more
@@ -1348,10 +1349,11 @@ static unsigned long ecryptfs_get_zeroed_pages(gfp_t gfp_mask,
  *
  * Returns zero on success; non-zero on error
  */
-int ecryptfs_write_metadata(struct dentry *ecryptfs_dentry)
+int ecryptfs_write_metadata(struct dentry *ecryptfs_dentry,
+			    struct inode *ecryptfs_inode)
 {
 	struct ecryptfs_crypt_stat *crypt_stat =
-		&ecryptfs_inode_to_private(ecryptfs_dentry->d_inode)->crypt_stat;
+		&ecryptfs_inode_to_private(ecryptfs_inode)->crypt_stat;
 	unsigned int order;
 	char *virt;
 	size_t virt_len;
@@ -1391,7 +1393,7 @@ int ecryptfs_write_metadata(struct dentry *ecryptfs_dentry)
 		rc = ecryptfs_write_metadata_to_xattr(ecryptfs_dentry, virt,
 						      size);
 	else
-		rc = ecryptfs_write_metadata_to_contents(ecryptfs_dentry, virt,
+		rc = ecryptfs_write_metadata_to_contents(ecryptfs_inode, virt,
 							 virt_len);
 	if (rc) {
 		printk(KERN_ERR "%s: Error writing metadata out to lower file; "
@@ -1943,7 +1945,7 @@ static unsigned char *portable_filename_chars = ("-.0123456789ABCD"
 
 /* We could either offset on every reverse map or just pad some 0x00's
  * at the front here */
-static const unsigned char filename_rev_map[] = {
+static const unsigned char filename_rev_map[256] = {
 	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 7 */
 	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 15 */
 	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 23 */
@@ -1959,7 +1961,7 @@ static const unsigned char filename_rev_map[] = {
 	0x00, 0x26, 0x27, 0x28, 0x29, 0x2A, 0x2B, 0x2C, /* 103 */
 	0x2D, 0x2E, 0x2F, 0x30, 0x31, 0x32, 0x33, 0x34, /* 111 */
 	0x35, 0x36, 0x37, 0x38, 0x39, 0x3A, 0x3B, 0x3C, /* 119 */
-	0x3D, 0x3E, 0x3F
+	0x3D, 0x3E, 0x3F /* 123 - 255 initialized to 0x00 */
 };
 
 /**
diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h
index b36c5572b3f..9ce1e92c7d9 100644
--- a/fs/ecryptfs/ecryptfs_kernel.h
+++ b/fs/ecryptfs/ecryptfs_kernel.h
@@ -584,9 +584,10 @@ int ecryptfs_init_crypt_ctx(struct ecryptfs_crypt_stat *crypt_stat);
 int ecryptfs_write_inode_size_to_metadata(struct inode *ecryptfs_inode);
 int ecryptfs_encrypt_page(struct page *page);
 int ecryptfs_decrypt_page(struct page *page);
-int ecryptfs_write_metadata(struct dentry *ecryptfs_dentry);
+int ecryptfs_write_metadata(struct dentry *ecryptfs_dentry,
+			    struct inode *ecryptfs_inode);
 int ecryptfs_read_metadata(struct dentry *ecryptfs_dentry);
-int ecryptfs_new_file_context(struct dentry *ecryptfs_dentry);
+int ecryptfs_new_file_context(struct inode *ecryptfs_inode);
 void ecryptfs_write_crypt_stat_flags(char *page_virt,
 				     struct ecryptfs_crypt_stat *crypt_stat,
 				     size_t *written);
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index c6ac98cf9ba..d3f95f941c4 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -139,6 +139,27 @@ out:
 	return rc;
 }
 
+static void ecryptfs_vma_close(struct vm_area_struct *vma)
+{
+	filemap_write_and_wait(vma->vm_file->f_mapping);
+}
+
+static const struct vm_operations_struct ecryptfs_file_vm_ops = {
+	.close		= ecryptfs_vma_close,
+	.fault		= filemap_fault,
+};
+
+static int ecryptfs_file_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	int rc;
+
+	rc = generic_file_mmap(file, vma);
+	if (!rc)
+		vma->vm_ops = &ecryptfs_file_vm_ops;
+
+	return rc;
+}
+
 struct kmem_cache *ecryptfs_file_info_cache;
 
 /**
@@ -349,7 +370,7 @@ const struct file_operations ecryptfs_main_fops = {
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = ecryptfs_compat_ioctl,
 #endif
-	.mmap = generic_file_mmap,
+	.mmap = ecryptfs_file_mmap,
 	.open = ecryptfs_open,
 	.flush = ecryptfs_flush,
 	.release = ecryptfs_release,
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 11f8582d721..528da01fec2 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -172,22 +172,23 @@ ecryptfs_create_underlying_file(struct inode *lower_dir_inode,
  * it. It will also update the eCryptfs directory inode to mimic the
  * stat of the lower directory inode.
  *
- * Returns zero on success; non-zero on error condition
+ * Returns the new eCryptfs inode on success; an ERR_PTR on error condition
  */
-static int
+static struct inode *
 ecryptfs_do_create(struct inode *directory_inode,
 		   struct dentry *ecryptfs_dentry, int mode)
 {
 	int rc;
 	struct dentry *lower_dentry;
 	struct dentry *lower_dir_dentry;
+	struct inode *inode;
 
 	lower_dentry = ecryptfs_dentry_to_lower(ecryptfs_dentry);
 	lower_dir_dentry = lock_parent(lower_dentry);
 	if (IS_ERR(lower_dir_dentry)) {
 		ecryptfs_printk(KERN_ERR, "Error locking directory of "
 				"dentry\n");
-		rc = PTR_ERR(lower_dir_dentry);
+		inode = ERR_CAST(lower_dir_dentry);
 		goto out;
 	}
 	rc = ecryptfs_create_underlying_file(lower_dir_dentry->d_inode,
@@ -195,20 +196,19 @@ ecryptfs_do_create(struct inode *directory_inode,
 	if (rc) {
 		printk(KERN_ERR "%s: Failure to create dentry in lower fs; "
 		       "rc = [%d]\n", __func__, rc);
+		inode = ERR_PTR(rc);
 		goto out_lock;
 	}
-	rc = ecryptfs_interpose(lower_dentry, ecryptfs_dentry,
-				directory_inode->i_sb);
-	if (rc) {
-		ecryptfs_printk(KERN_ERR, "Failure in ecryptfs_interpose\n");
+	inode = __ecryptfs_get_inode(lower_dentry->d_inode,
+				     directory_inode->i_sb);
+	if (IS_ERR(inode))
 		goto out_lock;
-	}
 	fsstack_copy_attr_times(directory_inode, lower_dir_dentry->d_inode);
 	fsstack_copy_inode_size(directory_inode, lower_dir_dentry->d_inode);
 out_lock:
 	unlock_dir(lower_dir_dentry);
 out:
-	return rc;
+	return inode;
 }
 
 /**
@@ -219,26 +219,26 @@ out:
  *
  * Returns zero on success
  */
-static int ecryptfs_initialize_file(struct dentry *ecryptfs_dentry)
+static int ecryptfs_initialize_file(struct dentry *ecryptfs_dentry,
+				    struct inode *ecryptfs_inode)
 {
 	struct ecryptfs_crypt_stat *crypt_stat =
-		&ecryptfs_inode_to_private(ecryptfs_dentry->d_inode)->crypt_stat;
+		&ecryptfs_inode_to_private(ecryptfs_inode)->crypt_stat;
 	int rc = 0;
 
-	if (S_ISDIR(ecryptfs_dentry->d_inode->i_mode)) {
+	if (S_ISDIR(ecryptfs_inode->i_mode)) {
 		ecryptfs_printk(KERN_DEBUG, "This is a directory\n");
 		crypt_stat->flags &= ~(ECRYPTFS_ENCRYPTED);
 		goto out;
 	}
 	ecryptfs_printk(KERN_DEBUG, "Initializing crypto context\n");
-	rc = ecryptfs_new_file_context(ecryptfs_dentry);
+	rc = ecryptfs_new_file_context(ecryptfs_inode);
 	if (rc) {
 		ecryptfs_printk(KERN_ERR, "Error creating new file "
 				"context; rc = [%d]\n", rc);
 		goto out;
 	}
-	rc = ecryptfs_get_lower_file(ecryptfs_dentry,
-				     ecryptfs_dentry->d_inode);
+	rc = ecryptfs_get_lower_file(ecryptfs_dentry, ecryptfs_inode);
 	if (rc) {
 		printk(KERN_ERR "%s: Error attempting to initialize "
 			"the lower file for the dentry with name "
@@ -246,10 +246,10 @@ static int ecryptfs_initialize_file(struct dentry *ecryptfs_dentry)
 			ecryptfs_dentry->d_name.name, rc);
 		goto out;
 	}
-	rc = ecryptfs_write_metadata(ecryptfs_dentry);
+	rc = ecryptfs_write_metadata(ecryptfs_dentry, ecryptfs_inode);
 	if (rc)
 		printk(KERN_ERR "Error writing headers; rc = [%d]\n", rc);
-	ecryptfs_put_lower_file(ecryptfs_dentry->d_inode);
+	ecryptfs_put_lower_file(ecryptfs_inode);
 out:
 	return rc;
 }
@@ -269,18 +269,28 @@ static int
 ecryptfs_create(struct inode *directory_inode, struct dentry *ecryptfs_dentry,
 		int mode, struct nameidata *nd)
 {
+	struct inode *ecryptfs_inode;
 	int rc;
 
-	/* ecryptfs_do_create() calls ecryptfs_interpose() */
-	rc = ecryptfs_do_create(directory_inode, ecryptfs_dentry, mode);
-	if (unlikely(rc)) {
+	ecryptfs_inode = ecryptfs_do_create(directory_inode, ecryptfs_dentry,
+					    mode);
+	if (unlikely(IS_ERR(ecryptfs_inode))) {
 		ecryptfs_printk(KERN_WARNING, "Failed to create file in"
 				"lower filesystem\n");
+		rc = PTR_ERR(ecryptfs_inode);
 		goto out;
 	}
 	/* At this point, a file exists on "disk"; we need to make sure
 	 * that this on disk file is prepared to be an ecryptfs file */
-	rc = ecryptfs_initialize_file(ecryptfs_dentry);
+	rc = ecryptfs_initialize_file(ecryptfs_dentry, ecryptfs_inode);
+	if (rc) {
+		drop_nlink(ecryptfs_inode);
+		unlock_new_inode(ecryptfs_inode);
+		iput(ecryptfs_inode);
+		goto out;
+	}
+	d_instantiate(ecryptfs_dentry, ecryptfs_inode);
+	unlock_new_inode(ecryptfs_inode);
 out:
 	return rc;
 }
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index fe047d966dc..2d1744ab5bc 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -70,6 +70,15 @@
  * simultaneous inserts (A into B and B into A) from racing and
  * constructing a cycle without either insert observing that it is
  * going to.
+ * It is necessary to acquire multiple "ep->mtx"es at once in the
+ * case when one epoll fd is added to another. In this case, we
+ * always acquire the locks in the order of nesting (i.e. after
+ * epoll_ctl(e1, EPOLL_CTL_ADD, e2), e1->mtx will always be acquired
+ * before e2->mtx). Since we disallow cycles of epoll file
+ * descriptors, this ensures that the mutexes are well-ordered. In
+ * order to communicate this nesting to lockdep, when walking a tree
+ * of epoll file descriptors, we use the current recursion depth as
+ * the lockdep subkey.
  * It is possible to drop the "ep->mtx" and to use the global
  * mutex "epmutex" (together with "ep->lock") to have it working,
  * but having "ep->mtx" will make the interface more scalable.
@@ -464,13 +473,15 @@ static void ep_unregister_pollwait(struct eventpoll *ep, struct epitem *epi)
  * @ep: Pointer to the epoll private data structure.
  * @sproc: Pointer to the scan callback.
  * @priv: Private opaque data passed to the @sproc callback.
+ * @depth: The current depth of recursive f_op->poll calls.
  *
  * Returns: The same integer error code returned by the @sproc callback.
  */
 static int ep_scan_ready_list(struct eventpoll *ep,
 			      int (*sproc)(struct eventpoll *,
 					   struct list_head *, void *),
-			      void *priv)
+			      void *priv,
+			      int depth)
 {
 	int error, pwake = 0;
 	unsigned long flags;
@@ -481,7 +492,7 @@ static int ep_scan_ready_list(struct eventpoll *ep,
 	 * We need to lock this because we could be hit by
 	 * eventpoll_release_file() and epoll_ctl().
 	 */
-	mutex_lock(&ep->mtx);
+	mutex_lock_nested(&ep->mtx, depth);
 
 	/*
 	 * Steal the ready list, and re-init the original one to the
@@ -670,7 +681,7 @@ static int ep_read_events_proc(struct eventpoll *ep, struct list_head *head,
 
 static int ep_poll_readyevents_proc(void *priv, void *cookie, int call_nests)
 {
-	return ep_scan_ready_list(priv, ep_read_events_proc, NULL);
+	return ep_scan_ready_list(priv, ep_read_events_proc, NULL, call_nests + 1);
 }
 
 static unsigned int ep_eventpoll_poll(struct file *file, poll_table *wait)
@@ -737,7 +748,7 @@ void eventpoll_release_file(struct file *file)
 
 		ep = epi->ep;
 		list_del_init(&epi->fllink);
-		mutex_lock(&ep->mtx);
+		mutex_lock_nested(&ep->mtx, 0);
 		ep_remove(ep, epi);
 		mutex_unlock(&ep->mtx);
 	}
@@ -1134,7 +1145,7 @@ static int ep_send_events(struct eventpoll *ep,
 	esed.maxevents = maxevents;
 	esed.events = events;
 
-	return ep_scan_ready_list(ep, ep_send_events_proc, &esed);
+	return ep_scan_ready_list(ep, ep_send_events_proc, &esed, 0);
 }
 
 static inline struct timespec ep_set_mstimeout(long ms)
@@ -1267,7 +1278,7 @@ static int ep_loop_check_proc(void *priv, void *cookie, int call_nests)
 	struct rb_node *rbp;
 	struct epitem *epi;
 
-	mutex_lock(&ep->mtx);
+	mutex_lock_nested(&ep->mtx, call_nests + 1);
 	for (rbp = rb_first(&ep->rbr); rbp; rbp = rb_next(rbp)) {
 		epi = rb_entry(rbp, struct epitem, rbn);
 		if (unlikely(is_file_epoll(epi->ffd.file))) {
@@ -1409,7 +1420,7 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 	}
 
 
-	mutex_lock(&ep->mtx);
+	mutex_lock_nested(&ep->mtx, 0);
 
 	/*
 	 * Try to lookup the file inside our RB tree, Since we grabbed "mtx"
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index b7d7bd0f066..5c38120c389 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -358,8 +358,7 @@ struct flex_groups {
 
 /* Flags that should be inherited by new inodes from their parent. */
 #define EXT4_FL_INHERITED (EXT4_SECRM_FL | EXT4_UNRM_FL | EXT4_COMPR_FL |\
-			   EXT4_SYNC_FL | EXT4_IMMUTABLE_FL | EXT4_APPEND_FL |\
-			   EXT4_NODUMP_FL | EXT4_NOATIME_FL |\
+			   EXT4_SYNC_FL | EXT4_NODUMP_FL | EXT4_NOATIME_FL |\
 			   EXT4_NOCOMPR_FL | EXT4_JOURNAL_DATA_FL |\
 			   EXT4_NOTAIL_FL | EXT4_DIRSYNC_FL)
 
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 986e2388f03..b644b9c164a 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2656,8 +2656,8 @@ out:
 	spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
 
 	/* queue the work to convert unwritten extents to written */
-	queue_work(wq, &io_end->work);
 	iocb->private = NULL;
+	queue_work(wq, &io_end->work);
 
 	/* XXX: probably should move into the real I/O completion handler */
 	inode_dio_done(inode);
@@ -4416,6 +4416,7 @@ retry_alloc:
 			  PAGE_CACHE_SIZE, NULL, do_journal_get_write_access)) {
 			unlock_page(page);
 			ret = VM_FAULT_SIGBUS;
+			ext4_journal_stop(handle);
 			goto out;
 		}
 		ext4_set_inode_state(inode, EXT4_STATE_JDATA);
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 1c924faeb6c..50c72943d7b 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1586,7 +1586,7 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
 			dxtrace(dx_show_index("node", frames[1].entries));
 			dxtrace(dx_show_index("node",
 			       ((struct dx_node *) bh2->b_data)->entries));
-			err = ext4_handle_dirty_metadata(handle, inode, bh2);
+			err = ext4_handle_dirty_metadata(handle, dir, bh2);
 			if (err)
 				goto journal_error;
 			brelse (bh2);
@@ -1612,7 +1612,7 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
 			if (err)
 				goto journal_error;
 		}
-		err = ext4_handle_dirty_metadata(handle, inode, frames[0].bh);
+		err = ext4_handle_dirty_metadata(handle, dir, frames[0].bh);
 		if (err) {
 			ext4_std_error(inode->i_sb, err);
 			goto cleanup;
@@ -1863,7 +1863,7 @@ retry:
 	ext4_set_de_type(dir->i_sb, de, S_IFDIR);
 	inode->i_nlink = 2;
 	BUFFER_TRACE(dir_block, "call ext4_handle_dirty_metadata");
-	err = ext4_handle_dirty_metadata(handle, dir, dir_block);
+	err = ext4_handle_dirty_metadata(handle, inode, dir_block);
 	if (err)
 		goto out_clear_inode;
 	err = ext4_mark_inode_dirty(handle, inode);
@@ -2530,7 +2530,7 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
 		PARENT_INO(dir_bh->b_data, new_dir->i_sb->s_blocksize) =
 						cpu_to_le32(new_dir->i_ino);
 		BUFFER_TRACE(dir_bh, "call ext4_handle_dirty_metadata");
-		retval = ext4_handle_dirty_metadata(handle, old_dir, dir_bh);
+		retval = ext4_handle_dirty_metadata(handle, old_inode, dir_bh);
 		if (retval) {
 			ext4_std_error(old_dir->i_sb, retval);
 			goto end_rename;
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index c757adc9725..19fe4e3d39e 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -820,8 +820,14 @@ inserted:
 			if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
 				goal = goal & EXT4_MAX_BLOCK_FILE_PHYS;
 
+			/*
+			 * take i_data_sem because we will test
+			 * i_delalloc_reserved_flag in ext4_mb_new_blocks
+			 */
+			down_read((&EXT4_I(inode)->i_data_sem));
 			block = ext4_new_meta_blocks(handle, inode, goal, 0,
 						     NULL, &error);
+			up_read((&EXT4_I(inode)->i_data_sem));
 			if (error)
 				goto cleanup;
 
diff --git a/fs/hfs/trans.c b/fs/hfs/trans.c
index e673a88b8ae..b1ce4c7ad3f 100644
--- a/fs/hfs/trans.c
+++ b/fs/hfs/trans.c
@@ -40,6 +40,8 @@ int hfs_mac2asc(struct super_block *sb, char *out, const struct hfs_name *in)
 
 	src = in->name;
 	srclen = in->len;
+	if (srclen > HFS_NAMELEN)
+		srclen = HFS_NAMELEN;
 	dst = out;
 	dstlen = HFS_MAX_NAMELEN;
 	if (nls_io) {
diff --git a/fs/namei.c b/fs/namei.c
index 0b3138de2a3..3d150720c37 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -137,7 +137,7 @@ static int do_getname(const char __user *filename, char *page)
 	return retval;
 }
 
-static char *getname_flags(const char __user * filename, int flags)
+static char *getname_flags(const char __user *filename, int flags, int *empty)
 {
 	char *tmp, *result;
 
@@ -148,6 +148,8 @@ static char *getname_flags(const char __user * filename, int flags)
 
 		result = tmp;
 		if (retval < 0) {
+			if (retval == -ENOENT && empty)
+				*empty = 1;
 			if (retval != -ENOENT || !(flags & LOOKUP_EMPTY)) {
 				__putname(tmp);
 				result = ERR_PTR(retval);
@@ -160,7 +162,7 @@ static char *getname_flags(const char __user * filename, int flags)
 
 char *getname(const char __user * filename)
 {
-	return getname_flags(filename, 0);
+	return getname_flags(filename, 0, 0);
 }
 
 #ifdef CONFIG_AUDITSYSCALL
@@ -850,7 +852,7 @@ static int follow_managed(struct path *path, unsigned flags)
 		mntput(path->mnt);
 	if (ret == -EISDIR)
 		ret = 0;
-	return ret;
+	return ret < 0 ? ret : need_mntput;
 }
 
 int follow_down_one(struct path *path)
@@ -898,6 +900,7 @@ static bool __follow_mount_rcu(struct nameidata *nd, struct path *path,
 			break;
 		path->mnt = mounted;
 		path->dentry = mounted->mnt_root;
+		nd->flags |= LOOKUP_JUMPED;
 		nd->seq = read_seqcount_begin(&path->dentry->d_seq);
 		/*
 		 * Update the inode too. We don't need to re-check the
@@ -1211,6 +1214,8 @@ retry:
 		path_put_conditional(path, nd);
 		return err;
 	}
+	if (err)
+		nd->flags |= LOOKUP_JUMPED;
 	*inode = path->dentry->d_inode;
 	return 0;
 }
@@ -1798,11 +1803,11 @@ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len)
 	return __lookup_hash(&this, base, NULL);
 }
 
-int user_path_at(int dfd, const char __user *name, unsigned flags,
-		 struct path *path)
+int user_path_at_empty(int dfd, const char __user *name, unsigned flags,
+		 struct path *path, int *empty)
 {
 	struct nameidata nd;
-	char *tmp = getname_flags(name, flags);
+	char *tmp = getname_flags(name, flags, empty);
 	int err = PTR_ERR(tmp);
 	if (!IS_ERR(tmp)) {
 
@@ -1816,6 +1821,12 @@ int user_path_at(int dfd, const char __user *name, unsigned flags,
 	return err;
 }
 
+int user_path_at(int dfd, const char __user *name, unsigned flags,
+		 struct path *path)
+{
+	return user_path_at_empty(dfd, name, flags, path, 0);
+}
+
 static int user_path_parent(int dfd, const char __user *path,
 			struct nameidata *nd, char **name)
 {
@@ -2141,6 +2152,10 @@ static struct file *do_last(struct nameidata *nd, struct path *path,
 	}
 
 	/* create side of things */
+	/*
+	 * This will *only* deal with leaving RCU mode - LOOKUP_JUMPED has been
+	 * cleared when we got to the last component we are about to look up
+	 */
 	error = complete_walk(nd);
 	if (error)
 		return ERR_PTR(error);
@@ -2209,6 +2224,9 @@ static struct file *do_last(struct nameidata *nd, struct path *path,
 	if (error < 0)
 		goto exit_dput;
 
+	if (error)
+		nd->flags |= LOOKUP_JUMPED;
+
 	error = -ENOENT;
 	if (!path->dentry->d_inode)
 		goto exit_dput;
@@ -2218,6 +2236,10 @@ static struct file *do_last(struct nameidata *nd, struct path *path,
 
 	path_to_nameidata(path, nd);
 	nd->inode = path->dentry->d_inode;
+	/* Why this, you ask?  _Now_ we might have grown LOOKUP_JUMPED... */
+	error = complete_walk(nd);
+	if (error)
+		goto exit;
 	error = -EISDIR;
 	if (S_ISDIR(nd->inode->i_mode))
 		goto exit;
diff --git a/fs/namespace.c b/fs/namespace.c
index b4febb29d3b..e5e1c7d1839 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1109,6 +1109,7 @@ static int show_vfsstat(struct seq_file *m, void *v)
 
 	/* device */
 	if (mnt->mnt_sb->s_op->show_devname) {
+		seq_puts(m, "device ");
 		err = mnt->mnt_sb->s_op->show_devname(m, mnt);
 	} else {
 		if (mnt->mnt_devname) {
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 9561c8fc8bd..281ae95932c 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -176,17 +176,6 @@ retry:
 	return bio;
 }
 
-static void bl_set_lo_fail(struct pnfs_layout_segment *lseg)
-{
-	if (lseg->pls_range.iomode == IOMODE_RW) {
-		dprintk("%s Setting layout IOMODE_RW fail bit\n", __func__);
-		set_bit(lo_fail_bit(IOMODE_RW), &lseg->pls_layout->plh_flags);
-	} else {
-		dprintk("%s Setting layout IOMODE_READ fail bit\n", __func__);
-		set_bit(lo_fail_bit(IOMODE_READ), &lseg->pls_layout->plh_flags);
-	}
-}
-
 /* This is basically copied from mpage_end_io_read */
 static void bl_end_io_read(struct bio *bio, int err)
 {
@@ -206,7 +195,7 @@ static void bl_end_io_read(struct bio *bio, int err)
 	if (!uptodate) {
 		if (!rdata->pnfs_error)
 			rdata->pnfs_error = -EIO;
-		bl_set_lo_fail(rdata->lseg);
+		pnfs_set_lo_fail(rdata->lseg);
 	}
 	bio_put(bio);
 	put_parallel(par);
@@ -303,6 +292,7 @@ bl_read_pagelist(struct nfs_read_data *rdata)
 						 bl_end_io_read, par);
 			if (IS_ERR(bio)) {
 				rdata->pnfs_error = PTR_ERR(bio);
+				bio = NULL;
 				goto out;
 			}
 		}
@@ -370,7 +360,7 @@ static void bl_end_io_write_zero(struct bio *bio, int err)
 	if (!uptodate) {
 		if (!wdata->pnfs_error)
 			wdata->pnfs_error = -EIO;
-		bl_set_lo_fail(wdata->lseg);
+		pnfs_set_lo_fail(wdata->lseg);
 	}
 	bio_put(bio);
 	put_parallel(par);
@@ -386,7 +376,7 @@ static void bl_end_io_write(struct bio *bio, int err)
 	if (!uptodate) {
 		if (!wdata->pnfs_error)
 			wdata->pnfs_error = -EIO;
-		bl_set_lo_fail(wdata->lseg);
+		pnfs_set_lo_fail(wdata->lseg);
 	}
 	bio_put(bio);
 	put_parallel(par);
@@ -543,6 +533,11 @@ bl_write_pagelist(struct nfs_write_data *wdata, int sync)
 fill_invalid_ext:
 		dprintk("%s need to zero %d pages\n", __func__, npg_zero);
 		for (;npg_zero > 0; npg_zero--) {
+			if (bl_is_sector_init(be->be_inval, isect)) {
+				dprintk("isect %llu already init\n",
+					(unsigned long long)isect);
+				goto next_page;
+			}
 			/* page ref released in bl_end_io_write_zero */
 			index = isect >> PAGE_CACHE_SECTOR_SHIFT;
 			dprintk("%s zero %dth page: index %lu isect %llu\n",
@@ -562,8 +557,7 @@ fill_invalid_ext:
 			 * PageUptodate: It was read before
 			 * sector_initialized: already written out
 			 */
-			if (PageDirty(page) || PageWriteback(page) ||
-			    bl_is_sector_init(be->be_inval, isect)) {
+			if (PageDirty(page) || PageWriteback(page)) {
 				print_page(page);
 				unlock_page(page);
 				page_cache_release(page);
@@ -592,6 +586,7 @@ fill_invalid_ext:
 						 bl_end_io_write_zero, par);
 			if (IS_ERR(bio)) {
 				wdata->pnfs_error = PTR_ERR(bio);
+				bio = NULL;
 				goto out;
 			}
 			/* FIXME: This should be done in bi_end_io */
@@ -640,6 +635,7 @@ next_page:
 					 bl_end_io_write, par);
 		if (IS_ERR(bio)) {
 			wdata->pnfs_error = PTR_ERR(bio);
+			bio = NULL;
 			goto out;
 		}
 		isect += PAGE_CACHE_SECTORS;
@@ -805,7 +801,7 @@ nfs4_blk_get_deviceinfo(struct nfs_server *server, const struct nfs_fh *fh,
 			struct nfs4_deviceid *d_id)
 {
 	struct pnfs_device *dev;
-	struct pnfs_block_dev *rv = NULL;
+	struct pnfs_block_dev *rv;
 	u32 max_resp_sz;
 	int max_pages;
 	struct page **pages = NULL;
@@ -823,18 +819,20 @@ nfs4_blk_get_deviceinfo(struct nfs_server *server, const struct nfs_fh *fh,
 	dev = kmalloc(sizeof(*dev), GFP_NOFS);
 	if (!dev) {
 		dprintk("%s kmalloc failed\n", __func__);
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 	}
 
 	pages = kzalloc(max_pages * sizeof(struct page *), GFP_NOFS);
 	if (pages == NULL) {
 		kfree(dev);
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 	}
 	for (i = 0; i < max_pages; i++) {
 		pages[i] = alloc_page(GFP_NOFS);
-		if (!pages[i])
+		if (!pages[i]) {
+			rv = ERR_PTR(-ENOMEM);
 			goto out_free;
+		}
 	}
 
 	memcpy(&dev->dev_id, d_id, sizeof(*d_id));
@@ -847,8 +845,10 @@ nfs4_blk_get_deviceinfo(struct nfs_server *server, const struct nfs_fh *fh,
 	dprintk("%s: dev_id: %s\n", __func__, dev->dev_id.data);
 	rc = nfs4_proc_getdeviceinfo(server, dev);
 	dprintk("%s getdevice info returns %d\n", __func__, rc);
-	if (rc)
+	if (rc) {
+		rv = ERR_PTR(rc);
 		goto out_free;
+	}
 
 	rv = nfs4_blk_decode_device(server, dev);
  out_free:
@@ -866,7 +866,7 @@ bl_set_layoutdriver(struct nfs_server *server, const struct nfs_fh *fh)
 	struct pnfs_devicelist *dlist = NULL;
 	struct pnfs_block_dev *bdev;
 	LIST_HEAD(block_disklist);
-	int status = 0, i;
+	int status, i;
 
 	dprintk("%s enter\n", __func__);
 
@@ -898,8 +898,8 @@ bl_set_layoutdriver(struct nfs_server *server, const struct nfs_fh *fh)
 		for (i = 0; i < dlist->num_devs; i++) {
 			bdev = nfs4_blk_get_deviceinfo(server, fh,
 						       &dlist->dev_id[i]);
-			if (!bdev) {
-				status = -ENODEV;
+			if (IS_ERR(bdev)) {
+				status = PTR_ERR(bdev);
 				goto out_error;
 			}
 			spin_lock(&b_mt_id->bm_lock);
@@ -960,7 +960,7 @@ static struct pnfs_layoutdriver_type blocklayout_type = {
 };
 
 static const struct rpc_pipe_ops bl_upcall_ops = {
-	.upcall		= bl_pipe_upcall,
+	.upcall		= rpc_pipe_generic_upcall,
 	.downcall	= bl_pipe_downcall,
 	.destroy_msg	= bl_pipe_destroy_msg,
 };
@@ -989,17 +989,20 @@ static int __init nfs4blocklayout_init(void)
 			      mnt,
 			      NFS_PIPE_DIRNAME, 0, &path);
 	if (ret)
-		goto out_remove;
+		goto out_putrpc;
 
 	bl_device_pipe = rpc_mkpipe(path.dentry, "blocklayout", NULL,
 				    &bl_upcall_ops, 0);
+	path_put(&path);
 	if (IS_ERR(bl_device_pipe)) {
 		ret = PTR_ERR(bl_device_pipe);
-		goto out_remove;
+		goto out_putrpc;
 	}
 out:
 	return ret;
 
+out_putrpc:
+	rpc_put_mount();
 out_remove:
 	pnfs_unregister_layoutdriver(&blocklayout_type);
 	return ret;
@@ -1012,6 +1015,7 @@ static void __exit nfs4blocklayout_exit(void)
 
 	pnfs_unregister_layoutdriver(&blocklayout_type);
 	rpc_unlink(bl_device_pipe);
+	rpc_put_mount();
 }
 
 MODULE_ALIAS("nfs-layouttype4-3");
diff --git a/fs/nfs/blocklayout/blocklayout.h b/fs/nfs/blocklayout/blocklayout.h
index f27d827960a..42acf7ef599 100644
--- a/fs/nfs/blocklayout/blocklayout.h
+++ b/fs/nfs/blocklayout/blocklayout.h
@@ -150,7 +150,7 @@ BLK_LSEG2EXT(struct pnfs_layout_segment *lseg)
 }
 
 struct bl_dev_msg {
-	int status;
+	int32_t status;
 	uint32_t major, minor;
 };
 
@@ -169,8 +169,6 @@ extern wait_queue_head_t bl_wq;
 #define BL_DEVICE_REQUEST_ERR          0x2 /* User level process fails */
 
 /* blocklayoutdev.c */
-ssize_t bl_pipe_upcall(struct file *, struct rpc_pipe_msg *,
-		       char __user *, size_t);
 ssize_t bl_pipe_downcall(struct file *, const char __user *, size_t);
 void bl_pipe_destroy_msg(struct rpc_pipe_msg *);
 struct block_device *nfs4_blkdev_get(dev_t dev);
diff --git a/fs/nfs/blocklayout/blocklayoutdev.c b/fs/nfs/blocklayout/blocklayoutdev.c
index a83b393fb01..d08ba9107fd 100644
--- a/fs/nfs/blocklayout/blocklayoutdev.c
+++ b/fs/nfs/blocklayout/blocklayoutdev.c
@@ -79,28 +79,6 @@ int nfs4_blkdev_put(struct block_device *bdev)
 	return blkdev_put(bdev, FMODE_READ);
 }
 
-/*
- * Shouldn't there be a rpc_generic_upcall() to do this for us?
- */
-ssize_t bl_pipe_upcall(struct file *filp, struct rpc_pipe_msg *msg,
-		       char __user *dst, size_t buflen)
-{
-	char *data = (char *)msg->data + msg->copied;
-	size_t mlen = min(msg->len - msg->copied, buflen);
-	unsigned long left;
-
-	left = copy_to_user(dst, data, mlen);
-	if (left == mlen) {
-		msg->errno = -EFAULT;
-		return -EFAULT;
-	}
-
-	mlen -= left;
-	msg->copied += mlen;
-	msg->errno = 0;
-	return mlen;
-}
-
 static struct bl_dev_msg bl_mount_reply;
 
 ssize_t bl_pipe_downcall(struct file *filp, const char __user *src,
@@ -131,7 +109,7 @@ struct pnfs_block_dev *
 nfs4_blk_decode_device(struct nfs_server *server,
 		       struct pnfs_device *dev)
 {
-	struct pnfs_block_dev *rv = NULL;
+	struct pnfs_block_dev *rv;
 	struct block_device *bd = NULL;
 	struct rpc_pipe_msg msg;
 	struct bl_msg_hdr bl_msg = {
@@ -141,7 +119,7 @@ nfs4_blk_decode_device(struct nfs_server *server,
 	uint8_t *dataptr;
 	DECLARE_WAITQUEUE(wq, current);
 	struct bl_dev_msg *reply = &bl_mount_reply;
-	int offset, len, i;
+	int offset, len, i, rc;
 
 	dprintk("%s CREATING PIPEFS MESSAGE\n", __func__);
 	dprintk("%s: deviceid: %s, mincount: %d\n", __func__, dev->dev_id.data,
@@ -168,8 +146,10 @@ nfs4_blk_decode_device(struct nfs_server *server,
 
 	dprintk("%s CALLING USERSPACE DAEMON\n", __func__);
 	add_wait_queue(&bl_wq, &wq);
-	if (rpc_queue_upcall(bl_device_pipe->d_inode, &msg) < 0) {
+	rc = rpc_queue_upcall(bl_device_pipe->d_inode, &msg);
+	if (rc < 0) {
 		remove_wait_queue(&bl_wq, &wq);
+		rv = ERR_PTR(rc);
 		goto out;
 	}
 
@@ -187,8 +167,9 @@ nfs4_blk_decode_device(struct nfs_server *server,
 
 	bd = nfs4_blkdev_get(MKDEV(reply->major, reply->minor));
 	if (IS_ERR(bd)) {
-		dprintk("%s failed to open device : %ld\n",
-			__func__, PTR_ERR(bd));
+		rc = PTR_ERR(bd);
+		dprintk("%s failed to open device : %d\n", __func__, rc);
+		rv = ERR_PTR(rc);
 		goto out;
 	}
 
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index b238d95ac48..ac289909814 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1468,12 +1468,12 @@ static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry
 				res = NULL;
 				goto out;
 			/* This turned out not to be a regular file */
+			case -EISDIR:
 			case -ENOTDIR:
 				goto no_open;
 			case -ELOOP:
 				if (!(nd->intent.open.flags & O_NOFOLLOW))
 					goto no_open;
-			/* case -EISDIR: */
 			/* case -EINVAL: */
 			default:
 				res = ERR_CAST(inode);
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 28b8c3f3cda..5b3d9842c40 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -895,3 +895,35 @@ static int nfs_setlease(struct file *file, long arg, struct file_lock **fl)
 			file->f_path.dentry->d_name.name, arg);
 	return -EINVAL;
 }
+
+#ifdef CONFIG_NFS_V4
+static int
+nfs4_file_open(struct inode *inode, struct file *filp)
+{
+	/*
+	 * NFSv4 opens are handled in d_lookup and d_revalidate. If we get to
+	 * this point, then something is very wrong
+	 */
+	dprintk("NFS: %s called! inode=%p filp=%p\n", __func__, inode, filp);
+	return -ENOTDIR;
+}
+
+const struct file_operations nfs4_file_operations = {
+	.llseek		= nfs_file_llseek,
+	.read		= do_sync_read,
+	.write		= do_sync_write,
+	.aio_read	= nfs_file_read,
+	.aio_write	= nfs_file_write,
+	.mmap		= nfs_file_mmap,
+	.open		= nfs4_file_open,
+	.flush		= nfs_file_flush,
+	.release	= nfs_file_release,
+	.fsync		= nfs_file_fsync,
+	.lock		= nfs_lock,
+	.flock		= nfs_flock,
+	.splice_read	= nfs_file_splice_read,
+	.splice_write	= nfs_file_splice_write,
+	.check_flags	= nfs_check_flags,
+	.setlease	= nfs_setlease,
+};
+#endif /* CONFIG_NFS_V4 */
diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c
index f20801ae0a1..47d1c6ff2d8 100644
--- a/fs/nfs/idmap.c
+++ b/fs/nfs/idmap.c
@@ -336,8 +336,6 @@ struct idmap {
 	struct idmap_hashtable	idmap_group_hash;
 };
 
-static ssize_t idmap_pipe_upcall(struct file *, struct rpc_pipe_msg *,
-				 char __user *, size_t);
 static ssize_t idmap_pipe_downcall(struct file *, const char __user *,
 				   size_t);
 static void idmap_pipe_destroy_msg(struct rpc_pipe_msg *);
@@ -345,7 +343,7 @@ static void idmap_pipe_destroy_msg(struct rpc_pipe_msg *);
 static unsigned int fnvhash32(const void *, size_t);
 
 static const struct rpc_pipe_ops idmap_upcall_ops = {
-	.upcall		= idmap_pipe_upcall,
+	.upcall		= rpc_pipe_generic_upcall,
 	.downcall	= idmap_pipe_downcall,
 	.destroy_msg	= idmap_pipe_destroy_msg,
 };
@@ -595,27 +593,6 @@ nfs_idmap_name(struct idmap *idmap, struct idmap_hashtable *h,
 	return ret;
 }
 
-/* RPC pipefs upcall/downcall routines */
-static ssize_t
-idmap_pipe_upcall(struct file *filp, struct rpc_pipe_msg *msg,
-		  char __user *dst, size_t buflen)
-{
-	char *data = (char *)msg->data + msg->copied;
-	size_t mlen = min(msg->len, buflen);
-	unsigned long left;
-
-	left = copy_to_user(dst, data, mlen);
-	if (left == mlen) {
-		msg->errno = -EFAULT;
-		return -EFAULT;
-	}
-
-	mlen -= left;
-	msg->copied += mlen;
-	msg->errno = 0;
-	return mlen;
-}
-
 static ssize_t
 idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen)
 {
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index fe1203797b2..679d2f50b14 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -291,7 +291,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
 		 */
 		inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->file_inode_ops;
 		if (S_ISREG(inode->i_mode)) {
-			inode->i_fop = &nfs_file_operations;
+			inode->i_fop = NFS_SB(sb)->nfs_client->rpc_ops->file_ops;
 			inode->i_data.a_ops = &nfs_file_aops;
 			inode->i_data.backing_dev_info = &NFS_SB(sb)->backing_dev_info;
 		} else if (S_ISDIR(inode->i_mode)) {
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index 85f1690ca08..d4bc9ed9174 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -853,6 +853,7 @@ const struct nfs_rpc_ops nfs_v3_clientops = {
 	.dentry_ops	= &nfs_dentry_operations,
 	.dir_inode_ops	= &nfs3_dir_inode_operations,
 	.file_inode_ops	= &nfs3_file_inode_operations,
+	.file_ops	= &nfs_file_operations,
 	.getroot	= nfs3_proc_get_root,
 	.getattr	= nfs3_proc_getattr,
 	.setattr	= nfs3_proc_setattr,
diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c
index e8915d4840a..4c78c62639e 100644
--- a/fs/nfs/nfs4filelayout.c
+++ b/fs/nfs/nfs4filelayout.c
@@ -77,19 +77,6 @@ filelayout_get_dserver_offset(struct pnfs_layout_segment *lseg, loff_t offset)
 	BUG();
 }
 
-/* For data server errors we don't recover from */
-static void
-filelayout_set_lo_fail(struct pnfs_layout_segment *lseg)
-{
-	if (lseg->pls_range.iomode == IOMODE_RW) {
-		dprintk("%s Setting layout IOMODE_RW fail bit\n", __func__);
-		set_bit(lo_fail_bit(IOMODE_RW), &lseg->pls_layout->plh_flags);
-	} else {
-		dprintk("%s Setting layout IOMODE_READ fail bit\n", __func__);
-		set_bit(lo_fail_bit(IOMODE_READ), &lseg->pls_layout->plh_flags);
-	}
-}
-
 static int filelayout_async_handle_error(struct rpc_task *task,
 					 struct nfs4_state *state,
 					 struct nfs_client *clp,
@@ -145,7 +132,7 @@ static int filelayout_read_done_cb(struct rpc_task *task,
 		dprintk("%s calling restart ds_clp %p ds_clp->cl_session %p\n",
 			__func__, data->ds_clp, data->ds_clp->cl_session);
 		if (reset) {
-			filelayout_set_lo_fail(data->lseg);
+			pnfs_set_lo_fail(data->lseg);
 			nfs4_reset_read(task, data);
 			clp = NFS_SERVER(data->inode)->nfs_client;
 		}
@@ -221,7 +208,7 @@ static int filelayout_write_done_cb(struct rpc_task *task,
 		dprintk("%s calling restart ds_clp %p ds_clp->cl_session %p\n",
 			__func__, data->ds_clp, data->ds_clp->cl_session);
 		if (reset) {
-			filelayout_set_lo_fail(data->lseg);
+			pnfs_set_lo_fail(data->lseg);
 			nfs4_reset_write(task, data);
 			clp = NFS_SERVER(data->inode)->nfs_client;
 		} else
@@ -256,7 +243,7 @@ static int filelayout_commit_done_cb(struct rpc_task *task,
 			__func__, data->ds_clp, data->ds_clp->cl_session);
 		if (reset) {
 			prepare_to_resend_writes(data);
-			filelayout_set_lo_fail(data->lseg);
+			pnfs_set_lo_fail(data->lseg);
 		} else
 			nfs_restart_rpc(task, data->ds_clp);
 		return -EAGAIN;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 4700fae1ada..2d8a1693ed0 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -6267,6 +6267,7 @@ const struct nfs_rpc_ops nfs_v4_clientops = {
 	.dentry_ops	= &nfs4_dentry_operations,
 	.dir_inode_ops	= &nfs4_dir_inode_operations,
 	.file_inode_ops	= &nfs4_file_inode_operations,
+	.file_ops	= &nfs4_file_operations,
 	.getroot	= nfs4_proc_get_root,
 	.getattr	= nfs4_proc_getattr,
 	.setattr	= nfs4_proc_setattr,
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index e550e8836c3..ee73d9a4f70 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1168,23 +1168,17 @@ EXPORT_SYMBOL_GPL(pnfs_generic_pg_test);
 /*
  * Called by non rpc-based layout drivers
  */
-int
-pnfs_ld_write_done(struct nfs_write_data *data)
+void pnfs_ld_write_done(struct nfs_write_data *data)
 {
-	int status;
-
-	if (!data->pnfs_error) {
+	if (likely(!data->pnfs_error)) {
 		pnfs_set_layoutcommit(data);
 		data->mds_ops->rpc_call_done(&data->task, data);
-		data->mds_ops->rpc_release(data);
-		return 0;
+	} else {
+		put_lseg(data->lseg);
+		data->lseg = NULL;
+		dprintk("pnfs write error = %d\n", data->pnfs_error);
 	}
-
-	dprintk("%s: pnfs_error=%d, retry via MDS\n", __func__,
-		data->pnfs_error);
-	status = nfs_initiate_write(data, NFS_CLIENT(data->inode),
-				    data->mds_ops, NFS_FILE_SYNC);
-	return status ? : -EAGAIN;
+	data->mds_ops->rpc_release(data);
 }
 EXPORT_SYMBOL_GPL(pnfs_ld_write_done);
 
@@ -1268,23 +1262,17 @@ EXPORT_SYMBOL_GPL(pnfs_generic_pg_writepages);
 /*
  * Called by non rpc-based layout drivers
  */
-int
-pnfs_ld_read_done(struct nfs_read_data *data)
+void pnfs_ld_read_done(struct nfs_read_data *data)
 {
-	int status;
-
-	if (!data->pnfs_error) {
+	if (likely(!data->pnfs_error)) {
 		__nfs4_read_done_cb(data);
 		data->mds_ops->rpc_call_done(&data->task, data);
-		data->mds_ops->rpc_release(data);
-		return 0;
+	} else {
+		put_lseg(data->lseg);
+		data->lseg = NULL;
+		dprintk("pnfs write error = %d\n", data->pnfs_error);
 	}
-
-	dprintk("%s: pnfs_error=%d, retry via MDS\n", __func__,
-		data->pnfs_error);
-	status = nfs_initiate_read(data, NFS_CLIENT(data->inode),
-				   data->mds_ops);
-	return status ? : -EAGAIN;
+	data->mds_ops->rpc_release(data);
 }
 EXPORT_SYMBOL_GPL(pnfs_ld_read_done);
 
@@ -1381,6 +1369,18 @@ static void pnfs_list_write_lseg(struct inode *inode, struct list_head *listp)
 	}
 }
 
+void pnfs_set_lo_fail(struct pnfs_layout_segment *lseg)
+{
+	if (lseg->pls_range.iomode == IOMODE_RW) {
+		dprintk("%s Setting layout IOMODE_RW fail bit\n", __func__);
+		set_bit(lo_fail_bit(IOMODE_RW), &lseg->pls_layout->plh_flags);
+	} else {
+		dprintk("%s Setting layout IOMODE_READ fail bit\n", __func__);
+		set_bit(lo_fail_bit(IOMODE_READ), &lseg->pls_layout->plh_flags);
+	}
+}
+EXPORT_SYMBOL_GPL(pnfs_set_lo_fail);
+
 void
 pnfs_set_layoutcommit(struct nfs_write_data *wdata)
 {
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 01cbfd54f3c..1509530cb11 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -178,6 +178,7 @@ int pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc);
 void pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *, struct nfs_page *);
 int pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc);
 bool pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev, struct nfs_page *req);
+void pnfs_set_lo_fail(struct pnfs_layout_segment *lseg);
 int pnfs_layout_process(struct nfs4_layoutget *lgp);
 void pnfs_free_lseg_list(struct list_head *tmp_list);
 void pnfs_destroy_layout(struct nfs_inode *);
@@ -200,8 +201,8 @@ void pnfs_set_layoutcommit(struct nfs_write_data *wdata);
 void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data);
 int pnfs_layoutcommit_inode(struct inode *inode, bool sync);
 int _pnfs_return_layout(struct inode *);
-int pnfs_ld_write_done(struct nfs_write_data *);
-int pnfs_ld_read_done(struct nfs_read_data *);
+void pnfs_ld_write_done(struct nfs_write_data *);
+void pnfs_ld_read_done(struct nfs_read_data *);
 struct pnfs_layout_segment *pnfs_update_layout(struct inode *ino,
 					       struct nfs_open_context *ctx,
 					       loff_t pos,
diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c
index ac40b8535d7..f48125da198 100644
--- a/fs/nfs/proc.c
+++ b/fs/nfs/proc.c
@@ -710,6 +710,7 @@ const struct nfs_rpc_ops nfs_v2_clientops = {
 	.dentry_ops	= &nfs_dentry_operations,
 	.dir_inode_ops	= &nfs_dir_inode_operations,
 	.file_inode_ops	= &nfs_file_inode_operations,
+	.file_ops	= &nfs_file_operations,
 	.getroot	= nfs_proc_get_root,
 	.getattr	= nfs_proc_getattr,
 	.setattr	= nfs_proc_setattr,
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index 2171c043ab0..bfc20b16024 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -541,13 +541,23 @@ static void nfs_readpage_result_full(struct rpc_task *task, void *calldata)
 static void nfs_readpage_release_full(void *calldata)
 {
 	struct nfs_read_data *data = calldata;
+	struct nfs_pageio_descriptor pgio;
 
+	if (data->pnfs_error) {
+		nfs_pageio_init_read_mds(&pgio, data->inode);
+		pgio.pg_recoalesce = 1;
+	}
 	while (!list_empty(&data->pages)) {
 		struct nfs_page *req = nfs_list_entry(data->pages.next);
 
 		nfs_list_remove_request(req);
-		nfs_readpage_release(req);
+		if (!data->pnfs_error)
+			nfs_readpage_release(req);
+		else
+			nfs_pageio_add_request(&pgio, req);
 	}
+	if (data->pnfs_error)
+		nfs_pageio_complete(&pgio);
 	nfs_readdata_release(calldata);
 }
 
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index c9bd2a6b7d4..106fd0634ab 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -428,7 +428,6 @@ static void
 nfs_mark_request_dirty(struct nfs_page *req)
 {
 	__set_page_dirty_nobuffers(req->wb_page);
-	__mark_inode_dirty(req->wb_page->mapping->host, I_DIRTY_DATASYNC);
 }
 
 #if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
@@ -762,6 +761,8 @@ int nfs_updatepage(struct file *file, struct page *page,
 	status = nfs_writepage_setup(ctx, page, offset, count);
 	if (status < 0)
 		nfs_set_pageerror(page);
+	else
+		__set_page_dirty_nobuffers(page);
 
 	dprintk("NFS:       nfs_updatepage returns %d (isize %lld)\n",
 			status, (long long)i_size_read(inode));
@@ -1165,7 +1166,13 @@ static void nfs_writeback_done_full(struct rpc_task *task, void *calldata)
 static void nfs_writeback_release_full(void *calldata)
 {
 	struct nfs_write_data	*data = calldata;
-	int status = data->task.tk_status;
+	int ret, status = data->task.tk_status;
+	struct nfs_pageio_descriptor pgio;
+
+	if (data->pnfs_error) {
+		nfs_pageio_init_write_mds(&pgio, data->inode, FLUSH_STABLE);
+		pgio.pg_recoalesce = 1;
+	}
 
 	/* Update attributes as result of writeback. */
 	while (!list_empty(&data->pages)) {
@@ -1181,6 +1188,11 @@ static void nfs_writeback_release_full(void *calldata)
 			req->wb_bytes,
 			(long long)req_offset(req));
 
+		if (data->pnfs_error) {
+			dprintk(", pnfs error = %d\n", data->pnfs_error);
+			goto next;
+		}
+
 		if (status < 0) {
 			nfs_set_pageerror(page);
 			nfs_context_set_write_error(req->wb_context, status);
@@ -1200,7 +1212,19 @@ remove_request:
 	next:
 		nfs_clear_page_tag_locked(req);
 		nfs_end_page_writeback(page);
+		if (data->pnfs_error) {
+			lock_page(page);
+			nfs_pageio_cond_complete(&pgio, page->index);
+			ret = nfs_page_async_flush(&pgio, page, 0);
+			if (ret) {
+				nfs_set_pageerror(page);
+				dprintk("rewrite to MDS error = %d\n", ret);
+			}
+			unlock_page(page);
+		}
 	}
+	if (data->pnfs_error)
+		nfs_pageio_complete(&pgio);
 	nfs_writedata_release(calldata);
 }
 
@@ -1553,6 +1577,10 @@ static int nfs_commit_unstable_pages(struct inode *inode, struct writeback_contr
 	int flags = FLUSH_SYNC;
 	int ret = 0;
 
+	/* no commits means nothing needs to be done */
+	if (!nfsi->ncommit)
+		return ret;
+
 	if (wbc->sync_mode == WB_SYNC_NONE) {
 		/* Don't commit yet if this is a non-blocking flush and there
 		 * are a lot of outstanding writes for this mapping.
@@ -1686,34 +1714,20 @@ out_error:
 int nfs_migrate_page(struct address_space *mapping, struct page *newpage,
 		struct page *page)
 {
-	struct nfs_page *req;
-	int ret;
+	/*
+	 * If PagePrivate is set, then the page is currently associated with
+	 * an in-progress read or write request. Don't try to migrate it.
+	 *
+	 * FIXME: we could do this in principle, but we'll need a way to ensure
+	 *        that we can safely release the inode reference while holding
+	 *        the page lock.
+	 */
+	if (PagePrivate(page))
+		return -EBUSY;
 
 	nfs_fscache_release_page(page, GFP_KERNEL);
 
-	req = nfs_find_and_lock_request(page, false);
-	ret = PTR_ERR(req);
-	if (IS_ERR(req))
-		goto out;
-
-	ret = migrate_page(mapping, newpage, page);
-	if (!req)
-		goto out;
-	if (ret)
-		goto out_unlock;
-	page_cache_get(newpage);
-	spin_lock(&mapping->host->i_lock);
-	req->wb_page = newpage;
-	SetPagePrivate(newpage);
-	set_page_private(newpage, (unsigned long)req);
-	ClearPagePrivate(page);
-	set_page_private(page, 0);
-	spin_unlock(&mapping->host->i_lock);
-	page_cache_release(page);
-out_unlock:
-	nfs_clear_page_tag_locked(req);
-out:
-	return ret;
+	return migrate_page(mapping, newpage, page);
 }
 #endif
 
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index e8077766661..05b397ce70f 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -156,6 +156,8 @@ do_open_permission(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfs
 		!(open->op_share_access & NFS4_SHARE_ACCESS_WRITE))
 		return nfserr_inval;
 
+	accmode |= NFSD_MAY_READ_IF_EXEC;
+
 	if (open->op_share_access & NFS4_SHARE_ACCESS_READ)
 		accmode |= NFSD_MAY_READ;
 	if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE)
@@ -691,7 +693,7 @@ nfsd4_readdir(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	readdir->rd_bmval[1] &= nfsd_suppattrs1(cstate->minorversion);
 	readdir->rd_bmval[2] &= nfsd_suppattrs2(cstate->minorversion);
 
-	if ((cookie > ~(u32)0) || (cookie == 1) || (cookie == 2) ||
+	if ((cookie == 1) || (cookie == 2) ||
 	    (cookie == 0 && memcmp(readdir->rd_verf.data, zeroverf.data, NFS4_VERIFIER_SIZE)))
 		return nfserr_bad_cookie;
 
@@ -930,7 +932,7 @@ _nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	count = 4 + (verify->ve_attrlen >> 2);
 	buf = kmalloc(count << 2, GFP_KERNEL);
 	if (!buf)
-		return nfserr_resource;
+		return nfserr_jukebox;
 
 	status = nfsd4_encode_fattr(&cstate->current_fh,
 				    cstate->current_fh.fh_export,
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index 29d77f60585..02eb38ecbfe 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -88,7 +88,7 @@ nfs4_make_rec_clidname(char *dname, struct xdr_netobj *clname)
 	struct xdr_netobj cksum;
 	struct hash_desc desc;
 	struct scatterlist sg;
-	__be32 status = nfserr_resource;
+	__be32 status = nfserr_jukebox;
 
 	dprintk("NFSD: nfs4_make_rec_clidname for %.*s\n",
 			clname->len, clname->data);
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 3787ec11740..6f8bcc733f7 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -192,8 +192,15 @@ static void nfs4_file_put_fd(struct nfs4_file *fp, int oflag)
 static void __nfs4_file_put_access(struct nfs4_file *fp, int oflag)
 {
 	if (atomic_dec_and_test(&fp->fi_access[oflag])) {
-		nfs4_file_put_fd(fp, O_RDWR);
 		nfs4_file_put_fd(fp, oflag);
+		/*
+		 * It's also safe to get rid of the RDWR open *if*
+		 * we no longer have need of the other kind of access
+		 * or if we already have the other kind of open:
+		 */
+		if (fp->fi_fds[1-oflag]
+			|| atomic_read(&fp->fi_access[1 - oflag]) == 0)
+			nfs4_file_put_fd(fp, O_RDWR);
 	}
 }
 
@@ -1946,7 +1953,7 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	 * of 5 bullet points, labeled as CASE0 - CASE4 below.
 	 */
 	unconf = find_unconfirmed_client_by_str(dname, strhashval);
-	status = nfserr_resource;
+	status = nfserr_jukebox;
 	if (!conf) {
 		/*
 		 * RFC 3530 14.2.33 CASE 4:
@@ -2483,7 +2490,7 @@ renew:
 	if (open->op_stateowner == NULL) {
 		sop = alloc_init_open_stateowner(strhashval, clp, open);
 		if (sop == NULL)
-			return nfserr_resource;
+			return nfserr_jukebox;
 		open->op_stateowner = sop;
 	}
 	list_del_init(&sop->so_close_lru);
@@ -2619,7 +2626,7 @@ nfs4_new_open(struct svc_rqst *rqstp, struct nfs4_stateid **stpp,
 
 	stp = nfs4_alloc_stateid();
 	if (stp == NULL)
-		return nfserr_resource;
+		return nfserr_jukebox;
 
 	status = nfs4_get_vfs_file(rqstp, fp, cur_fh, open);
 	if (status) {
@@ -2850,7 +2857,7 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
 		status = nfserr_bad_stateid;
 		if (open->op_claim_type == NFS4_OPEN_CLAIM_DELEGATE_CUR)
 			goto out;
-		status = nfserr_resource;
+		status = nfserr_jukebox;
 		fp = alloc_init_file(ino);
 		if (fp == NULL)
 			goto out;
@@ -3530,8 +3537,9 @@ static inline void nfs4_file_downgrade(struct nfs4_stateid *stp, unsigned int to
 	int i;
 
 	for (i = 1; i < 4; i++) {
-		if (test_bit(i, &stp->st_access_bmap) && !(i & to_access)) {
-			nfs4_file_put_access(stp->st_file, i);
+		if (test_bit(i, &stp->st_access_bmap)
+					&& ((i & to_access) != i)) {
+			nfs4_file_put_access(stp->st_file, nfs4_access_to_omode(i));
 			__clear_bit(i, &stp->st_access_bmap);
 		}
 	}
@@ -3562,6 +3570,8 @@ nfsd4_open_downgrade(struct svc_rqst *rqstp,
 	if (!access_valid(od->od_share_access, cstate->minorversion)
 			|| !deny_valid(od->od_share_deny))
 		return nfserr_inval;
+	/* We don't yet support WANT bits: */
+	od->od_share_access &= NFS4_SHARE_ACCESS_MASK;
 
 	nfs4_lock_state();
 	if ((status = nfs4_preprocess_seqid_op(cstate,
@@ -4035,7 +4045,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		/* XXX: Do we need to check for duplicate stateowners on
 		 * the same file, or should they just be allowed (and
 		 * create new stateids)? */
-		status = nfserr_resource;
+		status = nfserr_jukebox;
 		lock_sop = alloc_init_lock_stateowner(strhashval,
 				open_sop->so_client, open_stp, lock);
 		if (lock_sop == NULL)
@@ -4119,9 +4129,9 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	case (EDEADLK):
 		status = nfserr_deadlock;
 		break;
-	default:        
+	default:
 		dprintk("NFSD: nfsd4_lock: vfs_lock_file() failed! status %d\n",err);
-		status = nfserr_resource;
+		status = nfserrno(err);
 		break;
 	}
 out:
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index c8bf405d19d..f8109960525 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -1623,6 +1623,18 @@ static void write_cinfo(__be32 **p, struct nfsd4_change_info *c)
 								\
 	save = resp->p;
 
+static bool seqid_mutating_err(__be32 err)
+{
+	/* rfc 3530 section 8.1.5: */
+	return	err != nfserr_stale_clientid &&
+		err != nfserr_stale_stateid &&
+		err != nfserr_bad_stateid &&
+		err != nfserr_bad_seqid &&
+		err != nfserr_bad_xdr &&
+		err != nfserr_resource &&
+		err != nfserr_nofilehandle;
+}
+
 /*
  * Routine for encoding the result of a "seqid-mutating" NFSv4 operation.  This
  * is where sequence id's are incremented, and the replay cache is filled.
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 4eefaf1b42e..5cfebe50405 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -447,12 +447,6 @@ struct nfs4_stateid {
 #define WR_STATE	        0x00000020
 #define CLOSE_STATE             0x00000040
 
-#define seqid_mutating_err(err)                       \
-	(((err) != nfserr_stale_clientid) &&    \
-	((err) != nfserr_bad_seqid) &&          \
-	((err) != nfserr_stale_stateid) &&      \
-	((err) != nfserr_bad_stateid))
-
 struct nfsd4_compound_state;
 
 extern __be32 nfs4_preprocess_stateid_op(struct nfsd4_compound_state *cstate,
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index fd0acca5370..acf88aea211 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -2114,7 +2114,8 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp,
 
 	/* Allow read access to binaries even when mode 111 */
 	if (err == -EACCES && S_ISREG(inode->i_mode) &&
-	    acc == (NFSD_MAY_READ | NFSD_MAY_OWNER_OVERRIDE))
+	     (acc == (NFSD_MAY_READ | NFSD_MAY_OWNER_OVERRIDE) ||
+	      acc == (NFSD_MAY_READ | NFSD_MAY_READ_IF_EXEC)))
 		err = inode_permission(inode, MAY_EXEC);
 
 	return err? nfserrno(err) : 0;
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index e0bbac04d1d..a22e40e2786 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -25,6 +25,7 @@
 #define NFSD_MAY_BYPASS_GSS_ON_ROOT 256
 #define NFSD_MAY_NOT_BREAK_LEASE 512
 #define NFSD_MAY_BYPASS_GSS	1024
+#define NFSD_MAY_READ_IF_EXEC	2048
 
 #define NFSD_MAY_CREATE		(NFSD_MAY_EXEC|NFSD_MAY_WRITE)
 #define NFSD_MAY_REMOVE		(NFSD_MAY_EXEC|NFSD_MAY_WRITE|NFSD_MAY_TRUNC)
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 5afaa58a863..c7d4ee663f1 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1039,6 +1039,9 @@ static int show_numa_map(struct seq_file *m, void *v)
 		seq_printf(m, " stack");
 	}
 
+	if (is_vm_hugetlb_page(vma))
+		seq_printf(m, " huge");
+
 	walk_page_range(vma->vm_start, vma->vm_end, &walk);
 
 	if (!md->pages)
diff --git a/fs/stat.c b/fs/stat.c
index 78a3aa83c7e..8806b8997d2 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -294,15 +294,16 @@ SYSCALL_DEFINE4(readlinkat, int, dfd, const char __user *, pathname,
 {
 	struct path path;
 	int error;
+	int empty = 0;
 
 	if (bufsiz <= 0)
 		return -EINVAL;
 
-	error = user_path_at(dfd, pathname, LOOKUP_EMPTY, &path);
+	error = user_path_at_empty(dfd, pathname, LOOKUP_EMPTY, &path, &empty);
 	if (!error) {
 		struct inode *inode = path.dentry->d_inode;
 
-		error = -EINVAL;
+		error = empty ? -ENOENT : -EINVAL;
 		if (inode->i_op->readlink) {
 			error = security_inode_readlink(path.dentry);
 			if (!error) {
diff --git a/fs/statfs.c b/fs/statfs.c
index 8244924dec5..9cf04a11896 100644
--- a/fs/statfs.c
+++ b/fs/statfs.c
@@ -76,7 +76,7 @@ EXPORT_SYMBOL(vfs_statfs);
 int user_statfs(const char __user *pathname, struct kstatfs *st)
 {
 	struct path path;
-	int error = user_path(pathname, &path);
+	int error = user_path_at(AT_FDCWD, pathname, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &path);
 	if (!error) {
 		error = vfs_statfs(&path, st);
 		path_put(&path);
diff --git a/fs/super.c b/fs/super.c
index 3f56a269a4f..32a81f3467e 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -61,7 +61,7 @@ static int prune_super(struct shrinker *shrink, struct shrink_control *sc)
 		return -1;
 
 	if (!grab_super_passive(sb))
-		return -1;
+		return !sc->nr_to_scan ? 0 : -1;
 
 	if (sb->s_op && sb->s_op->nr_cached_objects)
 		fs_objects = sb->s_op->nr_cached_objects(sb);
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index 620972b8094..8e8b06b90b6 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -320,7 +320,6 @@ extern struct list_head *xfs_get_buftarg_list(void);
 #define xfs_getsize_buftarg(buftarg)	block_size((buftarg)->bt_bdev)
 #define xfs_readonly_buftarg(buftarg)	bdev_read_only((buftarg)->bt_bdev)
 
-#define xfs_binval(buftarg)		xfs_flush_buftarg(buftarg, 1)
 #define XFS_bflush(buftarg)		xfs_flush_buftarg(buftarg, 1)
 
 #endif	/* __XFS_BUF_H__ */
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 7f7b42469ea..b7e75c6ba09 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -317,7 +317,19 @@ xfs_file_aio_read(
 	if (XFS_FORCED_SHUTDOWN(mp))
 		return -EIO;
 
-	if (unlikely(ioflags & IO_ISDIRECT)) {
+	/*
+	 * Locking is a bit tricky here. If we take an exclusive lock
+	 * for direct IO, we effectively serialise all new concurrent
+	 * read IO to this file and block it behind IO that is currently in
+	 * progress because IO in progress holds the IO lock shared. We only
+	 * need to hold the lock exclusive to blow away the page cache, so
+	 * only take lock exclusively if the page cache needs invalidation.
+	 * This allows the normal direct IO case of no page cache pages to
+	 * proceeed concurrently without serialisation.
+	 */
+	xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
+	if ((ioflags & IO_ISDIRECT) && inode->i_mapping->nrpages) {
+		xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
 		xfs_rw_ilock(ip, XFS_IOLOCK_EXCL);
 
 		if (inode->i_mapping->nrpages) {
@@ -330,8 +342,7 @@ xfs_file_aio_read(
 			}
 		}
 		xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL);
-	} else
-		xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
+	}
 
 	trace_xfs_file_read(ip, size, iocb->ki_pos, ioflags);
 
@@ -666,6 +677,7 @@ xfs_file_aio_write_checks(
 	xfs_fsize_t		new_size;
 	int			error = 0;
 
+	xfs_rw_ilock(ip, XFS_ILOCK_EXCL);
 	error = generic_write_checks(file, pos, count, S_ISBLK(inode->i_mode));
 	if (error) {
 		xfs_rw_iunlock(ip, XFS_ILOCK_EXCL | *iolock);
@@ -757,14 +769,24 @@ xfs_file_dio_aio_write(
 		*iolock = XFS_IOLOCK_EXCL;
 	else
 		*iolock = XFS_IOLOCK_SHARED;
-	xfs_rw_ilock(ip, XFS_ILOCK_EXCL | *iolock);
+	xfs_rw_ilock(ip, *iolock);
 
 	ret = xfs_file_aio_write_checks(file, &pos, &count, iolock);
 	if (ret)
 		return ret;
 
+	/*
+	 * Recheck if there are cached pages that need invalidate after we got
+	 * the iolock to protect against other threads adding new pages while
+	 * we were waiting for the iolock.
+	 */
+	if (mapping->nrpages && *iolock == XFS_IOLOCK_SHARED) {
+		xfs_rw_iunlock(ip, *iolock);
+		*iolock = XFS_IOLOCK_EXCL;
+		xfs_rw_ilock(ip, *iolock);
+	}
+
 	if (mapping->nrpages) {
-		WARN_ON(*iolock != XFS_IOLOCK_EXCL);
 		ret = -xfs_flushinval_pages(ip, (pos & PAGE_CACHE_MASK), -1,
 							FI_REMAPF_LOCKED);
 		if (ret)
@@ -809,7 +831,7 @@ xfs_file_buffered_aio_write(
 	size_t			count = ocount;
 
 	*iolock = XFS_IOLOCK_EXCL;
-	xfs_rw_ilock(ip, XFS_ILOCK_EXCL | *iolock);
+	xfs_rw_ilock(ip, *iolock);
 
 	ret = xfs_file_aio_write_checks(file, &pos, &count, iolock);
 	if (ret)
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 673704fab74..474920b4655 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -465,7 +465,7 @@ xfs_vn_getattr(
 	trace_xfs_getattr(ip);
 
 	if (XFS_FORCED_SHUTDOWN(mp))
-		return XFS_ERROR(EIO);
+		return -XFS_ERROR(EIO);
 
 	stat->size = XFS_ISIZE(ip);
 	stat->dev = inode->i_sb->s_dev;
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 0081657ad98..d4d5775d6e2 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -44,9 +44,6 @@
 #include "xfs_trace.h"
 
 
-STATIC void	xfs_unmountfs_wait(xfs_mount_t *);
-
-
 #ifdef HAVE_PERCPU_SB
 STATIC void	xfs_icsb_balance_counter(xfs_mount_t *, xfs_sb_field_t,
 						int);
@@ -1496,11 +1493,6 @@ xfs_unmountfs(
 	 */
 	xfs_log_force(mp, XFS_LOG_SYNC);
 
-	xfs_binval(mp->m_ddev_targp);
-	if (mp->m_rtdev_targp) {
-		xfs_binval(mp->m_rtdev_targp);
-	}
-
 	/*
 	 * Unreserve any blocks we have so that when we unmount we don't account
 	 * the reserved free space as used. This is really only necessary for
@@ -1526,7 +1518,16 @@ xfs_unmountfs(
 		xfs_warn(mp, "Unable to update superblock counters. "
 				"Freespace may not be correct on next mount.");
 	xfs_unmountfs_writesb(mp);
-	xfs_unmountfs_wait(mp); 		/* wait for async bufs */
+
+	/*
+	 * Make sure all buffers have been flushed and completed before
+	 * unmounting the log.
+	 */
+	error = xfs_flush_buftarg(mp->m_ddev_targp, 1);
+	if (error)
+		xfs_warn(mp, "%d busy buffers during unmount.", error);
+	xfs_wait_buftarg(mp->m_ddev_targp);
+
 	xfs_log_unmount_write(mp);
 	xfs_log_unmount(mp);
 	xfs_uuid_unmount(mp);
@@ -1537,16 +1538,6 @@ xfs_unmountfs(
 	xfs_free_perag(mp);
 }
 
-STATIC void
-xfs_unmountfs_wait(xfs_mount_t *mp)
-{
-	if (mp->m_logdev_targp != mp->m_ddev_targp)
-		xfs_wait_buftarg(mp->m_logdev_targp);
-	if (mp->m_rtdev_targp)
-		xfs_wait_buftarg(mp->m_rtdev_targp);
-	xfs_wait_buftarg(mp->m_ddev_targp);
-}
-
 int
 xfs_fs_writable(xfs_mount_t *mp)
 {
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 9a0aa76facd..95ba6dc885a 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -674,7 +674,8 @@ xfs_qm_dqattach_one(
 	 * disk and we didn't ask it to allocate;
 	 * ESRCH if quotas got turned off suddenly.
 	 */
-	error = xfs_qm_dqget(ip->i_mount, ip, id, type, XFS_QMOPT_DOWARN, &dqp);
+	error = xfs_qm_dqget(ip->i_mount, ip, id, type,
+			     doalloc | XFS_QMOPT_DOWARN, &dqp);
 	if (error)
 		return error;
 
diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c
index 51fc429527b..b9e28730bbd 100644
--- a/fs/xfs/xfs_vnodeops.c
+++ b/fs/xfs/xfs_vnodeops.c
@@ -113,7 +113,7 @@ xfs_readlink(
 	char		*link)
 {
 	xfs_mount_t	*mp = ip->i_mount;
-	int		pathlen;
+	xfs_fsize_t	pathlen;
 	int		error = 0;
 
 	trace_xfs_readlink(ip);
@@ -123,13 +123,19 @@ xfs_readlink(
 
 	xfs_ilock(ip, XFS_ILOCK_SHARED);
 
-	ASSERT(S_ISLNK(ip->i_d.di_mode));
-	ASSERT(ip->i_d.di_size <= MAXPATHLEN);
-
 	pathlen = ip->i_d.di_size;
 	if (!pathlen)
 		goto out;
 
+	if (pathlen < 0 || pathlen > MAXPATHLEN) {
+		xfs_alert(mp, "%s: inode (%llu) bad symlink length (%lld)",
+			 __func__, (unsigned long long) ip->i_ino,
+			 (long long) pathlen);
+		ASSERT(0);
+		return XFS_ERROR(EFSCORRUPTED);
+	}
+
+
 	if (ip->i_df.if_flags & XFS_IFINLINE) {
 		memcpy(link, ip->i_df.if_u1.if_data, pathlen);
 		link[pathlen] = '\0';
diff --git a/include/acpi/acpi_drivers.h b/include/acpi/acpi_drivers.h
index e49c36d38d7..bb145e4b935 100644
--- a/include/acpi/acpi_drivers.h
+++ b/include/acpi/acpi_drivers.h
@@ -144,7 +144,7 @@ static inline void unregister_dock_notifier(struct notifier_block *nb)
 {
 }
 static inline int register_hotplug_dock_device(acpi_handle handle,
-					       struct acpi_dock_ops *ops,
+					       const struct acpi_dock_ops *ops,
 					       void *context)
 {
 	return -ENODEV;
diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h
index 91567bbdb02..03eb1d68d50 100644
--- a/include/drm/drm_dp_helper.h
+++ b/include/drm/drm_dp_helper.h
@@ -72,6 +72,7 @@
 
 #define DP_MAIN_LINK_CHANNEL_CODING         0x006
 
+#define DP_EDP_CONFIGURATION_CAP            0x00d
 #define DP_TRAINING_AUX_RD_INTERVAL         0x00e
 
 /* link configuration */
@@ -133,6 +134,8 @@
 #define DP_MAIN_LINK_CHANNEL_CODING_SET	    0x108
 # define DP_SET_ANSI_8B10B		    (1 << 0)
 
+#define DP_EDP_CONFIGURATION_SET            0x10a
+
 #define DP_LANE0_1_STATUS		    0x202
 #define DP_LANE2_3_STATUS		    0x203
 # define DP_LANE_CR_DONE		    (1 << 0)
diff --git a/include/drm/drm_mode.h b/include/drm/drm_mode.h
index c4961ea50a4..53dfa1098b9 100644
--- a/include/drm/drm_mode.h
+++ b/include/drm/drm_mode.h
@@ -233,6 +233,8 @@ struct drm_mode_fb_cmd {
 #define DRM_MODE_FB_DIRTY_ANNOTATE_FILL 0x02
 #define DRM_MODE_FB_DIRTY_FLAGS         0x03
 
+#define DRM_MODE_FB_DIRTY_MAX_CLIPS     256
+
 /*
  * Mark a region of a framebuffer as dirty.
  *
diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h
index 3d53efd25ab..4e4fbb820e2 100644
--- a/include/drm/drm_pciids.h
+++ b/include/drm/drm_pciids.h
@@ -4,6 +4,7 @@
 */
 #define radeon_PCI_IDS \
 	{0x1002, 0x3150, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV380|RADEON_IS_MOBILITY}, \
+	{0x1002, 0x3151, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV380|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x3152, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV380|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x3154, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV380|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x3155, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV380|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
@@ -55,6 +56,7 @@
 	{0x1002, 0x4C64, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV250|RADEON_IS_MOBILITY}, \
 	{0x1002, 0x4C66, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV250|RADEON_IS_MOBILITY}, \
 	{0x1002, 0x4C67, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV250|RADEON_IS_MOBILITY}, \
+	{0x1002, 0x4C6E, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV280|RADEON_IS_MOBILITY}, \
 	{0x1002, 0x4E44, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R300}, \
 	{0x1002, 0x4E45, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R300}, \
 	{0x1002, 0x4E46, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R300}, \
@@ -195,6 +197,14 @@
 	{0x1002, 0x6770, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6778, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6779, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6840, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6841, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6842, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6843, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6849, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6850, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6858, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6859, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6880, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYPRESS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6888, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYPRESS|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6889, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYPRESS|RADEON_NEW_MEMMAP}, \
diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index 139c4db55f1..c86c940d1de 100644
--- a/include/linux/clocksource.h
+++ b/include/linux/clocksource.h
@@ -156,6 +156,7 @@ extern u64 timecounter_cyc2time(struct timecounter *tc,
  * @mult:		cycle to nanosecond multiplier
  * @shift:		cycle to nanosecond divisor (power of two)
  * @max_idle_ns:	max idle time permitted by the clocksource (nsecs)
+ * @maxadj		maximum adjustment value to mult (~11%)
  * @flags:		flags describing special properties
  * @archdata:		arch-specific data
  * @suspend:		suspend function for the clocksource, if necessary
@@ -172,7 +173,7 @@ struct clocksource {
 	u32 mult;
 	u32 shift;
 	u64 max_idle_ns;
-
+	u32 maxadj;
 #ifdef CONFIG_ARCH_CLOCKSOURCE_DATA
 	struct arch_clocksource_data archdata;
 #endif
diff --git a/include/linux/cpu_cooling.h b/include/linux/cpu_cooling.h
new file mode 100644
index 00000000000..0c573751f57
--- /dev/null
+++ b/include/linux/cpu_cooling.h
@@ -0,0 +1,45 @@
+/*
+ *  linux/include/linux/cpu_cooling.h
+ *
+ *  Copyright (C) 2011	Samsung Electronics Co., Ltd(http://www.samsung.com)
+ *  Copyright (C) 2011  Amit Daniel <amit.kachhap@linaro.org>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; version 2 of the License.
+ *
+ *  This program is distributed in the hope that it will be useful, but
+ *  WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License along
+ *  with this program; if not, write to the Free Software Foundation, Inc.,
+ *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+
+#ifndef __CPU_COOLING_H__
+#define __CPU_COOLING_H__
+
+#include <linux/thermal.h>
+
+struct freq_pctg_table {
+	unsigned int freq_clip_pctg[NR_CPUS];
+	unsigned int polling_interval;
+};
+
+extern struct thermal_cooling_device *cpufreq_cooling_register(
+	struct freq_pctg_table *tab_ptr, unsigned int tab_size,
+	const struct cpumask *mask_val);
+
+extern void cpufreq_cooling_unregister(void);
+
+extern struct thermal_cooling_device *cpuhotplug_cooling_register(
+	const struct cpumask *mask_val);
+
+extern void cpuhotplug_cooling_unregister(void);
+
+#endif /* __CPU_COOLING_H__ */
diff --git a/include/linux/cpu_pm.h b/include/linux/cpu_pm.h
new file mode 100644
index 00000000000..455b233dd3b
--- /dev/null
+++ b/include/linux/cpu_pm.h
@@ -0,0 +1,109 @@
+/*
+ * Copyright (C) 2011 Google, Inc.
+ *
+ * Author:
+ *	Colin Cross <ccross@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _LINUX_CPU_PM_H
+#define _LINUX_CPU_PM_H
+
+#include <linux/kernel.h>
+#include <linux/notifier.h>
+
+/*
+ * When a CPU goes to a low power state that turns off power to the CPU's
+ * power domain, the contents of some blocks (floating point coprocessors,
+ * interrupt controllers, caches, timers) in the same power domain can
+ * be lost.  The cpm_pm notifiers provide a method for platform idle, suspend,
+ * and hotplug implementations to notify the drivers for these blocks that
+ * they may be reset.
+ *
+ * All cpu_pm notifications must be called with interrupts disabled.
+ *
+ * The notifications are split into two classes: CPU notifications and CPU
+ * cluster notifications.
+ *
+ * CPU notifications apply to a single CPU and must be called on the affected
+ * CPU.  They are used to save per-cpu context for affected blocks.
+ *
+ * CPU cluster notifications apply to all CPUs in a single power domain. They
+ * are used to save any global context for affected blocks, and must be called
+ * after all the CPUs in the power domain have been notified of the low power
+ * state.
+ */
+
+/*
+ * Event codes passed as unsigned long val to notifier calls
+ */
+enum cpu_pm_event {
+	/* A single cpu is entering a low power state */
+	CPU_PM_ENTER,
+
+	/* A single cpu failed to enter a low power state */
+	CPU_PM_ENTER_FAILED,
+
+	/* A single cpu is exiting a low power state */
+	CPU_PM_EXIT,
+
+	/* A cpu power domain is entering a low power state */
+	CPU_CLUSTER_PM_ENTER,
+
+	/* A cpu power domain failed to enter a low power state */
+	CPU_CLUSTER_PM_ENTER_FAILED,
+
+	/* A cpu power domain is exiting a low power state */
+	CPU_CLUSTER_PM_EXIT,
+};
+
+#ifdef CONFIG_CPU_PM
+int cpu_pm_register_notifier(struct notifier_block *nb);
+int cpu_pm_unregister_notifier(struct notifier_block *nb);
+int cpu_pm_enter(void);
+int cpu_pm_exit(void);
+int cpu_cluster_pm_enter(void);
+int cpu_cluster_pm_exit(void);
+
+#else
+
+static inline int cpu_pm_register_notifier(struct notifier_block *nb)
+{
+	return 0;
+}
+
+static inline int cpu_pm_unregister_notifier(struct notifier_block *nb)
+{
+	return 0;
+}
+
+static inline int cpu_pm_enter(void)
+{
+	return 0;
+}
+
+static inline int cpu_pm_exit(void)
+{
+	return 0;
+}
+
+static inline int cpu_cluster_pm_enter(void)
+{
+	return 0;
+}
+
+static inline int cpu_cluster_pm_exit(void)
+{
+	return 0;
+}
+#endif
+#endif
diff --git a/include/linux/ext2_fs.h b/include/linux/ext2_fs.h
index 53792bf36c7..ce1b719e8bd 100644
--- a/include/linux/ext2_fs.h
+++ b/include/linux/ext2_fs.h
@@ -197,8 +197,8 @@ struct ext2_group_desc
 
 /* Flags that should be inherited by new inodes from their parent. */
 #define EXT2_FL_INHERITED (EXT2_SECRM_FL | EXT2_UNRM_FL | EXT2_COMPR_FL |\
-			   EXT2_SYNC_FL | EXT2_IMMUTABLE_FL | EXT2_APPEND_FL |\
-			   EXT2_NODUMP_FL | EXT2_NOATIME_FL | EXT2_COMPRBLK_FL|\
+			   EXT2_SYNC_FL | EXT2_NODUMP_FL |\
+			   EXT2_NOATIME_FL | EXT2_COMPRBLK_FL |\
 			   EXT2_NOCOMP_FL | EXT2_JOURNAL_DATA_FL |\
 			   EXT2_NOTAIL_FL | EXT2_DIRSYNC_FL)
 
diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h
index 67a803aee61..0244611eb2b 100644
--- a/include/linux/ext3_fs.h
+++ b/include/linux/ext3_fs.h
@@ -180,8 +180,8 @@ struct ext3_group_desc
 
 /* Flags that should be inherited by new inodes from their parent. */
 #define EXT3_FL_INHERITED (EXT3_SECRM_FL | EXT3_UNRM_FL | EXT3_COMPR_FL |\
-			   EXT3_SYNC_FL | EXT3_IMMUTABLE_FL | EXT3_APPEND_FL |\
-			   EXT3_NODUMP_FL | EXT3_NOATIME_FL | EXT3_COMPRBLK_FL|\
+			   EXT3_SYNC_FL | EXT3_NODUMP_FL |\
+			   EXT3_NOATIME_FL | EXT3_COMPRBLK_FL |\
 			   EXT3_NOCOMPR_FL | EXT3_JOURNAL_DATA_FL |\
 			   EXT3_NOTAIL_FL | EXT3_DIRSYNC_FL)
 
diff --git a/include/linux/exynos_thermal.h b/include/linux/exynos_thermal.h
new file mode 100644
index 00000000000..15f1a17453d
--- /dev/null
+++ b/include/linux/exynos_thermal.h
@@ -0,0 +1,32 @@
+/* linux/include/linux/exynos_thermal.h
+ *
+ * Copyright (c) 2010-2011 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+*/
+
+#ifndef THERMAL_INTERFACE_H
+#define THERMAL_INTERFACE_H
+/* CPU Zone information */
+
+#define SENSOR_NAME_LEN	16
+
+#define PANIC_ZONE      4
+#define WARN_ZONE       3
+#define MONITOR_ZONE    2
+#define SAFE_ZONE       1
+#define NO_ACTION       0
+
+struct thermal_sensor_info {
+	char	name[SENSOR_NAME_LEN];
+	int	(*read_temperature)(void *data);
+	void	*private_data;
+	void	*sensor_data;
+};
+
+extern int exynos4_register_temp_sensor(struct thermal_sensor_info *sensor);
+extern void exynos4_report_trigger(void);
+#endif
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index a103732b758..f51a81bc46d 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -59,6 +59,8 @@
  * IRQF_NO_SUSPEND - Do not disable this IRQ during suspend
  * IRQF_FORCE_RESUME - Force enable it on resume even if IRQF_NO_SUSPEND is set
  * IRQF_NO_THREAD - Interrupt cannot be threaded
+ * IRQF_EARLY_RESUME - Resume IRQ early during syscore instead of at device
+ *                resume time.
  */
 #define IRQF_DISABLED		0x00000020
 #define IRQF_SAMPLE_RANDOM	0x00000040
@@ -72,6 +74,7 @@
 #define IRQF_NO_SUSPEND		0x00004000
 #define IRQF_FORCE_RESUME	0x00008000
 #define IRQF_NO_THREAD		0x00010000
+#define IRQF_EARLY_RESUME	0x00020000
 
 #define IRQF_TIMER		(__IRQF_TIMER | IRQF_NO_SUSPEND | IRQF_NO_THREAD)
 
diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h
index 8cdcc2a199a..1feeb526356 100644
--- a/include/linux/io-mapping.h
+++ b/include/linux/io-mapping.h
@@ -117,6 +117,8 @@ io_mapping_unmap(void __iomem *vaddr)
 
 #else
 
+#include <linux/uaccess.h>
+
 /* this struct isn't actually defined anywhere */
 struct io_mapping;
 
@@ -138,12 +140,14 @@ static inline void __iomem *
 io_mapping_map_atomic_wc(struct io_mapping *mapping,
 			 unsigned long offset)
 {
+	pagefault_disable();
 	return ((char __force __iomem *) mapping) + offset;
 }
 
 static inline void
 io_mapping_unmap_atomic(void __iomem *vaddr)
 {
+	pagefault_enable();
 }
 
 /* Non-atomic map/unmap */
diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h
index f97672a36fa..265e2c3cbd1 100644
--- a/include/linux/jiffies.h
+++ b/include/linux/jiffies.h
@@ -303,7 +303,7 @@ extern void jiffies_to_timespec(const unsigned long jiffies,
 extern unsigned long timeval_to_jiffies(const struct timeval *value);
 extern void jiffies_to_timeval(const unsigned long jiffies,
 			       struct timeval *value);
-extern clock_t jiffies_to_clock_t(long x);
+extern clock_t jiffies_to_clock_t(unsigned long x);
 extern unsigned long clock_t_to_jiffies(unsigned long x);
 extern u64 jiffies_64_to_clock_t(u64 x);
 extern u64 nsec_to_clock_t(u64 x);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 7438071b44a..fedc5f0e62e 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -356,36 +356,50 @@ static inline struct page *compound_head(struct page *page)
 	return page;
 }
 
+/*
+ * The atomic page->_mapcount, starts from -1: so that transitions
+ * both from it and to it can be tracked, using atomic_inc_and_test
+ * and atomic_add_negative(-1).
+ */
+static inline void reset_page_mapcount(struct page *page)
+{
+	atomic_set(&(page)->_mapcount, -1);
+}
+
+static inline int page_mapcount(struct page *page)
+{
+	return atomic_read(&(page)->_mapcount) + 1;
+}
+
 static inline int page_count(struct page *page)
 {
 	return atomic_read(&compound_head(page)->_count);
 }
 
+static inline void get_huge_page_tail(struct page *page)
+{
+	/*
+	 * __split_huge_page_refcount() cannot run
+	 * from under us.
+	 */
+	VM_BUG_ON(page_mapcount(page) < 0);
+	VM_BUG_ON(atomic_read(&page->_count) != 0);
+	atomic_inc(&page->_mapcount);
+}
+
+extern bool __get_page_tail(struct page *page);
+
 static inline void get_page(struct page *page)
 {
+	if (unlikely(PageTail(page)))
+		if (likely(__get_page_tail(page)))
+			return;
 	/*
 	 * Getting a normal page or the head of a compound page
-	 * requires to already have an elevated page->_count. Only if
-	 * we're getting a tail page, the elevated page->_count is
-	 * required only in the head page, so for tail pages the
-	 * bugcheck only verifies that the page->_count isn't
-	 * negative.
+	 * requires to already have an elevated page->_count.
 	 */
-	VM_BUG_ON(atomic_read(&page->_count) < !PageTail(page));
+	VM_BUG_ON(atomic_read(&page->_count) <= 0);
 	atomic_inc(&page->_count);
-	/*
-	 * Getting a tail page will elevate both the head and tail
-	 * page->_count(s).
-	 */
-	if (unlikely(PageTail(page))) {
-		/*
-		 * This is safe only because
-		 * __split_huge_page_refcount can't run under
-		 * get_page().
-		 */
-		VM_BUG_ON(atomic_read(&page->first_page->_count) <= 0);
-		atomic_inc(&page->first_page->_count);
-	}
 }
 
 static inline struct page *virt_to_head_page(const void *x)
@@ -804,21 +818,6 @@ static inline pgoff_t page_index(struct page *page)
 }
 
 /*
- * The atomic page->_mapcount, like _count, starts from -1:
- * so that transitions both from it and to it can be tracked,
- * using atomic_inc_and_test and atomic_add_negative(-1).
- */
-static inline void reset_page_mapcount(struct page *page)
-{
-	atomic_set(&(page)->_mapcount, -1);
-}
-
-static inline int page_mapcount(struct page *page)
-{
-	return atomic_read(&(page)->_mapcount) + 1;
-}
-
-/*
  * Return true if this page is mapped into pagetables.
  */
 static inline int page_mapped(struct page *page)
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 774b8952deb..10a2f62cd56 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -62,10 +62,23 @@ struct page {
 			struct {
 
 				union {
-					atomic_t _mapcount;	/* Count of ptes mapped in mms,
-							 * to show when page is mapped
-							 * & limit reverse map searches.
-							 */
+					/*
+					 * Count of ptes mapped in
+					 * mms, to show when page is
+					 * mapped & limit reverse map
+					 * searches.
+					 *
+					 * Used also for tail pages
+					 * refcounting instead of
+					 * _count. Tail pages cannot
+					 * be mapped and keeping the
+					 * tail page _count zero at
+					 * all times guarantees
+					 * get_page_unless_zero() will
+					 * never succeed on tail
+					 * pages.
+					 */
+					atomic_t _mapcount;
 
 					struct {
 						unsigned inuse:16;
diff --git a/include/linux/namei.h b/include/linux/namei.h
index 409328d1cbb..ffc02135c48 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -67,6 +67,7 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND};
 #define LOOKUP_EMPTY		0x4000
 
 extern int user_path_at(int, const char __user *, unsigned, struct path *);
+extern int user_path_at_empty(int, const char __user *, unsigned, struct path *, int *empty);
 
 #define user_path(name, path) user_path_at(AT_FDCWD, name, LOOKUP_FOLLOW, path)
 #define user_lpath(name, path) user_path_at(AT_FDCWD, name, 0, path)
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index eaac770f886..fc0fd15c28d 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -410,6 +410,9 @@ extern const struct inode_operations nfs_file_inode_operations;
 extern const struct inode_operations nfs3_file_inode_operations;
 #endif /* CONFIG_NFS_V3 */
 extern const struct file_operations nfs_file_operations;
+#ifdef CONFIG_NFS_V4
+extern const struct file_operations nfs4_file_operations;
+#endif /* CONFIG_NFS_V4 */
 extern const struct address_space_operations nfs_file_aops;
 extern const struct address_space_operations nfs_dir_aops;
 
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index abd615d74a2..8475f340b14 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1194,6 +1194,7 @@ struct nfs_rpc_ops {
 	const struct dentry_operations *dentry_ops;
 	const struct inode_operations *dir_inode_ops;
 	const struct inode_operations *file_inode_ops;
+	const struct file_operations *file_ops;
 
 	int	(*getroot) (struct nfs_server *, struct nfs_fh *,
 			    struct nfs_fsinfo *);
diff --git a/include/linux/of.h b/include/linux/of.h
index 9180dc5cb00..92c40a14224 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -68,6 +68,7 @@ struct device_node {
 /* Pointer for first entry in chain of all nodes. */
 extern struct device_node *allnodes;
 extern struct device_node *of_chosen;
+extern struct device_node *of_aliases;
 extern rwlock_t devtree_lock;
 
 static inline bool of_have_populated_dt(void)
@@ -199,6 +200,8 @@ extern int of_property_read_u32_array(const struct device_node *np,
 				      const char *propname,
 				      u32 *out_values,
 				      size_t sz);
+extern int of_property_read_u64(const struct device_node *np,
+				const char *propname, u64 *out_value);
 
 extern int of_property_read_string(struct device_node *np,
 				   const char *propname,
@@ -209,6 +212,9 @@ extern int of_device_is_available(const struct device_node *device);
 extern const void *of_get_property(const struct device_node *node,
 				const char *name,
 				int *lenp);
+#define for_each_property(pp, properties) \
+	for (pp = properties; pp != NULL; pp = pp->next)
+
 extern int of_n_addr_cells(struct device_node *np);
 extern int of_n_size_cells(struct device_node *np);
 extern const struct of_device_id *of_match_node(
@@ -221,6 +227,9 @@ extern int of_parse_phandles_with_args(struct device_node *np,
 	const char *list_name, const char *cells_name, int index,
 	struct device_node **out_node, const void **out_args);
 
+extern void of_alias_scan(void * (*dt_alloc)(u64 size, u64 align));
+extern int of_alias_get_id(struct device_node *np, const char *stem);
+
 extern int of_machine_is_compatible(const char *compat);
 
 extern int prom_add_property(struct device_node* np, struct property* prop);
@@ -235,6 +244,7 @@ extern void of_attach_node(struct device_node *);
 extern void of_detach_node(struct device_node *);
 #endif
 
+#define of_match_ptr(_ptr)	(_ptr)
 #else /* CONFIG_OF */
 
 static inline bool of_have_populated_dt(void)
@@ -242,6 +252,22 @@ static inline bool of_have_populated_dt(void)
 	return false;
 }
 
+#define for_each_child_of_node(parent, child) \
+	while (0)
+
+static inline int of_device_is_compatible(const struct device_node *device,
+					  const char *name)
+{
+	return 0;
+}
+
+static inline struct property *of_find_property(const struct device_node *np,
+						const char *name,
+						int *lenp)
+{
+	return NULL;
+}
+
 static inline int of_property_read_u32_array(const struct device_node *np,
 					     const char *propname,
 					     u32 *out_values, size_t sz)
@@ -263,6 +289,21 @@ static inline const void *of_get_property(const struct device_node *node,
 	return NULL;
 }
 
+static inline int of_property_read_u64(const struct device_node *np,
+				       const char *propname, u64 *out_value)
+{
+	return -ENOSYS;
+}
+
+static inline struct device_node *of_parse_phandle(struct device_node *np,
+						   const char *phandle_name,
+						   int index)
+{
+	return NULL;
+}
+
+#define of_match_ptr(_ptr)	NULL
+#define of_match_node(_matches, _node)	NULL
 #endif /* CONFIG_OF */
 
 static inline int of_property_read_u32(const struct device_node *np,
diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h
index 5a6f458a4bb..0c53ecbd937 100644
--- a/include/linux/of_platform.h
+++ b/include/linux/of_platform.h
@@ -45,13 +45,18 @@ struct of_dev_auxdata {
 	char *compatible;
 	resource_size_t phys_addr;
 	char *name;
+	int id;
 	void *platform_data;
 };
 
 /* Macro to simplify populating a lookup table */
 #define OF_DEV_AUXDATA(_compat,_phys,_name,_pdata) \
 	{ .compatible = _compat, .phys_addr = _phys, .name = _name, \
-	  .platform_data = _pdata }
+	  .id = -1, .platform_data = _pdata }
+
+#define OF_DEV_AUXDATA_ID(_compat,_phys,_name,_id,_pdata) \
+	{ .compatible = _compat, .phys_addr = _phys, .name = _name, \
+	  .id = _id, .platform_data = _pdata }
 
 /**
  * of_platform_driver - Legacy of-aware driver for platform devices.
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 54fc4138955..79f337c4738 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -420,7 +420,7 @@ struct phy_driver {
 
 	/*
 	 * Requests a Tx timestamp for 'skb'. The phy driver promises
-	 * to deliver it to the socket's error queue as soon as a
+	 * to deliver it using skb_complete_tx_timestamp() as soon as a
 	 * timestamp becomes available. One of the PTP_CLASS_ values
 	 * is passed in 'type'.
 	 */
diff --git a/include/linux/platform_data/exynos4_tmu.h b/include/linux/platform_data/exynos4_tmu.h
new file mode 100644
index 00000000000..f655dcdd6b1
--- /dev/null
+++ b/include/linux/platform_data/exynos4_tmu.h
@@ -0,0 +1,87 @@
+/*
+ * exynos4_tmu.h - Samsung EXYNOS4 TMU (Thermal Management Unit)
+ *
+ *  Copyright (C) 2011 Samsung Electronics
+ *  Donggeun Kim <dg77.kim@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#ifndef _LINUX_EXYNOS4_TMU_H
+#define _LINUX_EXYNOS4_TMU_H
+#include <linux/cpu_cooling.h>
+
+enum calibration_type {
+	TYPE_ONE_POINT_TRIMMING,
+	TYPE_TWO_POINT_TRIMMING,
+	TYPE_NONE,
+};
+
+/**
+ * struct exynos4_tmu_platform_data
+ * @threshold: basic temperature for generating interrupt
+ *	       25 <= threshold <= 125 [unit: degree Celsius]
+ * @trigger_levels: array for each interrupt levels
+ *	[unit: degree Celsius]
+ *	0: temperature for trigger_level0 interrupt
+ *	   condition for trigger_level0 interrupt:
+ *		current temperature > threshold + trigger_levels[0]
+ *	1: temperature for trigger_level1 interrupt
+ *	   condition for trigger_level1 interrupt:
+ *		current temperature > threshold + trigger_levels[1]
+ *	2: temperature for trigger_level2 interrupt
+ *	   condition for trigger_level2 interrupt:
+ *		current temperature > threshold + trigger_levels[2]
+ *	3: temperature for trigger_level3 interrupt
+ *	   condition for trigger_level3 interrupt:
+ *		current temperature > threshold + trigger_levels[3]
+ * @trigger_level0_en:
+ *	1 = enable trigger_level0 interrupt,
+ *	0 = disable trigger_level0 interrupt
+ * @trigger_level1_en:
+ *	1 = enable trigger_level1 interrupt,
+ *	0 = disable trigger_level1 interrupt
+ * @trigger_level2_en:
+ *	1 = enable trigger_level2 interrupt,
+ *	0 = disable trigger_level2 interrupt
+ * @trigger_level3_en:
+ *	1 = enable trigger_level3 interrupt,
+ *	0 = disable trigger_level3 interrupt
+ * @gain: gain of amplifier in the positive-TC generator block
+ *	0 <= gain <= 15
+ * @reference_voltage: reference voltage of amplifier
+ *	in the positive-TC generator block
+ *	0 <= reference_voltage <= 31
+ * @cal_type: calibration type for temperature
+ *
+ * This structure is required for configuration of exynos4_tmu driver.
+ */
+struct exynos4_tmu_platform_data {
+	u8 threshold;
+	u8 trigger_levels[4];
+	bool trigger_level0_en;
+	bool trigger_level1_en;
+	bool trigger_level2_en;
+	bool trigger_level3_en;
+
+	u8 gain;
+	u8 reference_voltage;
+
+	enum calibration_type cal_type;
+
+	struct freq_pctg_table freq_tab[4];
+	unsigned int level_count;
+};
+#endif /* _LINUX_EXYNOS4_TMU_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 41d0237fd44..8610921984b 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -901,6 +901,7 @@ struct sched_group_power {
 	 * single CPU.
 	 */
 	unsigned int power, power_orig;
+	unsigned long next_update;
 };
 
 struct sched_group {
diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h
index 790651b4e5b..a83833a1f7a 100644
--- a/include/linux/shrinker.h
+++ b/include/linux/shrinker.h
@@ -20,6 +20,7 @@ struct shrink_control {
  * 'nr_to_scan' entries and attempt to free them up.  It should return
  * the number of objects which remain in the cache.  If it returns -1, it means
  * it cannot do any scanning at this time (eg. there is a risk of deadlock).
+ * The callback must not return -1 if nr_to_scan is zero.
  *
  * The 'gfpmask' refers to the allocation we are currently trying to
  * fulfil.
diff --git a/include/linux/sigma.h b/include/linux/sigma.h
index e2accb3164d..d0de882c0d9 100644
--- a/include/linux/sigma.h
+++ b/include/linux/sigma.h
@@ -24,7 +24,7 @@ struct sigma_firmware {
 struct sigma_firmware_header {
 	unsigned char magic[7];
 	u8 version;
-	u32 crc;
+	__le32 crc;
 };
 
 enum {
@@ -40,19 +40,14 @@ enum {
 struct sigma_action {
 	u8 instr;
 	u8 len_hi;
-	u16 len;
-	u16 addr;
+	__le16 len;
+	__be16 addr;
 	unsigned char payload[];
 };
 
 static inline u32 sigma_action_len(struct sigma_action *sa)
 {
-	return (sa->len_hi << 16) | sa->len;
-}
-
-static inline size_t sigma_action_size(struct sigma_action *sa, u32 payload_len)
-{
-	return sizeof(*sa) + payload_len + (payload_len % 2);
+	return (sa->len_hi << 16) | le16_to_cpu(sa->len);
 }
 
 extern int process_sigma_firmware(struct i2c_client *client, const char *name);
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 8bd383caa36..0f966460a34 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2020,8 +2020,13 @@ static inline bool skb_defer_rx_timestamp(struct sk_buff *skb)
 /**
  * skb_complete_tx_timestamp() - deliver cloned skb with tx timestamps
  *
+ * PHY drivers may accept clones of transmitted packets for
+ * timestamping via their phy_driver.txtstamp method. These drivers
+ * must call this function to return the skb back to the stack, with
+ * or without a timestamp.
+ *
  * @skb: clone of the the original outgoing packet
- * @hwtstamps: hardware time stamps
+ * @hwtstamps: hardware time stamps, may be NULL if not available
  *
  */
 void skb_complete_tx_timestamp(struct sk_buff *skb,
diff --git a/include/linux/sunrpc/rpc_pipe_fs.h b/include/linux/sunrpc/rpc_pipe_fs.h
index cf14db975da..e4ea43058d8 100644
--- a/include/linux/sunrpc/rpc_pipe_fs.h
+++ b/include/linux/sunrpc/rpc_pipe_fs.h
@@ -44,6 +44,8 @@ RPC_I(struct inode *inode)
 	return container_of(inode, struct rpc_inode, vfs_inode);
 }
 
+extern ssize_t rpc_pipe_generic_upcall(struct file *, struct rpc_pipe_msg *,
+				       char __user *, size_t);
 extern int rpc_queue_upcall(struct inode *, struct rpc_pipe_msg *);
 
 struct rpc_clnt;
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index 47b4a27e6e9..d7d0a27d1a0 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -42,6 +42,7 @@ enum thermal_trip_type {
 	THERMAL_TRIP_PASSIVE,
 	THERMAL_TRIP_HOT,
 	THERMAL_TRIP_CRITICAL,
+	THERMAL_TRIP_STATE_ACTIVE,
 };
 
 struct thermal_zone_device_ops {
diff --git a/include/linux/tty.h b/include/linux/tty.h
index 5f2ede82b3d..d553ea4fe09 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -473,7 +473,9 @@ extern void proc_clear_tty(struct task_struct *p);
 extern struct tty_struct *get_current_tty(void);
 extern void tty_default_fops(struct file_operations *fops);
 extern struct tty_struct *alloc_tty_struct(void);
-extern int tty_add_file(struct tty_struct *tty, struct file *file);
+extern int tty_alloc_file(struct file *file);
+extern void tty_add_file(struct tty_struct *tty, struct file *file);
+extern void tty_free_file(struct file *file);
 extern void free_tty_struct(struct tty_struct *tty);
 extern void initialize_tty_struct(struct tty_struct *tty,
 		struct tty_driver *driver, int idx);
diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h
index 0097136ba45..c0ecc5a2ef9 100644
--- a/include/linux/usb/hcd.h
+++ b/include/linux/usb/hcd.h
@@ -178,7 +178,7 @@ struct usb_hcd {
 	 * this structure.
 	 */
 	unsigned long hcd_priv[0]
-			__attribute__ ((aligned(sizeof(unsigned long))));
+			__attribute__ ((aligned(sizeof(s64))));
 };
 
 /* 2.4 does this a bit differently ... */
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 9332e52ea8c..687fb11e201 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -13,6 +13,7 @@ struct vm_area_struct;		/* vma defining user mapping in mm_types.h */
 #define VM_MAP		0x00000004	/* vmap()ed pages */
 #define VM_USERMAP	0x00000008	/* suitable for remap_vmalloc_range */
 #define VM_VPAGES	0x00000010	/* buffer for pages was vmalloc'ed */
+#define VM_UNLIST	0x00000020	/* vm_struct is not listed in vmlist */
 /* bits [20..32] reserved for arch specific ioremap internals */
 
 /*
diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h
index 78c83e62218..e9ff3fc5e68 100644
--- a/include/net/inetpeer.h
+++ b/include/net/inetpeer.h
@@ -35,6 +35,7 @@ struct inet_peer {
 
 	u32			metrics[RTAX_MAX];
 	u32			rate_tokens;	/* rate limiting for ICMP */
+	int			redirect_genid;
 	unsigned long		rate_last;
 	unsigned long		pmtu_expires;
 	u32			pmtu_orig;
diff --git a/include/net/red.h b/include/net/red.h
index 3319f16b3be..b72a3b83393 100644
--- a/include/net/red.h
+++ b/include/net/red.h
@@ -116,7 +116,7 @@ struct red_parms {
 	u32		qR;		/* Cached random number */
 
 	unsigned long	qavg;		/* Average queue length: A scaled */
-	psched_time_t	qidlestart;	/* Start of current idle period */
+	ktime_t		qidlestart;	/* Start of current idle period */
 };
 
 static inline u32 red_rmask(u8 Plog)
@@ -148,17 +148,17 @@ static inline void red_set_parms(struct red_parms *p,
 
 static inline int red_is_idling(struct red_parms *p)
 {
-	return p->qidlestart != PSCHED_PASTPERFECT;
+	return p->qidlestart.tv64 != 0;
 }
 
 static inline void red_start_of_idle_period(struct red_parms *p)
 {
-	p->qidlestart = psched_get_time();
+	p->qidlestart = ktime_get();
 }
 
 static inline void red_end_of_idle_period(struct red_parms *p)
 {
-	p->qidlestart = PSCHED_PASTPERFECT;
+	p->qidlestart.tv64 = 0;
 }
 
 static inline void red_restart(struct red_parms *p)
@@ -170,13 +170,10 @@ static inline void red_restart(struct red_parms *p)
 
 static inline unsigned long red_calc_qavg_from_idle_time(struct red_parms *p)
 {
-	psched_time_t now;
-	long us_idle;
+	s64 delta = ktime_us_delta(ktime_get(), p->qidlestart);
+	long us_idle = min_t(s64, delta, p->Scell_max);
 	int  shift;
 
-	now = psched_get_time();
-	us_idle = psched_tdiff_bounded(now, p->qidlestart, p->Scell_max);
-
 	/*
 	 * The problem: ideally, average length queue recalcultion should
 	 * be done over constant clock intervals. This is too expensive, so
diff --git a/kernel/Makefile b/kernel/Makefile
index eca595e2fd5..988cb3da703 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -101,6 +101,7 @@ obj-$(CONFIG_RING_BUFFER) += trace/
 obj-$(CONFIG_TRACEPOINTS) += trace/
 obj-$(CONFIG_SMP) += sched_cpupri.o
 obj-$(CONFIG_IRQ_WORK) += irq_work.o
+obj-$(CONFIG_CPU_PM) += cpu_pm.o
 
 obj-$(CONFIG_PERF_EVENTS) += events/
 
diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
index e691818d7e4..a3f638ac3de 100644
--- a/kernel/cgroup_freezer.c
+++ b/kernel/cgroup_freezer.c
@@ -153,6 +153,13 @@ static void freezer_destroy(struct cgroup_subsys *ss,
 	kfree(cgroup_freezer(cgroup));
 }
 
+/* task is frozen or will freeze immediately when next it gets woken */
+static bool is_task_frozen_enough(struct task_struct *task)
+{
+	return frozen(task) ||
+		(task_is_stopped_or_traced(task) && freezing(task));
+}
+
 /*
  * The call to cgroup_lock() in the freezer.state write method prevents
  * a write to that file racing against an attach, and hence the
@@ -231,7 +238,7 @@ static void update_if_frozen(struct cgroup *cgroup,
 	cgroup_iter_start(cgroup, &it);
 	while ((task = cgroup_iter_next(cgroup, &it))) {
 		ntotal++;
-		if (frozen(task))
+		if (is_task_frozen_enough(task))
 			nfrozen++;
 	}
 
@@ -284,7 +291,7 @@ static int try_to_freeze_cgroup(struct cgroup *cgroup, struct freezer *freezer)
 	while ((task = cgroup_iter_next(cgroup, &it))) {
 		if (!freeze_task(task, true))
 			continue;
-		if (frozen(task))
+		if (is_task_frozen_enough(task))
 			continue;
 		if (!freezing(task) && !freezer_should_skip(task))
 			num_cant_freeze_now++;
diff --git a/kernel/cpu_pm.c b/kernel/cpu_pm.c
new file mode 100644
index 00000000000..249152e1530
--- /dev/null
+++ b/kernel/cpu_pm.c
@@ -0,0 +1,233 @@
+/*
+ * Copyright (C) 2011 Google, Inc.
+ *
+ * Author:
+ *	Colin Cross <ccross@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/cpu_pm.h>
+#include <linux/module.h>
+#include <linux/notifier.h>
+#include <linux/spinlock.h>
+#include <linux/syscore_ops.h>
+
+static DEFINE_RWLOCK(cpu_pm_notifier_lock);
+static RAW_NOTIFIER_HEAD(cpu_pm_notifier_chain);
+
+static int cpu_pm_notify(enum cpu_pm_event event, int nr_to_call, int *nr_calls)
+{
+	int ret;
+
+	ret = __raw_notifier_call_chain(&cpu_pm_notifier_chain, event, NULL,
+		nr_to_call, nr_calls);
+
+	return notifier_to_errno(ret);
+}
+
+/**
+ * cpu_pm_register_notifier - register a driver with cpu_pm
+ * @nb: notifier block to register
+ *
+ * Add a driver to a list of drivers that are notified about
+ * CPU and CPU cluster low power entry and exit.
+ *
+ * This function may sleep, and has the same return conditions as
+ * raw_notifier_chain_register.
+ */
+int cpu_pm_register_notifier(struct notifier_block *nb)
+{
+	unsigned long flags;
+	int ret;
+
+	write_lock_irqsave(&cpu_pm_notifier_lock, flags);
+	ret = raw_notifier_chain_register(&cpu_pm_notifier_chain, nb);
+	write_unlock_irqrestore(&cpu_pm_notifier_lock, flags);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(cpu_pm_register_notifier);
+
+/**
+ * cpu_pm_unregister_notifier - unregister a driver with cpu_pm
+ * @nb: notifier block to be unregistered
+ *
+ * Remove a driver from the CPU PM notifier list.
+ *
+ * This function may sleep, and has the same return conditions as
+ * raw_notifier_chain_unregister.
+ */
+int cpu_pm_unregister_notifier(struct notifier_block *nb)
+{
+	unsigned long flags;
+	int ret;
+
+	write_lock_irqsave(&cpu_pm_notifier_lock, flags);
+	ret = raw_notifier_chain_unregister(&cpu_pm_notifier_chain, nb);
+	write_unlock_irqrestore(&cpu_pm_notifier_lock, flags);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(cpu_pm_unregister_notifier);
+
+/**
+ * cpm_pm_enter - CPU low power entry notifier
+ *
+ * Notifies listeners that a single CPU is entering a low power state that may
+ * cause some blocks in the same power domain as the cpu to reset.
+ *
+ * Must be called on the affected CPU with interrupts disabled.  Platform is
+ * responsible for ensuring that cpu_pm_enter is not called twice on the same
+ * CPU before cpu_pm_exit is called. Notified drivers can include VFP
+ * co-processor, interrupt controller and it's PM extensions, local CPU
+ * timers context save/restore which shouldn't be interrupted. Hence it
+ * must be called with interrupts disabled.
+ *
+ * Return conditions are same as __raw_notifier_call_chain.
+ */
+int cpu_pm_enter(void)
+{
+	int nr_calls;
+	int ret = 0;
+
+	read_lock(&cpu_pm_notifier_lock);
+	ret = cpu_pm_notify(CPU_PM_ENTER, -1, &nr_calls);
+	if (ret)
+		/*
+		 * Inform listeners (nr_calls - 1) about failure of CPU PM
+		 * PM entry who are notified earlier to prepare for it.
+		 */
+		cpu_pm_notify(CPU_PM_ENTER_FAILED, nr_calls - 1, NULL);
+	read_unlock(&cpu_pm_notifier_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(cpu_pm_enter);
+
+/**
+ * cpm_pm_exit - CPU low power exit notifier
+ *
+ * Notifies listeners that a single CPU is exiting a low power state that may
+ * have caused some blocks in the same power domain as the cpu to reset.
+ *
+ * Notified drivers can include VFP co-processor, interrupt controller
+ * and it's PM extensions, local CPU timers context save/restore which
+ * shouldn't be interrupted. Hence it must be called with interrupts disabled.
+ *
+ * Return conditions are same as __raw_notifier_call_chain.
+ */
+int cpu_pm_exit(void)
+{
+	int ret;
+
+	read_lock(&cpu_pm_notifier_lock);
+	ret = cpu_pm_notify(CPU_PM_EXIT, -1, NULL);
+	read_unlock(&cpu_pm_notifier_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(cpu_pm_exit);
+
+/**
+ * cpm_cluster_pm_enter - CPU cluster low power entry notifier
+ *
+ * Notifies listeners that all cpus in a power domain are entering a low power
+ * state that may cause some blocks in the same power domain to reset.
+ *
+ * Must be called after cpu_pm_enter has been called on all cpus in the power
+ * domain, and before cpu_pm_exit has been called on any cpu in the power
+ * domain. Notified drivers can include VFP co-processor, interrupt controller
+ * and it's PM extensions, local CPU timers context save/restore which
+ * shouldn't be interrupted. Hence it must be called with interrupts disabled.
+ *
+ * Must be called with interrupts disabled.
+ *
+ * Return conditions are same as __raw_notifier_call_chain.
+ */
+int cpu_cluster_pm_enter(void)
+{
+	int nr_calls;
+	int ret = 0;
+
+	read_lock(&cpu_pm_notifier_lock);
+	ret = cpu_pm_notify(CPU_CLUSTER_PM_ENTER, -1, &nr_calls);
+	if (ret)
+		/*
+		 * Inform listeners (nr_calls - 1) about failure of CPU cluster
+		 * PM entry who are notified earlier to prepare for it.
+		 */
+		cpu_pm_notify(CPU_CLUSTER_PM_ENTER_FAILED, nr_calls - 1, NULL);
+	read_unlock(&cpu_pm_notifier_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(cpu_cluster_pm_enter);
+
+/**
+ * cpm_cluster_pm_exit - CPU cluster low power exit notifier
+ *
+ * Notifies listeners that all cpus in a power domain are exiting form a
+ * low power state that may have caused some blocks in the same power domain
+ * to reset.
+ *
+ * Must be called after cpu_pm_exit has been called on all cpus in the power
+ * domain, and before cpu_pm_exit has been called on any cpu in the power
+ * domain. Notified drivers can include VFP co-processor, interrupt controller
+ * and it's PM extensions, local CPU timers context save/restore which
+ * shouldn't be interrupted. Hence it must be called with interrupts disabled.
+ *
+ * Return conditions are same as __raw_notifier_call_chain.
+ */
+int cpu_cluster_pm_exit(void)
+{
+	int ret;
+
+	read_lock(&cpu_pm_notifier_lock);
+	ret = cpu_pm_notify(CPU_CLUSTER_PM_EXIT, -1, NULL);
+	read_unlock(&cpu_pm_notifier_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(cpu_cluster_pm_exit);
+
+#ifdef CONFIG_PM
+static int cpu_pm_suspend(void)
+{
+	int ret;
+
+	ret = cpu_pm_enter();
+	if (ret)
+		return ret;
+
+	ret = cpu_cluster_pm_enter();
+	return ret;
+}
+
+static void cpu_pm_resume(void)
+{
+	cpu_cluster_pm_exit();
+	cpu_pm_exit();
+}
+
+static struct syscore_ops cpu_pm_syscore_ops = {
+	.suspend = cpu_pm_suspend,
+	.resume = cpu_pm_resume,
+};
+
+static int cpu_pm_init(void)
+{
+	register_syscore_ops(&cpu_pm_syscore_ops);
+	return 0;
+}
+core_initcall(cpu_pm_init);
+#endif
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 0f857782d06..fbe38f2e8ed 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5758,6 +5758,7 @@ struct pmu *perf_init_event(struct perf_event *event)
 	pmu = idr_find(&pmu_idr, event->attr.type);
 	rcu_read_unlock();
 	if (pmu) {
+		event->pmu = pmu;
 		ret = pmu->event_init(event);
 		if (ret)
 			pmu = ERR_PTR(ret);
@@ -5765,6 +5766,7 @@ struct pmu *perf_init_event(struct perf_event *event)
 	}
 
 	list_for_each_entry_rcu(pmu, &pmus, entry) {
+		event->pmu = pmu;
 		ret = pmu->event_init(event);
 		if (!ret)
 			goto unlock;
@@ -5891,8 +5893,6 @@ done:
 		return ERR_PTR(err);
 	}
 
-	event->pmu = pmu;
-
 	if (!event->parent) {
 		if (event->attach_state & PERF_ATTACH_TASK)
 			jump_label_inc(&perf_sched_events);
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index a9205e32a05..2043c08d36c 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -885,10 +885,13 @@ static void __remove_hrtimer(struct hrtimer *timer,
 			     struct hrtimer_clock_base *base,
 			     unsigned long newstate, int reprogram)
 {
+	struct timerqueue_node *next_timer;
 	if (!(timer->state & HRTIMER_STATE_ENQUEUED))
 		goto out;
 
-	if (&timer->node == timerqueue_getnext(&base->active)) {
+	next_timer = timerqueue_getnext(&base->active);
+	timerqueue_del(&base->active, &timer->node);
+	if (&timer->node == next_timer) {
 #ifdef CONFIG_HIGH_RES_TIMERS
 		/* Reprogram the clock event device. if enabled */
 		if (reprogram && hrtimer_hres_active()) {
@@ -901,7 +904,6 @@ static void __remove_hrtimer(struct hrtimer *timer,
 		}
 #endif
 	}
-	timerqueue_del(&base->active, &timer->node);
 	if (!timerqueue_getnext(&base->active))
 		base->cpu_base->active_bases &= ~(1 << base->index);
 out:
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 9b956fa2030..d6c4adc2804 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -620,8 +620,9 @@ static irqreturn_t irq_nested_primary_handler(int irq, void *dev_id)
 
 static int irq_wait_for_interrupt(struct irqaction *action)
 {
+	set_current_state(TASK_INTERRUPTIBLE);
+
 	while (!kthread_should_stop()) {
-		set_current_state(TASK_INTERRUPTIBLE);
 
 		if (test_and_clear_bit(IRQTF_RUNTHREAD,
 				       &action->thread_flags)) {
@@ -629,7 +630,9 @@ static int irq_wait_for_interrupt(struct irqaction *action)
 			return 0;
 		}
 		schedule();
+		set_current_state(TASK_INTERRUPTIBLE);
 	}
+	__set_current_state(TASK_RUNNING);
 	return -1;
 }
 
diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c
index f76fc00c987..15e53b1766a 100644
--- a/kernel/irq/pm.c
+++ b/kernel/irq/pm.c
@@ -9,6 +9,7 @@
 #include <linux/irq.h>
 #include <linux/module.h>
 #include <linux/interrupt.h>
+#include <linux/syscore_ops.h>
 
 #include "internals.h"
 
@@ -39,25 +40,58 @@ void suspend_device_irqs(void)
 }
 EXPORT_SYMBOL_GPL(suspend_device_irqs);
 
-/**
- * resume_device_irqs - enable interrupt lines disabled by suspend_device_irqs()
- *
- * Enable all interrupt lines previously disabled by suspend_device_irqs() that
- * have the IRQS_SUSPENDED flag set.
- */
-void resume_device_irqs(void)
+static void resume_irqs(bool want_early)
 {
 	struct irq_desc *desc;
 	int irq;
 
 	for_each_irq_desc(irq, desc) {
 		unsigned long flags;
+		bool is_early = desc->action &&
+			desc->action->flags & IRQF_EARLY_RESUME;
+
+		if (is_early != want_early)
+			continue;
 
 		raw_spin_lock_irqsave(&desc->lock, flags);
 		__enable_irq(desc, irq, true);
 		raw_spin_unlock_irqrestore(&desc->lock, flags);
 	}
 }
+
+/**
+ * irq_pm_syscore_ops - enable interrupt lines early
+ *
+ * Enable all interrupt lines with %IRQF_EARLY_RESUME set.
+ */
+static void irq_pm_syscore_resume(void)
+{
+	resume_irqs(true);
+}
+
+static struct syscore_ops irq_pm_syscore_ops = {
+	.resume		= irq_pm_syscore_resume,
+};
+
+static int __init irq_pm_init_ops(void)
+{
+	register_syscore_ops(&irq_pm_syscore_ops);
+	return 0;
+}
+
+device_initcall(irq_pm_init_ops);
+
+/**
+ * resume_device_irqs - enable interrupt lines disabled by suspend_device_irqs()
+ *
+ * Enable all non-%IRQF_EARLY_RESUME interrupt lines previously
+ * disabled by suspend_device_irqs() that have the IRQS_SUSPENDED flag
+ * set as well as those with %IRQF_FORCE_RESUME.
+ */
+void resume_device_irqs(void)
+{
+	resume_irqs(false);
+}
 EXPORT_SYMBOL_GPL(resume_device_irqs);
 
 /**
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index aa57d5da18c..dc813a948be 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -84,7 +84,9 @@ static int try_one_irq(int irq, struct irq_desc *desc, bool force)
 	 */
 	action = desc->action;
 	if (!action || !(action->flags & IRQF_SHARED) ||
-	    (action->flags & __IRQF_TIMER) || !action->next)
+	    (action->flags & __IRQF_TIMER) ||
+	    (action->handler(irq, action->dev_id) == IRQ_HANDLED) ||
+	    !action->next)
 		goto out;
 
 	/* Already running on another processor */
@@ -115,7 +117,7 @@ static int misrouted_irq(int irq)
 	struct irq_desc *desc;
 	int i, ok = 0;
 
-	if (atomic_inc_return(&irq_poll_active) == 1)
+	if (atomic_inc_return(&irq_poll_active) != 1)
 		goto out;
 
 	irq_poll_cpu = smp_processor_id();
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index a8ce45097f3..e6f1f24ad57 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -66,8 +66,9 @@ void jump_label_inc(struct jump_label_key *key)
 		return;
 
 	jump_label_lock();
-	if (atomic_add_return(1, &key->enabled) == 1)
+	if (atomic_read(&key->enabled) == 0)
 		jump_label_update(key, JUMP_LABEL_ENABLE);
+	atomic_inc(&key->enabled);
 	jump_label_unlock();
 }
 
diff --git a/kernel/kmod.c b/kernel/kmod.c
index ddc7644c130..a4bea97c75b 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -114,10 +114,12 @@ int __request_module(bool wait, const char *fmt, ...)
 	atomic_inc(&kmod_concurrent);
 	if (atomic_read(&kmod_concurrent) > max_modprobes) {
 		/* We may be blaming an innocent here, but unlikely */
-		if (kmod_loop_msg++ < 5)
+		if (kmod_loop_msg < 5) {
 			printk(KERN_ERR
 			       "request_module: runaway loop modprobe %s\n",
 			       module_name);
+			kmod_loop_msg++;
+		}
 		atomic_dec(&kmod_concurrent);
 		return -ENOMEM;
 	}
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 3744c594b19..80a85971cf6 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -235,3 +235,7 @@ config PM_GENERIC_DOMAINS
 config PM_GENERIC_DOMAINS_RUNTIME
 	def_bool y
 	depends on PM_RUNTIME && PM_GENERIC_DOMAINS
+
+config CPU_PM
+	bool
+	depends on SUSPEND || CPU_IDLE
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index b6b71ad2208..d3caa763498 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -315,7 +315,7 @@ int enter_state(suspend_state_t state)
  */
 int pm_suspend(suspend_state_t state)
 {
-	if (state > PM_SUSPEND_ON && state <= PM_SUSPEND_MAX)
+	if (state > PM_SUSPEND_ON && state < PM_SUSPEND_MAX)
 		return enter_state(state);
 	return -EINVAL;
 }
diff --git a/kernel/sched.c b/kernel/sched.c
index b50b0f0c9aa..036311afeed 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -510,7 +510,7 @@ struct rq {
 
 	unsigned long cpu_power;
 
-	unsigned char idle_at_tick;
+	unsigned char idle_balance;
 	/* For active balancing */
 	int post_schedule;
 	int active_balance;
@@ -1272,6 +1272,18 @@ void wake_up_idle_cpu(int cpu)
 		smp_send_reschedule(cpu);
 }
 
+static inline bool got_nohz_idle_kick(void)
+{
+	return idle_cpu(smp_processor_id()) && this_rq()->nohz_balance_kick;
+}
+
+#else /* CONFIG_NO_HZ */
+
+static inline bool got_nohz_idle_kick(void)
+{
+	return false;
+}
+
 #endif /* CONFIG_NO_HZ */
 
 static u64 sched_avg_period(void)
@@ -2591,7 +2603,7 @@ void scheduler_ipi(void)
 	struct rq *rq = this_rq();
 	struct task_struct *list = xchg(&rq->wake_list, NULL);
 
-	if (!list)
+	if ((!list) && !got_nohz_idle_kick())
 		return;
 
 	/*
@@ -2609,6 +2621,14 @@ void scheduler_ipi(void)
 	 */
 	irq_enter();
 	sched_ttwu_do_pending(list);
+
+	/*
+	 * Check if someone kicked us for doing the nohz idle load balance.
+	 */
+	if (unlikely(got_nohz_idle_kick() && !need_resched())) {
+		this_rq()->idle_balance = 1;
+		raise_softirq_irqoff(SCHED_SOFTIRQ);
+	}
 	irq_exit();
 }
 
@@ -4116,7 +4136,7 @@ void scheduler_tick(void)
 	perf_event_task_tick();
 
 #ifdef CONFIG_SMP
-	rq->idle_at_tick = idle_cpu(cpu);
+	rq->idle_balance = idle_cpu(cpu);
 	trigger_load_balance(rq, cpu);
 #endif
 }
@@ -8133,7 +8153,6 @@ void __init sched_init(void)
 		rq_attach_root(rq, &def_root_domain);
 #ifdef CONFIG_NO_HZ
 		rq->nohz_balance_kick = 0;
-		init_sched_softirq_csd(&per_cpu(remote_sched_softirq_cb, i));
 #endif
 #endif
 		init_rq_hrtick(rq);
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index bc8ee999381..2107c3c3049 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -91,6 +91,8 @@ unsigned int __read_mostly sysctl_sched_shares_window = 10000000UL;
 
 static const struct sched_class fair_sched_class;
 
+static unsigned long __read_mostly max_load_balance_interval = HZ/10;
+
 /**************************************************************
  * CFS operations on generic schedulable entities:
  */
@@ -2667,6 +2669,11 @@ static void update_group_power(struct sched_domain *sd, int cpu)
 	struct sched_domain *child = sd->child;
 	struct sched_group *group, *sdg = sd->groups;
 	unsigned long power;
+	unsigned long interval;
+
+	interval = msecs_to_jiffies(sd->balance_interval);
+	interval = clamp(interval, 1UL, max_load_balance_interval);
+	sdg->sgp->next_update = jiffies + interval;
 
 	if (!child) {
 		update_cpu_power(sd, cpu);
@@ -2774,12 +2781,15 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
 	 * domains. In the newly idle case, we will allow all the cpu's
 	 * to do the newly idle load balance.
 	 */
-	if (idle != CPU_NEWLY_IDLE && local_group) {
-		if (balance_cpu != this_cpu) {
-			*balance = 0;
-			return;
-		}
-		update_group_power(sd, this_cpu);
+	if (local_group) {
+		if (idle != CPU_NEWLY_IDLE) {
+			if (balance_cpu != this_cpu) {
+				*balance = 0;
+				return;
+			}
+			update_group_power(sd, this_cpu);
+		} else if (time_after_eq(jiffies, group->sgp->next_update))
+			update_group_power(sd, this_cpu);
 	}
 
 	/* Adjust by relative CPU power of the group */
@@ -3612,22 +3622,6 @@ out_unlock:
 }
 
 #ifdef CONFIG_NO_HZ
-
-static DEFINE_PER_CPU(struct call_single_data, remote_sched_softirq_cb);
-
-static void trigger_sched_softirq(void *data)
-{
-	raise_softirq_irqoff(SCHED_SOFTIRQ);
-}
-
-static inline void init_sched_softirq_csd(struct call_single_data *csd)
-{
-	csd->func = trigger_sched_softirq;
-	csd->info = NULL;
-	csd->flags = 0;
-	csd->priv = 0;
-}
-
 /*
  * idle load balancing details
  * - One of the idle CPUs nominates itself as idle load_balancer, while
@@ -3793,11 +3787,16 @@ static void nohz_balancer_kick(int cpu)
 	}
 
 	if (!cpu_rq(ilb_cpu)->nohz_balance_kick) {
-		struct call_single_data *cp;
-
 		cpu_rq(ilb_cpu)->nohz_balance_kick = 1;
-		cp = &per_cpu(remote_sched_softirq_cb, cpu);
-		__smp_call_function_single(ilb_cpu, cp, 0);
+
+		smp_mb();
+		/*
+		 * Use smp_send_reschedule() instead of resched_cpu().
+		 * This way we generate a sched IPI on the target cpu which
+		 * is idle. And the softirq performing nohz idle load balance
+		 * will be run before returning from the IPI.
+		 */
+		smp_send_reschedule(ilb_cpu);
 	}
 	return;
 }
@@ -3879,8 +3878,6 @@ void select_nohz_load_balancer(int stop_tick)
 
 static DEFINE_SPINLOCK(balancing);
 
-static unsigned long __read_mostly max_load_balance_interval = HZ/10;
-
 /*
  * Scale the max load_balance interval with the number of CPUs in the system.
  * This trades load-balance latency on larger machines for less cross talk.
@@ -4030,7 +4027,7 @@ static inline int nohz_kick_needed(struct rq *rq, int cpu)
 	if (time_before(now, nohz.next_balance))
 		return 0;
 
-	if (rq->idle_at_tick)
+	if (idle_cpu(cpu))
 		return 0;
 
 	first_pick_cpu = atomic_read(&nohz.first_pick_cpu);
@@ -4066,7 +4063,7 @@ static void run_rebalance_domains(struct softirq_action *h)
 {
 	int this_cpu = smp_processor_id();
 	struct rq *this_rq = cpu_rq(this_cpu);
-	enum cpu_idle_type idle = this_rq->idle_at_tick ?
+	enum cpu_idle_type idle = this_rq->idle_balance ?
 						CPU_IDLE : CPU_NOT_IDLE;
 
 	rebalance_domains(this_cpu, idle);
diff --git a/kernel/sched_features.h b/kernel/sched_features.h
index 2e74677cb04..85f8bd92a64 100644
--- a/kernel/sched_features.h
+++ b/kernel/sched_features.h
@@ -47,7 +47,7 @@ SCHED_FEAT(CACHE_HOT_BUDDY, 1)
 /*
  * Use arch dependent cpu power functions
  */
-SCHED_FEAT(ARCH_POWER, 0)
+SCHED_FEAT(ARCH_POWER, 1)
 
 SCHED_FEAT(HRTICK, 0)
 SCHED_FEAT(DOUBLE_TICK, 0)
diff --git a/kernel/time.c b/kernel/time.c
index 8e8dc6d705c..d7760621452 100644
--- a/kernel/time.c
+++ b/kernel/time.c
@@ -575,7 +575,7 @@ EXPORT_SYMBOL(jiffies_to_timeval);
 /*
  * Convert jiffies/jiffies_64 to clock_t and back.
  */
-clock_t jiffies_to_clock_t(long x)
+clock_t jiffies_to_clock_t(unsigned long x)
 {
 #if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0
 # if HZ < USER_HZ
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index e4c699dfa4e..13dfaaba406 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -286,6 +286,7 @@ void clockevents_exchange_device(struct clock_event_device *old,
 	 * released list and do a notify add later.
 	 */
 	if (old) {
+		old->event_handler = clockevents_handle_noop;
 		clockevents_set_mode(old, CLOCK_EVT_MODE_UNUSED);
 		list_del(&old->list);
 		list_add(&old->list, &clockevents_released);
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index e0980f0d9a0..8f77da18fef 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -494,6 +494,22 @@ void clocksource_touch_watchdog(void)
 }
 
 /**
+ * clocksource_max_adjustment- Returns max adjustment amount
+ * @cs:         Pointer to clocksource
+ *
+ */
+static u32 clocksource_max_adjustment(struct clocksource *cs)
+{
+	u64 ret;
+	/*
+	 * We won't try to correct for more then 11% adjustments (110,000 ppm),
+	 */
+	ret = (u64)cs->mult * 11;
+	do_div(ret,100);
+	return (u32)ret;
+}
+
+/**
  * clocksource_max_deferment - Returns max time the clocksource can be deferred
  * @cs:         Pointer to clocksource
  *
@@ -505,25 +521,28 @@ static u64 clocksource_max_deferment(struct clocksource *cs)
 	/*
 	 * Calculate the maximum number of cycles that we can pass to the
 	 * cyc2ns function without overflowing a 64-bit signed result. The
-	 * maximum number of cycles is equal to ULLONG_MAX/cs->mult which
-	 * is equivalent to the below.
-	 * max_cycles < (2^63)/cs->mult
-	 * max_cycles < 2^(log2((2^63)/cs->mult))
-	 * max_cycles < 2^(log2(2^63) - log2(cs->mult))
-	 * max_cycles < 2^(63 - log2(cs->mult))
-	 * max_cycles < 1 << (63 - log2(cs->mult))
+	 * maximum number of cycles is equal to ULLONG_MAX/(cs->mult+cs->maxadj)
+	 * which is equivalent to the below.
+	 * max_cycles < (2^63)/(cs->mult + cs->maxadj)
+	 * max_cycles < 2^(log2((2^63)/(cs->mult + cs->maxadj)))
+	 * max_cycles < 2^(log2(2^63) - log2(cs->mult + cs->maxadj))
+	 * max_cycles < 2^(63 - log2(cs->mult + cs->maxadj))
+	 * max_cycles < 1 << (63 - log2(cs->mult + cs->maxadj))
 	 * Please note that we add 1 to the result of the log2 to account for
 	 * any rounding errors, ensure the above inequality is satisfied and
 	 * no overflow will occur.
 	 */
-	max_cycles = 1ULL << (63 - (ilog2(cs->mult) + 1));
+	max_cycles = 1ULL << (63 - (ilog2(cs->mult + cs->maxadj) + 1));
 
 	/*
 	 * The actual maximum number of cycles we can defer the clocksource is
 	 * determined by the minimum of max_cycles and cs->mask.
+	 * Note: Here we subtract the maxadj to make sure we don't sleep for
+	 * too long if there's a large negative adjustment.
 	 */
 	max_cycles = min_t(u64, max_cycles, (u64) cs->mask);
-	max_nsecs = clocksource_cyc2ns(max_cycles, cs->mult, cs->shift);
+	max_nsecs = clocksource_cyc2ns(max_cycles, cs->mult - cs->maxadj,
+					cs->shift);
 
 	/*
 	 * To ensure that the clocksource does not wrap whilst we are idle,
@@ -531,7 +550,7 @@ static u64 clocksource_max_deferment(struct clocksource *cs)
 	 * note a margin of 12.5% is used because this can be computed with
 	 * a shift, versus say 10% which would require division.
 	 */
-	return max_nsecs - (max_nsecs >> 5);
+	return max_nsecs - (max_nsecs >> 3);
 }
 
 #ifndef CONFIG_ARCH_USES_GETTIMEOFFSET
@@ -642,7 +661,6 @@ static void clocksource_enqueue(struct clocksource *cs)
 void __clocksource_updatefreq_scale(struct clocksource *cs, u32 scale, u32 freq)
 {
 	u64 sec;
-
 	/*
 	 * Calc the maximum number of seconds which we can run before
 	 * wrapping around. For clocksources which have a mask > 32bit
@@ -653,7 +671,7 @@ void __clocksource_updatefreq_scale(struct clocksource *cs, u32 scale, u32 freq)
 	 * ~ 0.06ppm granularity for NTP. We apply the same 12.5%
 	 * margin as we do in clocksource_max_deferment()
 	 */
-	sec = (cs->mask - (cs->mask >> 5));
+	sec = (cs->mask - (cs->mask >> 3));
 	do_div(sec, freq);
 	do_div(sec, scale);
 	if (!sec)
@@ -663,6 +681,20 @@ void __clocksource_updatefreq_scale(struct clocksource *cs, u32 scale, u32 freq)
 
 	clocks_calc_mult_shift(&cs->mult, &cs->shift, freq,
 			       NSEC_PER_SEC / scale, sec * scale);
+
+	/*
+	 * for clocksources that have large mults, to avoid overflow.
+	 * Since mult may be adjusted by ntp, add an safety extra margin
+	 *
+	 */
+	cs->maxadj = clocksource_max_adjustment(cs);
+	while ((cs->mult + cs->maxadj < cs->mult)
+		|| (cs->mult - cs->maxadj > cs->mult)) {
+		cs->mult >>= 1;
+		cs->shift--;
+		cs->maxadj = clocksource_max_adjustment(cs);
+	}
+
 	cs->max_idle_ns = clocksource_max_deferment(cs);
 }
 EXPORT_SYMBOL_GPL(__clocksource_updatefreq_scale);
@@ -703,6 +735,12 @@ EXPORT_SYMBOL_GPL(__clocksource_register_scale);
  */
 int clocksource_register(struct clocksource *cs)
 {
+	/* calculate max adjustment for given mult/shift */
+	cs->maxadj = clocksource_max_adjustment(cs);
+	WARN_ONCE(cs->mult + cs->maxadj < cs->mult,
+		"Clocksource %s might overflow on 11%% adjustment\n",
+		cs->name);
+
 	/* calculate max idle time permitted for this clocksource */
 	cs->max_idle_ns = clocksource_max_deferment(cs);
 
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index c7218d13273..7a90d021b79 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -71,7 +71,7 @@ int tick_check_broadcast_device(struct clock_event_device *dev)
 	     (dev->features & CLOCK_EVT_FEAT_C3STOP))
 		return 0;
 
-	clockevents_exchange_device(NULL, dev);
+	clockevents_exchange_device(tick_broadcast_device.evtdev, dev);
 	tick_broadcast_device.evtdev = dev;
 	if (!cpumask_empty(tick_get_broadcast_mask()))
 		tick_broadcast_start_periodic(dev);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 2b021b0e850..6f9798bf240 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -249,6 +249,8 @@ ktime_t ktime_get(void)
 		secs = xtime.tv_sec + wall_to_monotonic.tv_sec;
 		nsecs = xtime.tv_nsec + wall_to_monotonic.tv_nsec;
 		nsecs += timekeeping_get_ns();
+		/* If arch requires, add in gettimeoffset() */
+		nsecs += arch_gettimeoffset();
 
 	} while (read_seqretry(&xtime_lock, seq));
 	/*
@@ -280,6 +282,8 @@ void ktime_get_ts(struct timespec *ts)
 		*ts = xtime;
 		tomono = wall_to_monotonic;
 		nsecs = timekeeping_get_ns();
+		/* If arch requires, add in gettimeoffset() */
+		nsecs += arch_gettimeoffset();
 
 	} while (read_seqretry(&xtime_lock, seq));
 
@@ -820,6 +824,13 @@ static void timekeeping_adjust(s64 offset)
 	} else
 		return;
 
+	WARN_ONCE(timekeeper.clock->maxadj &&
+			(timekeeper.mult + adj > timekeeper.clock->mult +
+						timekeeper.clock->maxadj),
+			"Adjusting %s more then 11%% (%ld vs %ld)\n",
+			timekeeper.clock->name, (long)timekeeper.mult + adj,
+			(long)timekeeper.clock->mult +
+				timekeeper.clock->maxadj);
 	timekeeper.mult += adj;
 	timekeeper.xtime_interval += interval;
 	timekeeper.xtime_nsec -= offset;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index c3e4575e782..48d3762b828 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -151,7 +151,6 @@ void clear_ftrace_function(void)
 	ftrace_pid_function = ftrace_stub;
 }
 
-#undef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
 #ifndef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
 /*
  * For those archs that do not test ftrace_trace_stop in their
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index e7aa00caa38..3c9b9686be2 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3817,8 +3817,6 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 	if (info->read < PAGE_SIZE)
 		goto read;
 
-	info->read = 0;
-
 	trace_access_lock(info->cpu);
 	ret = ring_buffer_read_page(info->tr->buffer,
 				    &info->spare,
@@ -3828,6 +3826,8 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 	if (ret < 0)
 		return 0;
 
+	info->read = 0;
+
 read:
 	size = PAGE_SIZE - info->read;
 	if (size > count)
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index b066c6dd41a..773cb84adc8 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1079,7 +1079,6 @@ event_subsystem_dir(const char *name, struct dentry *d_events)
 	/* First see if we did not already create this dir */
 	list_for_each_entry(system, &event_subsystems, list) {
 		if (strcmp(system->name, name) == 0) {
-			__get_system(system);
 			system->nr_events++;
 			return system->entry;
 		}
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 256764ecccd..bd3c6369f80 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -1766,7 +1766,7 @@ static int replace_system_preds(struct event_subsystem *system,
 		 * replace the filter for the call.
 		 */
 		filter = call->filter;
-		call->filter = filter_item->filter;
+		rcu_assign_pointer(call->filter, filter_item->filter);
 		filter_item->filter = filter;
 
 		fail = false;
@@ -1821,7 +1821,7 @@ int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
 		filter = call->filter;
 		if (!filter)
 			goto out_unlock;
-		call->filter = NULL;
+		RCU_INIT_POINTER(call->filter, NULL);
 		/* Make sure the filter is not being used */
 		synchronize_sched();
 		__free_filter(filter);
@@ -1862,7 +1862,7 @@ out:
 	 * string
 	 */
 	tmp = call->filter;
-	call->filter = filter;
+	rcu_assign_pointer(call->filter, filter);
 	if (tmp) {
 		/* Make sure the call is done with the filter */
 		synchronize_sched();
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 5fb3697bf0e..00d527c945a 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -836,11 +836,17 @@ static void __unregister_trace_probe(struct trace_probe *tp)
 }
 
 /* Unregister a trace_probe and probe_event: call with locking probe_lock */
-static void unregister_trace_probe(struct trace_probe *tp)
+static int unregister_trace_probe(struct trace_probe *tp)
 {
+	/* Enabled event can not be unregistered */
+	if (trace_probe_is_enabled(tp))
+		return -EBUSY;
+
 	__unregister_trace_probe(tp);
 	list_del(&tp->list);
 	unregister_probe_event(tp);
+
+	return 0;
 }
 
 /* Register a trace_probe and probe_event */
@@ -854,7 +860,9 @@ static int register_trace_probe(struct trace_probe *tp)
 	/* Delete old (same name) event if exist */
 	old_tp = find_trace_probe(tp->call.name, tp->call.class->system);
 	if (old_tp) {
-		unregister_trace_probe(old_tp);
+		ret = unregister_trace_probe(old_tp);
+		if (ret < 0)
+			goto end;
 		free_trace_probe(old_tp);
 	}
 
@@ -892,6 +900,7 @@ static int trace_probe_module_callback(struct notifier_block *nb,
 	mutex_lock(&probe_lock);
 	list_for_each_entry(tp, &probe_list, list) {
 		if (trace_probe_within_module(tp, mod)) {
+			/* Don't need to check busy - this should have gone. */
 			__unregister_trace_probe(tp);
 			ret = __register_trace_probe(tp);
 			if (ret)
@@ -1205,10 +1214,11 @@ static int create_trace_probe(int argc, char **argv)
 			return -ENOENT;
 		}
 		/* delete an event */
-		unregister_trace_probe(tp);
-		free_trace_probe(tp);
+		ret = unregister_trace_probe(tp);
+		if (ret == 0)
+			free_trace_probe(tp);
 		mutex_unlock(&probe_lock);
-		return 0;
+		return ret;
 	}
 
 	if (argc < 2) {
@@ -1317,18 +1327,29 @@ error:
 	return ret;
 }
 
-static void release_all_trace_probes(void)
+static int release_all_trace_probes(void)
 {
 	struct trace_probe *tp;
+	int ret = 0;
 
 	mutex_lock(&probe_lock);
+	/* Ensure no probe is in use. */
+	list_for_each_entry(tp, &probe_list, list)
+		if (trace_probe_is_enabled(tp)) {
+			ret = -EBUSY;
+			goto end;
+		}
 	/* TODO: Use batch unregistration */
 	while (!list_empty(&probe_list)) {
 		tp = list_entry(probe_list.next, struct trace_probe, list);
 		unregister_trace_probe(tp);
 		free_trace_probe(tp);
 	}
+
+end:
 	mutex_unlock(&probe_lock);
+
+	return ret;
 }
 
 /* Probes listing interfaces */
@@ -1380,9 +1401,13 @@ static const struct seq_operations probes_seq_op = {
 
 static int probes_open(struct inode *inode, struct file *file)
 {
-	if ((file->f_mode & FMODE_WRITE) &&
-	    (file->f_flags & O_TRUNC))
-		release_all_trace_probes();
+	int ret;
+
+	if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) {
+		ret = release_all_trace_probes();
+		if (ret < 0)
+			return ret;
+	}
 
 	return seq_open(file, &probes_seq_op);
 }
@@ -2055,6 +2080,21 @@ static __init int kprobe_trace_self_tests_init(void)
 
 	ret = target(1, 2, 3, 4, 5, 6);
 
+	/* Disable trace points before removing it */
+	tp = find_trace_probe("testprobe", KPROBE_EVENT_SYSTEM);
+	if (WARN_ON_ONCE(tp == NULL)) {
+		pr_warning("error on getting test probe.\n");
+		warn++;
+	} else
+		disable_trace_probe(tp, TP_FLAG_TRACE);
+
+	tp = find_trace_probe("testprobe2", KPROBE_EVENT_SYSTEM);
+	if (WARN_ON_ONCE(tp == NULL)) {
+		pr_warning("error on getting 2nd test probe.\n");
+		warn++;
+	} else
+		disable_trace_probe(tp, TP_FLAG_TRACE);
+
 	ret = command_trace_probe("-:testprobe");
 	if (WARN_ON_ONCE(ret)) {
 		pr_warning("error on deleting a probe.\n");
diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c
index 70af0a7f97c..ad72a03ce5e 100644
--- a/lib/kobject_uevent.c
+++ b/lib/kobject_uevent.c
@@ -282,7 +282,7 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action,
 							    kobj_bcast_filter,
 							    kobj);
 			/* ENOBUFS should be handled in userspace */
-			if (retval == -ENOBUFS)
+			if (retval == -ENOBUFS || retval == -ESRCH)
 				retval = 0;
 		} else
 			retval = -ENOMEM;
diff --git a/lib/nlattr.c b/lib/nlattr.c
index ac09f2226dc..a8408b6cacd 100644
--- a/lib/nlattr.c
+++ b/lib/nlattr.c
@@ -20,6 +20,7 @@ static const u16 nla_attr_minlen[NLA_TYPE_MAX+1] = {
 	[NLA_U16]	= sizeof(u16),
 	[NLA_U32]	= sizeof(u32),
 	[NLA_U64]	= sizeof(u64),
+	[NLA_MSECS]	= sizeof(u64),
 	[NLA_NESTED]	= NLA_HDRLEN,
 };
 
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index a87da524a4a..253b071b7d9 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -720,6 +720,14 @@ void bdi_destroy(struct backing_dev_info *bdi)
 
 	bdi_unregister(bdi);
 
+	/*
+	 * If bdi_unregister() had already been called earlier, the
+	 * wakeup_timer could still be armed because bdi_prune_sb()
+	 * can race with the bdi_wakeup_thread_delayed() calls from
+	 * __mark_inode_dirty().
+	 */
+	del_timer_sync(&bdi->wb.wakeup_timer);
+
 	for (i = 0; i < NR_BDI_STAT_ITEMS; i++)
 		percpu_counter_destroy(&bdi->bdi_stat[i]);
 
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index e2d1587be26..d819d938288 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -989,7 +989,7 @@ struct page *follow_trans_huge_pmd(struct mm_struct *mm,
 	page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT;
 	VM_BUG_ON(!PageCompound(page));
 	if (flags & FOLL_GET)
-		get_page(page);
+		get_page_foll(page);
 
 out:
 	return page;
@@ -1156,6 +1156,7 @@ static void __split_huge_page_refcount(struct page *page)
 	unsigned long head_index = page->index;
 	struct zone *zone = page_zone(page);
 	int zonestat;
+	int tail_count = 0;
 
 	/* prevent PageLRU to go away from under us, and freeze lru stats */
 	spin_lock_irq(&zone->lru_lock);
@@ -1164,11 +1165,27 @@ static void __split_huge_page_refcount(struct page *page)
 	for (i = 1; i < HPAGE_PMD_NR; i++) {
 		struct page *page_tail = page + i;
 
-		/* tail_page->_count cannot change */
-		atomic_sub(atomic_read(&page_tail->_count), &page->_count);
-		BUG_ON(page_count(page) <= 0);
-		atomic_add(page_mapcount(page) + 1, &page_tail->_count);
-		BUG_ON(atomic_read(&page_tail->_count) <= 0);
+		/* tail_page->_mapcount cannot change */
+		BUG_ON(page_mapcount(page_tail) < 0);
+		tail_count += page_mapcount(page_tail);
+		/* check for overflow */
+		BUG_ON(tail_count < 0);
+		BUG_ON(atomic_read(&page_tail->_count) != 0);
+		/*
+		 * tail_page->_count is zero and not changing from
+		 * under us. But get_page_unless_zero() may be running
+		 * from under us on the tail_page. If we used
+		 * atomic_set() below instead of atomic_add(), we
+		 * would then run atomic_set() concurrently with
+		 * get_page_unless_zero(), and atomic_set() is
+		 * implemented in C not using locked ops. spin_unlock
+		 * on x86 sometime uses locked ops because of PPro
+		 * errata 66, 92, so unless somebody can guarantee
+		 * atomic_set() here would be safe on all archs (and
+		 * not only on x86), it's safer to use atomic_add().
+		 */
+		atomic_add(page_mapcount(page) + page_mapcount(page_tail) + 1,
+			   &page_tail->_count);
 
 		/* after clearing PageTail the gup refcount can be released */
 		smp_mb();
@@ -1186,10 +1203,7 @@ static void __split_huge_page_refcount(struct page *page)
 				      (1L << PG_uptodate)));
 		page_tail->flags |= (1L << PG_dirty);
 
-		/*
-		 * 1) clear PageTail before overwriting first_page
-		 * 2) clear PageTail before clearing PageHead for VM_BUG_ON
-		 */
+		/* clear PageTail before overwriting first_page */
 		smp_wmb();
 
 		/*
@@ -1206,7 +1220,6 @@ static void __split_huge_page_refcount(struct page *page)
 		 * status is achieved setting a reserved bit in the
 		 * pmd, not by clearing the present bit.
 		*/
-		BUG_ON(page_mapcount(page_tail));
 		page_tail->_mapcount = page->_mapcount;
 
 		BUG_ON(page_tail->mapping);
@@ -1223,6 +1236,8 @@ static void __split_huge_page_refcount(struct page *page)
 
 		lru_add_page_tail(zone, page, page_tail);
 	}
+	atomic_sub(tail_count, &page->_count);
+	BUG_ON(atomic_read(&page->_count) <= 0);
 
 	__dec_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES);
 	__mod_zone_page_state(zone, NR_ANON_PAGES, HPAGE_PMD_NR);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index dae27ba3be2..bb28a5f9db8 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2422,6 +2422,8 @@ retry_avoidcopy:
 	 * anon_vma prepared.
 	 */
 	if (unlikely(anon_vma_prepare(vma))) {
+		page_cache_release(new_page);
+		page_cache_release(old_page);
 		/* Caller expects lock to be held */
 		spin_lock(&mm->page_table_lock);
 		return VM_FAULT_OOM;
diff --git a/mm/internal.h b/mm/internal.h
index d071d380fb4..2189af49178 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -37,6 +37,52 @@ static inline void __put_page(struct page *page)
 	atomic_dec(&page->_count);
 }
 
+static inline void __get_page_tail_foll(struct page *page,
+					bool get_page_head)
+{
+	/*
+	 * If we're getting a tail page, the elevated page->_count is
+	 * required only in the head page and we will elevate the head
+	 * page->_count and tail page->_mapcount.
+	 *
+	 * We elevate page_tail->_mapcount for tail pages to force
+	 * page_tail->_count to be zero at all times to avoid getting
+	 * false positives from get_page_unless_zero() with
+	 * speculative page access (like in
+	 * page_cache_get_speculative()) on tail pages.
+	 */
+	VM_BUG_ON(atomic_read(&page->first_page->_count) <= 0);
+	VM_BUG_ON(atomic_read(&page->_count) != 0);
+	VM_BUG_ON(page_mapcount(page) < 0);
+	if (get_page_head)
+		atomic_inc(&page->first_page->_count);
+	atomic_inc(&page->_mapcount);
+}
+
+/*
+ * This is meant to be called as the FOLL_GET operation of
+ * follow_page() and it must be called while holding the proper PT
+ * lock while the pte (or pmd_trans_huge) is still mapping the page.
+ */
+static inline void get_page_foll(struct page *page)
+{
+	if (unlikely(PageTail(page)))
+		/*
+		 * This is safe only because
+		 * __split_huge_page_refcount() can't run under
+		 * get_page_foll() because we hold the proper PT lock.
+		 */
+		__get_page_tail_foll(page, true);
+	else {
+		/*
+		 * Getting a normal page or the head of a compound page
+		 * requires to already have an elevated page->_count.
+		 */
+		VM_BUG_ON(atomic_read(&page->_count) <= 0);
+		atomic_inc(&page->_count);
+	}
+}
+
 extern unsigned long highest_memmap_pfn;
 
 /*
diff --git a/mm/memory.c b/mm/memory.c
index a56e3ba816b..b2b87315cdc 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1503,7 +1503,7 @@ split_fallthrough:
 	}
 
 	if (flags & FOLL_GET)
-		get_page(page);
+		get_page_foll(page);
 	if (flags & FOLL_TOUCH) {
 		if ((flags & FOLL_WRITE) &&
 		    !pte_dirty(pte) && !PageDirty(page))
diff --git a/mm/slab.c b/mm/slab.c
index 6d90a091fdc..893c76df924 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -595,6 +595,7 @@ static enum {
 	PARTIAL_AC,
 	PARTIAL_L3,
 	EARLY,
+	LATE,
 	FULL
 } g_cpucache_up;
 
@@ -671,7 +672,7 @@ static void init_node_lock_keys(int q)
 {
 	struct cache_sizes *s = malloc_sizes;
 
-	if (g_cpucache_up != FULL)
+	if (g_cpucache_up < LATE)
 		return;
 
 	for (s = malloc_sizes; s->cs_size != ULONG_MAX; s++) {
@@ -1666,6 +1667,8 @@ void __init kmem_cache_init_late(void)
 {
 	struct kmem_cache *cachep;
 
+	g_cpucache_up = LATE;
+
 	/* Annotate slab for lockdep -- annotate the malloc caches */
 	init_lock_keys();
 
diff --git a/mm/swap.c b/mm/swap.c
index 3a442f18b0b..87627f181c3 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -78,39 +78,22 @@ static void put_compound_page(struct page *page)
 {
 	if (unlikely(PageTail(page))) {
 		/* __split_huge_page_refcount can run under us */
-		struct page *page_head = page->first_page;
-		smp_rmb();
-		/*
-		 * If PageTail is still set after smp_rmb() we can be sure
-		 * that the page->first_page we read wasn't a dangling pointer.
-		 * See __split_huge_page_refcount() smp_wmb().
-		 */
-		if (likely(PageTail(page) && get_page_unless_zero(page_head))) {
+		struct page *page_head = compound_trans_head(page);
+
+		if (likely(page != page_head &&
+			   get_page_unless_zero(page_head))) {
 			unsigned long flags;
 			/*
-			 * Verify that our page_head wasn't converted
-			 * to a a regular page before we got a
-			 * reference on it.
+			 * page_head wasn't a dangling pointer but it
+			 * may not be a head page anymore by the time
+			 * we obtain the lock. That is ok as long as it
+			 * can't be freed from under us.
 			 */
-			if (unlikely(!PageHead(page_head))) {
-				/* PageHead is cleared after PageTail */
-				smp_rmb();
-				VM_BUG_ON(PageTail(page));
-				goto out_put_head;
-			}
-			/*
-			 * Only run compound_lock on a valid PageHead,
-			 * after having it pinned with
-			 * get_page_unless_zero() above.
-			 */
-			smp_mb();
-			/* page_head wasn't a dangling pointer */
 			flags = compound_lock_irqsave(page_head);
 			if (unlikely(!PageTail(page))) {
 				/* __split_huge_page_refcount run before us */
 				compound_unlock_irqrestore(page_head, flags);
 				VM_BUG_ON(PageHead(page_head));
-			out_put_head:
 				if (put_page_testzero(page_head))
 					__put_single_page(page_head);
 			out_put_single:
@@ -121,16 +104,17 @@ static void put_compound_page(struct page *page)
 			VM_BUG_ON(page_head != page->first_page);
 			/*
 			 * We can release the refcount taken by
-			 * get_page_unless_zero now that
-			 * split_huge_page_refcount is blocked on the
-			 * compound_lock.
+			 * get_page_unless_zero() now that
+			 * __split_huge_page_refcount() is blocked on
+			 * the compound_lock.
 			 */
 			if (put_page_testzero(page_head))
 				VM_BUG_ON(1);
 			/* __split_huge_page_refcount will wait now */
-			VM_BUG_ON(atomic_read(&page->_count) <= 0);
-			atomic_dec(&page->_count);
+			VM_BUG_ON(page_mapcount(page) <= 0);
+			atomic_dec(&page->_mapcount);
 			VM_BUG_ON(atomic_read(&page_head->_count) <= 0);
+			VM_BUG_ON(atomic_read(&page->_count) != 0);
 			compound_unlock_irqrestore(page_head, flags);
 			if (put_page_testzero(page_head)) {
 				if (PageHead(page_head))
@@ -160,6 +144,45 @@ void put_page(struct page *page)
 }
 EXPORT_SYMBOL(put_page);
 
+/*
+ * This function is exported but must not be called by anything other
+ * than get_page(). It implements the slow path of get_page().
+ */
+bool __get_page_tail(struct page *page)
+{
+	/*
+	 * This takes care of get_page() if run on a tail page
+	 * returned by one of the get_user_pages/follow_page variants.
+	 * get_user_pages/follow_page itself doesn't need the compound
+	 * lock because it runs __get_page_tail_foll() under the
+	 * proper PT lock that already serializes against
+	 * split_huge_page().
+	 */
+	unsigned long flags;
+	bool got = false;
+	struct page *page_head = compound_trans_head(page);
+
+	if (likely(page != page_head && get_page_unless_zero(page_head))) {
+		/*
+		 * page_head wasn't a dangling pointer but it
+		 * may not be a head page anymore by the time
+		 * we obtain the lock. That is ok as long as it
+		 * can't be freed from under us.
+		 */
+		flags = compound_lock_irqsave(page_head);
+		/* here __split_huge_page_refcount won't run anymore */
+		if (likely(PageTail(page))) {
+			__get_page_tail_foll(page, false);
+			got = true;
+		}
+		compound_unlock_irqrestore(page_head, flags);
+		if (unlikely(!got))
+			put_page(page_head);
+	}
+	return got;
+}
+EXPORT_SYMBOL(__get_page_tail);
+
 /**
  * put_pages_list() - release a list of pages
  * @pages: list of pages threaded on page->lru
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 5016f19e166..56faf3163ee 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1253,18 +1253,22 @@ EXPORT_SYMBOL_GPL(map_vm_area);
 DEFINE_RWLOCK(vmlist_lock);
 struct vm_struct *vmlist;
 
-static void insert_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va,
+static void setup_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va,
 			      unsigned long flags, void *caller)
 {
-	struct vm_struct *tmp, **p;
-
 	vm->flags = flags;
 	vm->addr = (void *)va->va_start;
 	vm->size = va->va_end - va->va_start;
 	vm->caller = caller;
 	va->private = vm;
 	va->flags |= VM_VM_AREA;
+}
+
+static void insert_vmalloc_vmlist(struct vm_struct *vm)
+{
+	struct vm_struct *tmp, **p;
 
+	vm->flags &= ~VM_UNLIST;
 	write_lock(&vmlist_lock);
 	for (p = &vmlist; (tmp = *p) != NULL; p = &tmp->next) {
 		if (tmp->addr >= vm->addr)
@@ -1275,6 +1279,13 @@ static void insert_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va,
 	write_unlock(&vmlist_lock);
 }
 
+static void insert_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va,
+			      unsigned long flags, void *caller)
+{
+	setup_vmalloc_vm(vm, va, flags, caller);
+	insert_vmalloc_vmlist(vm);
+}
+
 static struct vm_struct *__get_vm_area_node(unsigned long size,
 		unsigned long align, unsigned long flags, unsigned long start,
 		unsigned long end, int node, gfp_t gfp_mask, void *caller)
@@ -1313,7 +1324,18 @@ static struct vm_struct *__get_vm_area_node(unsigned long size,
 		return NULL;
 	}
 
-	insert_vmalloc_vm(area, va, flags, caller);
+	/*
+	 * When this function is called from __vmalloc_node_range,
+	 * we do not add vm_struct to vmlist here to avoid
+	 * accessing uninitialized members of vm_struct such as
+	 * pages and nr_pages fields. They will be set later.
+	 * To distinguish it from others, we use a VM_UNLIST flag.
+	 */
+	if (flags & VM_UNLIST)
+		setup_vmalloc_vm(area, va, flags, caller);
+	else
+		insert_vmalloc_vm(area, va, flags, caller);
+
 	return area;
 }
 
@@ -1381,17 +1403,20 @@ struct vm_struct *remove_vm_area(const void *addr)
 	va = find_vmap_area((unsigned long)addr);
 	if (va && va->flags & VM_VM_AREA) {
 		struct vm_struct *vm = va->private;
-		struct vm_struct *tmp, **p;
-		/*
-		 * remove from list and disallow access to this vm_struct
-		 * before unmap. (address range confliction is maintained by
-		 * vmap.)
-		 */
-		write_lock(&vmlist_lock);
-		for (p = &vmlist; (tmp = *p) != vm; p = &tmp->next)
-			;
-		*p = tmp->next;
-		write_unlock(&vmlist_lock);
+
+		if (!(vm->flags & VM_UNLIST)) {
+			struct vm_struct *tmp, **p;
+			/*
+			 * remove from list and disallow access to
+			 * this vm_struct before unmap. (address range
+			 * confliction is maintained by vmap.)
+			 */
+			write_lock(&vmlist_lock);
+			for (p = &vmlist; (tmp = *p) != vm; p = &tmp->next)
+				;
+			*p = tmp->next;
+			write_unlock(&vmlist_lock);
+		}
 
 		vmap_debug_free_range(va->va_start, va->va_end);
 		free_unmap_vmap_area(va);
@@ -1602,8 +1627,8 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align,
 	if (!size || (size >> PAGE_SHIFT) > totalram_pages)
 		return NULL;
 
-	area = __get_vm_area_node(size, align, VM_ALLOC, start, end, node,
-				  gfp_mask, caller);
+	area = __get_vm_area_node(size, align, VM_ALLOC | VM_UNLIST,
+				  start, end, node, gfp_mask, caller);
 
 	if (!area)
 		return NULL;
@@ -1611,6 +1636,12 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align,
 	addr = __vmalloc_area_node(area, gfp_mask, prot, node, caller);
 
 	/*
+	 * In this function, newly allocated vm_struct is not added
+	 * to vmlist at __get_vm_area_node(). so, it is added here.
+	 */
+	insert_vmalloc_vmlist(area);
+
+	/*
 	 * A ref_count = 3 is needed because the vm_struct and vmap_area
 	 * structures allocated in the __get_vm_area_node() function contain
 	 * references to the virtual address of the vmalloc'ed block.
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index fb6931d00cd..d58fd8b9c81 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -137,10 +137,22 @@ static void tt_local_entry_free_ref(struct tt_local_entry *tt_local_entry)
 		kfree_rcu(tt_local_entry, rcu);
 }
 
+static void tt_global_entry_free_rcu(struct rcu_head *rcu)
+{
+	struct tt_global_entry *tt_global_entry;
+
+	tt_global_entry = container_of(rcu, struct tt_global_entry, rcu);
+
+	if (tt_global_entry->orig_node)
+		orig_node_free_ref(tt_global_entry->orig_node);
+
+	kfree(tt_global_entry);
+}
+
 static void tt_global_entry_free_ref(struct tt_global_entry *tt_global_entry)
 {
 	if (atomic_dec_and_test(&tt_global_entry->refcount))
-		kfree_rcu(tt_global_entry, rcu);
+		call_rcu(&tt_global_entry->rcu, tt_global_entry_free_rcu);
 }
 
 static void tt_local_event(struct bat_priv *bat_priv, const uint8_t *addr,
@@ -686,6 +698,9 @@ void tt_global_del_orig(struct bat_priv *bat_priv,
 	struct hlist_head *head;
 	spinlock_t *list_lock; /* protects write access to the hash lists */
 
+	if (!hash)
+		return;
+
 	for (i = 0; i < hash->size; i++) {
 		head = &hash->table[i];
 		list_lock = &hash->list_locks[i];
@@ -999,7 +1014,6 @@ static struct sk_buff *tt_response_fill_table(uint16_t tt_len, uint8_t ttvn,
 	tt_response = (struct tt_query_packet *)skb_put(skb,
 						     tt_query_size + tt_len);
 	tt_response->ttvn = ttvn;
-	tt_response->tt_data = htons(tt_tot);
 
 	tt_change = (struct tt_change *)(skb->data + tt_query_size);
 	tt_count = 0;
@@ -1025,6 +1039,10 @@ static struct sk_buff *tt_response_fill_table(uint16_t tt_len, uint8_t ttvn,
 	}
 	rcu_read_unlock();
 
+	/* store in the message the number of entries we have successfully
+	 * copied */
+	tt_response->tt_data = htons(tt_count);
+
 out:
 	return skb;
 }
@@ -1668,6 +1686,8 @@ static void tt_local_reset_flags(struct bat_priv *bat_priv, uint16_t flags)
 		rcu_read_lock();
 		hlist_for_each_entry_rcu(tt_local_entry, node,
 					 head, hash_entry) {
+			if (!(tt_local_entry->flags & flags))
+				continue;
 			tt_local_entry->flags &= ~flags;
 			atomic_inc(&bat_priv->num_local_tt);
 		}
diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h
index 25bd1db3537..51a0db7f644 100644
--- a/net/batman-adv/types.h
+++ b/net/batman-adv/types.h
@@ -223,22 +223,22 @@ struct socket_packet {
 
 struct tt_local_entry {
 	uint8_t addr[ETH_ALEN];
+	struct hlist_node hash_entry;
 	unsigned long last_seen;
 	uint16_t flags;
 	atomic_t refcount;
 	struct rcu_head rcu;
-	struct hlist_node hash_entry;
 };
 
 struct tt_global_entry {
 	uint8_t addr[ETH_ALEN];
+	struct hlist_node hash_entry; /* entry in the global table */
 	struct orig_node *orig_node;
 	uint8_t ttvn;
 	uint16_t flags; /* only TT_GLOBAL_ROAM is used */
 	unsigned long roam_at; /* time at which TT_GLOBAL_ROAM was set */
 	atomic_t refcount;
 	struct rcu_head rcu;
-	struct hlist_node hash_entry; /* entry in the global table */
 };
 
 struct tt_change_node {
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 995cbe0ac0b..e79ff75b0e7 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1501,6 +1501,8 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br,
 
 	__skb_pull(skb2, offset);
 	skb_reset_transport_header(skb2);
+	skb_postpull_rcsum(skb2, skb_network_header(skb2),
+			   skb_network_header_len(skb2));
 
 	icmp6_type = icmp6_hdr(skb2)->icmp6_type;
 
diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c
index 7f9ac0742d1..47fc8f3a47c 100644
--- a/net/caif/caif_dev.c
+++ b/net/caif/caif_dev.c
@@ -212,8 +212,7 @@ static int caif_device_notify(struct notifier_block *me, unsigned long what,
 	enum cfcnfg_phy_preference pref;
 	enum cfcnfg_phy_type phy_type;
 	struct cfcnfg *cfg;
-	struct caif_device_entry_list *caifdevs =
-	    caif_device_list(dev_net(dev));
+	struct caif_device_entry_list *caifdevs;
 
 	if (dev->type != ARPHRD_CAIF)
 		return 0;
@@ -222,6 +221,8 @@ static int caif_device_notify(struct notifier_block *me, unsigned long what,
 	if (cfg == NULL)
 		return 0;
 
+	caifdevs = caif_device_list(dev_net(dev));
+
 	switch (what) {
 	case NETDEV_REGISTER:
 		caifd = caif_device_alloc(dev);
diff --git a/net/core/dev.c b/net/core/dev.c
index b10ff0a7185..ae5cf2d630e 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6115,6 +6115,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char
 	*/
 	call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
 	call_netdevice_notifiers(NETDEV_UNREGISTER_BATCH, dev);
+	rtmsg_ifinfo(RTM_DELLINK, dev, ~0U);
 
 	/*
 	 *	Flush the unicast and multicast chains
diff --git a/net/core/sock.c b/net/core/sock.c
index bc745d00ea4..11d67b36c32 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1260,6 +1260,7 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority)
 			/* It is still raw copy of parent, so invalidate
 			 * destructor and make plain sk_free() */
 			newsk->sk_destruct = NULL;
+			bh_unlock_sock(newsk);
 			sk_free(newsk);
 			newsk = NULL;
 			goto out;
diff --git a/net/core/timestamping.c b/net/core/timestamping.c
index 98a52640e7c..82fb28857b6 100644
--- a/net/core/timestamping.c
+++ b/net/core/timestamping.c
@@ -57,9 +57,13 @@ void skb_clone_tx_timestamp(struct sk_buff *skb)
 	case PTP_CLASS_V2_VLAN:
 		phydev = skb->dev->phydev;
 		if (likely(phydev->drv->txtstamp)) {
+			if (!atomic_inc_not_zero(&sk->sk_refcnt))
+				return;
 			clone = skb_clone(skb, GFP_ATOMIC);
-			if (!clone)
+			if (!clone) {
+				sock_put(sk);
 				return;
+			}
 			clone->sk = sk;
 			phydev->drv->txtstamp(phydev, clone, type);
 		}
@@ -77,8 +81,11 @@ void skb_complete_tx_timestamp(struct sk_buff *skb,
 	struct sock_exterr_skb *serr;
 	int err;
 
-	if (!hwtstamps)
+	if (!hwtstamps) {
+		sock_put(sk);
+		kfree_skb(skb);
 		return;
+	}
 
 	*skb_hwtstamps(skb) = *hwtstamps;
 	serr = SKB_EXT_ERR(skb);
@@ -87,6 +94,7 @@ void skb_complete_tx_timestamp(struct sk_buff *skb,
 	serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING;
 	skb->sk = NULL;
 	err = sock_queue_err_skb(sk, skb);
+	sock_put(sk);
 	if (err)
 		kfree_skb(skb);
 }
diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c
index c1f4154552f..c7056b2e831 100644
--- a/net/ipv4/ah4.c
+++ b/net/ipv4/ah4.c
@@ -136,8 +136,6 @@ static void ah_output_done(struct crypto_async_request *base, int err)
 		memcpy(top_iph+1, iph+1, top_iph->ihl*4 - sizeof(struct iphdr));
 	}
 
-	err = ah->nexthdr;
-
 	kfree(AH_SKB_CB(skb)->tmp);
 	xfrm_output_resume(skb, err);
 }
@@ -264,12 +262,12 @@ static void ah_input_done(struct crypto_async_request *base, int err)
 	if (err)
 		goto out;
 
+	err = ah->nexthdr;
+
 	skb->network_header += ah_hlen;
 	memcpy(skb_network_header(skb), work_iph, ihl);
 	__skb_pull(skb, ah_hlen + ihl);
 	skb_set_transport_header(skb, -ihl);
-
-	err = ah->nexthdr;
 out:
 	kfree(AH_SKB_CB(skb)->tmp);
 	xfrm_input_resume(skb, err);
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index ec93335901d..05d20cca9d6 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -640,6 +640,7 @@ int ip_options_rcv_srr(struct sk_buff *skb)
 	}
 	if (srrptr <= srrspace) {
 		opt->srr_is_hit = 1;
+		iph->daddr = nexthop;
 		opt->is_changed = 1;
 	}
 	return 0;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 075212e41b8..05ac666c330 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -112,7 +112,7 @@
 #include <net/secure_seq.h>
 
 #define RT_FL_TOS(oldflp4) \
-    ((u32)(oldflp4->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK)))
+	((oldflp4)->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK))
 
 #define IP_MAX_MTU	0xFFF0
 
@@ -132,6 +132,7 @@ static int ip_rt_mtu_expires __read_mostly	= 10 * 60 * HZ;
 static int ip_rt_min_pmtu __read_mostly		= 512 + 20 + 20;
 static int ip_rt_min_advmss __read_mostly	= 256;
 static int rt_chain_length_max __read_mostly	= 20;
+static int redirect_genid;
 
 /*
  *	Interface to generic destination cache.
@@ -417,9 +418,13 @@ static int rt_cache_seq_show(struct seq_file *seq, void *v)
 	else {
 		struct rtable *r = v;
 		struct neighbour *n;
-		int len;
+		int len, HHUptod;
 
+		rcu_read_lock();
 		n = dst_get_neighbour(&r->dst);
+		HHUptod = (n && (n->nud_state & NUD_CONNECTED)) ? 1 : 0;
+		rcu_read_unlock();
+
 		seq_printf(seq, "%s\t%08X\t%08X\t%8X\t%d\t%u\t%d\t"
 			      "%08X\t%d\t%u\t%u\t%02X\t%d\t%1d\t%08X%n",
 			r->dst.dev ? r->dst.dev->name : "*",
@@ -433,7 +438,7 @@ static int rt_cache_seq_show(struct seq_file *seq, void *v)
 			      dst_metric(&r->dst, RTAX_RTTVAR)),
 			r->rt_key_tos,
 			-1,
-			(n && (n->nud_state & NUD_CONNECTED)) ? 1 : 0,
+			HHUptod,
 			r->rt_spec_dst, &len);
 
 		seq_printf(seq, "%*s\n", 127 - len, "");
@@ -838,6 +843,7 @@ static void rt_cache_invalidate(struct net *net)
 
 	get_random_bytes(&shuffle, sizeof(shuffle));
 	atomic_add(shuffle + 1U, &net->ipv4.rt_genid);
+	redirect_genid++;
 }
 
 /*
@@ -1305,11 +1311,40 @@ static void rt_del(unsigned hash, struct rtable *rt)
 	spin_unlock_bh(rt_hash_lock_addr(hash));
 }
 
+static void check_peer_redir(struct dst_entry *dst, struct inet_peer *peer)
+{
+	struct rtable *rt = (struct rtable *) dst;
+	__be32 orig_gw = rt->rt_gateway;
+	struct neighbour *n, *old_n;
+
+	dst_confirm(&rt->dst);
+
+	rt->rt_gateway = peer->redirect_learned.a4;
+
+	n = ipv4_neigh_lookup(&rt->dst, &rt->rt_gateway);
+	if (IS_ERR(n)) {
+		rt->rt_gateway = orig_gw;
+		return;
+	}
+	old_n = xchg(&rt->dst._neighbour, n);
+	if (old_n)
+		neigh_release(old_n);
+	if (!(n->nud_state & NUD_VALID)) {
+		neigh_event_send(n, NULL);
+	} else {
+		rt->rt_flags |= RTCF_REDIRECTED;
+		call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n);
+	}
+}
+
 /* called in rcu_read_lock() section */
 void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw,
 		    __be32 saddr, struct net_device *dev)
 {
+	int s, i;
 	struct in_device *in_dev = __in_dev_get_rcu(dev);
+	__be32 skeys[2] = { saddr, 0 };
+	int    ikeys[2] = { dev->ifindex, 0 };
 	struct inet_peer *peer;
 	struct net *net;
 
@@ -1332,13 +1367,45 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw,
 			goto reject_redirect;
 	}
 
-	peer = inet_getpeer_v4(daddr, 1);
-	if (peer) {
-		peer->redirect_learned.a4 = new_gw;
+	for (s = 0; s < 2; s++) {
+		for (i = 0; i < 2; i++) {
+			unsigned int hash;
+			struct rtable __rcu **rthp;
+			struct rtable *rt;
 
-		inet_putpeer(peer);
+			hash = rt_hash(daddr, skeys[s], ikeys[i], rt_genid(net));
+
+			rthp = &rt_hash_table[hash].chain;
 
-		atomic_inc(&__rt_peer_genid);
+			while ((rt = rcu_dereference(*rthp)) != NULL) {
+				rthp = &rt->dst.rt_next;
+
+				if (rt->rt_key_dst != daddr ||
+				    rt->rt_key_src != skeys[s] ||
+				    rt->rt_oif != ikeys[i] ||
+				    rt_is_input_route(rt) ||
+				    rt_is_expired(rt) ||
+				    !net_eq(dev_net(rt->dst.dev), net) ||
+				    rt->dst.error ||
+				    rt->dst.dev != dev ||
+				    rt->rt_gateway != old_gw)
+					continue;
+
+				if (!rt->peer)
+					rt_bind_peer(rt, rt->rt_dst, 1);
+
+				peer = rt->peer;
+				if (peer) {
+					if (peer->redirect_learned.a4 != new_gw ||
+					    peer->redirect_genid != redirect_genid) {
+						peer->redirect_learned.a4 = new_gw;
+						peer->redirect_genid = redirect_genid;
+						atomic_inc(&__rt_peer_genid);
+					}
+					check_peer_redir(&rt->dst, peer);
+				}
+			}
+		}
 	}
 	return;
 
@@ -1568,11 +1635,10 @@ unsigned short ip_rt_frag_needed(struct net *net, const struct iphdr *iph,
 			est_mtu = mtu;
 			peer->pmtu_learned = mtu;
 			peer->pmtu_expires = pmtu_expires;
+			atomic_inc(&__rt_peer_genid);
 		}
 
 		inet_putpeer(peer);
-
-		atomic_inc(&__rt_peer_genid);
 	}
 	return est_mtu ? : new_mtu;
 }
@@ -1625,40 +1691,9 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu)
 	}
 }
 
-static int check_peer_redir(struct dst_entry *dst, struct inet_peer *peer)
-{
-	struct rtable *rt = (struct rtable *) dst;
-	__be32 orig_gw = rt->rt_gateway;
-	struct neighbour *n, *old_n;
-
-	dst_confirm(&rt->dst);
-
-	rt->rt_gateway = peer->redirect_learned.a4;
-
-	n = ipv4_neigh_lookup(&rt->dst, &rt->rt_gateway);
-	if (IS_ERR(n))
-		return PTR_ERR(n);
-	old_n = xchg(&rt->dst._neighbour, n);
-	if (old_n)
-		neigh_release(old_n);
-	if (!n || !(n->nud_state & NUD_VALID)) {
-		if (n)
-			neigh_event_send(n, NULL);
-		rt->rt_gateway = orig_gw;
-		return -EAGAIN;
-	} else {
-		rt->rt_flags |= RTCF_REDIRECTED;
-		call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n);
-	}
-	return 0;
-}
 
-static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
+static void ipv4_validate_peer(struct rtable *rt)
 {
-	struct rtable *rt = (struct rtable *) dst;
-
-	if (rt_is_expired(rt))
-		return NULL;
 	if (rt->rt_peer_genid != rt_peer_genid()) {
 		struct inet_peer *peer;
 
@@ -1667,17 +1702,26 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
 
 		peer = rt->peer;
 		if (peer) {
-			check_peer_pmtu(dst, peer);
+			check_peer_pmtu(&rt->dst, peer);
 
+			if (peer->redirect_genid != redirect_genid)
+				peer->redirect_learned.a4 = 0;
 			if (peer->redirect_learned.a4 &&
-			    peer->redirect_learned.a4 != rt->rt_gateway) {
-				if (check_peer_redir(dst, peer))
-					return NULL;
-			}
+			    peer->redirect_learned.a4 != rt->rt_gateway)
+				check_peer_redir(&rt->dst, peer);
 		}
 
 		rt->rt_peer_genid = rt_peer_genid();
 	}
+}
+
+static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
+{
+	struct rtable *rt = (struct rtable *) dst;
+
+	if (rt_is_expired(rt))
+		return NULL;
+	ipv4_validate_peer(rt);
 	return dst;
 }
 
@@ -1820,6 +1864,8 @@ static void rt_init_metrics(struct rtable *rt, const struct flowi4 *fl4,
 		dst_init_metrics(&rt->dst, peer->metrics, false);
 
 		check_peer_pmtu(&rt->dst, peer);
+		if (peer->redirect_genid != redirect_genid)
+			peer->redirect_learned.a4 = 0;
 		if (peer->redirect_learned.a4 &&
 		    peer->redirect_learned.a4 != rt->rt_gateway) {
 			rt->rt_gateway = peer->redirect_learned.a4;
@@ -2325,6 +2371,7 @@ int ip_route_input_common(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 		    rth->rt_mark == skb->mark &&
 		    net_eq(dev_net(rth->dst.dev), net) &&
 		    !rt_is_expired(rth)) {
+			ipv4_validate_peer(rth);
 			if (noref) {
 				dst_use_noref(&rth->dst, jiffies);
 				skb_dst_set_noref(skb, &rth->dst);
@@ -2383,11 +2430,11 @@ EXPORT_SYMBOL(ip_route_input_common);
 static struct rtable *__mkroute_output(const struct fib_result *res,
 				       const struct flowi4 *fl4,
 				       __be32 orig_daddr, __be32 orig_saddr,
-				       int orig_oif, struct net_device *dev_out,
+				       int orig_oif, __u8 orig_rtos,
+				       struct net_device *dev_out,
 				       unsigned int flags)
 {
 	struct fib_info *fi = res->fi;
-	u32 tos = RT_FL_TOS(fl4);
 	struct in_device *in_dev;
 	u16 type = res->type;
 	struct rtable *rth;
@@ -2438,7 +2485,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 	rth->rt_genid = rt_genid(dev_net(dev_out));
 	rth->rt_flags	= flags;
 	rth->rt_type	= type;
-	rth->rt_key_tos	= tos;
+	rth->rt_key_tos	= orig_rtos;
 	rth->rt_dst	= fl4->daddr;
 	rth->rt_src	= fl4->saddr;
 	rth->rt_route_iif = 0;
@@ -2488,7 +2535,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 static struct rtable *ip_route_output_slow(struct net *net, struct flowi4 *fl4)
 {
 	struct net_device *dev_out = NULL;
-	u32 tos	= RT_FL_TOS(fl4);
+	__u8 tos = RT_FL_TOS(fl4);
 	unsigned int flags = 0;
 	struct fib_result res;
 	struct rtable *rth;
@@ -2664,7 +2711,7 @@ static struct rtable *ip_route_output_slow(struct net *net, struct flowi4 *fl4)
 
 make_route:
 	rth = __mkroute_output(&res, fl4, orig_daddr, orig_saddr, orig_oif,
-			       dev_out, flags);
+			       tos, dev_out, flags);
 	if (!IS_ERR(rth)) {
 		unsigned int hash;
 
@@ -2700,6 +2747,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *flp4)
 			    (IPTOS_RT_MASK | RTO_ONLINK)) &&
 		    net_eq(dev_net(rth->dst.dev), net) &&
 		    !rt_is_expired(rth)) {
+			ipv4_validate_peer(rth);
 			dst_use(&rth->dst, jiffies);
 			RT_CACHE_STAT_INC(out_hit);
 			rcu_read_unlock_bh();
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index fc5368ad2b0..a0b4c5da8d4 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -79,13 +79,13 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
 	struct rtable *rt = (struct rtable *)xdst->route;
 	const struct flowi4 *fl4 = &fl->u.ip4;
 
-	rt->rt_key_dst = fl4->daddr;
-	rt->rt_key_src = fl4->saddr;
-	rt->rt_key_tos = fl4->flowi4_tos;
-	rt->rt_route_iif = fl4->flowi4_iif;
-	rt->rt_iif = fl4->flowi4_iif;
-	rt->rt_oif = fl4->flowi4_oif;
-	rt->rt_mark = fl4->flowi4_mark;
+	xdst->u.rt.rt_key_dst = fl4->daddr;
+	xdst->u.rt.rt_key_src = fl4->saddr;
+	xdst->u.rt.rt_key_tos = fl4->flowi4_tos;
+	xdst->u.rt.rt_route_iif = fl4->flowi4_iif;
+	xdst->u.rt.rt_iif = fl4->flowi4_iif;
+	xdst->u.rt.rt_oif = fl4->flowi4_oif;
+	xdst->u.rt.rt_mark = fl4->flowi4_mark;
 
 	xdst->u.dst.dev = dev;
 	dev_hold(dev);
diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c
index 2195ae65192..7a33aaa0022 100644
--- a/net/ipv6/ah6.c
+++ b/net/ipv6/ah6.c
@@ -324,8 +324,6 @@ static void ah6_output_done(struct crypto_async_request *base, int err)
 #endif
 	}
 
-	err = ah->nexthdr;
-
 	kfree(AH_SKB_CB(skb)->tmp);
 	xfrm_output_resume(skb, err);
 }
@@ -466,12 +464,12 @@ static void ah6_input_done(struct crypto_async_request *base, int err)
 	if (err)
 		goto out;
 
+	err = ah->nexthdr;
+
 	skb->network_header += ah_hlen;
 	memcpy(skb_network_header(skb), work_iph, hdr_len);
 	__skb_pull(skb, ah_hlen + hdr_len);
 	skb_set_transport_header(skb, -hdr_len);
-
-	err = ah->nexthdr;
 out:
 	kfree(AH_SKB_CB(skb)->tmp);
 	xfrm_input_resume(skb, err);
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 0bc98886c38..4e6922f1c68 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -289,6 +289,8 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct ip6_tnl_parm *p)
 	if ((err = register_netdevice(dev)) < 0)
 		goto failed_free;
 
+	strcpy(t->parms.name, dev->name);
+
 	dev_hold(dev);
 	ip6_tnl_link(ip6n, t);
 	return t;
@@ -1397,7 +1399,6 @@ ip6_tnl_dev_init_gen(struct net_device *dev)
 	struct ip6_tnl *t = netdev_priv(dev);
 
 	t->dev = dev;
-	strcpy(t->parms.name, dev->name);
 	dev->tstats = alloc_percpu(struct pcpu_tstats);
 	if (!dev->tstats)
 		return -ENOMEM;
@@ -1477,6 +1478,7 @@ static void __net_exit ip6_tnl_destroy_tunnels(struct ip6_tnl_net *ip6n)
 static int __net_init ip6_tnl_init_net(struct net *net)
 {
 	struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
+	struct ip6_tnl *t = NULL;
 	int err;
 
 	ip6n->tnls[0] = ip6n->tnls_wc;
@@ -1497,6 +1499,10 @@ static int __net_init ip6_tnl_init_net(struct net *net)
 	err = register_netdev(ip6n->fb_tnl_dev);
 	if (err < 0)
 		goto err_register;
+
+	t = netdev_priv(ip6n->fb_tnl_dev);
+
+	strcpy(t->parms.name, ip6n->fb_tnl_dev->name);
 	return 0;
 
 err_register:
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index fb545edef6e..57b82dc1ae9 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1086,11 +1086,10 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev,
 	rt->dst.output  = ip6_output;
 	dst_set_neighbour(&rt->dst, neigh);
 	atomic_set(&rt->dst.__refcnt, 1);
-	dst_metric_set(&rt->dst, RTAX_HOPLIMIT, 255);
-
 	ipv6_addr_copy(&rt->rt6i_dst.addr, addr);
 	rt->rt6i_dst.plen = 128;
 	rt->rt6i_idev     = idev;
+	dst_metric_set(&rt->dst, RTAX_HOPLIMIT, 255);
 
 	spin_lock_bh(&icmp6_dst_lock);
 	rt->dst.next = icmp6_dst_gc_list;
diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c
index c8be8eff70d..db7db43ccf4 100644
--- a/net/mac80211/agg-tx.c
+++ b/net/mac80211/agg-tx.c
@@ -162,6 +162,12 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid,
 		return -ENOENT;
 	}
 
+	/* if we're already stopping ignore any new requests to stop */
+	if (test_bit(HT_AGG_STATE_STOPPING, &tid_tx->state)) {
+		spin_unlock_bh(&sta->lock);
+		return -EALREADY;
+	}
+
 	if (test_bit(HT_AGG_STATE_WANT_START, &tid_tx->state)) {
 		/* not even started yet! */
 		ieee80211_assign_tid_tx(sta, tid, NULL);
@@ -170,6 +176,8 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid,
 		return 0;
 	}
 
+	set_bit(HT_AGG_STATE_STOPPING, &tid_tx->state);
+
 	spin_unlock_bh(&sta->lock);
 
 #ifdef CONFIG_MAC80211_HT_DEBUG
@@ -177,8 +185,6 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid,
 	       sta->sta.addr, tid);
 #endif /* CONFIG_MAC80211_HT_DEBUG */
 
-	set_bit(HT_AGG_STATE_STOPPING, &tid_tx->state);
-
 	del_timer_sync(&tid_tx->addba_resp_timer);
 
 	/*
@@ -188,6 +194,20 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid,
 	 */
 	clear_bit(HT_AGG_STATE_OPERATIONAL, &tid_tx->state);
 
+	/*
+	 * There might be a few packets being processed right now (on
+	 * another CPU) that have already gotten past the aggregation
+	 * check when it was still OPERATIONAL and consequently have
+	 * IEEE80211_TX_CTL_AMPDU set. In that case, this code might
+	 * call into the driver at the same time or even before the
+	 * TX paths calls into it, which could confuse the driver.
+	 *
+	 * Wait for all currently running TX paths to finish before
+	 * telling the driver. New packets will not go through since
+	 * the aggregation session is no longer OPERATIONAL.
+	 */
+	synchronize_net();
+
 	tid_tx->stop_initiator = initiator;
 	tid_tx->tx_stop = tx;
 
@@ -772,12 +792,27 @@ void ieee80211_process_addba_resp(struct ieee80211_local *local,
 		goto out;
 	}
 
-	del_timer(&tid_tx->addba_resp_timer);
+	del_timer_sync(&tid_tx->addba_resp_timer);
 
 #ifdef CONFIG_MAC80211_HT_DEBUG
 	printk(KERN_DEBUG "switched off addBA timer for tid %d\n", tid);
 #endif
 
+	/*
+	 * addba_resp_timer may have fired before we got here, and
+	 * caused WANT_STOP to be set. If the stop then was already
+	 * processed further, STOPPING might be set.
+	 */
+	if (test_bit(HT_AGG_STATE_WANT_STOP, &tid_tx->state) ||
+	    test_bit(HT_AGG_STATE_STOPPING, &tid_tx->state)) {
+#ifdef CONFIG_MAC80211_HT_DEBUG
+		printk(KERN_DEBUG
+		       "got addBA resp for tid %d but we already gave up\n",
+		       tid);
+#endif
+		goto out;
+	}
+
 	if (le16_to_cpu(mgmt->u.action.u.addba_resp.status)
 			== WLAN_STATUS_SUCCESS) {
 		/*
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 3d1b091d9b2..10c95be3b30 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -1821,7 +1821,7 @@ ieee80211_offchan_tx_done(struct ieee80211_work *wk, struct sk_buff *skb)
 	 * so in that case userspace will have to deal with it.
 	 */
 
-	if (wk->offchan_tx.wait && wk->offchan_tx.frame)
+	if (wk->offchan_tx.wait && !wk->offchan_tx.status)
 		cfg80211_mgmt_tx_status(wk->sdata->dev,
 					(unsigned long) wk->offchan_tx.frame,
 					wk->ie, wk->ie_len, false, GFP_KERNEL);
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 1d4a81f4c1b..d4668c992af 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -346,6 +346,7 @@ struct ieee80211_work {
 		struct {
 			struct sk_buff *frame;
 			u32 wait;
+			bool status;
 		} offchan_tx;
 	};
 
@@ -390,6 +391,7 @@ struct ieee80211_if_managed {
 
 	unsigned long timers_running; /* used for quiesce/restart */
 	bool powersave; /* powersave requested for this iface */
+	bool broken_ap; /* AP is broken -- turn off powersave */
 	enum ieee80211_smps_mode req_smps, /* requested smps mode */
 				 ap_smps, /* smps mode AP thinks we're in */
 				 driver_smps_mode; /* smps mode request */
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 64bb140bb67..556572edd88 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -743,6 +743,12 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 	if (!local->int_scan_req)
 		return -ENOMEM;
 
+	for (band = 0; band < IEEE80211_NUM_BANDS; band++) {
+		if (!local->hw.wiphy->bands[band])
+			continue;
+		local->int_scan_req->rates[band] = (u32) -1;
+	}
+
 	/* if low-level driver supports AP, we also support VLAN */
 	if (local->hw.wiphy->interface_modes & BIT(NL80211_IFTYPE_AP)) {
 		hw->wiphy->interface_modes |= BIT(NL80211_IFTYPE_AP_VLAN);
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 19fecc95391..2fb3d79e0f7 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -613,6 +613,9 @@ static bool ieee80211_powersave_allowed(struct ieee80211_sub_if_data *sdata)
 	if (!mgd->powersave)
 		return false;
 
+	if (mgd->broken_ap)
+		return false;
+
 	if (!mgd->associated)
 		return false;
 
@@ -1467,10 +1470,21 @@ static bool ieee80211_assoc_success(struct ieee80211_work *wk,
 	capab_info = le16_to_cpu(mgmt->u.assoc_resp.capab_info);
 
 	if ((aid & (BIT(15) | BIT(14))) != (BIT(15) | BIT(14)))
-		printk(KERN_DEBUG "%s: invalid aid value %d; bits 15:14 not "
-		       "set\n", sdata->name, aid);
+		printk(KERN_DEBUG
+		       "%s: invalid AID value 0x%x; bits 15:14 not set\n",
+		       sdata->name, aid);
 	aid &= ~(BIT(15) | BIT(14));
 
+	ifmgd->broken_ap = false;
+
+	if (aid == 0 || aid > IEEE80211_MAX_AID) {
+		printk(KERN_DEBUG
+		       "%s: invalid AID value %d (out of range), turn off PS\n",
+		       sdata->name, aid);
+		aid = 0;
+		ifmgd->broken_ap = true;
+	}
+
 	pos = mgmt->u.assoc_resp.variable;
 	ieee802_11_parse_elems(pos, len - (pos - (u8 *) mgmt), &elems);
 
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index a86e0df2fe8..5779d06299e 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -141,8 +141,9 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local,
 	pos++;
 
 	/* IEEE80211_RADIOTAP_RATE */
-	if (status->flag & RX_FLAG_HT) {
+	if (!rate || status->flag & RX_FLAG_HT) {
 		/*
+		 * Without rate information don't add it. If we have,
 		 * MCS information is a separate field in radiotap,
 		 * added below. The byte here is needed as padding
 		 * for the channel though, so initialise it to 0.
@@ -163,12 +164,14 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local,
 	else if (status->flag & RX_FLAG_HT)
 		put_unaligned_le16(IEEE80211_CHAN_DYN | IEEE80211_CHAN_2GHZ,
 				   pos);
-	else if (rate->flags & IEEE80211_RATE_ERP_G)
+	else if (rate && rate->flags & IEEE80211_RATE_ERP_G)
 		put_unaligned_le16(IEEE80211_CHAN_OFDM | IEEE80211_CHAN_2GHZ,
 				   pos);
-	else
+	else if (rate)
 		put_unaligned_le16(IEEE80211_CHAN_CCK | IEEE80211_CHAN_2GHZ,
 				   pos);
+	else
+		put_unaligned_le16(IEEE80211_CHAN_2GHZ, pos);
 	pos += 2;
 
 	/* IEEE80211_RADIOTAP_DBM_ANTSIGNAL */
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index 1658efaa2e8..04cdbaf160b 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -336,7 +336,7 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
 				continue;
 			if (wk->offchan_tx.frame != skb)
 				continue;
-			wk->offchan_tx.frame = NULL;
+			wk->offchan_tx.status = true;
 			break;
 		}
 		rcu_read_unlock();
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index ddeb1b99838..fd031e821f4 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -1055,6 +1055,8 @@ struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata,
 	skb = ieee80211_probereq_get(&local->hw, &sdata->vif,
 				     ssid, ssid_len,
 				     buf, buf_len);
+	if (!skb)
+		goto out;
 
 	if (dst) {
 		mgmt = (struct ieee80211_mgmt *) skb->data;
@@ -1063,6 +1065,8 @@ struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata,
 	}
 
 	IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT;
+
+ out:
 	kfree(buf);
 
 	return skb;
diff --git a/net/mac80211/work.c b/net/mac80211/work.c
index c0c97317591..dc747c58603 100644
--- a/net/mac80211/work.c
+++ b/net/mac80211/work.c
@@ -603,7 +603,7 @@ ieee80211_offchannel_tx(struct ieee80211_work *wk)
 		/*
 		 * After this, offchan_tx.frame remains but now is no
 		 * longer a valid pointer -- we still need it as the
-		 * cookie for canceling this work.
+		 * cookie for canceling this work/status matching.
 		 */
 		ieee80211_tx_skb(wk->sdata, wk->offchan_tx.frame);
 
@@ -1110,14 +1110,13 @@ static void ieee80211_work_work(struct work_struct *work)
 			continue;
 		if (wk->chan != local->tmp_channel)
 			continue;
-		if (ieee80211_work_ct_coexists(wk->chan_type,
-					       local->tmp_channel_type))
+		if (!ieee80211_work_ct_coexists(wk->chan_type,
+						local->tmp_channel_type))
 			continue;
 		remain_off_channel = true;
 	}
 
 	if (!remain_off_channel && local->tmp_channel) {
-		bool on_oper_chan = ieee80211_cfg_on_oper_channel(local);
 		local->tmp_channel = NULL;
 		/* If tmp_channel wasn't operating channel, then
 		 * we need to go back on-channel.
@@ -1127,7 +1126,7 @@ static void ieee80211_work_work(struct work_struct *work)
 		 * we still need to do a hardware config.  Currently,
 		 * we cannot be here while scanning, however.
 		 */
-		if (ieee80211_cfg_on_oper_channel(local) && !on_oper_chan)
+		if (!ieee80211_cfg_on_oper_channel(local))
 			ieee80211_hw_config(local, 0);
 
 		/* At the least, we need to disable offchannel_ps,
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index 6649463da1b..d617161f8dd 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -209,8 +209,8 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt)
 				 ctl->Plog, ctl->Scell_log,
 				 nla_data(tb[TCA_RED_STAB]));
 
-	if (skb_queue_empty(&sch->q))
-		red_end_of_idle_period(&q->parms);
+	if (!q->qdisc->q.qlen)
+		red_start_of_idle_period(&q->parms);
 
 	sch_tree_unlock(sch);
 	return 0;
diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c
index a3b7120fcc7..4f4c52c0eeb 100644
--- a/net/sched/sch_teql.c
+++ b/net/sched/sch_teql.c
@@ -225,11 +225,11 @@ static int teql_qdisc_init(struct Qdisc *sch, struct nlattr *opt)
 
 
 static int
-__teql_resolve(struct sk_buff *skb, struct sk_buff *skb_res, struct net_device *dev)
+__teql_resolve(struct sk_buff *skb, struct sk_buff *skb_res,
+	       struct net_device *dev, struct netdev_queue *txq,
+	       struct neighbour *mn)
 {
-	struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, 0);
-	struct teql_sched_data *q = qdisc_priv(dev_queue->qdisc);
-	struct neighbour *mn = dst_get_neighbour(skb_dst(skb));
+	struct teql_sched_data *q = qdisc_priv(txq->qdisc);
 	struct neighbour *n = q->ncache;
 
 	if (mn->tbl == NULL)
@@ -262,17 +262,26 @@ __teql_resolve(struct sk_buff *skb, struct sk_buff *skb_res, struct net_device *
 }
 
 static inline int teql_resolve(struct sk_buff *skb,
-			       struct sk_buff *skb_res, struct net_device *dev)
+			       struct sk_buff *skb_res,
+			       struct net_device *dev,
+			       struct netdev_queue *txq)
 {
-	struct netdev_queue *txq = netdev_get_tx_queue(dev, 0);
+	struct dst_entry *dst = skb_dst(skb);
+	struct neighbour *mn;
+	int res;
+
 	if (txq->qdisc == &noop_qdisc)
 		return -ENODEV;
 
-	if (dev->header_ops == NULL ||
-	    skb_dst(skb) == NULL ||
-	    dst_get_neighbour(skb_dst(skb)) == NULL)
+	if (!dev->header_ops || !dst)
 		return 0;
-	return __teql_resolve(skb, skb_res, dev);
+
+	rcu_read_lock();
+	mn = dst_get_neighbour(dst);
+	res = mn ? __teql_resolve(skb, skb_res, dev, txq, mn) : 0;
+	rcu_read_unlock();
+
+	return res;
 }
 
 static netdev_tx_t teql_master_xmit(struct sk_buff *skb, struct net_device *dev)
@@ -307,7 +316,7 @@ restart:
 			continue;
 		}
 
-		switch (teql_resolve(skb, skb_res, slave)) {
+		switch (teql_resolve(skb, skb_res, slave, slave_txq)) {
 		case 0:
 			if (__netif_tx_trylock(slave_txq)) {
 				unsigned int length = qdisc_pkt_len(skb);
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index 364eb45e989..e9b76939268 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -603,26 +603,6 @@ out:
 	return err;
 }
 
-static ssize_t
-gss_pipe_upcall(struct file *filp, struct rpc_pipe_msg *msg,
-		char __user *dst, size_t buflen)
-{
-	char *data = (char *)msg->data + msg->copied;
-	size_t mlen = min(msg->len, buflen);
-	unsigned long left;
-
-	left = copy_to_user(dst, data, mlen);
-	if (left == mlen) {
-		msg->errno = -EFAULT;
-		return -EFAULT;
-	}
-
-	mlen -= left;
-	msg->copied += mlen;
-	msg->errno = 0;
-	return mlen;
-}
-
 #define MSG_BUF_MAXSIZE 1024
 
 static ssize_t
@@ -1590,7 +1570,7 @@ static const struct rpc_credops gss_nullops = {
 };
 
 static const struct rpc_pipe_ops gss_upcall_ops_v0 = {
-	.upcall		= gss_pipe_upcall,
+	.upcall		= rpc_pipe_generic_upcall,
 	.downcall	= gss_pipe_downcall,
 	.destroy_msg	= gss_pipe_destroy_msg,
 	.open_pipe	= gss_pipe_open_v0,
@@ -1598,7 +1578,7 @@ static const struct rpc_pipe_ops gss_upcall_ops_v0 = {
 };
 
 static const struct rpc_pipe_ops gss_upcall_ops_v1 = {
-	.upcall		= gss_pipe_upcall,
+	.upcall		= rpc_pipe_generic_upcall,
 	.downcall	= gss_pipe_downcall,
 	.destroy_msg	= gss_pipe_destroy_msg,
 	.open_pipe	= gss_pipe_open_v1,
diff --git a/net/sunrpc/auth_unix.c b/net/sunrpc/auth_unix.c
index 4cb70dc6e7a..e50502d8ceb 100644
--- a/net/sunrpc/auth_unix.c
+++ b/net/sunrpc/auth_unix.c
@@ -129,6 +129,9 @@ unx_match(struct auth_cred *acred, struct rpc_cred *rcred, int flags)
 	for (i = 0; i < groups ; i++)
 		if (cred->uc_gids[i] != GROUP_AT(acred->group_info, i))
 			return 0;
+	if (groups < NFS_NGROUPS &&
+	    cred->uc_gids[groups] != NOGROUP)
+		return 0;
 	return 1;
 }
 
diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c
index b181e344132..67dbc188438 100644
--- a/net/sunrpc/rpc_pipe.c
+++ b/net/sunrpc/rpc_pipe.c
@@ -77,6 +77,26 @@ rpc_timeout_upcall_queue(struct work_struct *work)
 	rpc_purge_list(rpci, &free_list, destroy_msg, -ETIMEDOUT);
 }
 
+ssize_t rpc_pipe_generic_upcall(struct file *filp, struct rpc_pipe_msg *msg,
+				char __user *dst, size_t buflen)
+{
+	char *data = (char *)msg->data + msg->copied;
+	size_t mlen = min(msg->len - msg->copied, buflen);
+	unsigned long left;
+
+	left = copy_to_user(dst, data, mlen);
+	if (left == mlen) {
+		msg->errno = -EFAULT;
+		return -EFAULT;
+	}
+
+	mlen -= left;
+	msg->copied += mlen;
+	msg->errno = 0;
+	return mlen;
+}
+EXPORT_SYMBOL_GPL(rpc_pipe_generic_upcall);
+
 /**
  * rpc_queue_upcall - queue an upcall message to userspace
  * @inode: inode of upcall pipe on which to queue given message
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index d7f97ef2659..b60b75082f3 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -496,7 +496,7 @@ static int xs_nospace(struct rpc_task *task)
 	struct rpc_rqst *req = task->tk_rqstp;
 	struct rpc_xprt *xprt = req->rq_xprt;
 	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
-	int ret = 0;
+	int ret = -EAGAIN;
 
 	dprintk("RPC: %5u xmit incomplete (%u left of %u)\n",
 			task->tk_pid, req->rq_slen - req->rq_bytes_sent,
@@ -508,7 +508,6 @@ static int xs_nospace(struct rpc_task *task)
 	/* Don't race with disconnect */
 	if (xprt_connected(xprt)) {
 		if (test_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags)) {
-			ret = -EAGAIN;
 			/*
 			 * Notify TCP that we're limited by the application
 			 * window size
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 39180512bfc..04c25f740ac 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -83,8 +83,8 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = {
 	[NL80211_ATTR_IFINDEX] = { .type = NLA_U32 },
 	[NL80211_ATTR_IFNAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ-1 },
 
-	[NL80211_ATTR_MAC] = { .type = NLA_BINARY, .len = ETH_ALEN },
-	[NL80211_ATTR_PREV_BSSID] = { .type = NLA_BINARY, .len = ETH_ALEN },
+	[NL80211_ATTR_MAC] = { .len = ETH_ALEN },
+	[NL80211_ATTR_PREV_BSSID] = { .len = ETH_ALEN },
 
 	[NL80211_ATTR_KEY] = { .type = NLA_NESTED, },
 	[NL80211_ATTR_KEY_DATA] = { .type = NLA_BINARY,
@@ -126,8 +126,7 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = {
 	[NL80211_ATTR_MESH_CONFIG] = { .type = NLA_NESTED },
 	[NL80211_ATTR_SUPPORT_MESH_AUTH] = { .type = NLA_FLAG },
 
-	[NL80211_ATTR_HT_CAPABILITY] = { .type = NLA_BINARY,
-					 .len = NL80211_HT_CAPABILITY_LEN },
+	[NL80211_ATTR_HT_CAPABILITY] = { .len = NL80211_HT_CAPABILITY_LEN },
 
 	[NL80211_ATTR_MGMT_SUBTYPE] = { .type = NLA_U8 },
 	[NL80211_ATTR_IE] = { .type = NLA_BINARY,
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 68a471ba193..1bc36d250ba 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -57,8 +57,17 @@
 #define REG_DBG_PRINT(args...)
 #endif
 
+static struct regulatory_request core_request_world = {
+	.initiator = NL80211_REGDOM_SET_BY_CORE,
+	.alpha2[0] = '0',
+	.alpha2[1] = '0',
+	.intersect = false,
+	.processed = true,
+	.country_ie_env = ENVIRON_ANY,
+};
+
 /* Receipt of information from last regulatory request */
-static struct regulatory_request *last_request;
+static struct regulatory_request *last_request = &core_request_world;
 
 /* To trigger userspace events */
 static struct platform_device *reg_pdev;
@@ -150,7 +159,7 @@ static char user_alpha2[2];
 module_param(ieee80211_regdom, charp, 0444);
 MODULE_PARM_DESC(ieee80211_regdom, "IEEE 802.11 regulatory domain code");
 
-static void reset_regdomains(void)
+static void reset_regdomains(bool full_reset)
 {
 	/* avoid freeing static information or freeing something twice */
 	if (cfg80211_regdomain == cfg80211_world_regdom)
@@ -165,6 +174,13 @@ static void reset_regdomains(void)
 
 	cfg80211_world_regdom = &world_regdom;
 	cfg80211_regdomain = NULL;
+
+	if (!full_reset)
+		return;
+
+	if (last_request != &core_request_world)
+		kfree(last_request);
+	last_request = &core_request_world;
 }
 
 /*
@@ -175,7 +191,7 @@ static void update_world_regdomain(const struct ieee80211_regdomain *rd)
 {
 	BUG_ON(!last_request);
 
-	reset_regdomains();
+	reset_regdomains(false);
 
 	cfg80211_world_regdom = rd;
 	cfg80211_regdomain = rd;
@@ -1396,7 +1412,8 @@ static int __regulatory_hint(struct wiphy *wiphy,
 	}
 
 new_request:
-	kfree(last_request);
+	if (last_request != &core_request_world)
+		kfree(last_request);
 
 	last_request = pending_request;
 	last_request->intersect = intersect;
@@ -1566,9 +1583,6 @@ static int regulatory_hint_core(const char *alpha2)
 {
 	struct regulatory_request *request;
 
-	kfree(last_request);
-	last_request = NULL;
-
 	request = kzalloc(sizeof(struct regulatory_request),
 			  GFP_KERNEL);
 	if (!request)
@@ -1766,7 +1780,7 @@ static void restore_regulatory_settings(bool reset_user)
 	mutex_lock(&cfg80211_mutex);
 	mutex_lock(&reg_mutex);
 
-	reset_regdomains();
+	reset_regdomains(true);
 	restore_alpha2(alpha2, reset_user);
 
 	/*
@@ -2026,12 +2040,18 @@ static int __set_regdom(const struct ieee80211_regdomain *rd)
 	}
 
 	request_wiphy = wiphy_idx_to_wiphy(last_request->wiphy_idx);
+	if (!request_wiphy &&
+	    (last_request->initiator == NL80211_REGDOM_SET_BY_DRIVER ||
+	     last_request->initiator == NL80211_REGDOM_SET_BY_COUNTRY_IE)) {
+		schedule_delayed_work(&reg_timeout, 0);
+		return -ENODEV;
+	}
 
 	if (!last_request->intersect) {
 		int r;
 
 		if (last_request->initiator != NL80211_REGDOM_SET_BY_DRIVER) {
-			reset_regdomains();
+			reset_regdomains(false);
 			cfg80211_regdomain = rd;
 			return 0;
 		}
@@ -2052,7 +2072,7 @@ static int __set_regdom(const struct ieee80211_regdomain *rd)
 		if (r)
 			return r;
 
-		reset_regdomains();
+		reset_regdomains(false);
 		cfg80211_regdomain = rd;
 		return 0;
 	}
@@ -2077,7 +2097,7 @@ static int __set_regdom(const struct ieee80211_regdomain *rd)
 
 		rd = NULL;
 
-		reset_regdomains();
+		reset_regdomains(false);
 		cfg80211_regdomain = intersected_rd;
 
 		return 0;
@@ -2097,7 +2117,7 @@ static int __set_regdom(const struct ieee80211_regdomain *rd)
 	kfree(rd);
 	rd = NULL;
 
-	reset_regdomains();
+	reset_regdomains(false);
 	cfg80211_regdomain = intersected_rd;
 
 	return 0;
@@ -2250,9 +2270,9 @@ void /* __init_or_exit */ regulatory_exit(void)
 	mutex_lock(&cfg80211_mutex);
 	mutex_lock(&reg_mutex);
 
-	reset_regdomains();
+	reset_regdomains(true);
 
-	kfree(last_request);
+	dev_set_uevent_suppress(&reg_pdev->dev, true);
 
 	platform_device_unregister(reg_pdev);
 
diff --git a/scripts/kconfig/menu.c b/scripts/kconfig/menu.c
index d66008639a4..beeb92e75f8 100644
--- a/scripts/kconfig/menu.c
+++ b/scripts/kconfig/menu.c
@@ -597,11 +597,10 @@ void menu_get_ext_help(struct menu *menu, struct gstr *help)
 	struct symbol *sym = menu->sym;
 
 	if (menu_has_help(menu)) {
-		if (sym->name) {
+		if (sym->name)
 			str_printf(help, "%s%s:\n\n", CONFIG_, sym->name);
-			str_append(help, _(menu_get_help(menu)));
-			str_append(help, "\n");
-		}
+		str_append(help, _(menu_get_help(menu)));
+		str_append(help, "\n");
 	} else {
 		str_append(help, nohelp_text);
 	}
diff --git a/security/keys/user_defined.c b/security/keys/user_defined.c
index 5b366d7af3c..69ff52c08e9 100644
--- a/security/keys/user_defined.c
+++ b/security/keys/user_defined.c
@@ -102,7 +102,8 @@ int user_update(struct key *key, const void *data, size_t datalen)
 		key->expiry = 0;
 	}
 
-	kfree_rcu(zap, rcu);
+	if (zap)
+		kfree_rcu(zap, rcu);
 
 error:
 	return ret;
diff --git a/sound/pci/hda/alc269_quirks.c b/sound/pci/hda/alc269_quirks.c
index 5ac0e2162a4..9aeeb326460 100644
--- a/sound/pci/hda/alc269_quirks.c
+++ b/sound/pci/hda/alc269_quirks.c
@@ -577,6 +577,9 @@ static const struct alc_config_preset alc269_presets[] = {
 				alc269_laptop_amic_init_verbs },
 		.num_dacs = ARRAY_SIZE(alc269_dac_nids),
 		.dac_nids = alc269_dac_nids,
+		.adc_nids = alc269_adc_nids,
+		.capsrc_nids = alc269_capsrc_nids,
+		.num_adc_nids = ARRAY_SIZE(alc269_adc_nids),
 		.hp_nid = 0x03,
 		.num_channel_mode = ARRAY_SIZE(alc269_modes),
 		.channel_mode = alc269_modes,
@@ -591,6 +594,9 @@ static const struct alc_config_preset alc269_presets[] = {
 				alc269_laptop_dmic_init_verbs },
 		.num_dacs = ARRAY_SIZE(alc269_dac_nids),
 		.dac_nids = alc269_dac_nids,
+		.adc_nids = alc269_adc_nids,
+		.capsrc_nids = alc269_capsrc_nids,
+		.num_adc_nids = ARRAY_SIZE(alc269_adc_nids),
 		.hp_nid = 0x03,
 		.num_channel_mode = ARRAY_SIZE(alc269_modes),
 		.channel_mode = alc269_modes,
@@ -605,6 +611,9 @@ static const struct alc_config_preset alc269_presets[] = {
 				alc269vb_laptop_amic_init_verbs },
 		.num_dacs = ARRAY_SIZE(alc269_dac_nids),
 		.dac_nids = alc269_dac_nids,
+		.adc_nids = alc269vb_adc_nids,
+		.capsrc_nids = alc269vb_capsrc_nids,
+		.num_adc_nids = ARRAY_SIZE(alc269vb_adc_nids),
 		.hp_nid = 0x03,
 		.num_channel_mode = ARRAY_SIZE(alc269_modes),
 		.channel_mode = alc269_modes,
@@ -619,6 +628,9 @@ static const struct alc_config_preset alc269_presets[] = {
 				alc269vb_laptop_dmic_init_verbs },
 		.num_dacs = ARRAY_SIZE(alc269_dac_nids),
 		.dac_nids = alc269_dac_nids,
+		.adc_nids = alc269vb_adc_nids,
+		.capsrc_nids = alc269vb_capsrc_nids,
+		.num_adc_nids = ARRAY_SIZE(alc269vb_adc_nids),
 		.hp_nid = 0x03,
 		.num_channel_mode = ARRAY_SIZE(alc269_modes),
 		.channel_mode = alc269_modes,
@@ -633,6 +645,8 @@ static const struct alc_config_preset alc269_presets[] = {
 				alc269_laptop_dmic_init_verbs },
 		.num_dacs = ARRAY_SIZE(alc269_dac_nids),
 		.dac_nids = alc269_dac_nids,
+		.adc_nids = alc269_adc_nids,
+		.capsrc_nids = alc269_capsrc_nids,
 		.hp_nid = 0x03,
 		.num_channel_mode = ARRAY_SIZE(alc269_modes),
 		.channel_mode = alc269_modes,
diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c
index f3aefef3721..3a1b47a9002 100644
--- a/sound/pci/hda/hda_codec.c
+++ b/sound/pci/hda/hda_codec.c
@@ -2296,6 +2296,39 @@ int snd_hda_codec_reset(struct hda_codec *codec)
 	return 0;
 }
 
+typedef int (*map_slave_func_t)(void *, struct snd_kcontrol *);
+
+/* apply the function to all matching slave ctls in the mixer list */
+static int map_slaves(struct hda_codec *codec, const char * const *slaves,
+		      map_slave_func_t func, void *data)
+{
+	struct hda_nid_item *items;
+	const char * const *s;
+	int i, err;
+
+	items = codec->mixers.list;
+	for (i = 0; i < codec->mixers.used; i++) {
+		struct snd_kcontrol *sctl = items[i].kctl;
+		if (!sctl || !sctl->id.name ||
+		    sctl->id.iface != SNDRV_CTL_ELEM_IFACE_MIXER)
+			continue;
+		for (s = slaves; *s; s++) {
+			if (!strcmp(sctl->id.name, *s)) {
+				err = func(data, sctl);
+				if (err)
+					return err;
+				break;
+			}
+		}
+	}
+	return 0;
+}
+
+static int check_slave_present(void *data, struct snd_kcontrol *sctl)
+{
+	return 1;
+}
+
 /**
  * snd_hda_add_vmaster - create a virtual master control and add slaves
  * @codec: HD-audio codec
@@ -2316,12 +2349,10 @@ int snd_hda_add_vmaster(struct hda_codec *codec, char *name,
 			unsigned int *tlv, const char * const *slaves)
 {
 	struct snd_kcontrol *kctl;
-	const char * const *s;
 	int err;
 
-	for (s = slaves; *s && !snd_hda_find_mixer_ctl(codec, *s); s++)
-		;
-	if (!*s) {
+	err = map_slaves(codec, slaves, check_slave_present, NULL);
+	if (err != 1) {
 		snd_printdd("No slave found for %s\n", name);
 		return 0;
 	}
@@ -2332,23 +2363,10 @@ int snd_hda_add_vmaster(struct hda_codec *codec, char *name,
 	if (err < 0)
 		return err;
 
-	for (s = slaves; *s; s++) {
-		struct snd_kcontrol *sctl;
-		int i = 0;
-		for (;;) {
-			sctl = _snd_hda_find_mixer_ctl(codec, *s, i);
-			if (!sctl) {
-				if (!i)
-					snd_printdd("Cannot find slave %s, "
-						    "skipped\n", *s);
-				break;
-			}
-			err = snd_ctl_add_slave(kctl, sctl);
-			if (err < 0)
-				return err;
-			i++;
-		}
-	}
+	err = map_slaves(codec, slaves, (map_slave_func_t)snd_ctl_add_slave,
+			 kctl);
+	if (err < 0)
+		return err;
 	return 0;
 }
 EXPORT_SYMBOL_HDA(snd_hda_add_vmaster);
diff --git a/sound/pci/hda/hda_eld.c b/sound/pci/hda/hda_eld.c
index c34f730f481..44f199c69c4 100644
--- a/sound/pci/hda/hda_eld.c
+++ b/sound/pci/hda/hda_eld.c
@@ -297,10 +297,10 @@ static int hdmi_update_eld(struct hdmi_eld *e,
 					buf + ELD_FIXED_BYTES + mnl + 3 * i);
 	}
 
+	e->eld_valid = true;
 	return 0;
 
 out_fail:
-	e->eld_ver = 0;
 	return -EINVAL;
 }
 
@@ -318,9 +318,6 @@ int snd_hdmi_get_eld(struct hdmi_eld *eld,
 	int size;
 	unsigned char *buf;
 
-	if (!eld->eld_valid)
-		return -ENOENT;
-
 	size = snd_hdmi_get_eld_size(codec, nid);
 	if (size == 0) {
 		/* wfg: workaround for ASUS P5E-VM HDMI board */
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 191284a1c0a..f6659751f0c 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -2912,12 +2912,12 @@ static DEFINE_PCI_DEVICE_TABLE(azx_ids) = {
 	  .class = PCI_CLASS_MULTIMEDIA_HD_AUDIO << 8,
 	  .class_mask = 0xffffff,
 	  .driver_data = AZX_DRIVER_CTX | AZX_DCAPS_CTX_WORKAROUND |
-	  AZX_DCAPS_RIRB_PRE_DELAY },
+	  AZX_DCAPS_RIRB_PRE_DELAY | AZX_DCAPS_POSFIX_LPIB },
 #else
 	/* this entry seems still valid -- i.e. without emu20kx chip */
 	{ PCI_DEVICE(0x1102, 0x0009),
 	  .driver_data = AZX_DRIVER_CTX | AZX_DCAPS_CTX_WORKAROUND |
-	  AZX_DCAPS_RIRB_PRE_DELAY },
+	  AZX_DCAPS_RIRB_PRE_DELAY | AZX_DCAPS_POSFIX_LPIB },
 #endif
 	/* Vortex86MX */
 	{ PCI_DEVICE(0x17f3, 0x3010), .driver_data = AZX_DRIVER_GENERIC },
diff --git a/sound/pci/hda/patch_cirrus.c b/sound/pci/hda/patch_cirrus.c
index c45f3e69bcf..4346ad2c906 100644
--- a/sound/pci/hda/patch_cirrus.c
+++ b/sound/pci/hda/patch_cirrus.c
@@ -236,6 +236,15 @@ static int cs_dig_playback_pcm_cleanup(struct hda_pcm_stream *hinfo,
 	return snd_hda_multi_out_dig_cleanup(codec, &spec->multiout);
 }
 
+static void cs_update_input_select(struct hda_codec *codec)
+{
+	struct cs_spec *spec = codec->spec;
+	if (spec->cur_adc)
+		snd_hda_codec_write(codec, spec->cur_adc, 0,
+				    AC_VERB_SET_CONNECT_SEL,
+				    spec->adc_idx[spec->cur_input]);
+}
+
 /*
  * Analog capture
  */
@@ -249,6 +258,7 @@ static int cs_capture_pcm_prepare(struct hda_pcm_stream *hinfo,
 	spec->cur_adc = spec->adc_nid[spec->cur_input];
 	spec->cur_adc_stream_tag = stream_tag;
 	spec->cur_adc_format = format;
+	cs_update_input_select(codec);
 	snd_hda_codec_setup_stream(codec, spec->cur_adc, stream_tag, 0, format);
 	return 0;
 }
@@ -688,10 +698,8 @@ static int change_cur_input(struct hda_codec *codec, unsigned int idx,
 					   spec->cur_adc_stream_tag, 0,
 					   spec->cur_adc_format);
 	}
-	snd_hda_codec_write(codec, spec->cur_adc, 0,
-			    AC_VERB_SET_CONNECT_SEL,
-			    spec->adc_idx[idx]);
 	spec->cur_input = idx;
+	cs_update_input_select(codec);
 	return 1;
 }
 
@@ -972,10 +980,7 @@ static void cs_automic(struct hda_codec *codec)
 		} else  {
 			spec->cur_input = spec->last_input;
 		}
-
-		snd_hda_codec_write_cache(codec, spec->cur_adc, 0,
-					AC_VERB_SET_CONNECT_SEL,
-					spec->adc_idx[spec->cur_input]);
+		cs_update_input_select(codec);
 	} else {
 		if (present)
 			change_cur_input(codec, spec->automic_idx, 0);
@@ -1072,9 +1077,7 @@ static void init_input(struct hda_codec *codec)
 			cs_automic(codec);
 		else  {
 			spec->cur_adc = spec->adc_nid[spec->cur_input];
-			snd_hda_codec_write(codec, spec->cur_adc, 0,
-					AC_VERB_SET_CONNECT_SEL,
-					spec->adc_idx[spec->cur_input]);
+			cs_update_input_select(codec);
 		}
 	} else {
 		change_cur_input(codec, spec->cur_input, 1);
diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c
index 76752d8ea73..41fecc1e7ad 100644
--- a/sound/pci/hda/patch_conexant.c
+++ b/sound/pci/hda/patch_conexant.c
@@ -136,6 +136,8 @@ struct conexant_spec {
 	unsigned int thinkpad:1;
 	unsigned int hp_laptop:1;
 	unsigned int asus:1;
+	unsigned int pin_eapd_ctrls:1;
+	unsigned int single_adc_amp:1;
 
 	unsigned int adc_switching:1;
 
@@ -3473,12 +3475,14 @@ static void cx_auto_turn_eapd(struct hda_codec *codec, int num_pins,
 static void do_automute(struct hda_codec *codec, int num_pins,
 			hda_nid_t *pins, bool on)
 {
+	struct conexant_spec *spec = codec->spec;
 	int i;
 	for (i = 0; i < num_pins; i++)
 		snd_hda_codec_write(codec, pins[i], 0,
 				    AC_VERB_SET_PIN_WIDGET_CONTROL,
 				    on ? PIN_OUT : 0);
-	cx_auto_turn_eapd(codec, num_pins, pins, on);
+	if (spec->pin_eapd_ctrls)
+		cx_auto_turn_eapd(codec, num_pins, pins, on);
 }
 
 static int detect_jacks(struct hda_codec *codec, int num_pins, hda_nid_t *pins)
@@ -3503,9 +3507,12 @@ static void cx_auto_update_speakers(struct hda_codec *codec)
 	int on = 1;
 
 	/* turn on HP EAPD when HP jacks are present */
-	if (spec->auto_mute)
-		on = spec->hp_present;
-	cx_auto_turn_eapd(codec, cfg->hp_outs, cfg->hp_pins, on);
+	if (spec->pin_eapd_ctrls) {
+		if (spec->auto_mute)
+			on = spec->hp_present;
+		cx_auto_turn_eapd(codec, cfg->hp_outs, cfg->hp_pins, on);
+	}
+
 	/* mute speakers in auto-mode if HP or LO jacks are plugged */
 	if (spec->auto_mute)
 		on = !(spec->hp_present ||
@@ -3932,20 +3939,10 @@ static void cx_auto_parse_beep(struct hda_codec *codec)
 #define cx_auto_parse_beep(codec)
 #endif
 
-static bool found_in_nid_list(hda_nid_t nid, const hda_nid_t *list, int nums)
-{
-	int i;
-	for (i = 0; i < nums; i++)
-		if (list[i] == nid)
-			return true;
-	return false;
-}
-
-/* parse extra-EAPD that aren't assigned to any pins */
+/* parse EAPDs */
 static void cx_auto_parse_eapd(struct hda_codec *codec)
 {
 	struct conexant_spec *spec = codec->spec;
-	struct auto_pin_cfg *cfg = &spec->autocfg;
 	hda_nid_t nid, end_nid;
 
 	end_nid = codec->start_nid + codec->num_nodes;
@@ -3954,14 +3951,18 @@ static void cx_auto_parse_eapd(struct hda_codec *codec)
 			continue;
 		if (!(snd_hda_query_pin_caps(codec, nid) & AC_PINCAP_EAPD))
 			continue;
-		if (found_in_nid_list(nid, cfg->line_out_pins, cfg->line_outs) ||
-		    found_in_nid_list(nid, cfg->hp_pins, cfg->hp_outs) ||
-		    found_in_nid_list(nid, cfg->speaker_pins, cfg->speaker_outs))
-			continue;
 		spec->eapds[spec->num_eapds++] = nid;
 		if (spec->num_eapds >= ARRAY_SIZE(spec->eapds))
 			break;
 	}
+
+	/* NOTE: below is a wild guess; if we have more than two EAPDs,
+	 * it's a new chip, where EAPDs are supposed to be associated to
+	 * pins, and we can control EAPD per pin.
+	 * OTOH, if only one or two EAPDs are found, it's an old chip,
+	 * thus it might control over all pins.
+	 */
+	spec->pin_eapd_ctrls = spec->num_eapds > 2;
 }
 
 static int cx_auto_parse_auto_config(struct hda_codec *codec)
@@ -4067,8 +4068,9 @@ static void cx_auto_init_output(struct hda_codec *codec)
 		}
 	}
 	cx_auto_update_speakers(codec);
-	/* turn on/off extra EAPDs, too */
-	cx_auto_turn_eapd(codec, spec->num_eapds, spec->eapds, true);
+	/* turn on all EAPDs if no individual EAPD control is available */
+	if (!spec->pin_eapd_ctrls)
+		cx_auto_turn_eapd(codec, spec->num_eapds, spec->eapds, true);
 }
 
 static void cx_auto_init_input(struct hda_codec *codec)
@@ -4255,6 +4257,8 @@ static int cx_auto_add_capture_volume(struct hda_codec *codec, hda_nid_t nid,
 		int idx = get_input_connection(codec, adc_nid, nid);
 		if (idx < 0)
 			continue;
+		if (spec->single_adc_amp)
+			idx = 0;
 		return cx_auto_add_volume_idx(codec, label, pfx,
 					      cidx, adc_nid, HDA_INPUT, idx);
 	}
@@ -4295,14 +4299,21 @@ static int cx_auto_build_input_controls(struct hda_codec *codec)
 	struct hda_input_mux *imux = &spec->private_imux;
 	const char *prev_label;
 	int input_conn[HDA_MAX_NUM_INPUTS];
-	int i, err, cidx;
+	int i, j, err, cidx;
 	int multi_connection;
 
+	if (!imux->num_items)
+		return 0;
+
 	multi_connection = 0;
 	for (i = 0; i < imux->num_items; i++) {
 		cidx = get_input_connection(codec, spec->imux_info[i].adc,
 					    spec->imux_info[i].pin);
-		input_conn[i] = (spec->imux_info[i].adc << 8) | cidx;
+		if (cidx < 0)
+			continue;
+		input_conn[i] = spec->imux_info[i].adc;
+		if (!spec->single_adc_amp)
+			input_conn[i] |= cidx << 8;
 		if (i > 0 && input_conn[i] != input_conn[0])
 			multi_connection = 1;
 	}
@@ -4331,6 +4342,15 @@ static int cx_auto_build_input_controls(struct hda_codec *codec)
 			err = cx_auto_add_capture_volume(codec, nid,
 							 "Capture", "", cidx);
 		} else {
+			bool dup_found = false;
+			for (j = 0; j < i; j++) {
+				if (input_conn[j] == input_conn[i]) {
+					dup_found = true;
+					break;
+				}
+			}
+			if (dup_found)
+				continue;
 			err = cx_auto_add_capture_volume(codec, nid,
 							 label, " Capture", cidx);
 		}
@@ -4407,6 +4427,13 @@ static int patch_conexant_auto(struct hda_codec *codec)
 		return -ENOMEM;
 	codec->spec = spec;
 	codec->pin_amp_workaround = 1;
+
+	switch (codec->vendor_id) {
+	case 0x14f15045:
+		spec->single_adc_amp = 1;
+		break;
+	}
+
 	err = cx_auto_search_adcs(codec);
 	if (err < 0)
 		return err;
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index 19cb72db9c3..e287015cbbb 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -920,20 +920,23 @@ static void hdmi_present_sense(struct hda_codec *codec, hda_nid_t pin_nid,
 	 * the unsolicited response to avoid custom WARs.
 	 */
 	int present = snd_hda_pin_sense(codec, pin_nid);
+	bool eld_valid = false;
 
-	memset(eld, 0, sizeof(*eld));
+#ifdef CONFIG_PROC_FS
+	memset(eld, 0, offsetof(struct hdmi_eld, proc_entry));
+#else
+	memset(eld, 0, sizeof(struct hdmi_eld));
+#endif
 
 	eld->monitor_present	= !!(present & AC_PINSENSE_PRESENCE);
 	if (eld->monitor_present)
-		eld->eld_valid	= !!(present & AC_PINSENSE_ELDV);
-	else
-		eld->eld_valid	= 0;
+		eld_valid	= !!(present & AC_PINSENSE_ELDV);
 
 	printk(KERN_INFO
 		"HDMI status: Codec=%d Pin=%d Presence_Detect=%d ELD_Valid=%d\n",
-		codec->addr, pin_nid, eld->monitor_present, eld->eld_valid);
+		codec->addr, pin_nid, eld->monitor_present, eld_valid);
 
-	if (eld->eld_valid)
+	if (eld_valid)
 		if (!snd_hdmi_get_eld(eld, codec, pin_nid))
 			snd_hdmi_show_eld(eld);
 
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 7a73621a890..c687e14733d 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -1023,8 +1023,20 @@ static bool alc_rebuild_imux_for_auto_mic(struct hda_codec *codec)
 	spec->imux_pins[2] = spec->dock_mic_pin;
 	for (i = 0; i < 3; i++) {
 		strcpy(imux->items[i].label, texts[i]);
-		if (spec->imux_pins[i])
+		if (spec->imux_pins[i]) {
+			hda_nid_t pin = spec->imux_pins[i];
+			int c;
+			for (c = 0; c < spec->num_adc_nids; c++) {
+				hda_nid_t cap = spec->capsrc_nids ?
+				spec->capsrc_nids[c] : spec->adc_nids[c];
+				int idx = get_connection_index(codec, cap, pin);
+				if (idx >= 0) {
+					imux->items[i].index = idx;
+					break;
+				}
+			}
 			imux->num_items = i + 1;
+		}
 	}
 	spec->num_mux_defs = 1;
 	spec->input_mux = imux;
@@ -1566,27 +1578,29 @@ static void alc_auto_init_digital(struct hda_codec *codec)
 static void alc_auto_parse_digital(struct hda_codec *codec)
 {
 	struct alc_spec *spec = codec->spec;
-	int i, err;
+	int i, err, nums;
 	hda_nid_t dig_nid;
 
 	/* support multiple SPDIFs; the secondary is set up as a slave */
+	nums = 0;
 	for (i = 0; i < spec->autocfg.dig_outs; i++) {
 		hda_nid_t conn[4];
 		err = snd_hda_get_connections(codec,
 					      spec->autocfg.dig_out_pins[i],
 					      conn, ARRAY_SIZE(conn));
-		if (err < 0)
+		if (err <= 0)
 			continue;
 		dig_nid = conn[0]; /* assume the first element is audio-out */
-		if (!i) {
+		if (!nums) {
 			spec->multiout.dig_out_nid = dig_nid;
 			spec->dig_out_type = spec->autocfg.dig_out_type[0];
 		} else {
 			spec->multiout.slave_dig_outs = spec->slave_dig_outs;
-			if (i >= ARRAY_SIZE(spec->slave_dig_outs) - 1)
+			if (nums >= ARRAY_SIZE(spec->slave_dig_outs) - 1)
 				break;
-			spec->slave_dig_outs[i - 1] = dig_nid;
+			spec->slave_dig_outs[nums - 1] = dig_nid;
 		}
+		nums++;
 	}
 
 	if (spec->autocfg.dig_in_pin) {
@@ -2232,6 +2246,7 @@ static int alc_build_pcms(struct hda_codec *codec)
 	struct alc_spec *spec = codec->spec;
 	struct hda_pcm *info = spec->pcm_rec;
 	const struct hda_pcm_stream *p;
+	bool have_multi_adcs;
 	int i;
 
 	codec->num_pcms = 1;
@@ -2310,8 +2325,11 @@ static int alc_build_pcms(struct hda_codec *codec)
 	/* If the use of more than one ADC is requested for the current
 	 * model, configure a second analog capture-only PCM.
 	 */
+	have_multi_adcs = (spec->num_adc_nids > 1) &&
+		!spec->dyn_adc_switch && !spec->auto_mic &&
+		(!spec->input_mux || spec->input_mux->num_items > 1);
 	/* Additional Analaog capture for index #2 */
-	if (spec->alt_dac_nid || spec->num_adc_nids > 1) {
+	if (spec->alt_dac_nid || have_multi_adcs) {
 		codec->num_pcms = 3;
 		info = spec->pcm_rec + 2;
 		info->name = spec->stream_name_analog;
@@ -2327,7 +2345,7 @@ static int alc_build_pcms(struct hda_codec *codec)
 				alc_pcm_null_stream;
 			info->stream[SNDRV_PCM_STREAM_PLAYBACK].nid = 0;
 		}
-		if (spec->num_adc_nids > 1) {
+		if (have_multi_adcs) {
 			p = spec->stream_analog_alt_capture;
 			if (!p)
 				p = &alc_pcm_analog_alt_capture;
@@ -3071,6 +3089,12 @@ static void alc_auto_set_output_and_unmute(struct hda_codec *codec,
 	if (nid)
 		snd_hda_codec_write(codec, nid, 0, AC_VERB_SET_AMP_GAIN_MUTE,
 				    AMP_OUT_ZERO);
+
+	/* unmute DAC if it's not assigned to a mixer */
+	nid = alc_look_for_out_mute_nid(codec, pin, dac);
+	if (nid == mix && nid_has_mute(codec, dac, HDA_OUTPUT))
+		snd_hda_codec_write(codec, dac, 0, AC_VERB_SET_AMP_GAIN_MUTE,
+				    AMP_OUT_ZERO);
 }
 
 static void alc_auto_init_multi_out(struct hda_codec *codec)
@@ -5421,6 +5445,8 @@ static const struct hda_codec_preset snd_hda_preset_realtek[] = {
 	  .patch = patch_alc882 },
 	{ .id = 0x10ec0662, .rev = 0x100101, .name = "ALC662 rev1",
 	  .patch = patch_alc662 },
+	{ .id = 0x10ec0662, .rev = 0x100300, .name = "ALC662 rev3",
+	  .patch = patch_alc662 },
 	{ .id = 0x10ec0663, .name = "ALC663", .patch = patch_alc662 },
 	{ .id = 0x10ec0665, .name = "ALC665", .patch = patch_alc662 },
 	{ .id = 0x10ec0670, .name = "ALC670", .patch = patch_alc662 },
diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c
index 987e3cf71a0..4538caa1fca 100644
--- a/sound/pci/hda/patch_sigmatel.c
+++ b/sound/pci/hda/patch_sigmatel.c
@@ -94,6 +94,7 @@ enum {
 	STAC_92HD83XXX_REF,
 	STAC_92HD83XXX_PWR_REF,
 	STAC_DELL_S14,
+	STAC_DELL_VOSTRO_3500,
 	STAC_92HD83XXX_HP,
 	STAC_92HD83XXX_HP_cNB11_INTQUAD,
 	STAC_HP_DV7_4000,
@@ -1658,6 +1659,12 @@ static const unsigned int dell_s14_pin_configs[10] = {
 	0x40f000f0, 0x40f000f0,
 };
 
+static const unsigned int dell_vostro_3500_pin_configs[10] = {
+	0x02a11020, 0x0221101f, 0x400000f0, 0x90170110,
+	0x400000f1, 0x400000f2, 0x400000f3, 0x90a60160,
+	0x400000f4, 0x400000f5,
+};
+
 static const unsigned int hp_dv7_4000_pin_configs[10] = {
 	0x03a12050, 0x0321201f, 0x40f000f0, 0x90170110,
 	0x40f000f0, 0x40f000f0, 0x90170110, 0xd5a30140,
@@ -1674,6 +1681,7 @@ static const unsigned int *stac92hd83xxx_brd_tbl[STAC_92HD83XXX_MODELS] = {
 	[STAC_92HD83XXX_REF] = ref92hd83xxx_pin_configs,
 	[STAC_92HD83XXX_PWR_REF] = ref92hd83xxx_pin_configs,
 	[STAC_DELL_S14] = dell_s14_pin_configs,
+	[STAC_DELL_VOSTRO_3500] = dell_vostro_3500_pin_configs,
 	[STAC_92HD83XXX_HP_cNB11_INTQUAD] = hp_cNB11_intquad_pin_configs,
 	[STAC_HP_DV7_4000] = hp_dv7_4000_pin_configs,
 };
@@ -1683,6 +1691,7 @@ static const char * const stac92hd83xxx_models[STAC_92HD83XXX_MODELS] = {
 	[STAC_92HD83XXX_REF] = "ref",
 	[STAC_92HD83XXX_PWR_REF] = "mic-ref",
 	[STAC_DELL_S14] = "dell-s14",
+	[STAC_DELL_VOSTRO_3500] = "dell-vostro-3500",
 	[STAC_92HD83XXX_HP] = "hp",
 	[STAC_92HD83XXX_HP_cNB11_INTQUAD] = "hp_cNB11_intquad",
 	[STAC_HP_DV7_4000] = "hp-dv7-4000",
@@ -1696,6 +1705,8 @@ static const struct snd_pci_quirk stac92hd83xxx_cfg_tbl[] = {
 		      "DFI LanParty", STAC_92HD83XXX_REF),
 	SND_PCI_QUIRK(PCI_VENDOR_ID_DELL, 0x02ba,
 		      "unknown Dell", STAC_DELL_S14),
+	SND_PCI_QUIRK(PCI_VENDOR_ID_DELL, 0x1028,
+		      "Dell Vostro 3500", STAC_DELL_VOSTRO_3500),
 	SND_PCI_QUIRK_MASK(PCI_VENDOR_ID_HP, 0xff00, 0x3600,
 			  "HP", STAC_92HD83XXX_HP),
 	SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x1656,
@@ -5024,20 +5035,6 @@ static int stac92xx_pre_resume(struct hda_codec *codec)
 	return 0;
 }
 
-static int stac92xx_post_suspend(struct hda_codec *codec)
-{
-	struct sigmatel_spec *spec = codec->spec;
-	if (spec->gpio_led > 8) {
-		/* with vref-out pin used for mute led control
-		 * codec AFG is prevented from D3 state, but on
-		 * system suspend it can (and should) be used
-		 */
-		snd_hda_codec_read(codec, codec->afg, 0,
-				AC_VERB_SET_POWER_STATE, AC_PWRST_D3);
-	}
-	return 0;
-}
-
 static void stac92xx_set_power_state(struct hda_codec *codec, hda_nid_t fg,
 				unsigned int power_state)
 {
@@ -5585,9 +5582,7 @@ static void stac92hd8x_fill_auto_spec(struct hda_codec *codec)
 static int patch_stac92hd83xxx(struct hda_codec *codec)
 {
 	struct sigmatel_spec *spec;
-	hda_nid_t conn[STAC92HD83_DAC_COUNT + 1];
 	int err;
-	int num_dacs;
 
 	spec  = kzalloc(sizeof(*spec), GFP_KERNEL);
 	if (spec == NULL)
@@ -5627,26 +5622,8 @@ again:
 		stac92xx_set_config_regs(codec,
 				stac92hd83xxx_brd_tbl[spec->board_config]);
 
-	switch (codec->vendor_id) {
-	case 0x111d76d1:
-	case 0x111d76d9:
-	case 0x111d76df:
-	case 0x111d76e5:
-	case 0x111d7666:
-	case 0x111d7667:
-	case 0x111d7668:
-	case 0x111d7669:
-	case 0x111d76e3:
-	case 0x111d7604:
-	case 0x111d76d4:
-	case 0x111d7605:
-	case 0x111d76d5:
-	case 0x111d76e7:
-		if (spec->board_config == STAC_92HD83XXX_PWR_REF)
-			break;
+	if (spec->board_config != STAC_92HD83XXX_PWR_REF)
 		spec->num_pwrs = 0;
-		break;
-	}
 
 	codec->patch_ops = stac92xx_patch_ops;
 
@@ -5664,8 +5641,6 @@ again:
 		} else {
 			codec->patch_ops.set_power_state =
 					stac92xx_set_power_state;
-			codec->patch_ops.post_suspend =
-					stac92xx_post_suspend;
 		}
 		codec->patch_ops.pre_resume = stac92xx_pre_resume;
 		codec->patch_ops.check_power_status =
@@ -5673,7 +5648,11 @@ again:
 	}
 #endif	
 
-	err = stac92xx_parse_auto_config(codec, 0x1d, 0);
+	/* 92HD65/66 series has S/PDIF-IN */
+	if (codec->vendor_id >= 0x111d76e8 && codec->vendor_id <= 0x111d76f3)
+		err = stac92xx_parse_auto_config(codec, 0x1d, 0x22);
+	else
+		err = stac92xx_parse_auto_config(codec, 0x1d, 0);
 	if (!err) {
 		if (spec->board_config < 0) {
 			printk(KERN_WARNING "hda_codec: No auto-config is "
@@ -5689,22 +5668,6 @@ again:
 		return err;
 	}
 
-	/* docking output support */
-	num_dacs = snd_hda_get_connections(codec, 0xF,
-				conn, STAC92HD83_DAC_COUNT + 1) - 1;
-	/* skip non-DAC connections */
-	while (num_dacs >= 0 &&
-			(get_wcaps_type(get_wcaps(codec, conn[num_dacs]))
-					!= AC_WID_AUD_OUT))
-		num_dacs--;
-	/* set port E and F to select the last DAC */
-	if (num_dacs >= 0) {
-		snd_hda_codec_write_cache(codec, 0xE, 0,
-			AC_VERB_SET_CONNECT_SEL, num_dacs);
-		snd_hda_codec_write_cache(codec, 0xF, 0,
-			AC_VERB_SET_CONNECT_SEL, num_dacs);
-	}
-
 	codec->proc_widget_hook = stac92hd_proc_hook;
 
 	return 0;
@@ -5999,8 +5962,6 @@ again:
 		} else {
 			codec->patch_ops.set_power_state =
 					stac92xx_set_power_state;
-			codec->patch_ops.post_suspend =
-					stac92xx_post_suspend;
 		}
 		codec->patch_ops.pre_resume = stac92xx_pre_resume;
 		codec->patch_ops.check_power_status =
@@ -6579,6 +6540,18 @@ static const struct hda_codec_preset snd_hda_preset_sigmatel[] = {
 	{ .id = 0x111d76e3, .name = "92HD98BXX", .patch = patch_stac92hd83xxx},
 	{ .id = 0x111d76e5, .name = "92HD99BXX", .patch = patch_stac92hd83xxx},
 	{ .id = 0x111d76e7, .name = "92HD90BXX", .patch = patch_stac92hd83xxx},
+	{ .id = 0x111d76e8, .name = "92HD66B1X5", .patch = patch_stac92hd83xxx},
+	{ .id = 0x111d76e9, .name = "92HD66B2X5", .patch = patch_stac92hd83xxx},
+	{ .id = 0x111d76ea, .name = "92HD66B3X5", .patch = patch_stac92hd83xxx},
+	{ .id = 0x111d76eb, .name = "92HD66C1X5", .patch = patch_stac92hd83xxx},
+	{ .id = 0x111d76ec, .name = "92HD66C2X5", .patch = patch_stac92hd83xxx},
+	{ .id = 0x111d76ed, .name = "92HD66C3X5", .patch = patch_stac92hd83xxx},
+	{ .id = 0x111d76ee, .name = "92HD66B1X3", .patch = patch_stac92hd83xxx},
+	{ .id = 0x111d76ef, .name = "92HD66B2X3", .patch = patch_stac92hd83xxx},
+	{ .id = 0x111d76f0, .name = "92HD66B3X3", .patch = patch_stac92hd83xxx},
+	{ .id = 0x111d76f1, .name = "92HD66C1X3", .patch = patch_stac92hd83xxx},
+	{ .id = 0x111d76f2, .name = "92HD66C2X3", .patch = patch_stac92hd83xxx},
+	{ .id = 0x111d76f3, .name = "92HD66C3/65", .patch = patch_stac92hd83xxx},
 	{} /* terminator */
 };
 
diff --git a/sound/pci/hda/patch_via.c b/sound/pci/hda/patch_via.c
index 4ebfbd874c9..d636d939641 100644
--- a/sound/pci/hda/patch_via.c
+++ b/sound/pci/hda/patch_via.c
@@ -207,6 +207,7 @@ struct via_spec {
 	/* work to check hp jack state */
 	struct hda_codec *codec;
 	struct delayed_work vt1708_hp_work;
+	int hp_work_active;
 	int vt1708_jack_detect;
 	int vt1708_hp_present;
 
@@ -304,27 +305,35 @@ enum {
 static void analog_low_current_mode(struct hda_codec *codec);
 static bool is_aa_path_mute(struct hda_codec *codec);
 
-static void vt1708_start_hp_work(struct via_spec *spec)
+#define hp_detect_with_aa(codec) \
+	(snd_hda_get_bool_hint(codec, "analog_loopback_hp_detect") == 1 && \
+	 !is_aa_path_mute(codec))
+
+static void vt1708_stop_hp_work(struct via_spec *spec)
 {
 	if (spec->codec_type != VT1708 || spec->autocfg.hp_pins[0] == 0)
 		return;
-	snd_hda_codec_write(spec->codec, 0x1, 0, 0xf81,
-			    !spec->vt1708_jack_detect);
-	if (!delayed_work_pending(&spec->vt1708_hp_work))
-		schedule_delayed_work(&spec->vt1708_hp_work,
-				      msecs_to_jiffies(100));
+	if (spec->hp_work_active) {
+		snd_hda_codec_write(spec->codec, 0x1, 0, 0xf81, 1);
+		cancel_delayed_work_sync(&spec->vt1708_hp_work);
+		spec->hp_work_active = 0;
+	}
 }
 
-static void vt1708_stop_hp_work(struct via_spec *spec)
+static void vt1708_update_hp_work(struct via_spec *spec)
 {
 	if (spec->codec_type != VT1708 || spec->autocfg.hp_pins[0] == 0)
 		return;
-	if (snd_hda_get_bool_hint(spec->codec, "analog_loopback_hp_detect") == 1
-	    && !is_aa_path_mute(spec->codec))
-		return;
-	snd_hda_codec_write(spec->codec, 0x1, 0, 0xf81,
-			    !spec->vt1708_jack_detect);
-	cancel_delayed_work_sync(&spec->vt1708_hp_work);
+	if (spec->vt1708_jack_detect &&
+	    (spec->active_streams || hp_detect_with_aa(spec->codec))) {
+		if (!spec->hp_work_active) {
+			snd_hda_codec_write(spec->codec, 0x1, 0, 0xf81, 0);
+			schedule_delayed_work(&spec->vt1708_hp_work,
+					      msecs_to_jiffies(100));
+			spec->hp_work_active = 1;
+		}
+	} else if (!hp_detect_with_aa(spec->codec))
+		vt1708_stop_hp_work(spec);
 }
 
 static void set_widgets_power_state(struct hda_codec *codec)
@@ -342,12 +351,7 @@ static int analog_input_switch_put(struct snd_kcontrol *kcontrol,
 
 	set_widgets_power_state(codec);
 	analog_low_current_mode(snd_kcontrol_chip(kcontrol));
-	if (snd_hda_get_bool_hint(codec, "analog_loopback_hp_detect") == 1) {
-		if (is_aa_path_mute(codec))
-			vt1708_start_hp_work(codec->spec);
-		else
-			vt1708_stop_hp_work(codec->spec);
-	}
+	vt1708_update_hp_work(codec->spec);
 	return change;
 }
 
@@ -1153,7 +1157,7 @@ static int via_playback_multi_pcm_prepare(struct hda_pcm_stream *hinfo,
 	spec->cur_dac_stream_tag = stream_tag;
 	spec->cur_dac_format = format;
 	mutex_unlock(&spec->config_mutex);
-	vt1708_start_hp_work(spec);
+	vt1708_update_hp_work(spec);
 	return 0;
 }
 
@@ -1173,7 +1177,7 @@ static int via_playback_hp_pcm_prepare(struct hda_pcm_stream *hinfo,
 	spec->cur_hp_stream_tag = stream_tag;
 	spec->cur_hp_format = format;
 	mutex_unlock(&spec->config_mutex);
-	vt1708_start_hp_work(spec);
+	vt1708_update_hp_work(spec);
 	return 0;
 }
 
@@ -1187,7 +1191,7 @@ static int via_playback_multi_pcm_cleanup(struct hda_pcm_stream *hinfo,
 	snd_hda_multi_out_analog_cleanup(codec, &spec->multiout);
 	spec->active_streams &= ~STREAM_MULTI_OUT;
 	mutex_unlock(&spec->config_mutex);
-	vt1708_stop_hp_work(spec);
+	vt1708_update_hp_work(spec);
 	return 0;
 }
 
@@ -1202,7 +1206,7 @@ static int via_playback_hp_pcm_cleanup(struct hda_pcm_stream *hinfo,
 		snd_hda_codec_setup_stream(codec, spec->hp_dac_nid, 0, 0, 0);
 	spec->active_streams &= ~STREAM_INDEP_HP;
 	mutex_unlock(&spec->config_mutex);
-	vt1708_stop_hp_work(spec);
+	vt1708_update_hp_work(spec);
 	return 0;
 }
 
@@ -1632,7 +1636,8 @@ static void via_hp_automute(struct hda_codec *codec)
 	int nums;
 	struct via_spec *spec = codec->spec;
 
-	if (!spec->hp_independent_mode && spec->autocfg.hp_pins[0])
+	if (!spec->hp_independent_mode && spec->autocfg.hp_pins[0] &&
+	    (spec->codec_type != VT1708 || spec->vt1708_jack_detect))
 		present = snd_hda_jack_detect(codec, spec->autocfg.hp_pins[0]);
 
 	if (spec->smart51_enabled)
@@ -2599,8 +2604,6 @@ static int vt1708_jack_detect_get(struct snd_kcontrol *kcontrol,
 
 	if (spec->codec_type != VT1708)
 		return 0;
-	spec->vt1708_jack_detect =
-		!((snd_hda_codec_read(codec, 0x1, 0, 0xf84, 0) >> 8) & 0x1);
 	ucontrol->value.integer.value[0] = spec->vt1708_jack_detect;
 	return 0;
 }
@@ -2610,18 +2613,22 @@ static int vt1708_jack_detect_put(struct snd_kcontrol *kcontrol,
 {
 	struct hda_codec *codec = snd_kcontrol_chip(kcontrol);
 	struct via_spec *spec = codec->spec;
-	int change;
+	int val;
 
 	if (spec->codec_type != VT1708)
 		return 0;
-	spec->vt1708_jack_detect = ucontrol->value.integer.value[0];
-	change = (0x1 & (snd_hda_codec_read(codec, 0x1, 0, 0xf84, 0) >> 8))
-		== !spec->vt1708_jack_detect;
-	if (spec->vt1708_jack_detect) {
+	val = !!ucontrol->value.integer.value[0];
+	if (spec->vt1708_jack_detect == val)
+		return 0;
+	spec->vt1708_jack_detect = val;
+	if (spec->vt1708_jack_detect &&
+	    snd_hda_get_bool_hint(codec, "analog_loopback_hp_detect") != 1) {
 		mute_aa_path(codec, 1);
 		notify_aa_path_ctls(codec);
 	}
-	return change;
+	via_hp_automute(codec);
+	vt1708_update_hp_work(spec);
+	return 1;
 }
 
 static const struct snd_kcontrol_new vt1708_jack_detect_ctl = {
@@ -2758,6 +2765,7 @@ static int via_init(struct hda_codec *codec)
 	via_auto_init_unsol_event(codec);
 
 	via_hp_automute(codec);
+	vt1708_update_hp_work(spec);
 
 	return 0;
 }
@@ -2774,7 +2782,9 @@ static void vt1708_update_hp_jack_state(struct work_struct *work)
 		spec->vt1708_hp_present ^= 1;
 		via_hp_automute(spec->codec);
 	}
-	vt1708_start_hp_work(spec);
+	if (spec->vt1708_jack_detect)
+		schedule_delayed_work(&spec->vt1708_hp_work,
+				      msecs_to_jiffies(100));
 }
 
 static int get_mux_nids(struct hda_codec *codec)
diff --git a/sound/pci/lx6464es/lx_core.c b/sound/pci/lx6464es/lx_core.c
index 5c8717e29ee..aa733725c56 100644
--- a/sound/pci/lx6464es/lx_core.c
+++ b/sound/pci/lx6464es/lx_core.c
@@ -80,8 +80,12 @@ unsigned long lx_dsp_reg_read(struct lx6464es *chip, int port)
 
 void lx_dsp_reg_readbuf(struct lx6464es *chip, int port, u32 *data, u32 len)
 {
-	void __iomem *address = lx_dsp_register(chip, port);
-	memcpy_fromio(data, address, len*sizeof(u32));
+	u32 __iomem *address = lx_dsp_register(chip, port);
+	int i;
+
+	/* we cannot use memcpy_fromio */
+	for (i = 0; i != len; ++i)
+		data[i] = ioread32(address + i);
 }
 
 
@@ -94,8 +98,12 @@ void lx_dsp_reg_write(struct lx6464es *chip, int port, unsigned data)
 void lx_dsp_reg_writebuf(struct lx6464es *chip, int port, const u32 *data,
 			 u32 len)
 {
-	void __iomem *address = lx_dsp_register(chip, port);
-	memcpy_toio(address, data, len*sizeof(u32));
+	u32 __iomem *address = lx_dsp_register(chip, port);
+	int i;
+
+	/* we cannot use memcpy_to */
+	for (i = 0; i != len; ++i)
+		iowrite32(data[i], address + i);
 }
 
 
diff --git a/sound/soc/codecs/ad1836.h b/sound/soc/codecs/ad1836.h
index 444747f0db2..dd7be0dbbc5 100644
--- a/sound/soc/codecs/ad1836.h
+++ b/sound/soc/codecs/ad1836.h
@@ -34,7 +34,7 @@
 
 #define AD1836_ADC_CTRL2               13
 #define AD1836_ADC_WORD_LEN_MASK       0x30
-#define AD1836_ADC_WORD_OFFSET         5
+#define AD1836_ADC_WORD_OFFSET         4
 #define AD1836_ADC_SERFMT_MASK         (7 << 6)
 #define AD1836_ADC_SERFMT_PCK256       (0x4 << 6)
 #define AD1836_ADC_SERFMT_PCK128       (0x5 << 6)
diff --git a/sound/soc/codecs/ak4535.c b/sound/soc/codecs/ak4535.c
index e1a214ee757..65abd09e1ca 100644
--- a/sound/soc/codecs/ak4535.c
+++ b/sound/soc/codecs/ak4535.c
@@ -40,11 +40,11 @@ struct ak4535_priv {
 /*
  * ak4535 register cache
  */
-static const u16 ak4535_reg[AK4535_CACHEREGNUM] = {
-    0x0000, 0x0080, 0x0000, 0x0003,
-    0x0002, 0x0000, 0x0011, 0x0001,
-    0x0000, 0x0040, 0x0036, 0x0010,
-    0x0000, 0x0000, 0x0057, 0x0000,
+static const u8 ak4535_reg[AK4535_CACHEREGNUM] = {
+	0x00, 0x80, 0x00, 0x03,
+	0x02, 0x00, 0x11, 0x01,
+	0x00, 0x40, 0x36, 0x10,
+	0x00, 0x00, 0x57, 0x00,
 };
 
 /*
diff --git a/sound/soc/codecs/ak4642.c b/sound/soc/codecs/ak4642.c
index 65f46047b1c..79c1b3d79f1 100644
--- a/sound/soc/codecs/ak4642.c
+++ b/sound/soc/codecs/ak4642.c
@@ -162,17 +162,17 @@ struct ak4642_priv {
 /*
  * ak4642 register cache
  */
-static const u16 ak4642_reg[AK4642_CACHEREGNUM] = {
-	0x0000, 0x0000, 0x0001, 0x0000,
-	0x0002, 0x0000, 0x0000, 0x0000,
-	0x00e1, 0x00e1, 0x0018, 0x0000,
-	0x00e1, 0x0018, 0x0011, 0x0008,
-	0x0000, 0x0000, 0x0000, 0x0000,
-	0x0000, 0x0000, 0x0000, 0x0000,
-	0x0000, 0x0000, 0x0000, 0x0000,
-	0x0000, 0x0000, 0x0000, 0x0000,
-	0x0000, 0x0000, 0x0000, 0x0000,
-	0x0000,
+static const u8 ak4642_reg[AK4642_CACHEREGNUM] = {
+	0x00, 0x00, 0x01, 0x00,
+	0x02, 0x00, 0x00, 0x00,
+	0xe1, 0xe1, 0x18, 0x00,
+	0xe1, 0x18, 0x11, 0x08,
+	0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+	0x00,
 };
 
 /*
diff --git a/sound/soc/codecs/sta32x.c b/sound/soc/codecs/sta32x.c
index fbd7eb9e61c..d5630aff6a0 100644
--- a/sound/soc/codecs/sta32x.c
+++ b/sound/soc/codecs/sta32x.c
@@ -76,6 +76,8 @@ struct sta32x_priv {
 
 	unsigned int mclk;
 	unsigned int format;
+
+	u32 coef_shadow[STA32X_COEF_COUNT];
 };
 
 static const DECLARE_TLV_DB_SCALE(mvol_tlv, -12700, 50, 1);
@@ -227,6 +229,7 @@ static int sta32x_coefficient_put(struct snd_kcontrol *kcontrol,
 				  struct snd_ctl_elem_value *ucontrol)
 {
 	struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
+	struct sta32x_priv *sta32x = snd_soc_codec_get_drvdata(codec);
 	int numcoef = kcontrol->private_value >> 16;
 	int index = kcontrol->private_value & 0xffff;
 	unsigned int cfud;
@@ -239,6 +242,11 @@ static int sta32x_coefficient_put(struct snd_kcontrol *kcontrol,
 	snd_soc_write(codec, STA32X_CFUD, cfud);
 
 	snd_soc_write(codec, STA32X_CFADDR2, index);
+	for (i = 0; i < numcoef && (index + i < STA32X_COEF_COUNT); i++)
+		sta32x->coef_shadow[index + i] =
+			  (ucontrol->value.bytes.data[3 * i] << 16)
+			| (ucontrol->value.bytes.data[3 * i + 1] << 8)
+			| (ucontrol->value.bytes.data[3 * i + 2]);
 	for (i = 0; i < 3 * numcoef; i++)
 		snd_soc_write(codec, STA32X_B1CF1 + i,
 			      ucontrol->value.bytes.data[i]);
@@ -252,6 +260,48 @@ static int sta32x_coefficient_put(struct snd_kcontrol *kcontrol,
 	return 0;
 }
 
+int sta32x_sync_coef_shadow(struct snd_soc_codec *codec)
+{
+	struct sta32x_priv *sta32x = snd_soc_codec_get_drvdata(codec);
+	unsigned int cfud;
+	int i;
+
+	/* preserve reserved bits in STA32X_CFUD */
+	cfud = snd_soc_read(codec, STA32X_CFUD) & 0xf0;
+
+	for (i = 0; i < STA32X_COEF_COUNT; i++) {
+		snd_soc_write(codec, STA32X_CFADDR2, i);
+		snd_soc_write(codec, STA32X_B1CF1,
+			      (sta32x->coef_shadow[i] >> 16) & 0xff);
+		snd_soc_write(codec, STA32X_B1CF2,
+			      (sta32x->coef_shadow[i] >> 8) & 0xff);
+		snd_soc_write(codec, STA32X_B1CF3,
+			      (sta32x->coef_shadow[i]) & 0xff);
+		/* chip documentation does not say if the bits are
+		 * self-clearing, so do it explicitly */
+		snd_soc_write(codec, STA32X_CFUD, cfud);
+		snd_soc_write(codec, STA32X_CFUD, cfud | 0x01);
+	}
+	return 0;
+}
+
+int sta32x_cache_sync(struct snd_soc_codec *codec)
+{
+	unsigned int mute;
+	int rc;
+
+	if (!codec->cache_sync)
+		return 0;
+
+	/* mute during register sync */
+	mute = snd_soc_read(codec, STA32X_MMUTE);
+	snd_soc_write(codec, STA32X_MMUTE, mute | STA32X_MMUTE_MMUTE);
+	sta32x_sync_coef_shadow(codec);
+	rc = snd_soc_cache_sync(codec);
+	snd_soc_write(codec, STA32X_MMUTE, mute);
+	return rc;
+}
+
 #define SINGLE_COEF(xname, index) \
 {	.iface = SNDRV_CTL_ELEM_IFACE_MIXER, .name = xname, \
 	.info = sta32x_coefficient_info, \
@@ -657,7 +707,7 @@ static int sta32x_set_bias_level(struct snd_soc_codec *codec,
 				return ret;
 			}
 
-			snd_soc_cache_sync(codec);
+			sta32x_cache_sync(codec);
 		}
 
 		/* Power up to mute */
@@ -792,6 +842,17 @@ static int sta32x_probe(struct snd_soc_codec *codec)
 			    STA32X_CxCFG_OM_MASK,
 			    2 << STA32X_CxCFG_OM_SHIFT);
 
+	/* initialize coefficient shadow RAM with reset values */
+	for (i = 4; i <= 49; i += 5)
+		sta32x->coef_shadow[i] = 0x400000;
+	for (i = 50; i <= 54; i++)
+		sta32x->coef_shadow[i] = 0x7fffff;
+	sta32x->coef_shadow[55] = 0x5a9df7;
+	sta32x->coef_shadow[56] = 0x7fffff;
+	sta32x->coef_shadow[59] = 0x7fffff;
+	sta32x->coef_shadow[60] = 0x400000;
+	sta32x->coef_shadow[61] = 0x400000;
+
 	sta32x_set_bias_level(codec, SND_SOC_BIAS_STANDBY);
 	/* Bias level configuration will have done an extra enable */
 	regulator_bulk_disable(ARRAY_SIZE(sta32x->supplies), sta32x->supplies);
diff --git a/sound/soc/codecs/sta32x.h b/sound/soc/codecs/sta32x.h
index b97ee5a7566..d8e32a6262e 100644
--- a/sound/soc/codecs/sta32x.h
+++ b/sound/soc/codecs/sta32x.h
@@ -19,6 +19,7 @@
 /* STA326 register addresses */
 
 #define STA32X_REGISTER_COUNT	0x2d
+#define STA32X_COEF_COUNT 62
 
 #define STA32X_CONFA	0x00
 #define STA32X_CONFB    0x01
diff --git a/sound/soc/codecs/wm8711.c b/sound/soc/codecs/wm8711.c
index a537e4af6ae..1dae5c4d993 100644
--- a/sound/soc/codecs/wm8711.c
+++ b/sound/soc/codecs/wm8711.c
@@ -150,7 +150,7 @@ static int wm8711_hw_params(struct snd_pcm_substream *substream,
 {
 	struct snd_soc_codec *codec = dai->codec;
 	struct wm8711_priv *wm8711 =  snd_soc_codec_get_drvdata(codec);
-	u16 iface = snd_soc_read(codec, WM8711_IFACE) & 0xfffc;
+	u16 iface = snd_soc_read(codec, WM8711_IFACE) & 0xfff3;
 	int i = get_coeff(wm8711->sysclk, params_rate(params));
 	u16 srate = (coeff_div[i].sr << 2) |
 		(coeff_div[i].bosr << 1) | coeff_div[i].usb;
@@ -231,7 +231,7 @@ static int wm8711_set_dai_fmt(struct snd_soc_dai *codec_dai,
 		unsigned int fmt)
 {
 	struct snd_soc_codec *codec = codec_dai->codec;
-	u16 iface = 0;
+	u16 iface = snd_soc_read(codec, WM8711_IFACE) & 0x000c;
 
 	/* set master/slave audio interface */
 	switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
diff --git a/sound/soc/codecs/wm8731.c b/sound/soc/codecs/wm8731.c
index 76b4361e9b8..f5a0ec4ade5 100644
--- a/sound/soc/codecs/wm8731.c
+++ b/sound/soc/codecs/wm8731.c
@@ -463,6 +463,7 @@ static int wm8731_set_bias_level(struct snd_soc_codec *codec,
 		snd_soc_write(codec, WM8731_PWR, 0xffff);
 		regulator_bulk_disable(ARRAY_SIZE(wm8731->supplies),
 				       wm8731->supplies);
+		codec->cache_sync = 1;
 		break;
 	}
 	codec->dapm.bias_level = level;
diff --git a/sound/soc/codecs/wm8741.c b/sound/soc/codecs/wm8741.c
index 25af901fe81..c173aee3390 100644
--- a/sound/soc/codecs/wm8741.c
+++ b/sound/soc/codecs/wm8741.c
@@ -337,10 +337,10 @@ static int wm8741_set_dai_fmt(struct snd_soc_dai *codec_dai,
 		iface |= 0x0004;
 		break;
 	case SND_SOC_DAIFMT_DSP_A:
-		iface |= 0x0003;
+		iface |= 0x000C;
 		break;
 	case SND_SOC_DAIFMT_DSP_B:
-		iface |= 0x0013;
+		iface |= 0x001C;
 		break;
 	default:
 		return -EINVAL;
diff --git a/sound/soc/codecs/wm8753.c b/sound/soc/codecs/wm8753.c
index aa091a0d818..66d18a3e57f 100644
--- a/sound/soc/codecs/wm8753.c
+++ b/sound/soc/codecs/wm8753.c
@@ -189,6 +189,9 @@ static int wm8753_set_dai(struct snd_kcontrol *kcontrol,
 	struct wm8753_priv *wm8753 = snd_soc_codec_get_drvdata(codec);
 	u16 ioctl;
 
+	if (wm8753->dai_func == ucontrol->value.integer.value[0])
+		return 0;
+
 	if (codec->active)
 		return -EBUSY;
 
diff --git a/sound/soc/codecs/wm8904.c b/sound/soc/codecs/wm8904.c
index b085575d4aa..cbba0b1d647 100644
--- a/sound/soc/codecs/wm8904.c
+++ b/sound/soc/codecs/wm8904.c
@@ -868,7 +868,7 @@ SOC_ENUM("Right Capture Mode", rin_mode),
 SOC_DOUBLE_R("Capture Volume", WM8904_ANALOGUE_LEFT_INPUT_0,
 	     WM8904_ANALOGUE_RIGHT_INPUT_0, 0, 31, 0),
 SOC_DOUBLE_R("Capture Switch", WM8904_ANALOGUE_LEFT_INPUT_0,
-	     WM8904_ANALOGUE_RIGHT_INPUT_0, 7, 1, 0),
+	     WM8904_ANALOGUE_RIGHT_INPUT_0, 7, 1, 1),
 
 SOC_SINGLE("High Pass Filter Switch", WM8904_ADC_DIGITAL_0, 4, 1, 0),
 SOC_ENUM("High Pass Filter Mode", hpf_mode),
diff --git a/sound/soc/codecs/wm8940.c b/sound/soc/codecs/wm8940.c
index 056daa0010f..d40da04db37 100644
--- a/sound/soc/codecs/wm8940.c
+++ b/sound/soc/codecs/wm8940.c
@@ -470,6 +470,8 @@ static int wm8940_set_bias_level(struct snd_soc_codec *codec,
 		break;
 	}
 
+	codec->dapm.bias_level = level;
+
 	return ret;
 }
 
diff --git a/sound/soc/codecs/wm8962.c b/sound/soc/codecs/wm8962.c
index d2c315fa1b9..c6106753090 100644
--- a/sound/soc/codecs/wm8962.c
+++ b/sound/soc/codecs/wm8962.c
@@ -1959,7 +1959,13 @@ static int wm8962_readable_register(struct snd_soc_codec *codec, unsigned int re
 
 static int wm8962_reset(struct snd_soc_codec *codec)
 {
-	return snd_soc_write(codec, WM8962_SOFTWARE_RESET, 0x6243);
+	int ret;
+
+	ret = snd_soc_write(codec, WM8962_SOFTWARE_RESET, 0x6243);
+	if (ret != 0)
+		return ret;
+
+	return snd_soc_write(codec, WM8962_PLL_SOFTWARE_RESET, 0);
 }
 
 static const DECLARE_TLV_DB_SCALE(inpga_tlv, -2325, 75, 0);
@@ -2021,7 +2027,6 @@ static int wm8962_put_spk_sw(struct snd_kcontrol *kcontrol,
 			    struct snd_ctl_elem_value *ucontrol)
 {
 	struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
-	u16 *reg_cache = codec->reg_cache;
 	int ret;
 
 	/* Apply the update (if any) */
@@ -2030,16 +2035,19 @@ static int wm8962_put_spk_sw(struct snd_kcontrol *kcontrol,
 		return 0;
 
 	/* If the left PGA is enabled hit that VU bit... */
-	if (reg_cache[WM8962_PWR_MGMT_2] & WM8962_SPKOUTL_PGA_ENA)
-		return snd_soc_write(codec, WM8962_SPKOUTL_VOLUME,
-				     reg_cache[WM8962_SPKOUTL_VOLUME]);
+	ret = snd_soc_read(codec, WM8962_PWR_MGMT_2);
+	if (ret & WM8962_SPKOUTL_PGA_ENA) {
+		snd_soc_write(codec, WM8962_SPKOUTL_VOLUME,
+			      snd_soc_read(codec, WM8962_SPKOUTL_VOLUME));
+		return 1;
+	}
 
 	/* ...otherwise the right.  The VU is stereo. */
-	if (reg_cache[WM8962_PWR_MGMT_2] & WM8962_SPKOUTR_PGA_ENA)
-		return snd_soc_write(codec, WM8962_SPKOUTR_VOLUME,
-				     reg_cache[WM8962_SPKOUTR_VOLUME]);
+	if (ret & WM8962_SPKOUTR_PGA_ENA)
+		snd_soc_write(codec, WM8962_SPKOUTR_VOLUME,
+			      snd_soc_read(codec, WM8962_SPKOUTR_VOLUME));
 
-	return 0;
+	return 1;
 }
 
 static const char *cap_hpf_mode_text[] = {
@@ -2225,15 +2233,14 @@ static int sysclk_event(struct snd_soc_dapm_widget *w,
 
 			snd_soc_update_bits(codec, WM8962_FLL_CONTROL_1,
 					    WM8962_FLL_ENA, WM8962_FLL_ENA);
-			if (wm8962->irq) {
-				timeout = msecs_to_jiffies(5);
-				timeout = wait_for_completion_timeout(&wm8962->fll_lock,
-								      timeout);
-
-				if (timeout == 0)
-					dev_err(codec->dev,
-						"Timed out starting FLL\n");
-			}
+
+			timeout = msecs_to_jiffies(5);
+			timeout = wait_for_completion_timeout(&wm8962->fll_lock,
+							      timeout);
+
+			if (wm8962->irq && timeout == 0)
+				dev_err(codec->dev,
+					"Timed out starting FLL\n");
 		}
 		break;
 
@@ -2365,7 +2372,6 @@ static int out_pga_event(struct snd_soc_dapm_widget *w,
 			 struct snd_kcontrol *kcontrol, int event)
 {
 	struct snd_soc_codec *codec = w->codec;
-	u16 *reg_cache = codec->reg_cache;
 	int reg;
 
 	switch (w->shift) {
@@ -2388,7 +2394,7 @@ static int out_pga_event(struct snd_soc_dapm_widget *w,
 
 	switch (event) {
 	case SND_SOC_DAPM_POST_PMU:
-		return snd_soc_write(codec, reg, reg_cache[reg]);
+		return snd_soc_write(codec, reg, snd_soc_read(codec, reg));
 	default:
 		BUG();
 		return -EINVAL;
@@ -3058,9 +3064,9 @@ static int wm8962_set_dai_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 	int aif0 = 0;
 
 	switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
-	case SND_SOC_DAIFMT_DSP_A:
-		aif0 |= WM8962_LRCLK_INV;
 	case SND_SOC_DAIFMT_DSP_B:
+		aif0 |= WM8962_LRCLK_INV | 3;
+	case SND_SOC_DAIFMT_DSP_A:
 		aif0 |= 3;
 
 		switch (fmt & SND_SOC_DAIFMT_INV_MASK) {
@@ -3847,6 +3853,11 @@ static int wm8962_probe(struct snd_soc_codec *codec)
 	snd_soc_update_bits(codec, WM8962_CLOCKING2,
 			    WM8962_CLKREG_OVD, WM8962_CLKREG_OVD);
 
+	/* Ensure that the oscillator and PLLs are disabled */
+	snd_soc_update_bits(codec, WM8962_PLL2,
+			    WM8962_OSC_ENA | WM8962_PLL2_ENA | WM8962_PLL3_ENA,
+			    0);
+
 	regulator_bulk_disable(ARRAY_SIZE(wm8962->supplies), wm8962->supplies);
 
 	if (pdata) {
diff --git a/sound/soc/codecs/wm8994.c b/sound/soc/codecs/wm8994.c
index b393f9fac97..fa0a48066aa 100644
--- a/sound/soc/codecs/wm8994.c
+++ b/sound/soc/codecs/wm8994.c
@@ -56,7 +56,7 @@ static int wm8994_retune_mobile_base[] = {
 static int wm8994_readable(struct snd_soc_codec *codec, unsigned int reg)
 {
 	struct wm8994_priv *wm8994 = snd_soc_codec_get_drvdata(codec);
-	struct wm8994 *control = wm8994->control_data;
+	struct wm8994 *control = codec->control_data;
 
 	switch (reg) {
 	case WM8994_GPIO_1:
@@ -1282,7 +1282,7 @@ SND_SOC_DAPM_MUX("AIF2DAC Mux", SND_SOC_NOPM, 0, 0, &aif2dac_mux),
 SND_SOC_DAPM_MUX("AIF2ADC Mux", SND_SOC_NOPM, 0, 0, &aif2adc_mux),
 
 SND_SOC_DAPM_AIF_IN("AIF3DACDAT", "AIF3 Playback", 0, SND_SOC_NOPM, 0, 0),
-SND_SOC_DAPM_AIF_IN("AIF3ADCDAT", "AIF3 Capture", 0, SND_SOC_NOPM, 0, 0),
+SND_SOC_DAPM_AIF_OUT("AIF3ADCDAT", "AIF3 Capture", 0, SND_SOC_NOPM, 0, 0),
 
 SND_SOC_DAPM_SUPPLY("TOCLK", WM8994_CLOCKING_1, 4, 0, NULL, 0),
 
@@ -2311,7 +2311,7 @@ static void wm8994_aif_shutdown(struct snd_pcm_substream *substream,
 		rate_reg = WM8994_AIF1_RATE;
 		break;
 	case 2:
-		rate_reg = WM8994_AIF1_RATE;
+		rate_reg = WM8994_AIF2_RATE;
 		break;
 	default:
 		break;
diff --git a/sound/soc/codecs/wm8996.c b/sound/soc/codecs/wm8996.c
index 0cdb9d10567..c9c4e5c5949 100644
--- a/sound/soc/codecs/wm8996.c
+++ b/sound/soc/codecs/wm8996.c
@@ -1847,7 +1847,7 @@ static int wm8996_hw_params(struct snd_pcm_substream *substream,
 	snd_soc_update_bits(codec, lrclk_reg, WM8996_AIF1RX_RATE_MASK,
 			    lrclk);
 	snd_soc_update_bits(codec, WM8996_AIF_CLOCKING_2,
-			    WM8996_DSP1_DIV_SHIFT << dsp_shift, dsp);
+			    WM8996_DSP1_DIV_MASK << dsp_shift, dsp);
 
 	return 0;
 }
diff --git a/sound/soc/fsl/fsl_ssi.c b/sound/soc/fsl/fsl_ssi.c
index d48afea5d93..672982924f1 100644
--- a/sound/soc/fsl/fsl_ssi.c
+++ b/sound/soc/fsl/fsl_ssi.c
@@ -703,6 +703,7 @@ static int __devinit fsl_ssi_probe(struct platform_device *pdev)
 
 	/* Initialize the the device_attribute structure */
 	dev_attr = &ssi_private->dev_attr;
+	sysfs_attr_init(&dev_attr->attr);
 	dev_attr->attr.name = "statistics";
 	dev_attr->attr.mode = S_IRUGO;
 	dev_attr->show = fsl_sysfs_ssi_show;
diff --git a/sound/usb/misc/ua101.c b/sound/usb/misc/ua101.c
index 67bec761244..c0609c21030 100644
--- a/sound/usb/misc/ua101.c
+++ b/sound/usb/misc/ua101.c
@@ -459,7 +459,8 @@ static void kill_stream_urbs(struct ua101_stream *stream)
 	unsigned int i;
 
 	for (i = 0; i < stream->queue_length; ++i)
-		usb_kill_urb(&stream->urbs[i]->urb);
+		if (stream->urbs[i])
+			usb_kill_urb(&stream->urbs[i]->urb);
 }
 
 static int enable_iso_interface(struct ua101 *ua, unsigned int intf_index)
@@ -484,6 +485,9 @@ static void disable_iso_interface(struct ua101 *ua, unsigned int intf_index)
 {
 	struct usb_host_interface *alts;
 
+	if (!ua->intf[intf_index])
+		return;
+
 	alts = ua->intf[intf_index]->cur_altsetting;
 	if (alts->desc.bAlternateSetting != 0) {
 		int err = usb_set_interface(ua->dev,
@@ -1144,27 +1148,37 @@ static void free_stream_urbs(struct ua101_stream *stream)
 {
 	unsigned int i;
 
-	for (i = 0; i < stream->queue_length; ++i)
+	for (i = 0; i < stream->queue_length; ++i) {
 		kfree(stream->urbs[i]);
+		stream->urbs[i] = NULL;
+	}
 }
 
 static void free_usb_related_resources(struct ua101 *ua,
 				       struct usb_interface *interface)
 {
 	unsigned int i;
+	struct usb_interface *intf;
 
+	mutex_lock(&ua->mutex);
 	free_stream_urbs(&ua->capture);
 	free_stream_urbs(&ua->playback);
+	mutex_unlock(&ua->mutex);
 	free_stream_buffers(ua, &ua->capture);
 	free_stream_buffers(ua, &ua->playback);
 
-	for (i = 0; i < ARRAY_SIZE(ua->intf); ++i)
-		if (ua->intf[i]) {
-			usb_set_intfdata(ua->intf[i], NULL);
-			if (ua->intf[i] != interface)
+	for (i = 0; i < ARRAY_SIZE(ua->intf); ++i) {
+		mutex_lock(&ua->mutex);
+		intf = ua->intf[i];
+		ua->intf[i] = NULL;
+		mutex_unlock(&ua->mutex);
+		if (intf) {
+			usb_set_intfdata(intf, NULL);
+			if (intf != interface)
 				usb_driver_release_interface(&ua101_driver,
-							     ua->intf[i]);
+							     intf);
 		}
+	}
 }
 
 static void ua101_card_free(struct snd_card *card)
diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c
index cdd19d7fe50..0de7cbd99ea 100644
--- a/sound/usb/mixer.c
+++ b/sound/usb/mixer.c
@@ -765,10 +765,60 @@ static void usb_mixer_elem_free(struct snd_kcontrol *kctl)
  * interface to ALSA control for feature/mixer units
  */
 
+/* volume control quirks */
+static void volume_control_quirks(struct usb_mixer_elem_info *cval,
+				  struct snd_kcontrol *kctl)
+{
+	switch (cval->mixer->chip->usb_id) {
+	case USB_ID(0x0471, 0x0101):
+	case USB_ID(0x0471, 0x0104):
+	case USB_ID(0x0471, 0x0105):
+	case USB_ID(0x0672, 0x1041):
+	/* quirk for UDA1321/N101.
+	 * note that detection between firmware 2.1.1.7 (N101)
+	 * and later 2.1.1.21 is not very clear from datasheets.
+	 * I hope that the min value is -15360 for newer firmware --jk
+	 */
+		if (!strcmp(kctl->id.name, "PCM Playback Volume") &&
+		    cval->min == -15616) {
+			snd_printk(KERN_INFO
+				 "set volume quirk for UDA1321/N101 chip\n");
+			cval->max = -256;
+		}
+		break;
+
+	case USB_ID(0x046d, 0x09a4):
+		if (!strcmp(kctl->id.name, "Mic Capture Volume")) {
+			snd_printk(KERN_INFO
+				"set volume quirk for QuickCam E3500\n");
+			cval->min = 6080;
+			cval->max = 8768;
+			cval->res = 192;
+		}
+		break;
+
+	case USB_ID(0x046d, 0x0808):
+	case USB_ID(0x046d, 0x0809):
+	case USB_ID(0x046d, 0x0991):
+	/* Most audio usb devices lie about volume resolution.
+	 * Most Logitech webcams have res = 384.
+	 * Proboly there is some logitech magic behind this number --fishor
+	 */
+		if (!strcmp(kctl->id.name, "Mic Capture Volume")) {
+			snd_printk(KERN_INFO
+				"set resolution quirk: cval->res = 384\n");
+			cval->res = 384;
+		}
+		break;
+
+	}
+}
+
 /*
  * retrieve the minimum and maximum values for the specified control
  */
-static int get_min_max(struct usb_mixer_elem_info *cval, int default_min)
+static int get_min_max_with_quirks(struct usb_mixer_elem_info *cval,
+				   int default_min, struct snd_kcontrol *kctl)
 {
 	/* for failsafe */
 	cval->min = default_min;
@@ -844,6 +894,9 @@ static int get_min_max(struct usb_mixer_elem_info *cval, int default_min)
 		cval->initialized = 1;
 	}
 
+	if (kctl)
+		volume_control_quirks(cval, kctl);
+
 	/* USB descriptions contain the dB scale in 1/256 dB unit
 	 * while ALSA TLV contains in 1/100 dB unit
 	 */
@@ -864,6 +917,7 @@ static int get_min_max(struct usb_mixer_elem_info *cval, int default_min)
 	return 0;
 }
 
+#define get_min_max(cval, def)	get_min_max_with_quirks(cval, def, NULL)
 
 /* get a feature/mixer unit info */
 static int mixer_ctl_feature_info(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_info *uinfo)
@@ -881,8 +935,17 @@ static int mixer_ctl_feature_info(struct snd_kcontrol *kcontrol, struct snd_ctl_
 		uinfo->value.integer.min = 0;
 		uinfo->value.integer.max = 1;
 	} else {
-		if (! cval->initialized)
-			get_min_max(cval,  0);
+		if (!cval->initialized) {
+			get_min_max_with_quirks(cval, 0, kcontrol);
+			if (cval->initialized && cval->dBmin >= cval->dBmax) {
+				kcontrol->vd[0].access &=
+					~(SNDRV_CTL_ELEM_ACCESS_TLV_READ |
+					  SNDRV_CTL_ELEM_ACCESS_TLV_CALLBACK);
+				snd_ctl_notify(cval->mixer->chip->card,
+					       SNDRV_CTL_EVENT_MASK_INFO,
+					       &kcontrol->id);
+			}
+		}
 		uinfo->value.integer.min = 0;
 		uinfo->value.integer.max =
 			(cval->max - cval->min + cval->res - 1) / cval->res;
@@ -1036,9 +1099,6 @@ static void build_feature_ctl(struct mixer_build *state, void *raw_desc,
 		cval->ch_readonly = readonly_mask;
 	}
 
-	/* get min/max values */
-	get_min_max(cval, 0);
-
 	/* if all channels in the mask are marked read-only, make the control
 	 * read-only. set_cur_mix_value() will check the mask again and won't
 	 * issue write commands to read-only channels. */
@@ -1060,6 +1120,9 @@ static void build_feature_ctl(struct mixer_build *state, void *raw_desc,
 		len = snd_usb_copy_string_desc(state, nameid,
 				kctl->id.name, sizeof(kctl->id.name));
 
+	/* get min/max values */
+	get_min_max_with_quirks(cval, 0, kctl);
+
 	switch (control) {
 	case UAC_FU_MUTE:
 	case UAC_FU_VOLUME:
@@ -1109,51 +1172,6 @@ static void build_feature_ctl(struct mixer_build *state, void *raw_desc,
 		break;
 	}
 
-	/* volume control quirks */
-	switch (state->chip->usb_id) {
-	case USB_ID(0x0471, 0x0101):
-	case USB_ID(0x0471, 0x0104):
-	case USB_ID(0x0471, 0x0105):
-	case USB_ID(0x0672, 0x1041):
-	/* quirk for UDA1321/N101.
-	 * note that detection between firmware 2.1.1.7 (N101)
-	 * and later 2.1.1.21 is not very clear from datasheets.
-	 * I hope that the min value is -15360 for newer firmware --jk
-	 */
-		if (!strcmp(kctl->id.name, "PCM Playback Volume") &&
-		    cval->min == -15616) {
-			snd_printk(KERN_INFO
-				 "set volume quirk for UDA1321/N101 chip\n");
-			cval->max = -256;
-		}
-		break;
-
-	case USB_ID(0x046d, 0x09a4):
-		if (!strcmp(kctl->id.name, "Mic Capture Volume")) {
-			snd_printk(KERN_INFO
-				"set volume quirk for QuickCam E3500\n");
-			cval->min = 6080;
-			cval->max = 8768;
-			cval->res = 192;
-		}
-		break;
-
-	case USB_ID(0x046d, 0x0808):
-	case USB_ID(0x046d, 0x0809):
-	case USB_ID(0x046d, 0x0991):
-	/* Most audio usb devices lie about volume resolution.
-	 * Most Logitech webcams have res = 384.
-	 * Proboly there is some logitech magic behind this number --fishor
-	 */
-		if (!strcmp(kctl->id.name, "Mic Capture Volume")) {
-			snd_printk(KERN_INFO
-				"set resolution quirk: cval->res = 384\n");
-			cval->res = 384;
-		}
-		break;
-
-	}
-
 	range = (cval->max - cval->min) / cval->res;
 	/* Are there devices with volume range more than 255? I use a bit more
 	 * to be sure. 384 is a resolution magic number found on Logitech
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 1c7bfa5fe0a..eb25900e221 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -1956,8 +1956,10 @@ static int __del_trace_probe_event(int fd, struct str_node *ent)
 
 	pr_debug("Writing event: %s\n", buf);
 	ret = write(fd, buf, strlen(buf));
-	if (ret < 0)
+	if (ret < 0) {
+		ret = -errno;
 		goto error;
+	}
 
 	printf("Remove event: %s\n", ent->s);
 	return 0;
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index 0a7ed5b5e28..6c164dc9ee9 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -1537,6 +1537,8 @@ process_flags(struct event *event, struct print_arg *arg, char **tok)
 	field = malloc_or_die(sizeof(*field));
 
 	type = process_arg(event, field, &token);
+	while (type == EVENT_OP)
+		type = process_op(event, field, &token);
 	if (test_type_token(type, token, EVENT_DELIM, ","))
 		goto out_free;