diff --git a/Documentation/ABI/testing/debugfs-olpc b/Documentation/ABI/testing/debugfs-olpc
new file mode 100644
index 0000000..bd76cc6
--- /dev/null
+++ b/Documentation/ABI/testing/debugfs-olpc
@@ -0,0 +1,16 @@
+What:		/sys/kernel/debug/olpc-ec/cmd
+Date:		Dec 2011
+KernelVersion:	3.4
+Contact:	devel@lists.laptop.org
+Description:
+
+A generic interface for executing OLPC Embedded Controller commands and
+reading their responses.
+
+To execute a command, write data with the format: CC:N A A A A
+CC is the (hex) command, N is the count of expected reply bytes, and A A A A
+are optional (hex) arguments.
+
+To read the response (if any), read from the generic node after executing
+a command. Hex reply bytes will be returned, *whether or not* they came from
+the immediately previous command.
diff --git a/Documentation/devicetree/bindings/mtd/arm-versatile.txt b/Documentation/devicetree/bindings/mtd/arm-versatile.txt
index 476845d..beace4b 100644
--- a/Documentation/devicetree/bindings/mtd/arm-versatile.txt
+++ b/Documentation/devicetree/bindings/mtd/arm-versatile.txt
@@ -4,5 +4,5 @@
 - compatible : must be "arm,versatile-flash";
 - bank-width : width in bytes of flash interface.
 
-Optional properties:
-- Subnode partition map from mtd flash binding
+The device tree may optionally contain sub-nodes describing partitions of the
+address space. See partition.txt for more detail.
diff --git a/Documentation/devicetree/bindings/mtd/atmel-dataflash.txt b/Documentation/devicetree/bindings/mtd/atmel-dataflash.txt
index ef66ddd..1889a4d 100644
--- a/Documentation/devicetree/bindings/mtd/atmel-dataflash.txt
+++ b/Documentation/devicetree/bindings/mtd/atmel-dataflash.txt
@@ -3,6 +3,9 @@
 Required properties:
 - compatible : "atmel,<model>", "atmel,<series>", "atmel,dataflash".
 
+The device tree may optionally contain sub-nodes describing partitions of the
+address space. See partition.txt for more detail.
+
 Example:
 
 flash@1 {
diff --git a/Documentation/devicetree/bindings/mtd/fsl-upm-nand.txt b/Documentation/devicetree/bindings/mtd/fsl-upm-nand.txt
index 00f1f54..fce4894 100644
--- a/Documentation/devicetree/bindings/mtd/fsl-upm-nand.txt
+++ b/Documentation/devicetree/bindings/mtd/fsl-upm-nand.txt
@@ -19,6 +19,10 @@
 	read registers (tR). Required if property "gpios" is not used
 	(R/B# pins not connected).
 
+Each flash chip described may optionally contain additional sub-nodes
+describing partitions of the address space. See partition.txt for more
+detail.
+
 Examples:
 
 upm@1,0 {
diff --git a/Documentation/devicetree/bindings/mtd/gpio-control-nand.txt b/Documentation/devicetree/bindings/mtd/gpio-control-nand.txt
index 719f4dc..36ef07d 100644
--- a/Documentation/devicetree/bindings/mtd/gpio-control-nand.txt
+++ b/Documentation/devicetree/bindings/mtd/gpio-control-nand.txt
@@ -25,6 +25,9 @@
   GPIO state and before and after command byte writes, this register will be
   read to ensure that the GPIO accesses have completed.
 
+The device tree may optionally contain sub-nodes describing partitions of the
+address space. See partition.txt for more detail.
+
 Examples:
 
 gpio-nand@1,0 {
diff --git a/Documentation/devicetree/bindings/mtd/mtd-physmap.txt b/Documentation/devicetree/bindings/mtd/mtd-physmap.txt
index 80152cb..a63c2bd7 100644
--- a/Documentation/devicetree/bindings/mtd/mtd-physmap.txt
+++ b/Documentation/devicetree/bindings/mtd/mtd-physmap.txt
@@ -23,27 +23,8 @@
  - vendor-id : Contains the flash chip's vendor id (1 byte).
  - device-id : Contains the flash chip's device id (1 byte).
 
-In addition to the information on the mtd bank itself, the
-device tree may optionally contain additional information
-describing partitions of the address space.  This can be
-used on platforms which have strong conventions about which
-portions of a flash are used for what purposes, but which don't
-use an on-flash partition table such as RedBoot.
-
-Each partition is represented as a sub-node of the mtd device.
-Each node's name represents the name of the corresponding
-partition of the mtd device.
-
-Flash partitions
- - reg : The partition's offset and size within the mtd bank.
- - label : (optional) The label / name for this partition.
-   If omitted, the label is taken from the node name (excluding
-   the unit address).
- - read-only : (optional) This parameter, if present, is a hint to
-   Linux that this partition should only be mounted
-   read-only.  This is usually used for flash partitions
-   containing early-boot firmware images or data which should not
-   be clobbered.
+The device tree may optionally contain sub-nodes describing partitions of the
+address space. See partition.txt for more detail.
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/mtd/partition.txt b/Documentation/devicetree/bindings/mtd/partition.txt
new file mode 100644
index 0000000..f114ce1
--- /dev/null
+++ b/Documentation/devicetree/bindings/mtd/partition.txt
@@ -0,0 +1,38 @@
+Representing flash partitions in devicetree
+
+Partitions can be represented by sub-nodes of an mtd device. This can be used
+on platforms which have strong conventions about which portions of a flash are
+used for what purposes, but which don't use an on-flash partition table such
+as RedBoot.
+
+#address-cells & #size-cells must both be present in the mtd device and be
+equal to 1.
+
+Required properties:
+- reg : The partition's offset and size within the mtd bank.
+
+Optional properties:
+- label : The label / name for this partition.  If omitted, the label is taken
+  from the node name (excluding the unit address).
+- read-only : This parameter, if present, is a hint to Linux that this
+  partition should only be mounted read-only. This is usually used for flash
+  partitions containing early-boot firmware images or data which should not be
+  clobbered.
+
+Examples:
+
+
+flash@0 {
+	#address-cells = <1>;
+	#size-cells = <1>;
+
+	partition@0 {
+		label = "u-boot";
+		reg = <0x0000000 0x100000>;
+		read-only;
+	};
+
+	uimage@100000 {
+		reg = <0x0100000 0x200000>;
+	};
+];
diff --git a/Documentation/devicetree/usage-model.txt b/Documentation/devicetree/usage-model.txt
new file mode 100644
index 0000000..c5a8009
--- /dev/null
+++ b/Documentation/devicetree/usage-model.txt
@@ -0,0 +1,412 @@
+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 on the device tree usage page
+at devicetree.org[1].
+
+[1] http://devicetree.org/Device_Tree_Usage
+
+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.  Be wary,
+however, of creating a new binding without first doing some homework
+about what already exists.  There are currently two different,
+incompatible, bindings for i2c busses that came about because the new
+binding was created without first investigating how i2c devices were
+already being enumerated in existing systems.
+
+1. History
+----------
+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.  DT was
+also added to the PowerPC boot wrapper (arch/powerpc/boot/*) so that
+a dtb could be wrapped up with the kernel image to support booting
+existing non-DT aware firmware.
+
+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.
+
+2. Data Model
+-------------
+If you haven't already read the Device Tree Usage[1] page,
+then go read it now.  It's okay, I'll wait....
+
+2.1 High Level View
+-------------------
+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.
+
+2.2 Platform Identification
+---------------------------
+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.
+
+2.3 Runtime configuration
+-------------------------
+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 = <0xc8000000>;
+		initrd-end = <0xc8200000>;
+	};
+
+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.
+
+2.4 Device population
+---------------------
+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>;
+		};
+
+		i2s1: i2s@70002800 {
+			compatible = "nvidia,tegra20-i2s";
+			reg = <0x70002800 0x100>;
+			interrupts = <77>;
+			codec = <&wm8903>;
+		};
+
+		i2c@7000c000 {
+			compatible = "nvidia,tegra20-i2c";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x7000c000 0x100>;
+			interrupts = <70>;
+
+			wm8903: codec@1a {
+				compatible = "wlf,wm8903";
+				reg = <0x1a>;
+				interrupts = <347>;
+			};
+		};
+	};
+
+	sound {
+		compatible = "nvidia,harmony-sound";
+		i2s-controller = <&i2s1>;
+		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, a (theoretical) SoC device driver could 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?
+
+Actually, it turns out that registering children of some
+platform_devices as more platform_devices is a common pattern, and the
+device tree support code reflects that and makes the above example
+simpler.  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 void __init harmony_init_machine(void)
+{
+	/* ... */
+	of_platform_populate(NULL, of_default_bus_match_table, NULL, 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.
+
+[Need to add discussion of adding i2c/spi/etc child devices]
+
+Appendix A: AMBA devices
+------------------------
+
+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/filesystems/files.txt b/Documentation/filesystems/files.txt
index ac2facc..46dfc6b 100644
--- a/Documentation/filesystems/files.txt
+++ b/Documentation/filesystems/files.txt
@@ -113,8 +113,8 @@
 	if (fd >= 0) {
 		/* locate_fd() may have expanded fdtable, load the ptr */
 		fdt = files_fdtable(files);
-		FD_SET(fd, fdt->open_fds);
-		FD_CLR(fd, fdt->close_on_exec);
+		__set_open_fd(fd, fdt);
+		__clear_close_on_exec(fd, fdt);
 		spin_unlock(&files->file_lock);
 	.....
 
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index e2f8c29..c1601e5 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1699,6 +1699,12 @@
 			The default is to send the implementation identification
 			information.
 
+	nfsd.nfs4_disable_idmapping=
+			[NFSv4] When set to the default of '1', the NFSv4
+			server will return only numeric uids and gids to
+			clients using auth_sys, and will accept numeric uids
+			and gids from such clients.  This is intended to ease
+			migration from NFSv2/v3.
 
 	objlayoutdriver.osd_login_prog=
 			[NFS] [OBJLAYOUT] sets the pathname to the program which
diff --git a/MAINTAINERS b/MAINTAINERS
index 3dbf4d1..eecf344 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5185,7 +5185,7 @@
 PERFORMANCE EVENTS SUBSYSTEM
 M:	Peter Zijlstra <a.p.zijlstra@chello.nl>
 M:	Paul Mackerras <paulus@samba.org>
-M:	Ingo Molnar <mingo@elte.hu>
+M:	Ingo Molnar <mingo@redhat.com>
 M:	Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf/core
 S:	Supported
@@ -5833,7 +5833,7 @@
 F:	drivers/watchdog/sc1200wdt.c
 
 SCHEDULER
-M:	Ingo Molnar <mingo@elte.hu>
+M:	Ingo Molnar <mingo@redhat.com>
 M:	Peter Zijlstra <peterz@infradead.org>
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git sched/core
 S:	Maintained
diff --git a/arch/Kconfig b/arch/Kconfig
index a6f14f6..684eb5a 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -213,4 +213,7 @@
 config HAVE_CMPXCHG_DOUBLE
 	bool
 
+config ARCH_WANT_OLD_COMPAT_IPC
+	bool
+
 source "kernel/gcov/Kconfig"
diff --git a/arch/alpha/include/asm/posix_types.h b/arch/alpha/include/asm/posix_types.h
index db16741..24779fc 100644
--- a/arch/alpha/include/asm/posix_types.h
+++ b/arch/alpha/include/asm/posix_types.h
@@ -8,116 +8,13 @@
  */
 
 typedef unsigned int	__kernel_ino_t;
-typedef unsigned int	__kernel_mode_t;
+#define __kernel_ino_t __kernel_ino_t
+
 typedef unsigned int	__kernel_nlink_t;
-typedef long		__kernel_off_t;
-typedef long long	__kernel_loff_t;
-typedef int		__kernel_pid_t;
-typedef int		__kernel_ipc_pid_t;
-typedef unsigned int	__kernel_uid_t;
-typedef unsigned int	__kernel_gid_t;
-typedef unsigned long	__kernel_size_t;
-typedef long		__kernel_ssize_t;
-typedef long		__kernel_ptrdiff_t;
-typedef long		__kernel_time_t;
-typedef long		__kernel_suseconds_t;
-typedef long		__kernel_clock_t;
-typedef int		__kernel_daddr_t;
-typedef char *		__kernel_caddr_t;
+#define __kernel_nlink_t __kernel_nlink_t
+
 typedef unsigned long	__kernel_sigset_t;	/* at least 32 bits */
-typedef unsigned short	__kernel_uid16_t;
-typedef unsigned short	__kernel_gid16_t;
-typedef int		__kernel_clockid_t;
-typedef int		__kernel_timer_t;
 
-typedef struct {
-	int	val[2];
-} __kernel_fsid_t;
-
-typedef __kernel_uid_t __kernel_old_uid_t;
-typedef __kernel_gid_t __kernel_old_gid_t;
-typedef __kernel_uid_t __kernel_uid32_t;
-typedef __kernel_gid_t __kernel_gid32_t;
-
-typedef unsigned int	__kernel_old_dev_t;
-
-#ifdef __KERNEL__
-
-#ifndef __GNUC__
-
-#define	__FD_SET(d, set)	((set)->fds_bits[__FDELT(d)] |= __FDMASK(d))
-#define	__FD_CLR(d, set)	((set)->fds_bits[__FDELT(d)] &= ~__FDMASK(d))
-#define	__FD_ISSET(d, set)	(((set)->fds_bits[__FDELT(d)] & __FDMASK(d)) != 0)
-#define	__FD_ZERO(set)	\
-  ((void) memset ((void *) (set), 0, sizeof (__kernel_fd_set)))
-
-#else /* __GNUC__ */
-
-/* With GNU C, use inline functions instead so args are evaluated only once: */
-
-#undef __FD_SET
-static __inline__ void __FD_SET(unsigned long fd, __kernel_fd_set *fdsetp)
-{
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	fdsetp->fds_bits[_tmp] |= (1UL<<_rem);
-}
-
-#undef __FD_CLR
-static __inline__ void __FD_CLR(unsigned long fd, __kernel_fd_set *fdsetp)
-{
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	fdsetp->fds_bits[_tmp] &= ~(1UL<<_rem);
-}
-
-#undef __FD_ISSET
-static __inline__ int __FD_ISSET(unsigned long fd, const __kernel_fd_set *p)
-{ 
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	return (p->fds_bits[_tmp] & (1UL<<_rem)) != 0;
-}
-
-/*
- * This will unroll the loop for the normal constant case (8 ints,
- * for a 256-bit fd_set)
- */
-#undef __FD_ZERO
-static __inline__ void __FD_ZERO(__kernel_fd_set *p)
-{
-	unsigned long *tmp = p->fds_bits;
-	int i;
-
-	if (__builtin_constant_p(__FDSET_LONGS)) {
-		switch (__FDSET_LONGS) {
-		      case 16:
-			tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
-			tmp[ 4] = 0; tmp[ 5] = 0; tmp[ 6] = 0; tmp[ 7] = 0;
-			tmp[ 8] = 0; tmp[ 9] = 0; tmp[10] = 0; tmp[11] = 0;
-			tmp[12] = 0; tmp[13] = 0; tmp[14] = 0; tmp[15] = 0;
-			return;
-
-		      case 8:
-			tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
-			tmp[ 4] = 0; tmp[ 5] = 0; tmp[ 6] = 0; tmp[ 7] = 0;
-			return;
-
-		      case 4:
-			tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
-			return;
-		}
-	}
-	i = __FDSET_LONGS;
-	while (i) {
-		i--;
-		*tmp = 0;
-		tmp++;
-	}
-}
-
-#endif /* __GNUC__ */
-
-#endif /* __KERNEL__ */
+#include <asm-generic/posix_types.h>
 
 #endif /* _ALPHA_POSIX_TYPES_H */
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 5098564..9318084 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -9,6 +9,7 @@
 	select SYS_SUPPORTS_APM_EMULATION
 	select GENERIC_ATOMIC64 if (CPU_V6 || !CPU_32v6K || !AEABI)
 	select HAVE_OPROFILE if (HAVE_PERF_EVENTS)
+	select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL
 	select HAVE_ARCH_KGDB
 	select HAVE_KPROBES if !XIP_KERNEL
 	select HAVE_KRETPROBES if (HAVE_KPROBES)
@@ -21,6 +22,7 @@
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_LZO
 	select HAVE_KERNEL_LZMA
+	select HAVE_KERNEL_XZ
 	select HAVE_IRQ_WORK
 	select HAVE_PERF_EVENTS
 	select PERF_USE_VMALLOC
@@ -28,10 +30,10 @@
 	select HAVE_HW_BREAKPOINT if (PERF_EVENTS && (CPU_V6 || CPU_V6K || CPU_V7))
 	select HAVE_C_RECORDMCOUNT
 	select HAVE_GENERIC_HARDIRQS
-	select HAVE_SPARSE_IRQ
 	select GENERIC_IRQ_SHOW
 	select CPU_PM if (SUSPEND || CPU_IDLE)
 	select GENERIC_PCI_IOMAP
+	select HAVE_BPF_JIT if NET
 	help
 	  The ARM series is a line of low-power-consumption RISC chip designs
 	  licensed by ARM Ltd and targeted at embedded applications and
@@ -52,9 +54,6 @@
 config SYS_SUPPORTS_APM_EMULATION
 	bool
 
-config HAVE_SCHED_CLOCK
-	bool
-
 config GENERIC_GPIO
 	bool
 
@@ -180,6 +179,9 @@
 config NEED_DMA_MAP_STATE
        def_bool y
 
+config ARCH_HAS_DMA_SET_COHERENT_MASK
+	bool
+
 config GENERIC_ISA_DMA
 	bool
 
@@ -217,6 +219,13 @@
 	  this feature (eg, building a kernel for a single machine) and
 	  you need to shrink the kernel to the minimal size.
 
+config NEED_MACH_IO_H
+	bool
+	help
+	  Select this when mach/io.h is required to provide special
+	  definitions for this platform.  The need for mach/io.h should
+	  be avoided when possible.
+
 config NEED_MACH_MEMORY_H
 	bool
 	help
@@ -268,7 +277,9 @@
 	select GENERIC_CLOCKEVENTS
 	select PLAT_VERSATILE
 	select PLAT_VERSATILE_FPGA_IRQ
+	select NEED_MACH_IO_H
 	select NEED_MACH_MEMORY_H
+	select SPARSE_IRQ
 	help
 	  Support for ARM's Integrator platform.
 
@@ -315,6 +326,7 @@
 	select HAVE_CLK
 	select HAVE_PATA_PLATFORM
 	select ICST
+	select NO_IOPORT
 	select PLAT_VERSATILE
 	select PLAT_VERSATILE_CLCD
 	help
@@ -354,6 +366,7 @@
 	select GENERIC_CLOCKEVENTS
 	select HAVE_ARM_SCU
 	select HAVE_SMP
+	select SPARSE_IRQ
 	select USE_OF
 	help
 	  Support for the Calxeda Highbank SoC based boards.
@@ -404,6 +417,7 @@
 	select ISA
 	select NO_IOPORT
 	select ARCH_USES_GETTIMEOFFSET
+	select NEED_MACH_IO_H
 	select NEED_MACH_MEMORY_H
 	help
 	  This is an evaluation board for the StrongARM processor available
@@ -430,6 +444,7 @@
 	select FOOTBRIDGE
 	select GENERIC_CLOCKEVENTS
 	select HAVE_IDE
+	select NEED_MACH_IO_H
 	select NEED_MACH_MEMORY_H
 	help
 	  Support for systems based on the DC21285 companion chip
@@ -442,7 +457,6 @@
 	select CLKDEV_LOOKUP
 	select CLKSRC_MMIO
 	select GENERIC_IRQ_CHIP
-	select HAVE_SCHED_CLOCK
 	select MULTI_IRQ_HANDLER
 	help
 	  Support for Freescale MXC/iMX-based family of processors
@@ -482,6 +496,7 @@
 	select PCI
 	select ARCH_SUPPORTS_MSI
 	select VMSPLIT_1G
+	select NEED_MACH_IO_H
 	select NEED_MACH_MEMORY_H
 	select NEED_RET_TO_USER
 	help
@@ -491,6 +506,7 @@
 	bool "IOP32x-based"
 	depends on MMU
 	select CPU_XSCALE
+	select NEED_MACH_IO_H
 	select NEED_RET_TO_USER
 	select PLAT_IOP
 	select PCI
@@ -503,6 +519,7 @@
 	bool "IOP33x-based"
 	depends on MMU
 	select CPU_XSCALE
+	select NEED_MACH_IO_H
 	select NEED_RET_TO_USER
 	select PLAT_IOP
 	select PCI
@@ -516,6 +533,7 @@
 	select CPU_XSC3
  	select PCI
 	select ARCH_USES_GETTIMEOFFSET
+	select NEED_MACH_IO_H
 	select NEED_MACH_MEMORY_H
 	help
 	  Support for Intel's IXP23xx (XScale) family of processors.
@@ -526,6 +544,7 @@
 	select CPU_XSCALE
 	select PCI
 	select ARCH_USES_GETTIMEOFFSET
+	select NEED_MACH_IO_H
 	select NEED_MACH_MEMORY_H
 	help
 	  Support for Intel's IXP2400/2800 (XScale) family of processors.
@@ -533,12 +552,13 @@
 config ARCH_IXP4XX
 	bool "IXP4xx-based"
 	depends on MMU
+	select ARCH_HAS_DMA_SET_COHERENT_MASK
 	select CLKSRC_MMIO
 	select CPU_XSCALE
 	select GENERIC_GPIO
 	select GENERIC_CLOCKEVENTS
-	select HAVE_SCHED_CLOCK
 	select MIGHT_HAVE_PCI
+	select NEED_MACH_IO_H
 	select DMABOUNCE if PCI
 	help
 	  Support for Intel's IXP4XX (XScale) family of processors.
@@ -549,6 +569,7 @@
 	select PCI
 	select ARCH_REQUIRE_GPIOLIB
 	select GENERIC_CLOCKEVENTS
+	select NEED_MACH_IO_H
 	select PLAT_ORION
 	help
 	  Support for the Marvell Dove SoC 88AP510
@@ -559,6 +580,7 @@
 	select PCI
 	select ARCH_REQUIRE_GPIOLIB
 	select GENERIC_CLOCKEVENTS
+	select NEED_MACH_IO_H
 	select PLAT_ORION
 	help
 	  Support for the following Marvell Kirkwood series SoCs:
@@ -583,6 +605,7 @@
 	select PCI
 	select ARCH_REQUIRE_GPIOLIB
 	select GENERIC_CLOCKEVENTS
+	select NEED_MACH_IO_H
 	select PLAT_ORION
 	help
 	  Support for the following Marvell MV78xx0 series SoCs:
@@ -608,7 +631,6 @@
 	select CLKDEV_LOOKUP
 	select GENERIC_CLOCKEVENTS
 	select GPIO_PXA
-	select HAVE_SCHED_CLOCK
 	select TICK_ONESHOT
 	select PLAT_PXA
 	select SPARSE_IRQ
@@ -649,9 +671,9 @@
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_GPIO
 	select HAVE_CLK
-	select HAVE_SCHED_CLOCK
 	select HAVE_SMP
 	select MIGHT_HAVE_CACHE_L2X0
+	select NEED_MACH_IO_H if PCI
 	select ARCH_HAS_CPUFREQ
 	help
 	  This enables support for NVIDIA Tegra based systems (Tegra APX,
@@ -666,7 +688,6 @@
 	select DW_APB_TIMER
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_GPIO
-	select HAVE_SCHED_CLOCK
 	select HAVE_TCM
 	select NO_IOPORT
 	select SPARSE_IRQ
@@ -694,7 +715,6 @@
 	select ARCH_REQUIRE_GPIOLIB
 	select GENERIC_CLOCKEVENTS
 	select GPIO_PXA
-	select HAVE_SCHED_CLOCK
 	select TICK_ONESHOT
 	select PLAT_PXA
 	select SPARSE_IRQ
@@ -745,6 +765,7 @@
 	select ARCH_SPARSEMEM_ENABLE
 	select ARCH_USES_GETTIMEOFFSET
 	select HAVE_IDE
+	select NEED_MACH_IO_H
 	select NEED_MACH_MEMORY_H
 	help
 	  On the Acorn Risc-PC, Linux can support the internal IDE disk and
@@ -761,7 +782,6 @@
 	select CPU_FREQ
 	select GENERIC_CLOCKEVENTS
 	select CLKDEV_LOOKUP
-	select HAVE_SCHED_CLOCK
 	select TICK_ONESHOT
 	select ARCH_REQUIRE_GPIOLIB
 	select HAVE_IDE
@@ -780,6 +800,7 @@
 	select HAVE_S3C2410_I2C if I2C
 	select HAVE_S3C_RTC if RTC_CLASS
 	select HAVE_S3C2410_WATCHDOG if WATCHDOG
+	select NEED_MACH_IO_H
 	help
 	  Samsung S3C2410, S3C2412, S3C2413, S3C2416, S3C2440, S3C2442, S3C2443
 	  and S3C2450 SoCs based systems, such as the Simtec Electronics BAST
@@ -818,7 +839,6 @@
 	select CLKSRC_MMIO
 	select HAVE_S3C2410_WATCHDOG if WATCHDOG
 	select GENERIC_CLOCKEVENTS
-	select HAVE_SCHED_CLOCK
 	select HAVE_S3C2410_I2C if I2C
 	select HAVE_S3C_RTC if RTC_CLASS
 	help
@@ -849,7 +869,6 @@
 	select CLKSRC_MMIO
 	select ARCH_HAS_CPUFREQ
 	select GENERIC_CLOCKEVENTS
-	select HAVE_SCHED_CLOCK
 	select HAVE_S3C2410_I2C if I2C
 	select HAVE_S3C_RTC if RTC_CLASS
 	select HAVE_S3C2410_WATCHDOG if WATCHDOG
@@ -883,6 +902,7 @@
 	select PCI
 	select ARCH_USES_GETTIMEOFFSET
 	select NEED_MACH_MEMORY_H
+	select NEED_MACH_IO_H
 	help
 	  Support for the StrongARM based Digital DNARD machine, also known
 	  as "Shark" (<http://www.shark-linux.de/shark.html>).
@@ -892,7 +912,6 @@
 	depends on MMU
 	select CLKSRC_MMIO
 	select CPU_ARM926T
-	select HAVE_SCHED_CLOCK
 	select HAVE_TCM
 	select ARM_AMBA
 	select ARM_PATCH_PHYS_VIRT
@@ -951,7 +970,6 @@
 	select ARCH_HAS_CPUFREQ
 	select CLKSRC_MMIO
 	select GENERIC_CLOCKEVENTS
-	select HAVE_SCHED_CLOCK
 	select ARCH_HAS_HOLES_MEMORYMODEL
 	help
 	  Support for TI's OMAP platform (OMAP1/2/3/4).
@@ -1115,13 +1133,11 @@
 config PLAT_IOP
 	bool
 	select GENERIC_CLOCKEVENTS
-	select HAVE_SCHED_CLOCK
 
 config PLAT_ORION
 	bool
 	select CLKSRC_MMIO
 	select GENERIC_IRQ_CHIP
-	select HAVE_SCHED_CLOCK
 
 config PLAT_PXA
 	bool
diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug
index 66ca801..85348a0 100644
--- a/arch/arm/Kconfig.debug
+++ b/arch/arm/Kconfig.debug
@@ -292,6 +292,22 @@
 		  Note that the system will appear to hang during boot if there
 		  is nothing connected to read from the DCC.
 
+	config DEBUG_SEMIHOSTING
+		bool "Kernel low-level debug output via semihosting I"
+		help
+		  Semihosting enables code running on an ARM target to use
+		  the I/O facilities on a host debugger/emulator through a
+		  simple SVC calls. The host debugger or emulator must have
+		  semihosting enabled for the special svc call to be trapped
+		  otherwise the kernel will crash.
+
+		  This is known to work with OpenOCD, as wellas
+		  ARM's Fast Models, or any other controlling environment
+		  that implements semihosting.
+
+		  For more details about semihosting, please see
+		  chapter 8 of DUI0203I_rvct_developer_guide.pdf from ARM Ltd.
+
 endchoice
 
 config EARLY_PRINTK
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index dcb088e..047a207 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -253,6 +253,7 @@
 
 # If we have a machine-specific directory, then include it in the build.
 core-y				+= arch/arm/kernel/ arch/arm/mm/ arch/arm/common/
+core-y				+= arch/arm/net/
 core-y				+= $(machdirs) $(platdirs)
 
 drivers-$(CONFIG_OPROFILE)      += arch/arm/oprofile/
diff --git a/arch/arm/boot/compressed/.gitignore b/arch/arm/boot/compressed/.gitignore
index e0936a1..d0d441c 100644
--- a/arch/arm/boot/compressed/.gitignore
+++ b/arch/arm/boot/compressed/.gitignore
@@ -1,8 +1,10 @@
+ashldi3.S
 font.c
 lib1funcs.S
 piggy.gzip
 piggy.lzo
 piggy.lzma
+piggy.xzkern
 vmlinux
 vmlinux.lds
 
diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile
index cf0a64c..bb26756 100644
--- a/arch/arm/boot/compressed/Makefile
+++ b/arch/arm/boot/compressed/Makefile
@@ -92,6 +92,7 @@
 suffix_$(CONFIG_KERNEL_GZIP) = gzip
 suffix_$(CONFIG_KERNEL_LZO)  = lzo
 suffix_$(CONFIG_KERNEL_LZMA) = lzma
+suffix_$(CONFIG_KERNEL_XZ)   = xzkern
 
 # Borrowed libfdt files for the ATAG compatibility mode
 
@@ -112,10 +113,12 @@
 
 targets       := vmlinux vmlinux.lds \
 		 piggy.$(suffix_y) piggy.$(suffix_y).o \
-		 lib1funcs.o lib1funcs.S font.o font.c head.o misc.o $(OBJS)
+		 lib1funcs.o lib1funcs.S ashldi3.o ashldi3.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 $(libfdt) $(libfdt_hdrs)
+extra-y       += piggy.gzip piggy.lzo piggy.lzma piggy.xzkern \
+		 lib1funcs.S ashldi3.S $(libfdt) $(libfdt_hdrs)
 
 ifeq ($(CONFIG_FUNCTION_TRACER),y)
 ORIG_CFLAGS := $(KBUILD_CFLAGS)
@@ -151,6 +154,12 @@
 $(obj)/lib1funcs.S: $(srctree)/arch/$(SRCARCH)/lib/lib1funcs.S
 	$(call cmd,shipped)
 
+# For __aeabi_llsl
+ashldi3 = $(obj)/ashldi3.o
+
+$(obj)/ashldi3.S: $(srctree)/arch/$(SRCARCH)/lib/ashldi3.S
+	$(call cmd,shipped)
+
 # We need to prevent any GOTOFF relocs being used with references
 # to symbols in the .bss section since we cannot relocate them
 # independently from the rest at run time.  This can be achieved by
@@ -172,7 +181,7 @@
 fi
 
 $(obj)/vmlinux: $(obj)/vmlinux.lds $(obj)/$(HEAD) $(obj)/piggy.$(suffix_y).o \
-	 	$(addprefix $(obj)/, $(OBJS)) $(lib1funcs) FORCE
+		$(addprefix $(obj)/, $(OBJS)) $(lib1funcs) $(ashldi3) FORCE
 	@$(check_for_multiple_zreladdr)
 	$(call if_changed,ld)
 	@$(check_for_bad_syms)
diff --git a/arch/arm/boot/compressed/decompress.c b/arch/arm/boot/compressed/decompress.c
index 07be5a2..f41b38c 100644
--- a/arch/arm/boot/compressed/decompress.c
+++ b/arch/arm/boot/compressed/decompress.c
@@ -44,6 +44,12 @@
 #include "../../../../lib/decompress_unlzma.c"
 #endif
 
+#ifdef CONFIG_KERNEL_XZ
+#define memmove memmove
+#define memcpy memcpy
+#include "../../../../lib/decompress_unxz.c"
+#endif
+
 int do_decompress(u8 *input, int len, u8 *output, void (*error)(char *x))
 {
 	return decompress(input, len, NULL, NULL, output, NULL, error);
diff --git a/arch/arm/boot/compressed/piggy.xzkern.S b/arch/arm/boot/compressed/piggy.xzkern.S
new file mode 100644
index 0000000..5703f30
--- /dev/null
+++ b/arch/arm/boot/compressed/piggy.xzkern.S
@@ -0,0 +1,6 @@
+	.section .piggydata,#alloc
+	.globl	input_data
+input_data:
+	.incbin	"arch/arm/boot/compressed/piggy.xzkern"
+	.globl	input_data_end
+input_data_end:
diff --git a/arch/arm/common/Kconfig b/arch/arm/common/Kconfig
index 3bb1d75..283fa1d 100644
--- a/arch/arm/common/Kconfig
+++ b/arch/arm/common/Kconfig
@@ -24,9 +24,6 @@
 config ICST
 	bool
 
-config PL330
-	bool
-
 config SA1111
 	bool
 	select DMABOUNCE if !ARCH_PXA
diff --git a/arch/arm/common/Makefile b/arch/arm/common/Makefile
index 69feafe..215816f 100644
--- a/arch/arm/common/Makefile
+++ b/arch/arm/common/Makefile
@@ -5,7 +5,6 @@
 obj-$(CONFIG_ARM_GIC)		+= gic.o
 obj-$(CONFIG_ARM_VIC)		+= vic.o
 obj-$(CONFIG_ICST)		+= icst.o
-obj-$(CONFIG_PL330)		+= pl330.o
 obj-$(CONFIG_SA1111)		+= sa1111.o
 obj-$(CONFIG_PCI_HOST_VIA82C505) += via82c505.o
 obj-$(CONFIG_DMABOUNCE)		+= dmabounce.o
diff --git a/arch/arm/common/gic.c b/arch/arm/common/gic.c
index f0783be..aa52699 100644
--- a/arch/arm/common/gic.c
+++ b/arch/arm/common/gic.c
@@ -686,13 +686,12 @@
 	 * For primary GICs, skip over SGIs.
 	 * For secondary GICs, skip over PPIs, too.
 	 */
-	hwirq_base = 32;
-	if (gic_nr == 0) {
-		if ((irq_start & 31) > 0) {
-			hwirq_base = 16;
-			if (irq_start != -1)
-				irq_start = (irq_start & ~31) + 16;
-		}
+	if (gic_nr == 0 && (irq_start & 31) > 0) {
+		hwirq_base = 16;
+		if (irq_start != -1)
+			irq_start = (irq_start & ~31) + 16;
+	} else {
+		hwirq_base = 32;
 	}
 
 	/*
diff --git a/arch/arm/common/pl330.c b/arch/arm/common/pl330.c
deleted file mode 100644
index ff3ad22..0000000
--- a/arch/arm/common/pl330.c
+++ /dev/null
@@ -1,1960 +0,0 @@
-/* linux/arch/arm/common/pl330.c
- *
- * Copyright (C) 2010 Samsung Electronics Co Ltd.
- *	Jaswinder Singh <jassi.brar@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., 675 Mass Ave, Cambridge, MA 02139, USA.
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/slab.h>
-#include <linux/module.h>
-#include <linux/string.h>
-#include <linux/io.h>
-#include <linux/delay.h>
-#include <linux/interrupt.h>
-#include <linux/dma-mapping.h>
-
-#include <asm/hardware/pl330.h>
-
-/* Register and Bit field Definitions */
-#define DS		0x0
-#define DS_ST_STOP	0x0
-#define DS_ST_EXEC	0x1
-#define DS_ST_CMISS	0x2
-#define DS_ST_UPDTPC	0x3
-#define DS_ST_WFE	0x4
-#define DS_ST_ATBRR	0x5
-#define DS_ST_QBUSY	0x6
-#define DS_ST_WFP	0x7
-#define DS_ST_KILL	0x8
-#define DS_ST_CMPLT	0x9
-#define DS_ST_FLTCMP	0xe
-#define DS_ST_FAULT	0xf
-
-#define DPC		0x4
-#define INTEN		0x20
-#define ES		0x24
-#define INTSTATUS	0x28
-#define INTCLR		0x2c
-#define FSM		0x30
-#define FSC		0x34
-#define FTM		0x38
-
-#define _FTC		0x40
-#define FTC(n)		(_FTC + (n)*0x4)
-
-#define _CS		0x100
-#define CS(n)		(_CS + (n)*0x8)
-#define CS_CNS		(1 << 21)
-
-#define _CPC		0x104
-#define CPC(n)		(_CPC + (n)*0x8)
-
-#define _SA		0x400
-#define SA(n)		(_SA + (n)*0x20)
-
-#define _DA		0x404
-#define DA(n)		(_DA + (n)*0x20)
-
-#define _CC		0x408
-#define CC(n)		(_CC + (n)*0x20)
-
-#define CC_SRCINC	(1 << 0)
-#define CC_DSTINC	(1 << 14)
-#define CC_SRCPRI	(1 << 8)
-#define CC_DSTPRI	(1 << 22)
-#define CC_SRCNS	(1 << 9)
-#define CC_DSTNS	(1 << 23)
-#define CC_SRCIA	(1 << 10)
-#define CC_DSTIA	(1 << 24)
-#define CC_SRCBRSTLEN_SHFT	4
-#define CC_DSTBRSTLEN_SHFT	18
-#define CC_SRCBRSTSIZE_SHFT	1
-#define CC_DSTBRSTSIZE_SHFT	15
-#define CC_SRCCCTRL_SHFT	11
-#define CC_SRCCCTRL_MASK	0x7
-#define CC_DSTCCTRL_SHFT	25
-#define CC_DRCCCTRL_MASK	0x7
-#define CC_SWAP_SHFT	28
-
-#define _LC0		0x40c
-#define LC0(n)		(_LC0 + (n)*0x20)
-
-#define _LC1		0x410
-#define LC1(n)		(_LC1 + (n)*0x20)
-
-#define DBGSTATUS	0xd00
-#define DBG_BUSY	(1 << 0)
-
-#define DBGCMD		0xd04
-#define DBGINST0	0xd08
-#define DBGINST1	0xd0c
-
-#define CR0		0xe00
-#define CR1		0xe04
-#define CR2		0xe08
-#define CR3		0xe0c
-#define CR4		0xe10
-#define CRD		0xe14
-
-#define PERIPH_ID	0xfe0
-#define PCELL_ID	0xff0
-
-#define CR0_PERIPH_REQ_SET	(1 << 0)
-#define CR0_BOOT_EN_SET		(1 << 1)
-#define CR0_BOOT_MAN_NS		(1 << 2)
-#define CR0_NUM_CHANS_SHIFT	4
-#define CR0_NUM_CHANS_MASK	0x7
-#define CR0_NUM_PERIPH_SHIFT	12
-#define CR0_NUM_PERIPH_MASK	0x1f
-#define CR0_NUM_EVENTS_SHIFT	17
-#define CR0_NUM_EVENTS_MASK	0x1f
-
-#define CR1_ICACHE_LEN_SHIFT	0
-#define CR1_ICACHE_LEN_MASK	0x7
-#define CR1_NUM_ICACHELINES_SHIFT	4
-#define CR1_NUM_ICACHELINES_MASK	0xf
-
-#define CRD_DATA_WIDTH_SHIFT	0
-#define CRD_DATA_WIDTH_MASK	0x7
-#define CRD_WR_CAP_SHIFT	4
-#define CRD_WR_CAP_MASK		0x7
-#define CRD_WR_Q_DEP_SHIFT	8
-#define CRD_WR_Q_DEP_MASK	0xf
-#define CRD_RD_CAP_SHIFT	12
-#define CRD_RD_CAP_MASK		0x7
-#define CRD_RD_Q_DEP_SHIFT	16
-#define CRD_RD_Q_DEP_MASK	0xf
-#define CRD_DATA_BUFF_SHIFT	20
-#define CRD_DATA_BUFF_MASK	0x3ff
-
-#define	PART		0x330
-#define DESIGNER	0x41
-#define REVISION	0x0
-#define INTEG_CFG	0x0
-#define PERIPH_ID_VAL	((PART << 0) | (DESIGNER << 12))
-
-#define PCELL_ID_VAL	0xb105f00d
-
-#define PL330_STATE_STOPPED		(1 << 0)
-#define PL330_STATE_EXECUTING		(1 << 1)
-#define PL330_STATE_WFE			(1 << 2)
-#define PL330_STATE_FAULTING		(1 << 3)
-#define PL330_STATE_COMPLETING		(1 << 4)
-#define PL330_STATE_WFP			(1 << 5)
-#define PL330_STATE_KILLING		(1 << 6)
-#define PL330_STATE_FAULT_COMPLETING	(1 << 7)
-#define PL330_STATE_CACHEMISS		(1 << 8)
-#define PL330_STATE_UPDTPC		(1 << 9)
-#define PL330_STATE_ATBARRIER		(1 << 10)
-#define PL330_STATE_QUEUEBUSY		(1 << 11)
-#define PL330_STATE_INVALID		(1 << 15)
-
-#define PL330_STABLE_STATES (PL330_STATE_STOPPED | PL330_STATE_EXECUTING \
-				| PL330_STATE_WFE | PL330_STATE_FAULTING)
-
-#define CMD_DMAADDH	0x54
-#define CMD_DMAEND	0x00
-#define CMD_DMAFLUSHP	0x35
-#define CMD_DMAGO	0xa0
-#define CMD_DMALD	0x04
-#define CMD_DMALDP	0x25
-#define CMD_DMALP	0x20
-#define CMD_DMALPEND	0x28
-#define CMD_DMAKILL	0x01
-#define CMD_DMAMOV	0xbc
-#define CMD_DMANOP	0x18
-#define CMD_DMARMB	0x12
-#define CMD_DMASEV	0x34
-#define CMD_DMAST	0x08
-#define CMD_DMASTP	0x29
-#define CMD_DMASTZ	0x0c
-#define CMD_DMAWFE	0x36
-#define CMD_DMAWFP	0x30
-#define CMD_DMAWMB	0x13
-
-#define SZ_DMAADDH	3
-#define SZ_DMAEND	1
-#define SZ_DMAFLUSHP	2
-#define SZ_DMALD	1
-#define SZ_DMALDP	2
-#define SZ_DMALP	2
-#define SZ_DMALPEND	2
-#define SZ_DMAKILL	1
-#define SZ_DMAMOV	6
-#define SZ_DMANOP	1
-#define SZ_DMARMB	1
-#define SZ_DMASEV	2
-#define SZ_DMAST	1
-#define SZ_DMASTP	2
-#define SZ_DMASTZ	1
-#define SZ_DMAWFE	2
-#define SZ_DMAWFP	2
-#define SZ_DMAWMB	1
-#define SZ_DMAGO	6
-
-#define BRST_LEN(ccr)	((((ccr) >> CC_SRCBRSTLEN_SHFT) & 0xf) + 1)
-#define BRST_SIZE(ccr)	(1 << (((ccr) >> CC_SRCBRSTSIZE_SHFT) & 0x7))
-
-#define BYTE_TO_BURST(b, ccr)  ((b) / BRST_SIZE(ccr) / BRST_LEN(ccr))
-#define BURST_TO_BYTE(c, ccr)  ((c) * BRST_SIZE(ccr) * BRST_LEN(ccr))
-
-/*
- * With 256 bytes, we can do more than 2.5MB and 5MB xfers per req
- * at 1byte/burst for P<->M and M<->M respectively.
- * For typical scenario, at 1word/burst, 10MB and 20MB xfers per req
- * should be enough for P<->M and M<->M respectively.
- */
-#define MCODE_BUFF_PER_REQ	256
-
-/* If the _pl330_req is available to the client */
-#define IS_FREE(req)	(*((u8 *)((req)->mc_cpu)) == CMD_DMAEND)
-
-/* Use this _only_ to wait on transient states */
-#define UNTIL(t, s)	while (!(_state(t) & (s))) cpu_relax();
-
-#ifdef PL330_DEBUG_MCGEN
-static unsigned cmd_line;
-#define PL330_DBGCMD_DUMP(off, x...)	do { \
-						printk("%x:", cmd_line); \
-						printk(x); \
-						cmd_line += off; \
-					} while (0)
-#define PL330_DBGMC_START(addr)		(cmd_line = addr)
-#else
-#define PL330_DBGCMD_DUMP(off, x...)	do {} while (0)
-#define PL330_DBGMC_START(addr)		do {} while (0)
-#endif
-
-struct _xfer_spec {
-	u32 ccr;
-	struct pl330_req *r;
-	struct pl330_xfer *x;
-};
-
-enum dmamov_dst {
-	SAR = 0,
-	CCR,
-	DAR,
-};
-
-enum pl330_dst {
-	SRC = 0,
-	DST,
-};
-
-enum pl330_cond {
-	SINGLE,
-	BURST,
-	ALWAYS,
-};
-
-struct _pl330_req {
-	u32 mc_bus;
-	void *mc_cpu;
-	/* Number of bytes taken to setup MC for the req */
-	u32 mc_len;
-	struct pl330_req *r;
-	/* Hook to attach to DMAC's list of reqs with due callback */
-	struct list_head rqd;
-};
-
-/* ToBeDone for tasklet */
-struct _pl330_tbd {
-	bool reset_dmac;
-	bool reset_mngr;
-	u8 reset_chan;
-};
-
-/* A DMAC Thread */
-struct pl330_thread {
-	u8 id;
-	int ev;
-	/* If the channel is not yet acquired by any client */
-	bool free;
-	/* Parent DMAC */
-	struct pl330_dmac *dmac;
-	/* Only two at a time */
-	struct _pl330_req req[2];
-	/* Index of the last enqueued request */
-	unsigned lstenq;
-	/* Index of the last submitted request or -1 if the DMA is stopped */
-	int req_running;
-};
-
-enum pl330_dmac_state {
-	UNINIT,
-	INIT,
-	DYING,
-};
-
-/* A DMAC */
-struct pl330_dmac {
-	spinlock_t		lock;
-	/* Holds list of reqs with due callbacks */
-	struct list_head	req_done;
-	/* Pointer to platform specific stuff */
-	struct pl330_info	*pinfo;
-	/* Maximum possible events/irqs */
-	int			events[32];
-	/* BUS address of MicroCode buffer */
-	u32			mcode_bus;
-	/* CPU address of MicroCode buffer */
-	void			*mcode_cpu;
-	/* List of all Channel threads */
-	struct pl330_thread	*channels;
-	/* Pointer to the MANAGER thread */
-	struct pl330_thread	*manager;
-	/* To handle bad news in interrupt */
-	struct tasklet_struct	tasks;
-	struct _pl330_tbd	dmac_tbd;
-	/* State of DMAC operation */
-	enum pl330_dmac_state	state;
-};
-
-static inline void _callback(struct pl330_req *r, enum pl330_op_err err)
-{
-	if (r && r->xfer_cb)
-		r->xfer_cb(r->token, err);
-}
-
-static inline bool _queue_empty(struct pl330_thread *thrd)
-{
-	return (IS_FREE(&thrd->req[0]) && IS_FREE(&thrd->req[1]))
-		? true : false;
-}
-
-static inline bool _queue_full(struct pl330_thread *thrd)
-{
-	return (IS_FREE(&thrd->req[0]) || IS_FREE(&thrd->req[1]))
-		? false : true;
-}
-
-static inline bool is_manager(struct pl330_thread *thrd)
-{
-	struct pl330_dmac *pl330 = thrd->dmac;
-
-	/* MANAGER is indexed at the end */
-	if (thrd->id == pl330->pinfo->pcfg.num_chan)
-		return true;
-	else
-		return false;
-}
-
-/* If manager of the thread is in Non-Secure mode */
-static inline bool _manager_ns(struct pl330_thread *thrd)
-{
-	struct pl330_dmac *pl330 = thrd->dmac;
-
-	return (pl330->pinfo->pcfg.mode & DMAC_MODE_NS) ? true : false;
-}
-
-static inline u32 get_id(struct pl330_info *pi, u32 off)
-{
-	void __iomem *regs = pi->base;
-	u32 id = 0;
-
-	id |= (readb(regs + off + 0x0) << 0);
-	id |= (readb(regs + off + 0x4) << 8);
-	id |= (readb(regs + off + 0x8) << 16);
-	id |= (readb(regs + off + 0xc) << 24);
-
-	return id;
-}
-
-static inline u32 _emit_ADDH(unsigned dry_run, u8 buf[],
-		enum pl330_dst da, u16 val)
-{
-	if (dry_run)
-		return SZ_DMAADDH;
-
-	buf[0] = CMD_DMAADDH;
-	buf[0] |= (da << 1);
-	*((u16 *)&buf[1]) = val;
-
-	PL330_DBGCMD_DUMP(SZ_DMAADDH, "\tDMAADDH %s %u\n",
-		da == 1 ? "DA" : "SA", val);
-
-	return SZ_DMAADDH;
-}
-
-static inline u32 _emit_END(unsigned dry_run, u8 buf[])
-{
-	if (dry_run)
-		return SZ_DMAEND;
-
-	buf[0] = CMD_DMAEND;
-
-	PL330_DBGCMD_DUMP(SZ_DMAEND, "\tDMAEND\n");
-
-	return SZ_DMAEND;
-}
-
-static inline u32 _emit_FLUSHP(unsigned dry_run, u8 buf[], u8 peri)
-{
-	if (dry_run)
-		return SZ_DMAFLUSHP;
-
-	buf[0] = CMD_DMAFLUSHP;
-
-	peri &= 0x1f;
-	peri <<= 3;
-	buf[1] = peri;
-
-	PL330_DBGCMD_DUMP(SZ_DMAFLUSHP, "\tDMAFLUSHP %u\n", peri >> 3);
-
-	return SZ_DMAFLUSHP;
-}
-
-static inline u32 _emit_LD(unsigned dry_run, u8 buf[],	enum pl330_cond cond)
-{
-	if (dry_run)
-		return SZ_DMALD;
-
-	buf[0] = CMD_DMALD;
-
-	if (cond == SINGLE)
-		buf[0] |= (0 << 1) | (1 << 0);
-	else if (cond == BURST)
-		buf[0] |= (1 << 1) | (1 << 0);
-
-	PL330_DBGCMD_DUMP(SZ_DMALD, "\tDMALD%c\n",
-		cond == SINGLE ? 'S' : (cond == BURST ? 'B' : 'A'));
-
-	return SZ_DMALD;
-}
-
-static inline u32 _emit_LDP(unsigned dry_run, u8 buf[],
-		enum pl330_cond cond, u8 peri)
-{
-	if (dry_run)
-		return SZ_DMALDP;
-
-	buf[0] = CMD_DMALDP;
-
-	if (cond == BURST)
-		buf[0] |= (1 << 1);
-
-	peri &= 0x1f;
-	peri <<= 3;
-	buf[1] = peri;
-
-	PL330_DBGCMD_DUMP(SZ_DMALDP, "\tDMALDP%c %u\n",
-		cond == SINGLE ? 'S' : 'B', peri >> 3);
-
-	return SZ_DMALDP;
-}
-
-static inline u32 _emit_LP(unsigned dry_run, u8 buf[],
-		unsigned loop, u8 cnt)
-{
-	if (dry_run)
-		return SZ_DMALP;
-
-	buf[0] = CMD_DMALP;
-
-	if (loop)
-		buf[0] |= (1 << 1);
-
-	cnt--; /* DMAC increments by 1 internally */
-	buf[1] = cnt;
-
-	PL330_DBGCMD_DUMP(SZ_DMALP, "\tDMALP_%c %u\n", loop ? '1' : '0', cnt);
-
-	return SZ_DMALP;
-}
-
-struct _arg_LPEND {
-	enum pl330_cond cond;
-	bool forever;
-	unsigned loop;
-	u8 bjump;
-};
-
-static inline u32 _emit_LPEND(unsigned dry_run, u8 buf[],
-		const struct _arg_LPEND *arg)
-{
-	enum pl330_cond cond = arg->cond;
-	bool forever = arg->forever;
-	unsigned loop = arg->loop;
-	u8 bjump = arg->bjump;
-
-	if (dry_run)
-		return SZ_DMALPEND;
-
-	buf[0] = CMD_DMALPEND;
-
-	if (loop)
-		buf[0] |= (1 << 2);
-
-	if (!forever)
-		buf[0] |= (1 << 4);
-
-	if (cond == SINGLE)
-		buf[0] |= (0 << 1) | (1 << 0);
-	else if (cond == BURST)
-		buf[0] |= (1 << 1) | (1 << 0);
-
-	buf[1] = bjump;
-
-	PL330_DBGCMD_DUMP(SZ_DMALPEND, "\tDMALP%s%c_%c bjmpto_%x\n",
-			forever ? "FE" : "END",
-			cond == SINGLE ? 'S' : (cond == BURST ? 'B' : 'A'),
-			loop ? '1' : '0',
-			bjump);
-
-	return SZ_DMALPEND;
-}
-
-static inline u32 _emit_KILL(unsigned dry_run, u8 buf[])
-{
-	if (dry_run)
-		return SZ_DMAKILL;
-
-	buf[0] = CMD_DMAKILL;
-
-	return SZ_DMAKILL;
-}
-
-static inline u32 _emit_MOV(unsigned dry_run, u8 buf[],
-		enum dmamov_dst dst, u32 val)
-{
-	if (dry_run)
-		return SZ_DMAMOV;
-
-	buf[0] = CMD_DMAMOV;
-	buf[1] = dst;
-	*((u32 *)&buf[2]) = val;
-
-	PL330_DBGCMD_DUMP(SZ_DMAMOV, "\tDMAMOV %s 0x%x\n",
-		dst == SAR ? "SAR" : (dst == DAR ? "DAR" : "CCR"), val);
-
-	return SZ_DMAMOV;
-}
-
-static inline u32 _emit_NOP(unsigned dry_run, u8 buf[])
-{
-	if (dry_run)
-		return SZ_DMANOP;
-
-	buf[0] = CMD_DMANOP;
-
-	PL330_DBGCMD_DUMP(SZ_DMANOP, "\tDMANOP\n");
-
-	return SZ_DMANOP;
-}
-
-static inline u32 _emit_RMB(unsigned dry_run, u8 buf[])
-{
-	if (dry_run)
-		return SZ_DMARMB;
-
-	buf[0] = CMD_DMARMB;
-
-	PL330_DBGCMD_DUMP(SZ_DMARMB, "\tDMARMB\n");
-
-	return SZ_DMARMB;
-}
-
-static inline u32 _emit_SEV(unsigned dry_run, u8 buf[], u8 ev)
-{
-	if (dry_run)
-		return SZ_DMASEV;
-
-	buf[0] = CMD_DMASEV;
-
-	ev &= 0x1f;
-	ev <<= 3;
-	buf[1] = ev;
-
-	PL330_DBGCMD_DUMP(SZ_DMASEV, "\tDMASEV %u\n", ev >> 3);
-
-	return SZ_DMASEV;
-}
-
-static inline u32 _emit_ST(unsigned dry_run, u8 buf[], enum pl330_cond cond)
-{
-	if (dry_run)
-		return SZ_DMAST;
-
-	buf[0] = CMD_DMAST;
-
-	if (cond == SINGLE)
-		buf[0] |= (0 << 1) | (1 << 0);
-	else if (cond == BURST)
-		buf[0] |= (1 << 1) | (1 << 0);
-
-	PL330_DBGCMD_DUMP(SZ_DMAST, "\tDMAST%c\n",
-		cond == SINGLE ? 'S' : (cond == BURST ? 'B' : 'A'));
-
-	return SZ_DMAST;
-}
-
-static inline u32 _emit_STP(unsigned dry_run, u8 buf[],
-		enum pl330_cond cond, u8 peri)
-{
-	if (dry_run)
-		return SZ_DMASTP;
-
-	buf[0] = CMD_DMASTP;
-
-	if (cond == BURST)
-		buf[0] |= (1 << 1);
-
-	peri &= 0x1f;
-	peri <<= 3;
-	buf[1] = peri;
-
-	PL330_DBGCMD_DUMP(SZ_DMASTP, "\tDMASTP%c %u\n",
-		cond == SINGLE ? 'S' : 'B', peri >> 3);
-
-	return SZ_DMASTP;
-}
-
-static inline u32 _emit_STZ(unsigned dry_run, u8 buf[])
-{
-	if (dry_run)
-		return SZ_DMASTZ;
-
-	buf[0] = CMD_DMASTZ;
-
-	PL330_DBGCMD_DUMP(SZ_DMASTZ, "\tDMASTZ\n");
-
-	return SZ_DMASTZ;
-}
-
-static inline u32 _emit_WFE(unsigned dry_run, u8 buf[], u8 ev,
-		unsigned invalidate)
-{
-	if (dry_run)
-		return SZ_DMAWFE;
-
-	buf[0] = CMD_DMAWFE;
-
-	ev &= 0x1f;
-	ev <<= 3;
-	buf[1] = ev;
-
-	if (invalidate)
-		buf[1] |= (1 << 1);
-
-	PL330_DBGCMD_DUMP(SZ_DMAWFE, "\tDMAWFE %u%s\n",
-		ev >> 3, invalidate ? ", I" : "");
-
-	return SZ_DMAWFE;
-}
-
-static inline u32 _emit_WFP(unsigned dry_run, u8 buf[],
-		enum pl330_cond cond, u8 peri)
-{
-	if (dry_run)
-		return SZ_DMAWFP;
-
-	buf[0] = CMD_DMAWFP;
-
-	if (cond == SINGLE)
-		buf[0] |= (0 << 1) | (0 << 0);
-	else if (cond == BURST)
-		buf[0] |= (1 << 1) | (0 << 0);
-	else
-		buf[0] |= (0 << 1) | (1 << 0);
-
-	peri &= 0x1f;
-	peri <<= 3;
-	buf[1] = peri;
-
-	PL330_DBGCMD_DUMP(SZ_DMAWFP, "\tDMAWFP%c %u\n",
-		cond == SINGLE ? 'S' : (cond == BURST ? 'B' : 'P'), peri >> 3);
-
-	return SZ_DMAWFP;
-}
-
-static inline u32 _emit_WMB(unsigned dry_run, u8 buf[])
-{
-	if (dry_run)
-		return SZ_DMAWMB;
-
-	buf[0] = CMD_DMAWMB;
-
-	PL330_DBGCMD_DUMP(SZ_DMAWMB, "\tDMAWMB\n");
-
-	return SZ_DMAWMB;
-}
-
-struct _arg_GO {
-	u8 chan;
-	u32 addr;
-	unsigned ns;
-};
-
-static inline u32 _emit_GO(unsigned dry_run, u8 buf[],
-		const struct _arg_GO *arg)
-{
-	u8 chan = arg->chan;
-	u32 addr = arg->addr;
-	unsigned ns = arg->ns;
-
-	if (dry_run)
-		return SZ_DMAGO;
-
-	buf[0] = CMD_DMAGO;
-	buf[0] |= (ns << 1);
-
-	buf[1] = chan & 0x7;
-
-	*((u32 *)&buf[2]) = addr;
-
-	return SZ_DMAGO;
-}
-
-#define msecs_to_loops(t) (loops_per_jiffy / 1000 * HZ * t)
-
-/* Returns Time-Out */
-static bool _until_dmac_idle(struct pl330_thread *thrd)
-{
-	void __iomem *regs = thrd->dmac->pinfo->base;
-	unsigned long loops = msecs_to_loops(5);
-
-	do {
-		/* Until Manager is Idle */
-		if (!(readl(regs + DBGSTATUS) & DBG_BUSY))
-			break;
-
-		cpu_relax();
-	} while (--loops);
-
-	if (!loops)
-		return true;
-
-	return false;
-}
-
-static inline void _execute_DBGINSN(struct pl330_thread *thrd,
-		u8 insn[], bool as_manager)
-{
-	void __iomem *regs = thrd->dmac->pinfo->base;
-	u32 val;
-
-	val = (insn[0] << 16) | (insn[1] << 24);
-	if (!as_manager) {
-		val |= (1 << 0);
-		val |= (thrd->id << 8); /* Channel Number */
-	}
-	writel(val, regs + DBGINST0);
-
-	val = *((u32 *)&insn[2]);
-	writel(val, regs + DBGINST1);
-
-	/* If timed out due to halted state-machine */
-	if (_until_dmac_idle(thrd)) {
-		dev_err(thrd->dmac->pinfo->dev, "DMAC halted!\n");
-		return;
-	}
-
-	/* Get going */
-	writel(0, regs + DBGCMD);
-}
-
-/*
- * Mark a _pl330_req as free.
- * We do it by writing DMAEND as the first instruction
- * because no valid request is going to have DMAEND as
- * its first instruction to execute.
- */
-static void mark_free(struct pl330_thread *thrd, int idx)
-{
-	struct _pl330_req *req = &thrd->req[idx];
-
-	_emit_END(0, req->mc_cpu);
-	req->mc_len = 0;
-
-	thrd->req_running = -1;
-}
-
-static inline u32 _state(struct pl330_thread *thrd)
-{
-	void __iomem *regs = thrd->dmac->pinfo->base;
-	u32 val;
-
-	if (is_manager(thrd))
-		val = readl(regs + DS) & 0xf;
-	else
-		val = readl(regs + CS(thrd->id)) & 0xf;
-
-	switch (val) {
-	case DS_ST_STOP:
-		return PL330_STATE_STOPPED;
-	case DS_ST_EXEC:
-		return PL330_STATE_EXECUTING;
-	case DS_ST_CMISS:
-		return PL330_STATE_CACHEMISS;
-	case DS_ST_UPDTPC:
-		return PL330_STATE_UPDTPC;
-	case DS_ST_WFE:
-		return PL330_STATE_WFE;
-	case DS_ST_FAULT:
-		return PL330_STATE_FAULTING;
-	case DS_ST_ATBRR:
-		if (is_manager(thrd))
-			return PL330_STATE_INVALID;
-		else
-			return PL330_STATE_ATBARRIER;
-	case DS_ST_QBUSY:
-		if (is_manager(thrd))
-			return PL330_STATE_INVALID;
-		else
-			return PL330_STATE_QUEUEBUSY;
-	case DS_ST_WFP:
-		if (is_manager(thrd))
-			return PL330_STATE_INVALID;
-		else
-			return PL330_STATE_WFP;
-	case DS_ST_KILL:
-		if (is_manager(thrd))
-			return PL330_STATE_INVALID;
-		else
-			return PL330_STATE_KILLING;
-	case DS_ST_CMPLT:
-		if (is_manager(thrd))
-			return PL330_STATE_INVALID;
-		else
-			return PL330_STATE_COMPLETING;
-	case DS_ST_FLTCMP:
-		if (is_manager(thrd))
-			return PL330_STATE_INVALID;
-		else
-			return PL330_STATE_FAULT_COMPLETING;
-	default:
-		return PL330_STATE_INVALID;
-	}
-}
-
-static void _stop(struct pl330_thread *thrd)
-{
-	void __iomem *regs = thrd->dmac->pinfo->base;
-	u8 insn[6] = {0, 0, 0, 0, 0, 0};
-
-	if (_state(thrd) == PL330_STATE_FAULT_COMPLETING)
-		UNTIL(thrd, PL330_STATE_FAULTING | PL330_STATE_KILLING);
-
-	/* Return if nothing needs to be done */
-	if (_state(thrd) == PL330_STATE_COMPLETING
-		  || _state(thrd) == PL330_STATE_KILLING
-		  || _state(thrd) == PL330_STATE_STOPPED)
-		return;
-
-	_emit_KILL(0, insn);
-
-	/* Stop generating interrupts for SEV */
-	writel(readl(regs + INTEN) & ~(1 << thrd->ev), regs + INTEN);
-
-	_execute_DBGINSN(thrd, insn, is_manager(thrd));
-}
-
-/* Start doing req 'idx' of thread 'thrd' */
-static bool _trigger(struct pl330_thread *thrd)
-{
-	void __iomem *regs = thrd->dmac->pinfo->base;
-	struct _pl330_req *req;
-	struct pl330_req *r;
-	struct _arg_GO go;
-	unsigned ns;
-	u8 insn[6] = {0, 0, 0, 0, 0, 0};
-	int idx;
-
-	/* Return if already ACTIVE */
-	if (_state(thrd) != PL330_STATE_STOPPED)
-		return true;
-
-	idx = 1 - thrd->lstenq;
-	if (!IS_FREE(&thrd->req[idx]))
-		req = &thrd->req[idx];
-	else {
-		idx = thrd->lstenq;
-		if (!IS_FREE(&thrd->req[idx]))
-			req = &thrd->req[idx];
-		else
-			req = NULL;
-	}
-
-	/* Return if no request */
-	if (!req || !req->r)
-		return true;
-
-	r = req->r;
-
-	if (r->cfg)
-		ns = r->cfg->nonsecure ? 1 : 0;
-	else if (readl(regs + CS(thrd->id)) & CS_CNS)
-		ns = 1;
-	else
-		ns = 0;
-
-	/* See 'Abort Sources' point-4 at Page 2-25 */
-	if (_manager_ns(thrd) && !ns)
-		dev_info(thrd->dmac->pinfo->dev, "%s:%d Recipe for ABORT!\n",
-			__func__, __LINE__);
-
-	go.chan = thrd->id;
-	go.addr = req->mc_bus;
-	go.ns = ns;
-	_emit_GO(0, insn, &go);
-
-	/* Set to generate interrupts for SEV */
-	writel(readl(regs + INTEN) | (1 << thrd->ev), regs + INTEN);
-
-	/* Only manager can execute GO */
-	_execute_DBGINSN(thrd, insn, true);
-
-	thrd->req_running = idx;
-
-	return true;
-}
-
-static bool _start(struct pl330_thread *thrd)
-{
-	switch (_state(thrd)) {
-	case PL330_STATE_FAULT_COMPLETING:
-		UNTIL(thrd, PL330_STATE_FAULTING | PL330_STATE_KILLING);
-
-		if (_state(thrd) == PL330_STATE_KILLING)
-			UNTIL(thrd, PL330_STATE_STOPPED)
-
-	case PL330_STATE_FAULTING:
-		_stop(thrd);
-
-	case PL330_STATE_KILLING:
-	case PL330_STATE_COMPLETING:
-		UNTIL(thrd, PL330_STATE_STOPPED)
-
-	case PL330_STATE_STOPPED:
-		return _trigger(thrd);
-
-	case PL330_STATE_WFP:
-	case PL330_STATE_QUEUEBUSY:
-	case PL330_STATE_ATBARRIER:
-	case PL330_STATE_UPDTPC:
-	case PL330_STATE_CACHEMISS:
-	case PL330_STATE_EXECUTING:
-		return true;
-
-	case PL330_STATE_WFE: /* For RESUME, nothing yet */
-	default:
-		return false;
-	}
-}
-
-static inline int _ldst_memtomem(unsigned dry_run, u8 buf[],
-		const struct _xfer_spec *pxs, int cyc)
-{
-	int off = 0;
-
-	while (cyc--) {
-		off += _emit_LD(dry_run, &buf[off], ALWAYS);
-		off += _emit_RMB(dry_run, &buf[off]);
-		off += _emit_ST(dry_run, &buf[off], ALWAYS);
-		off += _emit_WMB(dry_run, &buf[off]);
-	}
-
-	return off;
-}
-
-static inline int _ldst_devtomem(unsigned dry_run, u8 buf[],
-		const struct _xfer_spec *pxs, int cyc)
-{
-	int off = 0;
-
-	while (cyc--) {
-		off += _emit_WFP(dry_run, &buf[off], SINGLE, pxs->r->peri);
-		off += _emit_LDP(dry_run, &buf[off], SINGLE, pxs->r->peri);
-		off += _emit_ST(dry_run, &buf[off], ALWAYS);
-		off += _emit_FLUSHP(dry_run, &buf[off], pxs->r->peri);
-	}
-
-	return off;
-}
-
-static inline int _ldst_memtodev(unsigned dry_run, u8 buf[],
-		const struct _xfer_spec *pxs, int cyc)
-{
-	int off = 0;
-
-	while (cyc--) {
-		off += _emit_WFP(dry_run, &buf[off], SINGLE, pxs->r->peri);
-		off += _emit_LD(dry_run, &buf[off], ALWAYS);
-		off += _emit_STP(dry_run, &buf[off], SINGLE, pxs->r->peri);
-		off += _emit_FLUSHP(dry_run, &buf[off], pxs->r->peri);
-	}
-
-	return off;
-}
-
-static int _bursts(unsigned dry_run, u8 buf[],
-		const struct _xfer_spec *pxs, int cyc)
-{
-	int off = 0;
-
-	switch (pxs->r->rqtype) {
-	case MEMTODEV:
-		off += _ldst_memtodev(dry_run, &buf[off], pxs, cyc);
-		break;
-	case DEVTOMEM:
-		off += _ldst_devtomem(dry_run, &buf[off], pxs, cyc);
-		break;
-	case MEMTOMEM:
-		off += _ldst_memtomem(dry_run, &buf[off], pxs, cyc);
-		break;
-	default:
-		off += 0x40000000; /* Scare off the Client */
-		break;
-	}
-
-	return off;
-}
-
-/* Returns bytes consumed and updates bursts */
-static inline int _loop(unsigned dry_run, u8 buf[],
-		unsigned long *bursts, const struct _xfer_spec *pxs)
-{
-	int cyc, cycmax, szlp, szlpend, szbrst, off;
-	unsigned lcnt0, lcnt1, ljmp0, ljmp1;
-	struct _arg_LPEND lpend;
-
-	/* Max iterations possible in DMALP is 256 */
-	if (*bursts >= 256*256) {
-		lcnt1 = 256;
-		lcnt0 = 256;
-		cyc = *bursts / lcnt1 / lcnt0;
-	} else if (*bursts > 256) {
-		lcnt1 = 256;
-		lcnt0 = *bursts / lcnt1;
-		cyc = 1;
-	} else {
-		lcnt1 = *bursts;
-		lcnt0 = 0;
-		cyc = 1;
-	}
-
-	szlp = _emit_LP(1, buf, 0, 0);
-	szbrst = _bursts(1, buf, pxs, 1);
-
-	lpend.cond = ALWAYS;
-	lpend.forever = false;
-	lpend.loop = 0;
-	lpend.bjump = 0;
-	szlpend = _emit_LPEND(1, buf, &lpend);
-
-	if (lcnt0) {
-		szlp *= 2;
-		szlpend *= 2;
-	}
-
-	/*
-	 * Max bursts that we can unroll due to limit on the
-	 * size of backward jump that can be encoded in DMALPEND
-	 * which is 8-bits and hence 255
-	 */
-	cycmax = (255 - (szlp + szlpend)) / szbrst;
-
-	cyc = (cycmax < cyc) ? cycmax : cyc;
-
-	off = 0;
-
-	if (lcnt0) {
-		off += _emit_LP(dry_run, &buf[off], 0, lcnt0);
-		ljmp0 = off;
-	}
-
-	off += _emit_LP(dry_run, &buf[off], 1, lcnt1);
-	ljmp1 = off;
-
-	off += _bursts(dry_run, &buf[off], pxs, cyc);
-
-	lpend.cond = ALWAYS;
-	lpend.forever = false;
-	lpend.loop = 1;
-	lpend.bjump = off - ljmp1;
-	off += _emit_LPEND(dry_run, &buf[off], &lpend);
-
-	if (lcnt0) {
-		lpend.cond = ALWAYS;
-		lpend.forever = false;
-		lpend.loop = 0;
-		lpend.bjump = off - ljmp0;
-		off += _emit_LPEND(dry_run, &buf[off], &lpend);
-	}
-
-	*bursts = lcnt1 * cyc;
-	if (lcnt0)
-		*bursts *= lcnt0;
-
-	return off;
-}
-
-static inline int _setup_loops(unsigned dry_run, u8 buf[],
-		const struct _xfer_spec *pxs)
-{
-	struct pl330_xfer *x = pxs->x;
-	u32 ccr = pxs->ccr;
-	unsigned long c, bursts = BYTE_TO_BURST(x->bytes, ccr);
-	int off = 0;
-
-	while (bursts) {
-		c = bursts;
-		off += _loop(dry_run, &buf[off], &c, pxs);
-		bursts -= c;
-	}
-
-	return off;
-}
-
-static inline int _setup_xfer(unsigned dry_run, u8 buf[],
-		const struct _xfer_spec *pxs)
-{
-	struct pl330_xfer *x = pxs->x;
-	int off = 0;
-
-	/* DMAMOV SAR, x->src_addr */
-	off += _emit_MOV(dry_run, &buf[off], SAR, x->src_addr);
-	/* DMAMOV DAR, x->dst_addr */
-	off += _emit_MOV(dry_run, &buf[off], DAR, x->dst_addr);
-
-	/* Setup Loop(s) */
-	off += _setup_loops(dry_run, &buf[off], pxs);
-
-	return off;
-}
-
-/*
- * A req is a sequence of one or more xfer units.
- * Returns the number of bytes taken to setup the MC for the req.
- */
-static int _setup_req(unsigned dry_run, struct pl330_thread *thrd,
-		unsigned index, struct _xfer_spec *pxs)
-{
-	struct _pl330_req *req = &thrd->req[index];
-	struct pl330_xfer *x;
-	u8 *buf = req->mc_cpu;
-	int off = 0;
-
-	PL330_DBGMC_START(req->mc_bus);
-
-	/* DMAMOV CCR, ccr */
-	off += _emit_MOV(dry_run, &buf[off], CCR, pxs->ccr);
-
-	x = pxs->r->x;
-	do {
-		/* Error if xfer length is not aligned at burst size */
-		if (x->bytes % (BRST_SIZE(pxs->ccr) * BRST_LEN(pxs->ccr)))
-			return -EINVAL;
-
-		pxs->x = x;
-		off += _setup_xfer(dry_run, &buf[off], pxs);
-
-		x = x->next;
-	} while (x);
-
-	/* DMASEV peripheral/event */
-	off += _emit_SEV(dry_run, &buf[off], thrd->ev);
-	/* DMAEND */
-	off += _emit_END(dry_run, &buf[off]);
-
-	return off;
-}
-
-static inline u32 _prepare_ccr(const struct pl330_reqcfg *rqc)
-{
-	u32 ccr = 0;
-
-	if (rqc->src_inc)
-		ccr |= CC_SRCINC;
-
-	if (rqc->dst_inc)
-		ccr |= CC_DSTINC;
-
-	/* We set same protection levels for Src and DST for now */
-	if (rqc->privileged)
-		ccr |= CC_SRCPRI | CC_DSTPRI;
-	if (rqc->nonsecure)
-		ccr |= CC_SRCNS | CC_DSTNS;
-	if (rqc->insnaccess)
-		ccr |= CC_SRCIA | CC_DSTIA;
-
-	ccr |= (((rqc->brst_len - 1) & 0xf) << CC_SRCBRSTLEN_SHFT);
-	ccr |= (((rqc->brst_len - 1) & 0xf) << CC_DSTBRSTLEN_SHFT);
-
-	ccr |= (rqc->brst_size << CC_SRCBRSTSIZE_SHFT);
-	ccr |= (rqc->brst_size << CC_DSTBRSTSIZE_SHFT);
-
-	ccr |= (rqc->scctl << CC_SRCCCTRL_SHFT);
-	ccr |= (rqc->dcctl << CC_DSTCCTRL_SHFT);
-
-	ccr |= (rqc->swap << CC_SWAP_SHFT);
-
-	return ccr;
-}
-
-static inline bool _is_valid(u32 ccr)
-{
-	enum pl330_dstcachectrl dcctl;
-	enum pl330_srccachectrl scctl;
-
-	dcctl = (ccr >> CC_DSTCCTRL_SHFT) & CC_DRCCCTRL_MASK;
-	scctl = (ccr >> CC_SRCCCTRL_SHFT) & CC_SRCCCTRL_MASK;
-
-	if (dcctl == DINVALID1 || dcctl == DINVALID2
-			|| scctl == SINVALID1 || scctl == SINVALID2)
-		return false;
-	else
-		return true;
-}
-
-/*
- * Submit a list of xfers after which the client wants notification.
- * Client is not notified after each xfer unit, just once after all
- * xfer units are done or some error occurs.
- */
-int pl330_submit_req(void *ch_id, struct pl330_req *r)
-{
-	struct pl330_thread *thrd = ch_id;
-	struct pl330_dmac *pl330;
-	struct pl330_info *pi;
-	struct _xfer_spec xs;
-	unsigned long flags;
-	void __iomem *regs;
-	unsigned idx;
-	u32 ccr;
-	int ret = 0;
-
-	/* No Req or Unacquired Channel or DMAC */
-	if (!r || !thrd || thrd->free)
-		return -EINVAL;
-
-	pl330 = thrd->dmac;
-	pi = pl330->pinfo;
-	regs = pi->base;
-
-	if (pl330->state == DYING
-		|| pl330->dmac_tbd.reset_chan & (1 << thrd->id)) {
-		dev_info(thrd->dmac->pinfo->dev, "%s:%d\n",
-			__func__, __LINE__);
-		return -EAGAIN;
-	}
-
-	/* If request for non-existing peripheral */
-	if (r->rqtype != MEMTOMEM && r->peri >= pi->pcfg.num_peri) {
-		dev_info(thrd->dmac->pinfo->dev,
-				"%s:%d Invalid peripheral(%u)!\n",
-				__func__, __LINE__, r->peri);
-		return -EINVAL;
-	}
-
-	spin_lock_irqsave(&pl330->lock, flags);
-
-	if (_queue_full(thrd)) {
-		ret = -EAGAIN;
-		goto xfer_exit;
-	}
-
-	/* Prefer Secure Channel */
-	if (!_manager_ns(thrd))
-		r->cfg->nonsecure = 0;
-	else
-		r->cfg->nonsecure = 1;
-
-	/* Use last settings, if not provided */
-	if (r->cfg)
-		ccr = _prepare_ccr(r->cfg);
-	else
-		ccr = readl(regs + CC(thrd->id));
-
-	/* If this req doesn't have valid xfer settings */
-	if (!_is_valid(ccr)) {
-		ret = -EINVAL;
-		dev_info(thrd->dmac->pinfo->dev, "%s:%d Invalid CCR(%x)!\n",
-			__func__, __LINE__, ccr);
-		goto xfer_exit;
-	}
-
-	idx = IS_FREE(&thrd->req[0]) ? 0 : 1;
-
-	xs.ccr = ccr;
-	xs.r = r;
-
-	/* First dry run to check if req is acceptable */
-	ret = _setup_req(1, thrd, idx, &xs);
-	if (ret < 0)
-		goto xfer_exit;
-
-	if (ret > pi->mcbufsz / 2) {
-		dev_info(thrd->dmac->pinfo->dev,
-			"%s:%d Trying increasing mcbufsz\n",
-				__func__, __LINE__);
-		ret = -ENOMEM;
-		goto xfer_exit;
-	}
-
-	/* Hook the request */
-	thrd->lstenq = idx;
-	thrd->req[idx].mc_len = _setup_req(0, thrd, idx, &xs);
-	thrd->req[idx].r = r;
-
-	ret = 0;
-
-xfer_exit:
-	spin_unlock_irqrestore(&pl330->lock, flags);
-
-	return ret;
-}
-EXPORT_SYMBOL(pl330_submit_req);
-
-static void pl330_dotask(unsigned long data)
-{
-	struct pl330_dmac *pl330 = (struct pl330_dmac *) data;
-	struct pl330_info *pi = pl330->pinfo;
-	unsigned long flags;
-	int i;
-
-	spin_lock_irqsave(&pl330->lock, flags);
-
-	/* The DMAC itself gone nuts */
-	if (pl330->dmac_tbd.reset_dmac) {
-		pl330->state = DYING;
-		/* Reset the manager too */
-		pl330->dmac_tbd.reset_mngr = true;
-		/* Clear the reset flag */
-		pl330->dmac_tbd.reset_dmac = false;
-	}
-
-	if (pl330->dmac_tbd.reset_mngr) {
-		_stop(pl330->manager);
-		/* Reset all channels */
-		pl330->dmac_tbd.reset_chan = (1 << pi->pcfg.num_chan) - 1;
-		/* Clear the reset flag */
-		pl330->dmac_tbd.reset_mngr = false;
-	}
-
-	for (i = 0; i < pi->pcfg.num_chan; i++) {
-
-		if (pl330->dmac_tbd.reset_chan & (1 << i)) {
-			struct pl330_thread *thrd = &pl330->channels[i];
-			void __iomem *regs = pi->base;
-			enum pl330_op_err err;
-
-			_stop(thrd);
-
-			if (readl(regs + FSC) & (1 << thrd->id))
-				err = PL330_ERR_FAIL;
-			else
-				err = PL330_ERR_ABORT;
-
-			spin_unlock_irqrestore(&pl330->lock, flags);
-
-			_callback(thrd->req[1 - thrd->lstenq].r, err);
-			_callback(thrd->req[thrd->lstenq].r, err);
-
-			spin_lock_irqsave(&pl330->lock, flags);
-
-			thrd->req[0].r = NULL;
-			thrd->req[1].r = NULL;
-			mark_free(thrd, 0);
-			mark_free(thrd, 1);
-
-			/* Clear the reset flag */
-			pl330->dmac_tbd.reset_chan &= ~(1 << i);
-		}
-	}
-
-	spin_unlock_irqrestore(&pl330->lock, flags);
-
-	return;
-}
-
-/* Returns 1 if state was updated, 0 otherwise */
-int pl330_update(const struct pl330_info *pi)
-{
-	struct _pl330_req *rqdone;
-	struct pl330_dmac *pl330;
-	unsigned long flags;
-	void __iomem *regs;
-	u32 val;
-	int id, ev, ret = 0;
-
-	if (!pi || !pi->pl330_data)
-		return 0;
-
-	regs = pi->base;
-	pl330 = pi->pl330_data;
-
-	spin_lock_irqsave(&pl330->lock, flags);
-
-	val = readl(regs + FSM) & 0x1;
-	if (val)
-		pl330->dmac_tbd.reset_mngr = true;
-	else
-		pl330->dmac_tbd.reset_mngr = false;
-
-	val = readl(regs + FSC) & ((1 << pi->pcfg.num_chan) - 1);
-	pl330->dmac_tbd.reset_chan |= val;
-	if (val) {
-		int i = 0;
-		while (i < pi->pcfg.num_chan) {
-			if (val & (1 << i)) {
-				dev_info(pi->dev,
-					"Reset Channel-%d\t CS-%x FTC-%x\n",
-						i, readl(regs + CS(i)),
-						readl(regs + FTC(i)));
-				_stop(&pl330->channels[i]);
-			}
-			i++;
-		}
-	}
-
-	/* Check which event happened i.e, thread notified */
-	val = readl(regs + ES);
-	if (pi->pcfg.num_events < 32
-			&& val & ~((1 << pi->pcfg.num_events) - 1)) {
-		pl330->dmac_tbd.reset_dmac = true;
-		dev_err(pi->dev, "%s:%d Unexpected!\n", __func__, __LINE__);
-		ret = 1;
-		goto updt_exit;
-	}
-
-	for (ev = 0; ev < pi->pcfg.num_events; ev++) {
-		if (val & (1 << ev)) { /* Event occurred */
-			struct pl330_thread *thrd;
-			u32 inten = readl(regs + INTEN);
-			int active;
-
-			/* Clear the event */
-			if (inten & (1 << ev))
-				writel(1 << ev, regs + INTCLR);
-
-			ret = 1;
-
-			id = pl330->events[ev];
-
-			thrd = &pl330->channels[id];
-
-			active = thrd->req_running;
-			if (active == -1) /* Aborted */
-				continue;
-
-			rqdone = &thrd->req[active];
-			mark_free(thrd, active);
-
-			/* Get going again ASAP */
-			_start(thrd);
-
-			/* For now, just make a list of callbacks to be done */
-			list_add_tail(&rqdone->rqd, &pl330->req_done);
-		}
-	}
-
-	/* Now that we are in no hurry, do the callbacks */
-	while (!list_empty(&pl330->req_done)) {
-		struct pl330_req *r;
-
-		rqdone = container_of(pl330->req_done.next,
-					struct _pl330_req, rqd);
-
-		list_del_init(&rqdone->rqd);
-
-		/* Detach the req */
-		r = rqdone->r;
-		rqdone->r = NULL;
-
-		spin_unlock_irqrestore(&pl330->lock, flags);
-		_callback(r, PL330_ERR_NONE);
-		spin_lock_irqsave(&pl330->lock, flags);
-	}
-
-updt_exit:
-	spin_unlock_irqrestore(&pl330->lock, flags);
-
-	if (pl330->dmac_tbd.reset_dmac
-			|| pl330->dmac_tbd.reset_mngr
-			|| pl330->dmac_tbd.reset_chan) {
-		ret = 1;
-		tasklet_schedule(&pl330->tasks);
-	}
-
-	return ret;
-}
-EXPORT_SYMBOL(pl330_update);
-
-int pl330_chan_ctrl(void *ch_id, enum pl330_chan_op op)
-{
-	struct pl330_thread *thrd = ch_id;
-	struct pl330_dmac *pl330;
-	unsigned long flags;
-	int ret = 0, active;
-
-	if (!thrd || thrd->free || thrd->dmac->state == DYING)
-		return -EINVAL;
-
-	pl330 = thrd->dmac;
-	active = thrd->req_running;
-
-	spin_lock_irqsave(&pl330->lock, flags);
-
-	switch (op) {
-	case PL330_OP_FLUSH:
-		/* Make sure the channel is stopped */
-		_stop(thrd);
-
-		thrd->req[0].r = NULL;
-		thrd->req[1].r = NULL;
-		mark_free(thrd, 0);
-		mark_free(thrd, 1);
-		break;
-
-	case PL330_OP_ABORT:
-		/* Make sure the channel is stopped */
-		_stop(thrd);
-
-		/* ABORT is only for the active req */
-		if (active == -1)
-			break;
-
-		thrd->req[active].r = NULL;
-		mark_free(thrd, active);
-
-		/* Start the next */
-	case PL330_OP_START:
-		if ((active == -1) && !_start(thrd))
-			ret = -EIO;
-		break;
-
-	default:
-		ret = -EINVAL;
-	}
-
-	spin_unlock_irqrestore(&pl330->lock, flags);
-	return ret;
-}
-EXPORT_SYMBOL(pl330_chan_ctrl);
-
-int pl330_chan_status(void *ch_id, struct pl330_chanstatus *pstatus)
-{
-	struct pl330_thread *thrd = ch_id;
-	struct pl330_dmac *pl330;
-	struct pl330_info *pi;
-	void __iomem *regs;
-	int active;
-	u32 val;
-
-	if (!pstatus || !thrd || thrd->free)
-		return -EINVAL;
-
-	pl330 = thrd->dmac;
-	pi = pl330->pinfo;
-	regs = pi->base;
-
-	/* The client should remove the DMAC and add again */
-	if (pl330->state == DYING)
-		pstatus->dmac_halted = true;
-	else
-		pstatus->dmac_halted = false;
-
-	val = readl(regs + FSC);
-	if (val & (1 << thrd->id))
-		pstatus->faulting = true;
-	else
-		pstatus->faulting = false;
-
-	active = thrd->req_running;
-
-	if (active == -1) {
-		/* Indicate that the thread is not running */
-		pstatus->top_req = NULL;
-		pstatus->wait_req = NULL;
-	} else {
-		pstatus->top_req = thrd->req[active].r;
-		pstatus->wait_req = !IS_FREE(&thrd->req[1 - active])
-					? thrd->req[1 - active].r : NULL;
-	}
-
-	pstatus->src_addr = readl(regs + SA(thrd->id));
-	pstatus->dst_addr = readl(regs + DA(thrd->id));
-
-	return 0;
-}
-EXPORT_SYMBOL(pl330_chan_status);
-
-/* Reserve an event */
-static inline int _alloc_event(struct pl330_thread *thrd)
-{
-	struct pl330_dmac *pl330 = thrd->dmac;
-	struct pl330_info *pi = pl330->pinfo;
-	int ev;
-
-	for (ev = 0; ev < pi->pcfg.num_events; ev++)
-		if (pl330->events[ev] == -1) {
-			pl330->events[ev] = thrd->id;
-			return ev;
-		}
-
-	return -1;
-}
-
-static bool _chan_ns(const struct pl330_info *pi, int i)
-{
-	return pi->pcfg.irq_ns & (1 << i);
-}
-
-/* Upon success, returns IdentityToken for the
- * allocated channel, NULL otherwise.
- */
-void *pl330_request_channel(const struct pl330_info *pi)
-{
-	struct pl330_thread *thrd = NULL;
-	struct pl330_dmac *pl330;
-	unsigned long flags;
-	int chans, i;
-
-	if (!pi || !pi->pl330_data)
-		return NULL;
-
-	pl330 = pi->pl330_data;
-
-	if (pl330->state == DYING)
-		return NULL;
-
-	chans = pi->pcfg.num_chan;
-
-	spin_lock_irqsave(&pl330->lock, flags);
-
-	for (i = 0; i < chans; i++) {
-		thrd = &pl330->channels[i];
-		if ((thrd->free) && (!_manager_ns(thrd) ||
-					_chan_ns(pi, i))) {
-			thrd->ev = _alloc_event(thrd);
-			if (thrd->ev >= 0) {
-				thrd->free = false;
-				thrd->lstenq = 1;
-				thrd->req[0].r = NULL;
-				mark_free(thrd, 0);
-				thrd->req[1].r = NULL;
-				mark_free(thrd, 1);
-				break;
-			}
-		}
-		thrd = NULL;
-	}
-
-	spin_unlock_irqrestore(&pl330->lock, flags);
-
-	return thrd;
-}
-EXPORT_SYMBOL(pl330_request_channel);
-
-/* Release an event */
-static inline void _free_event(struct pl330_thread *thrd, int ev)
-{
-	struct pl330_dmac *pl330 = thrd->dmac;
-	struct pl330_info *pi = pl330->pinfo;
-
-	/* If the event is valid and was held by the thread */
-	if (ev >= 0 && ev < pi->pcfg.num_events
-			&& pl330->events[ev] == thrd->id)
-		pl330->events[ev] = -1;
-}
-
-void pl330_release_channel(void *ch_id)
-{
-	struct pl330_thread *thrd = ch_id;
-	struct pl330_dmac *pl330;
-	unsigned long flags;
-
-	if (!thrd || thrd->free)
-		return;
-
-	_stop(thrd);
-
-	_callback(thrd->req[1 - thrd->lstenq].r, PL330_ERR_ABORT);
-	_callback(thrd->req[thrd->lstenq].r, PL330_ERR_ABORT);
-
-	pl330 = thrd->dmac;
-
-	spin_lock_irqsave(&pl330->lock, flags);
-	_free_event(thrd, thrd->ev);
-	thrd->free = true;
-	spin_unlock_irqrestore(&pl330->lock, flags);
-}
-EXPORT_SYMBOL(pl330_release_channel);
-
-/* Initialize the structure for PL330 configuration, that can be used
- * by the client driver the make best use of the DMAC
- */
-static void read_dmac_config(struct pl330_info *pi)
-{
-	void __iomem *regs = pi->base;
-	u32 val;
-
-	val = readl(regs + CRD) >> CRD_DATA_WIDTH_SHIFT;
-	val &= CRD_DATA_WIDTH_MASK;
-	pi->pcfg.data_bus_width = 8 * (1 << val);
-
-	val = readl(regs + CRD) >> CRD_DATA_BUFF_SHIFT;
-	val &= CRD_DATA_BUFF_MASK;
-	pi->pcfg.data_buf_dep = val + 1;
-
-	val = readl(regs + CR0) >> CR0_NUM_CHANS_SHIFT;
-	val &= CR0_NUM_CHANS_MASK;
-	val += 1;
-	pi->pcfg.num_chan = val;
-
-	val = readl(regs + CR0);
-	if (val & CR0_PERIPH_REQ_SET) {
-		val = (val >> CR0_NUM_PERIPH_SHIFT) & CR0_NUM_PERIPH_MASK;
-		val += 1;
-		pi->pcfg.num_peri = val;
-		pi->pcfg.peri_ns = readl(regs + CR4);
-	} else {
-		pi->pcfg.num_peri = 0;
-	}
-
-	val = readl(regs + CR0);
-	if (val & CR0_BOOT_MAN_NS)
-		pi->pcfg.mode |= DMAC_MODE_NS;
-	else
-		pi->pcfg.mode &= ~DMAC_MODE_NS;
-
-	val = readl(regs + CR0) >> CR0_NUM_EVENTS_SHIFT;
-	val &= CR0_NUM_EVENTS_MASK;
-	val += 1;
-	pi->pcfg.num_events = val;
-
-	pi->pcfg.irq_ns = readl(regs + CR3);
-
-	pi->pcfg.periph_id = get_id(pi, PERIPH_ID);
-	pi->pcfg.pcell_id = get_id(pi, PCELL_ID);
-}
-
-static inline void _reset_thread(struct pl330_thread *thrd)
-{
-	struct pl330_dmac *pl330 = thrd->dmac;
-	struct pl330_info *pi = pl330->pinfo;
-
-	thrd->req[0].mc_cpu = pl330->mcode_cpu
-				+ (thrd->id * pi->mcbufsz);
-	thrd->req[0].mc_bus = pl330->mcode_bus
-				+ (thrd->id * pi->mcbufsz);
-	thrd->req[0].r = NULL;
-	mark_free(thrd, 0);
-
-	thrd->req[1].mc_cpu = thrd->req[0].mc_cpu
-				+ pi->mcbufsz / 2;
-	thrd->req[1].mc_bus = thrd->req[0].mc_bus
-				+ pi->mcbufsz / 2;
-	thrd->req[1].r = NULL;
-	mark_free(thrd, 1);
-}
-
-static int dmac_alloc_threads(struct pl330_dmac *pl330)
-{
-	struct pl330_info *pi = pl330->pinfo;
-	int chans = pi->pcfg.num_chan;
-	struct pl330_thread *thrd;
-	int i;
-
-	/* Allocate 1 Manager and 'chans' Channel threads */
-	pl330->channels = kzalloc((1 + chans) * sizeof(*thrd),
-					GFP_KERNEL);
-	if (!pl330->channels)
-		return -ENOMEM;
-
-	/* Init Channel threads */
-	for (i = 0; i < chans; i++) {
-		thrd = &pl330->channels[i];
-		thrd->id = i;
-		thrd->dmac = pl330;
-		_reset_thread(thrd);
-		thrd->free = true;
-	}
-
-	/* MANAGER is indexed at the end */
-	thrd = &pl330->channels[chans];
-	thrd->id = chans;
-	thrd->dmac = pl330;
-	thrd->free = false;
-	pl330->manager = thrd;
-
-	return 0;
-}
-
-static int dmac_alloc_resources(struct pl330_dmac *pl330)
-{
-	struct pl330_info *pi = pl330->pinfo;
-	int chans = pi->pcfg.num_chan;
-	int ret;
-
-	/*
-	 * Alloc MicroCode buffer for 'chans' Channel threads.
-	 * A channel's buffer offset is (Channel_Id * MCODE_BUFF_PERCHAN)
-	 */
-	pl330->mcode_cpu = dma_alloc_coherent(pi->dev,
-				chans * pi->mcbufsz,
-				&pl330->mcode_bus, GFP_KERNEL);
-	if (!pl330->mcode_cpu) {
-		dev_err(pi->dev, "%s:%d Can't allocate memory!\n",
-			__func__, __LINE__);
-		return -ENOMEM;
-	}
-
-	ret = dmac_alloc_threads(pl330);
-	if (ret) {
-		dev_err(pi->dev, "%s:%d Can't to create channels for DMAC!\n",
-			__func__, __LINE__);
-		dma_free_coherent(pi->dev,
-				chans * pi->mcbufsz,
-				pl330->mcode_cpu, pl330->mcode_bus);
-		return ret;
-	}
-
-	return 0;
-}
-
-int pl330_add(struct pl330_info *pi)
-{
-	struct pl330_dmac *pl330;
-	void __iomem *regs;
-	int i, ret;
-
-	if (!pi || !pi->dev)
-		return -EINVAL;
-
-	/* If already added */
-	if (pi->pl330_data)
-		return -EINVAL;
-
-	/*
-	 * If the SoC can perform reset on the DMAC, then do it
-	 * before reading its configuration.
-	 */
-	if (pi->dmac_reset)
-		pi->dmac_reset(pi);
-
-	regs = pi->base;
-
-	/* Check if we can handle this DMAC */
-	if ((get_id(pi, PERIPH_ID) & 0xfffff) != PERIPH_ID_VAL
-	   || get_id(pi, PCELL_ID) != PCELL_ID_VAL) {
-		dev_err(pi->dev, "PERIPH_ID 0x%x, PCELL_ID 0x%x !\n",
-			get_id(pi, PERIPH_ID), get_id(pi, PCELL_ID));
-		return -EINVAL;
-	}
-
-	/* Read the configuration of the DMAC */
-	read_dmac_config(pi);
-
-	if (pi->pcfg.num_events == 0) {
-		dev_err(pi->dev, "%s:%d Can't work without events!\n",
-			__func__, __LINE__);
-		return -EINVAL;
-	}
-
-	pl330 = kzalloc(sizeof(*pl330), GFP_KERNEL);
-	if (!pl330) {
-		dev_err(pi->dev, "%s:%d Can't allocate memory!\n",
-			__func__, __LINE__);
-		return -ENOMEM;
-	}
-
-	/* Assign the info structure and private data */
-	pl330->pinfo = pi;
-	pi->pl330_data = pl330;
-
-	spin_lock_init(&pl330->lock);
-
-	INIT_LIST_HEAD(&pl330->req_done);
-
-	/* Use default MC buffer size if not provided */
-	if (!pi->mcbufsz)
-		pi->mcbufsz = MCODE_BUFF_PER_REQ * 2;
-
-	/* Mark all events as free */
-	for (i = 0; i < pi->pcfg.num_events; i++)
-		pl330->events[i] = -1;
-
-	/* Allocate resources needed by the DMAC */
-	ret = dmac_alloc_resources(pl330);
-	if (ret) {
-		dev_err(pi->dev, "Unable to create channels for DMAC\n");
-		kfree(pl330);
-		return ret;
-	}
-
-	tasklet_init(&pl330->tasks, pl330_dotask, (unsigned long) pl330);
-
-	pl330->state = INIT;
-
-	return 0;
-}
-EXPORT_SYMBOL(pl330_add);
-
-static int dmac_free_threads(struct pl330_dmac *pl330)
-{
-	struct pl330_info *pi = pl330->pinfo;
-	int chans = pi->pcfg.num_chan;
-	struct pl330_thread *thrd;
-	int i;
-
-	/* Release Channel threads */
-	for (i = 0; i < chans; i++) {
-		thrd = &pl330->channels[i];
-		pl330_release_channel((void *)thrd);
-	}
-
-	/* Free memory */
-	kfree(pl330->channels);
-
-	return 0;
-}
-
-static void dmac_free_resources(struct pl330_dmac *pl330)
-{
-	struct pl330_info *pi = pl330->pinfo;
-	int chans = pi->pcfg.num_chan;
-
-	dmac_free_threads(pl330);
-
-	dma_free_coherent(pi->dev, chans * pi->mcbufsz,
-				pl330->mcode_cpu, pl330->mcode_bus);
-}
-
-void pl330_del(struct pl330_info *pi)
-{
-	struct pl330_dmac *pl330;
-
-	if (!pi || !pi->pl330_data)
-		return;
-
-	pl330 = pi->pl330_data;
-
-	pl330->state = UNINIT;
-
-	tasklet_kill(&pl330->tasks);
-
-	/* Free DMAC resources */
-	dmac_free_resources(pl330);
-
-	kfree(pl330);
-	pi->pl330_data = NULL;
-}
-EXPORT_SYMBOL(pl330_del);
diff --git a/arch/arm/configs/integrator_defconfig b/arch/arm/configs/integrator_defconfig
index 1103f62..a8314c3 100644
--- a/arch/arm/configs/integrator_defconfig
+++ b/arch/arm/configs/integrator_defconfig
@@ -57,18 +57,24 @@
 CONFIG_NET_ETHERNET=y
 CONFIG_NET_PCI=y
 CONFIG_E100=y
+CONFIG_SMC91X=y
 # CONFIG_KEYBOARD_ATKBD is not set
 # CONFIG_SERIO_SERPORT is not set
 CONFIG_SERIAL_AMBA_PL010=y
 CONFIG_SERIAL_AMBA_PL010_CONSOLE=y
 CONFIG_FB=y
 CONFIG_FB_MODE_HELPERS=y
+CONFIG_FB_ARMCLCD=y
 CONFIG_FB_MATROX=y
 CONFIG_FB_MATROX_MILLENIUM=y
 CONFIG_FB_MATROX_MYSTIQUE=y
+# CONFIG_VGA_CONSOLE is not set
+CONFIG_MMC=y
+CONFIG_MMC_ARMMMCI=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_PL030=y
 CONFIG_EXT2_FS=y
+CONFIG_VFAT_FS=y
 CONFIG_TMPFS=y
 CONFIG_JFFS2_FS=y
 CONFIG_CRAMFS=y
@@ -78,5 +84,7 @@
 CONFIG_NFSD=y
 CONFIG_NFSD_V3=y
 CONFIG_PARTITION_ADVANCED=y
+CONFIG_NLS_CODEPAGE_437=y
+CONFIG_NLS_ISO8859_1=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_KERNEL=y
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index 23371b1..03fb936 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -23,6 +23,8 @@
 #include <asm/ptrace.h>
 #include <asm/domain.h>
 
+#define IOMEM(x)	(x)
+
 /*
  * Endian independent macros for shifting bytes within registers.
  */
diff --git a/arch/arm/include/asm/elf.h b/arch/arm/include/asm/elf.h
index 0e9ce8d..38050b1 100644
--- a/arch/arm/include/asm/elf.h
+++ b/arch/arm/include/asm/elf.h
@@ -130,8 +130,4 @@
 extern unsigned long arch_randomize_brk(struct mm_struct *mm);
 #define arch_randomize_brk arch_randomize_brk
 
-extern int vectors_user_mapping(void);
-#define arch_setup_additional_pages(bprm, uses_interp) vectors_user_mapping()
-#define ARCH_HAS_SETUP_ADDITIONAL_PAGES
-
 #endif
diff --git a/arch/arm/include/asm/hardware/cache-l2x0.h b/arch/arm/include/asm/hardware/cache-l2x0.h
index 7df239b..c4c87bc 100644
--- a/arch/arm/include/asm/hardware/cache-l2x0.h
+++ b/arch/arm/include/asm/hardware/cache-l2x0.h
@@ -103,11 +103,11 @@
 #define L2X0_ADDR_FILTER_EN		1
 
 #ifndef __ASSEMBLY__
-extern void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask);
+extern void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask);
 #if defined(CONFIG_CACHE_L2X0) && defined(CONFIG_OF)
-extern int l2x0_of_init(__u32 aux_val, __u32 aux_mask);
+extern int l2x0_of_init(u32 aux_val, u32 aux_mask);
 #else
-static inline int l2x0_of_init(__u32 aux_val, __u32 aux_mask)
+static inline int l2x0_of_init(u32 aux_val, u32 aux_mask)
 {
 	return -ENODEV;
 }
diff --git a/arch/arm/include/asm/hardware/iop_adma.h b/arch/arm/include/asm/hardware/iop_adma.h
index 59b8c38..122f86d 100644
--- a/arch/arm/include/asm/hardware/iop_adma.h
+++ b/arch/arm/include/asm/hardware/iop_adma.h
@@ -49,7 +49,6 @@
 /**
  * struct iop_adma_chan - internal representation of an ADMA device
  * @pending: allows batching of hardware operations
- * @completed_cookie: identifier for the most recently completed operation
  * @lock: serializes enqueue/dequeue operations to the slot pool
  * @mmr_base: memory mapped register base
  * @chain: device chain view of the descriptors
@@ -62,7 +61,6 @@
  */
 struct iop_adma_chan {
 	int pending;
-	dma_cookie_t completed_cookie;
 	spinlock_t lock; /* protects the descriptor slot pool */
 	void __iomem *mmr_base;
 	struct list_head chain;
diff --git a/arch/arm/include/asm/hardware/it8152.h b/arch/arm/include/asm/hardware/it8152.h
index 43cab49..73f84fa 100644
--- a/arch/arm/include/asm/hardware/it8152.h
+++ b/arch/arm/include/asm/hardware/it8152.h
@@ -9,6 +9,9 @@
 
 #ifndef __ASM_HARDWARE_IT8152_H
 #define __ASM_HARDWARE_IT8152_H
+
+#include <mach/irqs.h>
+
 extern void __iomem *it8152_base_address;
 
 #define IT8152_IO_BASE			(it8152_base_address + 0x03e00000)
diff --git a/arch/arm/include/asm/hardware/pl330.h b/arch/arm/include/asm/hardware/pl330.h
deleted file mode 100644
index c182138..0000000
--- a/arch/arm/include/asm/hardware/pl330.h
+++ /dev/null
@@ -1,217 +0,0 @@
-/* linux/include/asm/hardware/pl330.h
- *
- * Copyright (C) 2010 Samsung Electronics Co. Ltd.
- *	Jaswinder Singh <jassi.brar@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., 675 Mass Ave, Cambridge, MA 02139, USA.
- */
-
-#ifndef __PL330_CORE_H
-#define __PL330_CORE_H
-
-#define PL330_MAX_CHAN		8
-#define PL330_MAX_IRQS		32
-#define PL330_MAX_PERI		32
-
-enum pl330_srccachectrl {
-	SCCTRL0 = 0, /* Noncacheable and nonbufferable */
-	SCCTRL1, /* Bufferable only */
-	SCCTRL2, /* Cacheable, but do not allocate */
-	SCCTRL3, /* Cacheable and bufferable, but do not allocate */
-	SINVALID1,
-	SINVALID2,
-	SCCTRL6, /* Cacheable write-through, allocate on reads only */
-	SCCTRL7, /* Cacheable write-back, allocate on reads only */
-};
-
-enum pl330_dstcachectrl {
-	DCCTRL0 = 0, /* Noncacheable and nonbufferable */
-	DCCTRL1, /* Bufferable only */
-	DCCTRL2, /* Cacheable, but do not allocate */
-	DCCTRL3, /* Cacheable and bufferable, but do not allocate */
-	DINVALID1,              /* AWCACHE = 0x1000 */
-	DINVALID2,
-	DCCTRL6, /* Cacheable write-through, allocate on writes only */
-	DCCTRL7, /* Cacheable write-back, allocate on writes only */
-};
-
-/* Populated by the PL330 core driver for DMA API driver's info */
-struct pl330_config {
-	u32	periph_id;
-	u32	pcell_id;
-#define DMAC_MODE_NS	(1 << 0)
-	unsigned int	mode;
-	unsigned int	data_bus_width:10; /* In number of bits */
-	unsigned int	data_buf_dep:10;
-	unsigned int	num_chan:4;
-	unsigned int	num_peri:6;
-	u32		peri_ns;
-	unsigned int	num_events:6;
-	u32		irq_ns;
-};
-
-/* Handle to the DMAC provided to the PL330 core */
-struct pl330_info {
-	/* Owning device */
-	struct device *dev;
-	/* Size of MicroCode buffers for each channel. */
-	unsigned mcbufsz;
-	/* ioremap'ed address of PL330 registers. */
-	void __iomem	*base;
-	/* Client can freely use it. */
-	void	*client_data;
-	/* PL330 core data, Client must not touch it. */
-	void	*pl330_data;
-	/* Populated by the PL330 core driver during pl330_add */
-	struct pl330_config	pcfg;
-	/*
-	 * If the DMAC has some reset mechanism, then the
-	 * client may want to provide pointer to the method.
-	 */
-	void (*dmac_reset)(struct pl330_info *pi);
-};
-
-enum pl330_byteswap {
-	SWAP_NO = 0,
-	SWAP_2,
-	SWAP_4,
-	SWAP_8,
-	SWAP_16,
-};
-
-/**
- * Request Configuration.
- * The PL330 core does not modify this and uses the last
- * working configuration if the request doesn't provide any.
- *
- * The Client may want to provide this info only for the
- * first request and a request with new settings.
- */
-struct pl330_reqcfg {
-	/* Address Incrementing */
-	unsigned dst_inc:1;
-	unsigned src_inc:1;
-
-	/*
-	 * For now, the SRC & DST protection levels
-	 * and burst size/length are assumed same.
-	 */
-	bool nonsecure;
-	bool privileged;
-	bool insnaccess;
-	unsigned brst_len:5;
-	unsigned brst_size:3; /* in power of 2 */
-
-	enum pl330_dstcachectrl dcctl;
-	enum pl330_srccachectrl scctl;
-	enum pl330_byteswap swap;
-};
-
-/*
- * One cycle of DMAC operation.
- * There may be more than one xfer in a request.
- */
-struct pl330_xfer {
-	u32 src_addr;
-	u32 dst_addr;
-	/* Size to xfer */
-	u32 bytes;
-	/*
-	 * Pointer to next xfer in the list.
-	 * The last xfer in the req must point to NULL.
-	 */
-	struct pl330_xfer *next;
-};
-
-/* The xfer callbacks are made with one of these arguments. */
-enum pl330_op_err {
-	/* The all xfers in the request were success. */
-	PL330_ERR_NONE,
-	/* If req aborted due to global error. */
-	PL330_ERR_ABORT,
-	/* If req failed due to problem with Channel. */
-	PL330_ERR_FAIL,
-};
-
-enum pl330_reqtype {
-	MEMTOMEM,
-	MEMTODEV,
-	DEVTOMEM,
-	DEVTODEV,
-};
-
-/* A request defining Scatter-Gather List ending with NULL xfer. */
-struct pl330_req {
-	enum pl330_reqtype rqtype;
-	/* Index of peripheral for the xfer. */
-	unsigned peri:5;
-	/* Unique token for this xfer, set by the client. */
-	void *token;
-	/* Callback to be called after xfer. */
-	void (*xfer_cb)(void *token, enum pl330_op_err err);
-	/* If NULL, req will be done at last set parameters. */
-	struct pl330_reqcfg *cfg;
-	/* Pointer to first xfer in the request. */
-	struct pl330_xfer *x;
-};
-
-/*
- * To know the status of the channel and DMAC, the client
- * provides a pointer to this structure. The PL330 core
- * fills it with current information.
- */
-struct pl330_chanstatus {
-	/*
-	 * If the DMAC engine halted due to some error,
-	 * the client should remove-add DMAC.
-	 */
-	bool dmac_halted;
-	/*
-	 * If channel is halted due to some error,
-	 * the client should ABORT/FLUSH and START the channel.
-	 */
-	bool faulting;
-	/* Location of last load */
-	u32 src_addr;
-	/* Location of last store */
-	u32 dst_addr;
-	/*
-	 * Pointer to the currently active req, NULL if channel is
-	 * inactive, even though the requests may be present.
-	 */
-	struct pl330_req *top_req;
-	/* Pointer to req waiting second in the queue if any. */
-	struct pl330_req *wait_req;
-};
-
-enum pl330_chan_op {
-	/* Start the channel */
-	PL330_OP_START,
-	/* Abort the active xfer */
-	PL330_OP_ABORT,
-	/* Stop xfer and flush queue */
-	PL330_OP_FLUSH,
-};
-
-extern int pl330_add(struct pl330_info *);
-extern void pl330_del(struct pl330_info *pi);
-extern int pl330_update(const struct pl330_info *pi);
-extern void pl330_release_channel(void *ch_id);
-extern void *pl330_request_channel(const struct pl330_info *pi);
-extern int pl330_chan_status(void *ch_id, struct pl330_chanstatus *pstatus);
-extern int pl330_chan_ctrl(void *ch_id, enum pl330_chan_op op);
-extern int pl330_submit_req(void *ch_id, struct pl330_req *r);
-
-#endif	/* __PL330_CORE_H */
diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h
index bae7eb6..df0ac0b 100644
--- a/arch/arm/include/asm/io.h
+++ b/arch/arm/include/asm/io.h
@@ -82,6 +82,11 @@
 extern void __iomem *__arm_ioremap(unsigned long, size_t, unsigned int);
 extern void __iomem *__arm_ioremap_exec(unsigned long, size_t, bool cached);
 extern void __iounmap(volatile void __iomem *addr);
+extern void __arm_iounmap(volatile void __iomem *addr);
+
+extern void __iomem * (*arch_ioremap_caller)(unsigned long, size_t,
+	unsigned int, void *);
+extern void (*arch_iounmap)(volatile void __iomem *);
 
 /*
  * Bad read/write accesses...
@@ -96,6 +101,8 @@
 	return (void __iomem *)addr;
 }
 
+#define IOMEM(x)	((void __force __iomem *)(x))
+
 /* IO barriers */
 #ifdef CONFIG_ARM_DMA_MEM_BUFFERABLE
 #include <asm/barrier.h>
@@ -109,7 +116,11 @@
 /*
  * Now, pick up the machine-defined IO definitions
  */
+#ifdef CONFIG_NEED_MACH_IO_H
 #include <mach/io.h>
+#else
+#define __io(a)		({ (void)(a); __typesafe_io(0); })
+#endif
 
 /*
  * This is the limit of PC card/PCI/ISA IO space, which is by default
@@ -211,18 +222,18 @@
  * Again, this are defined to perform little endian accesses.  See the
  * IO port primitives for more information.
  */
-#ifdef __mem_pci
-#define readb_relaxed(c) ({ u8  __r = __raw_readb(__mem_pci(c)); __r; })
+#ifndef readl
+#define readb_relaxed(c) ({ u8  __r = __raw_readb(c); __r; })
 #define readw_relaxed(c) ({ u16 __r = le16_to_cpu((__force __le16) \
-					__raw_readw(__mem_pci(c))); __r; })
+					__raw_readw(c)); __r; })
 #define readl_relaxed(c) ({ u32 __r = le32_to_cpu((__force __le32) \
-					__raw_readl(__mem_pci(c))); __r; })
+					__raw_readl(c)); __r; })
 
-#define writeb_relaxed(v,c)	((void)__raw_writeb(v,__mem_pci(c)))
+#define writeb_relaxed(v,c)	((void)__raw_writeb(v,c))
 #define writew_relaxed(v,c)	((void)__raw_writew((__force u16) \
-					cpu_to_le16(v),__mem_pci(c)))
+					cpu_to_le16(v),c))
 #define writel_relaxed(v,c)	((void)__raw_writel((__force u32) \
-					cpu_to_le32(v),__mem_pci(c)))
+					cpu_to_le32(v),c))
 
 #define readb(c)		({ u8  __v = readb_relaxed(c); __iormb(); __v; })
 #define readw(c)		({ u16 __v = readw_relaxed(c); __iormb(); __v; })
@@ -232,30 +243,19 @@
 #define writew(v,c)		({ __iowmb(); writew_relaxed(v,c); })
 #define writel(v,c)		({ __iowmb(); writel_relaxed(v,c); })
 
-#define readsb(p,d,l)		__raw_readsb(__mem_pci(p),d,l)
-#define readsw(p,d,l)		__raw_readsw(__mem_pci(p),d,l)
-#define readsl(p,d,l)		__raw_readsl(__mem_pci(p),d,l)
+#define readsb(p,d,l)		__raw_readsb(p,d,l)
+#define readsw(p,d,l)		__raw_readsw(p,d,l)
+#define readsl(p,d,l)		__raw_readsl(p,d,l)
 
-#define writesb(p,d,l)		__raw_writesb(__mem_pci(p),d,l)
-#define writesw(p,d,l)		__raw_writesw(__mem_pci(p),d,l)
-#define writesl(p,d,l)		__raw_writesl(__mem_pci(p),d,l)
+#define writesb(p,d,l)		__raw_writesb(p,d,l)
+#define writesw(p,d,l)		__raw_writesw(p,d,l)
+#define writesl(p,d,l)		__raw_writesl(p,d,l)
 
-#define memset_io(c,v,l)	_memset_io(__mem_pci(c),(v),(l))
-#define memcpy_fromio(a,c,l)	_memcpy_fromio((a),__mem_pci(c),(l))
-#define memcpy_toio(c,a,l)	_memcpy_toio(__mem_pci(c),(a),(l))
+#define memset_io(c,v,l)	_memset_io(c,(v),(l))
+#define memcpy_fromio(a,c,l)	_memcpy_fromio((a),c,(l))
+#define memcpy_toio(c,a,l)	_memcpy_toio(c,(a),(l))
 
-#elif !defined(readb)
-
-#define readb(c)			(__readwrite_bug("readb"),0)
-#define readw(c)			(__readwrite_bug("readw"),0)
-#define readl(c)			(__readwrite_bug("readl"),0)
-#define writeb(v,c)			__readwrite_bug("writeb")
-#define writew(v,c)			__readwrite_bug("writew")
-#define writel(v,c)			__readwrite_bug("writel")
-
-#define check_signature(io,sig,len)	(0)
-
-#endif	/* __mem_pci */
+#endif	/* readl */
 
 /*
  * ioremap and friends.
@@ -264,16 +264,11 @@
  * Documentation/io-mapping.txt.
  *
  */
-#ifndef __arch_ioremap
-#define __arch_ioremap			__arm_ioremap
-#define __arch_iounmap			__iounmap
-#endif
-
-#define ioremap(cookie,size)		__arch_ioremap((cookie), (size), MT_DEVICE)
-#define ioremap_nocache(cookie,size)	__arch_ioremap((cookie), (size), MT_DEVICE)
-#define ioremap_cached(cookie,size)	__arch_ioremap((cookie), (size), MT_DEVICE_CACHED)
-#define ioremap_wc(cookie,size)		__arch_ioremap((cookie), (size), MT_DEVICE_WC)
-#define iounmap				__arch_iounmap
+#define ioremap(cookie,size)		__arm_ioremap((cookie), (size), MT_DEVICE)
+#define ioremap_nocache(cookie,size)	__arm_ioremap((cookie), (size), MT_DEVICE)
+#define ioremap_cached(cookie,size)	__arm_ioremap((cookie), (size), MT_DEVICE_CACHED)
+#define ioremap_wc(cookie,size)		__arm_ioremap((cookie), (size), MT_DEVICE_WC)
+#define iounmap				__arm_iounmap
 
 /*
  * io{read,write}{8,16,32} macros
diff --git a/arch/arm/include/asm/irq.h b/arch/arm/include/asm/irq.h
index 5a526af..35c21c3 100644
--- a/arch/arm/include/asm/irq.h
+++ b/arch/arm/include/asm/irq.h
@@ -1,14 +1,18 @@
 #ifndef __ASM_ARM_IRQ_H
 #define __ASM_ARM_IRQ_H
 
+#define NR_IRQS_LEGACY	16
+
+#ifndef CONFIG_SPARSE_IRQ
 #include <mach/irqs.h>
+#else
+#define NR_IRQS NR_IRQS_LEGACY
+#endif
 
 #ifndef irq_canonicalize
 #define irq_canonicalize(i)	(i)
 #endif
 
-#define NR_IRQS_LEGACY	16
-
 /*
  * Use this value to indicate lack of interrupt
  * capability
diff --git a/arch/arm/include/asm/jump_label.h b/arch/arm/include/asm/jump_label.h
new file mode 100644
index 0000000..5c5ca2e
--- /dev/null
+++ b/arch/arm/include/asm/jump_label.h
@@ -0,0 +1,41 @@
+#ifndef _ASM_ARM_JUMP_LABEL_H
+#define _ASM_ARM_JUMP_LABEL_H
+
+#ifdef __KERNEL__
+
+#include <linux/types.h>
+#include <asm/system.h>
+
+#define JUMP_LABEL_NOP_SIZE 4
+
+#ifdef CONFIG_THUMB2_KERNEL
+#define JUMP_LABEL_NOP	"nop.w"
+#else
+#define JUMP_LABEL_NOP	"nop"
+#endif
+
+static __always_inline bool arch_static_branch(struct jump_label_key *key)
+{
+	asm goto("1:\n\t"
+		 JUMP_LABEL_NOP "\n\t"
+		 ".pushsection __jump_table,  \"aw\"\n\t"
+		 ".word 1b, %l[l_yes], %c0\n\t"
+		 ".popsection\n\t"
+		 : :  "i" (key) :  : l_yes);
+
+	return false;
+l_yes:
+	return true;
+}
+
+#endif /* __KERNEL__ */
+
+typedef u32 jump_label_t;
+
+struct jump_entry {
+	jump_label_t code;
+	jump_label_t target;
+	jump_label_t key;
+};
+
+#endif
diff --git a/arch/arm/include/asm/mc146818rtc.h b/arch/arm/include/asm/mc146818rtc.h
index 6b884d2..e8567bb 100644
--- a/arch/arm/include/asm/mc146818rtc.h
+++ b/arch/arm/include/asm/mc146818rtc.h
@@ -5,7 +5,9 @@
 #define _ASM_MC146818RTC_H
 
 #include <linux/io.h>
-#include <mach/irqs.h>
+#include <linux/kernel.h>
+
+#define RTC_IRQ BUILD_BUG_ON(1)
 
 #ifndef RTC_PORT
 #define RTC_PORT(x)	(0x70 + (x))
diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index a8997d7..fcb5757 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -116,6 +116,8 @@
 #define MODULES_END		(END_MEM)
 #define MODULES_VADDR		(PHYS_OFFSET)
 
+#define XIP_VIRT_ADDR(physaddr)  (physaddr)
+
 #endif /* !CONFIG_MMU */
 
 /*
diff --git a/arch/arm/include/asm/mmu_context.h b/arch/arm/include/asm/mmu_context.h
index 71605d9..a0b3cac 100644
--- a/arch/arm/include/asm/mmu_context.h
+++ b/arch/arm/include/asm/mmu_context.h
@@ -18,6 +18,7 @@
 #include <asm/cacheflush.h>
 #include <asm/cachetype.h>
 #include <asm/proc-fns.h>
+#include <asm-generic/mm_hooks.h>
 
 void __check_kvm_seq(struct mm_struct *mm);
 
@@ -133,32 +134,4 @@
 #define deactivate_mm(tsk,mm)	do { } while (0)
 #define activate_mm(prev,next)	switch_mm(prev, next, NULL)
 
-/*
- * We are inserting a "fake" vma for the user-accessible vector page so
- * gdb and friends can get to it through ptrace and /proc/<pid>/mem.
- * But we also want to remove it before the generic code gets to see it
- * during process exit or the unmapping of it would  cause total havoc.
- * (the macro is used as remove_vma() is static to mm/mmap.c)
- */
-#define arch_exit_mmap(mm) \
-do { \
-	struct vm_area_struct *high_vma = find_vma(mm, 0xffff0000); \
-	if (high_vma) { \
-		BUG_ON(high_vma->vm_next);  /* it should be last */ \
-		if (high_vma->vm_prev) \
-			high_vma->vm_prev->vm_next = NULL; \
-		else \
-			mm->mmap = NULL; \
-		rb_erase(&high_vma->vm_rb, &mm->mm_rb); \
-		mm->mmap_cache = NULL; \
-		mm->map_count--; \
-		remove_vma(high_vma); \
-	} \
-} while (0)
-
-static inline void arch_dup_mmap(struct mm_struct *oldmm,
-				 struct mm_struct *mm)
-{
-}
-
 #endif
diff --git a/arch/arm/include/asm/opcodes.h b/arch/arm/include/asm/opcodes.h
index c0efdd6..19c48de 100644
--- a/arch/arm/include/asm/opcodes.h
+++ b/arch/arm/include/asm/opcodes.h
@@ -17,4 +17,63 @@
 #define ARM_OPCODE_CONDTEST_PASS   1
 #define ARM_OPCODE_CONDTEST_UNCOND 2
 
+
+/*
+ * Opcode byteswap helpers
+ *
+ * These macros help with converting instructions between a canonical integer
+ * format and in-memory representation, in an endianness-agnostic manner.
+ *
+ * __mem_to_opcode_*() convert from in-memory representation to canonical form.
+ * __opcode_to_mem_*() convert from canonical form to in-memory representation.
+ *
+ *
+ * Canonical instruction representation:
+ *
+ *	ARM:		0xKKLLMMNN
+ *	Thumb 16-bit:	0x0000KKLL, where KK < 0xE8
+ *	Thumb 32-bit:	0xKKLLMMNN, where KK >= 0xE8
+ *
+ * There is no way to distinguish an ARM instruction in canonical representation
+ * from a Thumb instruction (just as these cannot be distinguished in memory).
+ * Where this distinction is important, it needs to be tracked separately.
+ *
+ * Note that values in the range 0x0000E800..0xE7FFFFFF intentionally do not
+ * represent any valid Thumb-2 instruction.  For this range,
+ * __opcode_is_thumb32() and __opcode_is_thumb16() will both be false.
+ */
+
+#ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+#include <linux/swab.h>
+
+#ifdef CONFIG_CPU_ENDIAN_BE8
+#define __opcode_to_mem_arm(x) swab32(x)
+#define __opcode_to_mem_thumb16(x) swab16(x)
+#define __opcode_to_mem_thumb32(x) swahb32(x)
+#else
+#define __opcode_to_mem_arm(x) ((u32)(x))
+#define __opcode_to_mem_thumb16(x) ((u16)(x))
+#define __opcode_to_mem_thumb32(x) swahw32(x)
+#endif
+
+#define __mem_to_opcode_arm(x) __opcode_to_mem_arm(x)
+#define __mem_to_opcode_thumb16(x) __opcode_to_mem_thumb16(x)
+#define __mem_to_opcode_thumb32(x) __opcode_to_mem_thumb32(x)
+
+/* Operations specific to Thumb opcodes */
+
+/* Instruction size checks: */
+#define __opcode_is_thumb32(x) ((u32)(x) >= 0xE8000000UL)
+#define __opcode_is_thumb16(x) ((u32)(x) < 0xE800UL)
+
+/* Operations to construct or split 32-bit Thumb instructions: */
+#define __opcode_thumb32_first(x) ((u16)((x) >> 16))
+#define __opcode_thumb32_second(x) ((u16)(x))
+#define __opcode_thumb32_compose(first, second) \
+	(((u32)(u16)(first) << 16) | (u32)(u16)(second))
+
+#endif /* __ASSEMBLY__ */
+
 #endif /* __ASM_ARM_OPCODES_H */
diff --git a/arch/arm/include/asm/page.h b/arch/arm/include/asm/page.h
index 97b440c..5838361 100644
--- a/arch/arm/include/asm/page.h
+++ b/arch/arm/include/asm/page.h
@@ -151,6 +151,8 @@
 #define clear_page(page)	memset((void *)(page), 0, PAGE_SIZE)
 extern void copy_page(void *to, const void *from);
 
+#define __HAVE_ARCH_GATE_AREA 1
+
 #ifdef CONFIG_ARM_LPAE
 #include <asm/pgtable-3level-types.h>
 #else
diff --git a/arch/arm/include/asm/perf_event.h b/arch/arm/include/asm/perf_event.h
index 7523340a..00cbe10 100644
--- a/arch/arm/include/asm/perf_event.h
+++ b/arch/arm/include/asm/perf_event.h
@@ -22,6 +22,7 @@
 	ARM_PERF_PMU_ID_CA9,
 	ARM_PERF_PMU_ID_CA5,
 	ARM_PERF_PMU_ID_CA15,
+	ARM_PERF_PMU_ID_CA7,
 	ARM_NUM_PMU_IDS,
 };
 
diff --git a/arch/arm/include/asm/posix_types.h b/arch/arm/include/asm/posix_types.h
index 2446d23..efdf990 100644
--- a/arch/arm/include/asm/posix_types.h
+++ b/arch/arm/include/asm/posix_types.h
@@ -19,59 +19,22 @@
  * assume GCC is being used.
  */
 
-typedef unsigned long		__kernel_ino_t;
 typedef unsigned short		__kernel_mode_t;
+#define __kernel_mode_t __kernel_mode_t
+
 typedef unsigned short		__kernel_nlink_t;
-typedef long			__kernel_off_t;
-typedef int			__kernel_pid_t;
+#define __kernel_nlink_t __kernel_nlink_t
+
 typedef unsigned short		__kernel_ipc_pid_t;
+#define __kernel_ipc_pid_t __kernel_ipc_pid_t
+
 typedef unsigned short		__kernel_uid_t;
 typedef unsigned short		__kernel_gid_t;
-typedef unsigned int		__kernel_size_t;
-typedef int			__kernel_ssize_t;
-typedef int			__kernel_ptrdiff_t;
-typedef long			__kernel_time_t;
-typedef long			__kernel_suseconds_t;
-typedef long			__kernel_clock_t;
-typedef int			__kernel_timer_t;
-typedef int			__kernel_clockid_t;
-typedef int			__kernel_daddr_t;
-typedef char *			__kernel_caddr_t;
-typedef unsigned short		__kernel_uid16_t;
-typedef unsigned short		__kernel_gid16_t;
-typedef unsigned int		__kernel_uid32_t;
-typedef unsigned int		__kernel_gid32_t;
+#define __kernel_uid_t __kernel_uid_t
 
-typedef unsigned short		__kernel_old_uid_t;
-typedef unsigned short		__kernel_old_gid_t;
 typedef unsigned short		__kernel_old_dev_t;
+#define __kernel_old_dev_t __kernel_old_dev_t
 
-#ifdef __GNUC__
-typedef long long		__kernel_loff_t;
-#endif
-
-typedef struct {
-	int	val[2];
-} __kernel_fsid_t;
-
-#if defined(__KERNEL__)
-
-#undef	__FD_SET
-#define __FD_SET(fd, fdsetp) \
-		(((fd_set *)(fdsetp))->fds_bits[(fd) >> 5] |= (1<<((fd) & 31)))
-
-#undef	__FD_CLR
-#define __FD_CLR(fd, fdsetp) \
-		(((fd_set *)(fdsetp))->fds_bits[(fd) >> 5] &= ~(1<<((fd) & 31)))
-
-#undef	__FD_ISSET
-#define __FD_ISSET(fd, fdsetp) \
-		((((fd_set *)(fdsetp))->fds_bits[(fd) >> 5] & (1<<((fd) & 31))) != 0)
-
-#undef	__FD_ZERO
-#define __FD_ZERO(fdsetp) \
-		(memset (fdsetp, 0, sizeof (*(fd_set *)(fdsetp))))
-
-#endif
+#include <asm-generic/posix_types.h>
 
 #endif
diff --git a/arch/arm/include/asm/processor.h b/arch/arm/include/asm/processor.h
index f4d7f56..5ac8d3d 100644
--- a/arch/arm/include/asm/processor.h
+++ b/arch/arm/include/asm/processor.h
@@ -55,7 +55,6 @@
 #define start_thread(regs,pc,sp)					\
 ({									\
 	unsigned long *stack = (unsigned long *)sp;			\
-	set_fs(USER_DS);						\
 	memset(regs->uregs, 0, sizeof(regs->uregs));			\
 	if (current->personality & ADDR_LIMIT_32BIT)			\
 		regs->ARM_cpsr = USR_MODE;				\
diff --git a/arch/arm/include/asm/prom.h b/arch/arm/include/asm/prom.h
index ee03633..aeae9c6 100644
--- a/arch/arm/include/asm/prom.h
+++ b/arch/arm/include/asm/prom.h
@@ -13,8 +13,6 @@
 
 #ifdef CONFIG_OF
 
-#include <asm/irq.h>
-
 extern struct machine_desc *setup_machine_fdt(unsigned int dt_phys);
 extern void arm_dt_memblock_reserve(void);
 
diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h
index 02b2f82..85fe61e 100644
--- a/arch/arm/include/asm/tlbflush.h
+++ b/arch/arm/include/asm/tlbflush.h
@@ -318,6 +318,21 @@
 
 #define tlb_flag(f)	((always_tlb_flags & (f)) || (__tlb_flag & possible_tlb_flags & (f)))
 
+#define __tlb_op(f, insnarg, arg)					\
+	do {								\
+		if (always_tlb_flags & (f))				\
+			asm("mcr " insnarg				\
+			    : : "r" (arg) : "cc");			\
+		else if (possible_tlb_flags & (f))			\
+			asm("tst %1, %2\n\t"				\
+			    "mcrne " insnarg				\
+			    : : "r" (arg), "r" (__tlb_flag), "Ir" (f)	\
+			    : "cc");					\
+	} while (0)
+
+#define tlb_op(f, regs, arg)	__tlb_op(f, "p15, 0, %0, " regs, arg)
+#define tlb_l2_op(f, regs, arg)	__tlb_op(f, "p15, 1, %0, " regs, arg)
+
 static inline void local_flush_tlb_all(void)
 {
 	const int zero = 0;
@@ -326,16 +341,11 @@
 	if (tlb_flag(TLB_WB))
 		dsb();
 
-	if (tlb_flag(TLB_V3_FULL))
-		asm("mcr p15, 0, %0, c6, c0, 0" : : "r" (zero) : "cc");
-	if (tlb_flag(TLB_V4_U_FULL | TLB_V6_U_FULL))
-		asm("mcr p15, 0, %0, c8, c7, 0" : : "r" (zero) : "cc");
-	if (tlb_flag(TLB_V4_D_FULL | TLB_V6_D_FULL))
-		asm("mcr p15, 0, %0, c8, c6, 0" : : "r" (zero) : "cc");
-	if (tlb_flag(TLB_V4_I_FULL | TLB_V6_I_FULL))
-		asm("mcr p15, 0, %0, c8, c5, 0" : : "r" (zero) : "cc");
-	if (tlb_flag(TLB_V7_UIS_FULL))
-		asm("mcr p15, 0, %0, c8, c3, 0" : : "r" (zero) : "cc");
+	tlb_op(TLB_V3_FULL, "c6, c0, 0", zero);
+	tlb_op(TLB_V4_U_FULL | TLB_V6_U_FULL, "c8, c7, 0", zero);
+	tlb_op(TLB_V4_D_FULL | TLB_V6_D_FULL, "c8, c6, 0", zero);
+	tlb_op(TLB_V4_I_FULL | TLB_V6_I_FULL, "c8, c5, 0", zero);
+	tlb_op(TLB_V7_UIS_FULL, "c8, c3, 0", zero);
 
 	if (tlb_flag(TLB_BARRIER)) {
 		dsb();
@@ -352,29 +362,23 @@
 	if (tlb_flag(TLB_WB))
 		dsb();
 
-	if (cpumask_test_cpu(get_cpu(), mm_cpumask(mm))) {
-		if (tlb_flag(TLB_V3_FULL))
-			asm("mcr p15, 0, %0, c6, c0, 0" : : "r" (zero) : "cc");
-		if (tlb_flag(TLB_V4_U_FULL))
-			asm("mcr p15, 0, %0, c8, c7, 0" : : "r" (zero) : "cc");
-		if (tlb_flag(TLB_V4_D_FULL))
-			asm("mcr p15, 0, %0, c8, c6, 0" : : "r" (zero) : "cc");
-		if (tlb_flag(TLB_V4_I_FULL))
-			asm("mcr p15, 0, %0, c8, c5, 0" : : "r" (zero) : "cc");
+	if (possible_tlb_flags & (TLB_V3_FULL|TLB_V4_U_FULL|TLB_V4_D_FULL|TLB_V4_I_FULL)) {
+		if (cpumask_test_cpu(get_cpu(), mm_cpumask(mm))) {
+			tlb_op(TLB_V3_FULL, "c6, c0, 0", zero);
+			tlb_op(TLB_V4_U_FULL, "c8, c7, 0", zero);
+			tlb_op(TLB_V4_D_FULL, "c8, c6, 0", zero);
+			tlb_op(TLB_V4_I_FULL, "c8, c5, 0", zero);
+		}
+		put_cpu();
 	}
-	put_cpu();
 
-	if (tlb_flag(TLB_V6_U_ASID))
-		asm("mcr p15, 0, %0, c8, c7, 2" : : "r" (asid) : "cc");
-	if (tlb_flag(TLB_V6_D_ASID))
-		asm("mcr p15, 0, %0, c8, c6, 2" : : "r" (asid) : "cc");
-	if (tlb_flag(TLB_V6_I_ASID))
-		asm("mcr p15, 0, %0, c8, c5, 2" : : "r" (asid) : "cc");
-	if (tlb_flag(TLB_V7_UIS_ASID))
+	tlb_op(TLB_V6_U_ASID, "c8, c7, 2", asid);
+	tlb_op(TLB_V6_D_ASID, "c8, c6, 2", asid);
+	tlb_op(TLB_V6_I_ASID, "c8, c5, 2", asid);
 #ifdef CONFIG_ARM_ERRATA_720789
-		asm("mcr p15, 0, %0, c8, c3, 0" : : "r" (zero) : "cc");
+	tlb_op(TLB_V7_UIS_ASID, "c8, c3, 0", zero);
 #else
-		asm("mcr p15, 0, %0, c8, c3, 2" : : "r" (asid) : "cc");
+	tlb_op(TLB_V7_UIS_ASID, "c8, c3, 2", asid);
 #endif
 
 	if (tlb_flag(TLB_BARRIER))
@@ -392,30 +396,23 @@
 	if (tlb_flag(TLB_WB))
 		dsb();
 
-	if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) {
-		if (tlb_flag(TLB_V3_PAGE))
-			asm("mcr p15, 0, %0, c6, c0, 0" : : "r" (uaddr) : "cc");
-		if (tlb_flag(TLB_V4_U_PAGE))
-			asm("mcr p15, 0, %0, c8, c7, 1" : : "r" (uaddr) : "cc");
-		if (tlb_flag(TLB_V4_D_PAGE))
-			asm("mcr p15, 0, %0, c8, c6, 1" : : "r" (uaddr) : "cc");
-		if (tlb_flag(TLB_V4_I_PAGE))
-			asm("mcr p15, 0, %0, c8, c5, 1" : : "r" (uaddr) : "cc");
+	if (possible_tlb_flags & (TLB_V3_PAGE|TLB_V4_U_PAGE|TLB_V4_D_PAGE|TLB_V4_I_PAGE|TLB_V4_I_FULL) &&
+	    cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) {
+		tlb_op(TLB_V3_PAGE, "c6, c0, 0", uaddr);
+		tlb_op(TLB_V4_U_PAGE, "c8, c7, 1", uaddr);
+		tlb_op(TLB_V4_D_PAGE, "c8, c6, 1", uaddr);
+		tlb_op(TLB_V4_I_PAGE, "c8, c5, 1", uaddr);
 		if (!tlb_flag(TLB_V4_I_PAGE) && tlb_flag(TLB_V4_I_FULL))
 			asm("mcr p15, 0, %0, c8, c5, 0" : : "r" (zero) : "cc");
 	}
 
-	if (tlb_flag(TLB_V6_U_PAGE))
-		asm("mcr p15, 0, %0, c8, c7, 1" : : "r" (uaddr) : "cc");
-	if (tlb_flag(TLB_V6_D_PAGE))
-		asm("mcr p15, 0, %0, c8, c6, 1" : : "r" (uaddr) : "cc");
-	if (tlb_flag(TLB_V6_I_PAGE))
-		asm("mcr p15, 0, %0, c8, c5, 1" : : "r" (uaddr) : "cc");
-	if (tlb_flag(TLB_V7_UIS_PAGE))
+	tlb_op(TLB_V6_U_PAGE, "c8, c7, 1", uaddr);
+	tlb_op(TLB_V6_D_PAGE, "c8, c6, 1", uaddr);
+	tlb_op(TLB_V6_I_PAGE, "c8, c5, 1", uaddr);
 #ifdef CONFIG_ARM_ERRATA_720789
-		asm("mcr p15, 0, %0, c8, c3, 3" : : "r" (uaddr & PAGE_MASK) : "cc");
+	tlb_op(TLB_V7_UIS_PAGE, "c8, c3, 3", uaddr & PAGE_MASK);
 #else
-		asm("mcr p15, 0, %0, c8, c3, 1" : : "r" (uaddr) : "cc");
+	tlb_op(TLB_V7_UIS_PAGE, "c8, c3, 1", uaddr);
 #endif
 
 	if (tlb_flag(TLB_BARRIER))
@@ -432,25 +429,17 @@
 	if (tlb_flag(TLB_WB))
 		dsb();
 
-	if (tlb_flag(TLB_V3_PAGE))
-		asm("mcr p15, 0, %0, c6, c0, 0" : : "r" (kaddr) : "cc");
-	if (tlb_flag(TLB_V4_U_PAGE))
-		asm("mcr p15, 0, %0, c8, c7, 1" : : "r" (kaddr) : "cc");
-	if (tlb_flag(TLB_V4_D_PAGE))
-		asm("mcr p15, 0, %0, c8, c6, 1" : : "r" (kaddr) : "cc");
-	if (tlb_flag(TLB_V4_I_PAGE))
-		asm("mcr p15, 0, %0, c8, c5, 1" : : "r" (kaddr) : "cc");
+	tlb_op(TLB_V3_PAGE, "c6, c0, 0", kaddr);
+	tlb_op(TLB_V4_U_PAGE, "c8, c7, 1", kaddr);
+	tlb_op(TLB_V4_D_PAGE, "c8, c6, 1", kaddr);
+	tlb_op(TLB_V4_I_PAGE, "c8, c5, 1", kaddr);
 	if (!tlb_flag(TLB_V4_I_PAGE) && tlb_flag(TLB_V4_I_FULL))
 		asm("mcr p15, 0, %0, c8, c5, 0" : : "r" (zero) : "cc");
 
-	if (tlb_flag(TLB_V6_U_PAGE))
-		asm("mcr p15, 0, %0, c8, c7, 1" : : "r" (kaddr) : "cc");
-	if (tlb_flag(TLB_V6_D_PAGE))
-		asm("mcr p15, 0, %0, c8, c6, 1" : : "r" (kaddr) : "cc");
-	if (tlb_flag(TLB_V6_I_PAGE))
-		asm("mcr p15, 0, %0, c8, c5, 1" : : "r" (kaddr) : "cc");
-	if (tlb_flag(TLB_V7_UIS_PAGE))
-		asm("mcr p15, 0, %0, c8, c3, 1" : : "r" (kaddr) : "cc");
+	tlb_op(TLB_V6_U_PAGE, "c8, c7, 1", kaddr);
+	tlb_op(TLB_V6_D_PAGE, "c8, c6, 1", kaddr);
+	tlb_op(TLB_V6_I_PAGE, "c8, c5, 1", kaddr);
+	tlb_op(TLB_V7_UIS_PAGE, "c8, c3, 1", kaddr);
 
 	if (tlb_flag(TLB_BARRIER)) {
 		dsb();
@@ -475,13 +464,8 @@
 {
 	const unsigned int __tlb_flag = __cpu_tlb_flags;
 
-	if (tlb_flag(TLB_DCLEAN))
-		asm("mcr	p15, 0, %0, c7, c10, 1	@ flush_pmd"
-			: : "r" (pmd) : "cc");
-
-	if (tlb_flag(TLB_L2CLEAN_FR))
-		asm("mcr	p15, 1, %0, c15, c9, 1  @ L2 flush_pmd"
-			: : "r" (pmd) : "cc");
+	tlb_op(TLB_DCLEAN, "c7, c10, 1	@ flush_pmd", pmd);
+	tlb_l2_op(TLB_L2CLEAN_FR, "c15, c9, 1  @ L2 flush_pmd", pmd);
 
 	if (tlb_flag(TLB_WB))
 		dsb();
@@ -491,15 +475,11 @@
 {
 	const unsigned int __tlb_flag = __cpu_tlb_flags;
 
-	if (tlb_flag(TLB_DCLEAN))
-		asm("mcr	p15, 0, %0, c7, c10, 1	@ flush_pmd"
-			: : "r" (pmd) : "cc");
-
-	if (tlb_flag(TLB_L2CLEAN_FR))
-		asm("mcr	p15, 1, %0, c15, c9, 1  @ L2 flush_pmd"
-			: : "r" (pmd) : "cc");
+	tlb_op(TLB_DCLEAN, "c7, c10, 1	@ flush_pmd", pmd);
+	tlb_l2_op(TLB_L2CLEAN_FR, "c15, c9, 1  @ L2 flush_pmd", pmd);
 }
 
+#undef tlb_op
 #undef tlb_flag
 #undef always_tlb_flags
 #undef possible_tlb_flags
diff --git a/arch/arm/include/asm/traps.h b/arch/arm/include/asm/traps.h
index 5b29a66..f555bb3 100644
--- a/arch/arm/include/asm/traps.h
+++ b/arch/arm/include/asm/traps.h
@@ -46,7 +46,7 @@
 	return in ? : __in_irqentry_text(ptr);
 }
 
-extern void __init early_trap_init(void);
+extern void __init early_trap_init(void *);
 extern void dump_backtrace_entry(unsigned long where, unsigned long from, unsigned long frame);
 extern void ptrace_break(struct task_struct *tsk, struct pt_regs *regs);
 
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index 3a27487..8269d89 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -7,6 +7,8 @@
 
 ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_ftrace.o = -pg
+CFLAGS_REMOVE_insn.o = -pg
+CFLAGS_REMOVE_patch.o = -pg
 endif
 
 CFLAGS_REMOVE_return_address.o = -pg
@@ -14,8 +16,8 @@
 # Object file lists.
 
 obj-y		:= elf.o entry-armv.o entry-common.o irq.o opcodes.o \
-		   process.o ptrace.o return_address.o setup.o signal.o \
-		   sys_arm.o stacktrace.o time.o traps.o
+		   process.o ptrace.o return_address.o sched_clock.o \
+		   setup.o signal.o stacktrace.o sys_arm.o time.o traps.o
 
 obj-$(CONFIG_DEPRECATED_PARAM_STRUCT) += compat.o
 
@@ -29,14 +31,14 @@
 obj-$(CONFIG_ISA_DMA)		+= dma-isa.o
 obj-$(CONFIG_PCI)		+= bios32.o isa.o
 obj-$(CONFIG_ARM_CPU_SUSPEND)	+= sleep.o suspend.o
-obj-$(CONFIG_HAVE_SCHED_CLOCK)	+= sched_clock.o
 obj-$(CONFIG_SMP)		+= smp.o smp_tlb.o
 obj-$(CONFIG_HAVE_ARM_SCU)	+= smp_scu.o
 obj-$(CONFIG_HAVE_ARM_TWD)	+= smp_twd.o
-obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
-obj-$(CONFIG_FUNCTION_GRAPH_TRACER)	+= ftrace.o
+obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o insn.o
+obj-$(CONFIG_FUNCTION_GRAPH_TRACER)	+= ftrace.o insn.o
+obj-$(CONFIG_JUMP_LABEL)	+= jump_label.o insn.o patch.o
 obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o
-obj-$(CONFIG_KPROBES)		+= kprobes.o kprobes-common.o
+obj-$(CONFIG_KPROBES)		+= kprobes.o kprobes-common.o patch.o
 ifdef CONFIG_THUMB2_KERNEL
 obj-$(CONFIG_KPROBES)		+= kprobes-thumb.o
 else
diff --git a/arch/arm/kernel/debug.S b/arch/arm/kernel/debug.S
index 204e216..c45522c 100644
--- a/arch/arm/kernel/debug.S
+++ b/arch/arm/kernel/debug.S
@@ -10,6 +10,7 @@
  *  32-bit debugging code
  */
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 
 		.text
 
@@ -100,7 +101,7 @@
 
 #endif	/* CONFIG_CPU_V6 */
 
-#else
+#elif !defined(CONFIG_DEBUG_SEMIHOSTING)
 #include <mach/debug-macro.S>
 #endif	/* CONFIG_DEBUG_ICEDCC */
 
@@ -155,6 +156,8 @@
 
 		.ltorg
 
+#ifndef CONFIG_DEBUG_SEMIHOSTING
+
 ENTRY(printascii)
 		addruart_current r3, r1, r2
 		b	2f
@@ -177,3 +180,24 @@
 		mov	r0, #0
 		b	1b
 ENDPROC(printch)
+
+#else
+
+ENTRY(printascii)
+		mov	r1, r0
+		mov	r0, #0x04		@ SYS_WRITE0
+	ARM(	svc	#0x123456	)
+	THUMB(	svc	#0xab		)
+		mov	pc, lr
+ENDPROC(printascii)
+
+ENTRY(printch)
+		adr	r1, hexbuf
+		strb	r0, [r1]
+		mov	r0, #0x03		@ SYS_WRITEC
+	ARM(	svc	#0x123456	)
+	THUMB(	svc	#0xab		)
+		mov	pc, lr
+ENDPROC(printch)
+
+#endif
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 8ec5eed..7fd3ad0 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -15,6 +15,7 @@
  *  that causes it to save wrong values...  Be aware!
  */
 
+#include <asm/assembler.h>
 #include <asm/memory.h>
 #include <asm/glue-df.h>
 #include <asm/glue-pf.h>
diff --git a/arch/arm/kernel/ftrace.c b/arch/arm/kernel/ftrace.c
index c0062ad..df0bf0c 100644
--- a/arch/arm/kernel/ftrace.c
+++ b/arch/arm/kernel/ftrace.c
@@ -16,10 +16,13 @@
 #include <linux/uaccess.h>
 
 #include <asm/cacheflush.h>
+#include <asm/opcodes.h>
 #include <asm/ftrace.h>
 
+#include "insn.h"
+
 #ifdef CONFIG_THUMB2_KERNEL
-#define	NOP		0xeb04f85d	/* pop.w {lr} */
+#define	NOP		0xf85deb04	/* pop.w {lr} */
 #else
 #define	NOP		0xe8bd4000	/* pop {lr} */
 #endif
@@ -60,76 +63,31 @@
 }
 #endif
 
-#ifdef CONFIG_THUMB2_KERNEL
-static unsigned long ftrace_gen_branch(unsigned long pc, unsigned long addr,
-				       bool link)
-{
-	unsigned long s, j1, j2, i1, i2, imm10, imm11;
-	unsigned long first, second;
-	long offset;
-
-	offset = (long)addr - (long)(pc + 4);
-	if (offset < -16777216 || offset > 16777214) {
-		WARN_ON_ONCE(1);
-		return 0;
-	}
-
-	s	= (offset >> 24) & 0x1;
-	i1	= (offset >> 23) & 0x1;
-	i2	= (offset >> 22) & 0x1;
-	imm10	= (offset >> 12) & 0x3ff;
-	imm11	= (offset >>  1) & 0x7ff;
-
-	j1 = (!i1) ^ s;
-	j2 = (!i2) ^ s;
-
-	first = 0xf000 | (s << 10) | imm10;
-	second = 0x9000 | (j1 << 13) | (j2 << 11) | imm11;
-	if (link)
-		second |= 1 << 14;
-
-	return (second << 16) | first;
-}
-#else
-static unsigned long ftrace_gen_branch(unsigned long pc, unsigned long addr,
-				       bool link)
-{
-	unsigned long opcode = 0xea000000;
-	long offset;
-
-	if (link)
-		opcode |= 1 << 24;
-
-	offset = (long)addr - (long)(pc + 8);
-	if (unlikely(offset < -33554432 || offset > 33554428)) {
-		/* Can't generate branches that far (from ARM ARM). Ftrace
-		 * doesn't generate branches outside of kernel text.
-		 */
-		WARN_ON_ONCE(1);
-		return 0;
-	}
-
-	offset = (offset >> 2) & 0x00ffffff;
-
-	return opcode | offset;
-}
-#endif
-
 static unsigned long ftrace_call_replace(unsigned long pc, unsigned long addr)
 {
-	return ftrace_gen_branch(pc, addr, true);
+	return arm_gen_branch_link(pc, addr);
 }
 
 static int ftrace_modify_code(unsigned long pc, unsigned long old,
-			      unsigned long new)
+			      unsigned long new, bool validate)
 {
 	unsigned long replaced;
 
-	if (probe_kernel_read(&replaced, (void *)pc, MCOUNT_INSN_SIZE))
-		return -EFAULT;
+	if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) {
+		old = __opcode_to_mem_thumb32(old);
+		new = __opcode_to_mem_thumb32(new);
+	} else {
+		old = __opcode_to_mem_arm(old);
+		new = __opcode_to_mem_arm(new);
+	}
 
-	if (replaced != old)
-		return -EINVAL;
+	if (validate) {
+		if (probe_kernel_read(&replaced, (void *)pc, MCOUNT_INSN_SIZE))
+			return -EFAULT;
+
+		if (replaced != old)
+			return -EINVAL;
+	}
 
 	if (probe_kernel_write((void *)pc, &new, MCOUNT_INSN_SIZE))
 		return -EPERM;
@@ -141,23 +99,21 @@
 
 int ftrace_update_ftrace_func(ftrace_func_t func)
 {
-	unsigned long pc, old;
+	unsigned long pc;
 	unsigned long new;
 	int ret;
 
 	pc = (unsigned long)&ftrace_call;
-	memcpy(&old, &ftrace_call, MCOUNT_INSN_SIZE);
 	new = ftrace_call_replace(pc, (unsigned long)func);
 
-	ret = ftrace_modify_code(pc, old, new);
+	ret = ftrace_modify_code(pc, 0, new, false);
 
 #ifdef CONFIG_OLD_MCOUNT
 	if (!ret) {
 		pc = (unsigned long)&ftrace_call_old;
-		memcpy(&old, &ftrace_call_old, MCOUNT_INSN_SIZE);
 		new = ftrace_call_replace(pc, (unsigned long)func);
 
-		ret = ftrace_modify_code(pc, old, new);
+		ret = ftrace_modify_code(pc, 0, new, false);
 	}
 #endif
 
@@ -172,7 +128,7 @@
 	old = ftrace_nop_replace(rec);
 	new = ftrace_call_replace(ip, adjust_address(rec, addr));
 
-	return ftrace_modify_code(rec->ip, old, new);
+	return ftrace_modify_code(rec->ip, old, new, true);
 }
 
 int ftrace_make_nop(struct module *mod,
@@ -185,7 +141,7 @@
 
 	old = ftrace_call_replace(ip, adjust_address(rec, addr));
 	new = ftrace_nop_replace(rec);
-	ret = ftrace_modify_code(ip, old, new);
+	ret = ftrace_modify_code(ip, old, new, true);
 
 #ifdef CONFIG_OLD_MCOUNT
 	if (ret == -EINVAL && addr == MCOUNT_ADDR) {
@@ -193,7 +149,7 @@
 
 		old = ftrace_call_replace(ip, adjust_address(rec, addr));
 		new = ftrace_nop_replace(rec);
-		ret = ftrace_modify_code(ip, old, new);
+		ret = ftrace_modify_code(ip, old, new, true);
 	}
 #endif
 
@@ -249,12 +205,12 @@
 {
 	unsigned long caller_fn = (unsigned long) func;
 	unsigned long pc = (unsigned long) callsite;
-	unsigned long branch = ftrace_gen_branch(pc, caller_fn, false);
+	unsigned long branch = arm_gen_branch(pc, caller_fn);
 	unsigned long nop = 0xe1a00000;	/* mov r0, r0 */
 	unsigned long old = enable ? nop : branch;
 	unsigned long new = enable ? branch : nop;
 
-	return ftrace_modify_code(pc, old, new);
+	return ftrace_modify_code(pc, old, new, true);
 }
 
 static int ftrace_modify_graph_caller(bool enable)
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index a2e9694..3bf0c7f 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -265,7 +265,7 @@
 	str	r6, [r3]
 
 #ifdef CONFIG_DEBUG_LL
-#ifndef CONFIG_DEBUG_ICEDCC
+#if !defined(CONFIG_DEBUG_ICEDCC) && !defined(CONFIG_DEBUG_SEMIHOSTING)
 	/*
 	 * Map in IO space for serial debugging.
 	 * This allows debug messages to be output
@@ -297,10 +297,10 @@
 	cmp	r0, r6
 	blo	1b
 
-#else /* CONFIG_DEBUG_ICEDCC */
-	/* we don't need any serial debugging mappings for ICEDCC */
+#else /* CONFIG_DEBUG_ICEDCC || CONFIG_DEBUG_SEMIHOSTING */
+	/* we don't need any serial debugging mappings */
 	ldr	r7, [r10, #PROCINFO_IO_MMUFLAGS] @ io_mmuflags
-#endif /* !CONFIG_DEBUG_ICEDCC */
+#endif
 
 #if defined(CONFIG_ARCH_NETWINDER) || defined(CONFIG_ARCH_CATS)
 	/*
diff --git a/arch/arm/kernel/insn.c b/arch/arm/kernel/insn.c
new file mode 100644
index 0000000..ab312e5
--- /dev/null
+++ b/arch/arm/kernel/insn.c
@@ -0,0 +1,61 @@
+#include <linux/kernel.h>
+#include <asm/opcodes.h>
+
+static unsigned long
+__arm_gen_branch_thumb2(unsigned long pc, unsigned long addr, bool link)
+{
+	unsigned long s, j1, j2, i1, i2, imm10, imm11;
+	unsigned long first, second;
+	long offset;
+
+	offset = (long)addr - (long)(pc + 4);
+	if (offset < -16777216 || offset > 16777214) {
+		WARN_ON_ONCE(1);
+		return 0;
+	}
+
+	s	= (offset >> 24) & 0x1;
+	i1	= (offset >> 23) & 0x1;
+	i2	= (offset >> 22) & 0x1;
+	imm10	= (offset >> 12) & 0x3ff;
+	imm11	= (offset >>  1) & 0x7ff;
+
+	j1 = (!i1) ^ s;
+	j2 = (!i2) ^ s;
+
+	first = 0xf000 | (s << 10) | imm10;
+	second = 0x9000 | (j1 << 13) | (j2 << 11) | imm11;
+	if (link)
+		second |= 1 << 14;
+
+	return __opcode_thumb32_compose(first, second);
+}
+
+static unsigned long
+__arm_gen_branch_arm(unsigned long pc, unsigned long addr, bool link)
+{
+	unsigned long opcode = 0xea000000;
+	long offset;
+
+	if (link)
+		opcode |= 1 << 24;
+
+	offset = (long)addr - (long)(pc + 8);
+	if (unlikely(offset < -33554432 || offset > 33554428)) {
+		WARN_ON_ONCE(1);
+		return 0;
+	}
+
+	offset = (offset >> 2) & 0x00ffffff;
+
+	return opcode | offset;
+}
+
+unsigned long
+__arm_gen_branch(unsigned long pc, unsigned long addr, bool link)
+{
+	if (IS_ENABLED(CONFIG_THUMB2_KERNEL))
+		return __arm_gen_branch_thumb2(pc, addr, link);
+	else
+		return __arm_gen_branch_arm(pc, addr, link);
+}
diff --git a/arch/arm/kernel/insn.h b/arch/arm/kernel/insn.h
new file mode 100644
index 0000000..e96065d
--- /dev/null
+++ b/arch/arm/kernel/insn.h
@@ -0,0 +1,29 @@
+#ifndef __ASM_ARM_INSN_H
+#define __ASM_ARM_INSN_H
+
+static inline unsigned long
+arm_gen_nop(void)
+{
+#ifdef CONFIG_THUMB2_KERNEL
+	return 0xf3af8000; /* nop.w */
+#else
+	return 0xe1a00000; /* mov r0, r0 */
+#endif
+}
+
+unsigned long
+__arm_gen_branch(unsigned long pc, unsigned long addr, bool link);
+
+static inline unsigned long
+arm_gen_branch(unsigned long pc, unsigned long addr)
+{
+	return __arm_gen_branch(pc, addr, false);
+}
+
+static inline unsigned long
+arm_gen_branch_link(unsigned long pc, unsigned long addr)
+{
+	return __arm_gen_branch(pc, addr, true);
+}
+
+#endif
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index 6a6a097..71ccdbf 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -180,10 +180,7 @@
 	local_irq_save(flags);
 
 	for_each_irq_desc(i, desc) {
-		bool affinity_broken = false;
-
-		if (!desc)
-			continue;
+		bool affinity_broken;
 
 		raw_spin_lock(&desc->lock);
 		affinity_broken = migrate_one_irq(desc);
diff --git a/arch/arm/kernel/jump_label.c b/arch/arm/kernel/jump_label.c
new file mode 100644
index 0000000..4ce4f789
--- /dev/null
+++ b/arch/arm/kernel/jump_label.c
@@ -0,0 +1,39 @@
+#include <linux/kernel.h>
+#include <linux/jump_label.h>
+
+#include "insn.h"
+#include "patch.h"
+
+#ifdef HAVE_JUMP_LABEL
+
+static void __arch_jump_label_transform(struct jump_entry *entry,
+					enum jump_label_type type,
+					bool is_static)
+{
+	void *addr = (void *)entry->code;
+	unsigned int insn;
+
+	if (type == JUMP_LABEL_ENABLE)
+		insn = arm_gen_branch(entry->code, entry->target);
+	else
+		insn = arm_gen_nop();
+
+	if (is_static)
+		__patch_text(addr, insn);
+	else
+		patch_text(addr, insn);
+}
+
+void arch_jump_label_transform(struct jump_entry *entry,
+			       enum jump_label_type type)
+{
+	__arch_jump_label_transform(entry, type, false);
+}
+
+void arch_jump_label_transform_static(struct jump_entry *entry,
+				      enum jump_label_type type)
+{
+	__arch_jump_label_transform(entry, type, true);
+}
+
+#endif
diff --git a/arch/arm/kernel/kprobes.c b/arch/arm/kernel/kprobes.c
index 129c116..ab1869d 100644
--- a/arch/arm/kernel/kprobes.c
+++ b/arch/arm/kernel/kprobes.c
@@ -29,6 +29,7 @@
 #include <asm/cacheflush.h>
 
 #include "kprobes.h"
+#include "patch.h"
 
 #define MIN_STACK_SIZE(addr) 				\
 	min((unsigned long)MAX_STACK_SIZE,		\
@@ -103,58 +104,34 @@
 	return 0;
 }
 
-#ifdef CONFIG_THUMB2_KERNEL
-
-/*
- * For a 32-bit Thumb breakpoint spanning two memory words we need to take
- * special precautions to insert the breakpoint atomically, especially on SMP
- * systems. This is achieved by calling this arming function using stop_machine.
- */
-static int __kprobes set_t32_breakpoint(void *addr)
-{
-	((u16 *)addr)[0] = KPROBE_THUMB32_BREAKPOINT_INSTRUCTION >> 16;
-	((u16 *)addr)[1] = KPROBE_THUMB32_BREAKPOINT_INSTRUCTION & 0xffff;
-	flush_insns(addr, 2*sizeof(u16));
-	return 0;
-}
-
 void __kprobes arch_arm_kprobe(struct kprobe *p)
 {
-	uintptr_t addr = (uintptr_t)p->addr & ~1; /* Remove any Thumb flag */
+	unsigned int brkp;
+	void *addr;
 
-	if (!is_wide_instruction(p->opcode)) {
-		*(u16 *)addr = KPROBE_THUMB16_BREAKPOINT_INSTRUCTION;
-		flush_insns(addr, sizeof(u16));
-	} else if (addr & 2) {
-		/* A 32-bit instruction spanning two words needs special care */
-		stop_machine(set_t32_breakpoint, (void *)addr, &cpu_online_map);
+	if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) {
+		/* Remove any Thumb flag */
+		addr = (void *)((uintptr_t)p->addr & ~1);
+
+		if (is_wide_instruction(p->opcode))
+			brkp = KPROBE_THUMB32_BREAKPOINT_INSTRUCTION;
+		else
+			brkp = KPROBE_THUMB16_BREAKPOINT_INSTRUCTION;
 	} else {
-		/* Word aligned 32-bit instruction can be written atomically */
-		u32 bkp = KPROBE_THUMB32_BREAKPOINT_INSTRUCTION;
-#ifndef __ARMEB__ /* Swap halfwords for little-endian */
-		bkp = (bkp >> 16) | (bkp << 16);
-#endif
-		*(u32 *)addr = bkp;
-		flush_insns(addr, sizeof(u32));
+		kprobe_opcode_t insn = p->opcode;
+
+		addr = p->addr;
+		brkp = KPROBE_ARM_BREAKPOINT_INSTRUCTION;
+
+		if (insn >= 0xe0000000)
+			brkp |= 0xe0000000;  /* Unconditional instruction */
+		else
+			brkp |= insn & 0xf0000000;  /* Copy condition from insn */
 	}
+
+	patch_text(addr, brkp);
 }
 
-#else /* !CONFIG_THUMB2_KERNEL */
-
-void __kprobes arch_arm_kprobe(struct kprobe *p)
-{
-	kprobe_opcode_t insn = p->opcode;
-	kprobe_opcode_t brkp = KPROBE_ARM_BREAKPOINT_INSTRUCTION;
-	if (insn >= 0xe0000000)
-		brkp |= 0xe0000000;  /* Unconditional instruction */
-	else
-		brkp |= insn & 0xf0000000;  /* Copy condition from insn */
-	*p->addr = brkp;
-	flush_insns(p->addr, sizeof(p->addr[0]));
-}
-
-#endif /* !CONFIG_THUMB2_KERNEL */
-
 /*
  * The actual disarming is done here on each CPU and synchronized using
  * stop_machine. This synchronization is necessary on SMP to avoid removing
@@ -166,25 +143,10 @@
 int __kprobes __arch_disarm_kprobe(void *p)
 {
 	struct kprobe *kp = p;
-#ifdef CONFIG_THUMB2_KERNEL
-	u16 *addr = (u16 *)((uintptr_t)kp->addr & ~1);
-	kprobe_opcode_t insn = kp->opcode;
-	unsigned int len;
+	void *addr = (void *)((uintptr_t)kp->addr & ~1);
 
-	if (is_wide_instruction(insn)) {
-		((u16 *)addr)[0] = insn>>16;
-		((u16 *)addr)[1] = insn;
-		len = 2*sizeof(u16);
-	} else {
-		((u16 *)addr)[0] = insn;
-		len = sizeof(u16);
-	}
-	flush_insns(addr, len);
+	__patch_text(addr, kp->opcode);
 
-#else /* !CONFIG_THUMB2_KERNEL */
-	*kp->addr = kp->opcode;
-	flush_insns(kp->addr, sizeof(kp->addr[0]));
-#endif
 	return 0;
 }
 
diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c
index 5699598..dfcdb9f 100644
--- a/arch/arm/kernel/machine_kexec.c
+++ b/arch/arm/kernel/machine_kexec.c
@@ -7,6 +7,7 @@
 #include <linux/delay.h>
 #include <linux/reboot.h>
 #include <linux/io.h>
+#include <linux/irq.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/mmu_context.h>
@@ -53,6 +54,29 @@
 		cpu_relax();
 }
 
+static void machine_kexec_mask_interrupts(void)
+{
+	unsigned int i;
+	struct irq_desc *desc;
+
+	for_each_irq_desc(i, desc) {
+		struct irq_chip *chip;
+
+		chip = irq_desc_get_chip(desc);
+		if (!chip)
+			continue;
+
+		if (chip->irq_eoi && irqd_irq_inprogress(&desc->irq_data))
+			chip->irq_eoi(&desc->irq_data);
+
+		if (chip->irq_mask)
+			chip->irq_mask(&desc->irq_data);
+
+		if (chip->irq_disable && !irqd_irq_disabled(&desc->irq_data))
+			chip->irq_disable(&desc->irq_data);
+	}
+}
+
 void machine_crash_shutdown(struct pt_regs *regs)
 {
 	unsigned long msecs;
@@ -70,6 +94,7 @@
 		printk(KERN_WARNING "Non-crashing CPUs did not react to IPI\n");
 
 	crash_save_cpu(regs, smp_processor_id());
+	machine_kexec_mask_interrupts();
 
 	printk(KERN_INFO "Loading crashdump kernel...\n");
 }
diff --git a/arch/arm/kernel/patch.c b/arch/arm/kernel/patch.c
new file mode 100644
index 0000000..07314af
--- /dev/null
+++ b/arch/arm/kernel/patch.c
@@ -0,0 +1,75 @@
+#include <linux/kernel.h>
+#include <linux/kprobes.h>
+#include <linux/stop_machine.h>
+
+#include <asm/cacheflush.h>
+#include <asm/smp_plat.h>
+#include <asm/opcodes.h>
+
+#include "patch.h"
+
+struct patch {
+	void *addr;
+	unsigned int insn;
+};
+
+void __kprobes __patch_text(void *addr, unsigned int insn)
+{
+	bool thumb2 = IS_ENABLED(CONFIG_THUMB2_KERNEL);
+	int size;
+
+	if (thumb2 && __opcode_is_thumb16(insn)) {
+		*(u16 *)addr = __opcode_to_mem_thumb16(insn);
+		size = sizeof(u16);
+	} else if (thumb2 && ((uintptr_t)addr & 2)) {
+		u16 first = __opcode_thumb32_first(insn);
+		u16 second = __opcode_thumb32_second(insn);
+		u16 *addrh = addr;
+
+		addrh[0] = __opcode_to_mem_thumb16(first);
+		addrh[1] = __opcode_to_mem_thumb16(second);
+
+		size = sizeof(u32);
+	} else {
+		if (thumb2)
+			insn = __opcode_to_mem_thumb32(insn);
+		else
+			insn = __opcode_to_mem_arm(insn);
+
+		*(u32 *)addr = insn;
+		size = sizeof(u32);
+	}
+
+	flush_icache_range((uintptr_t)(addr),
+			   (uintptr_t)(addr) + size);
+}
+
+static int __kprobes patch_text_stop_machine(void *data)
+{
+	struct patch *patch = data;
+
+	__patch_text(patch->addr, patch->insn);
+
+	return 0;
+}
+
+void __kprobes patch_text(void *addr, unsigned int insn)
+{
+	struct patch patch = {
+		.addr = addr,
+		.insn = insn,
+	};
+
+	if (cache_ops_need_broadcast()) {
+		stop_machine(patch_text_stop_machine, &patch, cpu_online_mask);
+	} else {
+		bool straddles_word = IS_ENABLED(CONFIG_THUMB2_KERNEL)
+				      && __opcode_is_thumb32(insn)
+				      && ((uintptr_t)addr & 2);
+
+		if (straddles_word)
+			stop_machine(patch_text_stop_machine, &patch, NULL);
+		else
+			__patch_text(addr, insn);
+	}
+}
diff --git a/arch/arm/kernel/patch.h b/arch/arm/kernel/patch.h
new file mode 100644
index 0000000..b4731f2
--- /dev/null
+++ b/arch/arm/kernel/patch.h
@@ -0,0 +1,7 @@
+#ifndef _ARM_KERNEL_PATCH_H
+#define _ARM_KERNEL_PATCH_H
+
+void patch_text(void *addr, unsigned int insn);
+void __patch_text(void *addr, unsigned int insn);
+
+#endif
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index 8a89d3b..186c8cb 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -738,6 +738,9 @@
 		case 0xC0F0:	/* Cortex-A15 */
 			cpu_pmu = armv7_a15_pmu_init();
 			break;
+		case 0xC070:	/* Cortex-A7 */
+			cpu_pmu = armv7_a7_pmu_init();
+			break;
 		}
 	/* Intel CPUs [xscale]. */
 	} else if (0x69 == implementor) {
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index 4d7095a..00755d8 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -610,6 +610,130 @@
 };
 
 /*
+ * Cortex-A7 HW events mapping
+ */
+static const unsigned armv7_a7_perf_map[PERF_COUNT_HW_MAX] = {
+	[PERF_COUNT_HW_CPU_CYCLES]		= ARMV7_PERFCTR_CPU_CYCLES,
+	[PERF_COUNT_HW_INSTRUCTIONS]		= ARMV7_PERFCTR_INSTR_EXECUTED,
+	[PERF_COUNT_HW_CACHE_REFERENCES]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
+	[PERF_COUNT_HW_CACHE_MISSES]		= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= ARMV7_PERFCTR_PC_WRITE,
+	[PERF_COUNT_HW_BRANCH_MISSES]		= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+	[PERF_COUNT_HW_BUS_CYCLES]		= ARMV7_PERFCTR_BUS_CYCLES,
+	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= HW_OP_UNSUPPORTED,
+	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= HW_OP_UNSUPPORTED,
+};
+
+static const unsigned armv7_a7_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
+					[PERF_COUNT_HW_CACHE_OP_MAX]
+					[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+	[C(L1D)] = {
+		/*
+		 * The performance counters don't differentiate between read
+		 * and write accesses/misses so this isn't strictly correct,
+		 * but it's the best we can do. Writes and reads get
+		 * combined.
+		 */
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(L1I)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_ICACHE_ACCESS,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_ICACHE_REFILL,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_ICACHE_ACCESS,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_ICACHE_REFILL,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(LL)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L2_CACHE_ACCESS,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L2_CACHE_REFILL,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L2_CACHE_ACCESS,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L2_CACHE_REFILL,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(DTLB)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(ITLB)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(BPU)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(NODE)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+};
+
+/*
  * Perf Events' indices
  */
 #define	ARMV7_IDX_CYCLE_COUNTER	0
@@ -1104,6 +1228,12 @@
 				&armv7_a15_perf_cache_map, 0xFF);
 }
 
+static int armv7_a7_map_event(struct perf_event *event)
+{
+	return map_cpu_event(event, &armv7_a7_perf_map,
+				&armv7_a7_perf_cache_map, 0xFF);
+}
+
 static struct arm_pmu armv7pmu = {
 	.handle_irq		= armv7pmu_handle_irq,
 	.enable			= armv7pmu_enable_event,
@@ -1164,6 +1294,16 @@
 	armv7pmu.set_event_filter = armv7pmu_set_event_filter;
 	return &armv7pmu;
 }
+
+static struct arm_pmu *__init armv7_a7_pmu_init(void)
+{
+	armv7pmu.id		= ARM_PERF_PMU_ID_CA7;
+	armv7pmu.name		= "ARMv7 Cortex-A7";
+	armv7pmu.map_event	= armv7_a7_map_event;
+	armv7pmu.num_events	= armv7_read_num_pmnc_events();
+	armv7pmu.set_event_filter = armv7pmu_set_event_filter;
+	return &armv7pmu;
+}
 #else
 static struct arm_pmu *__init armv7_a8_pmu_init(void)
 {
@@ -1184,4 +1324,9 @@
 {
 	return NULL;
 }
+
+static struct arm_pmu *__init armv7_a7_pmu_init(void)
+{
+	return NULL;
+}
 #endif	/* CONFIG_CPU_V7 */
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 7b9cdde..2b7b017 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -528,21 +528,39 @@
 #ifdef CONFIG_MMU
 /*
  * The vectors page is always readable from user space for the
- * atomic helpers and the signal restart code.  Let's declare a mapping
- * for it so it is visible through ptrace and /proc/<pid>/mem.
+ * atomic helpers and the signal restart code. Insert it into the
+ * gate_vma so that it is visible through ptrace and /proc/<pid>/mem.
  */
+static struct vm_area_struct gate_vma;
 
-int vectors_user_mapping(void)
+static int __init gate_vma_init(void)
 {
-	struct mm_struct *mm = current->mm;
-	return install_special_mapping(mm, 0xffff0000, PAGE_SIZE,
-				       VM_READ | VM_EXEC |
-				       VM_MAYREAD | VM_MAYEXEC | VM_RESERVED,
-				       NULL);
+	gate_vma.vm_start	= 0xffff0000;
+	gate_vma.vm_end		= 0xffff0000 + PAGE_SIZE;
+	gate_vma.vm_page_prot	= PAGE_READONLY_EXEC;
+	gate_vma.vm_flags	= VM_READ | VM_EXEC |
+				  VM_MAYREAD | VM_MAYEXEC;
+	return 0;
+}
+arch_initcall(gate_vma_init);
+
+struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
+{
+	return &gate_vma;
+}
+
+int in_gate_area(struct mm_struct *mm, unsigned long addr)
+{
+	return (addr >= gate_vma.vm_start) && (addr < gate_vma.vm_end);
+}
+
+int in_gate_area_no_mm(unsigned long addr)
+{
+	return in_gate_area(NULL, addr);
 }
 
 const char *arch_vma_name(struct vm_area_struct *vma)
 {
-	return (vma->vm_start == 0xffff0000) ? "[vectors]" : NULL;
+	return (vma == &gate_vma) ? "[vectors]" : NULL;
 }
 #endif
diff --git a/arch/arm/kernel/sched_clock.c b/arch/arm/kernel/sched_clock.c
index 5416c7c..27d186a 100644
--- a/arch/arm/kernel/sched_clock.c
+++ b/arch/arm/kernel/sched_clock.c
@@ -10,6 +10,7 @@
 #include <linux/jiffies.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/syscore_ops.h>
 #include <linux/timer.h>
 
 #include <asm/sched_clock.h>
@@ -164,3 +165,20 @@
 
 	sched_clock_poll(sched_clock_timer.data);
 }
+
+static int sched_clock_suspend(void)
+{
+	sched_clock_poll(sched_clock_timer.data);
+	return 0;
+}
+
+static struct syscore_ops sched_clock_ops = {
+	.suspend = sched_clock_suspend,
+};
+
+static int __init sched_clock_syscore_init(void)
+{
+	register_syscore_ops(&sched_clock_ops);
+	return 0;
+}
+device_initcall(sched_clock_syscore_init);
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 9e0fdb3..b914113 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -976,7 +976,6 @@
 	conswitchp = &dummy_con;
 #endif
 #endif
-	early_trap_init();
 
 	if (mdesc->init_early)
 		mdesc->init_early();
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index 9e617bd..7cb532f 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -66,12 +66,13 @@
  */
 asmlinkage int sys_sigsuspend(int restart, unsigned long oldmask, old_sigset_t mask)
 {
-	mask &= _BLOCKABLE;
-	spin_lock_irq(&current->sighand->siglock);
+	sigset_t blocked;
+
 	current->saved_sigmask = current->blocked;
-	siginitset(&current->blocked, mask);
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
+
+	mask &= _BLOCKABLE;
+	siginitset(&blocked, mask);
+	set_current_blocked(&blocked);
 
 	current->state = TASK_INTERRUPTIBLE;
 	schedule();
@@ -280,10 +281,7 @@
 	err = __copy_from_user(&set, &sf->uc.uc_sigmask, sizeof(set));
 	if (err == 0) {
 		sigdelsetmask(&set, ~_BLOCKABLE);
-		spin_lock_irq(&current->sighand->siglock);
-		current->blocked = set;
-		recalc_sigpending();
-		spin_unlock_irq(&current->sighand->siglock);
+		set_current_blocked(&set);
 	}
 
 	__get_user_error(regs->ARM_r0, &sf->uc.uc_mcontext.arm_r0, err);
@@ -636,13 +634,7 @@
 	/*
 	 * Block the signal if we were successful.
 	 */
-	spin_lock_irq(&tsk->sighand->siglock);
-	sigorsets(&tsk->blocked, &tsk->blocked,
-		  &ka->sa.sa_mask);
-	if (!(ka->sa.sa_flags & SA_NODEFER))
-		sigaddset(&tsk->blocked, sig);
-	recalc_sigpending();
-	spin_unlock_irq(&tsk->sighand->siglock);
+	block_sigmask(ka, sig);
 
 	return 0;
 }
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 8f8cce2..2cee7d1 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -58,6 +58,8 @@
 	IPI_CPU_STOP,
 };
 
+static DECLARE_COMPLETION(cpu_running);
+
 int __cpuinit __cpu_up(unsigned int cpu)
 {
 	struct cpuinfo_arm *ci = &per_cpu(cpu_data, cpu);
@@ -98,20 +100,12 @@
 	 */
 	ret = boot_secondary(cpu, idle);
 	if (ret == 0) {
-		unsigned long timeout;
-
 		/*
 		 * CPU was successfully started, wait for it
 		 * to come online or time out.
 		 */
-		timeout = jiffies + HZ;
-		while (time_before(jiffies, timeout)) {
-			if (cpu_online(cpu))
-				break;
-
-			udelay(10);
-			barrier();
-		}
+		wait_for_completion_timeout(&cpu_running,
+						 msecs_to_jiffies(1000));
 
 		if (!cpu_online(cpu)) {
 			pr_crit("CPU%u: failed to come online\n", cpu);
@@ -288,9 +282,10 @@
 	/*
 	 * OK, now it's safe to let the boot CPU continue.  Wait for
 	 * the CPU migration code to notice that the CPU is online
-	 * before we continue.
+	 * before we continue - which happens after __cpu_up returns.
 	 */
 	set_cpu_online(cpu, true);
+	complete(&cpu_running);
 
 	/*
 	 * Setup the percpu timer for this CPU.
diff --git a/arch/arm/kernel/time.c b/arch/arm/kernel/time.c
index 8c57dd3..fe31b22 100644
--- a/arch/arm/kernel/time.c
+++ b/arch/arm/kernel/time.c
@@ -25,8 +25,6 @@
 #include <linux/timer.h>
 #include <linux/irq.h>
 
-#include <linux/mc146818rtc.h>
-
 #include <asm/leds.h>
 #include <asm/thread_info.h>
 #include <asm/sched_clock.h>
@@ -149,8 +147,6 @@
 {
 	system_timer = machine_desc->timer;
 	system_timer->init();
-#ifdef CONFIG_HAVE_SCHED_CLOCK
 	sched_clock_postinit();
-#endif
 }
 
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index cd77743..7784547 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -227,6 +227,11 @@
 #else
 #define S_SMP ""
 #endif
+#ifdef CONFIG_THUMB2_KERNEL
+#define S_ISA " THUMB2"
+#else
+#define S_ISA " ARM"
+#endif
 
 static int __die(const char *str, int err, struct thread_info *thread, struct pt_regs *regs)
 {
@@ -234,8 +239,8 @@
 	static int die_counter;
 	int ret;
 
-	printk(KERN_EMERG "Internal error: %s: %x [#%d]" S_PREEMPT S_SMP "\n",
-	       str, err, ++die_counter);
+	printk(KERN_EMERG "Internal error: %s: %x [#%d]" S_PREEMPT S_SMP
+	       S_ISA "\n", str, err, ++die_counter);
 
 	/* trap and error numbers are mostly meaningless on ARM */
 	ret = notify_die(DIE_OOPS, str, regs, err, tsk->thread.trap_no, SIGSEGV);
@@ -784,18 +789,16 @@
 		memcpy((void *)vectors + 0xfe0, (void *)vectors + 0xfe8, 4);
 }
 
-void __init early_trap_init(void)
+void __init early_trap_init(void *vectors_base)
 {
-#if defined(CONFIG_CPU_USE_DOMAINS)
-	unsigned long vectors = CONFIG_VECTORS_BASE;
-#else
-	unsigned long vectors = (unsigned long)vectors_page;
-#endif
+	unsigned long vectors = (unsigned long)vectors_base;
 	extern char __stubs_start[], __stubs_end[];
 	extern char __vectors_start[], __vectors_end[];
 	extern char __kuser_helper_start[], __kuser_helper_end[];
 	int kuser_sz = __kuser_helper_end - __kuser_helper_start;
 
+	vectors_page = vectors_base;
+
 	/*
 	 * Copy the vectors, stubs and kuser helpers (in entry-armv.S)
 	 * into the vector page, mapped at 0xffff0000, and ensure these
diff --git a/arch/arm/mach-at91/at91sam9g45_devices.c b/arch/arm/mach-at91/at91sam9g45_devices.c
index 4320b20..698479f 100644
--- a/arch/arm/mach-at91/at91sam9g45_devices.c
+++ b/arch/arm/mach-at91/at91sam9g45_devices.c
@@ -437,7 +437,6 @@
 
 	/* DMA slave channel configuration */
 	atslave->dma_dev = &at_hdmac_device.dev;
-	atslave->reg_width = AT_DMA_SLAVE_WIDTH_32BIT;
 	atslave->cfg = ATC_FIFOCFG_HALFFIFO
 			| ATC_SRC_H2SEL_HW | ATC_DST_H2SEL_HW;
 	atslave->ctrla = ATC_SCSIZE_16 | ATC_DCSIZE_16;
diff --git a/arch/arm/mach-at91/include/mach/at_hdmac.h b/arch/arm/mach-at91/include/mach/at_hdmac.h
index 187cb58..fff48d1 100644
--- a/arch/arm/mach-at91/include/mach/at_hdmac.h
+++ b/arch/arm/mach-at91/include/mach/at_hdmac.h
@@ -24,18 +24,6 @@
 };
 
 /**
- * enum at_dma_slave_width - DMA slave register access width.
- * @AT_DMA_SLAVE_WIDTH_8BIT: Do 8-bit slave register accesses
- * @AT_DMA_SLAVE_WIDTH_16BIT: Do 16-bit slave register accesses
- * @AT_DMA_SLAVE_WIDTH_32BIT: Do 32-bit slave register accesses
- */
-enum at_dma_slave_width {
-	AT_DMA_SLAVE_WIDTH_8BIT = 0,
-	AT_DMA_SLAVE_WIDTH_16BIT,
-	AT_DMA_SLAVE_WIDTH_32BIT,
-};
-
-/**
  * struct at_dma_slave - Controller-specific information about a slave
  * @dma_dev: required DMA master device
  * @tx_reg: physical address of data register used for
@@ -48,9 +36,6 @@
  */
 struct at_dma_slave {
 	struct device		*dma_dev;
-	dma_addr_t		tx_reg;
-	dma_addr_t		rx_reg;
-	enum at_dma_slave_width	reg_width;
 	u32			cfg;
 	u32			ctrla;
 };
diff --git a/arch/arm/mach-at91/include/mach/io.h b/arch/arm/mach-at91/include/mach/io.h
deleted file mode 100644
index 4003001..0000000
--- a/arch/arm/mach-at91/include/mach/io.h
+++ /dev/null
@@ -1,31 +0,0 @@
-/*
- * arch/arm/mach-at91/include/mach/io.h
- *
- *  Copyright (C) 2003 SAN People
- *
- * 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 __ASM_ARCH_IO_H
-#define __ASM_ARCH_IO_H
-
-#include <mach/hardware.h>
-
-#define IO_SPACE_LIMIT		0xFFFFFFFF
-
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
-
-#endif
diff --git a/arch/arm/mach-at91/include/mach/uncompress.h b/arch/arm/mach-at91/include/mach/uncompress.h
index 0234fd9..4218647 100644
--- a/arch/arm/mach-at91/include/mach/uncompress.h
+++ b/arch/arm/mach-at91/include/mach/uncompress.h
@@ -23,6 +23,7 @@
 
 #include <linux/io.h>
 #include <linux/atmel_serial.h>
+#include <mach/hardware.h>
 
 #if defined(CONFIG_AT91_EARLY_DBGU0)
 #define UART_OFFSET AT91_BASE_DBGU0
diff --git a/arch/arm/mach-bcmring/include/mach/io.h b/arch/arm/mach-bcmring/include/mach/io.h
deleted file mode 100644
index dae5e9b..0000000
--- a/arch/arm/mach-bcmring/include/mach/io.h
+++ /dev/null
@@ -1,33 +0,0 @@
-/*
- *
- *  Copyright (C) 1999 ARM Limited
- *
- * 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 __ASM_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H
-
-#include <mach/hardware.h>
-
-#define IO_SPACE_LIMIT 0xffffffff
-
-/*
- * We don't actually have real ISA nor PCI buses, but there is so many
- * drivers out there that might just work if we fake them...
- */
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
-
-#endif
diff --git a/arch/arm/mach-clps711x/include/mach/io.h b/arch/arm/mach-clps711x/include/mach/io.h
deleted file mode 100644
index 2e0b3ce..0000000
--- a/arch/arm/mach-clps711x/include/mach/io.h
+++ /dev/null
@@ -1,36 +0,0 @@
-/*
- *  arch/arm/mach-clps711x/include/mach/io.h
- *
- *  Copyright (C) 1999 ARM Limited
- *
- * 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 __ASM_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H
-
-#define IO_SPACE_LIMIT 0xffffffff
-
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
-
-/*
- * We don't support ins[lb]/outs[lb].  Make them fault.
- */
-#define __raw_readsb(p,d,l)	do { *(int *)0 = 0; } while (0)
-#define __raw_readsl(p,d,l)	do { *(int *)0 = 0; } while (0)
-#define __raw_writesb(p,d,l)	do { *(int *)0 = 0; } while (0)
-#define __raw_writesl(p,d,l)	do { *(int *)0 = 0; } while (0)
-
-#endif
diff --git a/arch/arm/mach-clps711x/include/mach/uncompress.h b/arch/arm/mach-clps711x/include/mach/uncompress.h
index 7164310..35ed731 100644
--- a/arch/arm/mach-clps711x/include/mach/uncompress.h
+++ b/arch/arm/mach-clps711x/include/mach/uncompress.h
@@ -17,7 +17,6 @@
  * along with this program; if not, write to the Free Software
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
-#include <mach/io.h>
 #include <mach/hardware.h>
 #include <asm/hardware/clps7111.h>
 
diff --git a/arch/arm/mach-cns3xxx/core.c b/arch/arm/mach-cns3xxx/core.c
index 941a308..031805b 100644
--- a/arch/arm/mach-cns3xxx/core.c
+++ b/arch/arm/mach-cns3xxx/core.c
@@ -72,13 +72,13 @@
 /* used by entry-macro.S */
 void __init cns3xxx_init_irq(void)
 {
-	gic_init(0, 29, __io(CNS3XXX_TC11MP_GIC_DIST_BASE_VIRT),
-		 __io(CNS3XXX_TC11MP_GIC_CPU_BASE_VIRT));
+	gic_init(0, 29, IOMEM(CNS3XXX_TC11MP_GIC_DIST_BASE_VIRT),
+		 IOMEM(CNS3XXX_TC11MP_GIC_CPU_BASE_VIRT));
 }
 
 void cns3xxx_power_off(void)
 {
-	u32 __iomem *pm_base = __io(CNS3XXX_PM_BASE_VIRT);
+	u32 __iomem *pm_base = IOMEM(CNS3XXX_PM_BASE_VIRT);
 	u32 clkctrl;
 
 	printk(KERN_INFO "powering system down...\n");
@@ -237,7 +237,7 @@
 
 static void __init cns3xxx_timer_init(void)
 {
-	cns3xxx_tmr1 = __io(CNS3XXX_TIMER1_2_3_BASE_VIRT);
+	cns3xxx_tmr1 = IOMEM(CNS3XXX_TIMER1_2_3_BASE_VIRT);
 
 	__cns3xxx_timer_init(IRQ_CNS3XXX_TIMER0);
 }
diff --git a/arch/arm/mach-cns3xxx/devices.c b/arch/arm/mach-cns3xxx/devices.c
index 79d1fb0..1e40c99 100644
--- a/arch/arm/mach-cns3xxx/devices.c
+++ b/arch/arm/mach-cns3xxx/devices.c
@@ -98,7 +98,7 @@
 
 void __init cns3xxx_sdhci_init(void)
 {
-	u32 __iomem *gpioa = __io(CNS3XXX_MISC_BASE_VIRT + 0x0014);
+	u32 __iomem *gpioa = IOMEM(CNS3XXX_MISC_BASE_VIRT + 0x0014);
 	u32 gpioa_pins = __raw_readl(gpioa);
 
 	/* MMC/SD pins share with GPIOA */
diff --git a/arch/arm/mach-cns3xxx/include/mach/io.h b/arch/arm/mach-cns3xxx/include/mach/io.h
deleted file mode 100644
index 33b6fc1..0000000
--- a/arch/arm/mach-cns3xxx/include/mach/io.h
+++ /dev/null
@@ -1,17 +0,0 @@
-/*
- * Copyright 2008 Cavium Networks
- * Copyright 2003 ARM Limited
- *
- * This file 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 __MACH_IO_H
-#define __MACH_IO_H
-
-#define IO_SPACE_LIMIT 0xffffffff
-
-#define __io(a)			__typesafe_io(a)
-#define __mem_pci(a)		(a)
-
-#endif
diff --git a/arch/arm/mach-davinci/include/mach/entry-macro.S b/arch/arm/mach-davinci/include/mach/entry-macro.S
index c1661d2..768b3c0 100644
--- a/arch/arm/mach-davinci/include/mach/entry-macro.S
+++ b/arch/arm/mach-davinci/include/mach/entry-macro.S
@@ -8,7 +8,6 @@
  * is licensed "as is" without any warranty of any kind, whether express
  * or implied.
  */
-#include <mach/io.h>
 #include <mach/irqs.h>
 
 		.macro  get_irqnr_preamble, base, tmp
diff --git a/arch/arm/mach-davinci/include/mach/hardware.h b/arch/arm/mach-davinci/include/mach/hardware.h
index 0209b1f..2184691 100644
--- a/arch/arm/mach-davinci/include/mach/hardware.h
+++ b/arch/arm/mach-davinci/include/mach/hardware.h
@@ -30,10 +30,4 @@
 #define __IO_ADDRESS(x)			((x) + IO_OFFSET)
 #define IO_ADDRESS(pa)			IOMEM(__IO_ADDRESS(pa))
 
-#ifdef __ASSEMBLER__
-#define IOMEM(x)                	x
-#else
-#define IOMEM(x)                	((void __force __iomem *)(x))
-#endif
-
 #endif /* __ASM_ARCH_HARDWARE_H */
diff --git a/arch/arm/mach-davinci/include/mach/io.h b/arch/arm/mach-davinci/include/mach/io.h
deleted file mode 100644
index b2267d1e..0000000
--- a/arch/arm/mach-davinci/include/mach/io.h
+++ /dev/null
@@ -1,24 +0,0 @@
-/*
- * DaVinci IO address definitions
- *
- * Copied from include/asm/arm/arch-omap/io.h
- *
- * 2007 (c) MontaVista Software, Inc. This file is licensed under
- * the terms of the GNU General Public License version 2. This program
- * is licensed "as is" without any warranty of any kind, whether express
- * or implied.
- */
-#ifndef __ASM_ARCH_IO_H
-#define __ASM_ARCH_IO_H
-
-#define IO_SPACE_LIMIT 0xffffffff
-
-/*
- * We don't actually have real ISA nor PCI buses, but there is so many
- * drivers out there that might just work if we fake them...
- */
-#define __io(a)			__typesafe_io(a)
-#define __mem_pci(a)		(a)
-#define __mem_isa(a)		(a)
-
-#endif /* __ASM_ARCH_IO_H */
diff --git a/arch/arm/mach-davinci/include/mach/uncompress.h b/arch/arm/mach-davinci/include/mach/uncompress.h
index 9dc7cf9..da2fb2c 100644
--- a/arch/arm/mach-davinci/include/mach/uncompress.h
+++ b/arch/arm/mach-davinci/include/mach/uncompress.h
@@ -25,6 +25,8 @@
 
 #include <mach/serial.h>
 
+#define IOMEM(x)	((void __force __iomem *)(x))
+
 u32 *uart;
 
 /* PORT_16C550A, in polled non-fifo mode */
diff --git a/arch/arm/mach-davinci/time.c b/arch/arm/mach-davinci/time.c
index e1969ce..75da315 100644
--- a/arch/arm/mach-davinci/time.c
+++ b/arch/arm/mach-davinci/time.c
@@ -19,11 +19,14 @@
 #include <linux/err.h>
 #include <linux/platform_device.h>
 
-#include <mach/hardware.h>
+#include <asm/sched_clock.h>
 #include <asm/mach/irq.h>
 #include <asm/mach/time.h>
+
 #include <mach/cputype.h>
+#include <mach/hardware.h>
 #include <mach/time.h>
+
 #include "clock.h"
 
 static struct clock_event_device clockevent_davinci;
@@ -272,19 +275,9 @@
 	return (cycles_t)timer32_read(t);
 }
 
-/*
- * Kernel assumes that sched_clock can be called early but may not have
- * things ready yet.
- */
-static cycle_t read_dummy(struct clocksource *cs)
-{
-	return 0;
-}
-
-
 static struct clocksource clocksource_davinci = {
 	.rating		= 300,
-	.read		= read_dummy,
+	.read		= read_cycles,
 	.mask		= CLOCKSOURCE_MASK(32),
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
@@ -292,12 +285,9 @@
 /*
  * Overwrite weak default sched_clock with something more precise
  */
-unsigned long long notrace sched_clock(void)
+static u32 notrace davinci_read_sched_clock(void)
 {
-	const cycle_t cyc = clocksource_davinci.read(&clocksource_davinci);
-
-	return clocksource_cyc2ns(cyc, clocksource_davinci.mult,
-				clocksource_davinci.shift);
+	return timer32_read(&timers[TID_CLOCKSOURCE]);
 }
 
 /*
@@ -397,12 +387,14 @@
 	davinci_clock_tick_rate = clk_get_rate(timer_clk);
 
 	/* setup clocksource */
-	clocksource_davinci.read = read_cycles;
 	clocksource_davinci.name = id_to_name[clocksource_id];
 	if (clocksource_register_hz(&clocksource_davinci,
 				    davinci_clock_tick_rate))
 		printk(err, clocksource_davinci.name);
 
+	setup_sched_clock(davinci_read_sched_clock, 32,
+			  davinci_clock_tick_rate);
+
 	/* setup clockevent */
 	clockevent_davinci.name = id_to_name[timers[TID_CLOCKEVENT].id];
 	clockevent_davinci.mult = div_sc(davinci_clock_tick_rate, NSEC_PER_SEC,
diff --git a/arch/arm/mach-dove/addr-map.c b/arch/arm/mach-dove/addr-map.c
index 98b8c83..2a06c01 100644
--- a/arch/arm/mach-dove/addr-map.c
+++ b/arch/arm/mach-dove/addr-map.c
@@ -14,6 +14,7 @@
 #include <linux/io.h>
 #include <asm/mach/arch.h>
 #include <asm/setup.h>
+#include <mach/dove.h>
 #include <plat/addr-map.h>
 #include "common.h"
 
diff --git a/arch/arm/mach-dove/include/mach/io.h b/arch/arm/mach-dove/include/mach/io.h
index eb4936f..29c8b85 100644
--- a/arch/arm/mach-dove/include/mach/io.h
+++ b/arch/arm/mach-dove/include/mach/io.h
@@ -15,6 +15,5 @@
 
 #define __io(a)  	((void __iomem *)(((a) - DOVE_PCIE0_IO_BUS_BASE) + \
 						 DOVE_PCIE0_IO_VIRT_BASE))
-#define __mem_pci(a)	(a)
 
 #endif
diff --git a/arch/arm/mach-ebsa110/core.c b/arch/arm/mach-ebsa110/core.c
index 8c9f56a..6f80686 100644
--- a/arch/arm/mach-ebsa110/core.c
+++ b/arch/arm/mach-ebsa110/core.c
@@ -116,6 +116,20 @@
 	iotable_init(ebsa110_io_desc, ARRAY_SIZE(ebsa110_io_desc));
 }
 
+static void __iomem *ebsa110_ioremap_caller(unsigned long cookie, size_t size,
+					    unsigned int flags, void *caller)
+{
+	return (void __iomem *)cookie;
+}
+
+static void ebsa110_iounmap(volatile void __iomem *io_addr)
+{}
+
+static void __init ebsa110_init_early(void)
+{
+	arch_ioremap_caller = ebsa110_ioremap_caller;
+	arch_iounmap = ebsa110_iounmap;
+}
 
 #define PIT_CTRL		(PIT_BASE + 0x0d)
 #define PIT_T2			(PIT_BASE + 0x09)
@@ -312,6 +326,7 @@
 	.reserve_lp2	= 1,
 	.restart_mode	= 's',
 	.map_io		= ebsa110_map_io,
+	.init_early	= ebsa110_init_early,
 	.init_irq	= ebsa110_init_irq,
 	.timer		= &ebsa110_timer,
 	.restart	= ebsa110_restart,
diff --git a/arch/arm/mach-ebsa110/include/mach/io.h b/arch/arm/mach-ebsa110/include/mach/io.h
index 44679db..11bb079 100644
--- a/arch/arm/mach-ebsa110/include/mach/io.h
+++ b/arch/arm/mach-ebsa110/include/mach/io.h
@@ -62,15 +62,6 @@
 #define writew(v,b)		__writew(v,b)
 #define writel(v,b)		__writel(v,b)
 
-static inline void __iomem *__arch_ioremap(unsigned long cookie, size_t size,
-					   unsigned int flags)
-{
-	return (void __iomem *)cookie;
-}
-
-#define __arch_ioremap		__arch_ioremap
-#define __arch_iounmap(cookie)	do { } while (0)
-
 extern void insb(unsigned int port, void *buf, int sz);
 extern void insw(unsigned int port, void *buf, int sz);
 extern void insl(unsigned int port, void *buf, int sz);
diff --git a/arch/arm/mach-ep93xx/include/mach/io.h b/arch/arm/mach-ep93xx/include/mach/io.h
deleted file mode 100644
index 594b77f..0000000
--- a/arch/arm/mach-ep93xx/include/mach/io.h
+++ /dev/null
@@ -1,22 +0,0 @@
-/*
- * arch/arm/mach-ep93xx/include/mach/io.h
- */
-
-#ifndef __ASM_MACH_IO_H
-#define __ASM_MACH_IO_H
-
-#define IO_SPACE_LIMIT		0xffffffff
-
-#define __io(p)			__typesafe_io(p)
-#define __mem_pci(p)		(p)
-
-/*
- * A typesafe __io() variation for variable initialisers
- */
-#ifdef __ASSEMBLER__
-#define IOMEM(p)		p
-#else
-#define IOMEM(p)		((void __iomem __force *)(p))
-#endif
-
-#endif /* __ASM_MACH_IO_H */
diff --git a/arch/arm/mach-exynos/include/mach/io.h b/arch/arm/mach-exynos/include/mach/io.h
deleted file mode 100644
index d5478d2..0000000
--- a/arch/arm/mach-exynos/include/mach/io.h
+++ /dev/null
@@ -1,26 +0,0 @@
-/* linux/arch/arm/mach-exynos4/include/mach/io.h
- *
- * Copyright (c) 2010-2011 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com
- *
- * Copyright 2008-2010 Ben Dooks <ben-linux@fluff.org>
- *
- * Based on arch/arm/mach-s5p6442/include/mach/io.h
- *
- * Default IO routines for EXYNOS4
- *
- * 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_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H __FILE__
-
-/* No current ISA/PCI bus support. */
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
-
-#define IO_SPACE_LIMIT (0xFFFFFFFF)
-
-#endif /* __ASM_ARM_ARCH_IO_H */
diff --git a/arch/arm/mach-footbridge/include/mach/io.h b/arch/arm/mach-footbridge/include/mach/io.h
index 15a7039..aba531ee 100644
--- a/arch/arm/mach-footbridge/include/mach/io.h
+++ b/arch/arm/mach-footbridge/include/mach/io.h
@@ -27,18 +27,5 @@
  * Translation of various region addresses to virtual addresses
  */
 #define __io(a)			((void __iomem *)(PCIO_BASE + (a)))
-#if 1
-#define __mem_pci(a)		(a)
-#else
-
-static inline void __iomem *___mem_pci(void __iomem *p)
-{
-	unsigned long a = (unsigned long)p;
-	BUG_ON(a <= 0xc0000000 || a >= 0xe0000000);
-	return p;
-}
-
-#define __mem_pci(a)		___mem_pci(a)
-#endif
 
 #endif
diff --git a/arch/arm/mach-gemini/include/mach/io.h b/arch/arm/mach-gemini/include/mach/io.h
deleted file mode 100644
index c548056..0000000
--- a/arch/arm/mach-gemini/include/mach/io.h
+++ /dev/null
@@ -1,18 +0,0 @@
-/*
- *  Copyright (C) 2001-2006 Storlink, Corp.
- *  Copyright (C) 2008-2009 Paulius Zaleckas <paulius.zaleckas@teltonika.lt>
- *
- * 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.
- */
-#ifndef __MACH_IO_H
-#define __MACH_IO_H
-
-#define IO_SPACE_LIMIT	0xffffffff
-
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
-
-#endif /* __MACH_IO_H */
diff --git a/arch/arm/mach-h720x/include/mach/io.h b/arch/arm/mach-h720x/include/mach/io.h
deleted file mode 100644
index 2c8659c..0000000
--- a/arch/arm/mach-h720x/include/mach/io.h
+++ /dev/null
@@ -1,22 +0,0 @@
-/*
- * arch/arm/mach-h720x/include/mach/io.h
- *
- * Copyright (C) 2000 Steve Hill (sjhill@cotw.com)
- *
- * Changelog:
- *
- *  09-19-2001	JJKIM
- *  		Created from arch/arm/mach-l7200/include/mach/io.h
- *
- *  03-27-2003  Robert Schwebel <r.schwebel@pengutronix.de>:
- *  		re-unified header files for h720x
- */
-#ifndef __ASM_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H
-
-#define IO_SPACE_LIMIT 0xffffffff
-
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
-
-#endif
diff --git a/arch/arm/mach-highbank/highbank.c b/arch/arm/mach-highbank/highbank.c
index 808b055..410a112 100644
--- a/arch/arm/mach-highbank/highbank.c
+++ b/arch/arm/mach-highbank/highbank.c
@@ -35,7 +35,6 @@
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
 #include <asm/mach/time.h>
-#include <mach/irqs.h>
 
 #include "core.h"
 #include "sysregs.h"
diff --git a/arch/arm/mach-highbank/include/mach/io.h b/arch/arm/mach-highbank/include/mach/io.h
deleted file mode 100644
index 70cfa3b..0000000
--- a/arch/arm/mach-highbank/include/mach/io.h
+++ /dev/null
@@ -1,7 +0,0 @@
-#ifndef __MACH_IO_H
-#define __MACH_IO_H
-
-#define __io(a)		({ (void)(a); __typesafe_io(0); })
-#define __mem_pci(a)	(a)
-
-#endif
diff --git a/arch/arm/mach-highbank/include/mach/irqs.h b/arch/arm/mach-highbank/include/mach/irqs.h
deleted file mode 100644
index 9746aab..0000000
--- a/arch/arm/mach-highbank/include/mach/irqs.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __MACH_IRQS_H
-#define __MACH_IRQS_H
-
-#define NR_IRQS			192
-
-#endif
diff --git a/arch/arm/mach-imx/Kconfig b/arch/arm/mach-imx/Kconfig
index 52359f8..7561eca 100644
--- a/arch/arm/mach-imx/Kconfig
+++ b/arch/arm/mach-imx/Kconfig
@@ -1,6 +1,3 @@
-config IMX_HAVE_DMA_V1
-	bool
-
 config HAVE_IMX_GPC
 	bool
 
@@ -38,7 +35,6 @@
 	bool
 	select ARCH_MX1
 	select CPU_ARM920T
-	select IMX_HAVE_DMA_V1
 	select IMX_HAVE_IOMUX_V1
 	select MXC_AVIC
 
@@ -46,7 +42,6 @@
 	bool
 	select MACH_MX21
 	select CPU_ARM926T
-	select IMX_HAVE_DMA_V1
 	select IMX_HAVE_IOMUX_V1
 	select MXC_AVIC
 
@@ -61,7 +56,6 @@
 	bool
 	select MACH_MX27
 	select CPU_ARM926T
-	select IMX_HAVE_DMA_V1
 	select IMX_HAVE_IOMUX_V1
 	select MXC_AVIC
 
diff --git a/arch/arm/mach-imx/Makefile b/arch/arm/mach-imx/Makefile
index 35fc450..ab939c5 100644
--- a/arch/arm/mach-imx/Makefile
+++ b/arch/arm/mach-imx/Makefile
@@ -1,5 +1,3 @@
-obj-$(CONFIG_IMX_HAVE_DMA_V1) += dma-v1.o
-
 obj-$(CONFIG_SOC_IMX1) += clock-imx1.o mm-imx1.o
 obj-$(CONFIG_SOC_IMX21) += clock-imx21.o mm-imx21.o
 
diff --git a/arch/arm/mach-imx/dma-v1.c b/arch/arm/mach-imx/dma-v1.c
deleted file mode 100644
index 3189a60..0000000
--- a/arch/arm/mach-imx/dma-v1.c
+++ /dev/null
@@ -1,845 +0,0 @@
-/*
- *  linux/arch/arm/plat-mxc/dma-v1.c
- *
- *  i.MX DMA registration and IRQ dispatching
- *
- * Copyright 2006 Pavel Pisa <pisa@cmp.felk.cvut.cz>
- * Copyright 2008 Juergen Beisert, <kernel@pengutronix.de>
- * Copyright 2008 Sascha Hauer, <s.hauer@pengutronix.de>
- *
- * 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., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
-
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/interrupt.h>
-#include <linux/err.h>
-#include <linux/errno.h>
-#include <linux/clk.h>
-#include <linux/scatterlist.h>
-#include <linux/io.h>
-
-#include <asm/irq.h>
-#include <mach/hardware.h>
-#include <mach/dma-v1.h>
-
-#define DMA_DCR     0x00		/* Control Register */
-#define DMA_DISR    0x04		/* Interrupt status Register */
-#define DMA_DIMR    0x08		/* Interrupt mask Register */
-#define DMA_DBTOSR  0x0c		/* Burst timeout status Register */
-#define DMA_DRTOSR  0x10		/* Request timeout Register */
-#define DMA_DSESR   0x14		/* Transfer Error Status Register */
-#define DMA_DBOSR   0x18		/* Buffer overflow status Register */
-#define DMA_DBTOCR  0x1c		/* Burst timeout control Register */
-#define DMA_WSRA    0x40		/* W-Size Register A */
-#define DMA_XSRA    0x44		/* X-Size Register A */
-#define DMA_YSRA    0x48		/* Y-Size Register A */
-#define DMA_WSRB    0x4c		/* W-Size Register B */
-#define DMA_XSRB    0x50		/* X-Size Register B */
-#define DMA_YSRB    0x54		/* Y-Size Register B */
-#define DMA_SAR(x)  (0x80 + ((x) << 6))	/* Source Address Registers */
-#define DMA_DAR(x)  (0x84 + ((x) << 6))	/* Destination Address Registers */
-#define DMA_CNTR(x) (0x88 + ((x) << 6))	/* Count Registers */
-#define DMA_CCR(x)  (0x8c + ((x) << 6))	/* Control Registers */
-#define DMA_RSSR(x) (0x90 + ((x) << 6))	/* Request source select Registers */
-#define DMA_BLR(x)  (0x94 + ((x) << 6))	/* Burst length Registers */
-#define DMA_RTOR(x) (0x98 + ((x) << 6))	/* Request timeout Registers */
-#define DMA_BUCR(x) (0x98 + ((x) << 6))	/* Bus Utilization Registers */
-#define DMA_CCNR(x) (0x9C + ((x) << 6))	/* Channel counter Registers */
-
-#define DCR_DRST           (1<<1)
-#define DCR_DEN            (1<<0)
-#define DBTOCR_EN          (1<<15)
-#define DBTOCR_CNT(x)      ((x) & 0x7fff)
-#define CNTR_CNT(x)        ((x) & 0xffffff)
-#define CCR_ACRPT          (1<<14)
-#define CCR_DMOD_LINEAR    (0x0 << 12)
-#define CCR_DMOD_2D        (0x1 << 12)
-#define CCR_DMOD_FIFO      (0x2 << 12)
-#define CCR_DMOD_EOBFIFO   (0x3 << 12)
-#define CCR_SMOD_LINEAR    (0x0 << 10)
-#define CCR_SMOD_2D        (0x1 << 10)
-#define CCR_SMOD_FIFO      (0x2 << 10)
-#define CCR_SMOD_EOBFIFO   (0x3 << 10)
-#define CCR_MDIR_DEC       (1<<9)
-#define CCR_MSEL_B         (1<<8)
-#define CCR_DSIZ_32        (0x0 << 6)
-#define CCR_DSIZ_8         (0x1 << 6)
-#define CCR_DSIZ_16        (0x2 << 6)
-#define CCR_SSIZ_32        (0x0 << 4)
-#define CCR_SSIZ_8         (0x1 << 4)
-#define CCR_SSIZ_16        (0x2 << 4)
-#define CCR_REN            (1<<3)
-#define CCR_RPT            (1<<2)
-#define CCR_FRC            (1<<1)
-#define CCR_CEN            (1<<0)
-#define RTOR_EN            (1<<15)
-#define RTOR_CLK           (1<<14)
-#define RTOR_PSC           (1<<13)
-
-/*
- * struct imx_dma_channel - i.MX specific DMA extension
- * @name: name specified by DMA client
- * @irq_handler: client callback for end of transfer
- * @err_handler: client callback for error condition
- * @data: clients context data for callbacks
- * @dma_mode: direction of the transfer %DMA_MODE_READ or %DMA_MODE_WRITE
- * @sg: pointer to the actual read/written chunk for scatter-gather emulation
- * @resbytes: total residual number of bytes to transfer
- *            (it can be lower or same as sum of SG mapped chunk sizes)
- * @sgcount: number of chunks to be read/written
- *
- * Structure is used for IMX DMA processing. It would be probably good
- * @struct dma_struct in the future for external interfacing and use
- * @struct imx_dma_channel only as extension to it.
- */
-
-struct imx_dma_channel {
-	const char *name;
-	void (*irq_handler) (int, void *);
-	void (*err_handler) (int, void *, int errcode);
-	void (*prog_handler) (int, void *, struct scatterlist *);
-	void *data;
-	unsigned int dma_mode;
-	struct scatterlist *sg;
-	unsigned int resbytes;
-	int dma_num;
-
-	int in_use;
-
-	u32 ccr_from_device;
-	u32 ccr_to_device;
-
-	struct timer_list watchdog;
-
-	int hw_chaining;
-};
-
-static void __iomem *imx_dmav1_baseaddr;
-
-static void imx_dmav1_writel(unsigned val, unsigned offset)
-{
-	__raw_writel(val, imx_dmav1_baseaddr + offset);
-}
-
-static unsigned imx_dmav1_readl(unsigned offset)
-{
-	return __raw_readl(imx_dmav1_baseaddr + offset);
-}
-
-static struct imx_dma_channel imx_dma_channels[IMX_DMA_CHANNELS];
-
-static struct clk *dma_clk;
-
-static int imx_dma_hw_chain(struct imx_dma_channel *imxdma)
-{
-	if (cpu_is_mx27())
-		return imxdma->hw_chaining;
-	else
-		return 0;
-}
-
-/*
- * imx_dma_sg_next - prepare next chunk for scatter-gather DMA emulation
- */
-static inline int imx_dma_sg_next(int channel, struct scatterlist *sg)
-{
-	struct imx_dma_channel *imxdma = &imx_dma_channels[channel];
-	unsigned long now;
-
-	if (!imxdma->name) {
-		printk(KERN_CRIT "%s: called for  not allocated channel %d\n",
-		       __func__, channel);
-		return 0;
-	}
-
-	now = min(imxdma->resbytes, sg->length);
-	if (imxdma->resbytes != IMX_DMA_LENGTH_LOOP)
-		imxdma->resbytes -= now;
-
-	if ((imxdma->dma_mode & DMA_MODE_MASK) == DMA_MODE_READ)
-		imx_dmav1_writel(sg->dma_address, DMA_DAR(channel));
-	else
-		imx_dmav1_writel(sg->dma_address, DMA_SAR(channel));
-
-	imx_dmav1_writel(now, DMA_CNTR(channel));
-
-	pr_debug("imxdma%d: next sg chunk dst 0x%08x, src 0x%08x, "
-		"size 0x%08x\n", channel,
-		 imx_dmav1_readl(DMA_DAR(channel)),
-		 imx_dmav1_readl(DMA_SAR(channel)),
-		 imx_dmav1_readl(DMA_CNTR(channel)));
-
-	return now;
-}
-
-/**
- * imx_dma_setup_single - setup i.MX DMA channel for linear memory to/from
- * device transfer
- *
- * @channel: i.MX DMA channel number
- * @dma_address: the DMA/physical memory address of the linear data block
- *		to transfer
- * @dma_length: length of the data block in bytes
- * @dev_addr: physical device port address
- * @dmamode: DMA transfer mode, %DMA_MODE_READ from the device to the memory
- *           or %DMA_MODE_WRITE from memory to the device
- *
- * Return value: if incorrect parameters are provided -%EINVAL.
- *		Zero indicates success.
- */
-int
-imx_dma_setup_single(int channel, dma_addr_t dma_address,
-		     unsigned int dma_length, unsigned int dev_addr,
-		     unsigned int dmamode)
-{
-	struct imx_dma_channel *imxdma = &imx_dma_channels[channel];
-
-	imxdma->sg = NULL;
-	imxdma->dma_mode = dmamode;
-
-	if (!dma_address) {
-		printk(KERN_ERR "imxdma%d: imx_dma_setup_single null address\n",
-		       channel);
-		return -EINVAL;
-	}
-
-	if (!dma_length) {
-		printk(KERN_ERR "imxdma%d: imx_dma_setup_single zero length\n",
-		       channel);
-		return -EINVAL;
-	}
-
-	if ((dmamode & DMA_MODE_MASK) == DMA_MODE_READ) {
-		pr_debug("imxdma%d: %s dma_addressg=0x%08x dma_length=%d "
-			"dev_addr=0x%08x for read\n",
-			channel, __func__, (unsigned int)dma_address,
-			dma_length, dev_addr);
-
-		imx_dmav1_writel(dev_addr, DMA_SAR(channel));
-		imx_dmav1_writel(dma_address, DMA_DAR(channel));
-		imx_dmav1_writel(imxdma->ccr_from_device, DMA_CCR(channel));
-	} else if ((dmamode & DMA_MODE_MASK) == DMA_MODE_WRITE) {
-		pr_debug("imxdma%d: %s dma_addressg=0x%08x dma_length=%d "
-			"dev_addr=0x%08x for write\n",
-			channel, __func__, (unsigned int)dma_address,
-			dma_length, dev_addr);
-
-		imx_dmav1_writel(dma_address, DMA_SAR(channel));
-		imx_dmav1_writel(dev_addr, DMA_DAR(channel));
-		imx_dmav1_writel(imxdma->ccr_to_device,
-				DMA_CCR(channel));
-	} else {
-		printk(KERN_ERR "imxdma%d: imx_dma_setup_single bad dmamode\n",
-		       channel);
-		return -EINVAL;
-	}
-
-	imx_dmav1_writel(dma_length, DMA_CNTR(channel));
-
-	return 0;
-}
-EXPORT_SYMBOL(imx_dma_setup_single);
-
-/**
- * imx_dma_setup_sg - setup i.MX DMA channel SG list to/from device transfer
- * @channel: i.MX DMA channel number
- * @sg: pointer to the scatter-gather list/vector
- * @sgcount: scatter-gather list hungs count
- * @dma_length: total length of the transfer request in bytes
- * @dev_addr: physical device port address
- * @dmamode: DMA transfer mode, %DMA_MODE_READ from the device to the memory
- *           or %DMA_MODE_WRITE from memory to the device
- *
- * The function sets up DMA channel state and registers to be ready for
- * transfer specified by provided parameters. The scatter-gather emulation
- * is set up according to the parameters.
- *
- * The full preparation of the transfer requires setup of more register
- * by the caller before imx_dma_enable() can be called.
- *
- * %BLR(channel) holds transfer burst length in bytes, 0 means 64 bytes
- *
- * %RSSR(channel) has to be set to the DMA request line source %DMA_REQ_xxx
- *
- * %CCR(channel) has to specify transfer parameters, the next settings is
- * typical for linear or simple scatter-gather transfers if %DMA_MODE_READ is
- * specified
- *
- * %CCR_DMOD_LINEAR | %CCR_DSIZ_32 | %CCR_SMOD_FIFO | %CCR_SSIZ_x
- *
- * The typical setup for %DMA_MODE_WRITE is specified by next options
- * combination
- *
- * %CCR_SMOD_LINEAR | %CCR_SSIZ_32 | %CCR_DMOD_FIFO | %CCR_DSIZ_x
- *
- * Be careful here and do not mistakenly mix source and target device
- * port sizes constants, they are really different:
- * %CCR_SSIZ_8, %CCR_SSIZ_16, %CCR_SSIZ_32,
- * %CCR_DSIZ_8, %CCR_DSIZ_16, %CCR_DSIZ_32
- *
- * Return value: if incorrect parameters are provided -%EINVAL.
- * Zero indicates success.
- */
-int
-imx_dma_setup_sg(int channel,
-		 struct scatterlist *sg, unsigned int sgcount,
-		 unsigned int dma_length, unsigned int dev_addr,
-		 unsigned int dmamode)
-{
-	struct imx_dma_channel *imxdma = &imx_dma_channels[channel];
-
-	if (imxdma->in_use)
-		return -EBUSY;
-
-	imxdma->sg = sg;
-	imxdma->dma_mode = dmamode;
-	imxdma->resbytes = dma_length;
-
-	if (!sg || !sgcount) {
-		printk(KERN_ERR "imxdma%d: imx_dma_setup_sg empty sg list\n",
-		       channel);
-		return -EINVAL;
-	}
-
-	if (!sg->length) {
-		printk(KERN_ERR "imxdma%d: imx_dma_setup_sg zero length\n",
-		       channel);
-		return -EINVAL;
-	}
-
-	if ((dmamode & DMA_MODE_MASK) == DMA_MODE_READ) {
-		pr_debug("imxdma%d: %s sg=%p sgcount=%d total length=%d "
-			"dev_addr=0x%08x for read\n",
-			channel, __func__, sg, sgcount, dma_length, dev_addr);
-
-		imx_dmav1_writel(dev_addr, DMA_SAR(channel));
-		imx_dmav1_writel(imxdma->ccr_from_device, DMA_CCR(channel));
-	} else if ((dmamode & DMA_MODE_MASK) == DMA_MODE_WRITE) {
-		pr_debug("imxdma%d: %s sg=%p sgcount=%d total length=%d "
-			"dev_addr=0x%08x for write\n",
-			channel, __func__, sg, sgcount, dma_length, dev_addr);
-
-		imx_dmav1_writel(dev_addr, DMA_DAR(channel));
-		imx_dmav1_writel(imxdma->ccr_to_device, DMA_CCR(channel));
-	} else {
-		printk(KERN_ERR "imxdma%d: imx_dma_setup_sg bad dmamode\n",
-		       channel);
-		return -EINVAL;
-	}
-
-	imx_dma_sg_next(channel, sg);
-
-	return 0;
-}
-EXPORT_SYMBOL(imx_dma_setup_sg);
-
-int
-imx_dma_config_channel(int channel, unsigned int config_port,
-	unsigned int config_mem, unsigned int dmareq, int hw_chaining)
-{
-	struct imx_dma_channel *imxdma = &imx_dma_channels[channel];
-	u32 dreq = 0;
-
-	imxdma->hw_chaining = 0;
-
-	if (hw_chaining) {
-		imxdma->hw_chaining = 1;
-		if (!imx_dma_hw_chain(imxdma))
-			return -EINVAL;
-	}
-
-	if (dmareq)
-		dreq = CCR_REN;
-
-	imxdma->ccr_from_device = config_port | (config_mem << 2) | dreq;
-	imxdma->ccr_to_device = config_mem | (config_port << 2) | dreq;
-
-	imx_dmav1_writel(dmareq, DMA_RSSR(channel));
-
-	return 0;
-}
-EXPORT_SYMBOL(imx_dma_config_channel);
-
-void imx_dma_config_burstlen(int channel, unsigned int burstlen)
-{
-	imx_dmav1_writel(burstlen, DMA_BLR(channel));
-}
-EXPORT_SYMBOL(imx_dma_config_burstlen);
-
-/**
- * imx_dma_setup_handlers - setup i.MX DMA channel end and error notification
- * handlers
- * @channel: i.MX DMA channel number
- * @irq_handler: the pointer to the function called if the transfer
- *		ends successfully
- * @err_handler: the pointer to the function called if the premature
- *		end caused by error occurs
- * @data: user specified value to be passed to the handlers
- */
-int
-imx_dma_setup_handlers(int channel,
-		       void (*irq_handler) (int, void *),
-		       void (*err_handler) (int, void *, int),
-		       void *data)
-{
-	struct imx_dma_channel *imxdma = &imx_dma_channels[channel];
-	unsigned long flags;
-
-	if (!imxdma->name) {
-		printk(KERN_CRIT "%s: called for  not allocated channel %d\n",
-		       __func__, channel);
-		return -ENODEV;
-	}
-
-	local_irq_save(flags);
-	imx_dmav1_writel(1 << channel, DMA_DISR);
-	imxdma->irq_handler = irq_handler;
-	imxdma->err_handler = err_handler;
-	imxdma->data = data;
-	local_irq_restore(flags);
-	return 0;
-}
-EXPORT_SYMBOL(imx_dma_setup_handlers);
-
-/**
- * imx_dma_setup_progression_handler - setup i.MX DMA channel progression
- * handlers
- * @channel: i.MX DMA channel number
- * @prog_handler: the pointer to the function called if the transfer progresses
- */
-int
-imx_dma_setup_progression_handler(int channel,
-			void (*prog_handler) (int, void*, struct scatterlist*))
-{
-	struct imx_dma_channel *imxdma = &imx_dma_channels[channel];
-	unsigned long flags;
-
-	if (!imxdma->name) {
-		printk(KERN_CRIT "%s: called for  not allocated channel %d\n",
-		       __func__, channel);
-		return -ENODEV;
-	}
-
-	local_irq_save(flags);
-	imxdma->prog_handler = prog_handler;
-	local_irq_restore(flags);
-	return 0;
-}
-EXPORT_SYMBOL(imx_dma_setup_progression_handler);
-
-/**
- * imx_dma_enable - function to start i.MX DMA channel operation
- * @channel: i.MX DMA channel number
- *
- * The channel has to be allocated by driver through imx_dma_request()
- * or imx_dma_request_by_prio() function.
- * The transfer parameters has to be set to the channel registers through
- * call of the imx_dma_setup_single() or imx_dma_setup_sg() function
- * and registers %BLR(channel), %RSSR(channel) and %CCR(channel) has to
- * be set prior this function call by the channel user.
- */
-void imx_dma_enable(int channel)
-{
-	struct imx_dma_channel *imxdma = &imx_dma_channels[channel];
-	unsigned long flags;
-
-	pr_debug("imxdma%d: imx_dma_enable\n", channel);
-
-	if (!imxdma->name) {
-		printk(KERN_CRIT "%s: called for  not allocated channel %d\n",
-		       __func__, channel);
-		return;
-	}
-
-	if (imxdma->in_use)
-		return;
-
-	local_irq_save(flags);
-
-	imx_dmav1_writel(1 << channel, DMA_DISR);
-	imx_dmav1_writel(imx_dmav1_readl(DMA_DIMR) & ~(1 << channel), DMA_DIMR);
-	imx_dmav1_writel(imx_dmav1_readl(DMA_CCR(channel)) | CCR_CEN |
-		CCR_ACRPT, DMA_CCR(channel));
-
-	if ((cpu_is_mx21() || cpu_is_mx27()) &&
-			imxdma->sg && imx_dma_hw_chain(imxdma)) {
-		imxdma->sg = sg_next(imxdma->sg);
-		if (imxdma->sg) {
-			u32 tmp;
-			imx_dma_sg_next(channel, imxdma->sg);
-			tmp = imx_dmav1_readl(DMA_CCR(channel));
-			imx_dmav1_writel(tmp | CCR_RPT | CCR_ACRPT,
-				DMA_CCR(channel));
-		}
-	}
-	imxdma->in_use = 1;
-
-	local_irq_restore(flags);
-}
-EXPORT_SYMBOL(imx_dma_enable);
-
-/**
- * imx_dma_disable - stop, finish i.MX DMA channel operatin
- * @channel: i.MX DMA channel number
- */
-void imx_dma_disable(int channel)
-{
-	struct imx_dma_channel *imxdma = &imx_dma_channels[channel];
-	unsigned long flags;
-
-	pr_debug("imxdma%d: imx_dma_disable\n", channel);
-
-	if (imx_dma_hw_chain(imxdma))
-		del_timer(&imxdma->watchdog);
-
-	local_irq_save(flags);
-	imx_dmav1_writel(imx_dmav1_readl(DMA_DIMR) | (1 << channel), DMA_DIMR);
-	imx_dmav1_writel(imx_dmav1_readl(DMA_CCR(channel)) & ~CCR_CEN,
-			DMA_CCR(channel));
-	imx_dmav1_writel(1 << channel, DMA_DISR);
-	imxdma->in_use = 0;
-	local_irq_restore(flags);
-}
-EXPORT_SYMBOL(imx_dma_disable);
-
-static void imx_dma_watchdog(unsigned long chno)
-{
-	struct imx_dma_channel *imxdma = &imx_dma_channels[chno];
-
-	imx_dmav1_writel(0, DMA_CCR(chno));
-	imxdma->in_use = 0;
-	imxdma->sg = NULL;
-
-	if (imxdma->err_handler)
-		imxdma->err_handler(chno, imxdma->data, IMX_DMA_ERR_TIMEOUT);
-}
-
-static irqreturn_t dma_err_handler(int irq, void *dev_id)
-{
-	int i, disr;
-	struct imx_dma_channel *imxdma;
-	unsigned int err_mask;
-	int errcode;
-
-	disr = imx_dmav1_readl(DMA_DISR);
-
-	err_mask = imx_dmav1_readl(DMA_DBTOSR) |
-		   imx_dmav1_readl(DMA_DRTOSR) |
-		   imx_dmav1_readl(DMA_DSESR)  |
-		   imx_dmav1_readl(DMA_DBOSR);
-
-	if (!err_mask)
-		return IRQ_HANDLED;
-
-	imx_dmav1_writel(disr & err_mask, DMA_DISR);
-
-	for (i = 0; i < IMX_DMA_CHANNELS; i++) {
-		if (!(err_mask & (1 << i)))
-			continue;
-		imxdma = &imx_dma_channels[i];
-		errcode = 0;
-
-		if (imx_dmav1_readl(DMA_DBTOSR) & (1 << i)) {
-			imx_dmav1_writel(1 << i, DMA_DBTOSR);
-			errcode |= IMX_DMA_ERR_BURST;
-		}
-		if (imx_dmav1_readl(DMA_DRTOSR) & (1 << i)) {
-			imx_dmav1_writel(1 << i, DMA_DRTOSR);
-			errcode |= IMX_DMA_ERR_REQUEST;
-		}
-		if (imx_dmav1_readl(DMA_DSESR) & (1 << i)) {
-			imx_dmav1_writel(1 << i, DMA_DSESR);
-			errcode |= IMX_DMA_ERR_TRANSFER;
-		}
-		if (imx_dmav1_readl(DMA_DBOSR) & (1 << i)) {
-			imx_dmav1_writel(1 << i, DMA_DBOSR);
-			errcode |= IMX_DMA_ERR_BUFFER;
-		}
-		if (imxdma->name && imxdma->err_handler) {
-			imxdma->err_handler(i, imxdma->data, errcode);
-			continue;
-		}
-
-		imx_dma_channels[i].sg = NULL;
-
-		printk(KERN_WARNING
-		       "DMA timeout on channel %d (%s) -%s%s%s%s\n",
-		       i, imxdma->name,
-		       errcode & IMX_DMA_ERR_BURST ?    " burst" : "",
-		       errcode & IMX_DMA_ERR_REQUEST ?  " request" : "",
-		       errcode & IMX_DMA_ERR_TRANSFER ? " transfer" : "",
-		       errcode & IMX_DMA_ERR_BUFFER ?   " buffer" : "");
-	}
-	return IRQ_HANDLED;
-}
-
-static void dma_irq_handle_channel(int chno)
-{
-	struct imx_dma_channel *imxdma = &imx_dma_channels[chno];
-
-	if (!imxdma->name) {
-		/*
-		 * IRQ for an unregistered DMA channel:
-		 * let's clear the interrupts and disable it.
-		 */
-		printk(KERN_WARNING
-		       "spurious IRQ for DMA channel %d\n", chno);
-		return;
-	}
-
-	if (imxdma->sg) {
-		u32 tmp;
-		struct scatterlist *current_sg = imxdma->sg;
-		imxdma->sg = sg_next(imxdma->sg);
-
-		if (imxdma->sg) {
-			imx_dma_sg_next(chno, imxdma->sg);
-
-			tmp = imx_dmav1_readl(DMA_CCR(chno));
-
-			if (imx_dma_hw_chain(imxdma)) {
-				/* FIXME: The timeout should probably be
-				 * configurable
-				 */
-				mod_timer(&imxdma->watchdog,
-					jiffies + msecs_to_jiffies(500));
-
-				tmp |= CCR_CEN | CCR_RPT | CCR_ACRPT;
-				imx_dmav1_writel(tmp, DMA_CCR(chno));
-			} else {
-				imx_dmav1_writel(tmp & ~CCR_CEN, DMA_CCR(chno));
-				tmp |= CCR_CEN;
-			}
-
-			imx_dmav1_writel(tmp, DMA_CCR(chno));
-
-			if (imxdma->prog_handler)
-				imxdma->prog_handler(chno, imxdma->data,
-						current_sg);
-
-			return;
-		}
-
-		if (imx_dma_hw_chain(imxdma)) {
-			del_timer(&imxdma->watchdog);
-			return;
-		}
-	}
-
-	imx_dmav1_writel(0, DMA_CCR(chno));
-	imxdma->in_use = 0;
-	if (imxdma->irq_handler)
-		imxdma->irq_handler(chno, imxdma->data);
-}
-
-static irqreturn_t dma_irq_handler(int irq, void *dev_id)
-{
-	int i, disr;
-
-	if (cpu_is_mx21() || cpu_is_mx27())
-		dma_err_handler(irq, dev_id);
-
-	disr = imx_dmav1_readl(DMA_DISR);
-
-	pr_debug("imxdma: dma_irq_handler called, disr=0x%08x\n",
-		     disr);
-
-	imx_dmav1_writel(disr, DMA_DISR);
-	for (i = 0; i < IMX_DMA_CHANNELS; i++) {
-		if (disr & (1 << i))
-			dma_irq_handle_channel(i);
-	}
-
-	return IRQ_HANDLED;
-}
-
-/**
- * imx_dma_request - request/allocate specified channel number
- * @channel: i.MX DMA channel number
- * @name: the driver/caller own non-%NULL identification
- */
-int imx_dma_request(int channel, const char *name)
-{
-	struct imx_dma_channel *imxdma = &imx_dma_channels[channel];
-	unsigned long flags;
-	int ret = 0;
-
-	/* basic sanity checks */
-	if (!name)
-		return -EINVAL;
-
-	if (channel >= IMX_DMA_CHANNELS) {
-		printk(KERN_CRIT "%s: called for  non-existed channel %d\n",
-		       __func__, channel);
-		return -EINVAL;
-	}
-
-	local_irq_save(flags);
-	if (imxdma->name) {
-		local_irq_restore(flags);
-		return -EBUSY;
-	}
-	memset(imxdma, 0, sizeof(*imxdma));
-	imxdma->name = name;
-	local_irq_restore(flags); /* request_irq() can block */
-
-	if (cpu_is_mx21() || cpu_is_mx27()) {
-		ret = request_irq(MX2x_INT_DMACH0 + channel,
-				dma_irq_handler, 0, "DMA", NULL);
-		if (ret) {
-			imxdma->name = NULL;
-			pr_crit("Can't register IRQ %d for DMA channel %d\n",
-					MX2x_INT_DMACH0 + channel, channel);
-			return ret;
-		}
-		init_timer(&imxdma->watchdog);
-		imxdma->watchdog.function = &imx_dma_watchdog;
-		imxdma->watchdog.data = channel;
-	}
-
-	return ret;
-}
-EXPORT_SYMBOL(imx_dma_request);
-
-/**
- * imx_dma_free - release previously acquired channel
- * @channel: i.MX DMA channel number
- */
-void imx_dma_free(int channel)
-{
-	unsigned long flags;
-	struct imx_dma_channel *imxdma = &imx_dma_channels[channel];
-
-	if (!imxdma->name) {
-		printk(KERN_CRIT
-		       "%s: trying to free free channel %d\n",
-		       __func__, channel);
-		return;
-	}
-
-	local_irq_save(flags);
-	/* Disable interrupts */
-	imx_dma_disable(channel);
-	imxdma->name = NULL;
-
-	if (cpu_is_mx21() || cpu_is_mx27())
-		free_irq(MX2x_INT_DMACH0 + channel, NULL);
-
-	local_irq_restore(flags);
-}
-EXPORT_SYMBOL(imx_dma_free);
-
-/**
- * imx_dma_request_by_prio - find and request some of free channels best
- * suiting requested priority
- * @channel: i.MX DMA channel number
- * @name: the driver/caller own non-%NULL identification
- *
- * This function tries to find a free channel in the specified priority group
- * if the priority cannot be achieved it tries to look for free channel
- * in the higher and then even lower priority groups.
- *
- * Return value: If there is no free channel to allocate, -%ENODEV is returned.
- *               On successful allocation channel is returned.
- */
-int imx_dma_request_by_prio(const char *name, enum imx_dma_prio prio)
-{
-	int i;
-	int best;
-
-	switch (prio) {
-	case (DMA_PRIO_HIGH):
-		best = 8;
-		break;
-	case (DMA_PRIO_MEDIUM):
-		best = 4;
-		break;
-	case (DMA_PRIO_LOW):
-	default:
-		best = 0;
-		break;
-	}
-
-	for (i = best; i < IMX_DMA_CHANNELS; i++)
-		if (!imx_dma_request(i, name))
-			return i;
-
-	for (i = best - 1; i >= 0; i--)
-		if (!imx_dma_request(i, name))
-			return i;
-
-	printk(KERN_ERR "%s: no free DMA channel found\n", __func__);
-
-	return -ENODEV;
-}
-EXPORT_SYMBOL(imx_dma_request_by_prio);
-
-static int __init imx_dma_init(void)
-{
-	int ret = 0;
-	int i;
-
-	if (cpu_is_mx1())
-		imx_dmav1_baseaddr = MX1_IO_ADDRESS(MX1_DMA_BASE_ADDR);
-	else if (cpu_is_mx21())
-		imx_dmav1_baseaddr = MX21_IO_ADDRESS(MX21_DMA_BASE_ADDR);
-	else if (cpu_is_mx27())
-		imx_dmav1_baseaddr = MX27_IO_ADDRESS(MX27_DMA_BASE_ADDR);
-	else
-		return 0;
-
-	dma_clk = clk_get(NULL, "dma");
-	if (IS_ERR(dma_clk))
-		return PTR_ERR(dma_clk);
-	clk_enable(dma_clk);
-
-	/* reset DMA module */
-	imx_dmav1_writel(DCR_DRST, DMA_DCR);
-
-	if (cpu_is_mx1()) {
-		ret = request_irq(MX1_DMA_INT, dma_irq_handler, 0, "DMA", NULL);
-		if (ret) {
-			pr_crit("Wow!  Can't register IRQ for DMA\n");
-			return ret;
-		}
-
-		ret = request_irq(MX1_DMA_ERR, dma_err_handler, 0, "DMA", NULL);
-		if (ret) {
-			pr_crit("Wow!  Can't register ERRIRQ for DMA\n");
-			free_irq(MX1_DMA_INT, NULL);
-			return ret;
-		}
-	}
-
-	/* enable DMA module */
-	imx_dmav1_writel(DCR_DEN, DMA_DCR);
-
-	/* clear all interrupts */
-	imx_dmav1_writel((1 << IMX_DMA_CHANNELS) - 1, DMA_DISR);
-
-	/* disable interrupts */
-	imx_dmav1_writel((1 << IMX_DMA_CHANNELS) - 1, DMA_DIMR);
-
-	for (i = 0; i < IMX_DMA_CHANNELS; i++) {
-		imx_dma_channels[i].sg = NULL;
-		imx_dma_channels[i].dma_num = i;
-	}
-
-	return ret;
-}
-
-arch_initcall(imx_dma_init);
diff --git a/arch/arm/mach-imx/include/mach/dma-v1.h b/arch/arm/mach-imx/include/mach/dma-v1.h
deleted file mode 100644
index ac6fd71..0000000
--- a/arch/arm/mach-imx/include/mach/dma-v1.h
+++ /dev/null
@@ -1,103 +0,0 @@
-/*
- *  linux/arch/arm/mach-imx/include/mach/dma-v1.h
- *
- *  i.MX DMA registration and IRQ dispatching
- *
- * Copyright 2006 Pavel Pisa <pisa@cmp.felk.cvut.cz>
- * Copyright 2008 Juergen Beisert, <kernel@pengutronix.de>
- * Copyright 2008 Sascha Hauer, <s.hauer@pengutronix.de>
- *
- * 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., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
-
-#ifndef __MACH_DMA_V1_H__
-#define __MACH_DMA_V1_H__
-
-#define imx_has_dma_v1()	(cpu_is_mx1() || cpu_is_mx21() || cpu_is_mx27())
-
-#include <mach/dma.h>
-
-#define IMX_DMA_CHANNELS  16
-
-#define DMA_MODE_READ		0
-#define DMA_MODE_WRITE		1
-#define DMA_MODE_MASK		1
-
-#define MX1_DMA_REG(offset)	MX1_IO_ADDRESS(MX1_DMA_BASE_ADDR + (offset))
-
-/* DMA Interrupt Mask Register */
-#define MX1_DMA_DIMR		MX1_DMA_REG(0x08)
-
-/* Channel Control Register */
-#define MX1_DMA_CCR(x)		MX1_DMA_REG(0x8c + ((x) << 6))
-
-#define IMX_DMA_MEMSIZE_32	(0 << 4)
-#define IMX_DMA_MEMSIZE_8	(1 << 4)
-#define IMX_DMA_MEMSIZE_16	(2 << 4)
-#define IMX_DMA_TYPE_LINEAR	(0 << 10)
-#define IMX_DMA_TYPE_2D		(1 << 10)
-#define IMX_DMA_TYPE_FIFO	(2 << 10)
-
-#define IMX_DMA_ERR_BURST     (1 << 0)
-#define IMX_DMA_ERR_REQUEST   (1 << 1)
-#define IMX_DMA_ERR_TRANSFER  (1 << 2)
-#define IMX_DMA_ERR_BUFFER    (1 << 3)
-#define IMX_DMA_ERR_TIMEOUT   (1 << 4)
-
-int
-imx_dma_config_channel(int channel, unsigned int config_port,
-	unsigned int config_mem, unsigned int dmareq, int hw_chaining);
-
-void
-imx_dma_config_burstlen(int channel, unsigned int burstlen);
-
-int
-imx_dma_setup_single(int channel, dma_addr_t dma_address,
-		unsigned int dma_length, unsigned int dev_addr,
-		unsigned int dmamode);
-
-
-/*
- * Use this flag as the dma_length argument to imx_dma_setup_sg()
- * to create an endless running dma loop. The end of the scatterlist
- * must be linked to the beginning for this to work.
- */
-#define IMX_DMA_LENGTH_LOOP	((unsigned int)-1)
-
-int
-imx_dma_setup_sg(int channel, struct scatterlist *sg,
-		unsigned int sgcount, unsigned int dma_length,
-		unsigned int dev_addr, unsigned int dmamode);
-
-int
-imx_dma_setup_handlers(int channel,
-		void (*irq_handler) (int, void *),
-		void (*err_handler) (int, void *, int), void *data);
-
-int
-imx_dma_setup_progression_handler(int channel,
-		void (*prog_handler) (int, void*, struct scatterlist*));
-
-void imx_dma_enable(int channel);
-
-void imx_dma_disable(int channel);
-
-int imx_dma_request(int channel, const char *name);
-
-void imx_dma_free(int channel);
-
-int imx_dma_request_by_prio(const char *name, enum imx_dma_prio prio);
-
-#endif	/* __MACH_DMA_V1_H__ */
diff --git a/arch/arm/mach-imx/mm-imx3.c b/arch/arm/mach-imx/mm-imx3.c
index f8ca96c..d534d7f 100644
--- a/arch/arm/mach-imx/mm-imx3.c
+++ b/arch/arm/mach-imx/mm-imx3.c
@@ -61,8 +61,8 @@
 		: "=r" (reg));
 }
 
-static void __iomem *imx3_ioremap(unsigned long phys_addr, size_t size,
-				  unsigned int mtype)
+static void __iomem *imx3_ioremap_caller(unsigned long phys_addr, size_t size,
+					 unsigned int mtype, void *caller)
 {
 	if (mtype == MT_DEVICE) {
 		/*
@@ -75,7 +75,7 @@
 			mtype = MT_DEVICE_NONSHARED;
 	}
 
-	return __arm_ioremap(phys_addr, size, mtype);
+	return __arm_ioremap_caller(phys_addr, size, mtype, caller);
 }
 
 void __init imx3_init_l2x0(void)
@@ -134,7 +134,7 @@
 {
 	mxc_set_cpu_type(MXC_CPU_MX31);
 	mxc_arch_reset_init(MX31_IO_ADDRESS(MX31_WDOG_BASE_ADDR));
-	imx_ioremap = imx3_ioremap;
+	arch_ioremap_caller = imx3_ioremap_caller;
 	arm_pm_idle = imx3_idle;
 }
 
@@ -208,7 +208,7 @@
 	mxc_iomux_v3_init(MX35_IO_ADDRESS(MX35_IOMUXC_BASE_ADDR));
 	mxc_arch_reset_init(MX35_IO_ADDRESS(MX35_WDOG_BASE_ADDR));
 	arm_pm_idle = imx3_idle;
-	imx_ioremap = imx3_ioremap;
+	arch_ioremap_caller = imx3_ioremap_caller;
 }
 
 void __init mx35_init_irq(void)
diff --git a/arch/arm/mach-integrator/core.c b/arch/arm/mach-integrator/core.c
index 1a65d77..eaf6c63 100644
--- a/arch/arm/mach-integrator/core.c
+++ b/arch/arm/mach-integrator/core.c
@@ -25,8 +25,9 @@
 
 #include <mach/hardware.h>
 #include <mach/platform.h>
-#include <asm/irq.h>
 #include <mach/cm.h>
+#include <mach/irqs.h>
+
 #include <asm/leds.h>
 #include <asm/mach-types.h>
 #include <asm/mach/time.h>
diff --git a/arch/arm/mach-integrator/include/mach/io.h b/arch/arm/mach-integrator/include/mach/io.h
index 37beed3..8de70de 100644
--- a/arch/arm/mach-integrator/include/mach/io.h
+++ b/arch/arm/mach-integrator/include/mach/io.h
@@ -29,6 +29,5 @@
 #define PCI_IO_VADDR            0xee000000
 
 #define __io(a)			((void __iomem *)(PCI_IO_VADDR + (a)))
-#define __mem_pci(a)		(a)
 
 #endif
diff --git a/arch/arm/mach-integrator/include/mach/irqs.h b/arch/arm/mach-integrator/include/mach/irqs.h
index 1fbe6d1..a19a1a2 100644
--- a/arch/arm/mach-integrator/include/mach/irqs.h
+++ b/arch/arm/mach-integrator/include/mach/irqs.h
@@ -78,5 +78,6 @@
 #define IRQ_SIC_CP_LMINT7		46
 #define IRQ_SIC_END			46
 
-#define NR_IRQS                         47
+#define NR_IRQS_INTEGRATOR_AP		34
+#define NR_IRQS_INTEGRATOR_CP		47
 
diff --git a/arch/arm/mach-integrator/integrator_ap.c b/arch/arm/mach-integrator/integrator_ap.c
index 21a1d6c..871f148 100644
--- a/arch/arm/mach-integrator/integrator_ap.c
+++ b/arch/arm/mach-integrator/integrator_ap.c
@@ -38,12 +38,13 @@
 #include <mach/hardware.h>
 #include <mach/platform.h>
 #include <asm/hardware/arm_timer.h>
-#include <asm/irq.h>
 #include <asm/setup.h>
 #include <asm/param.h>		/* HZ */
 #include <asm/mach-types.h>
+#include <asm/sched_clock.h>
 
 #include <mach/lm.h>
+#include <mach/irqs.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach/irq.h>
@@ -325,6 +326,11 @@
 
 static unsigned long timer_reload;
 
+static u32 notrace integrator_read_sched_clock(void)
+{
+	return -readl((void __iomem *) TIMER2_VA_BASE + TIMER_VALUE);
+}
+
 static void integrator_clocksource_init(unsigned long inrate)
 {
 	void __iomem *base = (void __iomem *)TIMER2_VA_BASE;
@@ -341,6 +347,7 @@
 
 	clocksource_mmio_init(base + TIMER_VALUE, "timer2",
 			rate, 200, 16, clocksource_mmio_readl_down);
+	setup_sched_clock(integrator_read_sched_clock, 16, rate);
 }
 
 static void __iomem * const clkevt_base = (void __iomem *)TIMER1_VA_BASE;
@@ -468,6 +475,7 @@
 	.atag_offset	= 0x100,
 	.reserve	= integrator_reserve,
 	.map_io		= ap_map_io,
+	.nr_irqs	= NR_IRQS_INTEGRATOR_AP,
 	.init_early	= integrator_init_early,
 	.init_irq	= ap_init_irq,
 	.timer		= &ap_timer,
diff --git a/arch/arm/mach-integrator/integrator_cp.c b/arch/arm/mach-integrator/integrator_cp.c
index be9ead4..48a115a 100644
--- a/arch/arm/mach-integrator/integrator_cp.c
+++ b/arch/arm/mach-integrator/integrator_cp.c
@@ -26,7 +26,6 @@
 
 #include <mach/hardware.h>
 #include <mach/platform.h>
-#include <asm/irq.h>
 #include <asm/setup.h>
 #include <asm/mach-types.h>
 #include <asm/hardware/arm_timer.h>
@@ -34,6 +33,7 @@
 
 #include <mach/cm.h>
 #include <mach/lm.h>
+#include <mach/irqs.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach/irq.h>
@@ -464,6 +464,7 @@
 	.atag_offset	= 0x100,
 	.reserve	= integrator_reserve,
 	.map_io		= intcp_map_io,
+	.nr_irqs	= NR_IRQS_INTEGRATOR_CP,
 	.init_early	= intcp_init_early,
 	.init_irq	= intcp_init_irq,
 	.timer		= &cp_timer,
diff --git a/arch/arm/mach-integrator/pci.c b/arch/arm/mach-integrator/pci.c
index 36068f4..f1ca9c1 100644
--- a/arch/arm/mach-integrator/pci.c
+++ b/arch/arm/mach-integrator/pci.c
@@ -26,10 +26,11 @@
 #include <linux/interrupt.h>
 #include <linux/init.h>
 
-#include <asm/irq.h>
 #include <asm/mach/pci.h>
 #include <asm/mach-types.h>
 
+#include <mach/irqs.h>
+
 /* 
  * A small note about bridges and interrupts.  The DECchip 21050 (and
  * later) adheres to the PCI-PCI bridge specification.  This says that
diff --git a/arch/arm/mach-integrator/pci_v3.c b/arch/arm/mach-integrator/pci_v3.c
index 4be172c..67e6f9a 100644
--- a/arch/arm/mach-integrator/pci_v3.c
+++ b/arch/arm/mach-integrator/pci_v3.c
@@ -30,7 +30,8 @@
 
 #include <mach/hardware.h>
 #include <mach/platform.h>
-#include <asm/irq.h>
+#include <mach/irqs.h>
+
 #include <asm/signal.h>
 #include <asm/mach/pci.h>
 #include <asm/irq_regs.h>
diff --git a/arch/arm/mach-iop13xx/include/mach/io.h b/arch/arm/mach-iop13xx/include/mach/io.h
index dffb234..f131885 100644
--- a/arch/arm/mach-iop13xx/include/mach/io.h
+++ b/arch/arm/mach-iop13xx/include/mach/io.h
@@ -22,20 +22,7 @@
 #define IO_SPACE_LIMIT 0xffffffff
 
 #define __io(a) __iop13xx_io(a)
-#define __mem_pci(a) (a)
-#define __mem_isa(a) (a)
 
 extern void __iomem * __iop13xx_io(unsigned long io_addr);
-extern void __iomem *__iop13xx_ioremap(unsigned long cookie, size_t size,
-	unsigned int mtype);
-extern void __iop13xx_iounmap(void __iomem *addr);
-
-extern u32 iop13xx_atue_mem_base;
-extern u32 iop13xx_atux_mem_base;
-extern size_t iop13xx_atue_mem_size;
-extern size_t iop13xx_atux_mem_size;
-
-#define __arch_ioremap	__iop13xx_ioremap
-#define __arch_iounmap	__iop13xx_iounmap
 
 #endif
diff --git a/arch/arm/mach-iop13xx/include/mach/iop13xx.h b/arch/arm/mach-iop13xx/include/mach/iop13xx.h
index 07e9ff7..e190dcd 100644
--- a/arch/arm/mach-iop13xx/include/mach/iop13xx.h
+++ b/arch/arm/mach-iop13xx/include/mach/iop13xx.h
@@ -5,6 +5,7 @@
 /* The ATU offsets can change based on the strapping */
 extern u32 iop13xx_atux_pmmr_offset;
 extern u32 iop13xx_atue_pmmr_offset;
+void iop13xx_init_early(void);
 void iop13xx_init_irq(void);
 void iop13xx_map_io(void);
 void iop13xx_platform_init(void);
diff --git a/arch/arm/mach-iop13xx/io.c b/arch/arm/mach-iop13xx/io.c
index 48642e6..3c36419 100644
--- a/arch/arm/mach-iop13xx/io.c
+++ b/arch/arm/mach-iop13xx/io.c
@@ -21,6 +21,8 @@
 #include <linux/io.h>
 #include <mach/hardware.h>
 
+#include "pci.h"
+
 void * __iomem __iop13xx_io(unsigned long io_addr)
 {
 	void __iomem * io_virt;
@@ -40,8 +42,8 @@
 }
 EXPORT_SYMBOL(__iop13xx_io);
 
-void * __iomem __iop13xx_ioremap(unsigned long cookie, size_t size,
-	unsigned int mtype)
+static void __iomem *__iop13xx_ioremap_caller(unsigned long cookie,
+	size_t size, unsigned int mtype, void *caller)
 {
 	void __iomem * retval;
 
@@ -76,17 +78,14 @@
 		break;
 	default:
 		retval = __arm_ioremap_caller(cookie, size, mtype,
-				__builtin_return_address(0));
+				caller);
 	}
 
 	return retval;
 }
-EXPORT_SYMBOL(__iop13xx_ioremap);
 
-void __iop13xx_iounmap(void __iomem *addr)
+static void __iop13xx_iounmap(volatile void __iomem *addr)
 {
-	extern void __iounmap(volatile void __iomem *addr);
-
 	if (iop13xx_atue_mem_base)
 		if (addr >= (void __iomem *) iop13xx_atue_mem_base &&
 	 	    addr < (void __iomem *) (iop13xx_atue_mem_base +
@@ -110,4 +109,9 @@
 skip:
 	return;
 }
-EXPORT_SYMBOL(__iop13xx_iounmap);
+
+void __init iop13xx_init_early(void)
+{
+	arch_ioremap_caller = __iop13xx_ioremap_caller;
+	arch_iounmap = __iop13xx_iounmap;
+}
diff --git a/arch/arm/mach-iop13xx/iq81340mc.c b/arch/arm/mach-iop13xx/iq81340mc.c
index abaee88..5c96b73 100644
--- a/arch/arm/mach-iop13xx/iq81340mc.c
+++ b/arch/arm/mach-iop13xx/iq81340mc.c
@@ -92,6 +92,7 @@
 MACHINE_START(IQ81340MC, "Intel IQ81340MC")
 	/* Maintainer: Dan Williams <dan.j.williams@intel.com> */
 	.atag_offset    = 0x100,
+	.init_early     = iop13xx_init_early,
 	.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 690916a..aa4dd75 100644
--- a/arch/arm/mach-iop13xx/iq81340sc.c
+++ b/arch/arm/mach-iop13xx/iq81340sc.c
@@ -94,6 +94,7 @@
 MACHINE_START(IQ81340SC, "Intel IQ81340SC")
 	/* Maintainer: Dan Williams <dan.j.williams@intel.com> */
 	.atag_offset    = 0x100,
+	.init_early     = iop13xx_init_early,
 	.map_io         = iop13xx_map_io,
 	.init_irq       = iop13xx_init_irq,
 	.timer          = &iq81340sc_timer,
diff --git a/arch/arm/mach-iop13xx/pci.h b/arch/arm/mach-iop13xx/pci.h
new file mode 100644
index 0000000..c70cf5b4
--- /dev/null
+++ b/arch/arm/mach-iop13xx/pci.h
@@ -0,0 +1,6 @@
+#include <linux/types.h>
+
+extern u32 iop13xx_atue_mem_base;
+extern u32 iop13xx_atux_mem_base;
+extern size_t iop13xx_atue_mem_size;
+extern size_t iop13xx_atux_mem_size;
diff --git a/arch/arm/mach-iop32x/include/mach/io.h b/arch/arm/mach-iop32x/include/mach/io.h
index 2d88264..e2ada26 100644
--- a/arch/arm/mach-iop32x/include/mach/io.h
+++ b/arch/arm/mach-iop32x/include/mach/io.h
@@ -15,6 +15,5 @@
 
 #define IO_SPACE_LIMIT		0xffffffff
 #define __io(p)		((void __iomem *)IOP3XX_PCI_IO_PHYS_TO_VIRT(p))
-#define __mem_pci(a)		(a)
 
 #endif
diff --git a/arch/arm/mach-iop33x/include/mach/io.h b/arch/arm/mach-iop33x/include/mach/io.h
index a8a66fc..f7c1b65 100644
--- a/arch/arm/mach-iop33x/include/mach/io.h
+++ b/arch/arm/mach-iop33x/include/mach/io.h
@@ -15,6 +15,5 @@
 
 #define IO_SPACE_LIMIT		0xffffffff
 #define __io(p)		((void __iomem *)IOP3XX_PCI_IO_PHYS_TO_VIRT(p))
-#define __mem_pci(a)		(a)
 
 #endif
diff --git a/arch/arm/mach-ixp2000/include/mach/io.h b/arch/arm/mach-ixp2000/include/mach/io.h
index 859e5849..f6552d6 100644
--- a/arch/arm/mach-ixp2000/include/mach/io.h
+++ b/arch/arm/mach-ixp2000/include/mach/io.h
@@ -18,7 +18,6 @@
 #include <mach/hardware.h>
 
 #define IO_SPACE_LIMIT		0xffffffff
-#define __mem_pci(a)		(a)
 
 /*
  * The A? revisions of the IXP2000s assert byte lanes for PCI I/O
diff --git a/arch/arm/mach-ixp23xx/include/mach/io.h b/arch/arm/mach-ixp23xx/include/mach/io.h
index 4ce4353..a7aceb5 100644
--- a/arch/arm/mach-ixp23xx/include/mach/io.h
+++ b/arch/arm/mach-ixp23xx/include/mach/io.h
@@ -18,6 +18,5 @@
 #define IO_SPACE_LIMIT 0xffffffff
 
 #define __io(p)		((void __iomem*)((p) + IXP23XX_PCI_IO_VIRT))
-#define __mem_pci(a)	(a)
 
 #endif
diff --git a/arch/arm/mach-ixp4xx/avila-setup.c b/arch/arm/mach-ixp4xx/avila-setup.c
index a7277ad..90e42e9 100644
--- a/arch/arm/mach-ixp4xx/avila-setup.c
+++ b/arch/arm/mach-ixp4xx/avila-setup.c
@@ -165,6 +165,7 @@
 MACHINE_START(AVILA, "Gateworks Avila Network Platform")
 	/* Maintainer: Deepak Saxena <dsaxena@plexity.net> */
 	.map_io		= ixp4xx_map_io,
+	.init_early	= ixp4xx_init_early,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
 	.atag_offset	= 0x100,
@@ -184,6 +185,7 @@
 MACHINE_START(LOFT, "Giant Shoulder Inc Loft board")
 	/* Maintainer: Tom Billman <kernel@giantshoulderinc.com> */
 	.map_io		= ixp4xx_map_io,
+	.init_early	= ixp4xx_init_early,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
 	.atag_offset	= 0x100,
diff --git a/arch/arm/mach-ixp4xx/common.c b/arch/arm/mach-ixp4xx/common.c
index a6329a0..c60e7b8 100644
--- a/arch/arm/mach-ixp4xx/common.c
+++ b/arch/arm/mach-ixp4xx/common.c
@@ -31,6 +31,7 @@
 
 #include <mach/udc.h>
 #include <mach/hardware.h>
+#include <mach/io.h>
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/page.h>
@@ -517,3 +518,35 @@
 		*IXP4XX_OSWE = IXP4XX_WDT_RESET_ENABLE | IXP4XX_WDT_COUNT_ENABLE;
 	}
 }
+
+#ifdef CONFIG_IXP4XX_INDIRECT_PCI
+/*
+ * In the case of using indirect PCI, we simply return the actual PCI
+ * address and our read/write implementation use that to drive the
+ * access registers. If something outside of PCI is ioremap'd, we
+ * fallback to the default.
+ */
+
+static void __iomem *ixp4xx_ioremap_caller(unsigned long addr, size_t size,
+					   unsigned int mtype, void *caller)
+{
+	if (!is_pci_memory(addr))
+		return __arm_ioremap_caller(addr, size, mtype, caller);
+
+	return (void __iomem *)addr;
+}
+
+static void ixp4xx_iounmap(void __iomem *addr)
+{
+	if (!is_pci_memory((__force u32)addr))
+		__iounmap(addr);
+}
+
+void __init ixp4xx_init_early(void)
+{
+	arch_ioremap_caller = ixp4xx_ioremap_caller;
+	arch_iounmap = ixp4xx_iounmap;
+}
+#else
+void __init ixp4xx_init_early(void) {}
+#endif
diff --git a/arch/arm/mach-ixp4xx/coyote-setup.c b/arch/arm/mach-ixp4xx/coyote-setup.c
index a74f86c..1b83110 100644
--- a/arch/arm/mach-ixp4xx/coyote-setup.c
+++ b/arch/arm/mach-ixp4xx/coyote-setup.c
@@ -110,6 +110,7 @@
 MACHINE_START(ADI_COYOTE, "ADI Engineering Coyote")
 	/* Maintainer: MontaVista Software, Inc. */
 	.map_io		= ixp4xx_map_io,
+	.init_early	= ixp4xx_init_early,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
 	.atag_offset	= 0x100,
@@ -129,6 +130,7 @@
 MACHINE_START(IXDPG425, "Intel IXDPG425")
 	/* Maintainer: MontaVista Software, Inc. */
 	.map_io		= ixp4xx_map_io,
+	.init_early	= ixp4xx_init_early,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
 	.atag_offset	= 0x100,
diff --git a/arch/arm/mach-ixp4xx/dsmg600-setup.c b/arch/arm/mach-ixp4xx/dsmg600-setup.c
index 67be177..97a0af8 100644
--- a/arch/arm/mach-ixp4xx/dsmg600-setup.c
+++ b/arch/arm/mach-ixp4xx/dsmg600-setup.c
@@ -280,6 +280,7 @@
 	/* Maintainer: www.nslu2-linux.org */
 	.atag_offset	= 0x100,
 	.map_io		= ixp4xx_map_io,
+	.init_early	= ixp4xx_init_early,
 	.init_irq	= ixp4xx_init_irq,
 	.timer          = &dsmg600_timer,
 	.init_machine	= dsmg600_init,
diff --git a/arch/arm/mach-ixp4xx/fsg-setup.c b/arch/arm/mach-ixp4xx/fsg-setup.c
index 6d58182..9175a25 100644
--- a/arch/arm/mach-ixp4xx/fsg-setup.c
+++ b/arch/arm/mach-ixp4xx/fsg-setup.c
@@ -270,6 +270,7 @@
 MACHINE_START(FSG, "Freecom FSG-3")
 	/* Maintainer: www.nslu2-linux.org */
 	.map_io		= ixp4xx_map_io,
+	.init_early	= ixp4xx_init_early,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
 	.atag_offset	= 0x100,
diff --git a/arch/arm/mach-ixp4xx/gateway7001-setup.c b/arch/arm/mach-ixp4xx/gateway7001-setup.c
index 7ecf9b2..033c717 100644
--- a/arch/arm/mach-ixp4xx/gateway7001-setup.c
+++ b/arch/arm/mach-ixp4xx/gateway7001-setup.c
@@ -97,6 +97,7 @@
 MACHINE_START(GATEWAY7001, "Gateway 7001 AP")
 	/* Maintainer: Imre Kaloz <kaloz@openwrt.org> */
 	.map_io		= ixp4xx_map_io,
+	.init_early	= ixp4xx_init_early,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
 	.atag_offset	= 0x100,
diff --git a/arch/arm/mach-ixp4xx/goramo_mlr.c b/arch/arm/mach-ixp4xx/goramo_mlr.c
index 78ae12c..46bb924 100644
--- a/arch/arm/mach-ixp4xx/goramo_mlr.c
+++ b/arch/arm/mach-ixp4xx/goramo_mlr.c
@@ -496,6 +496,7 @@
 MACHINE_START(GORAMO_MLR, "MultiLink")
 	/* Maintainer: Krzysztof Halasa */
 	.map_io		= ixp4xx_map_io,
+	.init_early	= ixp4xx_init_early,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
 	.atag_offset	= 0x100,
diff --git a/arch/arm/mach-ixp4xx/gtwx5715-setup.c b/arch/arm/mach-ixp4xx/gtwx5715-setup.c
index a23f893..18ebc6b 100644
--- a/arch/arm/mach-ixp4xx/gtwx5715-setup.c
+++ b/arch/arm/mach-ixp4xx/gtwx5715-setup.c
@@ -165,6 +165,7 @@
 MACHINE_START(GTWX5715, "Gemtek GTWX5715 (Linksys WRV54G)")
 	/* Maintainer: George Joseph */
 	.map_io		= ixp4xx_map_io,
+	.init_early	= ixp4xx_init_early,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
 	.atag_offset	= 0x100,
diff --git a/arch/arm/mach-ixp4xx/include/mach/hardware.h b/arch/arm/mach-ixp4xx/include/mach/hardware.h
index c30e7e9..034bb2a 100644
--- a/arch/arm/mach-ixp4xx/include/mach/hardware.h
+++ b/arch/arm/mach-ixp4xx/include/mach/hardware.h
@@ -23,8 +23,6 @@
 #define PCIBIOS_MAX_MEM		0x4BFFFFFF
 #endif
 
-#define ARCH_HAS_DMA_SET_COHERENT_MASK
-
 /* Register locations and bits */
 #include "ixp4xx-regs.h"
 
diff --git a/arch/arm/mach-ixp4xx/include/mach/io.h b/arch/arm/mach-ixp4xx/include/mach/io.h
index ffb9d6a..5cf30d1 100644
--- a/arch/arm/mach-ixp4xx/include/mach/io.h
+++ b/arch/arm/mach-ixp4xx/include/mach/io.h
@@ -39,11 +39,7 @@
  *    but in some cases the performance hit is acceptable. In addition, you
  *    cannot mmap() PCI devices in this case.
  */
-#ifndef	CONFIG_IXP4XX_INDIRECT_PCI
-
-#define __mem_pci(a)		(a)
-
-#else
+#ifdef	CONFIG_IXP4XX_INDIRECT_PCI
 
 /*
  * In the case of using indirect PCI, we simply return the actual PCI
@@ -57,24 +53,6 @@
 	return (addr >= PCIBIOS_MIN_MEM) && (addr <= 0x4FFFFFFF);
 }
 
-static inline void __iomem * __indirect_ioremap(unsigned long addr, size_t size,
-						unsigned int mtype)
-{
-	if (!is_pci_memory(addr))
-		return __arm_ioremap(addr, size, mtype);
-
-	return (void __iomem *)addr;
-}
-
-static inline void __indirect_iounmap(void __iomem *addr)
-{
-	if (!is_pci_memory((__force u32)addr))
-		__iounmap(addr);
-}
-
-#define __arch_ioremap			__indirect_ioremap
-#define __arch_iounmap			__indirect_iounmap
-
 #define writeb(v, p)			__indirect_writeb(v, p)
 #define writew(v, p)			__indirect_writew(v, p)
 #define writel(v, p)			__indirect_writel(v, p)
diff --git a/arch/arm/mach-ixp4xx/include/mach/platform.h b/arch/arm/mach-ixp4xx/include/mach/platform.h
index df9250b..b66bedc 100644
--- a/arch/arm/mach-ixp4xx/include/mach/platform.h
+++ b/arch/arm/mach-ixp4xx/include/mach/platform.h
@@ -121,6 +121,7 @@
  * Functions used by platform-level setup code
  */
 extern void ixp4xx_map_io(void);
+extern void ixp4xx_init_early(void);
 extern void ixp4xx_init_irq(void);
 extern void ixp4xx_sys_init(void);
 extern void ixp4xx_timer_init(void);
diff --git a/arch/arm/mach-ixp4xx/ixdp425-setup.c b/arch/arm/mach-ixp4xx/ixdp425-setup.c
index 8a38b39..3d742ae 100644
--- a/arch/arm/mach-ixp4xx/ixdp425-setup.c
+++ b/arch/arm/mach-ixp4xx/ixdp425-setup.c
@@ -254,6 +254,7 @@
 MACHINE_START(IXDP425, "Intel IXDP425 Development Platform")
 	/* Maintainer: MontaVista Software, Inc. */
 	.map_io		= ixp4xx_map_io,
+	.init_early	= ixp4xx_init_early,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
 	.atag_offset	= 0x100,
@@ -269,6 +270,7 @@
 MACHINE_START(IXDP465, "Intel IXDP465 Development Platform")
 	/* Maintainer: MontaVista Software, Inc. */
 	.map_io		= ixp4xx_map_io,
+	.init_early	= ixp4xx_init_early,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
 	.atag_offset	= 0x100,
@@ -283,6 +285,7 @@
 MACHINE_START(IXCDP1100, "Intel IXCDP1100 Development Platform")
 	/* Maintainer: MontaVista Software, Inc. */
 	.map_io		= ixp4xx_map_io,
+	.init_early	= ixp4xx_init_early,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
 	.atag_offset	= 0x100,
@@ -297,6 +300,7 @@
 MACHINE_START(KIXRP435, "Intel KIXRP435 Reference Platform")
 	/* Maintainer: MontaVista Software, Inc. */
 	.map_io		= ixp4xx_map_io,
+	.init_early	= ixp4xx_init_early,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
 	.atag_offset	= 0x100,
diff --git a/arch/arm/mach-ixp4xx/nas100d-setup.c b/arch/arm/mach-ixp4xx/nas100d-setup.c
index 1010eb7b..33cb095 100644
--- a/arch/arm/mach-ixp4xx/nas100d-setup.c
+++ b/arch/arm/mach-ixp4xx/nas100d-setup.c
@@ -315,6 +315,7 @@
 	/* Maintainer: www.nslu2-linux.org */
 	.atag_offset	= 0x100,
 	.map_io		= ixp4xx_map_io,
+	.init_early	= ixp4xx_init_early,
 	.init_irq	= ixp4xx_init_irq,
 	.timer          = &ixp4xx_timer,
 	.init_machine	= nas100d_init,
diff --git a/arch/arm/mach-ixp4xx/nslu2-setup.c b/arch/arm/mach-ixp4xx/nslu2-setup.c
index aa355c3..e2903fa 100644
--- a/arch/arm/mach-ixp4xx/nslu2-setup.c
+++ b/arch/arm/mach-ixp4xx/nslu2-setup.c
@@ -301,6 +301,7 @@
 	/* Maintainer: www.nslu2-linux.org */
 	.atag_offset	= 0x100,
 	.map_io		= ixp4xx_map_io,
+	.init_early	= ixp4xx_init_early,
 	.init_irq	= ixp4xx_init_irq,
 	.timer          = &nslu2_timer,
 	.init_machine	= nslu2_init,
diff --git a/arch/arm/mach-ixp4xx/omixp-setup.c b/arch/arm/mach-ixp4xx/omixp-setup.c
index 0940869..158ddb7 100644
--- a/arch/arm/mach-ixp4xx/omixp-setup.c
+++ b/arch/arm/mach-ixp4xx/omixp-setup.c
@@ -243,6 +243,7 @@
 MACHINE_START(DEVIXP, "Omicron DEVIXP")
 	.atag_offset    = 0x100,
 	.map_io		= ixp4xx_map_io,
+	.init_early	= ixp4xx_init_early,
 	.init_irq	= ixp4xx_init_irq,
 	.timer          = &ixp4xx_timer,
 	.init_machine	= omixp_init,
@@ -254,6 +255,7 @@
 MACHINE_START(MICCPT, "Omicron MICCPT")
 	.atag_offset    = 0x100,
 	.map_io		= ixp4xx_map_io,
+	.init_early	= ixp4xx_init_early,
 	.init_irq	= ixp4xx_init_irq,
 	.timer          = &ixp4xx_timer,
 	.init_machine	= omixp_init,
@@ -268,6 +270,7 @@
 MACHINE_START(MIC256, "Omicron MIC256")
 	.atag_offset    = 0x100,
 	.map_io		= ixp4xx_map_io,
+	.init_early	= ixp4xx_init_early,
 	.init_irq	= ixp4xx_init_irq,
 	.timer          = &ixp4xx_timer,
 	.init_machine	= omixp_init,
diff --git a/arch/arm/mach-ixp4xx/vulcan-setup.c b/arch/arm/mach-ixp4xx/vulcan-setup.c
index 9dec206..2798f43 100644
--- a/arch/arm/mach-ixp4xx/vulcan-setup.c
+++ b/arch/arm/mach-ixp4xx/vulcan-setup.c
@@ -237,6 +237,7 @@
 MACHINE_START(ARCOM_VULCAN, "Arcom/Eurotech Vulcan")
 	/* Maintainer: Marc Zyngier <maz@misterjones.org> */
 	.map_io		= ixp4xx_map_io,
+	.init_early	= ixp4xx_init_early,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
 	.atag_offset	= 0x100,
diff --git a/arch/arm/mach-ixp4xx/wg302v2-setup.c b/arch/arm/mach-ixp4xx/wg302v2-setup.c
index 5ac0f0a..a785175 100644
--- a/arch/arm/mach-ixp4xx/wg302v2-setup.c
+++ b/arch/arm/mach-ixp4xx/wg302v2-setup.c
@@ -98,6 +98,7 @@
 MACHINE_START(WG302V2, "Netgear WG302 v2 / WAG302 v2")
 	/* Maintainer: Imre Kaloz <kaloz@openwrt.org> */
 	.map_io		= ixp4xx_map_io,
+	.init_early	= ixp4xx_init_early,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
 	.atag_offset	= 0x100,
diff --git a/arch/arm/mach-kirkwood/include/mach/io.h b/arch/arm/mach-kirkwood/include/mach/io.h
index 49dd0cb5..5d0ab617 100644
--- a/arch/arm/mach-kirkwood/include/mach/io.h
+++ b/arch/arm/mach-kirkwood/include/mach/io.h
@@ -20,7 +20,5 @@
 }
 
 #define __io(a)			__io(a)
-#define __mem_pci(a)		(a)
-
 
 #endif
diff --git a/arch/arm/mach-ks8695/include/mach/io.h b/arch/arm/mach-ks8695/include/mach/io.h
deleted file mode 100644
index a7a63ac3..0000000
--- a/arch/arm/mach-ks8695/include/mach/io.h
+++ /dev/null
@@ -1,19 +0,0 @@
-/*
- * arch/arm/mach-ks8695/include/mach/io.h
- *
- * Copyright (C) 2006 Andrew Victor
- *
- * This file is licensed under  the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- */
-
-#ifndef __ASM_ARCH_IO_H
-#define __ASM_ARCH_IO_H
-
-#define IO_SPACE_LIMIT		0xffffffff
-
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
-
-#endif
diff --git a/arch/arm/mach-lpc32xx/clock.c b/arch/arm/mach-lpc32xx/clock.c
index b7ef511..2fc24ca 100644
--- a/arch/arm/mach-lpc32xx/clock.c
+++ b/arch/arm/mach-lpc32xx/clock.c
@@ -1134,7 +1134,7 @@
 	_REGISTER_CLOCK(NULL, "i2s1_ck", clk_i2s1)
 	_REGISTER_CLOCK("ts-lpc32xx", NULL, clk_tsc)
 	_REGISTER_CLOCK("dev:mmc0", NULL, clk_mmc)
-	_REGISTER_CLOCK("lpc-net.0", NULL, clk_net)
+	_REGISTER_CLOCK("lpc-eth.0", NULL, clk_net)
 	_REGISTER_CLOCK("dev:clcd", NULL, clk_lcd)
 	_REGISTER_CLOCK("lpc32xx_udc", "ck_usbd", clk_usbd)
 	_REGISTER_CLOCK("lpc32xx_rtc", NULL, clk_rtc)
diff --git a/arch/arm/mach-lpc32xx/include/mach/io.h b/arch/arm/mach-lpc32xx/include/mach/io.h
deleted file mode 100644
index 9b59ab5..0000000
--- a/arch/arm/mach-lpc32xx/include/mach/io.h
+++ /dev/null
@@ -1,27 +0,0 @@
-/*
- * arch/arm/mach-lpc32xx/include/mach/io.h
- *
- * Author: Kevin Wells <kevin.wells@nxp.com>
- *
- * Copyright (C) 2010 NXP Semiconductors
- *
- * 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.
- */
-
-#ifndef __ASM_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H
-
-#define IO_SPACE_LIMIT	0xffffffff
-
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
-
-#endif
diff --git a/arch/arm/mach-mmp/aspenite.c b/arch/arm/mach-mmp/aspenite.c
index 3588a55..bf5d8e1 100644
--- a/arch/arm/mach-mmp/aspenite.c
+++ b/arch/arm/mach-mmp/aspenite.c
@@ -23,6 +23,7 @@
 #include <mach/addr-map.h>
 #include <mach/mfp-pxa168.h>
 #include <mach/pxa168.h>
+#include <mach/irqs.h>
 #include <video/pxa168fb.h>
 #include <linux/input.h>
 #include <plat/pxa27x_keypad.h>
@@ -239,7 +240,7 @@
 
 MACHINE_START(ASPENITE, "PXA168-based Aspenite Development Platform")
 	.map_io		= mmp_map_io,
-	.nr_irqs	= IRQ_BOARD_START,
+	.nr_irqs	= MMP_NR_IRQS,
 	.init_irq       = pxa168_init_irq,
 	.timer          = &pxa168_timer,
 	.init_machine   = common_init,
@@ -248,7 +249,7 @@
 
 MACHINE_START(ZYLONITE2, "PXA168-based Zylonite2 Development Platform")
 	.map_io		= mmp_map_io,
-	.nr_irqs	= IRQ_BOARD_START,
+	.nr_irqs	= MMP_NR_IRQS,
 	.init_irq       = pxa168_init_irq,
 	.timer          = &pxa168_timer,
 	.init_machine   = common_init,
diff --git a/arch/arm/mach-mmp/avengers_lite.c b/arch/arm/mach-mmp/avengers_lite.c
index b148a9d..603542a 100644
--- a/arch/arm/mach-mmp/avengers_lite.c
+++ b/arch/arm/mach-mmp/avengers_lite.c
@@ -43,6 +43,7 @@
 
 MACHINE_START(AVENGERS_LITE, "PXA168 Avengers lite Development Platform")
 	.map_io		= mmp_map_io,
+	.nr_irqs	= MMP_NR_IRQS,
 	.init_irq       = pxa168_init_irq,
 	.timer          = &pxa168_timer,
 	.init_machine   = avengers_lite_init,
diff --git a/arch/arm/mach-mmp/brownstone.c b/arch/arm/mach-mmp/brownstone.c
index d839fe6..5cb769c 100644
--- a/arch/arm/mach-mmp/brownstone.c
+++ b/arch/arm/mach-mmp/brownstone.c
@@ -28,7 +28,7 @@
 
 #include "common.h"
 
-#define BROWNSTONE_NR_IRQS	(IRQ_BOARD_START + 40)
+#define BROWNSTONE_NR_IRQS	(MMP_NR_IRQS + 40)
 
 #define GPIO_5V_ENABLE		(89)
 
@@ -158,7 +158,7 @@
 };
 
 static struct max8925_platform_data brownstone_max8925_info = {
-	.irq_base		= IRQ_BOARD_START,
+	.irq_base		= MMP_NR_IRQS,
 };
 
 static struct i2c_board_info brownstone_twsi1_info[] = {
diff --git a/arch/arm/mach-mmp/flint.c b/arch/arm/mach-mmp/flint.c
index 2ee8cd7..8059cc0 100644
--- a/arch/arm/mach-mmp/flint.c
+++ b/arch/arm/mach-mmp/flint.c
@@ -23,10 +23,11 @@
 #include <mach/addr-map.h>
 #include <mach/mfp-mmp2.h>
 #include <mach/mmp2.h>
+#include <mach/irqs.h>
 
 #include "common.h"
 
-#define FLINT_NR_IRQS	(IRQ_BOARD_START + 48)
+#define FLINT_NR_IRQS	(MMP_NR_IRQS + 48)
 
 static unsigned long flint_pin_config[] __initdata = {
 	/* UART1 */
diff --git a/arch/arm/mach-mmp/gplugd.c b/arch/arm/mach-mmp/gplugd.c
index 8776546..f516e74 100644
--- a/arch/arm/mach-mmp/gplugd.c
+++ b/arch/arm/mach-mmp/gplugd.c
@@ -191,7 +191,7 @@
 
 MACHINE_START(GPLUGD, "PXA168-based GuruPlug Display (gplugD) Platform")
 	.map_io		= mmp_map_io,
-	.nr_irqs	= IRQ_BOARD_START,
+	.nr_irqs	= MMP_NR_IRQS,
 	.init_irq       = pxa168_init_irq,
 	.timer          = &pxa168_timer,
 	.init_machine   = gplugd_init,
diff --git a/arch/arm/mach-mmp/include/mach/addr-map.h b/arch/arm/mach-mmp/include/mach/addr-map.h
index 3e404ac..b1ece08 100644
--- a/arch/arm/mach-mmp/include/mach/addr-map.h
+++ b/arch/arm/mach-mmp/include/mach/addr-map.h
@@ -11,12 +11,6 @@
 #ifndef __ASM_MACH_ADDR_MAP_H
 #define __ASM_MACH_ADDR_MAP_H
 
-#ifndef __ASSEMBLER__
-#define IOMEM(x)	((void __iomem *)(x))
-#else
-#define IOMEM(x)	(x)
-#endif
-
 /* APB - Application Subsystem Peripheral Bus
  *
  * NOTE: the DMA controller registers are actually on the AXI fabric #1
diff --git a/arch/arm/mach-mmp/include/mach/io.h b/arch/arm/mach-mmp/include/mach/io.h
deleted file mode 100644
index e7adf3d..0000000
--- a/arch/arm/mach-mmp/include/mach/io.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/*
- * linux/arch/arm/mach-mmp/include/mach/io.h
- *
- * 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_MACH_IO_H
-#define __ASM_MACH_IO_H
-
-#define IO_SPACE_LIMIT 0xffffffff
-
-/*
- * We don't actually have real ISA nor PCI buses, but there is so many
- * drivers out there that might just work if we fake them...
- */
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
-
-#endif /* __ASM_MACH_IO_H */
diff --git a/arch/arm/mach-mmp/include/mach/irqs.h b/arch/arm/mach-mmp/include/mach/irqs.h
index 34635a0..d0e7466 100644
--- a/arch/arm/mach-mmp/include/mach/irqs.h
+++ b/arch/arm/mach-mmp/include/mach/irqs.h
@@ -223,7 +223,6 @@
 #define MMP_GPIO_TO_IRQ(gpio)		(IRQ_GPIO_START + (gpio))
 
 #define IRQ_BOARD_START			(IRQ_GPIO_START + MMP_NR_BUILTIN_GPIO)
-
-#define NR_IRQS				(IRQ_BOARD_START)
+#define MMP_NR_IRQS			IRQ_BOARD_START
 
 #endif /* __ASM_MACH_IRQS_H */
diff --git a/arch/arm/mach-mmp/irq-mmp2.c b/arch/arm/mach-mmp/irq-mmp2.c
index d21c544..7895d27 100644
--- a/arch/arm/mach-mmp/irq-mmp2.c
+++ b/arch/arm/mach-mmp/irq-mmp2.c
@@ -15,6 +15,7 @@
 #include <linux/irq.h>
 #include <linux/io.h>
 
+#include <mach/irqs.h>
 #include <mach/regs-icu.h>
 #include <mach/mmp2.h>
 
diff --git a/arch/arm/mach-mmp/jasper.c b/arch/arm/mach-mmp/jasper.c
index 96cf5c8..ff73249 100644
--- a/arch/arm/mach-mmp/jasper.c
+++ b/arch/arm/mach-mmp/jasper.c
@@ -19,6 +19,7 @@
 #include <linux/mfd/max8925.h>
 #include <linux/interrupt.h>
 
+#include <mach/irqs.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 #include <mach/addr-map.h>
@@ -27,7 +28,7 @@
 
 #include "common.h"
 
-#define JASPER_NR_IRQS		(IRQ_BOARD_START + 48)
+#define JASPER_NR_IRQS		(MMP_NR_IRQS + 48)
 
 static unsigned long jasper_pin_config[] __initdata = {
 	/* UART1 */
@@ -135,7 +136,7 @@
 static struct max8925_platform_data jasper_max8925_info = {
 	.backlight		= &jasper_backlight_data,
 	.power			= &jasper_power_data,
-	.irq_base		= IRQ_BOARD_START,
+	.irq_base		= MMP_NR_IRQS,
 };
 
 static struct i2c_board_info jasper_twsi1_info[] = {
diff --git a/arch/arm/mach-mmp/tavorevb.c b/arch/arm/mach-mmp/tavorevb.c
index bc97170..b28f908 100644
--- a/arch/arm/mach-mmp/tavorevb.c
+++ b/arch/arm/mach-mmp/tavorevb.c
@@ -101,6 +101,7 @@
 
 MACHINE_START(TAVOREVB, "PXA910 Evaluation Board (aka TavorEVB)")
 	.map_io		= mmp_map_io,
+	.nr_irqs	= MMP_NR_IRQS,
 	.init_irq       = pxa910_init_irq,
 	.timer          = &pxa910_timer,
 	.init_machine   = tavorevb_init,
diff --git a/arch/arm/mach-mmp/teton_bga.c b/arch/arm/mach-mmp/teton_bga.c
index 0523e42..42bef66 100644
--- a/arch/arm/mach-mmp/teton_bga.c
+++ b/arch/arm/mach-mmp/teton_bga.c
@@ -26,6 +26,7 @@
 #include <mach/mfp-pxa168.h>
 #include <mach/pxa168.h>
 #include <mach/teton_bga.h>
+#include <mach/irqs.h>
 
 #include "common.h"
 
@@ -83,7 +84,7 @@
 
 MACHINE_START(TETON_BGA, "PXA168-based Teton BGA Development Platform")
 	.map_io		= mmp_map_io,
-	.nr_irqs	= IRQ_BOARD_START,
+	.nr_irqs	= MMP_NR_IRQS,
 	.init_irq       = pxa168_init_irq,
 	.timer          = &pxa168_timer,
 	.init_machine   = teton_bga_init,
diff --git a/arch/arm/mach-mmp/ttc_dkb.c b/arch/arm/mach-mmp/ttc_dkb.c
index e72c709d..3fc9ed2 100644
--- a/arch/arm/mach-mmp/ttc_dkb.c
+++ b/arch/arm/mach-mmp/ttc_dkb.c
@@ -38,7 +38,7 @@
  * 16 board interrupts -- PCA9575 GPIO expander
  * 24 board interrupts -- 88PM860x PMIC
  */
-#define TTCDKB_NR_IRQS		(IRQ_BOARD_START + 16 + 16 + 24)
+#define TTCDKB_NR_IRQS		(MMP_NR_IRQS + 16 + 16 + 24)
 
 static unsigned long ttc_dkb_pin_config[] __initdata = {
 	/* UART2 */
@@ -131,7 +131,7 @@
 static struct pca953x_platform_data max7312_data[] = {
 	{
 		.gpio_base	= TTCDKB_GPIO_EXT0(0),
-		.irq_base	= IRQ_BOARD_START,
+		.irq_base	= MMP_NR_IRQS,
 	},
 };
 
diff --git a/arch/arm/mach-msm/board-halibut.c b/arch/arm/mach-msm/board-halibut.c
index a60ab6d..3698a37 100644
--- a/arch/arm/mach-msm/board-halibut.c
+++ b/arch/arm/mach-msm/board-halibut.c
@@ -68,6 +68,11 @@
 
 extern struct sys_timer msm_timer;
 
+static void __init halibut_init_early(void)
+{
+	arch_ioremap_caller = __msm_ioremap_caller;
+}
+
 static void __init halibut_init_irq(void)
 {
 	msm_init_irq();
@@ -96,6 +101,7 @@
 	.atag_offset	= 0x100,
 	.fixup		= halibut_fixup,
 	.map_io		= halibut_map_io,
+	.init_early	= halibut_init_early,
 	.init_irq	= halibut_init_irq,
 	.init_machine	= halibut_init,
 	.timer		= &msm_timer,
diff --git a/arch/arm/mach-msm/board-trout.c b/arch/arm/mach-msm/board-trout.c
index 6b9b227..5414f76 100644
--- a/arch/arm/mach-msm/board-trout.c
+++ b/arch/arm/mach-msm/board-trout.c
@@ -43,6 +43,11 @@
 
 extern struct sys_timer msm_timer;
 
+static void __init trout_init_early(void)
+{
+	arch_ioremap_caller = __msm_ioremap_caller;
+}
+
 static void __init trout_init_irq(void)
 {
 	msm_init_irq();
@@ -96,6 +101,7 @@
 	.atag_offset	= 0x100,
 	.fixup		= trout_fixup,
 	.map_io		= trout_map_io,
+	.init_early	= trout_init_early,
 	.init_irq	= trout_init_irq,
 	.init_machine	= trout_init,
 	.timer		= &msm_timer,
diff --git a/arch/arm/mach-msm/include/mach/io.h b/arch/arm/mach-msm/include/mach/io.h
deleted file mode 100644
index dc1b928..0000000
--- a/arch/arm/mach-msm/include/mach/io.h
+++ /dev/null
@@ -1,36 +0,0 @@
-/* arch/arm/mach-msm/include/mach/io.h
- *
- * Copyright (C) 2007 Google, Inc.
- *
- * 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 __ASM_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H
-
-#define IO_SPACE_LIMIT 0xffffffff
-
-#define __arch_ioremap __msm_ioremap
-#define __arch_iounmap __iounmap
-
-void __iomem *__msm_ioremap(unsigned long phys_addr, size_t size, unsigned int mtype);
-
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)    (a)
-
-void msm_map_qsd8x50_io(void);
-void msm_map_msm7x30_io(void);
-void msm_map_msm8x60_io(void);
-void msm_map_msm8960_io(void);
-
-extern unsigned int msm_shared_ram_phys;
-
-#endif
diff --git a/arch/arm/mach-msm/include/mach/msm_iomap-7x00.h b/arch/arm/mach-msm/include/mach/msm_iomap-7x00.h
index 8af4612..6c4046c 100644
--- a/arch/arm/mach-msm/include/mach/msm_iomap-7x00.h
+++ b/arch/arm/mach-msm/include/mach/msm_iomap-7x00.h
@@ -38,12 +38,6 @@
  *
  */
 
-#ifdef __ASSEMBLY__
-#define IOMEM(x)	x
-#else
-#define IOMEM(x)	((void __force __iomem *)(x))
-#endif
-
 #define MSM_VIC_BASE          IOMEM(0xE0000000)
 #define MSM_VIC_PHYS          0xC0000000
 #define MSM_VIC_SIZE          SZ_4K
@@ -111,5 +105,11 @@
 #define MSM_AD5_PHYS          0xAC000000
 #define MSM_AD5_SIZE          (SZ_1M*13)
 
+#ifndef __ASSEMBLY__
+
+extern void __iomem *__msm_ioremap_caller(unsigned long phys_addr, size_t size,
+					  unsigned int mtype, void *caller);
+
+#endif
 
 #endif
diff --git a/arch/arm/mach-msm/include/mach/msm_iomap-7x30.h b/arch/arm/mach-msm/include/mach/msm_iomap-7x30.h
index 198202c..f944fe6 100644
--- a/arch/arm/mach-msm/include/mach/msm_iomap-7x30.h
+++ b/arch/arm/mach-msm/include/mach/msm_iomap-7x30.h
@@ -100,4 +100,8 @@
 #define MSM_HSUSB_PHYS        0xA3600000
 #define MSM_HSUSB_SIZE        SZ_1K
 
+#ifndef __ASSEMBLY__
+extern void msm_map_msm7x30_io(void);
+#endif
+
 #endif
diff --git a/arch/arm/mach-msm/include/mach/msm_iomap-8960.h b/arch/arm/mach-msm/include/mach/msm_iomap-8960.h
index 800b557..a1752c0 100644
--- a/arch/arm/mach-msm/include/mach/msm_iomap-8960.h
+++ b/arch/arm/mach-msm/include/mach/msm_iomap-8960.h
@@ -50,4 +50,8 @@
 #define MSM_DEBUG_UART_PHYS	0x16440000
 #endif
 
+#ifndef __ASSEMBLY__
+extern void msm_map_msm8960_io(void);
+#endif
+
 #endif
diff --git a/arch/arm/mach-msm/include/mach/msm_iomap-8x50.h b/arch/arm/mach-msm/include/mach/msm_iomap-8x50.h
index 0faa894..da77cc1d 100644
--- a/arch/arm/mach-msm/include/mach/msm_iomap-8x50.h
+++ b/arch/arm/mach-msm/include/mach/msm_iomap-8x50.h
@@ -122,4 +122,8 @@
 #define MSM_SDC4_PHYS          0xA0600000
 #define MSM_SDC4_SIZE          SZ_4K
 
+#ifndef __ASSEMBLY__
+extern void msm_map_qsd8x50_io(void);
+#endif
+
 #endif
diff --git a/arch/arm/mach-msm/include/mach/msm_iomap-8x60.h b/arch/arm/mach-msm/include/mach/msm_iomap-8x60.h
index 54e12ca..5aed57d 100644
--- a/arch/arm/mach-msm/include/mach/msm_iomap-8x60.h
+++ b/arch/arm/mach-msm/include/mach/msm_iomap-8x60.h
@@ -67,4 +67,8 @@
 #define MSM_DEBUG_UART_PHYS	0x19C40000
 #endif
 
+#ifndef __ASSEMBLY__
+extern void msm_map_msm8x60_io(void);
+#endif
+
 #endif
diff --git a/arch/arm/mach-msm/include/mach/msm_iomap.h b/arch/arm/mach-msm/include/mach/msm_iomap.h
index 90682f4..00afdfb 100644
--- a/arch/arm/mach-msm/include/mach/msm_iomap.h
+++ b/arch/arm/mach-msm/include/mach/msm_iomap.h
@@ -37,12 +37,6 @@
  *
  */
 
-#ifdef __ASSEMBLY__
-#define IOMEM(x)	x
-#else
-#define IOMEM(x)	((void __force __iomem *)(x))
-#endif
-
 #if defined(CONFIG_ARCH_MSM7X30)
 #include "msm_iomap-7x30.h"
 #elif defined(CONFIG_ARCH_QSD8X50)
diff --git a/arch/arm/mach-msm/io.c b/arch/arm/mach-msm/io.c
index 578b04e..a1e7b11 100644
--- a/arch/arm/mach-msm/io.c
+++ b/arch/arm/mach-msm/io.c
@@ -172,8 +172,8 @@
 }
 #endif /* CONFIG_ARCH_MSM7X30 */
 
-void __iomem *
-__msm_ioremap(unsigned long phys_addr, size_t size, unsigned int mtype)
+void __iomem *__msm_ioremap_caller(unsigned long phys_addr, size_t size,
+				   unsigned int mtype, void *caller)
 {
 	if (mtype == MT_DEVICE) {
 		/* The peripherals in the 88000000 - D0000000 range
@@ -184,7 +184,5 @@
 			mtype = MT_DEVICE_NONSHARED;
 	}
 
-	return __arm_ioremap_caller(phys_addr, size, mtype,
-		__builtin_return_address(0));
+	return __arm_ioremap_caller(phys_addr, size, mtype, caller);
 }
-EXPORT_SYMBOL(__msm_ioremap);
diff --git a/arch/arm/mach-msm/timer.c b/arch/arm/mach-msm/timer.c
index 75f4be4..81280825 100644
--- a/arch/arm/mach-msm/timer.c
+++ b/arch/arm/mach-msm/timer.c
@@ -24,6 +24,7 @@
 #include <asm/mach/time.h>
 #include <asm/hardware/gic.h>
 #include <asm/localtimer.h>
+#include <asm/sched_clock.h>
 
 #include <mach/msm_iomap.h>
 #include <mach/cpu.h>
@@ -105,12 +106,12 @@
 
 static void __iomem *source_base;
 
-static cycle_t msm_read_timer_count(struct clocksource *cs)
+static notrace cycle_t msm_read_timer_count(struct clocksource *cs)
 {
 	return readl_relaxed(source_base + TIMER_COUNT_VAL);
 }
 
-static cycle_t msm_read_timer_count_shift(struct clocksource *cs)
+static notrace cycle_t msm_read_timer_count_shift(struct clocksource *cs)
 {
 	/*
 	 * Shift timer count down by a constant due to unreliable lower bits
@@ -166,6 +167,11 @@
 };
 #endif /* CONFIG_LOCAL_TIMERS */
 
+static notrace u32 msm_sched_clock_read(void)
+{
+	return msm_clocksource.read(&msm_clocksource);
+}
+
 static void __init msm_timer_init(void)
 {
 	struct clock_event_device *ce = &msm_clockevent;
@@ -232,6 +238,8 @@
 	res = clocksource_register_hz(cs, dgt_hz);
 	if (res)
 		pr_err("clocksource_register failed\n");
+	setup_sched_clock(msm_sched_clock_read,
+			cpu_is_msm7x01() ? 32 - MSM_DGT_SHIFT : 32, dgt_hz);
 }
 
 struct sys_timer msm_timer = {
diff --git a/arch/arm/mach-mv78xx0/include/mach/io.h b/arch/arm/mach-mv78xx0/include/mach/io.h
index 450e0e1..c7d9d00 100644
--- a/arch/arm/mach-mv78xx0/include/mach/io.h
+++ b/arch/arm/mach-mv78xx0/include/mach/io.h
@@ -20,7 +20,5 @@
 }
 
 #define __io(a)			__io(a)
-#define __mem_pci(a)		(a)
-
 
 #endif
diff --git a/arch/arm/mach-mxs/include/mach/hardware.h b/arch/arm/mach-mxs/include/mach/hardware.h
index 53e89a0..4c0e8a6 100644
--- a/arch/arm/mach-mxs/include/mach/hardware.h
+++ b/arch/arm/mach-mxs/include/mach/hardware.h
@@ -20,10 +20,4 @@
 #ifndef __MACH_MXS_HARDWARE_H__
 #define __MACH_MXS_HARDWARE_H__
 
-#ifdef __ASSEMBLER__
-#define IOMEM(addr)	(addr)
-#else
-#define IOMEM(addr)	((void __force __iomem *)(addr))
-#endif
-
 #endif /* __MACH_MXS_HARDWARE_H__ */
diff --git a/arch/arm/mach-mxs/include/mach/io.h b/arch/arm/mach-mxs/include/mach/io.h
deleted file mode 100644
index 289b722..0000000
--- a/arch/arm/mach-mxs/include/mach/io.h
+++ /dev/null
@@ -1,22 +0,0 @@
-/*
- *  Copyright 2004-2007 Freescale Semiconductor, Inc. All Rights Reserved.
- */
-
-/*
- * 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 __MACH_MXS_IO_H__
-#define __MACH_MXS_IO_H__
-
-/* Allow IO space to be anywhere in the memory */
-#define IO_SPACE_LIMIT 0xffffffff
-
-/* io address mapping macro */
-#define __io(a)		__typesafe_io(a)
-
-#define __mem_pci(a)	(a)
-
-#endif /* __MACH_MXS_IO_H__ */
diff --git a/arch/arm/mach-netx/generic.c b/arch/arm/mach-netx/generic.c
index 59e6797..aa62746 100644
--- a/arch/arm/mach-netx/generic.c
+++ b/arch/arm/mach-netx/generic.c
@@ -168,7 +168,7 @@
 {
 	int irq;
 
-	vic_init(__io(io_p2v(NETX_PA_VIC)), 0, ~0, 0);
+	vic_init(io_p2v(NETX_PA_VIC), 0, ~0, 0);
 
 	for (irq = NETX_IRQ_HIF_CHAINED(0); irq <= NETX_IRQ_HIF_LAST; irq++) {
 		irq_set_chip_and_handler(irq, &netx_hif_chip,
diff --git a/arch/arm/mach-netx/include/mach/hardware.h b/arch/arm/mach-netx/include/mach/hardware.h
index 517a2bd..b661af2 100644
--- a/arch/arm/mach-netx/include/mach/hardware.h
+++ b/arch/arm/mach-netx/include/mach/hardware.h
@@ -33,7 +33,7 @@
 #define XMAC_MEM_SIZE 0x1000
 #define SRAM_MEM_SIZE 0x8000
 
-#define io_p2v(x) ((x) - NETX_IO_PHYS + NETX_IO_VIRT)
+#define io_p2v(x) IOMEM((x) - NETX_IO_PHYS + NETX_IO_VIRT)
 #define io_v2p(x) ((x) - NETX_IO_VIRT + NETX_IO_PHYS)
 
 #endif
diff --git a/arch/arm/mach-netx/include/mach/io.h b/arch/arm/mach-netx/include/mach/io.h
deleted file mode 100644
index c3921cb..0000000
--- a/arch/arm/mach-netx/include/mach/io.h
+++ /dev/null
@@ -1,28 +0,0 @@
-/*
- *  arch/arm/mach-netx/include/mach/io.h
- *
- * Copyright (C) 2005 Sascha Hauer <s.hauer@pengutronix.de>, Pengutronix
- *
- * 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_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H
-
-#define IO_SPACE_LIMIT 0xffffffff
-
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)            (a)
-
-#endif
diff --git a/arch/arm/mach-netx/include/mach/netx-regs.h b/arch/arm/mach-netx/include/mach/netx-regs.h
index 5a03e7c..fdde22b 100644
--- a/arch/arm/mach-netx/include/mach/netx-regs.h
+++ b/arch/arm/mach-netx/include/mach/netx-regs.h
@@ -115,7 +115,7 @@
  *********************************/
 
 /* Registers */
-#define NETX_SYSTEM_REG(ofs)            __io(NETX_VA_SYSTEM + (ofs))
+#define NETX_SYSTEM_REG(ofs)            IOMEM(NETX_VA_SYSTEM + (ofs))
 #define NETX_SYSTEM_BOO_SR          NETX_SYSTEM_REG(0x00)
 #define NETX_SYSTEM_IOC_CR          NETX_SYSTEM_REG(0x04)
 #define NETX_SYSTEM_IOC_MR          NETX_SYSTEM_REG(0x08)
@@ -185,7 +185,7 @@
  *******************************/
 
 /* Registers */
-#define NETX_GPIO_REG(ofs)                     __io(NETX_VA_GPIO + (ofs))
+#define NETX_GPIO_REG(ofs)                     IOMEM(NETX_VA_GPIO + (ofs))
 #define NETX_GPIO_CFG(gpio)                NETX_GPIO_REG(0x0  + ((gpio)<<2))
 #define NETX_GPIO_THRESHOLD_CAPTURE(gpio)  NETX_GPIO_REG(0x40 + ((gpio)<<2))
 #define NETX_GPIO_COUNTER_CTRL(counter)    NETX_GPIO_REG(0x80 + ((counter)<<2))
@@ -230,7 +230,7 @@
  *******************************/
 
 /* Registers */
-#define NETX_PIO_REG(ofs)        __io(NETX_VA_PIO + (ofs))
+#define NETX_PIO_REG(ofs)        IOMEM(NETX_VA_PIO + (ofs))
 #define NETX_PIO_INPIO       NETX_PIO_REG(0x0)
 #define NETX_PIO_OUTPIO      NETX_PIO_REG(0x4)
 #define NETX_PIO_OEPIO       NETX_PIO_REG(0x8)
@@ -240,7 +240,7 @@
  *******************************/
 
 /* Registers */
-#define NETX_MIIMU           __io(NETX_VA_MIIMU)
+#define NETX_MIIMU           IOMEM(NETX_VA_MIIMU)
 
 /* Bits */
 #define MIIMU_SNRDY        (1<<0)
@@ -317,7 +317,7 @@
  *******************************/
 
 /* Registers */
-#define NETX_PFIFO_REG(ofs)               __io(NETX_VA_PFIFO + (ofs))
+#define NETX_PFIFO_REG(ofs)               IOMEM(NETX_VA_PFIFO + (ofs))
 #define NETX_PFIFO_BASE(pfifo)        NETX_PFIFO_REG(0x00 + ((pfifo)<<2))
 #define NETX_PFIFO_BORDER_BASE(pfifo) NETX_PFIFO_REG(0x80 + ((pfifo)<<2))
 #define NETX_PFIFO_RESET              NETX_PFIFO_REG(0x100)
@@ -334,7 +334,7 @@
  *******************************/
 
 /* Registers */
-#define NETX_MEMCR_REG(ofs)               __io(NETX_VA_MEMCR + (ofs))
+#define NETX_MEMCR_REG(ofs)               IOMEM(NETX_VA_MEMCR + (ofs))
 #define NETX_MEMCR_SRAM_CTRL(cs)      NETX_MEMCR_REG(0x0 + 4 * (cs)) /* SRAM for CS 0..2 */
 #define NETX_MEMCR_SDRAM_CFG_CTRL     NETX_MEMCR_REG(0x40)
 #define NETX_MEMCR_SDRAM_TIMING_CTRL  NETX_MEMCR_REG(0x44)
@@ -355,7 +355,7 @@
  *******************************/
 
 /* Registers */
-#define NETX_DPMAS_REG(ofs)               __io(NETX_VA_DPMAS + (ofs))
+#define NETX_DPMAS_REG(ofs)               IOMEM(NETX_VA_DPMAS + (ofs))
 #define NETX_DPMAS_SYS_STAT           NETX_DPMAS_REG(0x4d8)
 #define NETX_DPMAS_INT_STAT           NETX_DPMAS_REG(0x4e0)
 #define NETX_DPMAS_INT_EN             NETX_DPMAS_REG(0x4f0)
@@ -425,7 +425,7 @@
 /*******************************
  * I2C                         *
  *******************************/
-#define NETX_I2C_REG(ofs)	__io(NETX_VA_I2C, (ofs))
+#define NETX_I2C_REG(ofs)	IOMEM(NETX_VA_I2C, (ofs))
 #define NETX_I2C_CTRL	NETX_I2C_REG(0x0)
 #define NETX_I2C_DATA	NETX_I2C_REG(0x4)
 
diff --git a/arch/arm/mach-nomadik/include/mach/io.h b/arch/arm/mach-nomadik/include/mach/io.h
deleted file mode 100644
index 2e1eca1..0000000
--- a/arch/arm/mach-nomadik/include/mach/io.h
+++ /dev/null
@@ -1,22 +0,0 @@
-/*
- * arch/arm/mach-nomadik/include/mach/io.h   (copied from mach-sa1100)
- *
- * Copyright (C) 1997-1999 Russell King
- *
- * Modifications:
- *  06-12-1997  RMK     Created.
- *  07-04-1999  RMK     Major cleanup
- */
-#ifndef __ASM_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H
-
-#define IO_SPACE_LIMIT 0xffffffff
-
-/*
- * We don't actually have real ISA nor PCI buses, but there is so many
- * drivers out there that might just work if we fake them...
- */
-#define __io(a)         __typesafe_io(a)
-#define __mem_pci(a)    (a)
-
-#endif
diff --git a/arch/arm/mach-omap1/ams-delta-fiq-handler.S b/arch/arm/mach-omap1/ams-delta-fiq-handler.S
index 399c4c4..a051cb8 100644
--- a/arch/arm/mach-omap1/ams-delta-fiq-handler.S
+++ b/arch/arm/mach-omap1/ams-delta-fiq-handler.S
@@ -14,6 +14,7 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 
 #include <plat/board-ams-delta.h>
 
diff --git a/arch/arm/mach-omap1/board-h2.c b/arch/arm/mach-omap1/board-h2.c
index c306862..553a2e5 100644
--- a/arch/arm/mach-omap1/board-h2.c
+++ b/arch/arm/mach-omap1/board-h2.c
@@ -245,8 +245,6 @@
 		.flags	= IORESOURCE_MEM,
 	},
 	[1] = {
-		.start	= OMAP_GPIO_IRQ(0),
-		.end	= OMAP_GPIO_IRQ(0),
 		.flags	= IORESOURCE_IRQ | IORESOURCE_IRQ_LOWEDGE,
 	},
 };
@@ -359,11 +357,9 @@
 static struct i2c_board_info __initdata h2_i2c_board_info[] = {
 	{
 		I2C_BOARD_INFO("tps65010", 0x48),
-		.irq            = OMAP_GPIO_IRQ(58),
 		.platform_data	= &tps_board,
 	}, {
 		I2C_BOARD_INFO("isp1301_omap", 0x2d),
-		.irq		= OMAP_GPIO_IRQ(2),
 	},
 };
 
@@ -428,8 +424,12 @@
 	omap_cfg_reg(E19_1610_KBR4);
 	omap_cfg_reg(N19_1610_KBR5);
 
+	h2_smc91x_resources[1].start = gpio_to_irq(0);
+	h2_smc91x_resources[1].end = gpio_to_irq(0);
 	platform_add_devices(h2_devices, ARRAY_SIZE(h2_devices));
 	omap_serial_init();
+	h2_i2c_board_info[0].irq = gpio_to_irq(58);
+	h2_i2c_board_info[1].irq = gpio_to_irq(2);
 	omap_register_i2c_bus(1, 100, h2_i2c_board_info,
 			      ARRAY_SIZE(h2_i2c_board_info));
 	omap1_usb_init(&h2_usb_config);
diff --git a/arch/arm/mach-omap1/board-h3.c b/arch/arm/mach-omap1/board-h3.c
index 64b8584..4c19f4c 100644
--- a/arch/arm/mach-omap1/board-h3.c
+++ b/arch/arm/mach-omap1/board-h3.c
@@ -247,8 +247,6 @@
 		.flags	= IORESOURCE_MEM,
 	},
 	[1] = {
-		.start	= OMAP_GPIO_IRQ(40),
-		.end	= OMAP_GPIO_IRQ(40),
 		.flags	= IORESOURCE_IRQ | IORESOURCE_IRQ_LOWEDGE,
 	},
 };
@@ -338,7 +336,6 @@
 		.modalias	= "tsc2101",
 		.bus_num	= 2,
 		.chip_select	= 0,
-		.irq		= OMAP_GPIO_IRQ(H3_TS_GPIO),
 		.max_speed_hz	= 16000000,
 		/* .platform_data	= &tsc_platform_data, */
 	},
@@ -374,11 +371,9 @@
 static struct i2c_board_info __initdata h3_i2c_board_info[] = {
        {
 		I2C_BOARD_INFO("tps65013", 0x48),
-               /* .irq         = OMAP_GPIO_IRQ(??), */
        },
 	{
 		I2C_BOARD_INFO("isp1301_omap", 0x2d),
-		.irq		= OMAP_GPIO_IRQ(14),
 	},
 };
 
@@ -420,10 +415,14 @@
 	omap_cfg_reg(E19_1610_KBR4);
 	omap_cfg_reg(N19_1610_KBR5);
 
+	smc91x_resources[1].start = gpio_to_irq(40);
+	smc91x_resources[1].end = gpio_to_irq(40);
 	platform_add_devices(devices, ARRAY_SIZE(devices));
+	h3_spi_board_info[0].irq = gpio_to_irq(H3_TS_GPIO);
 	spi_register_board_info(h3_spi_board_info,
 				ARRAY_SIZE(h3_spi_board_info));
 	omap_serial_init();
+	h3_i2c_board_info[1].irq = gpio_to_irq(14);
 	omap_register_i2c_bus(1, 100, h3_i2c_board_info,
 			      ARRAY_SIZE(h3_i2c_board_info));
 	omap1_usb_init(&h3_usb_config);
diff --git a/arch/arm/mach-omap1/board-htcherald.c b/arch/arm/mach-omap1/board-htcherald.c
index 827d83a..60c06ee 100644
--- a/arch/arm/mach-omap1/board-htcherald.c
+++ b/arch/arm/mach-omap1/board-htcherald.c
@@ -324,8 +324,6 @@
 
 static struct resource htcpld_resources[] = {
 	[0] = {
-		.start  = OMAP_GPIO_IRQ(HTCHERALD_GIRQ_BTNS),
-		.end    = OMAP_GPIO_IRQ(HTCHERALD_GIRQ_BTNS),
 		.flags  = IORESOURCE_IRQ,
 	},
 };
@@ -450,7 +448,6 @@
 	{
 		.modalias		= "ads7846",
 		.platform_data		= &htcherald_ts_platform_data,
-		.irq			= OMAP_GPIO_IRQ(HTCHERALD_GPIO_TS),
 		.max_speed_hz		= 2500000,
 		.bus_num		= 2,
 		.chip_select		= 1,
@@ -576,6 +573,8 @@
 	printk(KERN_INFO "HTC Herald init.\n");
 
 	/* Do board initialization before we register all the devices */
+	htcpld_resources[0].start = gpio_to_irq(HTCHERALD_GIRQ_BTNS);
+	htcpld_resources[0].end = gpio_to_irq(HTCHERALD_GIRQ_BTNS);
 	platform_add_devices(devices, ARRAY_SIZE(devices));
 
 	htcherald_disable_watchdog();
@@ -583,6 +582,7 @@
 	htcherald_usb_enable();
 	omap1_usb_init(&htcherald_usb_config);
 
+	htcherald_spi_board_info[0].irq = gpio_to_irq(HTCHERALD_GPIO_TS);
 	spi_register_board_info(htcherald_spi_board_info,
 		ARRAY_SIZE(htcherald_spi_board_info));
 
diff --git a/arch/arm/mach-omap1/board-innovator.c b/arch/arm/mach-omap1/board-innovator.c
index 6121918..67d7fd5 100644
--- a/arch/arm/mach-omap1/board-innovator.c
+++ b/arch/arm/mach-omap1/board-innovator.c
@@ -248,8 +248,6 @@
 		.flags	= IORESOURCE_MEM,
 	},
 	[1] = {
-		.start	= OMAP_GPIO_IRQ(0),
-		.end	= OMAP_GPIO_IRQ(0),
 		.flags	= IORESOURCE_IRQ | IORESOURCE_IRQ_LOWEDGE,
 	},
 };
@@ -409,6 +407,8 @@
 #endif
 #ifdef CONFIG_ARCH_OMAP16XX
 	if (!cpu_is_omap1510()) {
+		innovator1610_smc91x_resources[1].start = gpio_to_irq(0);
+		innovator1610_smc91x_resources[1].end = gpio_to_irq(0);
 		platform_add_devices(innovator1610_devices, ARRAY_SIZE(innovator1610_devices));
 	}
 #endif
diff --git a/arch/arm/mach-omap1/board-nokia770.c b/arch/arm/mach-omap1/board-nokia770.c
index fe95ec5..d21dcc2 100644
--- a/arch/arm/mach-omap1/board-nokia770.c
+++ b/arch/arm/mach-omap1/board-nokia770.c
@@ -147,7 +147,6 @@
 		.bus_num        = 2,
 		.chip_select    = 0,
 		.max_speed_hz   = 2500000,
-		.irq		= OMAP_GPIO_IRQ(15),
 		.platform_data	= &nokia770_ads7846_platform_data,
 	},
 };
@@ -237,6 +236,7 @@
 	omap_writew((omap_readw(0xfffb5004) & ~2), 0xfffb5004);
 
 	platform_add_devices(nokia770_devices, ARRAY_SIZE(nokia770_devices));
+	nokia770_spi_board_info[1].irq = gpio_to_irq(15);
 	spi_register_board_info(nokia770_spi_board_info,
 				ARRAY_SIZE(nokia770_spi_board_info));
 	omap_serial_init();
diff --git a/arch/arm/mach-omap1/board-osk.c b/arch/arm/mach-omap1/board-osk.c
index 1fe3473..a5f85dd 100644
--- a/arch/arm/mach-omap1/board-osk.c
+++ b/arch/arm/mach-omap1/board-osk.c
@@ -129,8 +129,6 @@
 		.flags	= IORESOURCE_MEM,
 	},
 	[1] = {
-		.start	= OMAP_GPIO_IRQ(0),
-		.end	= OMAP_GPIO_IRQ(0),
 		.flags	= IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHEDGE,
 	},
 };
@@ -147,8 +145,6 @@
 
 static struct resource osk5912_cf_resources[] = {
 	[0] = {
-		.start	= OMAP_GPIO_IRQ(62),
-		.end	= OMAP_GPIO_IRQ(62),
 		.flags	= IORESOURCE_IRQ,
 	},
 };
@@ -240,7 +236,6 @@
 static struct i2c_board_info __initdata osk_i2c_board_info[] = {
 	{
 		I2C_BOARD_INFO("tps65010", 0x48),
-		.irq		= OMAP_GPIO_IRQ(OMAP_MPUIO(1)),
 		.platform_data	= &tps_board,
 
 	},
@@ -408,7 +403,6 @@
 	/* MicroWire (bus 2) CS0 has an ads7846e */
 	.modalias		= "ads7846",
 	.platform_data		= &mistral_ts_info,
-	.irq			= OMAP_GPIO_IRQ(4),
 	.max_speed_hz		= 120000 /* max sample rate at 3V */
 					* 26 /* command + data + overhead */,
 	.bus_num		= 2,
@@ -471,6 +465,7 @@
 	gpio_direction_input(4);
 	irq_set_irq_type(gpio_to_irq(4), IRQ_TYPE_EDGE_FALLING);
 
+	mistral_boardinfo[0].irq = gpio_to_irq(4);
 	spi_register_board_info(mistral_boardinfo,
 			ARRAY_SIZE(mistral_boardinfo));
 
@@ -542,6 +537,10 @@
 
 	osk_flash_resource.end = osk_flash_resource.start = omap_cs3_phys();
 	osk_flash_resource.end += SZ_32M - 1;
+	osk5912_smc91x_resources[1].start = gpio_to_irq(0);
+	osk5912_smc91x_resources[1].end = gpio_to_irq(0);
+	osk5912_cf_resources[0].start = gpio_to_irq(62);
+	osk5912_cf_resources[0].end = gpio_to_irq(62);
 	platform_add_devices(osk5912_devices, ARRAY_SIZE(osk5912_devices));
 
 	l = omap_readl(USB_TRANSCEIVER_CTRL);
@@ -556,6 +555,7 @@
 		gpio_direction_input(OMAP_MPUIO(1));
 
 	omap_serial_init();
+	osk_i2c_board_info[0].irq = gpio_to_irq(OMAP_MPUIO(1));
 	omap_register_i2c_bus(1, 400, osk_i2c_board_info,
 			      ARRAY_SIZE(osk_i2c_board_info));
 	osk_mistral_init();
diff --git a/arch/arm/mach-omap1/board-palmte.c b/arch/arm/mach-omap1/board-palmte.c
index 0863d8e..a60e6c2 100644
--- a/arch/arm/mach-omap1/board-palmte.c
+++ b/arch/arm/mach-omap1/board-palmte.c
@@ -217,7 +217,6 @@
 		.modalias	= "tsc2102",
 		.bus_num	= 2,	/* uWire (officially) */
 		.chip_select	= 0,	/* As opposed to 3 */
-		.irq		= OMAP_GPIO_IRQ(PALMTE_PINTDAV_GPIO),
 		.max_speed_hz	= 8000000,
 	},
 };
@@ -251,6 +250,7 @@
 
 	platform_add_devices(palmte_devices, ARRAY_SIZE(palmte_devices));
 
+	palmte_spi_info[0].irq = gpio_to_irq(PALMTE_PINTDAV_GPIO);
 	spi_register_board_info(palmte_spi_info, ARRAY_SIZE(palmte_spi_info));
 	palmte_misc_gpio_setup();
 	omap_serial_init();
diff --git a/arch/arm/mach-omap1/board-palmtt.c b/arch/arm/mach-omap1/board-palmtt.c
index 4ff699c..8d85487 100644
--- a/arch/arm/mach-omap1/board-palmtt.c
+++ b/arch/arm/mach-omap1/board-palmtt.c
@@ -257,7 +257,6 @@
 		/* MicroWire (bus 2) CS0 has an ads7846e */
 		.modalias	= "ads7846",
 		.platform_data	= &palmtt_ts_info,
-		.irq		= OMAP_GPIO_IRQ(6),
 		.max_speed_hz	= 120000	/* max sample rate at 3V */
 					* 26	/* command + data + overhead */,
 		.bus_num	= 2,
@@ -298,6 +297,7 @@
 
 	platform_add_devices(palmtt_devices, ARRAY_SIZE(palmtt_devices));
 
+	palmtt_boardinfo[0].irq = gpio_to_irq(6);
 	spi_register_board_info(palmtt_boardinfo,ARRAY_SIZE(palmtt_boardinfo));
 	omap_serial_init();
 	omap1_usb_init(&palmtt_usb_config);
diff --git a/arch/arm/mach-omap1/board-palmz71.c b/arch/arm/mach-omap1/board-palmz71.c
index abcbbd3..a2c5abc 100644
--- a/arch/arm/mach-omap1/board-palmz71.c
+++ b/arch/arm/mach-omap1/board-palmz71.c
@@ -224,7 +224,6 @@
 	/* MicroWire (bus 2) CS0 has an ads7846e */
 	.modalias	= "ads7846",
 	.platform_data	= &palmz71_ts_info,
-	.irq		= OMAP_GPIO_IRQ(PALMZ71_PENIRQ_GPIO),
 	.max_speed_hz	= 120000	/* max sample rate at 3V */
 				* 26	/* command + data + overhead */,
 	.bus_num	= 2,
@@ -313,6 +312,7 @@
 
 	platform_add_devices(devices, ARRAY_SIZE(devices));
 
+	palmz71_boardinfo[0].irq = gpio_to_irq(PALMZ71_PENIRQ_GPIO);
 	spi_register_board_info(palmz71_boardinfo,
 				ARRAY_SIZE(palmz71_boardinfo));
 	omap1_usb_init(&palmz71_usb_config);
diff --git a/arch/arm/mach-omap1/board-voiceblue.c b/arch/arm/mach-omap1/board-voiceblue.c
index 659d0f7..37232d0 100644
--- a/arch/arm/mach-omap1/board-voiceblue.c
+++ b/arch/arm/mach-omap1/board-voiceblue.c
@@ -44,7 +44,6 @@
 static struct plat_serial8250_port voiceblue_ports[] = {
 	{
 		.mapbase	= (unsigned long)(OMAP_CS1_PHYS + 0x40000),
-		.irq		= OMAP_GPIO_IRQ(12),
 		.flags		= UPF_BOOT_AUTOCONF | UPF_IOREMAP,
 		.iotype		= UPIO_MEM,
 		.regshift	= 1,
@@ -52,7 +51,6 @@
 	},
 	{
 		.mapbase	= (unsigned long)(OMAP_CS1_PHYS + 0x50000),
-		.irq		= OMAP_GPIO_IRQ(13),
 		.flags		= UPF_BOOT_AUTOCONF | UPF_IOREMAP,
 		.iotype		= UPIO_MEM,
 		.regshift	= 1,
@@ -60,7 +58,6 @@
 	},
 	{
 		.mapbase	= (unsigned long)(OMAP_CS1_PHYS + 0x60000),
-		.irq		= OMAP_GPIO_IRQ(14),
 		.flags		= UPF_BOOT_AUTOCONF | UPF_IOREMAP,
 		.iotype		= UPIO_MEM,
 		.regshift	= 1,
@@ -68,7 +65,6 @@
 	},
 	{
 		.mapbase	= (unsigned long)(OMAP_CS1_PHYS + 0x70000),
-		.irq		= OMAP_GPIO_IRQ(15),
 		.flags		= UPF_BOOT_AUTOCONF | UPF_IOREMAP,
 		.iotype		= UPIO_MEM,
 		.regshift	= 1,
@@ -80,9 +76,6 @@
 static struct platform_device serial_device = {
 	.name			= "serial8250",
 	.id			= PLAT8250_DEV_PLATFORM1,
-	.dev			= {
-		.platform_data	= voiceblue_ports,
-	},
 };
 
 static int __init ext_uart_init(void)
@@ -90,6 +83,11 @@
 	if (!machine_is_voiceblue())
 		return -ENODEV;
 
+	voiceblue_ports[0].irq = gpio_to_irq(12);
+	voiceblue_ports[1].irq = gpio_to_irq(13);
+	voiceblue_ports[2].irq = gpio_to_irq(14);
+	voiceblue_ports[3].irq = gpio_to_irq(15);
+	serial_device.dev.platform_data = voiceblue_ports;
 	return platform_device_register(&serial_device);
 }
 arch_initcall(ext_uart_init);
@@ -128,8 +126,6 @@
 		.flags	= IORESOURCE_MEM,
 	},
 	[1] = {
-		.start	= OMAP_GPIO_IRQ(8),
-		.end	= OMAP_GPIO_IRQ(8),
 		.flags	= IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHEDGE,
 	},
 };
@@ -275,6 +271,8 @@
 	irq_set_irq_type(gpio_to_irq(14), IRQ_TYPE_EDGE_RISING);
 	irq_set_irq_type(gpio_to_irq(15), IRQ_TYPE_EDGE_RISING);
 
+	voiceblue_smc91x_resources[1].start = gpio_to_irq(8);
+	voiceblue_smc91x_resources[1].end = gpio_to_irq(8);
 	platform_add_devices(voiceblue_devices, ARRAY_SIZE(voiceblue_devices));
 	omap_board_config = voiceblue_config;
 	omap_board_config_size = ARRAY_SIZE(voiceblue_config);
diff --git a/arch/arm/mach-omap1/include/mach/entry-macro.S b/arch/arm/mach-omap1/include/mach/entry-macro.S
index fa0f32a..88f08ca 100644
--- a/arch/arm/mach-omap1/include/mach/entry-macro.S
+++ b/arch/arm/mach-omap1/include/mach/entry-macro.S
@@ -11,7 +11,6 @@
  */
 
 #include <mach/hardware.h>
-#include <mach/io.h>
 #include <mach/irqs.h>
 
 #include "../../iomap.h"
diff --git a/arch/arm/mach-omap1/include/mach/io.h b/arch/arm/mach-omap1/include/mach/io.h
deleted file mode 100644
index 37b12e1..0000000
--- a/arch/arm/mach-omap1/include/mach/io.h
+++ /dev/null
@@ -1,46 +0,0 @@
-/*
- * arch/arm/mach-omap1/include/mach/io.h
- *
- * IO definitions for TI OMAP processors and boards
- *
- * Copied from arch/arm/mach-sa1100/include/mach/io.h
- * Copyright (C) 1997-1999 Russell King
- *
- * 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 SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
- * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
- * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN
- * NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
- * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
- * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
- * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
- * ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
- * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * 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.,
- * 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- * Modifications:
- *  06-12-1997	RMK	Created.
- *  07-04-1999	RMK	Major cleanup
- */
-
-#ifndef __ASM_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H
-
-#define IO_SPACE_LIMIT 0xffffffff
-
-/*
- * We don't actually have real ISA nor PCI buses, but there is so many
- * drivers out there that might just work if we fake them...
- */
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
-
-#endif
diff --git a/arch/arm/mach-omap1/iomap.h b/arch/arm/mach-omap1/iomap.h
index d681757..330c471 100644
--- a/arch/arm/mach-omap1/iomap.h
+++ b/arch/arm/mach-omap1/iomap.h
@@ -22,12 +22,6 @@
  * 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
-#ifdef __ASSEMBLER__
-#define IOMEM(x)		(x)
-#else
-#define IOMEM(x)		((void __force __iomem *)(x))
-#endif
-
 #define OMAP1_IO_OFFSET		0x01000000	/* Virtual IO = 0xfefb0000 */
 #define OMAP1_IO_ADDRESS(pa)	IOMEM((pa) - OMAP1_IO_OFFSET)
 
diff --git a/arch/arm/mach-omap1/pm.c b/arch/arm/mach-omap1/pm.c
index 306beac..f66c329 100644
--- a/arch/arm/mach-omap1/pm.c
+++ b/arch/arm/mach-omap1/pm.c
@@ -44,6 +44,7 @@
 #include <linux/io.h>
 #include <linux/atomic.h>
 
+#include <asm/system_misc.h>
 #include <asm/irq.h>
 #include <asm/mach/time.h>
 #include <asm/mach/irq.h>
diff --git a/arch/arm/mach-omap1/sleep.S b/arch/arm/mach-omap1/sleep.S
index 0779db1..0e62874 100644
--- a/arch/arm/mach-omap1/sleep.S
+++ b/arch/arm/mach-omap1/sleep.S
@@ -36,8 +36,6 @@
 
 #include <asm/assembler.h>
 
-#include <mach/io.h>
-
 #include "iomap.h"
 #include "pm.h"
 
diff --git a/arch/arm/mach-omap1/sram.S b/arch/arm/mach-omap1/sram.S
index 2ce0b9a..00e9d9e 100644
--- a/arch/arm/mach-omap1/sram.S
+++ b/arch/arm/mach-omap1/sram.S
@@ -12,7 +12,6 @@
 
 #include <asm/assembler.h>
 
-#include <mach/io.h>
 #include <mach/hardware.h>
 
 #include "iomap.h"
diff --git a/arch/arm/mach-omap2/board-2430sdp.c b/arch/arm/mach-omap2/board-2430sdp.c
index c8bda62..e658f83 100644
--- a/arch/arm/mach-omap2/board-2430sdp.c
+++ b/arch/arm/mach-omap2/board-2430sdp.c
@@ -230,12 +230,12 @@
 	{
 		I2C_BOARD_INFO("isp1301_omap", 0x2D),
 		.flags = I2C_CLIENT_WAKE,
-		.irq = OMAP_GPIO_IRQ(78),
 	},
 };
 
 static int __init omap2430_i2c_init(void)
 {
+	sdp2430_i2c1_boardinfo[0].irq = gpio_to_irq(78);
 	omap_register_i2c_bus(1, 100, sdp2430_i2c1_boardinfo,
 			ARRAY_SIZE(sdp2430_i2c1_boardinfo));
 	omap_pmic_init(2, 100, "twl4030", INT_24XX_SYS_NIRQ,
diff --git a/arch/arm/mach-omap2/board-4430sdp.c b/arch/arm/mach-omap2/board-4430sdp.c
index 37dcb1b..a39fc4b 100644
--- a/arch/arm/mach-omap2/board-4430sdp.c
+++ b/arch/arm/mach-omap2/board-4430sdp.c
@@ -907,7 +907,6 @@
 }
 
 static struct wl12xx_platform_data omap4_sdp4430_wlan_data __initdata = {
-	.irq = OMAP_GPIO_IRQ(GPIO_WIFI_IRQ),
 	.board_ref_clock = WL12XX_REFCLOCK_26,
 	.board_tcxo_clock = WL12XX_TCXOCLOCK_26,
 };
@@ -917,6 +916,7 @@
 	int ret;
 
 	omap4_sdp4430_wifi_mux_init();
+	omap4_sdp4430_wlan_data.irq = gpio_to_irq(GPIO_WIFI_IRQ);
 	ret = wl12xx_set_platform_data(&omap4_sdp4430_wlan_data);
 	if (ret)
 		pr_err("Error setting wl12xx data: %d\n", ret);
diff --git a/arch/arm/mach-omap2/board-apollon.c b/arch/arm/mach-omap2/board-apollon.c
index ac77382..768ece2 100644
--- a/arch/arm/mach-omap2/board-apollon.c
+++ b/arch/arm/mach-omap2/board-apollon.c
@@ -136,8 +136,6 @@
 		.flags  = IORESOURCE_MEM,
 	},
 	[1] = {
-		.start	= OMAP_GPIO_IRQ(APOLLON_ETHR_GPIO_IRQ),
-		.end	= OMAP_GPIO_IRQ(APOLLON_ETHR_GPIO_IRQ),
 		.flags	= IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHEDGE,
 	},
 };
@@ -341,6 +339,8 @@
 	 * You have to mux them off in device drivers later on
 	 * if not needed.
 	 */
+	apollon_smc91x_resources[1].start = gpio_to_irq(APOLLON_ETHR_GPIO_IRQ);
+	apollon_smc91x_resources[1].end = gpio_to_irq(APOLLON_ETHR_GPIO_IRQ);
 	platform_add_devices(apollon_devices, ARRAY_SIZE(apollon_devices));
 	omap_serial_init();
 	omap_sdrc_init(NULL, NULL);
diff --git a/arch/arm/mach-omap2/board-devkit8000.c b/arch/arm/mach-omap2/board-devkit8000.c
index 11cd2a8..a2010f0 100644
--- a/arch/arm/mach-omap2/board-devkit8000.c
+++ b/arch/arm/mach-omap2/board-devkit8000.c
@@ -411,7 +411,6 @@
 		.flags		= IORESOURCE_MEM,
 	},
 	[2] = {
-		.start		= OMAP_GPIO_IRQ(OMAP_DM9000_GPIO_IRQ),
 		.flags		= IORESOURCE_IRQ | IRQF_TRIGGER_LOW,
 	},
 };
@@ -639,6 +638,7 @@
 
 	omap_hsmmc_init(mmc);
 	devkit8000_i2c_init();
+	omap_dm9000_resources[2].start = gpio_to_irq(OMAP_DM9000_GPIO_IRQ);
 	platform_add_devices(devkit8000_devices,
 			ARRAY_SIZE(devkit8000_devices));
 
diff --git a/arch/arm/mach-omap2/board-h4.c b/arch/arm/mach-omap2/board-h4.c
index 54af800..0bbbabe 100644
--- a/arch/arm/mach-omap2/board-h4.c
+++ b/arch/arm/mach-omap2/board-h4.c
@@ -348,7 +348,6 @@
 static struct i2c_board_info __initdata h4_i2c_board_info[] = {
 	{
 		I2C_BOARD_INFO("isp1301_omap", 0x2d),
-		.irq		= OMAP_GPIO_IRQ(125),
 	},
 	{	/* EEPROM on mainboard */
 		I2C_BOARD_INFO("24c01", 0x52),
@@ -377,6 +376,7 @@
 	 */
 
 	board_mkp_init();
+	h4_i2c_board_info[0].irq = gpio_to_irq(125);
 	i2c_register_board_info(1, h4_i2c_board_info,
 			ARRAY_SIZE(h4_i2c_board_info));
 
diff --git a/arch/arm/mach-omap2/board-omap3evm.c b/arch/arm/mach-omap2/board-omap3evm.c
index a659e19..4c90f07 100644
--- a/arch/arm/mach-omap2/board-omap3evm.c
+++ b/arch/arm/mach-omap2/board-omap3evm.c
@@ -487,7 +487,6 @@
 };
 
 struct wl12xx_platform_data omap3evm_wlan_data __initdata = {
-	.irq = OMAP_GPIO_IRQ(OMAP3EVM_WLAN_IRQ_GPIO),
 	.board_ref_clock = WL12XX_REFCLOCK_38, /* 38.4 MHz */
 };
 #endif
@@ -623,6 +622,7 @@
 	int ret;
 
 	/* WL12xx WLAN Init */
+	omap3evm_wlan_data.irq = gpio_to_irq(OMAP3EVM_WLAN_IRQ_GPIO);
 	ret = wl12xx_set_platform_data(&omap3evm_wlan_data);
 	if (ret)
 		pr_err("error setting wl12xx data: %d\n", ret);
diff --git a/arch/arm/mach-omap2/board-omap4panda.c b/arch/arm/mach-omap2/board-omap4panda.c
index 8bf8e99..d8c0e89 100644
--- a/arch/arm/mach-omap2/board-omap4panda.c
+++ b/arch/arm/mach-omap2/board-omap4panda.c
@@ -231,7 +231,6 @@
 };
 
 struct wl12xx_platform_data omap_panda_wlan_data  __initdata = {
-	.irq = OMAP_GPIO_IRQ(GPIO_WIFI_IRQ),
 	/* PANDA ref clock is 38.4 MHz */
 	.board_ref_clock = 2,
 };
@@ -558,6 +557,7 @@
 		package = OMAP_PACKAGE_CBL;
 	omap4_mux_init(board_mux, NULL, package);
 
+	omap_panda_wlan_data.irq = gpio_to_irq(GPIO_WIFI_IRQ);
 	ret = wl12xx_set_platform_data(&omap_panda_wlan_data);
 	if (ret)
 		pr_err("error setting wl12xx data: %d\n", ret);
diff --git a/arch/arm/mach-omap2/board-rx51-peripherals.c b/arch/arm/mach-omap2/board-rx51-peripherals.c
index f120997..d87ee06 100644
--- a/arch/arm/mach-omap2/board-rx51-peripherals.c
+++ b/arch/arm/mach-omap2/board-rx51-peripherals.c
@@ -170,7 +170,6 @@
 		.modalias		= "tsc2005",
 		.bus_num		= 1,
 		.chip_select		= 0,
-		.irq			= OMAP_GPIO_IRQ(RX51_TSC2005_IRQ_GPIO),
 		.max_speed_hz		= 6000000,
 		.controller_data	= &tsc2005_mcspi_config,
 		.platform_data		= &tsc2005_pdata,
@@ -1129,6 +1128,8 @@
 	}
 
 	tsc2005_pdata.set_reset = rx51_tsc2005_set_reset;
+	rx51_peripherals_spi_board_info[RX51_SPI_TSC2005].irq =
+				gpio_to_irq(RX51_TSC2005_IRQ_GPIO);
 }
 
 void __init rx51_peripherals_init(void)
diff --git a/arch/arm/mach-omap2/board-zoom-debugboard.c b/arch/arm/mach-omap2/board-zoom-debugboard.c
index 369c2eb7..1e8540e 100644
--- a/arch/arm/mach-omap2/board-zoom-debugboard.c
+++ b/arch/arm/mach-omap2/board-zoom-debugboard.c
@@ -43,7 +43,6 @@
 static struct plat_serial8250_port serial_platform_data[] = {
 	{
 		.mapbase	= ZOOM_UART_BASE,
-		.irq		= OMAP_GPIO_IRQ(102),
 		.flags		= UPF_BOOT_AUTOCONF|UPF_IOREMAP|UPF_SHARE_IRQ,
 		.irqflags	= IRQF_SHARED | IRQF_TRIGGER_RISING,
 		.iotype		= UPIO_MEM,
@@ -89,6 +88,8 @@
 	if (gpio_request_one(quart_gpio, GPIOF_IN, "TL16CP754C GPIO") < 0)
 		printk(KERN_ERR "Failed to request GPIO%d for TL16CP754C\n",
 								quart_gpio);
+
+	serial_platform_data[0].irq = gpio_to_irq(102);
 }
 
 static inline int omap_zoom_debugboard_detect(void)
diff --git a/arch/arm/mach-omap2/board-zoom-peripherals.c b/arch/arm/mach-omap2/board-zoom-peripherals.c
index 3d39cdb..b797cb2 100644
--- a/arch/arm/mach-omap2/board-zoom-peripherals.c
+++ b/arch/arm/mach-omap2/board-zoom-peripherals.c
@@ -193,7 +193,6 @@
 };
 
 static struct wl12xx_platform_data omap_zoom_wlan_data __initdata = {
-	.irq = OMAP_GPIO_IRQ(OMAP_ZOOM_WLAN_IRQ_GPIO),
 	/* ZOOM ref clock is 26 MHz */
 	.board_ref_clock = 1,
 };
@@ -297,7 +296,10 @@
 
 void __init zoom_peripherals_init(void)
 {
-	int ret = wl12xx_set_platform_data(&omap_zoom_wlan_data);
+	int ret;
+
+	omap_zoom_wlan_data.irq = gpio_to_irq(OMAP_ZOOM_WLAN_IRQ_GPIO);
+	ret = wl12xx_set_platform_data(&omap_zoom_wlan_data);
 
 	if (ret)
 		pr_err("error setting wl12xx data: %d\n", ret);
diff --git a/arch/arm/mach-omap2/clock3xxx_data.c b/arch/arm/mach-omap2/clock3xxx_data.c
index 981b9f9..480fb8f 100644
--- a/arch/arm/mach-omap2/clock3xxx_data.c
+++ b/arch/arm/mach-omap2/clock3xxx_data.c
@@ -19,6 +19,7 @@
 #include <linux/kernel.h>
 #include <linux/clk.h>
 #include <linux/list.h>
+#include <linux/io.h>
 
 #include <plat/hardware.h>
 #include <plat/clkdev_omap.h>
diff --git a/arch/arm/mach-omap2/clock44xx_data.c b/arch/arm/mach-omap2/clock44xx_data.c
index 79b98f2..c03c110 100644
--- a/arch/arm/mach-omap2/clock44xx_data.c
+++ b/arch/arm/mach-omap2/clock44xx_data.c
@@ -26,6 +26,7 @@
 #include <linux/kernel.h>
 #include <linux/list.h>
 #include <linux/clk.h>
+#include <linux/io.h>
 
 #include <plat/hardware.h>
 #include <plat/clkdev_omap.h>
diff --git a/arch/arm/mach-omap2/common-board-devices.c b/arch/arm/mach-omap2/common-board-devices.c
index 9498b0f..1706ebc 100644
--- a/arch/arm/mach-omap2/common-board-devices.c
+++ b/arch/arm/mach-omap2/common-board-devices.c
@@ -76,7 +76,7 @@
 	}
 
 	spi_bi->bus_num	= bus_num;
-	spi_bi->irq	= OMAP_GPIO_IRQ(gpio_pendown);
+	spi_bi->irq	= gpio_to_irq(gpio_pendown);
 
 	if (board_pdata) {
 		board_pdata->gpio_pendown = gpio_pendown;
diff --git a/arch/arm/mach-omap2/display.c b/arch/arm/mach-omap2/display.c
index 9706c64..db5a88a 100644
--- a/arch/arm/mach-omap2/display.c
+++ b/arch/arm/mach-omap2/display.c
@@ -99,7 +99,7 @@
 	{ "dss_hdmi", "omapdss_hdmi", -1 },
 };
 
-static void omap4_hdmi_mux_pads(enum omap_hdmi_flags flags)
+static void __init omap4_hdmi_mux_pads(enum omap_hdmi_flags flags)
 {
 	u32 reg;
 	u16 control_i2c_1;
@@ -125,7 +125,7 @@
 	}
 }
 
-static int __init omap4_dsi_mux_pads(int dsi_id, unsigned lanes)
+static int omap4_dsi_mux_pads(int dsi_id, unsigned lanes)
 {
 	u32 enable_mask, enable_shift;
 	u32 pipd_mask, pipd_shift;
@@ -166,7 +166,7 @@
 	return 0;
 }
 
-static int __init omap_dsi_enable_pads(int dsi_id, unsigned lane_mask)
+static int omap_dsi_enable_pads(int dsi_id, unsigned lane_mask)
 {
 	if (cpu_is_omap44xx())
 		return omap4_dsi_mux_pads(dsi_id, lane_mask);
@@ -174,7 +174,7 @@
 	return 0;
 }
 
-static void __init omap_dsi_disable_pads(int dsi_id, unsigned lane_mask)
+static void omap_dsi_disable_pads(int dsi_id, unsigned lane_mask)
 {
 	if (cpu_is_omap44xx())
 		omap4_dsi_mux_pads(dsi_id, 0);
diff --git a/arch/arm/mach-omap2/include/mach/io.h b/arch/arm/mach-omap2/include/mach/io.h
deleted file mode 100644
index b8758c8..0000000
--- a/arch/arm/mach-omap2/include/mach/io.h
+++ /dev/null
@@ -1,49 +0,0 @@
-/*
- * arch/arm/mach-omap2/include/mach/io.h
- *
- * IO definitions for TI OMAP processors and boards
- *
- * Copied from arch/arm/mach-sa1100/include/mach/io.h
- * Copyright (C) 1997-1999 Russell King
- *
- * Copyright (C) 2009 Texas Instruments
- * Added OMAP4 support - Santosh Shilimkar <santosh.shilimkar@ti.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 SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
- * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
- * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN
- * NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
- * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
- * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
- * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
- * ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
- * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * 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.,
- * 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- * Modifications:
- *  06-12-1997	RMK	Created.
- *  07-04-1999	RMK	Major cleanup
- */
-
-#ifndef __ASM_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H
-
-#define IO_SPACE_LIMIT 0xffffffff
-
-/*
- * We don't actually have real ISA nor PCI buses, but there is so many
- * drivers out there that might just work if we fake them...
- */
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
-
-#endif
diff --git a/arch/arm/mach-omap2/iomap.h b/arch/arm/mach-omap2/iomap.h
index e6f9581..0812b15 100644
--- a/arch/arm/mach-omap2/iomap.h
+++ b/arch/arm/mach-omap2/iomap.h
@@ -22,12 +22,6 @@
  * 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
-#ifdef __ASSEMBLER__
-#define IOMEM(x)		(x)
-#else
-#define IOMEM(x)		((void __force __iomem *)(x))
-#endif
-
 #define OMAP2_L3_IO_OFFSET	0x90000000
 #define OMAP2_L3_IO_ADDRESS(pa)	IOMEM((pa) + OMAP2_L3_IO_OFFSET) /* L3 */
 
diff --git a/arch/arm/mach-omap2/pm.c b/arch/arm/mach-omap2/pm.c
index a7bdec6..d0c1c96 100644
--- a/arch/arm/mach-omap2/pm.c
+++ b/arch/arm/mach-omap2/pm.c
@@ -17,6 +17,8 @@
 #include <linux/export.h>
 #include <linux/suspend.h>
 
+#include <asm/system_misc.h>
+
 #include <plat/omap-pm.h>
 #include <plat/omap_device.h>
 #include "common.h"
diff --git a/arch/arm/mach-orion5x/common.h b/arch/arm/mach-orion5x/common.h
index d2513ac..2e6454c 100644
--- a/arch/arm/mach-orion5x/common.h
+++ b/arch/arm/mach-orion5x/common.h
@@ -57,5 +57,14 @@
 struct tag;
 extern void __init tag_fixup_mem32(struct tag *, char **, struct meminfo *);
 
+/*****************************************************************************
+ * Helpers to access Orion registers
+ ****************************************************************************/
+/*
+ * These are not preempt-safe.  Locks, if needed, must be taken
+ * care of by the caller.
+ */
+#define orion5x_setbits(r, mask)	writel(readl(r) | (mask), (r))
+#define orion5x_clrbits(r, mask)	writel(readl(r) & ~(mask), (r))
 
 #endif
diff --git a/arch/arm/mach-orion5x/include/mach/io.h b/arch/arm/mach-orion5x/include/mach/io.h
deleted file mode 100644
index e9d9afd..0000000
--- a/arch/arm/mach-orion5x/include/mach/io.h
+++ /dev/null
@@ -1,33 +0,0 @@
-/*
- * arch/arm/mach-orion5x/include/mach/io.h
- *
- * Tzachi Perelstein <tzachi@marvell.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2.  This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- */
-
-#ifndef __ASM_ARCH_IO_H
-#define __ASM_ARCH_IO_H
-
-#include "orion5x.h"
-
-#define IO_SPACE_LIMIT		0xffffffff
-
-#define __io(a)			__typesafe_io(a)
-#define __mem_pci(a)		(a)
-
-
-/*****************************************************************************
- * Helpers to access Orion registers
- ****************************************************************************/
-/*
- * These are not preempt-safe.  Locks, if needed, must be taken
- * care of by the caller.
- */
-#define orion5x_setbits(r, mask)	writel(readl(r) | (mask), (r))
-#define orion5x_clrbits(r, mask)	writel(readl(r) & ~(mask), (r))
-
-
-#endif
diff --git a/arch/arm/mach-orion5x/pci.c b/arch/arm/mach-orion5x/pci.c
index d6a9194..cb19e16 100644
--- a/arch/arm/mach-orion5x/pci.c
+++ b/arch/arm/mach-orion5x/pci.c
@@ -19,6 +19,7 @@
 #include <asm/mach/pci.h>
 #include <plat/pcie.h>
 #include <plat/addr-map.h>
+#include <mach/orion5x.h>
 #include "common.h"
 
 /*****************************************************************************
diff --git a/arch/arm/mach-orion5x/tsx09-common.c b/arch/arm/mach-orion5x/tsx09-common.c
index c9abb8f..7189827 100644
--- a/arch/arm/mach-orion5x/tsx09-common.c
+++ b/arch/arm/mach-orion5x/tsx09-common.c
@@ -15,6 +15,7 @@
 #include <linux/mv643xx_eth.h>
 #include <linux/timex.h>
 #include <linux/serial_reg.h>
+#include <mach/orion5x.h>
 #include "tsx09-common.h"
 #include "common.h"
 
diff --git a/arch/arm/mach-picoxcell/include/mach/io.h b/arch/arm/mach-picoxcell/include/mach/io.h
deleted file mode 100644
index 7573ec7..0000000
--- a/arch/arm/mach-picoxcell/include/mach/io.h
+++ /dev/null
@@ -1,22 +0,0 @@
-/*
- * Copyright (c) 2011 Picochip Ltd., Jamie Iles
- *
- * 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.
- */
-#ifndef __ASM_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H
-
-/* No ioports, but needed for driver compatibility. */
-#define __io(a)			__typesafe_io(a)
-/* No PCI possible on picoxcell. */
-#define __mem_pci(a)		(a)
-
-#endif /* __ASM_ARM_ARCH_IO_H */
diff --git a/arch/arm/mach-picoxcell/include/mach/irqs.h b/arch/arm/mach-picoxcell/include/mach/irqs.h
deleted file mode 100644
index 59eac1e..0000000
--- a/arch/arm/mach-picoxcell/include/mach/irqs.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/*
- * Copyright (c) 2011 Picochip Ltd., Jamie Iles
- *
- * 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.
- */
-#ifndef __MACH_IRQS_H
-#define __MACH_IRQS_H
-
-/* We dynamically allocate our irq_desc's. */
-#define NR_IRQS				0
-
-#endif /* __MACH_IRQS_H */
diff --git a/arch/arm/mach-pnx4008/include/mach/io.h b/arch/arm/mach-pnx4008/include/mach/io.h
deleted file mode 100644
index cbf0904..0000000
--- a/arch/arm/mach-pnx4008/include/mach/io.h
+++ /dev/null
@@ -1,21 +0,0 @@
-
-/*
- *  arch/arm/mach-pnx4008/include/mach/io.h
- *
- * Author: Dmitry Chigirev <chigirev@ru.mvista.com>
- *
- * 2005 (c) MontaVista Software, Inc. This file is licensed under
- * the terms of the GNU General Public License version 2. This program
- * is licensed "as is" without any warranty of any kind, whether express
- * or implied.
- */
-
-#ifndef __ASM_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H
-
-#define IO_SPACE_LIMIT 0xffffffff
-
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
-
-#endif
diff --git a/arch/arm/mach-prima2/include/mach/io.h b/arch/arm/mach-prima2/include/mach/io.h
deleted file mode 100644
index 6c31e9e..0000000
--- a/arch/arm/mach-prima2/include/mach/io.h
+++ /dev/null
@@ -1,16 +0,0 @@
-/*
- * arch/arm/mach-prima2/include/mach/io.h
- *
- * Copyright (c) 2011 Cambridge Silicon Radio Limited, a CSR plc group company.
- *
- * Licensed under GPLv2 or later.
- */
-
-#ifndef __MACH_PRIMA2_IO_H
-#define __MACH_PRIMA2_IO_H
-
-#define IO_SPACE_LIMIT ((resource_size_t)0)
-
-#define __mem_pci(a)            (a)
-
-#endif
diff --git a/arch/arm/mach-prima2/timer.c b/arch/arm/mach-prima2/timer.c
index b7a6091..0d024b1 100644
--- a/arch/arm/mach-prima2/timer.c
+++ b/arch/arm/mach-prima2/timer.c
@@ -18,6 +18,7 @@
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <mach/map.h>
+#include <asm/sched_clock.h>
 #include <asm/mach/time.h>
 
 #define SIRFSOC_TIMER_COUNTER_LO	0x0000
@@ -165,21 +166,9 @@
 };
 
 /* Overwrite weak default sched_clock with more precise one */
-unsigned long long notrace sched_clock(void)
+static u32 notrace sirfsoc_read_sched_clock(void)
 {
-	static int is_mapped;
-
-	/*
-	 * sched_clock is called earlier than .init of sys_timer
-	 * if we map timer memory in .init of sys_timer, system
-	 * will panic due to illegal memory access
-	 */
-	if (!is_mapped) {
-		sirfsoc_of_timer_map();
-		is_mapped = 1;
-	}
-
-	return sirfsoc_timer_read(NULL) * (NSEC_PER_SEC / CLOCK_TICK_RATE);
+	return (u32)(sirfsoc_timer_read(NULL) & 0xffffffff);
 }
 
 static void __init sirfsoc_clockevent_init(void)
@@ -210,6 +199,8 @@
 	BUG_ON(rate < CLOCK_TICK_RATE);
 	BUG_ON(rate % CLOCK_TICK_RATE);
 
+	sirfsoc_of_timer_map();
+
 	writel_relaxed(rate / CLOCK_TICK_RATE / 2 - 1, sirfsoc_timer_base + SIRFSOC_TIMER_DIV);
 	writel_relaxed(0, sirfsoc_timer_base + SIRFSOC_TIMER_COUNTER_LO);
 	writel_relaxed(0, sirfsoc_timer_base + SIRFSOC_TIMER_COUNTER_HI);
@@ -217,6 +208,8 @@
 
 	BUG_ON(clocksource_register_hz(&sirfsoc_clocksource, CLOCK_TICK_RATE));
 
+	setup_sched_clock(sirfsoc_read_sched_clock, 32, CLOCK_TICK_RATE);
+
 	BUG_ON(setup_irq(sirfsoc_timer_irq.irq, &sirfsoc_timer_irq));
 
 	sirfsoc_clockevent_init();
diff --git a/arch/arm/mach-pxa/Kconfig b/arch/arm/mach-pxa/Kconfig
index 61d3c72..109ccd2 100644
--- a/arch/arm/mach-pxa/Kconfig
+++ b/arch/arm/mach-pxa/Kconfig
@@ -108,6 +108,7 @@
 
 config MACH_ARMCORE
 	bool "CompuLab CM-X255/CM-X270 modules"
+	select ARCH_HAS_DMA_SET_COHERENT_MASK if PCI
 	select PXA27x
 	select IWMMXT
 	select PXA25x
diff --git a/arch/arm/mach-pxa/capc7117.c b/arch/arm/mach-pxa/capc7117.c
index c91727d..9a8760b 100644
--- a/arch/arm/mach-pxa/capc7117.c
+++ b/arch/arm/mach-pxa/capc7117.c
@@ -150,6 +150,7 @@
 	      "Embedian CAPC-7117 evaluation kit based on the MXM-8x10 CoM")
 	.atag_offset = 0x100,
 	.map_io = pxa3xx_map_io,
+	.nr_irqs = PXA_NR_IRQS,
 	.init_irq = pxa3xx_init_irq,
 	.handle_irq = pxa3xx_handle_irq,
 	.timer = &pxa_timer,
diff --git a/arch/arm/mach-pxa/clock-pxa2xx.c b/arch/arm/mach-pxa/clock-pxa2xx.c
index 1d5859d..9ee2ad6 100644
--- a/arch/arm/mach-pxa/clock-pxa2xx.c
+++ b/arch/arm/mach-pxa/clock-pxa2xx.c
@@ -9,6 +9,7 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
+#include <linux/io.h>
 #include <linux/syscore_ops.h>
 
 #include <mach/pxa2xx-regs.h>
diff --git a/arch/arm/mach-pxa/cm-x300.c b/arch/arm/mach-pxa/cm-x300.c
index 895ee8c..3132740 100644
--- a/arch/arm/mach-pxa/cm-x300.c
+++ b/arch/arm/mach-pxa/cm-x300.c
@@ -714,7 +714,6 @@
 
 static struct regulator_consumer_supply buck2_consumers[] = {
 	{
-		.dev = NULL,
 		.supply = "vcc_core",
 	},
 };
@@ -854,6 +853,7 @@
 MACHINE_START(CM_X300, "CM-X300 module")
 	.atag_offset	= 0x100,
 	.map_io		= pxa3xx_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa3xx_init_irq,
 	.handle_irq	= pxa3xx_handle_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-pxa/colibri-pxa270.c b/arch/arm/mach-pxa/colibri-pxa270.c
index 29d5d54..b2f227d 100644
--- a/arch/arm/mach-pxa/colibri-pxa270.c
+++ b/arch/arm/mach-pxa/colibri-pxa270.c
@@ -310,6 +310,7 @@
 	.atag_offset	= 0x100,
 	.init_machine	= colibri_pxa270_init,
 	.map_io		= pxa27x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.timer		= &pxa_timer,
@@ -320,6 +321,7 @@
 	.atag_offset	= 0x100,
 	.init_machine	= colibri_pxa270_income_init,
 	.map_io		= pxa27x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-pxa/colibri-pxa300.c b/arch/arm/mach-pxa/colibri-pxa300.c
index 0846d21..bb6def8 100644
--- a/arch/arm/mach-pxa/colibri-pxa300.c
+++ b/arch/arm/mach-pxa/colibri-pxa300.c
@@ -186,6 +186,7 @@
 	.atag_offset	= 0x100,
 	.init_machine	= colibri_pxa300_init,
 	.map_io		= pxa3xx_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa3xx_init_irq,
 	.handle_irq	= pxa3xx_handle_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-pxa/colibri-pxa320.c b/arch/arm/mach-pxa/colibri-pxa320.c
index 6ad3359..d88e7b37 100644
--- a/arch/arm/mach-pxa/colibri-pxa320.c
+++ b/arch/arm/mach-pxa/colibri-pxa320.c
@@ -256,6 +256,7 @@
 	.atag_offset	= 0x100,
 	.init_machine	= colibri_pxa320_init,
 	.map_io		= pxa3xx_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa3xx_init_irq,
 	.handle_irq	= pxa3xx_handle_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-pxa/corgi.c b/arch/arm/mach-pxa/corgi.c
index de9d45e..c1fe32d 100644
--- a/arch/arm/mach-pxa/corgi.c
+++ b/arch/arm/mach-pxa/corgi.c
@@ -729,6 +729,7 @@
 MACHINE_START(CORGI, "SHARP Corgi")
 	.fixup		= fixup_corgi,
 	.map_io		= pxa25x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa25x_init_irq,
 	.handle_irq	= pxa25x_handle_irq,
 	.init_machine	= corgi_init,
@@ -741,6 +742,7 @@
 MACHINE_START(SHEPHERD, "SHARP Shepherd")
 	.fixup		= fixup_corgi,
 	.map_io		= pxa25x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa25x_init_irq,
 	.handle_irq	= pxa25x_handle_irq,
 	.init_machine	= corgi_init,
@@ -753,6 +755,7 @@
 MACHINE_START(HUSKY, "SHARP Husky")
 	.fixup		= fixup_corgi,
 	.map_io		= pxa25x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa25x_init_irq,
 	.handle_irq	= pxa25x_handle_irq,
 	.init_machine	= corgi_init,
diff --git a/arch/arm/mach-pxa/corgi_pm.c b/arch/arm/mach-pxa/corgi_pm.c
index 39e265c..048c4299 100644
--- a/arch/arm/mach-pxa/corgi_pm.c
+++ b/arch/arm/mach-pxa/corgi_pm.c
@@ -19,6 +19,7 @@
 #include <linux/interrupt.h>
 #include <linux/platform_device.h>
 #include <linux/apm-emulation.h>
+#include <linux/io.h>
 
 #include <asm/irq.h>
 #include <asm/mach-types.h>
diff --git a/arch/arm/mach-pxa/cpufreq-pxa3xx.c b/arch/arm/mach-pxa/cpufreq-pxa3xx.c
index 88fbec0..b85b4ab 100644
--- a/arch/arm/mach-pxa/cpufreq-pxa3xx.c
+++ b/arch/arm/mach-pxa/cpufreq-pxa3xx.c
@@ -15,6 +15,7 @@
 #include <linux/init.h>
 #include <linux/cpufreq.h>
 #include <linux/slab.h>
+#include <linux/io.h>
 
 #include <mach/pxa3xx-regs.h>
 
diff --git a/arch/arm/mach-pxa/csb726.c b/arch/arm/mach-pxa/csb726.c
index fb5a51d..67f0de3 100644
--- a/arch/arm/mach-pxa/csb726.c
+++ b/arch/arm/mach-pxa/csb726.c
@@ -274,6 +274,7 @@
 MACHINE_START(CSB726, "Cogent CSB726")
 	.atag_offset	= 0x100,
 	.map_io         = pxa27x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq       = pxa27x_init_irq,
 	.handle_irq       = pxa27x_handle_irq,
 	.init_machine   = csb726_init,
diff --git a/arch/arm/mach-pxa/devices.c b/arch/arm/mach-pxa/devices.c
index 84f2d701..166eee5 100644
--- a/arch/arm/mach-pxa/devices.c
+++ b/arch/arm/mach-pxa/devices.c
@@ -12,6 +12,7 @@
 #include <mach/pxafb.h>
 #include <mach/mmc.h>
 #include <mach/irda.h>
+#include <mach/irqs.h>
 #include <mach/ohci.h>
 #include <plat/pxa27x_keypad.h>
 #include <mach/camera.h>
diff --git a/arch/arm/mach-pxa/em-x270.c b/arch/arm/mach-pxa/em-x270.c
index d80c0ba..16ec557 100644
--- a/arch/arm/mach-pxa/em-x270.c
+++ b/arch/arm/mach-pxa/em-x270.c
@@ -1083,19 +1083,19 @@
 }
 
 /* DA9030 related initializations */
-#define REGULATOR_CONSUMER(_name, _dev, _supply)			       \
+#define REGULATOR_CONSUMER(_name, _dev_name, _supply)		        \
 	static struct regulator_consumer_supply _name##_consumers[] = {	\
 		{							\
-			.dev = _dev,					\
+			.dev_name = _dev_name,				\
 			.supply = _supply,				\
 		},							\
 	}
 
-REGULATOR_CONSUMER(ldo3, &em_x270_gps_userspace_consumer.dev, "vcc gps");
+REGULATOR_CONSUMER(ldo3, "reg-userspace-consumer.0", "vcc gps");
 REGULATOR_CONSUMER(ldo5, NULL, "vcc cam");
-REGULATOR_CONSUMER(ldo10, &pxa_device_mci.dev, "vcc sdio");
+REGULATOR_CONSUMER(ldo10, "pxa2xx-mci", "vcc sdio");
 REGULATOR_CONSUMER(ldo12, NULL, "vcc usb");
-REGULATOR_CONSUMER(ldo19, &em_x270_gprs_userspace_consumer.dev, "vcc gprs");
+REGULATOR_CONSUMER(ldo19, "reg-userspace-consumer.1", "vcc gprs");
 REGULATOR_CONSUMER(buck2, NULL, "vcc_core");
 
 #define REGULATOR_INIT(_ldo, _min_uV, _max_uV, _ops_mask)		\
@@ -1301,6 +1301,7 @@
 MACHINE_START(EM_X270, "Compulab EM-X270")
 	.atag_offset	= 0x100,
 	.map_io		= pxa27x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.timer		= &pxa_timer,
@@ -1311,6 +1312,7 @@
 MACHINE_START(EXEDA, "Compulab eXeda")
 	.atag_offset	= 0x100,
 	.map_io		= pxa27x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-pxa/gumstix.c b/arch/arm/mach-pxa/gumstix.c
index ac3b1ce..e529a35 100644
--- a/arch/arm/mach-pxa/gumstix.c
+++ b/arch/arm/mach-pxa/gumstix.c
@@ -235,6 +235,7 @@
 MACHINE_START(GUMSTIX, "Gumstix")
 	.atag_offset	= 0x100, /* match u-boot bi_boot_params */
 	.map_io		= pxa25x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa25x_init_irq,
 	.handle_irq	= pxa25x_handle_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-pxa/h5000.c b/arch/arm/mach-pxa/h5000.c
index fde6b4c..e7dec58 100644
--- a/arch/arm/mach-pxa/h5000.c
+++ b/arch/arm/mach-pxa/h5000.c
@@ -205,6 +205,7 @@
 MACHINE_START(H5400, "HP iPAQ H5000")
 	.atag_offset = 0x100,
 	.map_io = pxa25x_map_io,
+	.nr_irqs = PXA_NR_IRQS,
 	.init_irq = pxa25x_init_irq,
 	.handle_irq = pxa25x_handle_irq,
 	.timer = &pxa_timer,
diff --git a/arch/arm/mach-pxa/himalaya.c b/arch/arm/mach-pxa/himalaya.c
index 26d069a..2962de8 100644
--- a/arch/arm/mach-pxa/himalaya.c
+++ b/arch/arm/mach-pxa/himalaya.c
@@ -160,6 +160,7 @@
 MACHINE_START(HIMALAYA, "HTC Himalaya")
 	.atag_offset = 0x100,
 	.map_io = pxa25x_map_io,
+	.nr_irqs = PXA_NR_IRQS,
 	.init_irq = pxa25x_init_irq,
 	.handle_irq = pxa25x_handle_irq,
 	.init_machine = himalaya_init,
diff --git a/arch/arm/mach-pxa/hx4700.c b/arch/arm/mach-pxa/hx4700.c
index 3fa929d..b83b95a 100644
--- a/arch/arm/mach-pxa/hx4700.c
+++ b/arch/arm/mach-pxa/hx4700.c
@@ -681,11 +681,9 @@
 
 static struct regulator_consumer_supply bq24022_consumers[] = {
 	{
-		.dev = &gpio_vbus.dev,
 		.supply = "vbus_draw",
 	},
 	{
-		.dev = &power_supply.dev,
 		.supply = "ac_draw",
 	},
 };
diff --git a/arch/arm/mach-pxa/icontrol.c b/arch/arm/mach-pxa/icontrol.c
index 6740019..1d02eab 100644
--- a/arch/arm/mach-pxa/icontrol.c
+++ b/arch/arm/mach-pxa/icontrol.c
@@ -193,6 +193,7 @@
 MACHINE_START(ICONTROL, "iControl/SafeTcam boards using Embedian MXM-8x10 CoM")
 	.atag_offset	= 0x100,
 	.map_io		= pxa3xx_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa3xx_init_irq,
 	.handle_irq	= pxa3xx_handle_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-pxa/idp.c b/arch/arm/mach-pxa/idp.c
index 8af1840..6ff466b 100644
--- a/arch/arm/mach-pxa/idp.c
+++ b/arch/arm/mach-pxa/idp.c
@@ -195,6 +195,7 @@
 MACHINE_START(PXA_IDP, "Vibren PXA255 IDP")
 	/* Maintainer: Vibren Technologies */
 	.map_io		= idp_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa25x_init_irq,
 	.handle_irq	= pxa25x_handle_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-pxa/include/mach/hardware.h b/arch/arm/mach-pxa/include/mach/hardware.h
index 8184669..56d92e5 100644
--- a/arch/arm/mach-pxa/include/mach/hardware.h
+++ b/arch/arm/mach-pxa/include/mach/hardware.h
@@ -40,7 +40,6 @@
 #define io_p2v(x) IOMEM(0xf2000000 + ((x) & 0x01ffffff) + (((x) & 0x1c000000) >> 1))
 
 #ifndef __ASSEMBLY__
-# define IOMEM(x) ((void __iomem *)(x))
 # define __REG(x)	(*((volatile u32 __iomem *)io_p2v(x)))
 
 /* With indexed regs we don't want to feed the index through io_p2v()
@@ -52,7 +51,6 @@
 
 #else
 
-# define IOMEM(x)	x 
 # define __REG(x)	io_p2v(x)
 # define __PREG(x)	io_v2p(x)
 
@@ -337,8 +335,4 @@
 extern unsigned long get_clock_tick_rate(void);
 #endif
 
-#if defined(CONFIG_MACH_ARMCORE) && defined(CONFIG_PCI)
-#define ARCH_HAS_DMA_SET_COHERENT_MASK
-#endif
-
 #endif  /* _ASM_ARCH_HARDWARE_H */
diff --git a/arch/arm/mach-pxa/include/mach/io.h b/arch/arm/mach-pxa/include/mach/io.h
deleted file mode 100644
index fdca3be..0000000
--- a/arch/arm/mach-pxa/include/mach/io.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/*
- * arch/arm/mach-pxa/include/mach/io.h
- *
- * Copied from asm/arch/sa1100/io.h
- */
-#ifndef __ASM_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H
-
-#include <mach/hardware.h>
-
-#define IO_SPACE_LIMIT 0xffffffff
-
-/*
- * We don't actually have real ISA nor PCI buses, but there is so many
- * drivers out there that might just work if we fake them...
- */
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
-
-#endif
diff --git a/arch/arm/mach-pxa/include/mach/irqs.h b/arch/arm/mach-pxa/include/mach/irqs.h
index 32975ad..8765782 100644
--- a/arch/arm/mach-pxa/include/mach/irqs.h
+++ b/arch/arm/mach-pxa/include/mach/irqs.h
@@ -100,7 +100,7 @@
  */
 #define IRQ_BOARD_START		(PXA_GPIO_IRQ_BASE + PXA_NR_BUILTIN_GPIO)
 
-#define NR_IRQS			(IRQ_BOARD_START)
+#define PXA_NR_IRQS		(IRQ_BOARD_START)
 
 #ifndef __ASSEMBLY__
 struct irq_data;
diff --git a/arch/arm/mach-pxa/include/mach/mainstone.h b/arch/arm/mach-pxa/include/mach/mainstone.h
index 4c2d11c..1bfc4e8 100644
--- a/arch/arm/mach-pxa/include/mach/mainstone.h
+++ b/arch/arm/mach-pxa/include/mach/mainstone.h
@@ -13,6 +13,8 @@
 #ifndef ASM_ARCH_MAINSTONE_H
 #define ASM_ARCH_MAINSTONE_H
 
+#include <mach/irqs.h>
+
 #define MST_ETH_PHYS		PXA_CS4_PHYS
 
 #define MST_FPGA_PHYS		PXA_CS2_PHYS
diff --git a/arch/arm/mach-pxa/magician.c b/arch/arm/mach-pxa/magician.c
index 6f4785b..8de0651 100644
--- a/arch/arm/mach-pxa/magician.c
+++ b/arch/arm/mach-pxa/magician.c
@@ -580,11 +580,9 @@
 
 static struct regulator_consumer_supply bq24022_consumers[] = {
 	{
-		.dev = &gpio_vbus.dev,
 		.supply = "vbus_draw",
 	},
 	{
-		.dev = &power_supply.dev,
 		.supply = "ac_draw",
 	},
 };
diff --git a/arch/arm/mach-pxa/mfp-pxa2xx.c b/arch/arm/mach-pxa/mfp-pxa2xx.c
index 29b62af..b0a8428 100644
--- a/arch/arm/mach-pxa/mfp-pxa2xx.c
+++ b/arch/arm/mach-pxa/mfp-pxa2xx.c
@@ -17,6 +17,7 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
+#include <linux/io.h>
 #include <linux/syscore_ops.h>
 
 #include <mach/pxa2xx-regs.h>
diff --git a/arch/arm/mach-pxa/mioa701.c b/arch/arm/mach-pxa/mioa701.c
index e80a3db..061d570 100644
--- a/arch/arm/mach-pxa/mioa701.c
+++ b/arch/arm/mach-pxa/mioa701.c
@@ -758,6 +758,7 @@
 	.atag_offset	= 0x100,
 	.restart_mode	= 's',
 	.map_io		= &pxa27x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= &pxa27x_init_irq,
 	.handle_irq	= &pxa27x_handle_irq,
 	.init_machine	= mioa701_machine_init,
diff --git a/arch/arm/mach-pxa/mp900.c b/arch/arm/mach-pxa/mp900.c
index 169bf8f..152efbf 100644
--- a/arch/arm/mach-pxa/mp900.c
+++ b/arch/arm/mach-pxa/mp900.c
@@ -95,6 +95,7 @@
 	.atag_offset	= 0x220100,
 	.timer		= &pxa_timer,
 	.map_io		= pxa25x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa25x_init_irq,
 	.handle_irq	= pxa25x_handle_irq,
 	.init_machine	= mp900c_init,
diff --git a/arch/arm/mach-pxa/palmld.c b/arch/arm/mach-pxa/palmld.c
index 1fa80f4f..31e0433 100644
--- a/arch/arm/mach-pxa/palmld.c
+++ b/arch/arm/mach-pxa/palmld.c
@@ -344,6 +344,7 @@
 MACHINE_START(PALMLD, "Palm LifeDrive")
 	.atag_offset	= 0x100,
 	.map_io		= palmld_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-pxa/palmt5.c b/arch/arm/mach-pxa/palmt5.c
index 5ba1431..0f6bd4f 100644
--- a/arch/arm/mach-pxa/palmt5.c
+++ b/arch/arm/mach-pxa/palmt5.c
@@ -205,6 +205,7 @@
 	.atag_offset	= 0x100,
 	.map_io		= pxa27x_map_io,
 	.reserve	= palmt5_reserve,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-pxa/palmtc.c b/arch/arm/mach-pxa/palmtc.c
index 29b51b4..e2d97ee 100644
--- a/arch/arm/mach-pxa/palmtc.c
+++ b/arch/arm/mach-pxa/palmtc.c
@@ -539,6 +539,7 @@
 MACHINE_START(PALMTC, "Palm Tungsten|C")
 	.atag_offset 	= 0x100,
 	.map_io		= pxa25x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa25x_init_irq,
 	.handle_irq	= pxa25x_handle_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-pxa/palmte2.c b/arch/arm/mach-pxa/palmte2.c
index 5ebf49acb..c054827 100644
--- a/arch/arm/mach-pxa/palmte2.c
+++ b/arch/arm/mach-pxa/palmte2.c
@@ -358,6 +358,7 @@
 MACHINE_START(PALMTE2, "Palm Tungsten|E2")
 	.atag_offset	= 0x100,
 	.map_io		= pxa25x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa25x_init_irq,
 	.handle_irq	= pxa25x_handle_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-pxa/palmtreo.c b/arch/arm/mach-pxa/palmtreo.c
index ec82491..fbdebee3 100644
--- a/arch/arm/mach-pxa/palmtreo.c
+++ b/arch/arm/mach-pxa/palmtreo.c
@@ -448,6 +448,7 @@
 	.atag_offset    = 0x100,
 	.map_io         = pxa27x_map_io,
 	.reserve	= treo_reserve,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq       = pxa27x_init_irq,
 	.handle_irq       = pxa27x_handle_irq,
 	.timer          = &pxa_timer,
@@ -461,6 +462,7 @@
 	.atag_offset    = 0x100,
 	.map_io         = pxa27x_map_io,
 	.reserve	= treo_reserve,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq       = pxa27x_init_irq,
 	.handle_irq       = pxa27x_handle_irq,
 	.timer          = &pxa_timer,
diff --git a/arch/arm/mach-pxa/palmtx.c b/arch/arm/mach-pxa/palmtx.c
index 6170d76..9507605 100644
--- a/arch/arm/mach-pxa/palmtx.c
+++ b/arch/arm/mach-pxa/palmtx.c
@@ -366,6 +366,7 @@
 MACHINE_START(PALMTX, "Palm T|X")
 	.atag_offset	= 0x100,
 	.map_io		= palmtx_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-pxa/palmz72.c b/arch/arm/mach-pxa/palmz72.c
index b2dff9d..a97b599 100644
--- a/arch/arm/mach-pxa/palmz72.c
+++ b/arch/arm/mach-pxa/palmz72.c
@@ -401,6 +401,7 @@
 MACHINE_START(PALMZ72, "Palm Zire72")
 	.atag_offset	= 0x100,
 	.map_io		= pxa27x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-pxa/pxa2xx.c b/arch/arm/mach-pxa/pxa2xx.c
index 8682704..f8ec854 100644
--- a/arch/arm/mach-pxa/pxa2xx.c
+++ b/arch/arm/mach-pxa/pxa2xx.c
@@ -13,6 +13,7 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/device.h>
+#include <linux/io.h>
 
 #include <mach/hardware.h>
 #include <mach/pxa2xx-regs.h>
diff --git a/arch/arm/mach-pxa/pxa300.c b/arch/arm/mach-pxa/pxa300.c
index 40bb165..17cbc0c 100644
--- a/arch/arm/mach-pxa/pxa300.c
+++ b/arch/arm/mach-pxa/pxa300.c
@@ -16,6 +16,7 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
+#include <linux/io.h>
 
 #include <mach/pxa300.h>
 
diff --git a/arch/arm/mach-pxa/pxa320.c b/arch/arm/mach-pxa/pxa320.c
index 8d614ec..6dc99d4 100644
--- a/arch/arm/mach-pxa/pxa320.c
+++ b/arch/arm/mach-pxa/pxa320.c
@@ -16,6 +16,7 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
+#include <linux/io.h>
 
 #include <mach/pxa320.h>
 
diff --git a/arch/arm/mach-pxa/pxa3xx.c b/arch/arm/mach-pxa/pxa3xx.c
index 1570d45..dffb7e8 100644
--- a/arch/arm/mach-pxa/pxa3xx.c
+++ b/arch/arm/mach-pxa/pxa3xx.c
@@ -31,6 +31,7 @@
 #include <mach/pm.h>
 #include <mach/dma.h>
 #include <mach/smemc.h>
+#include <mach/irqs.h>
 
 #include "generic.h"
 #include "devices.h"
diff --git a/arch/arm/mach-pxa/raumfeld.c b/arch/arm/mach-pxa/raumfeld.c
index 22818c7..7d691e5 100644
--- a/arch/arm/mach-pxa/raumfeld.c
+++ b/arch/arm/mach-pxa/raumfeld.c
@@ -1090,6 +1090,7 @@
 	.atag_offset	= 0x100,
 	.init_machine	= raumfeld_controller_init,
 	.map_io		= pxa3xx_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa3xx_init_irq,
 	.handle_irq	= pxa3xx_handle_irq,
 	.timer		= &pxa_timer,
@@ -1102,6 +1103,7 @@
 	.atag_offset	= 0x100,
 	.init_machine	= raumfeld_connector_init,
 	.map_io		= pxa3xx_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa3xx_init_irq,
 	.handle_irq	= pxa3xx_handle_irq,
 	.timer		= &pxa_timer,
@@ -1114,6 +1116,7 @@
 	.atag_offset	= 0x100,
 	.init_machine	= raumfeld_speaker_init,
 	.map_io		= pxa3xx_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa3xx_init_irq,
 	.handle_irq	= pxa3xx_handle_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-pxa/saar.c b/arch/arm/mach-pxa/saar.c
index 0fe354e..86c95a5 100644
--- a/arch/arm/mach-pxa/saar.c
+++ b/arch/arm/mach-pxa/saar.c
@@ -598,6 +598,7 @@
 	/* Maintainer: Eric Miao <eric.miao@marvell.com> */
 	.atag_offset    = 0x100,
 	.map_io         = pxa3xx_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq       = pxa3xx_init_irq,
 	.handle_irq       = pxa3xx_handle_irq,
 	.timer          = &pxa_timer,
diff --git a/arch/arm/mach-pxa/sharpsl_pm.c b/arch/arm/mach-pxa/sharpsl_pm.c
index 30989ba..bdf4cb8 100644
--- a/arch/arm/mach-pxa/sharpsl_pm.c
+++ b/arch/arm/mach-pxa/sharpsl_pm.c
@@ -24,6 +24,7 @@
 #include <linux/leds.h>
 #include <linux/suspend.h>
 #include <linux/gpio.h>
+#include <linux/io.h>
 
 #include <asm/mach-types.h>
 #include <mach/pm.h>
diff --git a/arch/arm/mach-pxa/spitz.c b/arch/arm/mach-pxa/spitz.c
index abf355d..df2ab0f 100644
--- a/arch/arm/mach-pxa/spitz.c
+++ b/arch/arm/mach-pxa/spitz.c
@@ -984,6 +984,7 @@
 	.restart_mode	= 'g',
 	.fixup		= spitz_fixup,
 	.map_io		= pxa27x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.init_machine	= spitz_init,
@@ -997,6 +998,7 @@
 	.restart_mode	= 'g',
 	.fixup		= spitz_fixup,
 	.map_io		= pxa27x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.init_machine	= spitz_init,
@@ -1010,6 +1012,7 @@
 	.restart_mode	= 'g',
 	.fixup		= spitz_fixup,
 	.map_io		= pxa27x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.init_machine	= spitz_init,
diff --git a/arch/arm/mach-pxa/stargate2.c b/arch/arm/mach-pxa/stargate2.c
index b0656e15..4cd645e 100644
--- a/arch/arm/mach-pxa/stargate2.c
+++ b/arch/arm/mach-pxa/stargate2.c
@@ -152,7 +152,7 @@
 
 static struct regulator_consumer_supply stargate2_sensor_3_con[] = {
 	{
-		.dev = &sht15.dev,
+		.dev_name = "sht15",
 		.supply = "vcc",
 	},
 };
@@ -1006,6 +1006,7 @@
 #ifdef CONFIG_MACH_INTELMOTE2
 MACHINE_START(INTELMOTE2, "IMOTE 2")
 	.map_io		= pxa27x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-pxa/tavorevb.c b/arch/arm/mach-pxa/tavorevb.c
index 9fb38e8..736bfdc 100644
--- a/arch/arm/mach-pxa/tavorevb.c
+++ b/arch/arm/mach-pxa/tavorevb.c
@@ -491,6 +491,7 @@
 	/* Maintainer: Eric Miao <eric.miao@marvell.com> */
 	.atag_offset    = 0x100,
 	.map_io         = pxa3xx_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq       = pxa3xx_init_irq,
 	.handle_irq       = pxa3xx_handle_irq,
 	.timer          = &pxa_timer,
diff --git a/arch/arm/mach-pxa/time.c b/arch/arm/mach-pxa/time.c
index b503049..3d6c9bd 100644
--- a/arch/arm/mach-pxa/time.c
+++ b/arch/arm/mach-pxa/time.c
@@ -22,6 +22,7 @@
 #include <asm/mach/time.h>
 #include <asm/sched_clock.h>
 #include <mach/regs-ost.h>
+#include <mach/irqs.h>
 
 /*
  * This is PXA's sched_clock implementation. This has a resolution
diff --git a/arch/arm/mach-pxa/trizeps4.c b/arch/arm/mach-pxa/trizeps4.c
index 0f30af6..2b6ac00 100644
--- a/arch/arm/mach-pxa/trizeps4.c
+++ b/arch/arm/mach-pxa/trizeps4.c
@@ -558,6 +558,7 @@
 	.atag_offset	= 0x100,
 	.init_machine	= trizeps4_init,
 	.map_io		= trizeps4_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.timer		= &pxa_timer,
@@ -569,6 +570,7 @@
 	.atag_offset	= 0x100,
 	.init_machine	= trizeps4_init,
 	.map_io		= trizeps4_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-pxa/viper.c b/arch/arm/mach-pxa/viper.c
index 7a3d342..130379f 100644
--- a/arch/arm/mach-pxa/viper.c
+++ b/arch/arm/mach-pxa/viper.c
@@ -995,6 +995,7 @@
 	/* Maintainer: Marc Zyngier <maz@misterjones.org> */
 	.atag_offset	= 0x100,
 	.map_io		= viper_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= viper_init_irq,
 	.handle_irq	= pxa25x_handle_irq,
 	.timer          = &pxa_timer,
diff --git a/arch/arm/mach-pxa/vpac270.c b/arch/arm/mach-pxa/vpac270.c
index 1f5cfa9..c57ab63 100644
--- a/arch/arm/mach-pxa/vpac270.c
+++ b/arch/arm/mach-pxa/vpac270.c
@@ -718,6 +718,7 @@
 MACHINE_START(VPAC270, "Voipac PXA270")
 	.atag_offset	= 0x100,
 	.map_io		= pxa27x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-pxa/xcep.c b/arch/arm/mach-pxa/xcep.c
index 4bbe9a3..4275713 100644
--- a/arch/arm/mach-pxa/xcep.c
+++ b/arch/arm/mach-pxa/xcep.c
@@ -182,6 +182,7 @@
 	.atag_offset	= 0x100,
 	.init_machine	= xcep_init,
 	.map_io		= pxa25x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa25x_init_irq,
 	.handle_irq	= pxa25x_handle_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-pxa/z2.c b/arch/arm/mach-pxa/z2.c
index b647684..fa86199 100644
--- a/arch/arm/mach-pxa/z2.c
+++ b/arch/arm/mach-pxa/z2.c
@@ -721,6 +721,7 @@
 MACHINE_START(ZIPIT2, "Zipit Z2")
 	.atag_offset	= 0x100,
 	.map_io		= pxa27x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-realview/include/mach/hardware.h b/arch/arm/mach-realview/include/mach/hardware.h
index 8a638d1..281e71c 100644
--- a/arch/arm/mach-realview/include/mach/hardware.h
+++ b/arch/arm/mach-realview/include/mach/hardware.h
@@ -37,6 +37,6 @@
 #else
 #define IO_ADDRESS(x)		(x)
 #endif
-#define __io_address(n)		__io(IO_ADDRESS(n))
+#define __io_address(n)		IOMEM(IO_ADDRESS(n))
 
 #endif
diff --git a/arch/arm/mach-realview/include/mach/io.h b/arch/arm/mach-realview/include/mach/io.h
deleted file mode 100644
index f05bcdf..0000000
--- a/arch/arm/mach-realview/include/mach/io.h
+++ /dev/null
@@ -1,28 +0,0 @@
-/*
- *  arch/arm/mach-realview/include/mach/io.h
- *
- *  Copyright (C) 2003 ARM Limited
- *
- * 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 __ASM_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H
-
-#define IO_SPACE_LIMIT 0xffffffff
-
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
-
-#endif
diff --git a/arch/arm/mach-rpc/include/mach/hardware.h b/arch/arm/mach-rpc/include/mach/hardware.h
index 050d63c..257166b 100644
--- a/arch/arm/mach-rpc/include/mach/hardware.h
+++ b/arch/arm/mach-rpc/include/mach/hardware.h
@@ -14,12 +14,6 @@
 
 #include <mach/memory.h>
 
-#ifndef __ASSEMBLY__
-#define IOMEM(x) ((void __iomem *)(unsigned long)(x))
-#else
-#define IOMEM(x) x
-#endif /* __ASSEMBLY__ */
-
 /*
  * What hardware must be present
  */
diff --git a/arch/arm/mach-rpc/include/mach/io.h b/arch/arm/mach-rpc/include/mach/io.h
index 695f4ed..707071a 100644
--- a/arch/arm/mach-rpc/include/mach/io.h
+++ b/arch/arm/mach-rpc/include/mach/io.h
@@ -28,9 +28,4 @@
  */
 #define __io(a)		(PCIO_BASE + ((a) << 2))
 
-/*
- * 1:1 mapping for ioremapped regions.
- */
-#define __mem_pci(x)	(x)
-
 #endif
diff --git a/arch/arm/mach-s3c24xx/include/mach/io.h b/arch/arm/mach-s3c24xx/include/mach/io.h
index 118749f..5dd1db4 100644
--- a/arch/arm/mach-s3c24xx/include/mach/io.h
+++ b/arch/arm/mach-s3c24xx/include/mach/io.h
@@ -208,9 +208,4 @@
 #define outsw(p,d,l)	__raw_writesw(__ioaddr(p),d,l)
 #define outsl(p,d,l)	__raw_writesl(__ioaddr(p),d,l)
 
-/*
- * 1:1 mapping for ioremapped regions.
- */
-#define __mem_pci(x)	(x)
-
 #endif
diff --git a/arch/arm/mach-s3c64xx/include/mach/io.h b/arch/arm/mach-s3c64xx/include/mach/io.h
deleted file mode 100644
index de5716db..0000000
--- a/arch/arm/mach-s3c64xx/include/mach/io.h
+++ /dev/null
@@ -1,18 +0,0 @@
-/* arch/arm/mach-s3c64xxinclude/mach/io.h
- *
- * Copyright 2008 Simtec Electronics
- *	Ben Dooks <ben-linux@fluff.org>
- *
- * Default IO routines for S3C64XX based
- */
-
-#ifndef __ASM_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H
-
-/* No current ISA/PCI bus support. */
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
-
-#define IO_SPACE_LIMIT (0xFFFFFFFF)
-
-#endif
diff --git a/arch/arm/mach-s5p64x0/include/mach/io.h b/arch/arm/mach-s5p64x0/include/mach/io.h
deleted file mode 100644
index a3e095c..0000000
--- a/arch/arm/mach-s5p64x0/include/mach/io.h
+++ /dev/null
@@ -1,25 +0,0 @@
-/* linux/arch/arm/mach-s5p64x0/include/mach/io.h
- *
- * Copyright (c) 2010 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com
- *
- * Copyright 2008 Simtec Electronics
- *	Ben Dooks <ben-linux@fluff.org>
- *
- * Default IO routines for S5P64X0 based
- *
- * 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_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H
-
-/* No current ISA/PCI bus support. */
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
-
-#define IO_SPACE_LIMIT (0xFFFFFFFF)
-
-#endif
diff --git a/arch/arm/mach-s5pc100/include/mach/io.h b/arch/arm/mach-s5pc100/include/mach/io.h
deleted file mode 100644
index 819acf5..0000000
--- a/arch/arm/mach-s5pc100/include/mach/io.h
+++ /dev/null
@@ -1,18 +0,0 @@
-/* arch/arm/mach-s5pc100/include/mach/io.h
- *
- * Copyright 2008 Simtec Electronics
- *	Ben Dooks <ben-linux@fluff.org>
- *
- * Default IO routines for S5PC100 systems
- */
-
-#ifndef __ASM_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H
-
-/* No current ISA/PCI bus support. */
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
-
-#define IO_SPACE_LIMIT (0xFFFFFFFF)
-
-#endif
diff --git a/arch/arm/mach-s5pv210/include/mach/io.h b/arch/arm/mach-s5pv210/include/mach/io.h
deleted file mode 100644
index 5ab9d56..0000000
--- a/arch/arm/mach-s5pv210/include/mach/io.h
+++ /dev/null
@@ -1,26 +0,0 @@
-/* linux/arch/arm/mach-s5pv210/include/mach/io.h
- *
- * Copyright 2008-2010 Ben Dooks <ben-linux@fluff.org>
- *
- * Copyright (c) 2010 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
- *
- * Based on arch/arm/mach-s5p6442/include/mach/io.h
- *
- * Default IO routines for S5PV210
- *
- * 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_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H __FILE__
-
-/* No current ISA/PCI bus support. */
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
-
-#define IO_SPACE_LIMIT (0xFFFFFFFF)
-
-#endif /* __ASM_ARM_ARCH_IO_H */
diff --git a/arch/arm/mach-sa1100/include/mach/io.h b/arch/arm/mach-sa1100/include/mach/io.h
deleted file mode 100644
index dfc27ff..0000000
--- a/arch/arm/mach-sa1100/include/mach/io.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/*
- * arch/arm/mach-sa1100/include/mach/io.h
- *
- * Copyright (C) 1997-1999 Russell King
- *
- * Modifications:
- *  06-12-1997	RMK	Created.
- *  07-04-1999	RMK	Major cleanup
- */
-#ifndef __ASM_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H
-
-/*
- * __io() is required to be an equivalent mapping to __mem_pci() for
- * SOC_COMMON to work.
- */
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
-
-#endif
diff --git a/arch/arm/mach-shark/include/mach/io.h b/arch/arm/mach-shark/include/mach/io.h
index 9ccbcec..1a45fc0 100644
--- a/arch/arm/mach-shark/include/mach/io.h
+++ b/arch/arm/mach-shark/include/mach/io.h
@@ -15,6 +15,4 @@
 
 #define __io(a)                 ((void __iomem *)(0xe0000000 + (a)))
 
-#define __mem_pci(addr) (addr)
-
 #endif
diff --git a/arch/arm/mach-shmobile/Kconfig b/arch/arm/mach-shmobile/Kconfig
index 060e564..34560ca 100644
--- a/arch/arm/mach-shmobile/Kconfig
+++ b/arch/arm/mach-shmobile/Kconfig
@@ -100,6 +100,10 @@
 
 comment "SH-Mobile System Configuration"
 
+config CPU_HAS_INTEVT
+        bool
+	default y
+
 menu "Memory configuration"
 
 config MEMORY_START
diff --git a/arch/arm/mach-shmobile/board-ag5evm.c b/arch/arm/mach-shmobile/board-ag5evm.c
index f50d7c8..cb224a3 100644
--- a/arch/arm/mach-shmobile/board-ag5evm.c
+++ b/arch/arm/mach-shmobile/board-ag5evm.c
@@ -43,6 +43,7 @@
 #include <video/sh_mipi_dsi.h>
 #include <sound/sh_fsi.h>
 #include <mach/hardware.h>
+#include <mach/irqs.h>
 #include <mach/sh73a0.h>
 #include <mach/common.h>
 #include <asm/mach-types.h>
@@ -584,7 +585,7 @@
 
 #ifdef CONFIG_CACHE_L2X0
 	/* Shared attribute override enable, 64K*8way */
-	l2x0_init(__io(0xf0100000), 0x00460000, 0xc2000fff);
+	l2x0_init(IOMEM(0xf0100000), 0x00460000, 0xc2000fff);
 #endif
 	sh73a0_add_standard_devices();
 	platform_add_devices(ag5evm_devices, ARRAY_SIZE(ag5evm_devices));
diff --git a/arch/arm/mach-shmobile/board-bonito.c b/arch/arm/mach-shmobile/board-bonito.c
index 8b2124d..81fd95f 100644
--- a/arch/arm/mach-shmobile/board-bonito.c
+++ b/arch/arm/mach-shmobile/board-bonito.c
@@ -35,6 +35,7 @@
 #include <asm/mach/time.h>
 #include <asm/hardware/cache-l2x0.h>
 #include <mach/r8a7740.h>
+#include <mach/irqs.h>
 #include <video/sh_mobile_lcdc.h>
 
 /*
@@ -370,7 +371,7 @@
 
 #ifdef CONFIG_CACHE_L2X0
 	/* Early BRESP enable, Shared attribute override enable, 32K*8way */
-	l2x0_init(__io(0xf0002000), 0x40440000, 0x82000fff);
+	l2x0_init(IOMEM(0xf0002000), 0x40440000, 0x82000fff);
 #endif
 
 	r8a7740_add_standard_devices();
diff --git a/arch/arm/mach-shmobile/board-g3evm.c b/arch/arm/mach-shmobile/board-g3evm.c
index b627e89..39b6cf8 100644
--- a/arch/arm/mach-shmobile/board-g3evm.c
+++ b/arch/arm/mach-shmobile/board-g3evm.c
@@ -33,6 +33,7 @@
 #include <linux/input.h>
 #include <linux/input/sh_keysc.h>
 #include <linux/dma-mapping.h>
+#include <mach/irqs.h>
 #include <mach/sh7367.h>
 #include <mach/common.h>
 #include <asm/mach-types.h>
diff --git a/arch/arm/mach-shmobile/board-g4evm.c b/arch/arm/mach-shmobile/board-g4evm.c
index 46d757d..0e5a39c 100644
--- a/arch/arm/mach-shmobile/board-g4evm.c
+++ b/arch/arm/mach-shmobile/board-g4evm.c
@@ -34,6 +34,7 @@
 #include <linux/mmc/sh_mobile_sdhi.h>
 #include <linux/gpio.h>
 #include <linux/dma-mapping.h>
+#include <mach/irqs.h>
 #include <mach/sh7377.h>
 #include <mach/common.h>
 #include <asm/mach-types.h>
diff --git a/arch/arm/mach-shmobile/board-kota2.c b/arch/arm/mach-shmobile/board-kota2.c
index 61c0672..200dcd4 100644
--- a/arch/arm/mach-shmobile/board-kota2.c
+++ b/arch/arm/mach-shmobile/board-kota2.c
@@ -39,6 +39,7 @@
 #include <linux/mfd/tmio.h>
 #include <linux/mmc/sh_mobile_sdhi.h>
 #include <mach/hardware.h>
+#include <mach/irqs.h>
 #include <mach/sh73a0.h>
 #include <mach/common.h>
 #include <asm/mach-types.h>
@@ -507,7 +508,7 @@
 
 #ifdef CONFIG_CACHE_L2X0
 	/* Early BRESP enable, Shared attribute override enable, 64K*8way */
-	l2x0_init(__io(0xf0100000), 0x40460000, 0x82000fff);
+	l2x0_init(IOMEM(0xf0100000), 0x40460000, 0x82000fff);
 #endif
 	sh73a0_add_standard_devices();
 	platform_add_devices(kota2_devices, ARRAY_SIZE(kota2_devices));
diff --git a/arch/arm/mach-shmobile/board-mackerel.c b/arch/arm/mach-shmobile/board-mackerel.c
index ca60950..a125d4e 100644
--- a/arch/arm/mach-shmobile/board-mackerel.c
+++ b/arch/arm/mach-shmobile/board-mackerel.c
@@ -54,6 +54,7 @@
 #include <sound/sh_fsi.h>
 
 #include <mach/common.h>
+#include <mach/irqs.h>
 #include <mach/sh7372.h>
 
 #include <asm/mach/arch.h>
diff --git a/arch/arm/mach-shmobile/board-marzen.c b/arch/arm/mach-shmobile/board-marzen.c
index cbd5e4c..ef0e13b 100644
--- a/arch/arm/mach-shmobile/board-marzen.c
+++ b/arch/arm/mach-shmobile/board-marzen.c
@@ -31,6 +31,7 @@
 #include <mach/hardware.h>
 #include <mach/r8a7779.h>
 #include <mach/common.h>
+#include <mach/irqs.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 #include <asm/hardware/gic.h>
diff --git a/arch/arm/mach-shmobile/include/mach/io.h b/arch/arm/mach-shmobile/include/mach/io.h
deleted file mode 100644
index 7339fe4..0000000
--- a/arch/arm/mach-shmobile/include/mach/io.h
+++ /dev/null
@@ -1,9 +0,0 @@
-#ifndef __ASM_MACH_IO_H
-#define __ASM_MACH_IO_H
-
-#define IO_SPACE_LIMIT		0xffffffff
-
-#define __io(a)			((void __iomem *)(a))
-#define __mem_pci(a)		(a)
-
-#endif /* __ASM_MACH_IO_H */
diff --git a/arch/arm/mach-shmobile/include/mach/irqs.h b/arch/arm/mach-shmobile/include/mach/irqs.h
index dcb714f..4e686cc2 100644
--- a/arch/arm/mach-shmobile/include/mach/irqs.h
+++ b/arch/arm/mach-shmobile/include/mach/irqs.h
@@ -1,15 +1,11 @@
 #ifndef __ASM_MACH_IRQS_H
 #define __ASM_MACH_IRQS_H
 
-#define NR_IRQS         1024
+#include <linux/sh_intc.h>
 
 /* GIC */
 #define gic_spi(nr)		((nr) + 32)
 
-/* INTCA */
-#define evt2irq(evt)		(((evt) >> 5) - 16)
-#define irq2evt(irq)		(((irq) + 16) << 5)
-
 /* INTCS */
 #define INTCS_VECT_BASE		0x2200
 #define INTCS_VECT(n, vect)	INTC_VECT((n), INTCS_VECT_BASE + (vect))
diff --git a/arch/arm/mach-shmobile/intc-r8a7740.c b/arch/arm/mach-shmobile/intc-r8a7740.c
index 272c84c2..09c42afc 100644
--- a/arch/arm/mach-shmobile/intc-r8a7740.c
+++ b/arch/arm/mach-shmobile/intc-r8a7740.c
@@ -25,6 +25,7 @@
 #include <linux/io.h>
 #include <linux/sh_intc.h>
 #include <mach/intc.h>
+#include <mach/irqs.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 
diff --git a/arch/arm/mach-shmobile/intc-r8a7779.c b/arch/arm/mach-shmobile/intc-r8a7779.c
index 5d92fcd..550b23d 100644
--- a/arch/arm/mach-shmobile/intc-r8a7779.c
+++ b/arch/arm/mach-shmobile/intc-r8a7779.c
@@ -42,8 +42,8 @@
 
 void __init r8a7779_init_irq(void)
 {
-	void __iomem *gic_dist_base = __io(0xf0001000);
-	void __iomem *gic_cpu_base = __io(0xf0000100);
+	void __iomem *gic_dist_base = IOMEM(0xf0001000);
+	void __iomem *gic_cpu_base = IOMEM(0xf0000100);
 
 	/* use GIC to handle interrupts */
 	gic_init(0, 29, gic_dist_base, gic_cpu_base);
diff --git a/arch/arm/mach-shmobile/intc-sh7367.c b/arch/arm/mach-shmobile/intc-sh7367.c
index cfde9bf..5bf7764 100644
--- a/arch/arm/mach-shmobile/intc-sh7367.c
+++ b/arch/arm/mach-shmobile/intc-sh7367.c
@@ -23,6 +23,7 @@
 #include <linux/io.h>
 #include <linux/sh_intc.h>
 #include <mach/intc.h>
+#include <mach/irqs.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 
diff --git a/arch/arm/mach-shmobile/intc-sh7372.c b/arch/arm/mach-shmobile/intc-sh7372.c
index 89afcab..6447e0a 100644
--- a/arch/arm/mach-shmobile/intc-sh7372.c
+++ b/arch/arm/mach-shmobile/intc-sh7372.c
@@ -23,6 +23,7 @@
 #include <linux/io.h>
 #include <linux/sh_intc.h>
 #include <mach/intc.h>
+#include <mach/irqs.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 
diff --git a/arch/arm/mach-shmobile/intc-sh7377.c b/arch/arm/mach-shmobile/intc-sh7377.c
index 2af4e6e..b84a460 100644
--- a/arch/arm/mach-shmobile/intc-sh7377.c
+++ b/arch/arm/mach-shmobile/intc-sh7377.c
@@ -23,6 +23,7 @@
 #include <linux/io.h>
 #include <linux/sh_intc.h>
 #include <mach/intc.h>
+#include <mach/irqs.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 
diff --git a/arch/arm/mach-shmobile/intc-sh73a0.c b/arch/arm/mach-shmobile/intc-sh73a0.c
index 9857595..ee44740 100644
--- a/arch/arm/mach-shmobile/intc-sh73a0.c
+++ b/arch/arm/mach-shmobile/intc-sh73a0.c
@@ -24,6 +24,7 @@
 #include <linux/io.h>
 #include <linux/sh_intc.h>
 #include <mach/intc.h>
+#include <mach/irqs.h>
 #include <mach/sh73a0.h>
 #include <asm/hardware/gic.h>
 #include <asm/mach-types.h>
@@ -420,8 +421,8 @@
 
 void __init sh73a0_init_irq(void)
 {
-	void __iomem *gic_dist_base = __io(0xf0001000);
-	void __iomem *gic_cpu_base = __io(0xf0000100);
+	void __iomem *gic_dist_base = IOMEM(0xf0001000);
+	void __iomem *gic_cpu_base = IOMEM(0xf0000100);
 	void __iomem *intevtsa = ioremap_nocache(0xffd20100, PAGE_SIZE);
 	int k, n;
 
diff --git a/arch/arm/mach-shmobile/setup-r8a7740.c b/arch/arm/mach-shmobile/setup-r8a7740.c
index 74e5234..14edb5c 100644
--- a/arch/arm/mach-shmobile/setup-r8a7740.c
+++ b/arch/arm/mach-shmobile/setup-r8a7740.c
@@ -26,6 +26,7 @@
 #include <linux/sh_timer.h>
 #include <mach/r8a7740.h>
 #include <mach/common.h>
+#include <mach/irqs.h>
 #include <asm/mach-types.h>
 #include <asm/mach/map.h>
 #include <asm/mach/arch.h>
diff --git a/arch/arm/mach-shmobile/setup-r8a7779.c b/arch/arm/mach-shmobile/setup-r8a7779.c
index 6820d78..12c6f52 100644
--- a/arch/arm/mach-shmobile/setup-r8a7779.c
+++ b/arch/arm/mach-shmobile/setup-r8a7779.c
@@ -29,6 +29,7 @@
 #include <linux/sh_intc.h>
 #include <linux/sh_timer.h>
 #include <mach/hardware.h>
+#include <mach/irqs.h>
 #include <mach/r8a7779.h>
 #include <mach/common.h>
 #include <asm/mach-types.h>
diff --git a/arch/arm/mach-shmobile/setup-sh7367.c b/arch/arm/mach-shmobile/setup-sh7367.c
index a51e1a1..2e3074a 100644
--- a/arch/arm/mach-shmobile/setup-sh7367.c
+++ b/arch/arm/mach-shmobile/setup-sh7367.c
@@ -30,6 +30,7 @@
 #include <linux/sh_timer.h>
 #include <mach/hardware.h>
 #include <mach/common.h>
+#include <mach/irqs.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
diff --git a/arch/arm/mach-shmobile/setup-sh7372.c b/arch/arm/mach-shmobile/setup-sh7372.c
index 4e818b7..2fe8f83 100644
--- a/arch/arm/mach-shmobile/setup-sh7372.c
+++ b/arch/arm/mach-shmobile/setup-sh7372.c
@@ -33,6 +33,7 @@
 #include <linux/pm_domain.h>
 #include <linux/dma-mapping.h>
 #include <mach/hardware.h>
+#include <mach/irqs.h>
 #include <mach/sh7372.h>
 #include <mach/common.h>
 #include <asm/mach/map.h>
diff --git a/arch/arm/mach-shmobile/setup-sh7377.c b/arch/arm/mach-shmobile/setup-sh7377.c
index 9f14609..d576a6a 100644
--- a/arch/arm/mach-shmobile/setup-sh7377.c
+++ b/arch/arm/mach-shmobile/setup-sh7377.c
@@ -32,6 +32,7 @@
 #include <mach/hardware.h>
 #include <mach/common.h>
 #include <asm/mach/map.h>
+#include <mach/irqs.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/time.h>
diff --git a/arch/arm/mach-shmobile/setup-sh73a0.c b/arch/arm/mach-shmobile/setup-sh73a0.c
index b6a0734..5bebffc 100644
--- a/arch/arm/mach-shmobile/setup-sh73a0.c
+++ b/arch/arm/mach-shmobile/setup-sh73a0.c
@@ -31,6 +31,7 @@
 #include <linux/sh_intc.h>
 #include <linux/sh_timer.h>
 #include <mach/hardware.h>
+#include <mach/irqs.h>
 #include <mach/sh73a0.h>
 #include <mach/common.h>
 #include <asm/mach-types.h>
diff --git a/arch/arm/mach-shmobile/smp-r8a7779.c b/arch/arm/mach-shmobile/smp-r8a7779.c
index 9bb7b857..b62e19d 100644
--- a/arch/arm/mach-shmobile/smp-r8a7779.c
+++ b/arch/arm/mach-shmobile/smp-r8a7779.c
@@ -30,7 +30,7 @@
 #include <asm/smp_twd.h>
 #include <asm/hardware/gic.h>
 
-#define AVECR 0xfe700040
+#define AVECR IOMEM(0xfe700040)
 
 static struct r8a7779_pm_ch r8a7779_ch_cpu1 = {
 	.chan_offs = 0x40, /* PWRSR0 .. PWRER0 */
@@ -138,7 +138,7 @@
 	scu_enable(scu_base_addr());
 
 	/* Map the reset vector (in headsmp.S) */
-	__raw_writel(__pa(shmobile_secondary_vector), __io(AVECR));
+	__raw_writel(__pa(shmobile_secondary_vector), AVECR);
 
 	/* enable cache coherency on CPU0 */
 	modify_scu_cpu_psr(0, 3 << (cpu * 8));
diff --git a/arch/arm/mach-shmobile/smp-sh73a0.c b/arch/arm/mach-shmobile/smp-sh73a0.c
index c0a9093..14ad8b05 100644
--- a/arch/arm/mach-shmobile/smp-sh73a0.c
+++ b/arch/arm/mach-shmobile/smp-sh73a0.c
@@ -28,11 +28,11 @@
 #include <asm/smp_twd.h>
 #include <asm/hardware/gic.h>
 
-#define WUPCR		0xe6151010
-#define SRESCR		0xe6151018
-#define PSTR		0xe6151040
-#define SBAR            0xe6180020
-#define APARMBAREA      0xe6f10020
+#define WUPCR		IOMEM(0xe6151010)
+#define SRESCR		IOMEM(0xe6151018)
+#define PSTR		IOMEM(0xe6151040)
+#define SBAR		IOMEM(0xe6180020)
+#define APARMBAREA	IOMEM(0xe6f10020)
 
 static void __iomem *scu_base_addr(void)
 {
@@ -78,10 +78,10 @@
 	/* enable cache coherency */
 	modify_scu_cpu_psr(0, 3 << (cpu * 8));
 
-	if (((__raw_readl(__io(PSTR)) >> (4 * cpu)) & 3) == 3)
-		__raw_writel(1 << cpu, __io(WUPCR));	/* wake up */
+	if (((__raw_readl(PSTR) >> (4 * cpu)) & 3) == 3)
+		__raw_writel(1 << cpu, WUPCR);	/* wake up */
 	else
-		__raw_writel(1 << cpu, __io(SRESCR));	/* reset */
+		__raw_writel(1 << cpu, SRESCR);	/* reset */
 
 	return 0;
 }
@@ -93,8 +93,8 @@
 	scu_enable(scu_base_addr());
 
 	/* Map the reset vector (in headsmp.S) */
-	__raw_writel(0, __io(APARMBAREA));      /* 4k */
-	__raw_writel(__pa(shmobile_secondary_vector), __io(SBAR));
+	__raw_writel(0, APARMBAREA);      /* 4k */
+	__raw_writel(__pa(shmobile_secondary_vector), SBAR);
 
 	/* enable cache coherency on CPU0 */
 	modify_scu_cpu_psr(0, 3 << (cpu * 8));
diff --git a/arch/arm/mach-spear3xx/clock.c b/arch/arm/mach-spear3xx/clock.c
index f67860c..6c4841f 100644
--- a/arch/arm/mach-spear3xx/clock.c
+++ b/arch/arm/mach-spear3xx/clock.c
@@ -12,6 +12,7 @@
  */
 
 #include <linux/init.h>
+#include <linux/io.h>
 #include <linux/kernel.h>
 #include <asm/mach-types.h>
 #include <plat/clock.h>
diff --git a/arch/arm/mach-spear3xx/include/mach/io.h b/arch/arm/mach-spear3xx/include/mach/io.h
deleted file mode 100644
index 30cff8a..0000000
--- a/arch/arm/mach-spear3xx/include/mach/io.h
+++ /dev/null
@@ -1,19 +0,0 @@
-/*
- * arch/arm/mach-spear3xx/include/mach/io.h
- *
- * IO definitions for SPEAr3xx machine family
- *
- * Copyright (C) 2009 ST Microelectronics
- * Viresh Kumar<viresh.kumar@st.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- */
-
-#ifndef __MACH_IO_H
-#define __MACH_IO_H
-
-#include <plat/io.h>
-
-#endif /* __MACH_IO_H */
diff --git a/arch/arm/mach-spear6xx/clock.c b/arch/arm/mach-spear6xx/clock.c
index 358f280..a86499a 100644
--- a/arch/arm/mach-spear6xx/clock.c
+++ b/arch/arm/mach-spear6xx/clock.c
@@ -12,6 +12,7 @@
  */
 
 #include <linux/init.h>
+#include <linux/io.h>
 #include <linux/kernel.h>
 #include <plat/clock.h>
 #include <mach/misc_regs.h>
diff --git a/arch/arm/mach-spear6xx/include/mach/io.h b/arch/arm/mach-spear6xx/include/mach/io.h
deleted file mode 100644
index fb7c106..0000000
--- a/arch/arm/mach-spear6xx/include/mach/io.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/*
- * arch/arm/mach-spear6xx/include/mach/io.h
- *
- * IO definitions for SPEAr6xx machine family
- *
- * Copyright (C) 2009 ST Microelectronics
- * Rajeev Kumar Kumar<rajeev-dlh.kumar@st.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- */
-
-#ifndef __MACH_IO_H
-#define __MACH_IO_H
-
-#include <plat/io.h>
-
-#endif	/* __MACH_IO_H */
-
diff --git a/arch/arm/mach-tegra/board-dt-tegra20.c b/arch/arm/mach-tegra/board-dt-tegra20.c
index e20b419..0952494 100644
--- a/arch/arm/mach-tegra/board-dt-tegra20.c
+++ b/arch/arm/mach-tegra/board-dt-tegra20.c
@@ -68,11 +68,11 @@
 	OF_DEV_AUXDATA("nvidia,tegra20-i2s", TEGRA_I2S2_BASE, "tegra-i2s.1", NULL),
 	OF_DEV_AUXDATA("nvidia,tegra20-das", TEGRA_APB_MISC_DAS_BASE, "tegra-das", NULL),
 	OF_DEV_AUXDATA("nvidia,tegra20-ehci", TEGRA_USB_BASE, "tegra-ehci.0",
-		       &tegra_ehci1_device.dev.platform_data),
+		       &tegra_ehci1_pdata),
 	OF_DEV_AUXDATA("nvidia,tegra20-ehci", TEGRA_USB2_BASE, "tegra-ehci.1",
-		       &tegra_ehci2_device.dev.platform_data),
+		       &tegra_ehci2_pdata),
 	OF_DEV_AUXDATA("nvidia,tegra20-ehci", TEGRA_USB3_BASE, "tegra-ehci.2",
-		       &tegra_ehci3_device.dev.platform_data),
+		       &tegra_ehci3_pdata),
 	{}
 };
 
diff --git a/arch/arm/mach-tegra/devices.c b/arch/arm/mach-tegra/devices.c
index 7a2a02d..5f6b867 100644
--- a/arch/arm/mach-tegra/devices.c
+++ b/arch/arm/mach-tegra/devices.c
@@ -23,7 +23,6 @@
 #include <linux/fsl_devices.h>
 #include <linux/serial_8250.h>
 #include <linux/i2c-tegra.h>
-#include <linux/platform_data/tegra_usb.h>
 #include <asm/pmu.h>
 #include <mach/irqs.h>
 #include <mach/iomap.h>
@@ -446,18 +445,18 @@
 	.clk = "cdev2",
 };
 
-static struct tegra_ehci_platform_data tegra_ehci1_pdata = {
+struct tegra_ehci_platform_data tegra_ehci1_pdata = {
 	.operating_mode = TEGRA_USB_OTG,
 	.power_down_on_bus_suspend = 1,
 };
 
-static struct tegra_ehci_platform_data tegra_ehci2_pdata = {
+struct tegra_ehci_platform_data tegra_ehci2_pdata = {
 	.phy_config = &tegra_ehci2_ulpi_phy_config,
 	.operating_mode = TEGRA_USB_HOST,
 	.power_down_on_bus_suspend = 1,
 };
 
-static struct tegra_ehci_platform_data tegra_ehci3_pdata = {
+struct tegra_ehci_platform_data tegra_ehci3_pdata = {
 	.operating_mode = TEGRA_USB_HOST,
 	.power_down_on_bus_suspend = 1,
 };
diff --git a/arch/arm/mach-tegra/devices.h b/arch/arm/mach-tegra/devices.h
index 873ecb2..ec45567 100644
--- a/arch/arm/mach-tegra/devices.h
+++ b/arch/arm/mach-tegra/devices.h
@@ -20,6 +20,11 @@
 #define __MACH_TEGRA_DEVICES_H
 
 #include <linux/platform_device.h>
+#include <linux/platform_data/tegra_usb.h>
+
+extern struct tegra_ehci_platform_data tegra_ehci1_pdata;
+extern struct tegra_ehci_platform_data tegra_ehci2_pdata;
+extern struct tegra_ehci_platform_data tegra_ehci3_pdata;
 
 extern struct platform_device tegra_gpio_device;
 extern struct platform_device tegra_pinmux_device;
diff --git a/arch/arm/mach-tegra/include/mach/debug-macro.S b/arch/arm/mach-tegra/include/mach/debug-macro.S
index 90069ab..8ce0661 100644
--- a/arch/arm/mach-tegra/include/mach/debug-macro.S
+++ b/arch/arm/mach-tegra/include/mach/debug-macro.S
@@ -26,7 +26,6 @@
 
 #include <linux/serial_reg.h>
 
-#include <mach/io.h>
 #include <mach/iomap.h>
 #include <mach/irammap.h>
 
diff --git a/arch/arm/mach-tegra/include/mach/io.h b/arch/arm/mach-tegra/include/mach/io.h
index f15deff..fe700f9 100644
--- a/arch/arm/mach-tegra/include/mach/io.h
+++ b/arch/arm/mach-tegra/include/mach/io.h
@@ -23,56 +23,8 @@
 
 #define IO_SPACE_LIMIT 0xffff
 
-/* On TEGRA, many peripherals are very closely packed in
- * two 256MB io windows (that actually only use about 64KB
- * at the start of each).
- *
- * We will just map the first 1MB of each window (to minimize
- * pt entries needed) and provide a macro to transform physical
- * io addresses to an appropriate void __iomem *.
- *
- */
-
-#ifdef __ASSEMBLY__
-#define IOMEM(x)	(x)
-#else
-#define IOMEM(x)	((void __force __iomem *)(x))
-#endif
-
-#define IO_IRAM_PHYS	0x40000000
-#define IO_IRAM_VIRT	IOMEM(0xFE400000)
-#define IO_IRAM_SIZE	SZ_256K
-
-#define IO_CPU_PHYS     0x50040000
-#define IO_CPU_VIRT     IOMEM(0xFE000000)
-#define IO_CPU_SIZE	SZ_16K
-
-#define IO_PPSB_PHYS	0x60000000
-#define IO_PPSB_VIRT	IOMEM(0xFE200000)
-#define IO_PPSB_SIZE	SZ_1M
-
-#define IO_APB_PHYS	0x70000000
-#define IO_APB_VIRT	IOMEM(0xFE300000)
-#define IO_APB_SIZE	SZ_1M
-
-#define IO_TO_VIRT_BETWEEN(p, st, sz)	((p) >= (st) && (p) < ((st) + (sz)))
-#define IO_TO_VIRT_XLATE(p, pst, vst)	(((p) - (pst) + (vst)))
-
-#define IO_TO_VIRT(n) ( \
-	IO_TO_VIRT_BETWEEN((n), IO_PPSB_PHYS, IO_PPSB_SIZE) ?		\
-		IO_TO_VIRT_XLATE((n), IO_PPSB_PHYS, IO_PPSB_VIRT) :	\
-	IO_TO_VIRT_BETWEEN((n), IO_APB_PHYS, IO_APB_SIZE) ?		\
-		IO_TO_VIRT_XLATE((n), IO_APB_PHYS, IO_APB_VIRT) :	\
-	IO_TO_VIRT_BETWEEN((n), IO_CPU_PHYS, IO_CPU_SIZE) ?		\
-		IO_TO_VIRT_XLATE((n), IO_CPU_PHYS, IO_CPU_VIRT) :	\
-	IO_TO_VIRT_BETWEEN((n), IO_IRAM_PHYS, IO_IRAM_SIZE) ?		\
-		IO_TO_VIRT_XLATE((n), IO_IRAM_PHYS, IO_IRAM_VIRT) :	\
-	NULL)
-
 #ifndef __ASSEMBLER__
 
-#define IO_ADDRESS(n) (IO_TO_VIRT(n))
-
 #ifdef CONFIG_TEGRA_PCI
 extern void __iomem *tegra_pcie_io_base;
 
@@ -88,7 +40,6 @@
 #endif
 
 #define __io(a)         __io(a)
-#define __mem_pci(a)    (a)
 
 #endif
 
diff --git a/arch/arm/mach-tegra/include/mach/iomap.h b/arch/arm/mach-tegra/include/mach/iomap.h
index cff672a..7e76da7 100644
--- a/arch/arm/mach-tegra/include/mach/iomap.h
+++ b/arch/arm/mach-tegra/include/mach/iomap.h
@@ -277,4 +277,46 @@
 # define TEGRA_DEBUG_UART_BASE TEGRA_UARTE_BASE
 #endif
 
+/* On TEGRA, many peripherals are very closely packed in
+ * two 256MB io windows (that actually only use about 64KB
+ * at the start of each).
+ *
+ * We will just map the first 1MB of each window (to minimize
+ * pt entries needed) and provide a macro to transform physical
+ * io addresses to an appropriate void __iomem *.
+ *
+ */
+
+#define IO_IRAM_PHYS	0x40000000
+#define IO_IRAM_VIRT	IOMEM(0xFE400000)
+#define IO_IRAM_SIZE	SZ_256K
+
+#define IO_CPU_PHYS     0x50040000
+#define IO_CPU_VIRT     IOMEM(0xFE000000)
+#define IO_CPU_SIZE	SZ_16K
+
+#define IO_PPSB_PHYS	0x60000000
+#define IO_PPSB_VIRT	IOMEM(0xFE200000)
+#define IO_PPSB_SIZE	SZ_1M
+
+#define IO_APB_PHYS	0x70000000
+#define IO_APB_VIRT	IOMEM(0xFE300000)
+#define IO_APB_SIZE	SZ_1M
+
+#define IO_TO_VIRT_BETWEEN(p, st, sz)	((p) >= (st) && (p) < ((st) + (sz)))
+#define IO_TO_VIRT_XLATE(p, pst, vst)	(((p) - (pst) + (vst)))
+
+#define IO_TO_VIRT(n) ( \
+	IO_TO_VIRT_BETWEEN((n), IO_PPSB_PHYS, IO_PPSB_SIZE) ?		\
+		IO_TO_VIRT_XLATE((n), IO_PPSB_PHYS, IO_PPSB_VIRT) :	\
+	IO_TO_VIRT_BETWEEN((n), IO_APB_PHYS, IO_APB_SIZE) ?		\
+		IO_TO_VIRT_XLATE((n), IO_APB_PHYS, IO_APB_VIRT) :	\
+	IO_TO_VIRT_BETWEEN((n), IO_CPU_PHYS, IO_CPU_SIZE) ?		\
+		IO_TO_VIRT_XLATE((n), IO_CPU_PHYS, IO_CPU_VIRT) :	\
+	IO_TO_VIRT_BETWEEN((n), IO_IRAM_PHYS, IO_IRAM_SIZE) ?		\
+		IO_TO_VIRT_XLATE((n), IO_IRAM_PHYS, IO_IRAM_VIRT) :	\
+	NULL)
+
+#define IO_ADDRESS(n) (IO_TO_VIRT(n))
+
 #endif
diff --git a/arch/arm/mach-tegra/io.c b/arch/arm/mach-tegra/io.c
index d23ee2d..58b4baf 100644
--- a/arch/arm/mach-tegra/io.c
+++ b/arch/arm/mach-tegra/io.c
@@ -26,6 +26,7 @@
 
 #include <asm/page.h>
 #include <asm/mach/map.h>
+#include <mach/iomap.h>
 
 #include "board.h"
 
diff --git a/arch/arm/mach-tegra/sleep.S b/arch/arm/mach-tegra/sleep.S
index 8f9fde1..5b20197 100644
--- a/arch/arm/mach-tegra/sleep.S
+++ b/arch/arm/mach-tegra/sleep.S
@@ -23,7 +23,9 @@
  */
 
 #include <linux/linkage.h>
-#include <mach/io.h>
+
+#include <asm/assembler.h>
+
 #include <mach/iomap.h>
 
 #include "flowctrl.h"
diff --git a/arch/arm/mach-u300/include/mach/io.h b/arch/arm/mach-u300/include/mach/io.h
deleted file mode 100644
index 5d6b4c1..0000000
--- a/arch/arm/mach-u300/include/mach/io.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/*
- *
- * arch/arm/mach-u300/include/mach/io.h
- *
- *
- * Copyright (C) 2006-2009 ST-Ericsson AB
- * License terms: GNU General Public License (GPL) version 2
- * Dummy IO map for being able to use writew()/readw(),
- * writel()/readw() and similar accessor functions.
- * Author: Linus Walleij <linus.walleij@stericsson.com>
- */
-#ifndef __MACH_IO_H
-#define __MACH_IO_H
-
-#define IO_SPACE_LIMIT 0xffffffff
-
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
-
-#endif
diff --git a/arch/arm/mach-u300/include/mach/u300-regs.h b/arch/arm/mach-u300/include/mach/u300-regs.h
index 035fdc9..7b7cba9 100644
--- a/arch/arm/mach-u300/include/mach/u300-regs.h
+++ b/arch/arm/mach-u300/include/mach/u300-regs.h
@@ -18,12 +18,6 @@
  * the defines are used for setting up the I/O memory mapping.
  */
 
-#ifdef __ASSEMBLER__
-#define IOMEM(a) (a)
-#else
-#define IOMEM(a) (void __iomem *) a
-#endif
-
 /* NAND Flash CS0 */
 #define U300_NAND_CS0_PHYS_BASE		0x80000000
 
diff --git a/arch/arm/mach-ux500/include/mach/hardware.h b/arch/arm/mach-ux500/include/mach/hardware.h
index d93d6db..f846989 100644
--- a/arch/arm/mach-ux500/include/mach/hardware.h
+++ b/arch/arm/mach-ux500/include/mach/hardware.h
@@ -23,7 +23,7 @@
 	(((x) & 0x0fffffff) + (((x) >> 4) & 0x0f000000) + U8500_IO_VIRTUAL)
 
 /* typesafe io address */
-#define __io_address(n)		__io(IO_ADDRESS(n))
+#define __io_address(n)		IOMEM(IO_ADDRESS(n))
 /* Used by some plat-nomadik code */
 #define io_p2v(n)		__io_address(n)
 
diff --git a/arch/arm/mach-ux500/include/mach/io.h b/arch/arm/mach-ux500/include/mach/io.h
deleted file mode 100644
index 1cf3f44..0000000
--- a/arch/arm/mach-ux500/include/mach/io.h
+++ /dev/null
@@ -1,22 +0,0 @@
-/*
- * arch/arm/mach-u8500/include/mach/io.h
- *
- * Copyright (C) 1997-1999 Russell King
- *
- * Modifications:
- *  06-12-1997	RMK	Created.
- *  07-04-1999	RMK	Major cleanup
- */
-#ifndef __ASM_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H
-
-#define IO_SPACE_LIMIT 0xffffffff
-
-/*
- * We don't actually have real ISA nor PCI buses, but there is so many
- * drivers out there that might just work if we fake them...
- */
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
-
-#endif
diff --git a/arch/arm/mach-versatile/include/mach/io.h b/arch/arm/mach-versatile/include/mach/io.h
deleted file mode 100644
index f067c14..0000000
--- a/arch/arm/mach-versatile/include/mach/io.h
+++ /dev/null
@@ -1,28 +0,0 @@
-/*
- *  arch/arm/mach-versatile/include/mach/io.h
- *
- *  Copyright (C) 2003 ARM Limited
- *
- * 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 __ASM_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H
-
-#define IO_SPACE_LIMIT 0xffffffff
-
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
-
-#endif
diff --git a/arch/arm/mach-vexpress/include/mach/io.h b/arch/arm/mach-vexpress/include/mach/io.h
deleted file mode 100644
index 13522d8..0000000
--- a/arch/arm/mach-vexpress/include/mach/io.h
+++ /dev/null
@@ -1,26 +0,0 @@
-/*
- *  arch/arm/mach-vexpress/include/mach/io.h
- *
- *  Copyright (C) 2003 ARM Limited
- *
- * 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 __ASM_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H
-
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
-
-#endif
diff --git a/arch/arm/mach-vt8500/include/mach/io.h b/arch/arm/mach-vt8500/include/mach/io.h
deleted file mode 100644
index 46181ee..0000000
--- a/arch/arm/mach-vt8500/include/mach/io.h
+++ /dev/null
@@ -1,26 +0,0 @@
-/*
- *  arch/arm/mach-vt8500/include/mach/io.h
- *
- *  Copyright (C) 2010 Alexey Charkov
- *
- * 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 __ASM_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H
-
-#define __io(a)		__typesafe_io((a) + 0xf0000000)
-#define __mem_pci(a)	(a)
-
-#endif
diff --git a/arch/arm/mach-w90x900/include/mach/io.h b/arch/arm/mach-w90x900/include/mach/io.h
deleted file mode 100644
index d96ab99..0000000
--- a/arch/arm/mach-w90x900/include/mach/io.h
+++ /dev/null
@@ -1,30 +0,0 @@
-/*
- * arch/arm/mach-w90x900/include/mach/io.h
- *
- * Copyright (c) 2008 Nuvoton technology corporation
- * All rights reserved.
- *
- * Wan ZongShun <mcuos.com@gmail.com>
- *
- * Based on arch/arm/mach-s3c2410/include/mach/io.h
- *
- * 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.
- *
- */
-
-#ifndef __ASM_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H
-
-#define IO_SPACE_LIMIT	0xffffffff
-
-/*
- * 1:1 mapping for ioremapped regions.
- */
-
-#define __mem_pci(a)	(a)
-#define __io(a)		__typesafe_io(a)
-
-#endif
diff --git a/arch/arm/mach-zynq/include/mach/io.h b/arch/arm/mach-zynq/include/mach/io.h
deleted file mode 100644
index 39d9885..0000000
--- a/arch/arm/mach-zynq/include/mach/io.h
+++ /dev/null
@@ -1,33 +0,0 @@
-/* arch/arm/mach-zynq/include/mach/io.h
- *
- *  Copyright (C) 2011 Xilinx
- *
- * 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 __MACH_IO_H__
-#define __MACH_IO_H__
-
-/* Allow IO space to be anywhere in the memory */
-
-#define IO_SPACE_LIMIT 0xffff
-
-/* IO address mapping macros, nothing special at this time but required */
-
-#ifdef __ASSEMBLER__
-#define IOMEM(x)		(x)
-#else
-#define IOMEM(x)		((void __force __iomem *)(x))
-#endif
-
-#define __io(a)			__typesafe_io(a)
-#define __mem_pci(a)		(a)
-
-#endif
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index b1e192b..a53fd2a 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -30,13 +30,13 @@
 
 static void __iomem *l2x0_base;
 static DEFINE_RAW_SPINLOCK(l2x0_lock);
-static uint32_t l2x0_way_mask;	/* Bitmask of active ways */
-static uint32_t l2x0_size;
+static u32 l2x0_way_mask;	/* Bitmask of active ways */
+static u32 l2x0_size;
 
 struct l2x0_regs l2x0_saved_regs;
 
 struct l2x0_of_data {
-	void (*setup)(const struct device_node *, __u32 *, __u32 *);
+	void (*setup)(const struct device_node *, u32 *, u32 *);
 	void (*save)(void);
 	void (*resume)(void);
 };
@@ -288,7 +288,7 @@
 	raw_spin_unlock_irqrestore(&l2x0_lock, flags);
 }
 
-static void l2x0_unlock(__u32 cache_id)
+static void l2x0_unlock(u32 cache_id)
 {
 	int lockregs;
 	int i;
@@ -307,11 +307,11 @@
 	}
 }
 
-void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask)
+void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask)
 {
-	__u32 aux;
-	__u32 cache_id;
-	__u32 way_size = 0;
+	u32 aux;
+	u32 cache_id;
+	u32 way_size = 0;
 	int ways;
 	const char *type;
 
@@ -388,7 +388,7 @@
 
 #ifdef CONFIG_OF
 static void __init l2x0_of_setup(const struct device_node *np,
-				 __u32 *aux_val, __u32 *aux_mask)
+				 u32 *aux_val, u32 *aux_mask)
 {
 	u32 data[2] = { 0, 0 };
 	u32 tag = 0;
@@ -422,7 +422,7 @@
 }
 
 static void __init pl310_of_setup(const struct device_node *np,
-				  __u32 *aux_val, __u32 *aux_mask)
+				  u32 *aux_val, u32 *aux_mask)
 {
 	u32 data[3] = { 0, 0, 0 };
 	u32 tag[3] = { 0, 0, 0 };
@@ -548,7 +548,7 @@
 	{}
 };
 
-int __init l2x0_of_init(__u32 aux_val, __u32 aux_mask)
+int __init l2x0_of_init(u32 aux_val, u32 aux_mask)
 {
 	struct device_node *np;
 	struct l2x0_of_data *data;
diff --git a/arch/arm/mm/copypage-v4mc.c b/arch/arm/mm/copypage-v4mc.c
index ec8c3be..1267e64 100644
--- a/arch/arm/mm/copypage-v4mc.c
+++ b/arch/arm/mm/copypage-v4mc.c
@@ -23,10 +23,6 @@
 
 #include "mm.h"
 
-/*
- * 0xffff8000 to 0xffffffff is reserved for any ARM architecture
- * specific hacks for copying pages efficiently.
- */
 #define minicache_pgprot __pgprot(L_PTE_PRESENT | L_PTE_YOUNG | \
 				  L_PTE_MT_MINICACHE)
 
@@ -78,10 +74,9 @@
 
 	raw_spin_lock(&minicache_lock);
 
-	set_pte_ext(TOP_PTE(0xffff8000), pfn_pte(page_to_pfn(from), minicache_pgprot), 0);
-	flush_tlb_kernel_page(0xffff8000);
+	set_top_pte(COPYPAGE_MINICACHE, mk_pte(from, minicache_pgprot));
 
-	mc_copy_user_page((void *)0xffff8000, kto);
+	mc_copy_user_page((void *)COPYPAGE_MINICACHE, kto);
 
 	raw_spin_unlock(&minicache_lock);
 
diff --git a/arch/arm/mm/copypage-v6.c b/arch/arm/mm/copypage-v6.c
index 8b03a58..b9bcc9d 100644
--- a/arch/arm/mm/copypage-v6.c
+++ b/arch/arm/mm/copypage-v6.c
@@ -24,9 +24,6 @@
 #error FIX ME
 #endif
 
-#define from_address	(0xffff8000)
-#define to_address	(0xffffc000)
-
 static DEFINE_RAW_SPINLOCK(v6_lock);
 
 /*
@@ -90,14 +87,11 @@
 	 */
 	raw_spin_lock(&v6_lock);
 
-	set_pte_ext(TOP_PTE(from_address) + offset, pfn_pte(page_to_pfn(from), PAGE_KERNEL), 0);
-	set_pte_ext(TOP_PTE(to_address) + offset, pfn_pte(page_to_pfn(to), PAGE_KERNEL), 0);
+	kfrom = COPYPAGE_V6_FROM + (offset << PAGE_SHIFT);
+	kto   = COPYPAGE_V6_TO + (offset << PAGE_SHIFT);
 
-	kfrom = from_address + (offset << PAGE_SHIFT);
-	kto   = to_address + (offset << PAGE_SHIFT);
-
-	flush_tlb_kernel_page(kfrom);
-	flush_tlb_kernel_page(kto);
+	set_top_pte(kfrom, mk_pte(from, PAGE_KERNEL));
+	set_top_pte(kto, mk_pte(to, PAGE_KERNEL));
 
 	copy_page((void *)kto, (void *)kfrom);
 
@@ -111,8 +105,7 @@
  */
 static void v6_clear_user_highpage_aliasing(struct page *page, unsigned long vaddr)
 {
-	unsigned int offset = CACHE_COLOUR(vaddr);
-	unsigned long to = to_address + (offset << PAGE_SHIFT);
+	unsigned long to = COPYPAGE_V6_TO + (CACHE_COLOUR(vaddr) << PAGE_SHIFT);
 
 	/* FIXME: not highmem safe */
 	discard_old_kernel_data(page_address(page));
@@ -123,8 +116,7 @@
 	 */
 	raw_spin_lock(&v6_lock);
 
-	set_pte_ext(TOP_PTE(to_address) + offset, pfn_pte(page_to_pfn(page), PAGE_KERNEL), 0);
-	flush_tlb_kernel_page(to);
+	set_top_pte(to, mk_pte(page, PAGE_KERNEL));
 	clear_page((void *)to);
 
 	raw_spin_unlock(&v6_lock);
diff --git a/arch/arm/mm/copypage-xscale.c b/arch/arm/mm/copypage-xscale.c
index 439d106..0fb8502 100644
--- a/arch/arm/mm/copypage-xscale.c
+++ b/arch/arm/mm/copypage-xscale.c
@@ -23,12 +23,6 @@
 
 #include "mm.h"
 
-/*
- * 0xffff8000 to 0xffffffff is reserved for any ARM architecture
- * specific hacks for copying pages efficiently.
- */
-#define COPYPAGE_MINICACHE	0xffff8000
-
 #define minicache_pgprot __pgprot(L_PTE_PRESENT | L_PTE_YOUNG | \
 				  L_PTE_MT_MINICACHE)
 
@@ -100,8 +94,7 @@
 
 	raw_spin_lock(&minicache_lock);
 
-	set_pte_ext(TOP_PTE(COPYPAGE_MINICACHE), pfn_pte(page_to_pfn(from), minicache_pgprot), 0);
-	flush_tlb_kernel_page(COPYPAGE_MINICACHE);
+	set_top_pte(COPYPAGE_MINICACHE, mk_pte(from, minicache_pgprot));
 
 	mc_copy_user_page((void *)COPYPAGE_MINICACHE, kto);
 
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 1aa664a..db23ae4 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -214,7 +214,8 @@
 core_initcall(consistent_init);
 
 static void *
-__dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot)
+__dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot,
+	const void *caller)
 {
 	struct arm_vmregion *c;
 	size_t align;
@@ -241,7 +242,7 @@
 	 * Allocate a virtual address in the consistent mapping region.
 	 */
 	c = arm_vmregion_alloc(&consistent_head, align, size,
-			    gfp & ~(__GFP_DMA | __GFP_HIGHMEM));
+			    gfp & ~(__GFP_DMA | __GFP_HIGHMEM), caller);
 	if (c) {
 		pte_t *pte;
 		int idx = CONSISTENT_PTE_INDEX(c->vm_start);
@@ -320,14 +321,14 @@
 
 #else	/* !CONFIG_MMU */
 
-#define __dma_alloc_remap(page, size, gfp, prot)	page_address(page)
+#define __dma_alloc_remap(page, size, gfp, prot, c)	page_address(page)
 #define __dma_free_remap(addr, size)			do { } while (0)
 
 #endif	/* CONFIG_MMU */
 
 static void *
 __dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp,
-	    pgprot_t prot)
+	    pgprot_t prot, const void *caller)
 {
 	struct page *page;
 	void *addr;
@@ -349,7 +350,7 @@
 		return NULL;
 
 	if (!arch_is_coherent())
-		addr = __dma_alloc_remap(page, size, gfp, prot);
+		addr = __dma_alloc_remap(page, size, gfp, prot, caller);
 	else
 		addr = page_address(page);
 
@@ -374,7 +375,8 @@
 		return memory;
 
 	return __dma_alloc(dev, size, handle, gfp,
-			   pgprot_dmacoherent(pgprot_kernel));
+			   pgprot_dmacoherent(pgprot_kernel),
+			   __builtin_return_address(0));
 }
 EXPORT_SYMBOL(dma_alloc_coherent);
 
@@ -386,7 +388,8 @@
 dma_alloc_writecombine(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp)
 {
 	return __dma_alloc(dev, size, handle, gfp,
-			   pgprot_writecombine(pgprot_kernel));
+			   pgprot_writecombine(pgprot_kernel),
+			   __builtin_return_address(0));
 }
 EXPORT_SYMBOL(dma_alloc_writecombine);
 
@@ -723,6 +726,9 @@
 
 static int __init dma_debug_do_init(void)
 {
+#ifdef CONFIG_MMU
+	arm_vmregion_create_proc("dma-mappings", &consistent_head);
+#endif
 	dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
 	return 0;
 }
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index 5bdff5c..9055b5a 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -165,7 +165,8 @@
 	struct siginfo si;
 
 #ifdef CONFIG_DEBUG_USER
-	if (user_debug & UDBG_SEGV) {
+	if (((user_debug & UDBG_SEGV) && (sig == SIGSEGV)) ||
+	    ((user_debug & UDBG_BUS)  && (sig == SIGBUS))) {
 		printk(KERN_DEBUG "%s: unhandled page fault (%d) at 0x%08lx, code 0x%03x\n",
 		       tsk->comm, sig, addr, fsr);
 		show_pte(tsk->mm, addr);
diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c
index 062d61a..7745854 100644
--- a/arch/arm/mm/flush.c
+++ b/arch/arm/mm/flush.c
@@ -22,15 +22,12 @@
 
 #ifdef CONFIG_CPU_CACHE_VIPT
 
-#define ALIAS_FLUSH_START	0xffff4000
-
 static void flush_pfn_alias(unsigned long pfn, unsigned long vaddr)
 {
-	unsigned long to = ALIAS_FLUSH_START + (CACHE_COLOUR(vaddr) << PAGE_SHIFT);
+	unsigned long to = FLUSH_ALIAS_START + (CACHE_COLOUR(vaddr) << PAGE_SHIFT);
 	const int zero = 0;
 
-	set_pte_ext(TOP_PTE(to), pfn_pte(pfn, PAGE_KERNEL), 0);
-	flush_tlb_kernel_page(to);
+	set_top_pte(to, pfn_pte(pfn, PAGE_KERNEL));
 
 	asm(	"mcrr	p15, 0, %1, %0, c14\n"
 	"	mcr	p15, 0, %2, c7, c10, 4"
@@ -41,13 +38,12 @@
 
 static void flush_icache_alias(unsigned long pfn, unsigned long vaddr, unsigned long len)
 {
-	unsigned long colour = CACHE_COLOUR(vaddr);
+	unsigned long va = FLUSH_ALIAS_START + (CACHE_COLOUR(vaddr) << PAGE_SHIFT);
 	unsigned long offset = vaddr & (PAGE_SIZE - 1);
 	unsigned long to;
 
-	set_pte_ext(TOP_PTE(ALIAS_FLUSH_START) + colour, pfn_pte(pfn, PAGE_KERNEL), 0);
-	to = ALIAS_FLUSH_START + (colour << PAGE_SHIFT) + offset;
-	flush_tlb_kernel_page(to);
+	set_top_pte(va, pfn_pte(pfn, PAGE_KERNEL));
+	to = va + offset;
 	flush_icache_range(to, to + len);
 }
 
diff --git a/arch/arm/mm/highmem.c b/arch/arm/mm/highmem.c
index 5a21505..21b9e1b 100644
--- a/arch/arm/mm/highmem.c
+++ b/arch/arm/mm/highmem.c
@@ -69,15 +69,14 @@
 	 * With debugging enabled, kunmap_atomic forces that entry to 0.
 	 * Make sure it was indeed properly unmapped.
 	 */
-	BUG_ON(!pte_none(*(TOP_PTE(vaddr))));
+	BUG_ON(!pte_none(get_top_pte(vaddr)));
 #endif
-	set_pte_ext(TOP_PTE(vaddr), mk_pte(page, kmap_prot), 0);
 	/*
 	 * When debugging is off, kunmap_atomic leaves the previous mapping
-	 * in place, so this TLB flush ensures the TLB is updated with the
-	 * new mapping.
+	 * in place, so the contained TLB flush ensures the TLB is updated
+	 * with the new mapping.
 	 */
-	local_flush_tlb_kernel_page(vaddr);
+	set_top_pte(vaddr, mk_pte(page, kmap_prot));
 
 	return (void *)vaddr;
 }
@@ -96,8 +95,7 @@
 			__cpuc_flush_dcache_area((void *)vaddr, PAGE_SIZE);
 #ifdef CONFIG_DEBUG_HIGHMEM
 		BUG_ON(vaddr != __fix_to_virt(FIX_KMAP_BEGIN + idx));
-		set_pte_ext(TOP_PTE(vaddr), __pte(0), 0);
-		local_flush_tlb_kernel_page(vaddr);
+		set_top_pte(vaddr, __pte(0));
 #else
 		(void) idx;  /* to kill a warning */
 #endif
@@ -121,10 +119,9 @@
 	idx = type + KM_TYPE_NR * smp_processor_id();
 	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
 #ifdef CONFIG_DEBUG_HIGHMEM
-	BUG_ON(!pte_none(*(TOP_PTE(vaddr))));
+	BUG_ON(!pte_none(get_top_pte(vaddr)));
 #endif
-	set_pte_ext(TOP_PTE(vaddr), pfn_pte(pfn, kmap_prot), 0);
-	local_flush_tlb_kernel_page(vaddr);
+	set_top_pte(vaddr, pfn_pte(pfn, kmap_prot));
 
 	return (void *)vaddr;
 }
@@ -132,11 +129,9 @@
 struct page *kmap_atomic_to_page(const void *ptr)
 {
 	unsigned long vaddr = (unsigned long)ptr;
-	pte_t *pte;
 
 	if (vaddr < FIXADDR_START)
 		return virt_to_page(ptr);
 
-	pte = TOP_PTE(vaddr);
-	return pte_page(*pte);
+	return pte_page(get_top_pte(vaddr));
 }
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 245a55a..595079f 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -658,7 +658,9 @@
 #ifdef CONFIG_HIGHMEM
 			"    pkmap   : 0x%08lx - 0x%08lx   (%4ld MB)\n"
 #endif
+#ifdef CONFIG_MODULES
 			"    modules : 0x%08lx - 0x%08lx   (%4ld MB)\n"
+#endif
 			"      .text : 0x%p" " - 0x%p" "   (%4d kB)\n"
 			"      .init : 0x%p" " - 0x%p" "   (%4d kB)\n"
 			"      .data : 0x%p" " - 0x%p" "   (%4d kB)\n"
@@ -677,7 +679,9 @@
 			MLM(PKMAP_BASE, (PKMAP_BASE) + (LAST_PKMAP) *
 				(PAGE_SIZE)),
 #endif
+#ifdef CONFIG_MODULES
 			MLM(MODULES_VADDR, MODULES_END),
+#endif
 
 			MLK_ROUNDUP(_text, _etext),
 			MLK_ROUNDUP(__init_begin, __init_end),
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index 6780b49..4f55f50 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -308,11 +308,15 @@
 }
 EXPORT_SYMBOL(__arm_ioremap_pfn);
 
+void __iomem * (*arch_ioremap_caller)(unsigned long, size_t,
+				      unsigned int, void *) =
+	__arm_ioremap_caller;
+
 void __iomem *
 __arm_ioremap(unsigned long phys_addr, size_t size, unsigned int mtype)
 {
-	return __arm_ioremap_caller(phys_addr, size, mtype,
-			__builtin_return_address(0));
+	return arch_ioremap_caller(phys_addr, size, mtype,
+		__builtin_return_address(0));
 }
 EXPORT_SYMBOL(__arm_ioremap);
 
@@ -371,4 +375,11 @@
 
 	vunmap(addr);
 }
-EXPORT_SYMBOL(__iounmap);
+
+void (*arch_iounmap)(volatile void __iomem *) = __iounmap;
+
+void __arm_iounmap(volatile void __iomem *io_addr)
+{
+	arch_iounmap(io_addr);
+}
+EXPORT_SYMBOL(__arm_iounmap);
diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h
index 70f6d3ea..27f4a61 100644
--- a/arch/arm/mm/mm.h
+++ b/arch/arm/mm/mm.h
@@ -3,7 +3,31 @@
 /* the upper-most page table pointer */
 extern pmd_t *top_pmd;
 
-#define TOP_PTE(x)	pte_offset_kernel(top_pmd, x)
+/*
+ * 0xffff8000 to 0xffffffff is reserved for any ARM architecture
+ * specific hacks for copying pages efficiently, while 0xffff4000
+ * is reserved for VIPT aliasing flushing by generic code.
+ *
+ * Note that we don't allow VIPT aliasing caches with SMP.
+ */
+#define COPYPAGE_MINICACHE	0xffff8000
+#define COPYPAGE_V6_FROM	0xffff8000
+#define COPYPAGE_V6_TO		0xffffc000
+/* PFN alias flushing, for VIPT caches */
+#define FLUSH_ALIAS_START	0xffff4000
+
+static inline void set_top_pte(unsigned long va, pte_t pte)
+{
+	pte_t *ptep = pte_offset_kernel(top_pmd, va);
+	set_pte_ext(ptep, pte, 0);
+	local_flush_tlb_kernel_page(va);
+}
+
+static inline pte_t get_top_pte(unsigned long va)
+{
+	pte_t *ptep = pte_offset_kernel(top_pmd, va);
+	return *ptep;
+}
 
 static inline pmd_t *pmd_off_k(unsigned long virt)
 {
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index cd439c1..b86f893 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -999,11 +999,14 @@
 {
 	struct map_desc map;
 	unsigned long addr;
+	void *vectors;
 
 	/*
 	 * Allocate the vector page early.
 	 */
-	vectors_page = early_alloc(PAGE_SIZE);
+	vectors = early_alloc(PAGE_SIZE);
+
+	early_trap_init(vectors);
 
 	for (addr = VMALLOC_START; addr; addr += PMD_SIZE)
 		pmd_clear(pmd_off_k(addr));
@@ -1043,7 +1046,7 @@
 	 * location (0xffff0000).  If we aren't using high-vectors, also
 	 * create a mapping at the low-vectors virtual address.
 	 */
-	map.pfn = __phys_to_pfn(virt_to_phys(vectors_page));
+	map.pfn = __phys_to_pfn(virt_to_phys(vectors));
 	map.virtual = 0xffff0000;
 	map.length = PAGE_SIZE;
 	map.type = MT_HIGH_VECTORS;
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index 4fc6794..6486d2f 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -86,13 +86,17 @@
 }
 EXPORT_SYMBOL(__arm_ioremap);
 
+void __iomem * (*arch_ioremap_caller)(unsigned long, size_t, unsigned int, void *);
+
 void __iomem *__arm_ioremap_caller(unsigned long phys_addr, size_t size,
 				   unsigned int mtype, void *caller)
 {
 	return __arm_ioremap(phys_addr, size, mtype);
 }
 
-void __iounmap(volatile void __iomem *addr)
+void (*arch_iounmap)(volatile void __iomem *);
+
+void __arm_iounmap(volatile void __iomem *addr)
 {
 }
-EXPORT_SYMBOL(__iounmap);
+EXPORT_SYMBOL(__arm_iounmap);
diff --git a/arch/arm/mm/vmregion.c b/arch/arm/mm/vmregion.c
index 036fdbf..a631016 100644
--- a/arch/arm/mm/vmregion.c
+++ b/arch/arm/mm/vmregion.c
@@ -1,5 +1,8 @@
+#include <linux/fs.h>
 #include <linux/spinlock.h>
 #include <linux/list.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
 #include <linux/slab.h>
 
 #include "vmregion.h"
@@ -36,7 +39,7 @@
 
 struct arm_vmregion *
 arm_vmregion_alloc(struct arm_vmregion_head *head, size_t align,
-		   size_t size, gfp_t gfp)
+		   size_t size, gfp_t gfp, const void *caller)
 {
 	unsigned long start = head->vm_start, addr = head->vm_end;
 	unsigned long flags;
@@ -52,6 +55,8 @@
 	if (!new)
 		goto out;
 
+	new->caller = caller;
+
 	spin_lock_irqsave(&head->vm_lock, flags);
 
 	addr = rounddown(addr - size, align);
@@ -129,3 +134,72 @@
 
 	kfree(c);
 }
+
+#ifdef CONFIG_PROC_FS
+static int arm_vmregion_show(struct seq_file *m, void *p)
+{
+	struct arm_vmregion *c = list_entry(p, struct arm_vmregion, vm_list);
+
+	seq_printf(m, "0x%08lx-0x%08lx %7lu", c->vm_start, c->vm_end,
+		c->vm_end - c->vm_start);
+	if (c->caller)
+		seq_printf(m, " %pS", (void *)c->caller);
+	seq_putc(m, '\n');
+	return 0;
+}
+
+static void *arm_vmregion_start(struct seq_file *m, loff_t *pos)
+{
+	struct arm_vmregion_head *h = m->private;
+	spin_lock_irq(&h->vm_lock);
+	return seq_list_start(&h->vm_list, *pos);
+}
+
+static void *arm_vmregion_next(struct seq_file *m, void *p, loff_t *pos)
+{
+	struct arm_vmregion_head *h = m->private;
+	return seq_list_next(p, &h->vm_list, pos);
+}
+
+static void arm_vmregion_stop(struct seq_file *m, void *p)
+{
+	struct arm_vmregion_head *h = m->private;
+	spin_unlock_irq(&h->vm_lock);
+}
+
+static const struct seq_operations arm_vmregion_ops = {
+	.start	= arm_vmregion_start,
+	.stop	= arm_vmregion_stop,
+	.next	= arm_vmregion_next,
+	.show	= arm_vmregion_show,
+};
+
+static int arm_vmregion_open(struct inode *inode, struct file *file)
+{
+	struct arm_vmregion_head *h = PDE(inode)->data;
+	int ret = seq_open(file, &arm_vmregion_ops);
+	if (!ret) {
+		struct seq_file *m = file->private_data;
+		m->private = h;
+	}
+	return ret;
+}
+
+static const struct file_operations arm_vmregion_fops = {
+	.open	= arm_vmregion_open,
+	.read	= seq_read,
+	.llseek	= seq_lseek,
+	.release = seq_release,
+};
+
+int arm_vmregion_create_proc(const char *path, struct arm_vmregion_head *h)
+{
+	proc_create_data(path, S_IRUSR, NULL, &arm_vmregion_fops, h);
+	return 0;
+}
+#else
+int arm_vmregion_create_proc(const char *path, struct arm_vmregion_head *h)
+{
+	return 0;
+}
+#endif
diff --git a/arch/arm/mm/vmregion.h b/arch/arm/mm/vmregion.h
index 15e9f04..162be66 100644
--- a/arch/arm/mm/vmregion.h
+++ b/arch/arm/mm/vmregion.h
@@ -19,11 +19,14 @@
 	unsigned long		vm_end;
 	struct page		*vm_pages;
 	int			vm_active;
+	const void		*caller;
 };
 
-struct arm_vmregion *arm_vmregion_alloc(struct arm_vmregion_head *, size_t, size_t, gfp_t);
+struct arm_vmregion *arm_vmregion_alloc(struct arm_vmregion_head *, size_t, size_t, gfp_t, const void *);
 struct arm_vmregion *arm_vmregion_find(struct arm_vmregion_head *, unsigned long);
 struct arm_vmregion *arm_vmregion_find_remove(struct arm_vmregion_head *, unsigned long);
 void arm_vmregion_free(struct arm_vmregion_head *, struct arm_vmregion *);
 
+int arm_vmregion_create_proc(const char *, struct arm_vmregion_head *);
+
 #endif
diff --git a/arch/arm/net/Makefile b/arch/arm/net/Makefile
new file mode 100644
index 0000000..c2c1084
--- /dev/null
+++ b/arch/arm/net/Makefile
@@ -0,0 +1,3 @@
+# ARM-specific networking code
+
+obj-$(CONFIG_BPF_JIT) += bpf_jit_32.o
diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
new file mode 100644
index 0000000..62135849
--- /dev/null
+++ b/arch/arm/net/bpf_jit_32.c
@@ -0,0 +1,915 @@
+/*
+ * Just-In-Time compiler for BPF filters on 32bit ARM
+ *
+ * Copyright (c) 2011 Mircea Gherzan <mgherzan@gmail.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; version 2 of the License.
+ */
+
+#include <linux/bitops.h>
+#include <linux/compiler.h>
+#include <linux/errno.h>
+#include <linux/filter.h>
+#include <linux/moduleloader.h>
+#include <linux/netdevice.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+#include <asm/cacheflush.h>
+#include <asm/hwcap.h>
+
+#include "bpf_jit_32.h"
+
+/*
+ * ABI:
+ *
+ * r0	scratch register
+ * r4	BPF register A
+ * r5	BPF register X
+ * r6	pointer to the skb
+ * r7	skb->data
+ * r8	skb_headlen(skb)
+ */
+
+#define r_scratch	ARM_R0
+/* r1-r3 are (also) used for the unaligned loads on the non-ARMv7 slowpath */
+#define r_off		ARM_R1
+#define r_A		ARM_R4
+#define r_X		ARM_R5
+#define r_skb		ARM_R6
+#define r_skb_data	ARM_R7
+#define r_skb_hl	ARM_R8
+
+#define SCRATCH_SP_OFFSET	0
+#define SCRATCH_OFF(k)		(SCRATCH_SP_OFFSET + (k))
+
+#define SEEN_MEM		((1 << BPF_MEMWORDS) - 1)
+#define SEEN_MEM_WORD(k)	(1 << (k))
+#define SEEN_X			(1 << BPF_MEMWORDS)
+#define SEEN_CALL		(1 << (BPF_MEMWORDS + 1))
+#define SEEN_SKB		(1 << (BPF_MEMWORDS + 2))
+#define SEEN_DATA		(1 << (BPF_MEMWORDS + 3))
+
+#define FLAG_NEED_X_RESET	(1 << 0)
+
+struct jit_ctx {
+	const struct sk_filter *skf;
+	unsigned idx;
+	unsigned prologue_bytes;
+	int ret0_fp_idx;
+	u32 seen;
+	u32 flags;
+	u32 *offsets;
+	u32 *target;
+#if __LINUX_ARM_ARCH__ < 7
+	u16 epilogue_bytes;
+	u16 imm_count;
+	u32 *imms;
+#endif
+};
+
+int bpf_jit_enable __read_mostly;
+
+static u64 jit_get_skb_b(struct sk_buff *skb, unsigned offset)
+{
+	u8 ret;
+	int err;
+
+	err = skb_copy_bits(skb, offset, &ret, 1);
+
+	return (u64)err << 32 | ret;
+}
+
+static u64 jit_get_skb_h(struct sk_buff *skb, unsigned offset)
+{
+	u16 ret;
+	int err;
+
+	err = skb_copy_bits(skb, offset, &ret, 2);
+
+	return (u64)err << 32 | ntohs(ret);
+}
+
+static u64 jit_get_skb_w(struct sk_buff *skb, unsigned offset)
+{
+	u32 ret;
+	int err;
+
+	err = skb_copy_bits(skb, offset, &ret, 4);
+
+	return (u64)err << 32 | ntohl(ret);
+}
+
+/*
+ * Wrapper that handles both OABI and EABI and assures Thumb2 interworking
+ * (where the assembly routines like __aeabi_uidiv could cause problems).
+ */
+static u32 jit_udiv(u32 dividend, u32 divisor)
+{
+	return dividend / divisor;
+}
+
+static inline void _emit(int cond, u32 inst, struct jit_ctx *ctx)
+{
+	if (ctx->target != NULL)
+		ctx->target[ctx->idx] = inst | (cond << 28);
+
+	ctx->idx++;
+}
+
+/*
+ * Emit an instruction that will be executed unconditionally.
+ */
+static inline void emit(u32 inst, struct jit_ctx *ctx)
+{
+	_emit(ARM_COND_AL, inst, ctx);
+}
+
+static u16 saved_regs(struct jit_ctx *ctx)
+{
+	u16 ret = 0;
+
+	if ((ctx->skf->len > 1) ||
+	    (ctx->skf->insns[0].code == BPF_S_RET_A))
+		ret |= 1 << r_A;
+
+#ifdef CONFIG_FRAME_POINTER
+	ret |= (1 << ARM_FP) | (1 << ARM_IP) | (1 << ARM_LR) | (1 << ARM_PC);
+#else
+	if (ctx->seen & SEEN_CALL)
+		ret |= 1 << ARM_LR;
+#endif
+	if (ctx->seen & (SEEN_DATA | SEEN_SKB))
+		ret |= 1 << r_skb;
+	if (ctx->seen & SEEN_DATA)
+		ret |= (1 << r_skb_data) | (1 << r_skb_hl);
+	if (ctx->seen & SEEN_X)
+		ret |= 1 << r_X;
+
+	return ret;
+}
+
+static inline int mem_words_used(struct jit_ctx *ctx)
+{
+	/* yes, we do waste some stack space IF there are "holes" in the set" */
+	return fls(ctx->seen & SEEN_MEM);
+}
+
+static inline bool is_load_to_a(u16 inst)
+{
+	switch (inst) {
+	case BPF_S_LD_W_LEN:
+	case BPF_S_LD_W_ABS:
+	case BPF_S_LD_H_ABS:
+	case BPF_S_LD_B_ABS:
+	case BPF_S_ANC_CPU:
+	case BPF_S_ANC_IFINDEX:
+	case BPF_S_ANC_MARK:
+	case BPF_S_ANC_PROTOCOL:
+	case BPF_S_ANC_RXHASH:
+	case BPF_S_ANC_QUEUE:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static void build_prologue(struct jit_ctx *ctx)
+{
+	u16 reg_set = saved_regs(ctx);
+	u16 first_inst = ctx->skf->insns[0].code;
+	u16 off;
+
+#ifdef CONFIG_FRAME_POINTER
+	emit(ARM_MOV_R(ARM_IP, ARM_SP), ctx);
+	emit(ARM_PUSH(reg_set), ctx);
+	emit(ARM_SUB_I(ARM_FP, ARM_IP, 4), ctx);
+#else
+	if (reg_set)
+		emit(ARM_PUSH(reg_set), ctx);
+#endif
+
+	if (ctx->seen & (SEEN_DATA | SEEN_SKB))
+		emit(ARM_MOV_R(r_skb, ARM_R0), ctx);
+
+	if (ctx->seen & SEEN_DATA) {
+		off = offsetof(struct sk_buff, data);
+		emit(ARM_LDR_I(r_skb_data, r_skb, off), ctx);
+		/* headlen = len - data_len */
+		off = offsetof(struct sk_buff, len);
+		emit(ARM_LDR_I(r_skb_hl, r_skb, off), ctx);
+		off = offsetof(struct sk_buff, data_len);
+		emit(ARM_LDR_I(r_scratch, r_skb, off), ctx);
+		emit(ARM_SUB_R(r_skb_hl, r_skb_hl, r_scratch), ctx);
+	}
+
+	if (ctx->flags & FLAG_NEED_X_RESET)
+		emit(ARM_MOV_I(r_X, 0), ctx);
+
+	/* do not leak kernel data to userspace */
+	if ((first_inst != BPF_S_RET_K) && !(is_load_to_a(first_inst)))
+		emit(ARM_MOV_I(r_A, 0), ctx);
+
+	/* stack space for the BPF_MEM words */
+	if (ctx->seen & SEEN_MEM)
+		emit(ARM_SUB_I(ARM_SP, ARM_SP, mem_words_used(ctx) * 4), ctx);
+}
+
+static void build_epilogue(struct jit_ctx *ctx)
+{
+	u16 reg_set = saved_regs(ctx);
+
+	if (ctx->seen & SEEN_MEM)
+		emit(ARM_ADD_I(ARM_SP, ARM_SP, mem_words_used(ctx) * 4), ctx);
+
+	reg_set &= ~(1 << ARM_LR);
+
+#ifdef CONFIG_FRAME_POINTER
+	/* the first instruction of the prologue was: mov ip, sp */
+	reg_set &= ~(1 << ARM_IP);
+	reg_set |= (1 << ARM_SP);
+	emit(ARM_LDM(ARM_SP, reg_set), ctx);
+#else
+	if (reg_set) {
+		if (ctx->seen & SEEN_CALL)
+			reg_set |= 1 << ARM_PC;
+		emit(ARM_POP(reg_set), ctx);
+	}
+
+	if (!(ctx->seen & SEEN_CALL))
+		emit(ARM_BX(ARM_LR), ctx);
+#endif
+}
+
+static int16_t imm8m(u32 x)
+{
+	u32 rot;
+
+	for (rot = 0; rot < 16; rot++)
+		if ((x & ~ror32(0xff, 2 * rot)) == 0)
+			return rol32(x, 2 * rot) | (rot << 8);
+
+	return -1;
+}
+
+#if __LINUX_ARM_ARCH__ < 7
+
+static u16 imm_offset(u32 k, struct jit_ctx *ctx)
+{
+	unsigned i = 0, offset;
+	u16 imm;
+
+	/* on the "fake" run we just count them (duplicates included) */
+	if (ctx->target == NULL) {
+		ctx->imm_count++;
+		return 0;
+	}
+
+	while ((i < ctx->imm_count) && ctx->imms[i]) {
+		if (ctx->imms[i] == k)
+			break;
+		i++;
+	}
+
+	if (ctx->imms[i] == 0)
+		ctx->imms[i] = k;
+
+	/* constants go just after the epilogue */
+	offset =  ctx->offsets[ctx->skf->len];
+	offset += ctx->prologue_bytes;
+	offset += ctx->epilogue_bytes;
+	offset += i * 4;
+
+	ctx->target[offset / 4] = k;
+
+	/* PC in ARM mode == address of the instruction + 8 */
+	imm = offset - (8 + ctx->idx * 4);
+
+	return imm;
+}
+
+#endif /* __LINUX_ARM_ARCH__ */
+
+/*
+ * Move an immediate that's not an imm8m to a core register.
+ */
+static inline void emit_mov_i_no8m(int rd, u32 val, struct jit_ctx *ctx)
+{
+#if __LINUX_ARM_ARCH__ < 7
+	emit(ARM_LDR_I(rd, ARM_PC, imm_offset(val, ctx)), ctx);
+#else
+	emit(ARM_MOVW(rd, val & 0xffff), ctx);
+	if (val > 0xffff)
+		emit(ARM_MOVT(rd, val >> 16), ctx);
+#endif
+}
+
+static inline void emit_mov_i(int rd, u32 val, struct jit_ctx *ctx)
+{
+	int imm12 = imm8m(val);
+
+	if (imm12 >= 0)
+		emit(ARM_MOV_I(rd, imm12), ctx);
+	else
+		emit_mov_i_no8m(rd, val, ctx);
+}
+
+#if __LINUX_ARM_ARCH__ < 6
+
+static void emit_load_be32(u8 cond, u8 r_res, u8 r_addr, struct jit_ctx *ctx)
+{
+	_emit(cond, ARM_LDRB_I(ARM_R3, r_addr, 1), ctx);
+	_emit(cond, ARM_LDRB_I(ARM_R1, r_addr, 0), ctx);
+	_emit(cond, ARM_LDRB_I(ARM_R2, r_addr, 3), ctx);
+	_emit(cond, ARM_LSL_I(ARM_R3, ARM_R3, 16), ctx);
+	_emit(cond, ARM_LDRB_I(ARM_R0, r_addr, 2), ctx);
+	_emit(cond, ARM_ORR_S(ARM_R3, ARM_R3, ARM_R1, SRTYPE_LSL, 24), ctx);
+	_emit(cond, ARM_ORR_R(ARM_R3, ARM_R3, ARM_R2), ctx);
+	_emit(cond, ARM_ORR_S(r_res, ARM_R3, ARM_R0, SRTYPE_LSL, 8), ctx);
+}
+
+static void emit_load_be16(u8 cond, u8 r_res, u8 r_addr, struct jit_ctx *ctx)
+{
+	_emit(cond, ARM_LDRB_I(ARM_R1, r_addr, 0), ctx);
+	_emit(cond, ARM_LDRB_I(ARM_R2, r_addr, 1), ctx);
+	_emit(cond, ARM_ORR_S(r_res, ARM_R2, ARM_R1, SRTYPE_LSL, 8), ctx);
+}
+
+static inline void emit_swap16(u8 r_dst, u8 r_src, struct jit_ctx *ctx)
+{
+	emit(ARM_LSL_R(ARM_R1, r_src, 8), ctx);
+	emit(ARM_ORR_S(r_dst, ARM_R1, r_src, SRTYPE_LSL, 8), ctx);
+	emit(ARM_LSL_I(r_dst, r_dst, 8), ctx);
+	emit(ARM_LSL_R(r_dst, r_dst, 8), ctx);
+}
+
+#else  /* ARMv6+ */
+
+static void emit_load_be32(u8 cond, u8 r_res, u8 r_addr, struct jit_ctx *ctx)
+{
+	_emit(cond, ARM_LDR_I(r_res, r_addr, 0), ctx);
+#ifdef __LITTLE_ENDIAN
+	_emit(cond, ARM_REV(r_res, r_res), ctx);
+#endif
+}
+
+static void emit_load_be16(u8 cond, u8 r_res, u8 r_addr, struct jit_ctx *ctx)
+{
+	_emit(cond, ARM_LDRH_I(r_res, r_addr, 0), ctx);
+#ifdef __LITTLE_ENDIAN
+	_emit(cond, ARM_REV16(r_res, r_res), ctx);
+#endif
+}
+
+static inline void emit_swap16(u8 r_dst __maybe_unused,
+			       u8 r_src __maybe_unused,
+			       struct jit_ctx *ctx __maybe_unused)
+{
+#ifdef __LITTLE_ENDIAN
+	emit(ARM_REV16(r_dst, r_src), ctx);
+#endif
+}
+
+#endif /* __LINUX_ARM_ARCH__ < 6 */
+
+
+/* Compute the immediate value for a PC-relative branch. */
+static inline u32 b_imm(unsigned tgt, struct jit_ctx *ctx)
+{
+	u32 imm;
+
+	if (ctx->target == NULL)
+		return 0;
+	/*
+	 * BPF allows only forward jumps and the offset of the target is
+	 * still the one computed during the first pass.
+	 */
+	imm  = ctx->offsets[tgt] + ctx->prologue_bytes - (ctx->idx * 4 + 8);
+
+	return imm >> 2;
+}
+
+#define OP_IMM3(op, r1, r2, imm_val, ctx)				\
+	do {								\
+		imm12 = imm8m(imm_val);					\
+		if (imm12 < 0) {					\
+			emit_mov_i_no8m(r_scratch, imm_val, ctx);	\
+			emit(op ## _R((r1), (r2), r_scratch), ctx);	\
+		} else {						\
+			emit(op ## _I((r1), (r2), imm12), ctx);		\
+		}							\
+	} while (0)
+
+static inline void emit_err_ret(u8 cond, struct jit_ctx *ctx)
+{
+	if (ctx->ret0_fp_idx >= 0) {
+		_emit(cond, ARM_B(b_imm(ctx->ret0_fp_idx, ctx)), ctx);
+		/* NOP to keep the size constant between passes */
+		emit(ARM_MOV_R(ARM_R0, ARM_R0), ctx);
+	} else {
+		_emit(cond, ARM_MOV_I(ARM_R0, 0), ctx);
+		_emit(cond, ARM_B(b_imm(ctx->skf->len, ctx)), ctx);
+	}
+}
+
+static inline void emit_blx_r(u8 tgt_reg, struct jit_ctx *ctx)
+{
+#if __LINUX_ARM_ARCH__ < 5
+	emit(ARM_MOV_R(ARM_LR, ARM_PC), ctx);
+
+	if (elf_hwcap & HWCAP_THUMB)
+		emit(ARM_BX(tgt_reg), ctx);
+	else
+		emit(ARM_MOV_R(ARM_PC, tgt_reg), ctx);
+#else
+	emit(ARM_BLX_R(tgt_reg), ctx);
+#endif
+}
+
+static inline void emit_udiv(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx)
+{
+#if __LINUX_ARM_ARCH__ == 7
+	if (elf_hwcap & HWCAP_IDIVA) {
+		emit(ARM_UDIV(rd, rm, rn), ctx);
+		return;
+	}
+#endif
+	if (rm != ARM_R0)
+		emit(ARM_MOV_R(ARM_R0, rm), ctx);
+	if (rn != ARM_R1)
+		emit(ARM_MOV_R(ARM_R1, rn), ctx);
+
+	ctx->seen |= SEEN_CALL;
+	emit_mov_i(ARM_R3, (u32)jit_udiv, ctx);
+	emit_blx_r(ARM_R3, ctx);
+
+	if (rd != ARM_R0)
+		emit(ARM_MOV_R(rd, ARM_R0), ctx);
+}
+
+static inline void update_on_xread(struct jit_ctx *ctx)
+{
+	if (!(ctx->seen & SEEN_X))
+		ctx->flags |= FLAG_NEED_X_RESET;
+
+	ctx->seen |= SEEN_X;
+}
+
+static int build_body(struct jit_ctx *ctx)
+{
+	void *load_func[] = {jit_get_skb_b, jit_get_skb_h, jit_get_skb_w};
+	const struct sk_filter *prog = ctx->skf;
+	const struct sock_filter *inst;
+	unsigned i, load_order, off, condt;
+	int imm12;
+	u32 k;
+
+	for (i = 0; i < prog->len; i++) {
+		inst = &(prog->insns[i]);
+		/* K as an immediate value operand */
+		k = inst->k;
+
+		/* compute offsets only in the fake pass */
+		if (ctx->target == NULL)
+			ctx->offsets[i] = ctx->idx * 4;
+
+		switch (inst->code) {
+		case BPF_S_LD_IMM:
+			emit_mov_i(r_A, k, ctx);
+			break;
+		case BPF_S_LD_W_LEN:
+			ctx->seen |= SEEN_SKB;
+			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, len) != 4);
+			emit(ARM_LDR_I(r_A, r_skb,
+				       offsetof(struct sk_buff, len)), ctx);
+			break;
+		case BPF_S_LD_MEM:
+			/* A = scratch[k] */
+			ctx->seen |= SEEN_MEM_WORD(k);
+			emit(ARM_LDR_I(r_A, ARM_SP, SCRATCH_OFF(k)), ctx);
+			break;
+		case BPF_S_LD_W_ABS:
+			load_order = 2;
+			goto load;
+		case BPF_S_LD_H_ABS:
+			load_order = 1;
+			goto load;
+		case BPF_S_LD_B_ABS:
+			load_order = 0;
+load:
+			/* the interpreter will deal with the negative K */
+			if ((int)k < 0)
+				return -ENOTSUPP;
+			emit_mov_i(r_off, k, ctx);
+load_common:
+			ctx->seen |= SEEN_DATA | SEEN_CALL;
+
+			if (load_order > 0) {
+				emit(ARM_SUB_I(r_scratch, r_skb_hl,
+					       1 << load_order), ctx);
+				emit(ARM_CMP_R(r_scratch, r_off), ctx);
+				condt = ARM_COND_HS;
+			} else {
+				emit(ARM_CMP_R(r_skb_hl, r_off), ctx);
+				condt = ARM_COND_HI;
+			}
+
+			_emit(condt, ARM_ADD_R(r_scratch, r_off, r_skb_data),
+			      ctx);
+
+			if (load_order == 0)
+				_emit(condt, ARM_LDRB_I(r_A, r_scratch, 0),
+				      ctx);
+			else if (load_order == 1)
+				emit_load_be16(condt, r_A, r_scratch, ctx);
+			else if (load_order == 2)
+				emit_load_be32(condt, r_A, r_scratch, ctx);
+
+			_emit(condt, ARM_B(b_imm(i + 1, ctx)), ctx);
+
+			/* the slowpath */
+			emit_mov_i(ARM_R3, (u32)load_func[load_order], ctx);
+			emit(ARM_MOV_R(ARM_R0, r_skb), ctx);
+			/* the offset is already in R1 */
+			emit_blx_r(ARM_R3, ctx);
+			/* check the result of skb_copy_bits */
+			emit(ARM_CMP_I(ARM_R1, 0), ctx);
+			emit_err_ret(ARM_COND_NE, ctx);
+			emit(ARM_MOV_R(r_A, ARM_R0), ctx);
+			break;
+		case BPF_S_LD_W_IND:
+			load_order = 2;
+			goto load_ind;
+		case BPF_S_LD_H_IND:
+			load_order = 1;
+			goto load_ind;
+		case BPF_S_LD_B_IND:
+			load_order = 0;
+load_ind:
+			OP_IMM3(ARM_ADD, r_off, r_X, k, ctx);
+			goto load_common;
+		case BPF_S_LDX_IMM:
+			ctx->seen |= SEEN_X;
+			emit_mov_i(r_X, k, ctx);
+			break;
+		case BPF_S_LDX_W_LEN:
+			ctx->seen |= SEEN_X | SEEN_SKB;
+			emit(ARM_LDR_I(r_X, r_skb,
+				       offsetof(struct sk_buff, len)), ctx);
+			break;
+		case BPF_S_LDX_MEM:
+			ctx->seen |= SEEN_X | SEEN_MEM_WORD(k);
+			emit(ARM_LDR_I(r_X, ARM_SP, SCRATCH_OFF(k)), ctx);
+			break;
+		case BPF_S_LDX_B_MSH:
+			/* x = ((*(frame + k)) & 0xf) << 2; */
+			ctx->seen |= SEEN_X | SEEN_DATA | SEEN_CALL;
+			/* the interpreter should deal with the negative K */
+			if (k < 0)
+				return -1;
+			/* offset in r1: we might have to take the slow path */
+			emit_mov_i(r_off, k, ctx);
+			emit(ARM_CMP_R(r_skb_hl, r_off), ctx);
+
+			/* load in r0: common with the slowpath */
+			_emit(ARM_COND_HI, ARM_LDRB_R(ARM_R0, r_skb_data,
+						      ARM_R1), ctx);
+			/*
+			 * emit_mov_i() might generate one or two instructions,
+			 * the same holds for emit_blx_r()
+			 */
+			_emit(ARM_COND_HI, ARM_B(b_imm(i + 1, ctx) - 2), ctx);
+
+			emit(ARM_MOV_R(ARM_R0, r_skb), ctx);
+			/* r_off is r1 */
+			emit_mov_i(ARM_R3, (u32)jit_get_skb_b, ctx);
+			emit_blx_r(ARM_R3, ctx);
+			/* check the return value of skb_copy_bits */
+			emit(ARM_CMP_I(ARM_R1, 0), ctx);
+			emit_err_ret(ARM_COND_NE, ctx);
+
+			emit(ARM_AND_I(r_X, ARM_R0, 0x00f), ctx);
+			emit(ARM_LSL_I(r_X, r_X, 2), ctx);
+			break;
+		case BPF_S_ST:
+			ctx->seen |= SEEN_MEM_WORD(k);
+			emit(ARM_STR_I(r_A, ARM_SP, SCRATCH_OFF(k)), ctx);
+			break;
+		case BPF_S_STX:
+			update_on_xread(ctx);
+			ctx->seen |= SEEN_MEM_WORD(k);
+			emit(ARM_STR_I(r_X, ARM_SP, SCRATCH_OFF(k)), ctx);
+			break;
+		case BPF_S_ALU_ADD_K:
+			/* A += K */
+			OP_IMM3(ARM_ADD, r_A, r_A, k, ctx);
+			break;
+		case BPF_S_ALU_ADD_X:
+			update_on_xread(ctx);
+			emit(ARM_ADD_R(r_A, r_A, r_X), ctx);
+			break;
+		case BPF_S_ALU_SUB_K:
+			/* A -= K */
+			OP_IMM3(ARM_SUB, r_A, r_A, k, ctx);
+			break;
+		case BPF_S_ALU_SUB_X:
+			update_on_xread(ctx);
+			emit(ARM_SUB_R(r_A, r_A, r_X), ctx);
+			break;
+		case BPF_S_ALU_MUL_K:
+			/* A *= K */
+			emit_mov_i(r_scratch, k, ctx);
+			emit(ARM_MUL(r_A, r_A, r_scratch), ctx);
+			break;
+		case BPF_S_ALU_MUL_X:
+			update_on_xread(ctx);
+			emit(ARM_MUL(r_A, r_A, r_X), ctx);
+			break;
+		case BPF_S_ALU_DIV_K:
+			/* current k == reciprocal_value(userspace k) */
+			emit_mov_i(r_scratch, k, ctx);
+			/* A = top 32 bits of the product */
+			emit(ARM_UMULL(r_scratch, r_A, r_A, r_scratch), ctx);
+			break;
+		case BPF_S_ALU_DIV_X:
+			update_on_xread(ctx);
+			emit(ARM_CMP_I(r_X, 0), ctx);
+			emit_err_ret(ARM_COND_EQ, ctx);
+			emit_udiv(r_A, r_A, r_X, ctx);
+			break;
+		case BPF_S_ALU_OR_K:
+			/* A |= K */
+			OP_IMM3(ARM_ORR, r_A, r_A, k, ctx);
+			break;
+		case BPF_S_ALU_OR_X:
+			update_on_xread(ctx);
+			emit(ARM_ORR_R(r_A, r_A, r_X), ctx);
+			break;
+		case BPF_S_ALU_AND_K:
+			/* A &= K */
+			OP_IMM3(ARM_AND, r_A, r_A, k, ctx);
+			break;
+		case BPF_S_ALU_AND_X:
+			update_on_xread(ctx);
+			emit(ARM_AND_R(r_A, r_A, r_X), ctx);
+			break;
+		case BPF_S_ALU_LSH_K:
+			if (unlikely(k > 31))
+				return -1;
+			emit(ARM_LSL_I(r_A, r_A, k), ctx);
+			break;
+		case BPF_S_ALU_LSH_X:
+			update_on_xread(ctx);
+			emit(ARM_LSL_R(r_A, r_A, r_X), ctx);
+			break;
+		case BPF_S_ALU_RSH_K:
+			if (unlikely(k > 31))
+				return -1;
+			emit(ARM_LSR_I(r_A, r_A, k), ctx);
+			break;
+		case BPF_S_ALU_RSH_X:
+			update_on_xread(ctx);
+			emit(ARM_LSR_R(r_A, r_A, r_X), ctx);
+			break;
+		case BPF_S_ALU_NEG:
+			/* A = -A */
+			emit(ARM_RSB_I(r_A, r_A, 0), ctx);
+			break;
+		case BPF_S_JMP_JA:
+			/* pc += K */
+			emit(ARM_B(b_imm(i + k + 1, ctx)), ctx);
+			break;
+		case BPF_S_JMP_JEQ_K:
+			/* pc += (A == K) ? pc->jt : pc->jf */
+			condt  = ARM_COND_EQ;
+			goto cmp_imm;
+		case BPF_S_JMP_JGT_K:
+			/* pc += (A > K) ? pc->jt : pc->jf */
+			condt  = ARM_COND_HI;
+			goto cmp_imm;
+		case BPF_S_JMP_JGE_K:
+			/* pc += (A >= K) ? pc->jt : pc->jf */
+			condt  = ARM_COND_HS;
+cmp_imm:
+			imm12 = imm8m(k);
+			if (imm12 < 0) {
+				emit_mov_i_no8m(r_scratch, k, ctx);
+				emit(ARM_CMP_R(r_A, r_scratch), ctx);
+			} else {
+				emit(ARM_CMP_I(r_A, imm12), ctx);
+			}
+cond_jump:
+			if (inst->jt)
+				_emit(condt, ARM_B(b_imm(i + inst->jt + 1,
+						   ctx)), ctx);
+			if (inst->jf)
+				_emit(condt ^ 1, ARM_B(b_imm(i + inst->jf + 1,
+							     ctx)), ctx);
+			break;
+		case BPF_S_JMP_JEQ_X:
+			/* pc += (A == X) ? pc->jt : pc->jf */
+			condt   = ARM_COND_EQ;
+			goto cmp_x;
+		case BPF_S_JMP_JGT_X:
+			/* pc += (A > X) ? pc->jt : pc->jf */
+			condt   = ARM_COND_HI;
+			goto cmp_x;
+		case BPF_S_JMP_JGE_X:
+			/* pc += (A >= X) ? pc->jt : pc->jf */
+			condt   = ARM_COND_CS;
+cmp_x:
+			update_on_xread(ctx);
+			emit(ARM_CMP_R(r_A, r_X), ctx);
+			goto cond_jump;
+		case BPF_S_JMP_JSET_K:
+			/* pc += (A & K) ? pc->jt : pc->jf */
+			condt  = ARM_COND_NE;
+			/* not set iff all zeroes iff Z==1 iff EQ */
+
+			imm12 = imm8m(k);
+			if (imm12 < 0) {
+				emit_mov_i_no8m(r_scratch, k, ctx);
+				emit(ARM_TST_R(r_A, r_scratch), ctx);
+			} else {
+				emit(ARM_TST_I(r_A, imm12), ctx);
+			}
+			goto cond_jump;
+		case BPF_S_JMP_JSET_X:
+			/* pc += (A & X) ? pc->jt : pc->jf */
+			update_on_xread(ctx);
+			condt  = ARM_COND_NE;
+			emit(ARM_TST_R(r_A, r_X), ctx);
+			goto cond_jump;
+		case BPF_S_RET_A:
+			emit(ARM_MOV_R(ARM_R0, r_A), ctx);
+			goto b_epilogue;
+		case BPF_S_RET_K:
+			if ((k == 0) && (ctx->ret0_fp_idx < 0))
+				ctx->ret0_fp_idx = i;
+			emit_mov_i(ARM_R0, k, ctx);
+b_epilogue:
+			if (i != ctx->skf->len - 1)
+				emit(ARM_B(b_imm(prog->len, ctx)), ctx);
+			break;
+		case BPF_S_MISC_TAX:
+			/* X = A */
+			ctx->seen |= SEEN_X;
+			emit(ARM_MOV_R(r_X, r_A), ctx);
+			break;
+		case BPF_S_MISC_TXA:
+			/* A = X */
+			update_on_xread(ctx);
+			emit(ARM_MOV_R(r_A, r_X), ctx);
+			break;
+		case BPF_S_ANC_PROTOCOL:
+			/* A = ntohs(skb->protocol) */
+			ctx->seen |= SEEN_SKB;
+			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff,
+						  protocol) != 2);
+			off = offsetof(struct sk_buff, protocol);
+			emit(ARM_LDRH_I(r_scratch, r_skb, off), ctx);
+			emit_swap16(r_A, r_scratch, ctx);
+			break;
+		case BPF_S_ANC_CPU:
+			/* r_scratch = current_thread_info() */
+			OP_IMM3(ARM_BIC, r_scratch, ARM_SP, THREAD_SIZE - 1, ctx);
+			/* A = current_thread_info()->cpu */
+			BUILD_BUG_ON(FIELD_SIZEOF(struct thread_info, cpu) != 4);
+			off = offsetof(struct thread_info, cpu);
+			emit(ARM_LDR_I(r_A, r_scratch, off), ctx);
+			break;
+		case BPF_S_ANC_IFINDEX:
+			/* A = skb->dev->ifindex */
+			ctx->seen |= SEEN_SKB;
+			off = offsetof(struct sk_buff, dev);
+			emit(ARM_LDR_I(r_scratch, r_skb, off), ctx);
+
+			emit(ARM_CMP_I(r_scratch, 0), ctx);
+			emit_err_ret(ARM_COND_EQ, ctx);
+
+			BUILD_BUG_ON(FIELD_SIZEOF(struct net_device,
+						  ifindex) != 4);
+			off = offsetof(struct net_device, ifindex);
+			emit(ARM_LDR_I(r_A, r_scratch, off), ctx);
+			break;
+		case BPF_S_ANC_MARK:
+			ctx->seen |= SEEN_SKB;
+			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4);
+			off = offsetof(struct sk_buff, mark);
+			emit(ARM_LDR_I(r_A, r_skb, off), ctx);
+			break;
+		case BPF_S_ANC_RXHASH:
+			ctx->seen |= SEEN_SKB;
+			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, rxhash) != 4);
+			off = offsetof(struct sk_buff, rxhash);
+			emit(ARM_LDR_I(r_A, r_skb, off), ctx);
+			break;
+		case BPF_S_ANC_QUEUE:
+			ctx->seen |= SEEN_SKB;
+			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff,
+						  queue_mapping) != 2);
+			BUILD_BUG_ON(offsetof(struct sk_buff,
+					      queue_mapping) > 0xff);
+			off = offsetof(struct sk_buff, queue_mapping);
+			emit(ARM_LDRH_I(r_A, r_skb, off), ctx);
+			break;
+		default:
+			return -1;
+		}
+	}
+
+	/* compute offsets only during the first pass */
+	if (ctx->target == NULL)
+		ctx->offsets[i] = ctx->idx * 4;
+
+	return 0;
+}
+
+
+void bpf_jit_compile(struct sk_filter *fp)
+{
+	struct jit_ctx ctx;
+	unsigned tmp_idx;
+	unsigned alloc_size;
+
+	if (!bpf_jit_enable)
+		return;
+
+	memset(&ctx, 0, sizeof(ctx));
+	ctx.skf		= fp;
+	ctx.ret0_fp_idx = -1;
+
+	ctx.offsets = kzalloc(GFP_KERNEL, 4 * (ctx.skf->len + 1));
+	if (ctx.offsets == NULL)
+		return;
+
+	/* fake pass to fill in the ctx->seen */
+	if (unlikely(build_body(&ctx)))
+		goto out;
+
+	tmp_idx = ctx.idx;
+	build_prologue(&ctx);
+	ctx.prologue_bytes = (ctx.idx - tmp_idx) * 4;
+
+#if __LINUX_ARM_ARCH__ < 7
+	tmp_idx = ctx.idx;
+	build_epilogue(&ctx);
+	ctx.epilogue_bytes = (ctx.idx - tmp_idx) * 4;
+
+	ctx.idx += ctx.imm_count;
+	if (ctx.imm_count) {
+		ctx.imms = kzalloc(GFP_KERNEL, 4 * ctx.imm_count);
+		if (ctx.imms == NULL)
+			goto out;
+	}
+#else
+	/* there's nothing after the epilogue on ARMv7 */
+	build_epilogue(&ctx);
+#endif
+
+	alloc_size = 4 * ctx.idx;
+	ctx.target = module_alloc(max(sizeof(struct work_struct),
+				      alloc_size));
+	if (unlikely(ctx.target == NULL))
+		goto out;
+
+	ctx.idx = 0;
+	build_prologue(&ctx);
+	build_body(&ctx);
+	build_epilogue(&ctx);
+
+	flush_icache_range((u32)ctx.target, (u32)(ctx.target + ctx.idx));
+
+#if __LINUX_ARM_ARCH__ < 7
+	if (ctx.imm_count)
+		kfree(ctx.imms);
+#endif
+
+	if (bpf_jit_enable > 1)
+		print_hex_dump(KERN_INFO, "BPF JIT code: ",
+			       DUMP_PREFIX_ADDRESS, 16, 4, ctx.target,
+			       alloc_size, false);
+
+	fp->bpf_func = (void *)ctx.target;
+out:
+	kfree(ctx.offsets);
+	return;
+}
+
+static void bpf_jit_free_worker(struct work_struct *work)
+{
+	module_free(NULL, work);
+}
+
+void bpf_jit_free(struct sk_filter *fp)
+{
+	struct work_struct *work;
+
+	if (fp->bpf_func != sk_run_filter) {
+		work = (struct work_struct *)fp->bpf_func;
+
+		INIT_WORK(work, bpf_jit_free_worker);
+		schedule_work(work);
+	}
+}
diff --git a/arch/arm/net/bpf_jit_32.h b/arch/arm/net/bpf_jit_32.h
new file mode 100644
index 0000000..99ae5e3f
--- /dev/null
+++ b/arch/arm/net/bpf_jit_32.h
@@ -0,0 +1,190 @@
+/*
+ * Just-In-Time compiler for BPF filters on 32bit ARM
+ *
+ * Copyright (c) 2011 Mircea Gherzan <mgherzan@gmail.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; version 2 of the License.
+ */
+
+#ifndef PFILTER_OPCODES_ARM_H
+#define PFILTER_OPCODES_ARM_H
+
+#define ARM_R0	0
+#define ARM_R1	1
+#define ARM_R2	2
+#define ARM_R3	3
+#define ARM_R4	4
+#define ARM_R5	5
+#define ARM_R6	6
+#define ARM_R7	7
+#define ARM_R8	8
+#define ARM_R9	9
+#define ARM_R10	10
+#define ARM_FP	11
+#define ARM_IP	12
+#define ARM_SP	13
+#define ARM_LR	14
+#define ARM_PC	15
+
+#define ARM_COND_EQ		0x0
+#define ARM_COND_NE		0x1
+#define ARM_COND_CS		0x2
+#define ARM_COND_HS		ARM_COND_CS
+#define ARM_COND_CC		0x3
+#define ARM_COND_LO		ARM_COND_CC
+#define ARM_COND_MI		0x4
+#define ARM_COND_PL		0x5
+#define ARM_COND_VS		0x6
+#define ARM_COND_VC		0x7
+#define ARM_COND_HI		0x8
+#define ARM_COND_LS		0x9
+#define ARM_COND_GE		0xa
+#define ARM_COND_LT		0xb
+#define ARM_COND_GT		0xc
+#define ARM_COND_LE		0xd
+#define ARM_COND_AL		0xe
+
+/* register shift types */
+#define SRTYPE_LSL		0
+#define SRTYPE_LSR		1
+#define SRTYPE_ASR		2
+#define SRTYPE_ROR		3
+
+#define ARM_INST_ADD_R		0x00800000
+#define ARM_INST_ADD_I		0x02800000
+
+#define ARM_INST_AND_R		0x00000000
+#define ARM_INST_AND_I		0x02000000
+
+#define ARM_INST_BIC_R		0x01c00000
+#define ARM_INST_BIC_I		0x03c00000
+
+#define ARM_INST_B		0x0a000000
+#define ARM_INST_BX		0x012FFF10
+#define ARM_INST_BLX_R		0x012fff30
+
+#define ARM_INST_CMP_R		0x01500000
+#define ARM_INST_CMP_I		0x03500000
+
+#define ARM_INST_LDRB_I		0x05d00000
+#define ARM_INST_LDRB_R		0x07d00000
+#define ARM_INST_LDRH_I		0x01d000b0
+#define ARM_INST_LDR_I		0x05900000
+
+#define ARM_INST_LDM		0x08900000
+
+#define ARM_INST_LSL_I		0x01a00000
+#define ARM_INST_LSL_R		0x01a00010
+
+#define ARM_INST_LSR_I		0x01a00020
+#define ARM_INST_LSR_R		0x01a00030
+
+#define ARM_INST_MOV_R		0x01a00000
+#define ARM_INST_MOV_I		0x03a00000
+#define ARM_INST_MOVW		0x03000000
+#define ARM_INST_MOVT		0x03400000
+
+#define ARM_INST_MUL		0x00000090
+
+#define ARM_INST_POP		0x08bd0000
+#define ARM_INST_PUSH		0x092d0000
+
+#define ARM_INST_ORR_R		0x01800000
+#define ARM_INST_ORR_I		0x03800000
+
+#define ARM_INST_REV		0x06bf0f30
+#define ARM_INST_REV16		0x06bf0fb0
+
+#define ARM_INST_RSB_I		0x02600000
+
+#define ARM_INST_SUB_R		0x00400000
+#define ARM_INST_SUB_I		0x02400000
+
+#define ARM_INST_STR_I		0x05800000
+
+#define ARM_INST_TST_R		0x01100000
+#define ARM_INST_TST_I		0x03100000
+
+#define ARM_INST_UDIV		0x0730f010
+
+#define ARM_INST_UMULL		0x00800090
+
+/* register */
+#define _AL3_R(op, rd, rn, rm)	((op ## _R) | (rd) << 12 | (rn) << 16 | (rm))
+/* immediate */
+#define _AL3_I(op, rd, rn, imm)	((op ## _I) | (rd) << 12 | (rn) << 16 | (imm))
+
+#define ARM_ADD_R(rd, rn, rm)	_AL3_R(ARM_INST_ADD, rd, rn, rm)
+#define ARM_ADD_I(rd, rn, imm)	_AL3_I(ARM_INST_ADD, rd, rn, imm)
+
+#define ARM_AND_R(rd, rn, rm)	_AL3_R(ARM_INST_AND, rd, rn, rm)
+#define ARM_AND_I(rd, rn, imm)	_AL3_I(ARM_INST_AND, rd, rn, imm)
+
+#define ARM_BIC_R(rd, rn, rm)	_AL3_R(ARM_INST_BIC, rd, rn, rm)
+#define ARM_BIC_I(rd, rn, imm)	_AL3_I(ARM_INST_BIC, rd, rn, imm)
+
+#define ARM_B(imm24)		(ARM_INST_B | ((imm24) & 0xffffff))
+#define ARM_BX(rm)		(ARM_INST_BX | (rm))
+#define ARM_BLX_R(rm)		(ARM_INST_BLX_R | (rm))
+
+#define ARM_CMP_R(rn, rm)	_AL3_R(ARM_INST_CMP, 0, rn, rm)
+#define ARM_CMP_I(rn, imm)	_AL3_I(ARM_INST_CMP, 0, rn, imm)
+
+#define ARM_LDR_I(rt, rn, off)	(ARM_INST_LDR_I | (rt) << 12 | (rn) << 16 \
+				 | (off))
+#define ARM_LDRB_I(rt, rn, off)	(ARM_INST_LDRB_I | (rt) << 12 | (rn) << 16 \
+				 | (off))
+#define ARM_LDRB_R(rt, rn, rm)	(ARM_INST_LDRB_R | (rt) << 12 | (rn) << 16 \
+				 | (rm))
+#define ARM_LDRH_I(rt, rn, off)	(ARM_INST_LDRH_I | (rt) << 12 | (rn) << 16 \
+				 | (((off) & 0xf0) << 4) | ((off) & 0xf))
+
+#define ARM_LDM(rn, regs)	(ARM_INST_LDM | (rn) << 16 | (regs))
+
+#define ARM_LSL_R(rd, rn, rm)	(_AL3_R(ARM_INST_LSL, rd, 0, rn) | (rm) << 8)
+#define ARM_LSL_I(rd, rn, imm)	(_AL3_I(ARM_INST_LSL, rd, 0, rn) | (imm) << 7)
+
+#define ARM_LSR_R(rd, rn, rm)	(_AL3_R(ARM_INST_LSR, rd, 0, rn) | (rm) << 8)
+#define ARM_LSR_I(rd, rn, imm)	(_AL3_I(ARM_INST_LSR, rd, 0, rn) | (imm) << 7)
+
+#define ARM_MOV_R(rd, rm)	_AL3_R(ARM_INST_MOV, rd, 0, rm)
+#define ARM_MOV_I(rd, imm)	_AL3_I(ARM_INST_MOV, rd, 0, imm)
+
+#define ARM_MOVW(rd, imm)	\
+	(ARM_INST_MOVW | ((imm) >> 12) << 16 | (rd) << 12 | ((imm) & 0x0fff))
+
+#define ARM_MOVT(rd, imm)	\
+	(ARM_INST_MOVT | ((imm) >> 12) << 16 | (rd) << 12 | ((imm) & 0x0fff))
+
+#define ARM_MUL(rd, rm, rn)	(ARM_INST_MUL | (rd) << 16 | (rm) << 8 | (rn))
+
+#define ARM_POP(regs)		(ARM_INST_POP | (regs))
+#define ARM_PUSH(regs)		(ARM_INST_PUSH | (regs))
+
+#define ARM_ORR_R(rd, rn, rm)	_AL3_R(ARM_INST_ORR, rd, rn, rm)
+#define ARM_ORR_I(rd, rn, imm)	_AL3_I(ARM_INST_ORR, rd, rn, imm)
+#define ARM_ORR_S(rd, rn, rm, type, rs)	\
+	(ARM_ORR_R(rd, rn, rm) | (type) << 5 | (rs) << 7)
+
+#define ARM_REV(rd, rm)		(ARM_INST_REV | (rd) << 12 | (rm))
+#define ARM_REV16(rd, rm)	(ARM_INST_REV16 | (rd) << 12 | (rm))
+
+#define ARM_RSB_I(rd, rn, imm)	_AL3_I(ARM_INST_RSB, rd, rn, imm)
+
+#define ARM_SUB_R(rd, rn, rm)	_AL3_R(ARM_INST_SUB, rd, rn, rm)
+#define ARM_SUB_I(rd, rn, imm)	_AL3_I(ARM_INST_SUB, rd, rn, imm)
+
+#define ARM_STR_I(rt, rn, off)	(ARM_INST_STR_I | (rt) << 12 | (rn) << 16 \
+				 | (off))
+
+#define ARM_TST_R(rn, rm)	_AL3_R(ARM_INST_TST, 0, rn, rm)
+#define ARM_TST_I(rn, imm)	_AL3_I(ARM_INST_TST, 0, rn, imm)
+
+#define ARM_UDIV(rd, rn, rm)	(ARM_INST_UDIV | (rd) << 16 | (rn) | (rm) << 8)
+
+#define ARM_UMULL(rd_lo, rd_hi, rn, rm)	(ARM_INST_UMULL | (rd_hi) << 16 \
+					 | (rd_lo) << 12 | (rm) << 8 | rn)
+
+#endif /* PFILTER_OPCODES_ARM_H */
diff --git a/arch/arm/plat-mxc/include/mach/hardware.h b/arch/arm/plat-mxc/include/mach/hardware.h
index a599f01..0630513 100644
--- a/arch/arm/plat-mxc/include/mach/hardware.h
+++ b/arch/arm/plat-mxc/include/mach/hardware.h
@@ -22,11 +22,8 @@
 
 #include <asm/sizes.h>
 
-#ifdef __ASSEMBLER__
-#define IOMEM(addr)	(addr)
-#else
-#define IOMEM(addr)	((void __force __iomem *)(addr))
-#endif
+#define addr_in_module(addr, mod) \
+	((unsigned long)(addr) - mod ## _BASE_ADDR < mod ## _SIZE)
 
 #define IMX_IO_P2V_MODULE(addr, module)					\
 	(((addr) - module ## _BASE_ADDR) < module ## _SIZE ?		\
diff --git a/arch/arm/plat-mxc/include/mach/io.h b/arch/arm/plat-mxc/include/mach/io.h
deleted file mode 100644
index 338300b18..0000000
--- a/arch/arm/plat-mxc/include/mach/io.h
+++ /dev/null
@@ -1,39 +0,0 @@
-/*
- *  Copyright 2004-2007 Freescale Semiconductor, Inc. All Rights Reserved.
- */
-
-/*
- * 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_ARCH_MXC_IO_H__
-#define __ASM_ARCH_MXC_IO_H__
-
-/* Allow IO space to be anywhere in the memory */
-#define IO_SPACE_LIMIT 0xffffffff
-
-#define __arch_ioremap __imx_ioremap
-#define __arch_iounmap __iounmap
-
-#define addr_in_module(addr, mod) \
-	((unsigned long)(addr) - mod ## _BASE_ADDR < mod ## _SIZE)
-
-extern void __iomem *(*imx_ioremap)(unsigned long, size_t, unsigned int);
-
-static inline void __iomem *
-__imx_ioremap(unsigned long phys_addr, size_t size, unsigned int mtype)
-{
-	if (imx_ioremap != NULL)
-		return imx_ioremap(phys_addr, size, mtype);
-	else
-		return __arm_ioremap(phys_addr, size, mtype);
-}
-
-/* io address mapping macro */
-#define __io(a)		__typesafe_io(a)
-
-#define __mem_pci(a)	(a)
-
-#endif
diff --git a/arch/arm/plat-nomadik/Kconfig b/arch/arm/plat-nomadik/Kconfig
index bca4914..4c48c8b 100644
--- a/arch/arm/plat-nomadik/Kconfig
+++ b/arch/arm/plat-nomadik/Kconfig
@@ -23,7 +23,6 @@
 config NOMADIK_MTU_SCHED_CLOCK
 	bool
 	depends on HAS_MTU
-	select HAVE_SCHED_CLOCK
 	help
 	  Use the Multi Timer Unit as the sched_clock.
 
diff --git a/arch/arm/plat-nomadik/include/plat/ste_dma40.h b/arch/arm/plat-nomadik/include/plat/ste_dma40.h
index fd0ee84..9ff93b0 100644
--- a/arch/arm/plat-nomadik/include/plat/ste_dma40.h
+++ b/arch/arm/plat-nomadik/include/plat/ste_dma40.h
@@ -200,8 +200,7 @@
 	sg.dma_address = addr;
 	sg.length = size;
 
-	return chan->device->device_prep_slave_sg(chan, &sg, 1,
-						  direction, flags);
+	return dmaengine_prep_slave_sg(chan, &sg, 1, direction, flags);
 }
 
 #else
diff --git a/arch/arm/plat-omap/include/plat/gpio.h b/arch/arm/plat-omap/include/plat/gpio.h
index b8a96c6..2f6e992 100644
--- a/arch/arm/plat-omap/include/plat/gpio.h
+++ b/arch/arm/plat-omap/include/plat/gpio.h
@@ -158,10 +158,6 @@
 #define OMAP_MPUIO(nr)		(OMAP_MAX_GPIO_LINES + (nr))
 #define OMAP_GPIO_IS_MPUIO(nr)	((nr) >= OMAP_MAX_GPIO_LINES)
 
-#define OMAP_GPIO_IRQ(nr)	(OMAP_GPIO_IS_MPUIO(nr) ? \
-				 IH_MPUIO_BASE + ((nr) & 0x0f) : \
-				 IH_GPIO_BASE + (nr))
-
 struct omap_gpio_dev_attr {
 	int bank_width;		/* GPIO bank width */
 	bool dbck_flag;		/* dbck required or not - True for OMAP3&4 */
diff --git a/arch/arm/plat-omap/include/plat/hardware.h b/arch/arm/plat-omap/include/plat/hardware.h
index 537b05a..e897978 100644
--- a/arch/arm/plat-omap/include/plat/hardware.h
+++ b/arch/arm/plat-omap/include/plat/hardware.h
@@ -43,12 +43,6 @@
 #endif
 #include <plat/serial.h>
 
-#ifdef __ASSEMBLER__
-#define IOMEM(x)		(x)
-#else
-#define IOMEM(x)		((void __force __iomem *)(x))
-#endif
-
 /*
  * ---------------------------------------------------------------------------
  * Common definitions for all OMAP processors
diff --git a/arch/arm/plat-omap/include/plat/sdrc.h b/arch/arm/plat-omap/include/plat/sdrc.h
index 925b12b..9bb978e 100644
--- a/arch/arm/plat-omap/include/plat/sdrc.h
+++ b/arch/arm/plat-omap/include/plat/sdrc.h
@@ -16,7 +16,6 @@
  * published by the Free Software Foundation.
  */
 
-#include <mach/io.h>
 
 /* SDRC register offsets - read/write with sdrc_{read,write}_reg() */
 
diff --git a/arch/arm/plat-omap/include/plat/usb.h b/arch/arm/plat-omap/include/plat/usb.h
index d0fc9f4..762eeb06 100644
--- a/arch/arm/plat-omap/include/plat/usb.h
+++ b/arch/arm/plat-omap/include/plat/usb.h
@@ -112,7 +112,6 @@
  */
 
 #define OMAP2_L4_IO_OFFSET	0xb2000000
-#define IOMEM(x)		((void __force __iomem *)(x))
 #define OMAP2_L4_IO_ADDRESS(pa)	IOMEM((pa) + OMAP2_L4_IO_OFFSET)
 
 static inline u8 omap_readb(u32 pa)
diff --git a/arch/arm/plat-samsung/dma-ops.c b/arch/arm/plat-samsung/dma-ops.c
index 301d9c3..eb9f4f5 100644
--- a/arch/arm/plat-samsung/dma-ops.c
+++ b/arch/arm/plat-samsung/dma-ops.c
@@ -79,11 +79,11 @@
 			    info->len, offset_in_page(info->buf));
 		sg_dma_address(&sg) = info->buf;
 
-		desc = chan->device->device_prep_slave_sg(chan,
+		desc = dmaengine_prep_slave_sg(chan,
 			&sg, 1, info->direction, DMA_PREP_INTERRUPT);
 		break;
 	case DMA_CYCLIC:
-		desc = chan->device->device_prep_dma_cyclic(chan,
+		desc = dmaengine_prep_dma_cyclic(chan,
 			info->buf, info->len, info->period, info->direction);
 		break;
 	default:
diff --git a/arch/arm/plat-spear/include/plat/hardware.h b/arch/arm/plat-spear/include/plat/hardware.h
index 66d6772..70187d7 100644
--- a/arch/arm/plat-spear/include/plat/hardware.h
+++ b/arch/arm/plat-spear/include/plat/hardware.h
@@ -14,10 +14,4 @@
 #ifndef __PLAT_HARDWARE_H
 #define __PLAT_HARDWARE_H
 
-#ifndef __ASSEMBLY__
-#define IOMEM(x)	((void __iomem __force *)(x))
-#else
-#define IOMEM(x)	(x)
-#endif
-
 #endif /* __PLAT_HARDWARE_H */
diff --git a/arch/arm/plat-spear/include/plat/io.h b/arch/arm/plat-spear/include/plat/io.h
deleted file mode 100644
index 4d4ba82..0000000
--- a/arch/arm/plat-spear/include/plat/io.h
+++ /dev/null
@@ -1,22 +0,0 @@
-/*
- * arch/arm/plat-spear/include/plat/io.h
- *
- * IO definitions for SPEAr platform
- *
- * Copyright (C) 2009 ST Microelectronics
- * Viresh Kumar<viresh.kumar@st.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- */
-
-#ifndef __PLAT_IO_H
-#define __PLAT_IO_H
-
-#define IO_SPACE_LIMIT		0xFFFFFFFF
-
-#define __io(a)			__typesafe_io(a)
-#define __mem_pci(a)		(a)
-
-#endif /* __PLAT_IO_H */
diff --git a/arch/arm/plat-versatile/Kconfig b/arch/arm/plat-versatile/Kconfig
index 52353be..043f7b0 100644
--- a/arch/arm/plat-versatile/Kconfig
+++ b/arch/arm/plat-versatile/Kconfig
@@ -11,7 +11,6 @@
 	depends on ARCH_REALVIEW || ARCH_VERSATILE
 
 config PLAT_VERSATILE_SCHED_CLOCK
-	def_bool y if !ARCH_INTEGRATOR_AP
-	select HAVE_SCHED_CLOCK
+	def_bool y
 
 endif
diff --git a/arch/avr32/include/asm/posix_types.h b/arch/avr32/include/asm/posix_types.h
index fe0c0c0..74667bf 100644
--- a/arch/avr32/include/asm/posix_types.h
+++ b/arch/avr32/include/asm/posix_types.h
@@ -14,112 +14,27 @@
  * assume GCC is being used.
  */
 
-typedef unsigned long   __kernel_ino_t;
 typedef unsigned short  __kernel_mode_t;
+#define __kernel_mode_t __kernel_mode_t
+
 typedef unsigned short  __kernel_nlink_t;
-typedef long            __kernel_off_t;
-typedef int             __kernel_pid_t;
+#define __kernel_nlink_t __kernel_nlink_t
+
 typedef unsigned short  __kernel_ipc_pid_t;
-typedef unsigned int	__kernel_uid_t;
-typedef unsigned int	__kernel_gid_t;
+#define __kernel_ipc_pid_t __kernel_ipc_pid_t
+
 typedef unsigned long	__kernel_size_t;
 typedef long		__kernel_ssize_t;
 typedef int             __kernel_ptrdiff_t;
-typedef long            __kernel_time_t;
-typedef long            __kernel_suseconds_t;
-typedef long            __kernel_clock_t;
-typedef int             __kernel_timer_t;
-typedef int             __kernel_clockid_t;
-typedef int             __kernel_daddr_t;
-typedef char *          __kernel_caddr_t;
-typedef unsigned short  __kernel_uid16_t;
-typedef unsigned short  __kernel_gid16_t;
-typedef unsigned int    __kernel_uid32_t;
-typedef unsigned int    __kernel_gid32_t;
+#define __kernel_size_t __kernel_size_t
 
 typedef unsigned short  __kernel_old_uid_t;
 typedef unsigned short  __kernel_old_gid_t;
+#define __kernel_old_uid_t __kernel_old_uid_t
+
 typedef unsigned short  __kernel_old_dev_t;
+#define __kernel_old_dev_t __kernel_old_dev_t
 
-#ifdef __GNUC__
-typedef long long       __kernel_loff_t;
-#endif
-
-typedef struct {
-    int     val[2];
-} __kernel_fsid_t;
-
-#if defined(__KERNEL__)
-
-#undef  __FD_SET
-static __inline__ void __FD_SET(unsigned long __fd, __kernel_fd_set *__fdsetp)
-{
-    unsigned long __tmp = __fd / __NFDBITS;
-    unsigned long __rem = __fd % __NFDBITS;
-    __fdsetp->fds_bits[__tmp] |= (1UL<<__rem);
-}
-
-#undef  __FD_CLR
-static __inline__ void __FD_CLR(unsigned long __fd, __kernel_fd_set *__fdsetp)
-{
-    unsigned long __tmp = __fd / __NFDBITS;
-    unsigned long __rem = __fd % __NFDBITS;
-    __fdsetp->fds_bits[__tmp] &= ~(1UL<<__rem);
-}
-
-
-#undef  __FD_ISSET
-static __inline__ int __FD_ISSET(unsigned long __fd, const __kernel_fd_set *__p)
-{
-    unsigned long __tmp = __fd / __NFDBITS;
-    unsigned long __rem = __fd % __NFDBITS;
-    return (__p->fds_bits[__tmp] & (1UL<<__rem)) != 0;
-}
-
-/*
- * This will unroll the loop for the normal constant case (8 ints,
- * for a 256-bit fd_set)
- */
-#undef  __FD_ZERO
-static __inline__ void __FD_ZERO(__kernel_fd_set *__p)
-{
-    unsigned long *__tmp = __p->fds_bits;
-    int __i;
-
-    if (__builtin_constant_p(__FDSET_LONGS)) {
-        switch (__FDSET_LONGS) {
-            case 16:
-                __tmp[ 0] = 0; __tmp[ 1] = 0;
-                __tmp[ 2] = 0; __tmp[ 3] = 0;
-                __tmp[ 4] = 0; __tmp[ 5] = 0;
-                __tmp[ 6] = 0; __tmp[ 7] = 0;
-                __tmp[ 8] = 0; __tmp[ 9] = 0;
-                __tmp[10] = 0; __tmp[11] = 0;
-                __tmp[12] = 0; __tmp[13] = 0;
-                __tmp[14] = 0; __tmp[15] = 0;
-                return;
-
-            case 8:
-                __tmp[ 0] = 0; __tmp[ 1] = 0;
-                __tmp[ 2] = 0; __tmp[ 3] = 0;
-                __tmp[ 4] = 0; __tmp[ 5] = 0;
-                __tmp[ 6] = 0; __tmp[ 7] = 0;
-                return;
-
-            case 4:
-                __tmp[ 0] = 0; __tmp[ 1] = 0;
-                __tmp[ 2] = 0; __tmp[ 3] = 0;
-                return;
-        }
-    }
-    __i = __FDSET_LONGS;
-    while (__i) {
-        __i--;
-        *__tmp = 0;
-        __tmp++;
-    }
-}
-
-#endif /* defined(__KERNEL__) */
+#include <asm-generic/posix_types.h>
 
 #endif /* __ASM_AVR32_POSIX_TYPES_H */
diff --git a/arch/avr32/mach-at32ap/at32ap700x.c b/arch/avr32/mach-at32ap/at32ap700x.c
index 889c544..0445c4f 100644
--- a/arch/avr32/mach-at32ap/at32ap700x.c
+++ b/arch/avr32/mach-at32ap/at32ap700x.c
@@ -1351,7 +1351,6 @@
 		goto fail;
 
 	slave->sdata.dma_dev = &dw_dmac0_device.dev;
-	slave->sdata.reg_width = DW_DMA_SLAVE_WIDTH_32BIT;
 	slave->sdata.cfg_hi = (DWC_CFGH_SRC_PER(0)
 				| DWC_CFGH_DST_PER(1));
 	slave->sdata.cfg_lo &= ~(DWC_CFGL_HS_DST_POL
@@ -2046,27 +2045,19 @@
 	/* Check if DMA slave interface for capture should be configured. */
 	if (flags & AC97C_CAPTURE) {
 		rx_dws->dma_dev = &dw_dmac0_device.dev;
-		rx_dws->reg_width = DW_DMA_SLAVE_WIDTH_16BIT;
 		rx_dws->cfg_hi = DWC_CFGH_SRC_PER(3);
 		rx_dws->cfg_lo &= ~(DWC_CFGL_HS_DST_POL | DWC_CFGL_HS_SRC_POL);
 		rx_dws->src_master = 0;
 		rx_dws->dst_master = 1;
-		rx_dws->src_msize = DW_DMA_MSIZE_1;
-		rx_dws->dst_msize = DW_DMA_MSIZE_1;
-		rx_dws->fc = DW_DMA_FC_D_P2M;
 	}
 
 	/* Check if DMA slave interface for playback should be configured. */
 	if (flags & AC97C_PLAYBACK) {
 		tx_dws->dma_dev = &dw_dmac0_device.dev;
-		tx_dws->reg_width = DW_DMA_SLAVE_WIDTH_16BIT;
 		tx_dws->cfg_hi = DWC_CFGH_DST_PER(4);
 		tx_dws->cfg_lo &= ~(DWC_CFGL_HS_DST_POL | DWC_CFGL_HS_SRC_POL);
 		tx_dws->src_master = 0;
 		tx_dws->dst_master = 1;
-		tx_dws->src_msize = DW_DMA_MSIZE_1;
-		tx_dws->dst_msize = DW_DMA_MSIZE_1;
-		tx_dws->fc = DW_DMA_FC_D_M2P;
 	}
 
 	if (platform_device_add_data(pdev, data,
@@ -2136,14 +2127,10 @@
 	dws = &data->dws;
 
 	dws->dma_dev = &dw_dmac0_device.dev;
-	dws->reg_width = DW_DMA_SLAVE_WIDTH_32BIT;
 	dws->cfg_hi = DWC_CFGH_DST_PER(2);
 	dws->cfg_lo &= ~(DWC_CFGL_HS_DST_POL | DWC_CFGL_HS_SRC_POL);
 	dws->src_master = 0;
 	dws->dst_master = 1;
-	dws->src_msize = DW_DMA_MSIZE_1;
-	dws->dst_msize = DW_DMA_MSIZE_1;
-	dws->fc = DW_DMA_FC_D_M2P;
 
 	if (platform_device_add_data(pdev, data,
 				sizeof(struct atmel_abdac_pdata)))
diff --git a/arch/avr32/mach-at32ap/include/mach/atmel-mci.h b/arch/avr32/mach-at32ap/include/mach/atmel-mci.h
index a9b3896..4bba585 100644
--- a/arch/avr32/mach-at32ap/include/mach/atmel-mci.h
+++ b/arch/avr32/mach-at32ap/include/mach/atmel-mci.h
@@ -14,11 +14,4 @@
 #define	slave_data_ptr(s)	(&(s)->sdata)
 #define find_slave_dev(s)	((s)->sdata.dma_dev)
 
-#define	setup_dma_addr(s, t, r)	do {		\
-	if (s) {				\
-		(s)->sdata.tx_reg = (t);	\
-		(s)->sdata.rx_reg = (r);	\
-	}					\
-} while (0)
-
 #endif /* __MACH_ATMEL_MCI_H */
diff --git a/arch/c6x/Kconfig b/arch/c6x/Kconfig
index 3c64b28..1c3ccd4 100644
--- a/arch/c6x/Kconfig
+++ b/arch/c6x/Kconfig
@@ -11,7 +11,7 @@
 	select HAVE_DMA_API_DEBUG
 	select HAVE_GENERIC_HARDIRQS
 	select HAVE_MEMBLOCK
-	select HAVE_SPARSE_IRQ
+	select SPARSE_IRQ
 	select IRQ_DOMAIN
 	select OF
 	select OF_EARLY_FLATTREE
diff --git a/arch/cris/include/asm/posix_types.h b/arch/cris/include/asm/posix_types.h
index ce3fb25..72b3cd6 100644
--- a/arch/cris/include/asm/posix_types.h
+++ b/arch/cris/include/asm/posix_types.h
@@ -12,55 +12,25 @@
  * assume GCC is being used.
  */
 
-typedef unsigned long	__kernel_ino_t;
 typedef unsigned short	__kernel_mode_t;
+#define __kernel_mode_t __kernel_mode_t
+
 typedef unsigned short	__kernel_nlink_t;
-typedef long		__kernel_off_t;
-typedef int		__kernel_pid_t;
+#define __kernel_nlink_t __kernel_nlink_t
+
 typedef unsigned short  __kernel_ipc_pid_t;
+#define __kernel_ipc_pid_t __kernel_ipc_pid_t
+
 typedef unsigned short	__kernel_uid_t;
 typedef unsigned short	__kernel_gid_t;
+#define __kernel_uid_t __kernel_uid_t
+
 typedef __SIZE_TYPE__	__kernel_size_t;
 typedef long		__kernel_ssize_t;
 typedef int		__kernel_ptrdiff_t;
-typedef long		__kernel_time_t;
-typedef long            __kernel_suseconds_t;
-typedef long		__kernel_clock_t;
-typedef int		__kernel_timer_t;
-typedef int		__kernel_clockid_t;
-typedef int		__kernel_daddr_t;
-typedef char *		__kernel_caddr_t;
-typedef unsigned short  __kernel_uid16_t;
-typedef unsigned short  __kernel_gid16_t;
-typedef unsigned int    __kernel_uid32_t;
-typedef unsigned int    __kernel_gid32_t;
+#define __kernel_size_t __kernel_size_t
 
-typedef unsigned short  __kernel_old_uid_t;
-typedef unsigned short  __kernel_old_gid_t;
 typedef unsigned short	__kernel_old_dev_t;
-
-#ifdef __GNUC__
-typedef long long	__kernel_loff_t;
-#endif
-
-typedef struct {
-	int	val[2];
-} __kernel_fsid_t;
-
-#ifdef __KERNEL__
-
-#undef	__FD_SET
-#define __FD_SET(fd,fdsetp) set_bit(fd, (void *)(fdsetp))
-
-#undef	__FD_CLR
-#define __FD_CLR(fd,fdsetp) clear_bit(fd, (void *)(fdsetp))
-
-#undef	__FD_ISSET
-#define __FD_ISSET(fd,fdsetp) test_bit(fd, (void *)(fdsetp))
-
-#undef	__FD_ZERO
-#define __FD_ZERO(fdsetp) memset((void *)(fdsetp), 0, __FDSET_LONGS << 2)
-
-#endif /* __KERNEL__ */
+#define __kernel_old_dev_t __kernel_old_dev_t
 
 #endif /* __ARCH_CRIS_POSIX_TYPES_H */
diff --git a/arch/frv/include/asm/posix_types.h b/arch/frv/include/asm/posix_types.h
index a9f1f5b..3f34cb4 100644
--- a/arch/frv/include/asm/posix_types.h
+++ b/arch/frv/include/asm/posix_types.h
@@ -7,56 +7,23 @@
  * assume GCC is being used.
  */
 
-typedef unsigned long	__kernel_ino_t;
 typedef unsigned short	__kernel_mode_t;
+#define __kernel_mode_t __kernel_mode_t
+
 typedef unsigned short	__kernel_nlink_t;
-typedef long		__kernel_off_t;
-typedef int		__kernel_pid_t;
+#define __kernel_nlink_t __kernel_nlink_t
+
 typedef unsigned short	__kernel_ipc_pid_t;
+#define __kernel_ipc_pid_t __kernel_ipc_pid_t
+
 typedef unsigned short	__kernel_uid_t;
 typedef unsigned short	__kernel_gid_t;
-typedef unsigned int	__kernel_size_t;
-typedef int		__kernel_ssize_t;
-typedef int		__kernel_ptrdiff_t;
-typedef long		__kernel_time_t;
-typedef long		__kernel_suseconds_t;
-typedef long		__kernel_clock_t;
-typedef int		__kernel_timer_t;
-typedef int		__kernel_clockid_t;
-typedef int		__kernel_daddr_t;
-typedef char *		__kernel_caddr_t;
-typedef unsigned short	__kernel_uid16_t;
-typedef unsigned short	__kernel_gid16_t;
-typedef unsigned int	__kernel_uid32_t;
-typedef unsigned int	__kernel_gid32_t;
+#define __kernel_uid_t __kernel_uid_t
 
-typedef unsigned short	__kernel_old_uid_t;
-typedef unsigned short	__kernel_old_gid_t;
 typedef unsigned short	__kernel_old_dev_t;
+#define __kernel_old_dev_t __kernel_old_dev_t
 
-#ifdef __GNUC__
-typedef long long	__kernel_loff_t;
-#endif
-
-typedef struct {
-	int	val[2];
-} __kernel_fsid_t;
-
-#if defined(__KERNEL__)
-
-#undef	__FD_SET
-#define	__FD_SET(d, set)	((set)->fds_bits[__FDELT(d)] |= __FDMASK(d))
-
-#undef	__FD_CLR
-#define	__FD_CLR(d, set)	((set)->fds_bits[__FDELT(d)] &= ~__FDMASK(d))
-
-#undef	__FD_ISSET
-#define	__FD_ISSET(d, set)	(!!((set)->fds_bits[__FDELT(d)] & __FDMASK(d)))
-
-#undef	__FD_ZERO
-#define __FD_ZERO(fdsetp) (memset (fdsetp, 0, sizeof(*(fd_set *)fdsetp)))
-
-#endif /* defined(__KERNEL__) */
+#include <asm-generic/posix_types.h>
 
 #endif
 
diff --git a/arch/h8300/include/asm/posix_types.h b/arch/h8300/include/asm/posix_types.h
index 6f833a1..bc4c34e 100644
--- a/arch/h8300/include/asm/posix_types.h
+++ b/arch/h8300/include/asm/posix_types.h
@@ -7,54 +7,23 @@
  * assume GCC is being used.
  */
 
-typedef unsigned long	__kernel_ino_t;
 typedef unsigned short	__kernel_mode_t;
+#define __kernel_mode_t __kernel_mode_t
+
 typedef unsigned short	__kernel_nlink_t;
-typedef long		__kernel_off_t;
-typedef int		__kernel_pid_t;
+#define __kernel_nlink_t __kernel_nlink_t
+
 typedef unsigned short	__kernel_ipc_pid_t;
+#define __kernel_ipc_pid_t __kernel_ipc_pid_t
+
 typedef unsigned short	__kernel_uid_t;
 typedef unsigned short	__kernel_gid_t;
-typedef unsigned int	__kernel_size_t;
-typedef int		__kernel_ssize_t;
-typedef int		__kernel_ptrdiff_t;
-typedef long		__kernel_time_t;
-typedef long		__kernel_suseconds_t;
-typedef long		__kernel_clock_t;
-typedef int		__kernel_timer_t;
-typedef int		__kernel_clockid_t;
-typedef int		__kernel_daddr_t;
-typedef char *		__kernel_caddr_t;
-typedef unsigned short	__kernel_uid16_t;
-typedef unsigned short	__kernel_gid16_t;
-typedef unsigned int	__kernel_uid32_t;
-typedef unsigned int	__kernel_gid32_t;
+#define __kernel_uid_t __kernel_uid_t
 
 typedef unsigned short	__kernel_old_uid_t;
 typedef unsigned short	__kernel_old_gid_t;
+#define __kernel_old_uid_t __kernel_old_uid_t
 
-#ifdef __GNUC__
-typedef long long	__kernel_loff_t;
-#endif
-
-typedef struct {
-	int	val[2];
-} __kernel_fsid_t;
-
-#if defined(__KERNEL__)
-
-#undef	__FD_SET
-#define	__FD_SET(d, set)	((set)->fds_bits[__FDELT(d)] |= __FDMASK(d))
-
-#undef	__FD_CLR
-#define	__FD_CLR(d, set)	((set)->fds_bits[__FDELT(d)] &= ~__FDMASK(d))
-
-#undef	__FD_ISSET
-#define	__FD_ISSET(d, set)	(!!((set)->fds_bits[__FDELT(d)] & __FDMASK(d)))
-
-#undef	__FD_ZERO
-#define __FD_ZERO(fdsetp) (memset (fdsetp, 0, sizeof(*(fd_set *)fdsetp)))
-
-#endif /* defined(__KERNEL__) */
+#include <asm-generic/posix_types.h>
 
 #endif
diff --git a/arch/ia64/include/asm/cmpxchg.h b/arch/ia64/include/asm/cmpxchg.h
new file mode 100644
index 0000000..507c66c
--- /dev/null
+++ b/arch/ia64/include/asm/cmpxchg.h
@@ -0,0 +1 @@
+/* Future home of xchg() and cmpxchg() */
diff --git a/arch/ia64/include/asm/posix_types.h b/arch/ia64/include/asm/posix_types.h
index 17885567..7323ab9 100644
--- a/arch/ia64/include/asm/posix_types.h
+++ b/arch/ia64/include/asm/posix_types.h
@@ -1,126 +1,11 @@
 #ifndef _ASM_IA64_POSIX_TYPES_H
 #define _ASM_IA64_POSIX_TYPES_H
 
-/*
- * This file is generally used by user-level software, so you need to
- * be a little careful about namespace pollution etc.  Also, we cannot
- * assume GCC is being used.
- *
- * Based on <asm-alpha/posix_types.h>.
- *
- * Modified 1998-2000, 2003
- *	David Mosberger-Tang <davidm@hpl.hp.com>, Hewlett-Packard Co
- */
-
-typedef unsigned long	__kernel_ino_t;
-typedef unsigned int	__kernel_mode_t;
 typedef unsigned int	__kernel_nlink_t;
-typedef long		__kernel_off_t;
-typedef long long	__kernel_loff_t;
-typedef int		__kernel_pid_t;
-typedef int		__kernel_ipc_pid_t;
-typedef unsigned int	__kernel_uid_t;
-typedef unsigned int	__kernel_gid_t;
-typedef unsigned long	__kernel_size_t;
-typedef long		__kernel_ssize_t;
-typedef long		__kernel_ptrdiff_t;
-typedef long		__kernel_time_t;
-typedef long		__kernel_suseconds_t;
-typedef long		__kernel_clock_t;
-typedef int		__kernel_timer_t;
-typedef int		__kernel_clockid_t;
-typedef int		__kernel_daddr_t;
-typedef char *		__kernel_caddr_t;
+#define __kernel_nlink_t __kernel_nlink_t
+
 typedef unsigned long	__kernel_sigset_t;	/* at least 32 bits */
-typedef unsigned short	__kernel_uid16_t;
-typedef unsigned short	__kernel_gid16_t;
 
-typedef struct {
-	int	val[2];
-} __kernel_fsid_t;
+#include <asm-generic/posix_types.h>
 
-typedef __kernel_uid_t __kernel_old_uid_t;
-typedef __kernel_gid_t __kernel_old_gid_t;
-typedef __kernel_uid_t __kernel_uid32_t;
-typedef __kernel_gid_t __kernel_gid32_t;
-
-typedef unsigned int	__kernel_old_dev_t;
-
-# ifdef __KERNEL__
-
-#  ifndef __GNUC__
-
-#define	__FD_SET(d, set)	((set)->fds_bits[__FDELT(d)] |= __FDMASK(d))
-#define	__FD_CLR(d, set)	((set)->fds_bits[__FDELT(d)] &= ~__FDMASK(d))
-#define	__FD_ISSET(d, set)	(((set)->fds_bits[__FDELT(d)] & __FDMASK(d)) != 0)
-#define	__FD_ZERO(set)	\
-  ((void) memset ((void *) (set), 0, sizeof (__kernel_fd_set)))
-
-#  else /* !__GNUC__ */
-
-/* With GNU C, use inline functions instead so args are evaluated only once: */
-
-#undef __FD_SET
-static __inline__ void __FD_SET(unsigned long fd, __kernel_fd_set *fdsetp)
-{
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	fdsetp->fds_bits[_tmp] |= (1UL<<_rem);
-}
-
-#undef __FD_CLR
-static __inline__ void __FD_CLR(unsigned long fd, __kernel_fd_set *fdsetp)
-{
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	fdsetp->fds_bits[_tmp] &= ~(1UL<<_rem);
-}
-
-#undef __FD_ISSET
-static __inline__ int __FD_ISSET(unsigned long fd, const __kernel_fd_set *p)
-{ 
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	return (p->fds_bits[_tmp] & (1UL<<_rem)) != 0;
-}
-
-/*
- * This will unroll the loop for the normal constant case (8 ints,
- * for a 256-bit fd_set)
- */
-#undef __FD_ZERO
-static __inline__ void __FD_ZERO(__kernel_fd_set *p)
-{
-	unsigned long *tmp = p->fds_bits;
-	int i;
-
-	if (__builtin_constant_p(__FDSET_LONGS)) {
-		switch (__FDSET_LONGS) {
-		      case 16:
-			tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
-			tmp[ 4] = 0; tmp[ 5] = 0; tmp[ 6] = 0; tmp[ 7] = 0;
-			tmp[ 8] = 0; tmp[ 9] = 0; tmp[10] = 0; tmp[11] = 0;
-			tmp[12] = 0; tmp[13] = 0; tmp[14] = 0; tmp[15] = 0;
-			return;
-
-		      case 8:
-			tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
-			tmp[ 4] = 0; tmp[ 5] = 0; tmp[ 6] = 0; tmp[ 7] = 0;
-			return;
-
-		      case 4:
-			tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
-			return;
-		}
-	}
-	i = __FDSET_LONGS;
-	while (i) {
-		i--;
-		*tmp = 0;
-		tmp++;
-	}
-}
-
-#  endif /* !__GNUC__ */
-# endif /* __KERNEL__ */
 #endif /* _ASM_IA64_POSIX_TYPES_H */
diff --git a/arch/ia64/kernel/asm-offsets.c b/arch/ia64/kernel/asm-offsets.c
index af56501..a48bd9a 100644
--- a/arch/ia64/kernel/asm-offsets.c
+++ b/arch/ia64/kernel/asm-offsets.c
@@ -269,8 +269,8 @@
 	BLANK();
 
 	/* used by fsys_gettimeofday in arch/ia64/kernel/fsys.S */
-	DEFINE(IA64_GTOD_LOCK_OFFSET,
-		offsetof (struct fsyscall_gtod_data_t, lock));
+	DEFINE(IA64_GTOD_SEQ_OFFSET,
+	       offsetof (struct fsyscall_gtod_data_t, seq));
 	DEFINE(IA64_GTOD_WALL_TIME_OFFSET,
 		offsetof (struct fsyscall_gtod_data_t, wall_time));
 	DEFINE(IA64_GTOD_MONO_TIME_OFFSET,
diff --git a/arch/ia64/kernel/fsys.S b/arch/ia64/kernel/fsys.S
index f15d860..cc26eda 100644
--- a/arch/ia64/kernel/fsys.S
+++ b/arch/ia64/kernel/fsys.S
@@ -173,7 +173,7 @@
 	FSYS_RETURN
 END(fsys_set_tid_address)
 
-#if IA64_GTOD_LOCK_OFFSET !=0
+#if IA64_GTOD_SEQ_OFFSET !=0
 #error fsys_gettimeofday incompatible with changes to struct fsyscall_gtod_data_t
 #endif
 #if IA64_ITC_JITTER_OFFSET !=0
diff --git a/arch/ia64/kernel/fsyscall_gtod_data.h b/arch/ia64/kernel/fsyscall_gtod_data.h
index 57d2ee6..146b15b 100644
--- a/arch/ia64/kernel/fsyscall_gtod_data.h
+++ b/arch/ia64/kernel/fsyscall_gtod_data.h
@@ -6,7 +6,7 @@
  */
 
 struct fsyscall_gtod_data_t {
-	seqlock_t	lock;
+	seqcount_t	seq;
 	struct timespec	wall_time;
 	struct timespec monotonic_time;
 	cycle_t		clk_mask;
diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c
index 9dc52b6..ce74e14 100644
--- a/arch/ia64/kernel/process.c
+++ b/arch/ia64/kernel/process.c
@@ -38,6 +38,7 @@
 #include <asm/pgalloc.h>
 #include <asm/processor.h>
 #include <asm/sal.h>
+#include <asm/switch_to.h>
 #include <asm/tlbflush.h>
 #include <asm/uaccess.h>
 #include <asm/unwind.h>
diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c
index aa94bdd..ecc904b 100644
--- a/arch/ia64/kernel/time.c
+++ b/arch/ia64/kernel/time.c
@@ -34,9 +34,7 @@
 
 static cycle_t itc_get_cycles(struct clocksource *cs);
 
-struct fsyscall_gtod_data_t fsyscall_gtod_data = {
-	.lock = __SEQLOCK_UNLOCKED(fsyscall_gtod_data.lock),
-};
+struct fsyscall_gtod_data_t fsyscall_gtod_data;
 
 struct itc_jitter_data_t itc_jitter_data;
 
@@ -459,9 +457,7 @@
 void update_vsyscall(struct timespec *wall, struct timespec *wtm,
 			struct clocksource *c, u32 mult)
 {
-        unsigned long flags;
-
-        write_seqlock_irqsave(&fsyscall_gtod_data.lock, flags);
+	write_seqcount_begin(&fsyscall_gtod_data.seq);
 
         /* copy fsyscall clock data */
         fsyscall_gtod_data.clk_mask = c->mask;
@@ -484,6 +480,6 @@
 		fsyscall_gtod_data.monotonic_time.tv_sec++;
 	}
 
-        write_sequnlock_irqrestore(&fsyscall_gtod_data.lock, flags);
+	write_seqcount_end(&fsyscall_gtod_data.seq);
 }
 
diff --git a/arch/m32r/include/asm/posix_types.h b/arch/m32r/include/asm/posix_types.h
index b309c58..0195850 100644
--- a/arch/m32r/include/asm/posix_types.h
+++ b/arch/m32r/include/asm/posix_types.h
@@ -7,112 +7,22 @@
  * assume GCC is being used.
  */
 
-typedef unsigned long	__kernel_ino_t;
 typedef unsigned short	__kernel_mode_t;
+#define __kernel_mode_t __kernel_mode_t
+
 typedef unsigned short	__kernel_nlink_t;
-typedef long		__kernel_off_t;
-typedef int		__kernel_pid_t;
+#define __kernel_nlink_t __kernel_nlink_t
+
 typedef unsigned short	__kernel_ipc_pid_t;
+#define __kernel_ipc_pid_t __kernel_ipc_pid_t
+
 typedef unsigned short	__kernel_uid_t;
 typedef unsigned short	__kernel_gid_t;
-typedef unsigned int	__kernel_size_t;
-typedef int		__kernel_ssize_t;
-typedef int		__kernel_ptrdiff_t;
-typedef long		__kernel_time_t;
-typedef long		__kernel_suseconds_t;
-typedef long		__kernel_clock_t;
-typedef int		__kernel_timer_t;
-typedef int		__kernel_clockid_t;
-typedef int		__kernel_daddr_t;
-typedef char *		__kernel_caddr_t;
-typedef unsigned short	__kernel_uid16_t;
-typedef unsigned short	__kernel_gid16_t;
-typedef unsigned int	__kernel_uid32_t;
-typedef unsigned int	__kernel_gid32_t;
+#define __kernel_uid_t __kernel_uid_t
 
-typedef unsigned short	__kernel_old_uid_t;
-typedef unsigned short	__kernel_old_gid_t;
 typedef unsigned short	__kernel_old_dev_t;
+#define __kernel_old_dev_t __kernel_old_dev_t
 
-#ifdef __GNUC__
-typedef long long	__kernel_loff_t;
-#endif
-
-typedef struct {
-	int	val[2];
-} __kernel_fsid_t;
-
-#if defined(__KERNEL__)
-
-#undef	__FD_SET
-static __inline__ void __FD_SET(unsigned long __fd, __kernel_fd_set *__fdsetp)
-{
-	unsigned long __tmp = __fd / __NFDBITS;
-	unsigned long __rem = __fd % __NFDBITS;
-	__fdsetp->fds_bits[__tmp] |= (1UL<<__rem);
-}
-
-#undef	__FD_CLR
-static __inline__ void __FD_CLR(unsigned long __fd, __kernel_fd_set *__fdsetp)
-{
-	unsigned long __tmp = __fd / __NFDBITS;
-	unsigned long __rem = __fd % __NFDBITS;
-	__fdsetp->fds_bits[__tmp] &= ~(1UL<<__rem);
-}
-
-
-#undef	__FD_ISSET
-static __inline__ int __FD_ISSET(unsigned long __fd, const __kernel_fd_set *__p)
-{
-	unsigned long __tmp = __fd / __NFDBITS;
-	unsigned long __rem = __fd % __NFDBITS;
-	return (__p->fds_bits[__tmp] & (1UL<<__rem)) != 0;
-}
-
-/*
- * This will unroll the loop for the normal constant case (8 ints,
- * for a 256-bit fd_set)
- */
-#undef	__FD_ZERO
-static __inline__ void __FD_ZERO(__kernel_fd_set *__p)
-{
-	unsigned long *__tmp = __p->fds_bits;
-	int __i;
-
-	if (__builtin_constant_p(__FDSET_LONGS)) {
-		switch (__FDSET_LONGS) {
-		case 16:
-			__tmp[ 0] = 0; __tmp[ 1] = 0;
-			__tmp[ 2] = 0; __tmp[ 3] = 0;
-			__tmp[ 4] = 0; __tmp[ 5] = 0;
-			__tmp[ 6] = 0; __tmp[ 7] = 0;
-			__tmp[ 8] = 0; __tmp[ 9] = 0;
-			__tmp[10] = 0; __tmp[11] = 0;
-			__tmp[12] = 0; __tmp[13] = 0;
-			__tmp[14] = 0; __tmp[15] = 0;
-			return;
-
-		case 8:
-			__tmp[ 0] = 0; __tmp[ 1] = 0;
-			__tmp[ 2] = 0; __tmp[ 3] = 0;
-			__tmp[ 4] = 0; __tmp[ 5] = 0;
-			__tmp[ 6] = 0; __tmp[ 7] = 0;
-			return;
-
-		case 4:
-			__tmp[ 0] = 0; __tmp[ 1] = 0;
-			__tmp[ 2] = 0; __tmp[ 3] = 0;
-			return;
-		}
-	}
-	__i = __FDSET_LONGS;
-	while (__i) {
-		__i--;
-		*__tmp = 0;
-		__tmp++;
-	}
-}
-
-#endif /* defined(__KERNEL__) */
+#include <asm-generic/posix_types.h>
 
 #endif  /* _ASM_M32R_POSIX_TYPES_H */
diff --git a/arch/m68k/include/asm/posix_types.h b/arch/m68k/include/asm/posix_types.h
index 98d0970..6373093 100644
--- a/arch/m68k/include/asm/posix_types.h
+++ b/arch/m68k/include/asm/posix_types.h
@@ -7,55 +7,22 @@
  * assume GCC is being used.
  */
 
-typedef unsigned long	__kernel_ino_t;
 typedef unsigned short	__kernel_mode_t;
+#define __kernel_mode_t __kernel_mode_t
+
 typedef unsigned short	__kernel_nlink_t;
-typedef long		__kernel_off_t;
-typedef int		__kernel_pid_t;
+#define __kernel_nlink_t __kernel_nlink_t
+
 typedef unsigned short	__kernel_ipc_pid_t;
+#define __kernel_ipc_pid_t __kernel_ipc_pid_t
+
 typedef unsigned short	__kernel_uid_t;
 typedef unsigned short	__kernel_gid_t;
-typedef unsigned int	__kernel_size_t;
-typedef int		__kernel_ssize_t;
-typedef int		__kernel_ptrdiff_t;
-typedef long		__kernel_time_t;
-typedef long		__kernel_suseconds_t;
-typedef long		__kernel_clock_t;
-typedef int		__kernel_timer_t;
-typedef int		__kernel_clockid_t;
-typedef int		__kernel_daddr_t;
-typedef char *		__kernel_caddr_t;
-typedef unsigned short	__kernel_uid16_t;
-typedef unsigned short	__kernel_gid16_t;
-typedef unsigned int	__kernel_uid32_t;
-typedef unsigned int	__kernel_gid32_t;
+#define __kernel_uid_t __kernel_uid_t
 
-typedef unsigned short	__kernel_old_uid_t;
-typedef unsigned short	__kernel_old_gid_t;
 typedef unsigned short	__kernel_old_dev_t;
+#define __kernel_old_dev_t __kernel_old_dev_t
 
-#ifdef __GNUC__
-typedef long long	__kernel_loff_t;
-#endif
-
-typedef struct {
-	int	val[2];
-} __kernel_fsid_t;
-
-#if defined(__KERNEL__)
-
-#undef	__FD_SET
-#define	__FD_SET(d, set)	((set)->fds_bits[__FDELT(d)] |= __FDMASK(d))
-
-#undef	__FD_CLR
-#define	__FD_CLR(d, set)	((set)->fds_bits[__FDELT(d)] &= ~__FDMASK(d))
-
-#undef	__FD_ISSET
-#define	__FD_ISSET(d, set)	(!!((set)->fds_bits[__FDELT(d)] & __FDMASK(d)))
-
-#undef	__FD_ZERO
-#define __FD_ZERO(fdsetp) (memset (fdsetp, 0, sizeof(*(fd_set *)fdsetp)))
-
-#endif /* defined(__KERNEL__) */
+#include <asm-generic/posix_types.h>
 
 #endif
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index edbbae1..ce30e2f 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -2457,6 +2457,7 @@
 config COMPAT
 	bool
 	depends on MIPS32_COMPAT
+	select ARCH_WANT_OLD_COMPAT_IPC
 	default y
 
 config SYSVIPC_COMPAT
diff --git a/arch/mips/configs/db1300_defconfig b/arch/mips/configs/db1300_defconfig
index c38b190..3590ab5 100644
--- a/arch/mips/configs/db1300_defconfig
+++ b/arch/mips/configs/db1300_defconfig
@@ -133,7 +133,7 @@
 CONFIG_IOSCHED_NOOP=y
 CONFIG_DEFAULT_NOOP=y
 CONFIG_DEFAULT_IOSCHED="noop"
-CONFIG_INLINE_SPIN_UNLOCK=y
+# CONFIG_UNINLINE_SPIN_UNLOCK is not set
 CONFIG_INLINE_SPIN_UNLOCK_IRQ=y
 CONFIG_INLINE_READ_UNLOCK=y
 CONFIG_INLINE_READ_UNLOCK_IRQ=y
diff --git a/arch/mips/include/asm/posix_types.h b/arch/mips/include/asm/posix_types.h
index c200102..e0308dc 100644
--- a/arch/mips/include/asm/posix_types.h
+++ b/arch/mips/include/asm/posix_types.h
@@ -17,128 +17,21 @@
  * assume GCC is being used.
  */
 
-typedef unsigned long	__kernel_ino_t;
-typedef unsigned int	__kernel_mode_t;
-#if (_MIPS_SZLONG == 32)
-typedef unsigned long	__kernel_nlink_t;
-#endif
 #if (_MIPS_SZLONG == 64)
 typedef unsigned int	__kernel_nlink_t;
+#define __kernel_nlink_t __kernel_nlink_t
 #endif
-typedef long		__kernel_off_t;
-typedef int		__kernel_pid_t;
-typedef int		__kernel_ipc_pid_t;
-typedef unsigned int	__kernel_uid_t;
-typedef unsigned int	__kernel_gid_t;
-#if (_MIPS_SZLONG == 32)
-typedef unsigned int	__kernel_size_t;
-typedef int		__kernel_ssize_t;
-typedef int		__kernel_ptrdiff_t;
-#endif
-#if (_MIPS_SZLONG == 64)
-typedef unsigned long	__kernel_size_t;
-typedef long		__kernel_ssize_t;
-typedef long		__kernel_ptrdiff_t;
-#endif
-typedef long		__kernel_time_t;
-typedef long		__kernel_suseconds_t;
-typedef long		__kernel_clock_t;
-typedef int		__kernel_timer_t;
-typedef int		__kernel_clockid_t;
+
 typedef long		__kernel_daddr_t;
-typedef char *		__kernel_caddr_t;
+#define __kernel_daddr_t __kernel_daddr_t
 
-typedef unsigned short	__kernel_uid16_t;
-typedef unsigned short	__kernel_gid16_t;
-typedef unsigned int	__kernel_uid32_t;
-typedef unsigned int	__kernel_gid32_t;
-typedef __kernel_uid_t	__kernel_old_uid_t;
-typedef __kernel_gid_t	__kernel_old_gid_t;
-typedef unsigned int	__kernel_old_dev_t;
-
-#ifdef __GNUC__
-typedef long long      __kernel_loff_t;
-#endif
-
-typedef struct {
 #if (_MIPS_SZLONG == 32)
+typedef struct {
 	long	val[2];
-#endif
-#if (_MIPS_SZLONG == 64)
-	int	val[2];
-#endif
 } __kernel_fsid_t;
+#define __kernel_fsid_t __kernel_fsid_t
+#endif
 
-#if defined(__KERNEL__)
-
-#undef __FD_SET
-static __inline__ void __FD_SET(unsigned long __fd, __kernel_fd_set *__fdsetp)
-{
-	unsigned long __tmp = __fd / __NFDBITS;
-	unsigned long __rem = __fd % __NFDBITS;
-	__fdsetp->fds_bits[__tmp] |= (1UL<<__rem);
-}
-
-#undef __FD_CLR
-static __inline__ void __FD_CLR(unsigned long __fd, __kernel_fd_set *__fdsetp)
-{
-	unsigned long __tmp = __fd / __NFDBITS;
-	unsigned long __rem = __fd % __NFDBITS;
-	__fdsetp->fds_bits[__tmp] &= ~(1UL<<__rem);
-}
-
-#undef __FD_ISSET
-static __inline__ int __FD_ISSET(unsigned long __fd, const __kernel_fd_set *__p)
-{
-	unsigned long __tmp = __fd / __NFDBITS;
-	unsigned long __rem = __fd % __NFDBITS;
-	return (__p->fds_bits[__tmp] & (1UL<<__rem)) != 0;
-}
-
-/*
- * This will unroll the loop for the normal constant case (8 ints,
- * for a 256-bit fd_set)
- */
-#undef __FD_ZERO
-static __inline__ void __FD_ZERO(__kernel_fd_set *__p)
-{
-	unsigned long *__tmp = __p->fds_bits;
-	int __i;
-
-	if (__builtin_constant_p(__FDSET_LONGS)) {
-		switch (__FDSET_LONGS) {
-		case 16:
-			__tmp[ 0] = 0; __tmp[ 1] = 0;
-			__tmp[ 2] = 0; __tmp[ 3] = 0;
-			__tmp[ 4] = 0; __tmp[ 5] = 0;
-			__tmp[ 6] = 0; __tmp[ 7] = 0;
-			__tmp[ 8] = 0; __tmp[ 9] = 0;
-			__tmp[10] = 0; __tmp[11] = 0;
-			__tmp[12] = 0; __tmp[13] = 0;
-			__tmp[14] = 0; __tmp[15] = 0;
-			return;
-
-		case 8:
-			__tmp[ 0] = 0; __tmp[ 1] = 0;
-			__tmp[ 2] = 0; __tmp[ 3] = 0;
-			__tmp[ 4] = 0; __tmp[ 5] = 0;
-			__tmp[ 6] = 0; __tmp[ 7] = 0;
-			return;
-
-		case 4:
-			__tmp[ 0] = 0; __tmp[ 1] = 0;
-			__tmp[ 2] = 0; __tmp[ 3] = 0;
-			return;
-		}
-	}
-	__i = __FDSET_LONGS;
-	while (__i) {
-		__i--;
-		*__tmp = 0;
-		__tmp++;
-	}
-}
-
-#endif /* defined(__KERNEL__) */
+#include <asm-generic/posix_types.h>
 
 #endif /* _ASM_POSIX_TYPES_H */
diff --git a/arch/mips/kernel/kspd.c b/arch/mips/kernel/kspd.c
index 29811f0..84d0639 100644
--- a/arch/mips/kernel/kspd.c
+++ b/arch/mips/kernel/kspd.c
@@ -326,7 +326,7 @@
 		i = j * __NFDBITS;
 		if (i >= fdt->max_fds)
 			break;
-		set = fdt->open_fds->fds_bits[j++];
+		set = fdt->open_fds[j++];
 		while (set) {
 			if (set & 1) {
 				struct file * file = xchg(&fdt->fd[i], NULL);
diff --git a/arch/mn10300/include/asm/posix_types.h b/arch/mn10300/include/asm/posix_types.h
index 56ffbc1..ab50618 100644
--- a/arch/mn10300/include/asm/posix_types.h
+++ b/arch/mn10300/include/asm/posix_types.h
@@ -17,14 +17,19 @@
  * assume GCC is being used.
  */
 
-typedef unsigned long	__kernel_ino_t;
 typedef unsigned short	__kernel_mode_t;
+#define __kernel_mode_t __kernel_mode_t
+
 typedef unsigned short	__kernel_nlink_t;
-typedef long		__kernel_off_t;
-typedef int		__kernel_pid_t;
+#define __kernel_nlink_t __kernel_nlink_t
+
 typedef unsigned short	__kernel_ipc_pid_t;
+#define __kernel_ipc_pid_t __kernel_ipc_pid_t
+
 typedef unsigned short	__kernel_uid_t;
 typedef unsigned short	__kernel_gid_t;
+#define __kernel_uid_t __kernel_uid_t
+
 #if __GNUC__ == 4
 typedef unsigned int	__kernel_size_t;
 typedef signed int	__kernel_ssize_t;
@@ -33,105 +38,11 @@
 typedef signed long	__kernel_ssize_t;
 #endif
 typedef int		__kernel_ptrdiff_t;
-typedef long		__kernel_time_t;
-typedef long		__kernel_suseconds_t;
-typedef long		__kernel_clock_t;
-typedef int		__kernel_timer_t;
-typedef int		__kernel_clockid_t;
-typedef int		__kernel_daddr_t;
-typedef char *		__kernel_caddr_t;
-typedef unsigned short	__kernel_uid16_t;
-typedef unsigned short	__kernel_gid16_t;
-typedef unsigned int	__kernel_uid32_t;
-typedef unsigned int	__kernel_gid32_t;
+#define __kernel_size_t __kernel_size_t
 
-typedef unsigned short	__kernel_old_uid_t;
-typedef unsigned short	__kernel_old_gid_t;
 typedef unsigned short	__kernel_old_dev_t;
+#define __kernel_old_dev_t __kernel_old_dev_t
 
-#ifdef __GNUC__
-typedef long long	__kernel_loff_t;
-#endif
-
-typedef struct {
-#if defined(__KERNEL__) || defined(__USE_ALL)
-	int	val[2];
-#else /* !defined(__KERNEL__) && !defined(__USE_ALL) */
-	int	__val[2];
-#endif /* !defined(__KERNEL__) && !defined(__USE_ALL) */
-} __kernel_fsid_t;
-
-#if defined(__KERNEL__) || !defined(__GLIBC__) || (__GLIBC__ < 2)
-
-#undef	__FD_SET
-static inline void __FD_SET(unsigned long __fd, __kernel_fd_set *__fdsetp)
-{
-	unsigned long __tmp = __fd / __NFDBITS;
-	unsigned long __rem = __fd % __NFDBITS;
-	__fdsetp->fds_bits[__tmp] |= (1UL<<__rem);
-}
-
-#undef	__FD_CLR
-static inline void __FD_CLR(unsigned long __fd, __kernel_fd_set *__fdsetp)
-{
-	unsigned long __tmp = __fd / __NFDBITS;
-	unsigned long __rem = __fd % __NFDBITS;
-	__fdsetp->fds_bits[__tmp] &= ~(1UL<<__rem);
-}
-
-
-#undef	__FD_ISSET
-static inline int __FD_ISSET(unsigned long __fd, const __kernel_fd_set *__p)
-{
-	unsigned long __tmp = __fd / __NFDBITS;
-	unsigned long __rem = __fd % __NFDBITS;
-	return (__p->fds_bits[__tmp] & (1UL<<__rem)) != 0;
-}
-
-/*
- * This will unroll the loop for the normal constant case (8 ints,
- * for a 256-bit fd_set)
- */
-#undef	__FD_ZERO
-static inline void __FD_ZERO(__kernel_fd_set *__p)
-{
-	unsigned long *__tmp = __p->fds_bits;
-	int __i;
-
-	if (__builtin_constant_p(__FDSET_LONGS)) {
-		switch (__FDSET_LONGS) {
-		case 16:
-			__tmp[ 0] = 0; __tmp[ 1] = 0;
-			__tmp[ 2] = 0; __tmp[ 3] = 0;
-			__tmp[ 4] = 0; __tmp[ 5] = 0;
-			__tmp[ 6] = 0; __tmp[ 7] = 0;
-			__tmp[ 8] = 0; __tmp[ 9] = 0;
-			__tmp[10] = 0; __tmp[11] = 0;
-			__tmp[12] = 0; __tmp[13] = 0;
-			__tmp[14] = 0; __tmp[15] = 0;
-			return;
-
-		case 8:
-			__tmp[ 0] = 0; __tmp[ 1] = 0;
-			__tmp[ 2] = 0; __tmp[ 3] = 0;
-			__tmp[ 4] = 0; __tmp[ 5] = 0;
-			__tmp[ 6] = 0; __tmp[ 7] = 0;
-			return;
-
-		case 4:
-			__tmp[ 0] = 0; __tmp[ 1] = 0;
-			__tmp[ 2] = 0; __tmp[ 3] = 0;
-			return;
-		}
-	}
-	__i = __FDSET_LONGS;
-	while (__i) {
-		__i--;
-		*__tmp = 0;
-		__tmp++;
-	}
-}
-
-#endif /* defined(__KERNEL__) || !defined(__GLIBC__) || (__GLIBC__ < 2) */
+#include <asm-generic/posix_types.h>
 
 #endif /* _ASM_POSIX_TYPES_H */
diff --git a/arch/parisc/include/asm/posix_types.h b/arch/parisc/include/asm/posix_types.h
index 00da29a..5212b03 100644
--- a/arch/parisc/include/asm/posix_types.h
+++ b/arch/parisc/include/asm/posix_types.h
@@ -6,123 +6,22 @@
  * be a little careful about namespace pollution etc.  Also, we cannot
  * assume GCC is being used.
  */
-typedef unsigned long		__kernel_ino_t;
+
 typedef unsigned short		__kernel_mode_t;
+#define __kernel_mode_t __kernel_mode_t
+
 typedef unsigned short		__kernel_nlink_t;
-typedef long			__kernel_off_t;
-typedef int			__kernel_pid_t;
+#define __kernel_nlink_t __kernel_nlink_t
+
 typedef unsigned short		__kernel_ipc_pid_t;
-typedef unsigned int		__kernel_uid_t;
-typedef unsigned int		__kernel_gid_t;
+#define __kernel_ipc_pid_t __kernel_ipc_pid_t
+
 typedef int			__kernel_suseconds_t;
-typedef long			__kernel_clock_t;
-typedef int			__kernel_timer_t;
-typedef int			__kernel_clockid_t;
-typedef int			__kernel_daddr_t;
-/* Note these change from narrow to wide kernels */
-#ifdef CONFIG_64BIT
-typedef unsigned long		__kernel_size_t;
-typedef long			__kernel_ssize_t;
-typedef long			__kernel_ptrdiff_t;
-#else
-typedef unsigned int		__kernel_size_t;
-typedef int			__kernel_ssize_t;
-typedef int			__kernel_ptrdiff_t;
-#endif
-typedef long			__kernel_time_t;
-typedef char *			__kernel_caddr_t;
+#define __kernel_suseconds_t __kernel_suseconds_t
 
-typedef unsigned short		__kernel_uid16_t;
-typedef unsigned short		__kernel_gid16_t;
-typedef unsigned int		__kernel_uid32_t;
-typedef unsigned int		__kernel_gid32_t;
-
-#ifdef __GNUC__
-typedef long long		__kernel_loff_t;
 typedef long long		__kernel_off64_t;
 typedef unsigned long long	__kernel_ino64_t;
-#endif
 
-typedef unsigned int		__kernel_old_dev_t;
-
-typedef struct {
-	int	val[2];
-} __kernel_fsid_t;
-
-/* compatibility stuff */
-typedef __kernel_uid_t __kernel_old_uid_t;
-typedef __kernel_gid_t __kernel_old_gid_t;
-
-#if defined(__KERNEL__)
-
-#undef __FD_SET
-static __inline__ void __FD_SET(unsigned long __fd, __kernel_fd_set *__fdsetp)
-{
-	unsigned long __tmp = __fd / __NFDBITS;
-	unsigned long __rem = __fd % __NFDBITS;
-	__fdsetp->fds_bits[__tmp] |= (1UL<<__rem);
-}
-
-#undef __FD_CLR
-static __inline__ void __FD_CLR(unsigned long __fd, __kernel_fd_set *__fdsetp)
-{
-	unsigned long __tmp = __fd / __NFDBITS;
-	unsigned long __rem = __fd % __NFDBITS;
-	__fdsetp->fds_bits[__tmp] &= ~(1UL<<__rem);
-}
-
-#undef __FD_ISSET
-static __inline__ int __FD_ISSET(unsigned long __fd, const __kernel_fd_set *__p)
-{ 
-	unsigned long __tmp = __fd / __NFDBITS;
-	unsigned long __rem = __fd % __NFDBITS;
-	return (__p->fds_bits[__tmp] & (1UL<<__rem)) != 0;
-}
-
-/*
- * This will unroll the loop for the normal constant case (8 ints,
- * for a 256-bit fd_set)
- */
-#undef __FD_ZERO
-static __inline__ void __FD_ZERO(__kernel_fd_set *__p)
-{
-	unsigned long *__tmp = __p->fds_bits;
-	int __i;
-
-	if (__builtin_constant_p(__FDSET_LONGS)) {
-		switch (__FDSET_LONGS) {
-		case 16:
-			__tmp[ 0] = 0; __tmp[ 1] = 0;
-			__tmp[ 2] = 0; __tmp[ 3] = 0;
-			__tmp[ 4] = 0; __tmp[ 5] = 0;
-			__tmp[ 6] = 0; __tmp[ 7] = 0;
-			__tmp[ 8] = 0; __tmp[ 9] = 0;
-			__tmp[10] = 0; __tmp[11] = 0;
-			__tmp[12] = 0; __tmp[13] = 0;
-			__tmp[14] = 0; __tmp[15] = 0;
-			return;
-
-		case 8:
-			__tmp[ 0] = 0; __tmp[ 1] = 0;
-			__tmp[ 2] = 0; __tmp[ 3] = 0;
-			__tmp[ 4] = 0; __tmp[ 5] = 0;
-			__tmp[ 6] = 0; __tmp[ 7] = 0;
-			return;
-
-		case 4:
-			__tmp[ 0] = 0; __tmp[ 1] = 0;
-			__tmp[ 2] = 0; __tmp[ 3] = 0;
-			return;
-		}
-	}
-	__i = __FDSET_LONGS;
-	while (__i) {
-		__i--;
-		*__tmp = 0;
-		__tmp++;
-	}
-}
-
-#endif /* defined(__KERNEL__) */
+#include <asm-generic/posix_types.h>
 
 #endif
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index d219ebe..feab3ba 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -133,7 +133,6 @@
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_HW_BREAKPOINT if PERF_EVENTS && PPC_BOOK3S_64
 	select HAVE_GENERIC_HARDIRQS
-	select HAVE_SPARSE_IRQ
 	select SPARSE_IRQ
 	select IRQ_PER_CPU
 	select IRQ_DOMAIN
@@ -154,6 +153,7 @@
 	bool
 	default y if PPC64
 	select COMPAT_BINFMT_ELF
+	select ARCH_WANT_OLD_COMPAT_IPC
 
 config SYSVIPC_COMPAT
 	bool
diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug
index 72d55db..e5f2689 100644
--- a/arch/powerpc/Kconfig.debug
+++ b/arch/powerpc/Kconfig.debug
@@ -114,16 +114,6 @@
 	depends on KGDB || XMON
 	default y
 
-config VIRQ_DEBUG
-	bool "Expose hardware/virtual IRQ mapping via debugfs"
-	depends on DEBUG_FS
-	help
-	  This option will show the mapping relationship between hardware irq
-	  numbers and virtual irq numbers. The mapping is exposed via debugfs
-	  in the file powerpc/virq_mapping.
-
-	  If you don't know what this means you don't need it.
-
 config BDI_SWITCH
 	bool "Include BDI-2000 user context switcher"
 	depends on DEBUG_KERNEL && PPC32
diff --git a/arch/powerpc/configs/85xx/p1023rds_defconfig b/arch/powerpc/configs/85xx/p1023rds_defconfig
index c091aaf..f4337ba 100644
--- a/arch/powerpc/configs/85xx/p1023rds_defconfig
+++ b/arch/powerpc/configs/85xx/p1023rds_defconfig
@@ -165,7 +165,7 @@
 CONFIG_DEBUG_INFO=y
 # CONFIG_RCU_CPU_STALL_DETECTOR is not set
 CONFIG_SYSCTL_SYSCALL_CHECK=y
-CONFIG_VIRQ_DEBUG=y
+CONFIG_IRQ_DOMAIN_DEBUG=y
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_SHA256=y
 CONFIG_CRYPTO_SHA512=y
diff --git a/arch/powerpc/configs/chroma_defconfig b/arch/powerpc/configs/chroma_defconfig
index acf7fb2..f104ccd 100644
--- a/arch/powerpc/configs/chroma_defconfig
+++ b/arch/powerpc/configs/chroma_defconfig
@@ -279,7 +279,7 @@
 CONFIG_PPC_EMULATED_STATS=y
 CONFIG_XMON=y
 CONFIG_XMON_DEFAULT=y
-CONFIG_VIRQ_DEBUG=y
+CONFIG_IRQ_DOMAIN_DEBUG=y
 CONFIG_PPC_EARLY_DEBUG=y
 CONFIG_KEYS_DEBUG_PROC_KEYS=y
 CONFIG_CRYPTO_NULL=m
diff --git a/arch/powerpc/configs/corenet64_smp_defconfig b/arch/powerpc/configs/corenet64_smp_defconfig
index 7ed8d4c..82b13bf 100644
--- a/arch/powerpc/configs/corenet64_smp_defconfig
+++ b/arch/powerpc/configs/corenet64_smp_defconfig
@@ -95,7 +95,7 @@
 CONFIG_DETECT_HUNG_TASK=y
 CONFIG_DEBUG_INFO=y
 CONFIG_SYSCTL_SYSCALL_CHECK=y
-CONFIG_VIRQ_DEBUG=y
+CONFIG_IRQ_DOMAIN_DEBUG=y
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_SHA256=y
 CONFIG_CRYPTO_SHA512=y
diff --git a/arch/powerpc/configs/mpc85xx_defconfig b/arch/powerpc/configs/mpc85xx_defconfig
index 5fb0c8a..cc87a84 100644
--- a/arch/powerpc/configs/mpc85xx_defconfig
+++ b/arch/powerpc/configs/mpc85xx_defconfig
@@ -214,7 +214,7 @@
 CONFIG_DETECT_HUNG_TASK=y
 CONFIG_DEBUG_INFO=y
 CONFIG_SYSCTL_SYSCALL_CHECK=y
-CONFIG_VIRQ_DEBUG=y
+CONFIG_IRQ_DOMAIN_DEBUG=y
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_SHA256=y
 CONFIG_CRYPTO_SHA512=y
diff --git a/arch/powerpc/configs/mpc85xx_smp_defconfig b/arch/powerpc/configs/mpc85xx_smp_defconfig
index fb51bc9..48d6682 100644
--- a/arch/powerpc/configs/mpc85xx_smp_defconfig
+++ b/arch/powerpc/configs/mpc85xx_smp_defconfig
@@ -216,7 +216,7 @@
 CONFIG_DETECT_HUNG_TASK=y
 CONFIG_DEBUG_INFO=y
 CONFIG_SYSCTL_SYSCALL_CHECK=y
-CONFIG_VIRQ_DEBUG=y
+CONFIG_IRQ_DOMAIN_DEBUG=y
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_SHA256=y
 CONFIG_CRYPTO_SHA512=y
diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig
index 1acf650..c1442a3 100644
--- a/arch/powerpc/configs/ppc64_defconfig
+++ b/arch/powerpc/configs/ppc64_defconfig
@@ -457,7 +457,7 @@
 CONFIG_FTR_FIXUP_SELFTEST=y
 CONFIG_MSI_BITMAP_SELFTEST=y
 CONFIG_XMON=y
-CONFIG_VIRQ_DEBUG=y
+CONFIG_IRQ_DOMAIN_DEBUG=y
 CONFIG_BOOTX_TEXT=y
 CONFIG_CRYPTO_NULL=m
 CONFIG_CRYPTO_TEST=m
diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig
index 30e7d0d..6608232 100644
--- a/arch/powerpc/configs/pseries_defconfig
+++ b/arch/powerpc/configs/pseries_defconfig
@@ -340,7 +340,7 @@
 CONFIG_MSI_BITMAP_SELFTEST=y
 CONFIG_XMON=y
 CONFIG_XMON_DEFAULT=y
-CONFIG_VIRQ_DEBUG=y
+CONFIG_IRQ_DOMAIN_DEBUG=y
 CONFIG_CRYPTO_NULL=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CCM=m
diff --git a/arch/powerpc/include/asm/posix_types.h b/arch/powerpc/include/asm/posix_types.h
index c4e396b..f139325 100644
--- a/arch/powerpc/include/asm/posix_types.h
+++ b/arch/powerpc/include/asm/posix_types.h
@@ -7,122 +7,22 @@
  * assume GCC is being used.
  */
 
-typedef unsigned long	__kernel_ino_t;
-typedef unsigned int	__kernel_mode_t;
-typedef long		__kernel_off_t;
-typedef int		__kernel_pid_t;
-typedef unsigned int	__kernel_uid_t;
-typedef unsigned int	__kernel_gid_t;
-typedef long		__kernel_ptrdiff_t;
-typedef long		__kernel_time_t;
-typedef long		__kernel_clock_t;
-typedef int		__kernel_timer_t;
-typedef int		__kernel_clockid_t;
-typedef long		__kernel_suseconds_t;
-typedef int		__kernel_daddr_t;
-typedef char *		__kernel_caddr_t;
-typedef unsigned short	__kernel_uid16_t;
-typedef unsigned short	__kernel_gid16_t;
-typedef unsigned int	__kernel_uid32_t;
-typedef unsigned int	__kernel_gid32_t;
-typedef unsigned int	__kernel_old_uid_t;
-typedef unsigned int	__kernel_old_gid_t;
-
 #ifdef __powerpc64__
-typedef unsigned long  	__kernel_nlink_t;
-typedef int             __kernel_ipc_pid_t;
-typedef unsigned long	__kernel_size_t;
-typedef long		__kernel_ssize_t;
 typedef unsigned long	__kernel_old_dev_t;
+#define __kernel_old_dev_t __kernel_old_dev_t
 #else
-typedef unsigned short	__kernel_nlink_t;
-typedef short		__kernel_ipc_pid_t;
 typedef unsigned int	__kernel_size_t;
 typedef int		__kernel_ssize_t;
-typedef unsigned int	__kernel_old_dev_t;
+typedef long		__kernel_ptrdiff_t;
+#define __kernel_size_t __kernel_size_t
+
+typedef unsigned short	__kernel_nlink_t;
+#define __kernel_nlink_t __kernel_nlink_t
+
+typedef short		__kernel_ipc_pid_t;
+#define __kernel_ipc_pid_t __kernel_ipc_pid_t
 #endif
 
-#ifdef __powerpc64__
-typedef long long	__kernel_loff_t;
-#else
-#ifdef __GNUC__
-typedef long long	__kernel_loff_t;
-#endif
-#endif
+#include <asm-generic/posix_types.h>
 
-typedef struct {
-	int	val[2];
-} __kernel_fsid_t;
-
-#ifndef __GNUC__
-
-#define	__FD_SET(d, set)	((set)->fds_bits[__FDELT(d)] |= __FDMASK(d))
-#define	__FD_CLR(d, set)	((set)->fds_bits[__FDELT(d)] &= ~__FDMASK(d))
-#define	__FD_ISSET(d, set)	(((set)->fds_bits[__FDELT(d)] & __FDMASK(d)) != 0)
-#define	__FD_ZERO(set)	\
-  ((void) memset ((void *) (set), 0, sizeof (__kernel_fd_set)))
-
-#else /* __GNUC__ */
-
-#if defined(__KERNEL__)
-/* With GNU C, use inline functions instead so args are evaluated only once: */
-
-#undef __FD_SET
-static __inline__ void __FD_SET(unsigned long fd, __kernel_fd_set *fdsetp)
-{
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	fdsetp->fds_bits[_tmp] |= (1UL<<_rem);
-}
-
-#undef __FD_CLR
-static __inline__ void __FD_CLR(unsigned long fd, __kernel_fd_set *fdsetp)
-{
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	fdsetp->fds_bits[_tmp] &= ~(1UL<<_rem);
-}
-
-#undef __FD_ISSET
-static __inline__ int __FD_ISSET(unsigned long fd, __kernel_fd_set *p)
-{ 
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	return (p->fds_bits[_tmp] & (1UL<<_rem)) != 0;
-}
-
-/*
- * This will unroll the loop for the normal constant case (8 ints,
- * for a 256-bit fd_set)
- */
-#undef __FD_ZERO
-static __inline__ void __FD_ZERO(__kernel_fd_set *p)
-{
-	unsigned long *tmp = (unsigned long *)p->fds_bits;
-	int i;
-
-	if (__builtin_constant_p(__FDSET_LONGS)) {
-		switch (__FDSET_LONGS) {
-		      case 16:
-			tmp[12] = 0; tmp[13] = 0; tmp[14] = 0; tmp[15] = 0;
-			tmp[ 8] = 0; tmp[ 9] = 0; tmp[10] = 0; tmp[11] = 0;
-
-		      case 8:
-			tmp[ 4] = 0; tmp[ 5] = 0; tmp[ 6] = 0; tmp[ 7] = 0;
-
-		      case 4:
-			tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
-			return;
-		}
-	}
-	i = __FDSET_LONGS;
-	while (i) {
-		i--;
-		*tmp = 0;
-		tmp++;
-	}
-}
-
-#endif /* defined(__KERNEL__) */
-#endif /* __GNUC__ */
 #endif /* _ASM_POWERPC_POSIX_TYPES_H */
diff --git a/arch/powerpc/platforms/cell/spufs/coredump.c b/arch/powerpc/platforms/cell/spufs/coredump.c
index 03c5fce..c2c5b07 100644
--- a/arch/powerpc/platforms/cell/spufs/coredump.c
+++ b/arch/powerpc/platforms/cell/spufs/coredump.c
@@ -122,7 +122,7 @@
 	struct spu_context *ctx = NULL;
 
 	for (; *fd < fdt->max_fds; (*fd)++) {
-		if (!FD_ISSET(*fd, fdt->open_fds))
+		if (!fd_is_open(*fd, fdt))
 			continue;
 
 		file = fcheck(*fd);
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 465d5be..2b7c0fb 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -219,6 +219,7 @@
 	prompt "Kernel support for 31 bit emulation"
 	depends on 64BIT
 	select COMPAT_BINFMT_ELF
+	select ARCH_WANT_OLD_COMPAT_IPC
 	help
 	  Select this option if you want to enable your system kernel to
 	  handle system-calls from ELF binaries for 31 bit ESA.  This option
diff --git a/arch/s390/include/asm/posix_types.h b/arch/s390/include/asm/posix_types.h
index 8cc113f..edf8527 100644
--- a/arch/s390/include/asm/posix_types.h
+++ b/arch/s390/include/asm/posix_types.h
@@ -3,7 +3,6 @@
  *
  *  S390 version
  *
- *  Derived from "include/asm-i386/posix_types.h"
  */
 
 #ifndef __ARCH_S390_POSIX_TYPES_H
@@ -15,22 +14,11 @@
  * assume GCC is being used.
  */
 
-typedef long            __kernel_off_t;
-typedef int             __kernel_pid_t;
 typedef unsigned long   __kernel_size_t;
-typedef long            __kernel_time_t;
-typedef long            __kernel_suseconds_t;
-typedef long            __kernel_clock_t;
-typedef int		__kernel_timer_t;
-typedef int		__kernel_clockid_t;
-typedef int             __kernel_daddr_t;
-typedef char *          __kernel_caddr_t;
-typedef unsigned short	__kernel_uid16_t;
-typedef unsigned short	__kernel_gid16_t;
+#define __kernel_size_t __kernel_size_t
 
-#ifdef __GNUC__
-typedef long long       __kernel_loff_t;
-#endif
+typedef unsigned short	__kernel_old_dev_t;
+#define __kernel_old_dev_t __kernel_old_dev_t
 
 #ifndef __s390x__
 
@@ -42,11 +30,6 @@
 typedef unsigned short  __kernel_gid_t;
 typedef int             __kernel_ssize_t;
 typedef int             __kernel_ptrdiff_t;
-typedef unsigned int	__kernel_uid32_t;
-typedef unsigned int	__kernel_gid32_t;
-typedef unsigned short	__kernel_old_uid_t;
-typedef unsigned short	__kernel_old_gid_t;
-typedef unsigned short	__kernel_old_dev_t;
 
 #else /* __s390x__ */
 
@@ -59,49 +42,16 @@
 typedef long            __kernel_ssize_t;
 typedef long            __kernel_ptrdiff_t;
 typedef unsigned long   __kernel_sigset_t;      /* at least 32 bits */
-typedef __kernel_uid_t __kernel_old_uid_t;
-typedef __kernel_gid_t __kernel_old_gid_t;
-typedef __kernel_uid_t __kernel_uid32_t;
-typedef __kernel_gid_t __kernel_gid32_t;
-typedef unsigned short __kernel_old_dev_t;
 
 #endif /* __s390x__ */
 
-typedef struct {
-        int     val[2];
-} __kernel_fsid_t;
+#define __kernel_ino_t  __kernel_ino_t
+#define __kernel_mode_t __kernel_mode_t
+#define __kernel_nlink_t __kernel_nlink_t
+#define __kernel_ipc_pid_t __kernel_ipc_pid_t
+#define __kernel_uid_t __kernel_uid_t
+#define __kernel_gid_t __kernel_gid_t
 
-
-#ifdef __KERNEL__
-
-#undef __FD_SET
-static inline void __FD_SET(unsigned long fd, __kernel_fd_set *fdsetp)
-{
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	fdsetp->fds_bits[_tmp] |= (1UL<<_rem);
-}
-
-#undef __FD_CLR
-static inline void __FD_CLR(unsigned long fd, __kernel_fd_set *fdsetp)
-{
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	fdsetp->fds_bits[_tmp] &= ~(1UL<<_rem);
-}
-
-#undef __FD_ISSET
-static inline int __FD_ISSET(unsigned long fd, const __kernel_fd_set *fdsetp)
-{
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	return (fdsetp->fds_bits[_tmp] & (1UL<<_rem)) != 0;
-}
-
-#undef  __FD_ZERO
-#define __FD_ZERO(fdsetp) \
-	((void) memset ((void *) (fdsetp), 0, sizeof (__kernel_fd_set)))
-
-#endif     /* __KERNEL__ */
+#include <asm-generic/posix_types.h>
 
 #endif
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index 713fb58..b190eb1 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -22,7 +22,7 @@
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_GENERIC_HARDIRQS
-	select HAVE_SPARSE_IRQ
+	select MAY_HAVE_SPARSE_IRQ
 	select IRQ_FORCED_THREADING
 	select RTC_LIB
 	select GENERIC_ATOMIC64
diff --git a/arch/sh/include/asm/irq.h b/arch/sh/include/asm/irq.h
index 45d08b6..2a62017 100644
--- a/arch/sh/include/asm/irq.h
+++ b/arch/sh/include/asm/irq.h
@@ -21,17 +21,6 @@
 #define NO_IRQ_IGNORE		((unsigned int)-1)
 
 /*
- * Convert back and forth between INTEVT and IRQ values.
- */
-#ifdef CONFIG_CPU_HAS_INTEVT
-#define evt2irq(evt)		(((evt) >> 5) - 16)
-#define irq2evt(irq)		(((irq) + 16) << 5)
-#else
-#define evt2irq(evt)		(evt)
-#define irq2evt(irq)		(irq)
-#endif
-
-/*
  * Simple Mask Register Support
  */
 extern void make_maskreg_irq(unsigned int irq);
diff --git a/arch/sh/include/asm/posix_types_32.h b/arch/sh/include/asm/posix_types_32.h
index 6a9ceaa..abda584 100644
--- a/arch/sh/include/asm/posix_types_32.h
+++ b/arch/sh/include/asm/posix_types_32.h
@@ -12,11 +12,6 @@
 typedef unsigned short	__kernel_gid_t;
 #define __kernel_gid_t __kernel_gid_t
 
-typedef unsigned int	__kernel_uid32_t;
-#define __kernel_uid32_t __kernel_uid32_t
-typedef unsigned int	__kernel_gid32_t;
-#define __kernel_gid32_t __kernel_gid32_t
-
 typedef unsigned short	__kernel_old_uid_t;
 #define __kernel_old_uid_t __kernel_old_uid_t
 typedef unsigned short	__kernel_old_gid_t;
diff --git a/arch/sh/include/asm/posix_types_64.h b/arch/sh/include/asm/posix_types_64.h
index 8cd1148..fcda07b 100644
--- a/arch/sh/include/asm/posix_types_64.h
+++ b/arch/sh/include/asm/posix_types_64.h
@@ -17,10 +17,6 @@
 #define __kernel_ssize_t __kernel_ssize_t
 typedef int		__kernel_ptrdiff_t;
 #define __kernel_ptrdiff_t __kernel_ptrdiff_t
-typedef unsigned int	__kernel_uid32_t;
-#define __kernel_uid32_t __kernel_uid32_t
-typedef unsigned int	__kernel_gid32_t;
-#define __kernel_gid32_t __kernel_gid32_t
 
 typedef unsigned short	__kernel_old_uid_t;
 #define __kernel_old_uid_t __kernel_old_uid_t
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 1666de8..6c0683d 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -577,6 +577,7 @@
 	depends on SPARC64
 	default y
 	select COMPAT_BINFMT_ELF
+	select ARCH_WANT_OLD_COMPAT_IPC
 
 config SYSVIPC_COMPAT
 	bool
diff --git a/arch/sparc/include/asm/posix_types.h b/arch/sparc/include/asm/posix_types.h
index dbfc1a3..3070f25 100644
--- a/arch/sparc/include/asm/posix_types.h
+++ b/arch/sparc/include/asm/posix_types.h
@@ -9,35 +9,16 @@
 
 #if defined(__sparc__) && defined(__arch64__)
 /* sparc 64 bit */
-typedef unsigned long          __kernel_size_t;
-typedef long                   __kernel_ssize_t;
-typedef long                   __kernel_ptrdiff_t;
-typedef long                   __kernel_time_t;
-typedef long                   __kernel_clock_t;
-typedef int                    __kernel_pid_t;
-typedef int                    __kernel_ipc_pid_t;
-typedef unsigned int           __kernel_uid_t;
-typedef unsigned int           __kernel_gid_t;
-typedef unsigned long          __kernel_ino_t;
-typedef unsigned int           __kernel_mode_t;
 typedef unsigned int           __kernel_nlink_t;
-typedef int                    __kernel_daddr_t;
-typedef long                   __kernel_off_t;
-typedef char *                 __kernel_caddr_t;
-typedef unsigned short	       __kernel_uid16_t;
-typedef unsigned short	       __kernel_gid16_t;
-typedef int                    __kernel_clockid_t;
-typedef int                    __kernel_timer_t;
+#define __kernel_nlink_t __kernel_nlink_t
 
 typedef unsigned short 	       __kernel_old_uid_t;
 typedef unsigned short         __kernel_old_gid_t;
-typedef __kernel_uid_t	       __kernel_uid32_t;
-typedef __kernel_gid_t	       __kernel_gid32_t;
-
-typedef unsigned int	       __kernel_old_dev_t;
+#define __kernel_old_uid_t __kernel_old_uid_t
 
 /* Note this piece of asymmetry from the v9 ABI.  */
 typedef int		       __kernel_suseconds_t;
+#define __kernel_suseconds_t __kernel_suseconds_t
 
 #else
 /* sparc 32 bit */
@@ -45,109 +26,29 @@
 typedef unsigned int           __kernel_size_t;
 typedef int                    __kernel_ssize_t;
 typedef long int               __kernel_ptrdiff_t;
-typedef long                   __kernel_time_t;
-typedef long		       __kernel_suseconds_t;
-typedef long                   __kernel_clock_t;
-typedef int                    __kernel_pid_t;
+#define __kernel_size_t __kernel_size_t
+
 typedef unsigned short         __kernel_ipc_pid_t;
+#define __kernel_ipc_pid_t __kernel_ipc_pid_t
+
 typedef unsigned short         __kernel_uid_t;
 typedef unsigned short         __kernel_gid_t;
-typedef unsigned long          __kernel_ino_t;
+#define __kernel_uid_t __kernel_uid_t
+
 typedef unsigned short         __kernel_mode_t;
+#define __kernel_mode_t __kernel_mode_t
+
 typedef short                  __kernel_nlink_t;
+#define __kernel_nlink_t __kernel_nlink_t
+
 typedef long                   __kernel_daddr_t;
-typedef long                   __kernel_off_t;
-typedef char *                 __kernel_caddr_t;
-typedef unsigned short	       __kernel_uid16_t;
-typedef unsigned short	       __kernel_gid16_t;
-typedef unsigned int	       __kernel_uid32_t;
-typedef unsigned int	       __kernel_gid32_t;
-typedef unsigned short	       __kernel_old_uid_t;
-typedef unsigned short	       __kernel_old_gid_t;
+#define __kernel_daddr_t __kernel_daddr_t
+
 typedef unsigned short	       __kernel_old_dev_t;
-typedef int                    __kernel_clockid_t;
-typedef int                    __kernel_timer_t;
+#define __kernel_old_dev_t __kernel_old_dev_t
 
 #endif /* defined(__sparc__) && defined(__arch64__) */
 
-#ifdef __GNUC__
-typedef long long              __kernel_loff_t;
-#endif
+#include <asm-generic/posix_types.h>
 
-typedef struct {
-	int	val[2];
-} __kernel_fsid_t;
-
-#ifdef __KERNEL__
-
-#undef __FD_SET
-static inline void __FD_SET(unsigned long fd, __kernel_fd_set *fdsetp)
-{
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	fdsetp->fds_bits[_tmp] |= (1UL<<_rem);
-}
-
-#undef __FD_CLR
-static inline void __FD_CLR(unsigned long fd, __kernel_fd_set *fdsetp)
-{
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	fdsetp->fds_bits[_tmp] &= ~(1UL<<_rem);
-}
-
-#undef __FD_ISSET
-static inline int __FD_ISSET(unsigned long fd, __const__ __kernel_fd_set *p)
-{
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	return (p->fds_bits[_tmp] & (1UL<<_rem)) != 0;
-}
-
-/*
- * This will unroll the loop for the normal constant cases (8 or 32 longs,
- * for 256 and 1024-bit fd_sets respectively)
- */
-#undef __FD_ZERO
-static inline void __FD_ZERO(__kernel_fd_set *p)
-{
-	unsigned long *tmp = p->fds_bits;
-	int i;
-
-	if (__builtin_constant_p(__FDSET_LONGS)) {
-		switch (__FDSET_LONGS) {
-			case 32:
-			  tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
-			  tmp[ 4] = 0; tmp[ 5] = 0; tmp[ 6] = 0; tmp[ 7] = 0;
-			  tmp[ 8] = 0; tmp[ 9] = 0; tmp[10] = 0; tmp[11] = 0;
-			  tmp[12] = 0; tmp[13] = 0; tmp[14] = 0; tmp[15] = 0;
-			  tmp[16] = 0; tmp[17] = 0; tmp[18] = 0; tmp[19] = 0;
-			  tmp[20] = 0; tmp[21] = 0; tmp[22] = 0; tmp[23] = 0;
-			  tmp[24] = 0; tmp[25] = 0; tmp[26] = 0; tmp[27] = 0;
-			  tmp[28] = 0; tmp[29] = 0; tmp[30] = 0; tmp[31] = 0;
-			  return;
-			case 16:
-			  tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
-			  tmp[ 4] = 0; tmp[ 5] = 0; tmp[ 6] = 0; tmp[ 7] = 0;
-			  tmp[ 8] = 0; tmp[ 9] = 0; tmp[10] = 0; tmp[11] = 0;
-			  tmp[12] = 0; tmp[13] = 0; tmp[14] = 0; tmp[15] = 0;
-			  return;
-			case 8:
-			  tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
-			  tmp[ 4] = 0; tmp[ 5] = 0; tmp[ 6] = 0; tmp[ 7] = 0;
-			  return;
-			case 4:
-			  tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
-			  return;
-		}
-	}
-	i = __FDSET_LONGS;
-	while (i) {
-		i--;
-		*tmp = 0;
-		tmp++;
-	}
-}
-
-#endif /* __KERNEL__ */
 #endif /* __SPARC_POSIX_TYPES_H */
diff --git a/arch/tile/include/asm/compat.h b/arch/tile/include/asm/compat.h
index bf95f55..4b4b289 100644
--- a/arch/tile/include/asm/compat.h
+++ b/arch/tile/include/asm/compat.h
@@ -242,17 +242,6 @@
 long compat_sys_sched_rr_get_interval(compat_pid_t pid,
 				      struct compat_timespec __user *interval);
 
-/* Versions of compat functions that differ from generic Linux. */
-struct compat_msgbuf;
-long tile_compat_sys_msgsnd(int msqid,
-			    struct compat_msgbuf __user *msgp,
-			    size_t msgsz, int msgflg);
-long tile_compat_sys_msgrcv(int msqid,
-			    struct compat_msgbuf __user *msgp,
-			    size_t msgsz, long msgtyp, int msgflg);
-long tile_compat_sys_ptrace(compat_long_t request, compat_long_t pid,
-			    compat_long_t addr, compat_long_t data);
-
 /* Tilera Linux syscalls that don't have "compat" versions. */
 #define compat_sys_flush_cache sys_flush_cache
 
diff --git a/arch/tile/kernel/compat.c b/arch/tile/kernel/compat.c
index bf5e9d7..d67459b 100644
--- a/arch/tile/kernel/compat.c
+++ b/arch/tile/kernel/compat.c
@@ -16,7 +16,6 @@
 #define __SYSCALL_COMPAT
 
 #include <linux/compat.h>
-#include <linux/msg.h>
 #include <linux/syscalls.h>
 #include <linux/kdev_t.h>
 #include <linux/fs.h>
@@ -95,52 +94,10 @@
 	return ret;
 }
 
-/*
- * The usual compat_sys_msgsnd() and _msgrcv() seem to be assuming
- * some different calling convention than our normal 32-bit tile code.
- */
-
-/* Already defined in ipc/compat.c, but we need it here. */
-struct compat_msgbuf {
-	compat_long_t mtype;
-	char mtext[1];
-};
-
-long tile_compat_sys_msgsnd(int msqid,
-			    struct compat_msgbuf __user *msgp,
-			    size_t msgsz, int msgflg)
-{
-	compat_long_t mtype;
-
-	if (get_user(mtype, &msgp->mtype))
-		return -EFAULT;
-	return do_msgsnd(msqid, mtype, msgp->mtext, msgsz, msgflg);
-}
-
-long tile_compat_sys_msgrcv(int msqid,
-			    struct compat_msgbuf __user *msgp,
-			    size_t msgsz, long msgtyp, int msgflg)
-{
-	long err, mtype;
-
-	err =  do_msgrcv(msqid, &mtype, msgp->mtext, msgsz, msgtyp, msgflg);
-	if (err < 0)
-		goto out;
-
-	if (put_user(mtype, &msgp->mtype))
-		err = -EFAULT;
- out:
-	return err;
-}
-
 /* Provide the compat syscall number to call mapping. */
 #undef __SYSCALL
 #define __SYSCALL(nr, call) [nr] = (call),
 
-/* The generic versions of these don't work for Tile. */
-#define compat_sys_msgrcv tile_compat_sys_msgrcv
-#define compat_sys_msgsnd tile_compat_sys_msgsnd
-
 /* See comments in sys.c */
 #define compat_sys_fadvise64_64 sys32_fadvise64_64
 #define compat_sys_readahead sys32_readahead
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 3ad653d..1d14cc6 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -69,7 +69,6 @@
 	select HAVE_ARCH_JUMP_LABEL
 	select HAVE_TEXT_POKE_SMP
 	select HAVE_GENERIC_HARDIRQS
-	select HAVE_SPARSE_IRQ
 	select SPARSE_IRQ
 	select GENERIC_FIND_FIRST_BIT
 	select GENERIC_IRQ_PROBE
@@ -2164,9 +2163,9 @@
 	depends on X86_64
 	select COMPAT_BINFMT_ELF
 	---help---
-	  Include code to run 32-bit programs under a 64-bit kernel. You should
-	  likely turn this on, unless you're 100% sure that you don't have any
-	  32-bit programs left.
+	  Include code to run legacy 32-bit programs under a
+	  64-bit kernel. You should likely turn this on, unless you're
+	  100% sure that you don't have any 32-bit programs left.
 
 config IA32_AOUT
 	tristate "IA32 a.out support"
@@ -2174,9 +2173,23 @@
 	---help---
 	  Support old a.out binaries in the 32bit emulation.
 
+config X86_X32
+	bool "x32 ABI for 64-bit mode (EXPERIMENTAL)"
+	depends on X86_64 && IA32_EMULATION && EXPERIMENTAL
+	---help---
+	  Include code to run binaries for the x32 native 32-bit ABI
+	  for 64-bit processors.  An x32 process gets access to the
+	  full 64-bit register file and wide data path while leaving
+	  pointers at 32 bits for smaller memory footprint.
+
+	  You will need a recent binutils (2.22 or later) with
+	  elf32_x86_64 support enabled to compile a kernel with this
+	  option set.
+
 config COMPAT
 	def_bool y
-	depends on IA32_EMULATION
+	depends on IA32_EMULATION || X86_X32
+	select ARCH_WANT_OLD_COMPAT_IPC
 
 config COMPAT_FOR_U64_ALIGNMENT
 	def_bool COMPAT
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 209ba12..968dbe2 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -82,6 +82,22 @@
         endif
 endif
 
+ifdef CONFIG_X86_X32
+	x32_ld_ok := $(call try-run,\
+			/bin/echo -e '1: .quad 1b' | \
+			$(CC) $(KBUILD_AFLAGS) -c -xassembler -o "$$TMP" - && \
+			$(OBJCOPY) -O elf32-x86-64 "$$TMP" "$$TMPO" && \
+			$(LD) -m elf32_x86_64 "$$TMPO" -o "$$TMP",y,n)
+        ifeq ($(x32_ld_ok),y)
+                CONFIG_X86_X32_ABI := y
+                KBUILD_AFLAGS += -DCONFIG_X86_X32_ABI
+                KBUILD_CFLAGS += -DCONFIG_X86_X32_ABI
+        else
+                $(warning CONFIG_X86_X32 enabled but no binutils support)
+        endif
+endif
+export CONFIG_X86_X32_ABI
+
 # Don't unroll struct assignments with kmemcheck enabled
 ifeq ($(CONFIG_KMEMCHECK),y)
 	KBUILD_CFLAGS += $(call cc-option,-fno-builtin-memcpy)
diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig
index 2bf18059f..119db67 100644
--- a/arch/x86/configs/i386_defconfig
+++ b/arch/x86/configs/i386_defconfig
@@ -15,23 +15,28 @@
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_RESOURCE_COUNTERS=y
 CONFIG_CGROUP_SCHED=y
-CONFIG_UTS_NS=y
-CONFIG_IPC_NS=y
-CONFIG_USER_NS=y
-CONFIG_PID_NS=y
-CONFIG_NET_NS=y
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_KALLSYMS_EXTRA_PASS=y
 # CONFIG_COMPAT_BRK is not set
 CONFIG_PROFILING=y
 CONFIG_KPROBES=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_MODULE_FORCE_UNLOAD=y
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_OSF_PARTITION=y
+CONFIG_AMIGA_PARTITION=y
+CONFIG_MAC_PARTITION=y
+CONFIG_BSD_DISKLABEL=y
+CONFIG_MINIX_SUBPARTITION=y
+CONFIG_SOLARIS_X86_PARTITION=y
+CONFIG_UNIXWARE_DISKLABEL=y
+CONFIG_SGI_PARTITION=y
+CONFIG_SUN_PARTITION=y
+CONFIG_KARMA_PARTITION=y
+CONFIG_EFI_PARTITION=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_SMP=y
-CONFIG_SPARSE_IRQ=y
 CONFIG_X86_GENERIC=y
 CONFIG_HPET_TIMER=y
 CONFIG_SCHED_SMT=y
@@ -51,14 +56,12 @@
 CONFIG_KEXEC=y
 CONFIG_CRASH_DUMP=y
 # CONFIG_COMPAT_VDSO is not set
-CONFIG_PM=y
+CONFIG_HIBERNATION=y
 CONFIG_PM_DEBUG=y
 CONFIG_PM_TRACE_RTC=y
-CONFIG_HIBERNATION=y
 CONFIG_ACPI_PROCFS=y
 CONFIG_ACPI_DOCK=y
 CONFIG_CPU_FREQ=y
-CONFIG_CPU_FREQ_DEBUG=y
 # CONFIG_CPU_FREQ_STAT is not set
 CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE=y
 CONFIG_CPU_FREQ_GOV_PERFORMANCE=y
@@ -69,7 +72,6 @@
 CONFIG_PCCARD=y
 CONFIG_YENTA=y
 CONFIG_HOTPLUG_PCI=y
-CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS=y
 CONFIG_BINFMT_MISC=y
 CONFIG_NET=y
 CONFIG_PACKET=y
@@ -120,7 +122,6 @@
 CONFIG_IP_NF_IPTABLES=y
 CONFIG_IP_NF_FILTER=y
 CONFIG_IP_NF_TARGET_REJECT=y
-CONFIG_IP_NF_TARGET_LOG=y
 CONFIG_IP_NF_TARGET_ULOG=y
 CONFIG_NF_NAT=y
 CONFIG_IP_NF_TARGET_MASQUERADE=y
@@ -128,7 +129,6 @@
 CONFIG_NF_CONNTRACK_IPV6=y
 CONFIG_IP6_NF_IPTABLES=y
 CONFIG_IP6_NF_MATCH_IPV6HEADER=y
-CONFIG_IP6_NF_TARGET_LOG=y
 CONFIG_IP6_NF_FILTER=y
 CONFIG_IP6_NF_TARGET_REJECT=y
 CONFIG_IP6_NF_MANGLE=y
@@ -169,25 +169,20 @@
 CONFIG_MACINTOSH_DRIVERS=y
 CONFIG_MAC_EMUMOUSEBTN=y
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
-CONFIG_NET_VENDOR_3COM=y
+CONFIG_NETCONSOLE=y
+CONFIG_BNX2=y
+CONFIG_TIGON3=y
 CONFIG_NET_TULIP=y
-CONFIG_NET_PCI=y
-CONFIG_FORCEDETH=y
 CONFIG_E100=y
-CONFIG_NE2K_PCI=y
-CONFIG_8139TOO=y
-# CONFIG_8139TOO_PIO is not set
 CONFIG_E1000=y
 CONFIG_E1000E=y
-CONFIG_R8169=y
 CONFIG_SKY2=y
-CONFIG_TIGON3=y
-CONFIG_BNX2=y
-CONFIG_TR=y
-CONFIG_NET_PCMCIA=y
+CONFIG_NE2K_PCI=y
+CONFIG_FORCEDETH=y
+CONFIG_8139TOO=y
+# CONFIG_8139TOO_PIO is not set
+CONFIG_R8169=y
 CONFIG_FDDI=y
-CONFIG_NETCONSOLE=y
 CONFIG_INPUT_POLLDEV=y
 # CONFIG_INPUT_MOUSEDEV_PSAUX is not set
 CONFIG_INPUT_EVDEV=y
@@ -196,6 +191,7 @@
 CONFIG_INPUT_TOUCHSCREEN=y
 CONFIG_INPUT_MISC=y
 CONFIG_VT_HW_CONSOLE_BINDING=y
+# CONFIG_LEGACY_PTYS is not set
 CONFIG_SERIAL_NONSTANDARD=y
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
@@ -205,7 +201,6 @@
 CONFIG_SERIAL_8250_SHARE_IRQ=y
 CONFIG_SERIAL_8250_DETECT_IRQ=y
 CONFIG_SERIAL_8250_RSA=y
-# CONFIG_LEGACY_PTYS is not set
 CONFIG_HW_RANDOM=y
 CONFIG_NVRAM=y
 CONFIG_HPET=y
@@ -220,7 +215,6 @@
 CONFIG_FB_MODE_HELPERS=y
 CONFIG_FB_TILEBLITTING=y
 CONFIG_FB_EFI=y
-CONFIG_BACKLIGHT_LCD_SUPPORT=y
 # CONFIG_LCD_CLASS_DEVICE is not set
 CONFIG_VGACON_SOFT_SCROLLBACK=y
 CONFIG_LOGO=y
@@ -283,7 +277,6 @@
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
 CONFIG_TMPFS_POSIX_ACL=y
 CONFIG_HUGETLBFS=y
 CONFIG_NFS_FS=y
@@ -291,18 +284,6 @@
 CONFIG_NFS_V3_ACL=y
 CONFIG_NFS_V4=y
 CONFIG_ROOT_NFS=y
-CONFIG_PARTITION_ADVANCED=y
-CONFIG_OSF_PARTITION=y
-CONFIG_AMIGA_PARTITION=y
-CONFIG_MAC_PARTITION=y
-CONFIG_BSD_DISKLABEL=y
-CONFIG_MINIX_SUBPARTITION=y
-CONFIG_SOLARIS_X86_PARTITION=y
-CONFIG_UNIXWARE_DISKLABEL=y
-CONFIG_SGI_PARTITION=y
-CONFIG_SUN_PARTITION=y
-CONFIG_KARMA_PARTITION=y
-CONFIG_EFI_PARTITION=y
 CONFIG_NLS_DEFAULT="utf8"
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ASCII=y
@@ -317,13 +298,12 @@
 # CONFIG_SCHED_DEBUG is not set
 CONFIG_SCHEDSTATS=y
 CONFIG_TIMER_STATS=y
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
+CONFIG_DEBUG_STACK_USAGE=y
 CONFIG_SYSCTL_SYSCALL_CHECK=y
 CONFIG_BLK_DEV_IO_TRACE=y
 CONFIG_PROVIDE_OHCI1394_DMA_INIT=y
 CONFIG_EARLY_PRINTK_DBGP=y
 CONFIG_DEBUG_STACKOVERFLOW=y
-CONFIG_DEBUG_STACK_USAGE=y
 # CONFIG_DEBUG_RODATA_TEST is not set
 CONFIG_DEBUG_NX_TEST=m
 CONFIG_DEBUG_BOOT_PARAMS=y
diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig
index 058a35b..76eb290 100644
--- a/arch/x86/configs/x86_64_defconfig
+++ b/arch/x86/configs/x86_64_defconfig
@@ -1,4 +1,3 @@
-CONFIG_64BIT=y
 CONFIG_EXPERIMENTAL=y
 # CONFIG_LOCALVERSION_AUTO is not set
 CONFIG_SYSVIPC=y
@@ -16,26 +15,29 @@
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_RESOURCE_COUNTERS=y
 CONFIG_CGROUP_SCHED=y
-CONFIG_UTS_NS=y
-CONFIG_IPC_NS=y
-CONFIG_USER_NS=y
-CONFIG_PID_NS=y
-CONFIG_NET_NS=y
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_KALLSYMS_EXTRA_PASS=y
 # CONFIG_COMPAT_BRK is not set
 CONFIG_PROFILING=y
 CONFIG_KPROBES=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_MODULE_FORCE_UNLOAD=y
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_OSF_PARTITION=y
+CONFIG_AMIGA_PARTITION=y
+CONFIG_MAC_PARTITION=y
+CONFIG_BSD_DISKLABEL=y
+CONFIG_MINIX_SUBPARTITION=y
+CONFIG_SOLARIS_X86_PARTITION=y
+CONFIG_UNIXWARE_DISKLABEL=y
+CONFIG_SGI_PARTITION=y
+CONFIG_SUN_PARTITION=y
+CONFIG_KARMA_PARTITION=y
+CONFIG_EFI_PARTITION=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_SMP=y
-CONFIG_SPARSE_IRQ=y
 CONFIG_CALGARY_IOMMU=y
-CONFIG_AMD_IOMMU=y
-CONFIG_AMD_IOMMU_STATS=y
 CONFIG_NR_CPUS=64
 CONFIG_SCHED_SMT=y
 CONFIG_PREEMPT_VOLUNTARY=y
@@ -53,27 +55,22 @@
 CONFIG_KEXEC=y
 CONFIG_CRASH_DUMP=y
 # CONFIG_COMPAT_VDSO is not set
-CONFIG_PM=y
+CONFIG_HIBERNATION=y
 CONFIG_PM_DEBUG=y
 CONFIG_PM_TRACE_RTC=y
-CONFIG_HIBERNATION=y
 CONFIG_ACPI_PROCFS=y
 CONFIG_ACPI_DOCK=y
 CONFIG_CPU_FREQ=y
-CONFIG_CPU_FREQ_DEBUG=y
 # CONFIG_CPU_FREQ_STAT is not set
 CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE=y
 CONFIG_CPU_FREQ_GOV_PERFORMANCE=y
 CONFIG_CPU_FREQ_GOV_ONDEMAND=y
 CONFIG_X86_ACPI_CPUFREQ=y
 CONFIG_PCI_MMCONFIG=y
-CONFIG_INTEL_IOMMU=y
-# CONFIG_INTEL_IOMMU_DEFAULT_ON is not set
 CONFIG_PCIEPORTBUS=y
 CONFIG_PCCARD=y
 CONFIG_YENTA=y
 CONFIG_HOTPLUG_PCI=y
-CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS=y
 CONFIG_BINFMT_MISC=y
 CONFIG_IA32_EMULATION=y
 CONFIG_NET=y
@@ -125,7 +122,6 @@
 CONFIG_IP_NF_IPTABLES=y
 CONFIG_IP_NF_FILTER=y
 CONFIG_IP_NF_TARGET_REJECT=y
-CONFIG_IP_NF_TARGET_LOG=y
 CONFIG_IP_NF_TARGET_ULOG=y
 CONFIG_NF_NAT=y
 CONFIG_IP_NF_TARGET_MASQUERADE=y
@@ -133,7 +129,6 @@
 CONFIG_NF_CONNTRACK_IPV6=y
 CONFIG_IP6_NF_IPTABLES=y
 CONFIG_IP6_NF_MATCH_IPV6HEADER=y
-CONFIG_IP6_NF_TARGET_LOG=y
 CONFIG_IP6_NF_FILTER=y
 CONFIG_IP6_NF_TARGET_REJECT=y
 CONFIG_IP6_NF_MANGLE=y
@@ -172,20 +167,15 @@
 CONFIG_MACINTOSH_DRIVERS=y
 CONFIG_MAC_EMUMOUSEBTN=y
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
-CONFIG_NET_VENDOR_3COM=y
+CONFIG_NETCONSOLE=y
+CONFIG_TIGON3=y
 CONFIG_NET_TULIP=y
-CONFIG_NET_PCI=y
-CONFIG_FORCEDETH=y
 CONFIG_E100=y
-CONFIG_8139TOO=y
 CONFIG_E1000=y
 CONFIG_SKY2=y
-CONFIG_TIGON3=y
-CONFIG_TR=y
-CONFIG_NET_PCMCIA=y
+CONFIG_FORCEDETH=y
+CONFIG_8139TOO=y
 CONFIG_FDDI=y
-CONFIG_NETCONSOLE=y
 CONFIG_INPUT_POLLDEV=y
 # CONFIG_INPUT_MOUSEDEV_PSAUX is not set
 CONFIG_INPUT_EVDEV=y
@@ -194,6 +184,7 @@
 CONFIG_INPUT_TOUCHSCREEN=y
 CONFIG_INPUT_MISC=y
 CONFIG_VT_HW_CONSOLE_BINDING=y
+# CONFIG_LEGACY_PTYS is not set
 CONFIG_SERIAL_NONSTANDARD=y
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
@@ -203,7 +194,6 @@
 CONFIG_SERIAL_8250_SHARE_IRQ=y
 CONFIG_SERIAL_8250_DETECT_IRQ=y
 CONFIG_SERIAL_8250_RSA=y
-# CONFIG_LEGACY_PTYS is not set
 CONFIG_HW_RANDOM=y
 # CONFIG_HW_RANDOM_INTEL is not set
 # CONFIG_HW_RANDOM_AMD is not set
@@ -221,7 +211,6 @@
 CONFIG_FB_MODE_HELPERS=y
 CONFIG_FB_TILEBLITTING=y
 CONFIG_FB_EFI=y
-CONFIG_BACKLIGHT_LCD_SUPPORT=y
 # CONFIG_LCD_CLASS_DEVICE is not set
 CONFIG_VGACON_SOFT_SCROLLBACK=y
 CONFIG_LOGO=y
@@ -268,6 +257,10 @@
 # CONFIG_RTC_HCTOSYS is not set
 CONFIG_DMADEVICES=y
 CONFIG_EEEPC_LAPTOP=y
+CONFIG_AMD_IOMMU=y
+CONFIG_AMD_IOMMU_STATS=y
+CONFIG_INTEL_IOMMU=y
+# CONFIG_INTEL_IOMMU_DEFAULT_ON is not set
 CONFIG_EFI_VARS=y
 CONFIG_EXT3_FS=y
 # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
@@ -284,7 +277,6 @@
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
 CONFIG_TMPFS_POSIX_ACL=y
 CONFIG_HUGETLBFS=y
 CONFIG_NFS_FS=y
@@ -292,18 +284,6 @@
 CONFIG_NFS_V3_ACL=y
 CONFIG_NFS_V4=y
 CONFIG_ROOT_NFS=y
-CONFIG_PARTITION_ADVANCED=y
-CONFIG_OSF_PARTITION=y
-CONFIG_AMIGA_PARTITION=y
-CONFIG_MAC_PARTITION=y
-CONFIG_BSD_DISKLABEL=y
-CONFIG_MINIX_SUBPARTITION=y
-CONFIG_SOLARIS_X86_PARTITION=y
-CONFIG_UNIXWARE_DISKLABEL=y
-CONFIG_SGI_PARTITION=y
-CONFIG_SUN_PARTITION=y
-CONFIG_KARMA_PARTITION=y
-CONFIG_EFI_PARTITION=y
 CONFIG_NLS_DEFAULT="utf8"
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ASCII=y
@@ -317,13 +297,12 @@
 # CONFIG_SCHED_DEBUG is not set
 CONFIG_SCHEDSTATS=y
 CONFIG_TIMER_STATS=y
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
+CONFIG_DEBUG_STACK_USAGE=y
 CONFIG_SYSCTL_SYSCALL_CHECK=y
 CONFIG_BLK_DEV_IO_TRACE=y
 CONFIG_PROVIDE_OHCI1394_DMA_INIT=y
 CONFIG_EARLY_PRINTK_DBGP=y
 CONFIG_DEBUG_STACKOVERFLOW=y
-CONFIG_DEBUG_STACK_USAGE=y
 # CONFIG_DEBUG_RODATA_TEST is not set
 CONFIG_DEBUG_NX_TEST=m
 CONFIG_DEBUG_BOOT_PARAMS=y
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index 5563ba1..a69245b 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -12,10 +12,8 @@
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/kernel.h>
-#include <linux/signal.h>
 #include <linux/errno.h>
 #include <linux/wait.h>
-#include <linux/ptrace.h>
 #include <linux/unistd.h>
 #include <linux/stddef.h>
 #include <linux/personality.h>
@@ -32,20 +30,15 @@
 #include <asm/proto.h>
 #include <asm/vdso.h>
 #include <asm/sigframe.h>
+#include <asm/sighandling.h>
 #include <asm/sys_ia32.h>
 
-#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
-
-#define FIX_EFLAGS	(X86_EFLAGS_AC | X86_EFLAGS_OF | \
-			 X86_EFLAGS_DF | X86_EFLAGS_TF | X86_EFLAGS_SF | \
-			 X86_EFLAGS_ZF | X86_EFLAGS_AF | X86_EFLAGS_PF | \
-			 X86_EFLAGS_CF)
-
-void signal_fault(struct pt_regs *regs, void __user *frame, char *where);
+#define FIX_EFLAGS	__FIX_EFLAGS
 
 int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from)
 {
 	int err = 0;
+	bool ia32 = is_ia32_task();
 
 	if (!access_ok(VERIFY_WRITE, to, sizeof(compat_siginfo_t)))
 		return -EFAULT;
@@ -75,8 +68,13 @@
 			case __SI_FAULT >> 16:
 				break;
 			case __SI_CHLD >> 16:
-				put_user_ex(from->si_utime, &to->si_utime);
-				put_user_ex(from->si_stime, &to->si_stime);
+				if (ia32) {
+					put_user_ex(from->si_utime, &to->si_utime);
+					put_user_ex(from->si_stime, &to->si_stime);
+				} else {
+					put_user_ex(from->si_utime, &to->_sifields._sigchld_x32._utime);
+					put_user_ex(from->si_stime, &to->_sifields._sigchld_x32._stime);
+				}
 				put_user_ex(from->si_status, &to->si_status);
 				/* FALL THROUGH */
 			default:
@@ -348,7 +346,7 @@
 		put_user_ex(regs->dx, &sc->dx);
 		put_user_ex(regs->cx, &sc->cx);
 		put_user_ex(regs->ax, &sc->ax);
-		put_user_ex(current->thread.trap_no, &sc->trapno);
+		put_user_ex(current->thread.trap_nr, &sc->trapno);
 		put_user_ex(current->thread.error_code, &sc->err);
 		put_user_ex(regs->ip, &sc->ip);
 		put_user_ex(regs->cs, (unsigned int __user *)&sc->cs);
diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c
index f6f5c53..aec2202 100644
--- a/arch/x86/ia32/sys_ia32.c
+++ b/arch/x86/ia32/sys_ia32.c
@@ -287,46 +287,6 @@
 	return ret;
 }
 
-asmlinkage long sys32_rt_sigprocmask(int how, compat_sigset_t __user *set,
-				     compat_sigset_t __user *oset,
-				     unsigned int sigsetsize)
-{
-	sigset_t s;
-	compat_sigset_t s32;
-	int ret;
-	mm_segment_t old_fs = get_fs();
-
-	if (set) {
-		if (copy_from_user(&s32, set, sizeof(compat_sigset_t)))
-			return -EFAULT;
-		switch (_NSIG_WORDS) {
-		case 4: s.sig[3] = s32.sig[6] | (((long)s32.sig[7]) << 32);
-		case 3: s.sig[2] = s32.sig[4] | (((long)s32.sig[5]) << 32);
-		case 2: s.sig[1] = s32.sig[2] | (((long)s32.sig[3]) << 32);
-		case 1: s.sig[0] = s32.sig[0] | (((long)s32.sig[1]) << 32);
-		}
-	}
-	set_fs(KERNEL_DS);
-	ret = sys_rt_sigprocmask(how,
-				 set ? (sigset_t __user *)&s : NULL,
-				 oset ? (sigset_t __user *)&s : NULL,
-				 sigsetsize);
-	set_fs(old_fs);
-	if (ret)
-		return ret;
-	if (oset) {
-		switch (_NSIG_WORDS) {
-		case 4: s32.sig[7] = (s.sig[3] >> 32); s32.sig[6] = s.sig[3];
-		case 3: s32.sig[5] = (s.sig[2] >> 32); s32.sig[4] = s.sig[2];
-		case 2: s32.sig[3] = (s.sig[1] >> 32); s32.sig[2] = s.sig[1];
-		case 1: s32.sig[1] = (s.sig[0] >> 32); s32.sig[0] = s.sig[0];
-		}
-		if (copy_to_user(oset, &s32, sizeof(compat_sigset_t)))
-			return -EFAULT;
-	}
-	return 0;
-}
-
 asmlinkage long sys32_alarm(unsigned int seconds)
 {
 	return alarm_setitimer(seconds);
diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild
index b57e6a4..f9c0d3b 100644
--- a/arch/x86/include/asm/Kbuild
+++ b/arch/x86/include/asm/Kbuild
@@ -14,6 +14,7 @@
 header-y += mtrr.h
 header-y += posix_types_32.h
 header-y += posix_types_64.h
+header-y += posix_types_x32.h
 header-y += prctl.h
 header-y += processor-flags.h
 header-y += ptrace-abi.h
@@ -24,3 +25,4 @@
 
 genhdr-y += unistd_32.h
 genhdr-y += unistd_64.h
+genhdr-y += unistd_x32.h
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 4b2caee..d854101 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -534,7 +534,7 @@
 
 static inline int default_apic_id_valid(int apicid)
 {
-	return x2apic_mode || (apicid < 255);
+	return (apicid < 255);
 }
 
 extern void default_setup_apic_routing(void);
diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h
index 30d737e..d680579 100644
--- a/arch/x86/include/asm/compat.h
+++ b/arch/x86/include/asm/compat.h
@@ -6,7 +6,9 @@
  */
 #include <linux/types.h>
 #include <linux/sched.h>
+#include <asm/processor.h>
 #include <asm/user32.h>
+#include <asm/unistd.h>
 
 #define COMPAT_USER_HZ		100
 #define COMPAT_UTS_MACHINE	"i686\0\0"
@@ -186,7 +188,20 @@
 /*
  * The type of struct elf_prstatus.pr_reg in compatible core dumps.
  */
+#ifdef CONFIG_X86_X32_ABI
+typedef struct user_regs_struct compat_elf_gregset_t;
+
+#define PR_REG_SIZE(S) (test_thread_flag(TIF_IA32) ? 68 : 216)
+#define PRSTATUS_SIZE(S) (test_thread_flag(TIF_IA32) ? 144 : 296)
+#define SET_PR_FPVALID(S,V) \
+  do { *(int *) (((void *) &((S)->pr_reg)) + PR_REG_SIZE(0)) = (V); } \
+  while (0)
+
+#define COMPAT_USE_64BIT_TIME \
+	(!!(task_pt_regs(current)->orig_ax & __X32_SYSCALL_BIT))
+#else
 typedef struct user_regs_struct32 compat_elf_gregset_t;
+#endif
 
 /*
  * A pointer passed in from user mode. This should not
@@ -208,13 +223,30 @@
 
 static inline void __user *arch_compat_alloc_user_space(long len)
 {
-	struct pt_regs *regs = task_pt_regs(current);
-	return (void __user *)regs->sp - len;
+	compat_uptr_t sp;
+
+	if (test_thread_flag(TIF_IA32)) {
+		sp = task_pt_regs(current)->sp;
+	} else {
+		/* -128 for the x32 ABI redzone */
+		sp = percpu_read(old_rsp) - 128;
+	}
+
+	return (void __user *)round_down(sp - len, 16);
 }
 
-static inline int is_compat_task(void)
+static inline bool is_x32_task(void)
 {
-	return current_thread_info()->status & TS_COMPAT;
+#ifdef CONFIG_X86_X32_ABI
+	if (task_pt_regs(current)->orig_ax & __X32_SYSCALL_BIT)
+		return true;
+#endif
+	return false;
+}
+
+static inline bool is_compat_task(void)
+{
+	return is_ia32_task() || is_x32_task();
 }
 
 #endif /* _ASM_X86_COMPAT_H */
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index f27f79a..5939f44 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -155,7 +155,12 @@
 #define elf_check_arch(x)			\
 	((x)->e_machine == EM_X86_64)
 
-#define compat_elf_check_arch(x)	elf_check_arch_ia32(x)
+#define compat_elf_check_arch(x)		\
+	(elf_check_arch_ia32(x) || (x)->e_machine == EM_X86_64)
+
+#if __USER32_DS != __USER_DS
+# error "The following code assumes __USER32_DS == __USER_DS"
+#endif
 
 static inline void elf_common_init(struct thread_struct *t,
 				   struct pt_regs *regs, const u16 ds)
@@ -178,8 +183,9 @@
 void start_thread_ia32(struct pt_regs *regs, u32 new_ip, u32 new_sp);
 #define compat_start_thread start_thread_ia32
 
-void set_personality_ia32(void);
-#define COMPAT_SET_PERSONALITY(ex) set_personality_ia32()
+void set_personality_ia32(bool);
+#define COMPAT_SET_PERSONALITY(ex)			\
+	set_personality_ia32((ex).e_machine == EM_X86_64)
 
 #define COMPAT_ELF_PLATFORM			("i686")
 
@@ -286,7 +292,7 @@
 #define VDSO_HIGH_BASE		0xffffe000U /* CONFIG_COMPAT_VDSO address */
 
 /* 1GB for 64bit, 8MB for 32bit */
-#define STACK_RND_MASK (test_thread_flag(TIF_IA32) ? 0x7ff : 0x3fffff)
+#define STACK_RND_MASK (test_thread_flag(TIF_ADDR32) ? 0x7ff : 0x3fffff)
 
 #define ARCH_DLINFO							\
 do {									\
@@ -295,9 +301,20 @@
 			    (unsigned long)current->mm->context.vdso);	\
 } while (0)
 
+#define ARCH_DLINFO_X32							\
+do {									\
+	if (vdso_enabled)						\
+		NEW_AUX_ENT(AT_SYSINFO_EHDR,				\
+			    (unsigned long)current->mm->context.vdso);	\
+} while (0)
+
 #define AT_SYSINFO		32
 
-#define COMPAT_ARCH_DLINFO	ARCH_DLINFO_IA32(sysctl_vsyscall32)
+#define COMPAT_ARCH_DLINFO						\
+if (test_thread_flag(TIF_X32))						\
+	ARCH_DLINFO_X32;						\
+else									\
+	ARCH_DLINFO_IA32(sysctl_vsyscall32)
 
 #define COMPAT_ELF_ET_DYN_BASE	(TASK_UNMAPPED_BASE + 0x1000000)
 
@@ -313,6 +330,8 @@
 #define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1
 extern int arch_setup_additional_pages(struct linux_binprm *bprm,
 				       int uses_interp);
+extern int x32_setup_additional_pages(struct linux_binprm *bprm,
+				      int uses_interp);
 
 extern int syscall32_setup_pages(struct linux_binprm *, int exstack);
 #define compat_arch_setup_additional_pages	syscall32_setup_pages
@@ -329,7 +348,7 @@
 	return 1;
 #endif
 #ifdef CONFIG_IA32_EMULATION
-	if (test_thread_flag(TIF_IA32))
+	if (test_thread_flag(TIF_ADDR32))
 		return 1;
 #endif
 	return 0;
diff --git a/arch/x86/include/asm/ia32.h b/arch/x86/include/asm/ia32.h
index 1f7e625..ee52760 100644
--- a/arch/x86/include/asm/ia32.h
+++ b/arch/x86/include/asm/ia32.h
@@ -43,6 +43,15 @@
 	compat_sigset_t	  uc_sigmask;	/* mask last for extensibility */
 };
 
+struct ucontext_x32 {
+	unsigned int	  uc_flags;
+	unsigned int 	  uc_link;
+	stack_ia32_t	  uc_stack;
+	unsigned int	  uc__pad0;     /* needed for alignment */
+	struct sigcontext uc_mcontext;  /* the 64-bit sigcontext type */
+	compat_sigset_t	  uc_sigmask;	/* mask last for extensibility */
+};
+
 /* This matches struct stat64 in glibc2.2, hence the absolutely
  * insane amounts of padding around dev_t's.
  */
@@ -116,6 +125,15 @@
 			compat_clock_t _stime;
 		} _sigchld;
 
+		/* SIGCHLD (x32 version) */
+		struct {
+			unsigned int _pid;	/* which child */
+			unsigned int _uid;	/* sender's uid */
+			int _status;		/* exit code */
+			compat_s64 _utime;
+			compat_s64 _stime;
+		} _sigchld_x32;
+
 		/* SIGILL, SIGFPE, SIGSEGV, SIGBUS */
 		struct {
 			unsigned int _addr;	/* faulting insn/memory ref. */
diff --git a/arch/x86/include/asm/idle.h b/arch/x86/include/asm/idle.h
index f49253d7..c5d1785 100644
--- a/arch/x86/include/asm/idle.h
+++ b/arch/x86/include/asm/idle.h
@@ -14,6 +14,7 @@
 #else /* !CONFIG_X86_64 */
 static inline void enter_idle(void) { }
 static inline void exit_idle(void) { }
+static inline void __exit_idle(void) { }
 #endif /* CONFIG_X86_64 */
 
 void amd_e400_remove_cpu(int cpu);
diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index 690d1cc..2c4943d 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -21,6 +21,15 @@
 #define IO_APIC_REDIR_LEVEL_TRIGGER	(1 << 15)
 #define IO_APIC_REDIR_MASKED		(1 << 16)
 
+struct io_apic_ops {
+	void		(*init)  (void);
+	unsigned int	(*read)  (unsigned int apic, unsigned int reg);
+	void		(*write) (unsigned int apic, unsigned int reg, unsigned int value);
+	void		(*modify)(unsigned int apic, unsigned int reg, unsigned int value);
+};
+
+void __init set_io_apic_ops(const struct io_apic_ops *);
+
 /*
  * The structure of the IO-APIC:
  */
diff --git a/arch/x86/include/asm/mtrr.h b/arch/x86/include/asm/mtrr.h
index 4365ffd..7e3f17f 100644
--- a/arch/x86/include/asm/mtrr.h
+++ b/arch/x86/include/asm/mtrr.h
@@ -29,18 +29,18 @@
 
 #define	MTRR_IOCTL_BASE	'M'
 
-struct mtrr_sentry {
-    unsigned long base;    /*  Base address     */
-    unsigned int size;    /*  Size of region   */
-    unsigned int type;     /*  Type of region   */
-};
-
 /* Warning: this structure has a different order from i386
    on x86-64. The 32bit emulation code takes care of that.
    But you need to use this for 64bit, otherwise your X server
    will break. */
 
 #ifdef __i386__
+struct mtrr_sentry {
+    unsigned long base;    /*  Base address     */
+    unsigned int size;    /*  Size of region   */
+    unsigned int type;     /*  Type of region   */
+};
+
 struct mtrr_gentry {
     unsigned int regnum;   /*  Register number  */
     unsigned long base;    /*  Base address     */
@@ -50,12 +50,20 @@
 
 #else /* __i386__ */
 
-struct mtrr_gentry {
-    unsigned long base;    /*  Base address     */
-    unsigned int size;    /*  Size of region   */
-    unsigned int regnum;   /*  Register number  */
-    unsigned int type;     /*  Type of region   */
+struct mtrr_sentry {
+	__u64 base;		/*  Base address     */
+	__u32 size;		/*  Size of region   */
+	__u32 type;		/*  Type of region   */
 };
+
+struct mtrr_gentry {
+	__u64 base;		/*  Base address     */
+	__u32 size;		/*  Size of region   */
+	__u32 regnum;		/*  Register number  */
+	__u32 type;		/*  Type of region   */
+	__u32 _pad;		/*  Unused	     */
+};
+
 #endif /* !__i386__ */
 
 struct mtrr_var_range {
diff --git a/arch/x86/include/asm/posix_types.h b/arch/x86/include/asm/posix_types.h
index bb7133d..3427b77 100644
--- a/arch/x86/include/asm/posix_types.h
+++ b/arch/x86/include/asm/posix_types.h
@@ -7,7 +7,9 @@
 #else
 # ifdef __i386__
 #  include "posix_types_32.h"
-# else
+# elif defined(__LP64__)
 #  include "posix_types_64.h"
+# else
+#  include "posix_types_x32.h"
 # endif
 #endif
diff --git a/arch/x86/include/asm/posix_types_32.h b/arch/x86/include/asm/posix_types_32.h
index f7d9adf..99f262e 100644
--- a/arch/x86/include/asm/posix_types_32.h
+++ b/arch/x86/include/asm/posix_types_32.h
@@ -7,79 +7,22 @@
  * assume GCC is being used.
  */
 
-typedef unsigned long	__kernel_ino_t;
 typedef unsigned short	__kernel_mode_t;
+#define __kernel_mode_t __kernel_mode_t
+
 typedef unsigned short	__kernel_nlink_t;
-typedef long		__kernel_off_t;
-typedef int		__kernel_pid_t;
+#define __kernel_nlink_t __kernel_nlink_t
+
 typedef unsigned short	__kernel_ipc_pid_t;
+#define __kernel_ipc_pid_t __kernel_ipc_pid_t
+
 typedef unsigned short	__kernel_uid_t;
 typedef unsigned short	__kernel_gid_t;
-typedef unsigned int	__kernel_size_t;
-typedef int		__kernel_ssize_t;
-typedef int		__kernel_ptrdiff_t;
-typedef long		__kernel_time_t;
-typedef long		__kernel_suseconds_t;
-typedef long		__kernel_clock_t;
-typedef int		__kernel_timer_t;
-typedef int		__kernel_clockid_t;
-typedef int		__kernel_daddr_t;
-typedef char *		__kernel_caddr_t;
-typedef unsigned short	__kernel_uid16_t;
-typedef unsigned short	__kernel_gid16_t;
-typedef unsigned int	__kernel_uid32_t;
-typedef unsigned int	__kernel_gid32_t;
+#define __kernel_uid_t __kernel_uid_t
 
-typedef unsigned short	__kernel_old_uid_t;
-typedef unsigned short	__kernel_old_gid_t;
 typedef unsigned short	__kernel_old_dev_t;
+#define __kernel_old_dev_t __kernel_old_dev_t
 
-#ifdef __GNUC__
-typedef long long	__kernel_loff_t;
-#endif
-
-typedef struct {
-	int	val[2];
-} __kernel_fsid_t;
-
-#if defined(__KERNEL__)
-
-#undef	__FD_SET
-#define __FD_SET(fd,fdsetp)					\
-	asm volatile("btsl %1,%0":				\
-		     "+m" (*(__kernel_fd_set *)(fdsetp))	\
-		     : "r" ((int)(fd)))
-
-#undef	__FD_CLR
-#define __FD_CLR(fd,fdsetp)					\
-	asm volatile("btrl %1,%0":				\
-		     "+m" (*(__kernel_fd_set *)(fdsetp))	\
-		     : "r" ((int) (fd)))
-
-#undef	__FD_ISSET
-#define __FD_ISSET(fd,fdsetp)					\
-	(__extension__						\
-	 ({							\
-	 unsigned char __result;				\
-	 asm volatile("btl %1,%2 ; setb %0"			\
-		      : "=q" (__result)				\
-		      : "r" ((int)(fd)),			\
-			"m" (*(__kernel_fd_set *)(fdsetp)));	\
-	 __result;						\
-}))
-
-#undef	__FD_ZERO
-#define __FD_ZERO(fdsetp)					\
-do {								\
-	int __d0, __d1;						\
-	asm volatile("cld ; rep ; stosl"			\
-		     : "=m" (*(__kernel_fd_set *)(fdsetp)),	\
-		       "=&c" (__d0), "=&D" (__d1)		\
-		     : "a" (0), "1" (__FDSET_LONGS),		\
-		       "2" ((__kernel_fd_set *)(fdsetp))	\
-		     : "memory");				\
-} while (0)
-
-#endif /* defined(__KERNEL__) */
+#include <asm-generic/posix_types.h>
 
 #endif /* _ASM_X86_POSIX_TYPES_32_H */
diff --git a/arch/x86/include/asm/posix_types_64.h b/arch/x86/include/asm/posix_types_64.h
index eb8d2d9..cba0c1e 100644
--- a/arch/x86/include/asm/posix_types_64.h
+++ b/arch/x86/include/asm/posix_types_64.h
@@ -7,113 +7,13 @@
  * assume GCC is being used.
  */
 
-typedef unsigned long	__kernel_ino_t;
-typedef unsigned int	__kernel_mode_t;
-typedef unsigned long	__kernel_nlink_t;
-typedef long		__kernel_off_t;
-typedef int		__kernel_pid_t;
-typedef int		__kernel_ipc_pid_t;
-typedef unsigned int	__kernel_uid_t;
-typedef unsigned int	__kernel_gid_t;
-typedef unsigned long	__kernel_size_t;
-typedef long		__kernel_ssize_t;
-typedef long		__kernel_ptrdiff_t;
-typedef long		__kernel_time_t;
-typedef long		__kernel_suseconds_t;
-typedef long		__kernel_clock_t;
-typedef int		__kernel_timer_t;
-typedef int		__kernel_clockid_t;
-typedef int		__kernel_daddr_t;
-typedef char *		__kernel_caddr_t;
-typedef unsigned short	__kernel_uid16_t;
-typedef unsigned short	__kernel_gid16_t;
-
-#ifdef __GNUC__
-typedef long long	__kernel_loff_t;
-#endif
-
-typedef struct {
-	int	val[2];
-} __kernel_fsid_t;
-
 typedef unsigned short __kernel_old_uid_t;
 typedef unsigned short __kernel_old_gid_t;
-typedef __kernel_uid_t __kernel_uid32_t;
-typedef __kernel_gid_t __kernel_gid32_t;
+#define __kernel_old_uid_t __kernel_old_uid_t
 
 typedef unsigned long	__kernel_old_dev_t;
+#define __kernel_old_dev_t __kernel_old_dev_t
 
-#ifdef __KERNEL__
-
-#undef __FD_SET
-static inline void __FD_SET(unsigned long fd, __kernel_fd_set *fdsetp)
-{
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	fdsetp->fds_bits[_tmp] |= (1UL<<_rem);
-}
-
-#undef __FD_CLR
-static inline void __FD_CLR(unsigned long fd, __kernel_fd_set *fdsetp)
-{
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	fdsetp->fds_bits[_tmp] &= ~(1UL<<_rem);
-}
-
-#undef __FD_ISSET
-static inline int __FD_ISSET(unsigned long fd, __const__ __kernel_fd_set *p)
-{
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	return (p->fds_bits[_tmp] & (1UL<<_rem)) != 0;
-}
-
-/*
- * This will unroll the loop for the normal constant cases (8 or 32 longs,
- * for 256 and 1024-bit fd_sets respectively)
- */
-#undef __FD_ZERO
-static inline void __FD_ZERO(__kernel_fd_set *p)
-{
-	unsigned long *tmp = p->fds_bits;
-	int i;
-
-	if (__builtin_constant_p(__FDSET_LONGS)) {
-		switch (__FDSET_LONGS) {
-		case 32:
-			tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
-			tmp[ 4] = 0; tmp[ 5] = 0; tmp[ 6] = 0; tmp[ 7] = 0;
-			tmp[ 8] = 0; tmp[ 9] = 0; tmp[10] = 0; tmp[11] = 0;
-			tmp[12] = 0; tmp[13] = 0; tmp[14] = 0; tmp[15] = 0;
-			tmp[16] = 0; tmp[17] = 0; tmp[18] = 0; tmp[19] = 0;
-			tmp[20] = 0; tmp[21] = 0; tmp[22] = 0; tmp[23] = 0;
-			tmp[24] = 0; tmp[25] = 0; tmp[26] = 0; tmp[27] = 0;
-			tmp[28] = 0; tmp[29] = 0; tmp[30] = 0; tmp[31] = 0;
-			return;
-		case 16:
-			tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
-			tmp[ 4] = 0; tmp[ 5] = 0; tmp[ 6] = 0; tmp[ 7] = 0;
-			tmp[ 8] = 0; tmp[ 9] = 0; tmp[10] = 0; tmp[11] = 0;
-			tmp[12] = 0; tmp[13] = 0; tmp[14] = 0; tmp[15] = 0;
-			return;
-		case 8:
-			tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
-			tmp[ 4] = 0; tmp[ 5] = 0; tmp[ 6] = 0; tmp[ 7] = 0;
-			return;
-		case 4:
-			tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
-			return;
-		}
-	}
-	i = __FDSET_LONGS;
-	while (i) {
-		i--;
-		*tmp = 0;
-		tmp++;
-	}
-}
-
-#endif /* defined(__KERNEL__) */
+#include <asm-generic/posix_types.h>
 
 #endif /* _ASM_X86_POSIX_TYPES_64_H */
diff --git a/arch/x86/include/asm/posix_types_x32.h b/arch/x86/include/asm/posix_types_x32.h
new file mode 100644
index 0000000..85f9bda
--- /dev/null
+++ b/arch/x86/include/asm/posix_types_x32.h
@@ -0,0 +1,19 @@
+#ifndef _ASM_X86_POSIX_TYPES_X32_H
+#define _ASM_X86_POSIX_TYPES_X32_H
+
+/*
+ * This file is only used by user-level software, so you need to
+ * be a little careful about namespace pollution etc.  Also, we cannot
+ * assume GCC is being used.
+ *
+ * These types should generally match the ones used by the 64-bit kernel,
+ *
+ */
+
+typedef long long __kernel_long_t;
+typedef unsigned long long __kernel_ulong_t;
+#define __kernel_long_t __kernel_long_t
+
+#include <asm/posix_types_64.h>
+
+#endif /* _ASM_X86_POSIX_TYPES_X32_H */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index a19542c..7284c9a 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -463,7 +463,7 @@
 	unsigned long           ptrace_dr7;
 	/* Fault info: */
 	unsigned long		cr2;
-	unsigned long		trap_no;
+	unsigned long		trap_nr;
 	unsigned long		error_code;
 	/* floating point and extended processor state */
 	struct fpu		fpu;
@@ -873,9 +873,9 @@
 #define IA32_PAGE_OFFSET	((current->personality & ADDR_LIMIT_3GB) ? \
 					0xc0000000 : 0xFFFFe000)
 
-#define TASK_SIZE		(test_thread_flag(TIF_IA32) ? \
+#define TASK_SIZE		(test_thread_flag(TIF_ADDR32) ? \
 					IA32_PAGE_OFFSET : TASK_SIZE_MAX)
-#define TASK_SIZE_OF(child)	((test_tsk_thread_flag(child, TIF_IA32)) ? \
+#define TASK_SIZE_OF(child)	((test_tsk_thread_flag(child, TIF_ADDR32)) ? \
 					IA32_PAGE_OFFSET : TASK_SIZE_MAX)
 
 #define STACK_TOP		TASK_SIZE
@@ -897,6 +897,12 @@
 
 #define task_pt_regs(tsk)	((struct pt_regs *)(tsk)->thread.sp0 - 1)
 extern unsigned long KSTK_ESP(struct task_struct *task);
+
+/*
+ * User space RSP while inside the SYSCALL fast path
+ */
+DECLARE_PER_CPU(unsigned long, old_rsp);
+
 #endif /* CONFIG_X86_64 */
 
 extern void start_thread(struct pt_regs *regs, unsigned long new_ip,
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 3566454..dcfde52 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -145,7 +145,6 @@
 convert_ip_to_linear(struct task_struct *child, struct pt_regs *regs);
 extern void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs,
 			 int error_code, int si_code);
-void signal_fault(struct pt_regs *regs, void __user *frame, char *where);
 
 extern long syscall_trace_enter(struct pt_regs *);
 extern void syscall_trace_leave(struct pt_regs *);
diff --git a/arch/x86/include/asm/sigcontext.h b/arch/x86/include/asm/sigcontext.h
index 04459d2..4a08538 100644
--- a/arch/x86/include/asm/sigcontext.h
+++ b/arch/x86/include/asm/sigcontext.h
@@ -230,34 +230,37 @@
  * User-space might still rely on the old definition:
  */
 struct sigcontext {
-	unsigned long r8;
-	unsigned long r9;
-	unsigned long r10;
-	unsigned long r11;
-	unsigned long r12;
-	unsigned long r13;
-	unsigned long r14;
-	unsigned long r15;
-	unsigned long rdi;
-	unsigned long rsi;
-	unsigned long rbp;
-	unsigned long rbx;
-	unsigned long rdx;
-	unsigned long rax;
-	unsigned long rcx;
-	unsigned long rsp;
-	unsigned long rip;
-	unsigned long eflags;		/* RFLAGS */
-	unsigned short cs;
-	unsigned short gs;
-	unsigned short fs;
-	unsigned short __pad0;
-	unsigned long err;
-	unsigned long trapno;
-	unsigned long oldmask;
-	unsigned long cr2;
+	__u64 r8;
+	__u64 r9;
+	__u64 r10;
+	__u64 r11;
+	__u64 r12;
+	__u64 r13;
+	__u64 r14;
+	__u64 r15;
+	__u64 rdi;
+	__u64 rsi;
+	__u64 rbp;
+	__u64 rbx;
+	__u64 rdx;
+	__u64 rax;
+	__u64 rcx;
+	__u64 rsp;
+	__u64 rip;
+	__u64 eflags;		/* RFLAGS */
+	__u16 cs;
+	__u16 gs;
+	__u16 fs;
+	__u16 __pad0;
+	__u64 err;
+	__u64 trapno;
+	__u64 oldmask;
+	__u64 cr2;
 	struct _fpstate __user *fpstate;	/* zero when no FPU context */
-	unsigned long reserved1[8];
+#ifndef __LP64__
+	__u32 __fpstate_pad;
+#endif
+	__u64 reserved1[8];
 };
 #endif /* !__KERNEL__ */
 
diff --git a/arch/x86/include/asm/sigframe.h b/arch/x86/include/asm/sigframe.h
index 4e0fe26..7c7c27c 100644
--- a/arch/x86/include/asm/sigframe.h
+++ b/arch/x86/include/asm/sigframe.h
@@ -59,12 +59,25 @@
 #endif /* defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) */
 
 #ifdef CONFIG_X86_64
+
 struct rt_sigframe {
 	char __user *pretcode;
 	struct ucontext uc;
 	struct siginfo info;
 	/* fp state follows here */
 };
+
+#ifdef CONFIG_X86_X32_ABI
+
+struct rt_sigframe_x32 {
+	u64 pretcode;
+	struct ucontext_x32 uc;
+	compat_siginfo_t info;
+	/* fp state follows here */
+};
+
+#endif /* CONFIG_X86_X32_ABI */
+
 #endif /* CONFIG_X86_64 */
 
 #endif /* _ASM_X86_SIGFRAME_H */
diff --git a/arch/x86/include/asm/sighandling.h b/arch/x86/include/asm/sighandling.h
new file mode 100644
index 0000000..ada93b3
--- /dev/null
+++ b/arch/x86/include/asm/sighandling.h
@@ -0,0 +1,24 @@
+#ifndef _ASM_X86_SIGHANDLING_H
+#define _ASM_X86_SIGHANDLING_H
+
+#include <linux/compiler.h>
+#include <linux/ptrace.h>
+#include <linux/signal.h>
+
+#include <asm/processor-flags.h>
+
+#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
+
+#define __FIX_EFLAGS	(X86_EFLAGS_AC | X86_EFLAGS_OF | \
+			 X86_EFLAGS_DF | X86_EFLAGS_TF | X86_EFLAGS_SF | \
+			 X86_EFLAGS_ZF | X86_EFLAGS_AF | X86_EFLAGS_PF | \
+			 X86_EFLAGS_CF)
+
+void signal_fault(struct pt_regs *regs, void __user *frame, char *where);
+
+int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
+		       unsigned long *pax);
+int setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate,
+		     struct pt_regs *regs, unsigned long mask);
+
+#endif /* _ASM_X86_SIGHANDLING_H */
diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h
index cb23852..3fda9db4 100644
--- a/arch/x86/include/asm/sys_ia32.h
+++ b/arch/x86/include/asm/sys_ia32.h
@@ -10,6 +10,8 @@
 #ifndef _ASM_X86_SYS_IA32_H
 #define _ASM_X86_SYS_IA32_H
 
+#ifdef CONFIG_COMPAT
+
 #include <linux/compiler.h>
 #include <linux/linkage.h>
 #include <linux/types.h>
@@ -36,8 +38,6 @@
 				   struct sigaction32 __user *, unsigned int);
 asmlinkage long sys32_sigaction(int, struct old_sigaction32 __user *,
 				struct old_sigaction32 __user *);
-asmlinkage long sys32_rt_sigprocmask(int, compat_sigset_t __user *,
-				     compat_sigset_t __user *, unsigned int);
 asmlinkage long sys32_alarm(unsigned int);
 
 asmlinkage long sys32_waitpid(compat_pid_t, unsigned int *, int);
@@ -83,4 +83,7 @@
 
 asmlinkage long sys32_fanotify_mark(int, unsigned int, u32, u32, int,
 				    const char __user *);
+
+#endif /* CONFIG_COMPAT */
+
 #endif /* _ASM_X86_SYS_IA32_H */
diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h
index d962e56..386b786 100644
--- a/arch/x86/include/asm/syscall.h
+++ b/arch/x86/include/asm/syscall.h
@@ -16,6 +16,7 @@
 #include <linux/sched.h>
 #include <linux/err.h>
 #include <asm/asm-offsets.h>	/* For NR_syscalls */
+#include <asm/unistd.h>
 
 extern const unsigned long sys_call_table[];
 
@@ -26,13 +27,13 @@
  */
 static inline int syscall_get_nr(struct task_struct *task, struct pt_regs *regs)
 {
-	return regs->orig_ax;
+	return regs->orig_ax & __SYSCALL_MASK;
 }
 
 static inline void syscall_rollback(struct task_struct *task,
 				    struct pt_regs *regs)
 {
-	regs->ax = regs->orig_ax;
+	regs->ax = regs->orig_ax & __SYSCALL_MASK;
 }
 
 static inline long syscall_get_error(struct task_struct *task,
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index cfd8144..ad6df8c 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -86,7 +86,7 @@
 #define TIF_MCE_NOTIFY		10	/* notify userspace of an MCE */
 #define TIF_USER_RETURN_NOTIFY	11	/* notify kernel of userspace return */
 #define TIF_NOTSC		16	/* TSC is not accessible in userland */
-#define TIF_IA32		17	/* 32bit process */
+#define TIF_IA32		17	/* IA32 compatibility process */
 #define TIF_FORK		18	/* ret_from_fork */
 #define TIF_MEMDIE		20	/* is terminating due to OOM killer */
 #define TIF_DEBUG		21	/* uses debug registers */
@@ -95,6 +95,8 @@
 #define TIF_BLOCKSTEP		25	/* set when we want DEBUGCTLMSR_BTF */
 #define TIF_LAZY_MMU_UPDATES	27	/* task is updating the mmu lazily */
 #define TIF_SYSCALL_TRACEPOINT	28	/* syscall tracepoint instrumentation */
+#define TIF_ADDR32		29	/* 32-bit address space on 64 bits */
+#define TIF_X32			30	/* 32-bit native x86-64 binary */
 
 #define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
 #define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
@@ -116,6 +118,8 @@
 #define _TIF_BLOCKSTEP		(1 << TIF_BLOCKSTEP)
 #define _TIF_LAZY_MMU_UPDATES	(1 << TIF_LAZY_MMU_UPDATES)
 #define _TIF_SYSCALL_TRACEPOINT	(1 << TIF_SYSCALL_TRACEPOINT)
+#define _TIF_ADDR32		(1 << TIF_ADDR32)
+#define _TIF_X32		(1 << TIF_X32)
 
 /* work to do in syscall_trace_enter() */
 #define _TIF_WORK_SYSCALL_ENTRY	\
@@ -262,6 +266,18 @@
 	ti->status |= TS_RESTORE_SIGMASK;
 	set_bit(TIF_SIGPENDING, (unsigned long *)&ti->flags);
 }
+
+static inline bool is_ia32_task(void)
+{
+#ifdef CONFIG_X86_32
+	return true;
+#endif
+#ifdef CONFIG_IA32_EMULATION
+	if (current_thread_info()->status & TS_COMPAT)
+		return true;
+#endif
+	return false;
+}
 #endif	/* !__ASSEMBLY__ */
 
 #ifndef __ASSEMBLY__
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index 0012d09..88eae2a 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -89,4 +89,29 @@
 asmlinkage void mce_threshold_interrupt(void);
 #endif
 
+/* Interrupts/Exceptions */
+enum {
+	X86_TRAP_DE = 0,	/*  0, Divide-by-zero */
+	X86_TRAP_DB,		/*  1, Debug */
+	X86_TRAP_NMI,		/*  2, Non-maskable Interrupt */
+	X86_TRAP_BP,		/*  3, Breakpoint */
+	X86_TRAP_OF,		/*  4, Overflow */
+	X86_TRAP_BR,		/*  5, Bound Range Exceeded */
+	X86_TRAP_UD,		/*  6, Invalid Opcode */
+	X86_TRAP_NM,		/*  7, Device Not Available */
+	X86_TRAP_DF,		/*  8, Double Fault */
+	X86_TRAP_OLD_MF,	/*  9, Coprocessor Segment Overrun */
+	X86_TRAP_TS,		/* 10, Invalid TSS */
+	X86_TRAP_NP,		/* 11, Segment Not Present */
+	X86_TRAP_SS,		/* 12, Stack Segment Fault */
+	X86_TRAP_GP,		/* 13, General Protection Fault */
+	X86_TRAP_PF,		/* 14, Page Fault */
+	X86_TRAP_SPURIOUS,	/* 15, Spurious Interrupt */
+	X86_TRAP_MF,		/* 16, x87 Floating-Point Exception */
+	X86_TRAP_AC,		/* 17, Alignment Check */
+	X86_TRAP_MC,		/* 18, Machine Check */
+	X86_TRAP_XF,		/* 19, SIMD Floating-Point Exception */
+	X86_TRAP_IRET = 32,	/* 32, IRET Exception */
+};
+
 #endif /* _ASM_X86_TRAPS_H */
diff --git a/arch/x86/include/asm/unistd.h b/arch/x86/include/asm/unistd.h
index 21f77b8..37cdc9d 100644
--- a/arch/x86/include/asm/unistd.h
+++ b/arch/x86/include/asm/unistd.h
@@ -1,7 +1,17 @@
 #ifndef _ASM_X86_UNISTD_H
 #define _ASM_X86_UNISTD_H 1
 
+/* x32 syscall flag bit */
+#define __X32_SYSCALL_BIT	0x40000000
+
 #ifdef __KERNEL__
+
+# ifdef CONFIG_X86_X32_ABI
+#  define __SYSCALL_MASK (~(__X32_SYSCALL_BIT))
+# else
+#  define __SYSCALL_MASK (~0)
+# endif
+
 # ifdef CONFIG_X86_32
 
 #  include <asm/unistd_32.h>
@@ -14,6 +24,7 @@
 # else
 
 #  include <asm/unistd_64.h>
+#  include <asm/unistd_64_x32.h>
 #  define __ARCH_WANT_COMPAT_SYS_TIME
 
 # endif
@@ -52,8 +63,10 @@
 #else
 # ifdef __i386__
 #  include <asm/unistd_32.h>
-# else
+# elif defined(__LP64__)
 #  include <asm/unistd_64.h>
+# else
+#  include <asm/unistd_x32.h>
 # endif
 #endif
 
diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h
index 815285b..8b38be2 100644
--- a/arch/x86/include/asm/vgtod.h
+++ b/arch/x86/include/asm/vgtod.h
@@ -5,13 +5,8 @@
 #include <linux/clocksource.h>
 
 struct vsyscall_gtod_data {
-	seqlock_t	lock;
+	seqcount_t	seq;
 
-	/* open coded 'struct timespec' */
-	time_t		wall_time_sec;
-	u32		wall_time_nsec;
-
-	struct timezone sys_tz;
 	struct { /* extract of a clocksource struct */
 		int vclock_mode;
 		cycle_t	cycle_last;
@@ -19,8 +14,16 @@
 		u32	mult;
 		u32	shift;
 	} clock;
-	struct timespec wall_to_monotonic;
+
+	/* open coded 'struct timespec' */
+	time_t		wall_time_sec;
+	u32		wall_time_nsec;
+	u32		monotonic_time_nsec;
+	time_t		monotonic_time_sec;
+
+	struct timezone sys_tz;
 	struct timespec wall_time_coarse;
+	struct timespec monotonic_time_coarse;
 };
 extern struct vsyscall_gtod_data vsyscall_gtod_data;
 
diff --git a/arch/x86/include/asm/x2apic.h b/arch/x86/include/asm/x2apic.h
index 6bf5b8e..92e54ab 100644
--- a/arch/x86/include/asm/x2apic.h
+++ b/arch/x86/include/asm/x2apic.h
@@ -18,6 +18,11 @@
 	return cpu_online_mask;
 }
 
+static int x2apic_apic_id_valid(int apicid)
+{
+	return 1;
+}
+
 static int x2apic_apic_id_registered(void)
 {
 	return 1;
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 406ed77..0f42c2f 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -239,7 +239,7 @@
 	 * to not preallocating memory for all NR_CPUS
 	 * when we use CPU hotplug.
 	 */
-	if (!cpu_has_x2apic && (apic_id >= 0xff) && enabled)
+	if (!apic->apic_id_valid(apic_id) && enabled)
 		printk(KERN_WARNING PREFIX "x2apic entry ignored\n");
 	else
 		acpi_register_lapic(apic_id, enabled);
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 2eec05b..11544d8 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -383,20 +383,25 @@
 
 static unsigned int reserve_eilvt_offset(int offset, unsigned int new)
 {
-	unsigned int rsvd;			/* 0: uninitialized */
+	unsigned int rsvd, vector;
 
 	if (offset >= APIC_EILVT_NR_MAX)
 		return ~0;
 
-	rsvd = atomic_read(&eilvt_offsets[offset]) & ~APIC_EILVT_MASKED;
+	rsvd = atomic_read(&eilvt_offsets[offset]);
 	do {
-		if (rsvd &&
-		    !eilvt_entry_is_changeable(rsvd, new))
+		vector = rsvd & ~APIC_EILVT_MASKED;	/* 0: unassigned */
+		if (vector && !eilvt_entry_is_changeable(vector, new))
 			/* may not change if vectors are different */
 			return rsvd;
 		rsvd = atomic_cmpxchg(&eilvt_offsets[offset], rsvd, new);
 	} while (rsvd != new);
 
+	rsvd &= ~APIC_EILVT_MASKED;
+	if (rsvd && rsvd != vector)
+		pr_info("LVT offset %d assigned for vector 0x%02x\n",
+			offset, rsvd);
+
 	return new;
 }
 
diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c
index d9ea5f3..899803e 100644
--- a/arch/x86/kernel/apic/apic_numachip.c
+++ b/arch/x86/kernel/apic/apic_numachip.c
@@ -229,11 +229,10 @@
 }
 early_initcall(numachip_system_init);
 
-static int __cpuinit numachip_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+static int numachip_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 {
 	if (!strncmp(oem_id, "NUMASC", 6)) {
 		numachip_system = 1;
-		setup_force_cpu_cap(X86_FEATURE_X2APIC);
 		return 1;
 	}
 
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 6d10a66..e88300d 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -64,9 +64,28 @@
 #include <asm/apic.h>
 
 #define __apicdebuginit(type) static type __init
+
 #define for_each_irq_pin(entry, head) \
 	for (entry = head; entry; entry = entry->next)
 
+static void		__init __ioapic_init_mappings(void);
+
+static unsigned int	__io_apic_read  (unsigned int apic, unsigned int reg);
+static void		__io_apic_write (unsigned int apic, unsigned int reg, unsigned int val);
+static void		__io_apic_modify(unsigned int apic, unsigned int reg, unsigned int val);
+
+static struct io_apic_ops io_apic_ops = {
+	.init	= __ioapic_init_mappings,
+	.read	= __io_apic_read,
+	.write	= __io_apic_write,
+	.modify = __io_apic_modify,
+};
+
+void __init set_io_apic_ops(const struct io_apic_ops *ops)
+{
+	io_apic_ops = *ops;
+}
+
 /*
  *      Is the SiS APIC rmw bug present ?
  *      -1 = don't know, 0 = no, 1 = yes
@@ -294,6 +313,22 @@
 	irq_free_desc(at);
 }
 
+static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg)
+{
+	return io_apic_ops.read(apic, reg);
+}
+
+static inline void io_apic_write(unsigned int apic, unsigned int reg, unsigned int value)
+{
+	io_apic_ops.write(apic, reg, value);
+}
+
+static inline void io_apic_modify(unsigned int apic, unsigned int reg, unsigned int value)
+{
+	io_apic_ops.modify(apic, reg, value);
+}
+
+
 struct io_apic {
 	unsigned int index;
 	unsigned int unused[3];
@@ -314,16 +349,17 @@
 	writel(vector, &io_apic->eoi);
 }
 
-static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg)
+static unsigned int __io_apic_read(unsigned int apic, unsigned int reg)
 {
 	struct io_apic __iomem *io_apic = io_apic_base(apic);
 	writel(reg, &io_apic->index);
 	return readl(&io_apic->data);
 }
 
-static inline void io_apic_write(unsigned int apic, unsigned int reg, unsigned int value)
+static void __io_apic_write(unsigned int apic, unsigned int reg, unsigned int value)
 {
 	struct io_apic __iomem *io_apic = io_apic_base(apic);
+
 	writel(reg, &io_apic->index);
 	writel(value, &io_apic->data);
 }
@@ -334,7 +370,7 @@
  *
  * Older SiS APIC requires we rewrite the index register
  */
-static inline void io_apic_modify(unsigned int apic, unsigned int reg, unsigned int value)
+static void __io_apic_modify(unsigned int apic, unsigned int reg, unsigned int value)
 {
 	struct io_apic __iomem *io_apic = io_apic_base(apic);
 
@@ -377,6 +413,7 @@
 
 	eu.w1 = io_apic_read(apic, 0x10 + 2 * pin);
 	eu.w2 = io_apic_read(apic, 0x11 + 2 * pin);
+
 	return eu.entry;
 }
 
@@ -384,9 +421,11 @@
 {
 	union entry_union eu;
 	unsigned long flags;
+
 	raw_spin_lock_irqsave(&ioapic_lock, flags);
 	eu.entry = __ioapic_read_entry(apic, pin);
 	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
+
 	return eu.entry;
 }
 
@@ -396,8 +435,7 @@
  * the interrupt, and we need to make sure the entry is fully populated
  * before that happens.
  */
-static void
-__ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e)
+static void __ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e)
 {
 	union entry_union eu = {{0, 0}};
 
@@ -409,6 +447,7 @@
 static void ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e)
 {
 	unsigned long flags;
+
 	raw_spin_lock_irqsave(&ioapic_lock, flags);
 	__ioapic_write_entry(apic, pin, e);
 	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
@@ -435,8 +474,7 @@
  * shared ISA-space IRQs, so we have to support them. We are super
  * fast in the common case, and fast for shared ISA-space IRQs.
  */
-static int
-__add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin)
+static int __add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin)
 {
 	struct irq_pin_list **last, *entry;
 
@@ -521,6 +559,7 @@
 	 * a dummy read from the IO-APIC
 	 */
 	struct io_apic __iomem *io_apic;
+
 	io_apic = io_apic_base(entry->apic);
 	readl(&io_apic->data);
 }
@@ -2512,20 +2551,72 @@
 
 atomic_t irq_mis_count;
 
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+static inline bool ioapic_irqd_mask(struct irq_data *data, struct irq_cfg *cfg)
+{
+	/* If we are moving the irq we need to mask it */
+	if (unlikely(irqd_is_setaffinity_pending(data))) {
+		mask_ioapic(cfg);
+		return true;
+	}
+	return false;
+}
+
+static inline void ioapic_irqd_unmask(struct irq_data *data,
+				      struct irq_cfg *cfg, bool masked)
+{
+	if (unlikely(masked)) {
+		/* Only migrate the irq if the ack has been received.
+		 *
+		 * On rare occasions the broadcast level triggered ack gets
+		 * delayed going to ioapics, and if we reprogram the
+		 * vector while Remote IRR is still set the irq will never
+		 * fire again.
+		 *
+		 * To prevent this scenario we read the Remote IRR bit
+		 * of the ioapic.  This has two effects.
+		 * - On any sane system the read of the ioapic will
+		 *   flush writes (and acks) going to the ioapic from
+		 *   this cpu.
+		 * - We get to see if the ACK has actually been delivered.
+		 *
+		 * Based on failed experiments of reprogramming the
+		 * ioapic entry from outside of irq context starting
+		 * with masking the ioapic entry and then polling until
+		 * Remote IRR was clear before reprogramming the
+		 * ioapic I don't trust the Remote IRR bit to be
+		 * completey accurate.
+		 *
+		 * However there appears to be no other way to plug
+		 * this race, so if the Remote IRR bit is not
+		 * accurate and is causing problems then it is a hardware bug
+		 * and you can go talk to the chipset vendor about it.
+		 */
+		if (!io_apic_level_ack_pending(cfg))
+			irq_move_masked_irq(data);
+		unmask_ioapic(cfg);
+	}
+}
+#else
+static inline bool ioapic_irqd_mask(struct irq_data *data, struct irq_cfg *cfg)
+{
+	return false;
+}
+static inline void ioapic_irqd_unmask(struct irq_data *data,
+				      struct irq_cfg *cfg, bool masked)
+{
+}
+#endif
+
 static void ack_apic_level(struct irq_data *data)
 {
 	struct irq_cfg *cfg = data->chip_data;
-	int i, do_unmask_irq = 0, irq = data->irq;
+	int i, irq = data->irq;
 	unsigned long v;
+	bool masked;
 
 	irq_complete_move(cfg);
-#ifdef CONFIG_GENERIC_PENDING_IRQ
-	/* If we are moving the irq we need to mask it */
-	if (unlikely(irqd_is_setaffinity_pending(data))) {
-		do_unmask_irq = 1;
-		mask_ioapic(cfg);
-	}
-#endif
+	masked = ioapic_irqd_mask(data, cfg);
 
 	/*
 	 * It appears there is an erratum which affects at least version 0x11
@@ -2581,38 +2672,7 @@
 		eoi_ioapic_irq(irq, cfg);
 	}
 
-	/* Now we can move and renable the irq */
-	if (unlikely(do_unmask_irq)) {
-		/* Only migrate the irq if the ack has been received.
-		 *
-		 * On rare occasions the broadcast level triggered ack gets
-		 * delayed going to ioapics, and if we reprogram the
-		 * vector while Remote IRR is still set the irq will never
-		 * fire again.
-		 *
-		 * To prevent this scenario we read the Remote IRR bit
-		 * of the ioapic.  This has two effects.
-		 * - On any sane system the read of the ioapic will
-		 *   flush writes (and acks) going to the ioapic from
-		 *   this cpu.
-		 * - We get to see if the ACK has actually been delivered.
-		 *
-		 * Based on failed experiments of reprogramming the
-		 * ioapic entry from outside of irq context starting
-		 * with masking the ioapic entry and then polling until
-		 * Remote IRR was clear before reprogramming the
-		 * ioapic I don't trust the Remote IRR bit to be
-		 * completey accurate.
-		 *
-		 * However there appears to be no other way to plug
-		 * this race, so if the Remote IRR bit is not
-		 * accurate and is causing problems then it is a hardware bug
-		 * and you can go talk to the chipset vendor about it.
-		 */
-		if (!io_apic_level_ack_pending(cfg))
-			irq_move_masked_irq(data);
-		unmask_ioapic(cfg);
-	}
+	ioapic_irqd_unmask(data, cfg, masked);
 }
 
 #ifdef CONFIG_IRQ_REMAP
@@ -3873,6 +3933,11 @@
 
 void __init ioapic_and_gsi_init(void)
 {
+	io_apic_ops.init();
+}
+
+static void __init __ioapic_init_mappings(void)
+{
 	unsigned long ioapic_phys, idx = FIX_IO_APIC_BASE_0;
 	struct resource *ioapic_res;
 	int i;
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index 91937130..48f3103 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -213,7 +213,7 @@
 	.name				= "cluster x2apic",
 	.probe				= x2apic_cluster_probe,
 	.acpi_madt_oem_check		= x2apic_acpi_madt_oem_check,
-	.apic_id_valid			= default_apic_id_valid,
+	.apic_id_valid			= x2apic_apic_id_valid,
 	.apic_id_registered		= x2apic_apic_id_registered,
 
 	.irq_delivery_mode		= dest_LowestPrio,
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index bcd1db6..8a778db 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -119,7 +119,7 @@
 	.name				= "physical x2apic",
 	.probe				= x2apic_phys_probe,
 	.acpi_madt_oem_check		= x2apic_acpi_madt_oem_check,
-	.apic_id_valid			= default_apic_id_valid,
+	.apic_id_valid			= x2apic_apic_id_valid,
 	.apic_id_registered		= x2apic_apic_id_registered,
 
 	.irq_delivery_mode		= dest_Fixed,
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index fc47714..87bfa69 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -266,6 +266,11 @@
 	uv_send_IPI_mask(cpu_online_mask, vector);
 }
 
+static int uv_apic_id_valid(int apicid)
+{
+	return 1;
+}
+
 static int uv_apic_id_registered(void)
 {
 	return 1;
@@ -351,7 +356,7 @@
 	.name				= "UV large system",
 	.probe				= uv_probe,
 	.acpi_madt_oem_check		= uv_acpi_madt_oem_check,
-	.apic_id_valid			= default_apic_id_valid,
+	.apic_id_valid			= uv_apic_id_valid,
 	.apic_id_registered		= uv_apic_id_registered,
 
 	.irq_delivery_mode		= dest_Fixed,
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index 834e897..1b4754f 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -1,6 +1,12 @@
 #include <asm/ia32.h>
 
 #define __SYSCALL_64(nr, sym, compat) [nr] = 1,
+#define __SYSCALL_COMMON(nr, sym, compat) [nr] = 1,
+#ifdef CONFIG_X86_X32_ABI
+# define __SYSCALL_X32(nr, sym, compat) [nr] = 1,
+#else
+# define __SYSCALL_X32(nr, sym, compat) /* nothing */
+#endif
 static char syscalls_64[] = {
 #include <asm/syscalls_64.h>
 };
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index e494774..67e2583 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -999,7 +999,7 @@
 	else
 		printk(KERN_CONT "\n");
 
-	__print_cpu_msr();
+	print_cpu_msr(c);
 }
 
 void __cpuinit print_cpu_msr(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c
index 7928963..a041e09 100644
--- a/arch/x86/kernel/cpu/mtrr/if.c
+++ b/arch/x86/kernel/cpu/mtrr/if.c
@@ -167,6 +167,7 @@
 {
 	int err = 0;
 	mtrr_type type;
+	unsigned long base;
 	unsigned long size;
 	struct mtrr_sentry sentry;
 	struct mtrr_gentry gentry;
@@ -267,14 +268,14 @@
 #endif
 		if (gentry.regnum >= num_var_ranges)
 			return -EINVAL;
-		mtrr_if->get(gentry.regnum, &gentry.base, &size, &type);
+		mtrr_if->get(gentry.regnum, &base, &size, &type);
 
 		/* Hide entries that go above 4GB */
-		if (gentry.base + size - 1 >= (1UL << (8 * sizeof(gentry.size) - PAGE_SHIFT))
+		if (base + size - 1 >= (1UL << (8 * sizeof(gentry.size) - PAGE_SHIFT))
 		    || size >= (1UL << (8 * sizeof(gentry.size) - PAGE_SHIFT)))
 			gentry.base = gentry.size = gentry.type = 0;
 		else {
-			gentry.base <<= PAGE_SHIFT;
+			gentry.base = base << PAGE_SHIFT;
 			gentry.size = size << PAGE_SHIFT;
 			gentry.type = type;
 		}
@@ -321,11 +322,12 @@
 #endif
 		if (gentry.regnum >= num_var_ranges)
 			return -EINVAL;
-		mtrr_if->get(gentry.regnum, &gentry.base, &size, &type);
+		mtrr_if->get(gentry.regnum, &base, &size, &type);
 		/* Hide entries that would overflow */
 		if (size != (__typeof__(gentry.size))size)
 			gentry.base = gentry.size = gentry.type = 0;
 		else {
+			gentry.base = base;
 			gentry.size = size;
 			gentry.type = type;
 		}
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index fa2900c..40883ff 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -29,7 +29,6 @@
 #include <asm/apic.h>
 #include <asm/stacktrace.h>
 #include <asm/nmi.h>
-#include <asm/compat.h>
 #include <asm/smp.h>
 #include <asm/alternative.h>
 #include <asm/timer.h>
@@ -1748,6 +1747,9 @@
 }
 
 #ifdef CONFIG_COMPAT
+
+#include <asm/compat.h>
+
 static inline int
 perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
 {
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 4025fe4..1b81839 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -37,13 +37,16 @@
 			const struct stacktrace_ops *ops,
 			struct thread_info *tinfo, int *graph)
 {
-	struct task_struct *task = tinfo->task;
+	struct task_struct *task;
 	unsigned long ret_addr;
-	int index = task->curr_ret_stack;
+	int index;
 
 	if (addr != (unsigned long)return_to_handler)
 		return;
 
+	task = tinfo->task;
+	index = task->curr_ret_stack;
+
 	if (!task->ret_stack || index < *graph)
 		return;
 
@@ -265,7 +268,7 @@
 #endif
 	printk("\n");
 	if (notify_die(DIE_OOPS, str, regs, err,
-			current->thread.trap_no, SIGSEGV) == NOTIFY_STOP)
+			current->thread.trap_nr, SIGSEGV) == NOTIFY_STOP)
 		return 1;
 
 	show_registers(regs);
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 734ebd1..cdc79b5 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -481,7 +481,12 @@
 	testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
 	jnz tracesys
 system_call_fastpath:
+#if __SYSCALL_MASK == ~0
 	cmpq $__NR_syscall_max,%rax
+#else
+	andl $__SYSCALL_MASK,%eax
+	cmpl $__NR_syscall_max,%eax
+#endif
 	ja badsys
 	movq %r10,%rcx
 	call *sys_call_table(,%rax,8)  # XXX:	 rip relative
@@ -595,7 +600,12 @@
 	 */
 	LOAD_ARGS ARGOFFSET, 1
 	RESTORE_REST
+#if __SYSCALL_MASK == ~0
 	cmpq $__NR_syscall_max,%rax
+#else
+	andl $__SYSCALL_MASK,%eax
+	cmpl $__NR_syscall_max,%eax
+#endif
 	ja   int_ret_from_sys_call	/* RAX(%rsp) set to -ENOSYS above */
 	movq %r10,%rcx	/* fixup for C */
 	call *sys_call_table(,%rax,8)
@@ -735,6 +745,40 @@
 	CFI_ENDPROC
 END(stub_rt_sigreturn)
 
+#ifdef CONFIG_X86_X32_ABI
+	PTREGSCALL stub_x32_sigaltstack, sys32_sigaltstack, %rdx
+
+ENTRY(stub_x32_rt_sigreturn)
+	CFI_STARTPROC
+	addq $8, %rsp
+	PARTIAL_FRAME 0
+	SAVE_REST
+	movq %rsp,%rdi
+	FIXUP_TOP_OF_STACK %r11
+	call sys32_x32_rt_sigreturn
+	movq %rax,RAX(%rsp) # fixme, this could be done at the higher layer
+	RESTORE_REST
+	jmp int_ret_from_sys_call
+	CFI_ENDPROC
+END(stub_x32_rt_sigreturn)
+
+ENTRY(stub_x32_execve)
+	CFI_STARTPROC
+	addq $8, %rsp
+	PARTIAL_FRAME 0
+	SAVE_REST
+	FIXUP_TOP_OF_STACK %r11
+	movq %rsp, %rcx
+	call sys32_execve
+	RESTORE_TOP_OF_STACK %r11
+	movq %rax,RAX(%rsp)
+	RESTORE_REST
+	jmp int_ret_from_sys_call
+	CFI_ENDPROC
+END(stub_x32_execve)
+
+#endif
+
 /*
  * Build the entry stubs and pointer table with some assembler magic.
  * We pack 7 stubs into a single 32-byte chunk, which will fit in a
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index 6d5fc8c..252981a 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -60,7 +60,7 @@
 	outb(0, 0xF0);
 	if (ignore_fpu_irq || !boot_cpu_data.hard_math)
 		return IRQ_NONE;
-	math_error(get_irq_regs(), 0, 16);
+	math_error(get_irq_regs(), 0, X86_TRAP_MF);
 	return IRQ_HANDLED;
 }
 
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 9b24f36..a33afaa 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -12,6 +12,9 @@
 #include <linux/user-return-notifier.h>
 #include <linux/dmi.h>
 #include <linux/utsname.h>
+#include <linux/stackprotector.h>
+#include <linux/tick.h>
+#include <linux/cpuidle.h>
 #include <trace/events/power.h>
 #include <linux/hw_breakpoint.h>
 #include <asm/cpu.h>
@@ -22,6 +25,24 @@
 #include <asm/i387.h>
 #include <asm/fpu-internal.h>
 #include <asm/debugreg.h>
+#include <asm/nmi.h>
+
+#ifdef CONFIG_X86_64
+static DEFINE_PER_CPU(unsigned char, is_idle);
+static ATOMIC_NOTIFIER_HEAD(idle_notifier);
+
+void idle_notifier_register(struct notifier_block *n)
+{
+	atomic_notifier_chain_register(&idle_notifier, n);
+}
+EXPORT_SYMBOL_GPL(idle_notifier_register);
+
+void idle_notifier_unregister(struct notifier_block *n)
+{
+	atomic_notifier_chain_unregister(&idle_notifier, n);
+}
+EXPORT_SYMBOL_GPL(idle_notifier_unregister);
+#endif
 
 struct kmem_cache *task_xstate_cachep;
 EXPORT_SYMBOL_GPL(task_xstate_cachep);
@@ -370,6 +391,99 @@
 }
 #endif
 
+#ifndef CONFIG_SMP
+static inline void play_dead(void)
+{
+	BUG();
+}
+#endif
+
+#ifdef CONFIG_X86_64
+void enter_idle(void)
+{
+	percpu_write(is_idle, 1);
+	atomic_notifier_call_chain(&idle_notifier, IDLE_START, NULL);
+}
+
+static void __exit_idle(void)
+{
+	if (x86_test_and_clear_bit_percpu(0, is_idle) == 0)
+		return;
+	atomic_notifier_call_chain(&idle_notifier, IDLE_END, NULL);
+}
+
+/* Called from interrupts to signify idle end */
+void exit_idle(void)
+{
+	/* idle loop has pid 0 */
+	if (current->pid)
+		return;
+	__exit_idle();
+}
+#endif
+
+/*
+ * The idle thread. There's no useful work to be
+ * done, so just try to conserve power and have a
+ * low exit latency (ie sit in a loop waiting for
+ * somebody to say that they'd like to reschedule)
+ */
+void cpu_idle(void)
+{
+	/*
+	 * If we're the non-boot CPU, nothing set the stack canary up
+	 * for us.  CPU0 already has it initialized but no harm in
+	 * doing it again.  This is a good place for updating it, as
+	 * we wont ever return from this function (so the invalid
+	 * canaries already on the stack wont ever trigger).
+	 */
+	boot_init_stack_canary();
+	current_thread_info()->status |= TS_POLLING;
+
+	while (1) {
+		tick_nohz_idle_enter();
+
+		while (!need_resched()) {
+			rmb();
+
+			if (cpu_is_offline(smp_processor_id()))
+				play_dead();
+
+			/*
+			 * Idle routines should keep interrupts disabled
+			 * from here on, until they go to idle.
+			 * Otherwise, idle callbacks can misfire.
+			 */
+			local_touch_nmi();
+			local_irq_disable();
+
+			enter_idle();
+
+			/* Don't trace irqs off for idle */
+			stop_critical_timings();
+
+			/* enter_idle() needs rcu for notifiers */
+			rcu_idle_enter();
+
+			if (cpuidle_idle_call())
+				pm_idle();
+
+			rcu_idle_exit();
+			start_critical_timings();
+
+			/* In many cases the interrupt that ended idle
+			   has already called exit_idle. But some idle
+			   loops can be woken up without interrupt. */
+			__exit_idle();
+		}
+
+		tick_nohz_idle_exit();
+		preempt_enable_no_resched();
+		schedule();
+		preempt_disable();
+	}
+}
+
 /*
  * We use this if we don't have any better
  * idle routine..
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index aae4f4b..ae68473 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -9,7 +9,6 @@
  * This file handles the architecture-dependent parts of process handling..
  */
 
-#include <linux/stackprotector.h>
 #include <linux/cpu.h>
 #include <linux/errno.h>
 #include <linux/sched.h>
@@ -31,14 +30,12 @@
 #include <linux/kallsyms.h>
 #include <linux/ptrace.h>
 #include <linux/personality.h>
-#include <linux/tick.h>
 #include <linux/percpu.h>
 #include <linux/prctl.h>
 #include <linux/ftrace.h>
 #include <linux/uaccess.h>
 #include <linux/io.h>
 #include <linux/kdebug.h>
-#include <linux/cpuidle.h>
 
 #include <asm/pgtable.h>
 #include <asm/ldt.h>
@@ -57,7 +54,6 @@
 #include <asm/idle.h>
 #include <asm/syscalls.h>
 #include <asm/debugreg.h>
-#include <asm/nmi.h>
 #include <asm/switch_to.h>
 
 asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
@@ -70,60 +66,6 @@
 	return ((unsigned long *)tsk->thread.sp)[3];
 }
 
-#ifndef CONFIG_SMP
-static inline void play_dead(void)
-{
-	BUG();
-}
-#endif
-
-/*
- * The idle thread. There's no useful work to be
- * done, so just try to conserve power and have a
- * low exit latency (ie sit in a loop waiting for
- * somebody to say that they'd like to reschedule)
- */
-void cpu_idle(void)
-{
-	int cpu = smp_processor_id();
-
-	/*
-	 * If we're the non-boot CPU, nothing set the stack canary up
-	 * for us.  CPU0 already has it initialized but no harm in
-	 * doing it again.  This is a good place for updating it, as
-	 * we wont ever return from this function (so the invalid
-	 * canaries already on the stack wont ever trigger).
-	 */
-	boot_init_stack_canary();
-
-	current_thread_info()->status |= TS_POLLING;
-
-	/* endless idle loop with no priority at all */
-	while (1) {
-		tick_nohz_idle_enter();
-		rcu_idle_enter();
-		while (!need_resched()) {
-
-			check_pgt_cache();
-			rmb();
-
-			if (cpu_is_offline(cpu))
-				play_dead();
-
-			local_touch_nmi();
-			local_irq_disable();
-			/* Don't trace irqs off for idle */
-			stop_critical_timings();
-			if (cpuidle_idle_call())
-				pm_idle();
-			start_critical_timings();
-		}
-		rcu_idle_exit();
-		tick_nohz_idle_exit();
-		schedule_preempt_disabled();
-	}
-}
-
 void __show_regs(struct pt_regs *regs, int all)
 {
 	unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L;
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 61270e8..733ca39 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -14,7 +14,6 @@
  * This file handles the architecture-dependent parts of process handling..
  */
 
-#include <linux/stackprotector.h>
 #include <linux/cpu.h>
 #include <linux/errno.h>
 #include <linux/sched.h>
@@ -32,12 +31,10 @@
 #include <linux/notifier.h>
 #include <linux/kprobes.h>
 #include <linux/kdebug.h>
-#include <linux/tick.h>
 #include <linux/prctl.h>
 #include <linux/uaccess.h>
 #include <linux/io.h>
 #include <linux/ftrace.h>
-#include <linux/cpuidle.h>
 
 #include <asm/pgtable.h>
 #include <asm/processor.h>
@@ -51,115 +48,11 @@
 #include <asm/idle.h>
 #include <asm/syscalls.h>
 #include <asm/debugreg.h>
-#include <asm/nmi.h>
 #include <asm/switch_to.h>
 
 asmlinkage extern void ret_from_fork(void);
 
 DEFINE_PER_CPU(unsigned long, old_rsp);
-static DEFINE_PER_CPU(unsigned char, is_idle);
-
-static ATOMIC_NOTIFIER_HEAD(idle_notifier);
-
-void idle_notifier_register(struct notifier_block *n)
-{
-	atomic_notifier_chain_register(&idle_notifier, n);
-}
-EXPORT_SYMBOL_GPL(idle_notifier_register);
-
-void idle_notifier_unregister(struct notifier_block *n)
-{
-	atomic_notifier_chain_unregister(&idle_notifier, n);
-}
-EXPORT_SYMBOL_GPL(idle_notifier_unregister);
-
-void enter_idle(void)
-{
-	percpu_write(is_idle, 1);
-	atomic_notifier_call_chain(&idle_notifier, IDLE_START, NULL);
-}
-
-static void __exit_idle(void)
-{
-	if (x86_test_and_clear_bit_percpu(0, is_idle) == 0)
-		return;
-	atomic_notifier_call_chain(&idle_notifier, IDLE_END, NULL);
-}
-
-/* Called from interrupts to signify idle end */
-void exit_idle(void)
-{
-	/* idle loop has pid 0 */
-	if (current->pid)
-		return;
-	__exit_idle();
-}
-
-#ifndef CONFIG_SMP
-static inline void play_dead(void)
-{
-	BUG();
-}
-#endif
-
-/*
- * The idle thread. There's no useful work to be
- * done, so just try to conserve power and have a
- * low exit latency (ie sit in a loop waiting for
- * somebody to say that they'd like to reschedule)
- */
-void cpu_idle(void)
-{
-	current_thread_info()->status |= TS_POLLING;
-
-	/*
-	 * If we're the non-boot CPU, nothing set the stack canary up
-	 * for us.  CPU0 already has it initialized but no harm in
-	 * doing it again.  This is a good place for updating it, as
-	 * we wont ever return from this function (so the invalid
-	 * canaries already on the stack wont ever trigger).
-	 */
-	boot_init_stack_canary();
-
-	/* endless idle loop with no priority at all */
-	while (1) {
-		tick_nohz_idle_enter();
-		while (!need_resched()) {
-
-			rmb();
-
-			if (cpu_is_offline(smp_processor_id()))
-				play_dead();
-			/*
-			 * Idle routines should keep interrupts disabled
-			 * from here on, until they go to idle.
-			 * Otherwise, idle callbacks can misfire.
-			 */
-			local_touch_nmi();
-			local_irq_disable();
-			enter_idle();
-			/* Don't trace irqs off for idle */
-			stop_critical_timings();
-
-			/* enter_idle() needs rcu for notifiers */
-			rcu_idle_enter();
-
-			if (cpuidle_idle_call())
-				pm_idle();
-
-			rcu_idle_exit();
-			start_critical_timings();
-
-			/* In many cases the interrupt that ended idle
-			   has already called exit_idle. But some idle
-			   loops can be woken up without interrupt. */
-			__exit_idle();
-		}
-
-		tick_nohz_idle_exit();
-		schedule_preempt_disabled();
-	}
-}
 
 /* Prints also some state that isn't saved in the pt_regs */
 void __show_regs(struct pt_regs *regs, int all)
@@ -365,7 +258,9 @@
 void start_thread_ia32(struct pt_regs *regs, u32 new_ip, u32 new_sp)
 {
 	start_thread_common(regs, new_ip, new_sp,
-			    __USER32_CS, __USER32_DS, __USER32_DS);
+			    test_thread_flag(TIF_X32)
+			    ? __USER_CS : __USER32_CS,
+			    __USER_DS, __USER_DS);
 }
 #endif
 
@@ -488,6 +383,8 @@
 
 	/* Make sure to be in 64bit mode */
 	clear_thread_flag(TIF_IA32);
+	clear_thread_flag(TIF_ADDR32);
+	clear_thread_flag(TIF_X32);
 
 	/* Ensure the corresponding mm is not marked. */
 	if (current->mm)
@@ -500,20 +397,31 @@
 	current->personality &= ~READ_IMPLIES_EXEC;
 }
 
-void set_personality_ia32(void)
+void set_personality_ia32(bool x32)
 {
 	/* inherit personality from parent */
 
 	/* Make sure to be in 32bit mode */
-	set_thread_flag(TIF_IA32);
-	current->personality |= force_personality32;
+	set_thread_flag(TIF_ADDR32);
 
 	/* Mark the associated mm as containing 32-bit tasks. */
 	if (current->mm)
 		current->mm->context.ia32_compat = 1;
 
-	/* Prepare the first "return" to user space */
-	current_thread_info()->status |= TS_COMPAT;
+	if (x32) {
+		clear_thread_flag(TIF_IA32);
+		set_thread_flag(TIF_X32);
+		current->personality &= ~READ_IMPLIES_EXEC;
+		/* is_compat_task() uses the presence of the x32
+		   syscall bit flag to determine compat status */
+		current_thread_info()->status &= ~TS_COMPAT;
+	} else {
+		set_thread_flag(TIF_IA32);
+		clear_thread_flag(TIF_X32);
+		current->personality |= force_personality32;
+		/* Prepare the first "return" to user space */
+		current_thread_info()->status |= TS_COMPAT;
+	}
 }
 
 unsigned long get_wchan(struct task_struct *p)
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 8a634c8..685845c 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -33,6 +33,7 @@
 #include <asm/prctl.h>
 #include <asm/proto.h>
 #include <asm/hw_breakpoint.h>
+#include <asm/traps.h>
 
 #include "tls.h"
 
@@ -1130,6 +1131,100 @@
 	return ret;
 }
 
+#ifdef CONFIG_X86_X32_ABI
+static long x32_arch_ptrace(struct task_struct *child,
+			    compat_long_t request, compat_ulong_t caddr,
+			    compat_ulong_t cdata)
+{
+	unsigned long addr = caddr;
+	unsigned long data = cdata;
+	void __user *datap = compat_ptr(data);
+	int ret;
+
+	switch (request) {
+	/* Read 32bits at location addr in the USER area.  Only allow
+	   to return the lower 32bits of segment and debug registers.  */
+	case PTRACE_PEEKUSR: {
+		u32 tmp;
+
+		ret = -EIO;
+		if ((addr & (sizeof(data) - 1)) || addr >= sizeof(struct user) ||
+		    addr < offsetof(struct user_regs_struct, cs))
+			break;
+
+		tmp = 0;  /* Default return condition */
+		if (addr < sizeof(struct user_regs_struct))
+			tmp = getreg(child, addr);
+		else if (addr >= offsetof(struct user, u_debugreg[0]) &&
+			 addr <= offsetof(struct user, u_debugreg[7])) {
+			addr -= offsetof(struct user, u_debugreg[0]);
+			tmp = ptrace_get_debugreg(child, addr / sizeof(data));
+		}
+		ret = put_user(tmp, (__u32 __user *)datap);
+		break;
+	}
+
+	/* Write the word at location addr in the USER area.  Only allow
+	   to update segment and debug registers with the upper 32bits
+	   zero-extended. */
+	case PTRACE_POKEUSR:
+		ret = -EIO;
+		if ((addr & (sizeof(data) - 1)) || addr >= sizeof(struct user) ||
+		    addr < offsetof(struct user_regs_struct, cs))
+			break;
+
+		if (addr < sizeof(struct user_regs_struct))
+			ret = putreg(child, addr, data);
+		else if (addr >= offsetof(struct user, u_debugreg[0]) &&
+			 addr <= offsetof(struct user, u_debugreg[7])) {
+			addr -= offsetof(struct user, u_debugreg[0]);
+			ret = ptrace_set_debugreg(child,
+						  addr / sizeof(data), data);
+		}
+		break;
+
+	case PTRACE_GETREGS:	/* Get all gp regs from the child. */
+		return copy_regset_to_user(child,
+					   task_user_regset_view(current),
+					   REGSET_GENERAL,
+					   0, sizeof(struct user_regs_struct),
+					   datap);
+
+	case PTRACE_SETREGS:	/* Set all gp regs in the child. */
+		return copy_regset_from_user(child,
+					     task_user_regset_view(current),
+					     REGSET_GENERAL,
+					     0, sizeof(struct user_regs_struct),
+					     datap);
+
+	case PTRACE_GETFPREGS:	/* Get the child FPU state. */
+		return copy_regset_to_user(child,
+					   task_user_regset_view(current),
+					   REGSET_FP,
+					   0, sizeof(struct user_i387_struct),
+					   datap);
+
+	case PTRACE_SETFPREGS:	/* Set the child FPU state. */
+		return copy_regset_from_user(child,
+					     task_user_regset_view(current),
+					     REGSET_FP,
+					     0, sizeof(struct user_i387_struct),
+					     datap);
+
+		/* normal 64bit interface to access TLS data.
+		   Works just like arch_prctl, except that the arguments
+		   are reversed. */
+	case PTRACE_ARCH_PRCTL:
+		return do_arch_prctl(child, data, addr);
+
+	default:
+		return compat_ptrace_request(child, request, addr, data);
+	}
+
+	return ret;
+}
+#endif
+
 long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 			compat_ulong_t caddr, compat_ulong_t cdata)
 {
@@ -1139,6 +1234,11 @@
 	int ret;
 	__u32 val;
 
+#ifdef CONFIG_X86_X32_ABI
+	if (!is_ia32_task())
+		return x32_arch_ptrace(child, request, caddr, cdata);
+#endif
+
 	switch (request) {
 	case PTRACE_PEEKUSR:
 		ret = getreg32(child, addr, &val);
@@ -1326,7 +1426,7 @@
 				int error_code, int si_code,
 				struct siginfo *info)
 {
-	tsk->thread.trap_no = 1;
+	tsk->thread.trap_nr = X86_TRAP_DB;
 	tsk->thread.error_code = error_code;
 
 	memset(info, 0, sizeof(*info));
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 25edcfc..115eac4 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -10,10 +10,8 @@
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/kernel.h>
-#include <linux/signal.h>
 #include <linux/errno.h>
 #include <linux/wait.h>
-#include <linux/ptrace.h>
 #include <linux/tracehook.h>
 #include <linux/unistd.h>
 #include <linux/stddef.h>
@@ -27,10 +25,12 @@
 #include <asm/fpu-internal.h>
 #include <asm/vdso.h>
 #include <asm/mce.h>
+#include <asm/sighandling.h>
 
 #ifdef CONFIG_X86_64
 #include <asm/proto.h>
 #include <asm/ia32_unistd.h>
+#include <asm/sys_ia32.h>
 #endif /* CONFIG_X86_64 */
 
 #include <asm/syscall.h>
@@ -38,13 +38,6 @@
 
 #include <asm/sigframe.h>
 
-#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
-
-#define __FIX_EFLAGS	(X86_EFLAGS_AC | X86_EFLAGS_OF | \
-			 X86_EFLAGS_DF | X86_EFLAGS_TF | X86_EFLAGS_SF | \
-			 X86_EFLAGS_ZF | X86_EFLAGS_AF | X86_EFLAGS_PF | \
-			 X86_EFLAGS_CF)
-
 #ifdef CONFIG_X86_32
 # define FIX_EFLAGS	(__FIX_EFLAGS | X86_EFLAGS_RF)
 #else
@@ -69,9 +62,8 @@
 	regs->seg = GET_SEG(seg) | 3;			\
 } while (0)
 
-static int
-restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
-		   unsigned long *pax)
+int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
+		       unsigned long *pax)
 {
 	void __user *buf;
 	unsigned int tmpflags;
@@ -126,9 +118,8 @@
 	return err;
 }
 
-static int
-setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate,
-		 struct pt_regs *regs, unsigned long mask)
+int setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate,
+		     struct pt_regs *regs, unsigned long mask)
 {
 	int err = 0;
 
@@ -160,7 +151,7 @@
 		put_user_ex(regs->r15, &sc->r15);
 #endif /* CONFIG_X86_64 */
 
-		put_user_ex(current->thread.trap_no, &sc->trapno);
+		put_user_ex(current->thread.trap_nr, &sc->trapno);
 		put_user_ex(current->thread.error_code, &sc->err);
 		put_user_ex(regs->ip, &sc->ip);
 #ifdef CONFIG_X86_32
@@ -643,6 +634,16 @@
 #define is_ia32	0
 #endif /* CONFIG_IA32_EMULATION */
 
+#ifdef CONFIG_X86_X32_ABI
+#define is_x32	test_thread_flag(TIF_X32)
+
+static int x32_setup_rt_frame(int sig, struct k_sigaction *ka,
+			      siginfo_t *info, compat_sigset_t *set,
+			      struct pt_regs *regs);
+#else /* !CONFIG_X86_X32_ABI */
+#define is_x32	0
+#endif /* CONFIG_X86_X32_ABI */
+
 int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 		sigset_t *set, struct pt_regs *regs);
 int ia32_setup_frame(int sig, struct k_sigaction *ka,
@@ -667,8 +668,14 @@
 			ret = ia32_setup_rt_frame(usig, ka, info, set, regs);
 		else
 			ret = ia32_setup_frame(usig, ka, set, regs);
-	} else
+#ifdef CONFIG_X86_X32_ABI
+	} else if (is_x32) {
+		ret = x32_setup_rt_frame(usig, ka, info,
+					 (compat_sigset_t *)set, regs);
+#endif
+	} else {
 		ret = __setup_rt_frame(sig, ka, info, set, regs);
+	}
 
 	if (ret) {
 		force_sigsegv(sig, current);
@@ -851,3 +858,102 @@
 
 	force_sig(SIGSEGV, me);
 }
+
+#ifdef CONFIG_X86_X32_ABI
+static int x32_setup_rt_frame(int sig, struct k_sigaction *ka,
+			      siginfo_t *info, compat_sigset_t *set,
+			      struct pt_regs *regs)
+{
+	struct rt_sigframe_x32 __user *frame;
+	void __user *restorer;
+	int err = 0;
+	void __user *fpstate = NULL;
+
+	frame = get_sigframe(ka, regs, sizeof(*frame), &fpstate);
+
+	if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
+		return -EFAULT;
+
+	if (ka->sa.sa_flags & SA_SIGINFO) {
+		if (copy_siginfo_to_user32(&frame->info, info))
+			return -EFAULT;
+	}
+
+	put_user_try {
+		/* Create the ucontext.  */
+		if (cpu_has_xsave)
+			put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags);
+		else
+			put_user_ex(0, &frame->uc.uc_flags);
+		put_user_ex(0, &frame->uc.uc_link);
+		put_user_ex(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
+		put_user_ex(sas_ss_flags(regs->sp),
+			    &frame->uc.uc_stack.ss_flags);
+		put_user_ex(current->sas_ss_size, &frame->uc.uc_stack.ss_size);
+		put_user_ex(0, &frame->uc.uc__pad0);
+		err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate,
+					regs, set->sig[0]);
+		err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
+
+		if (ka->sa.sa_flags & SA_RESTORER) {
+			restorer = ka->sa.sa_restorer;
+		} else {
+			/* could use a vstub here */
+			restorer = NULL;
+			err |= -EFAULT;
+		}
+		put_user_ex(restorer, &frame->pretcode);
+	} put_user_catch(err);
+
+	if (err)
+		return -EFAULT;
+
+	/* Set up registers for signal handler */
+	regs->sp = (unsigned long) frame;
+	regs->ip = (unsigned long) ka->sa.sa_handler;
+
+	/* We use the x32 calling convention here... */
+	regs->di = sig;
+	regs->si = (unsigned long) &frame->info;
+	regs->dx = (unsigned long) &frame->uc;
+
+	loadsegment(ds, __USER_DS);
+	loadsegment(es, __USER_DS);
+
+	regs->cs = __USER_CS;
+	regs->ss = __USER_DS;
+
+	return 0;
+}
+
+asmlinkage long sys32_x32_rt_sigreturn(struct pt_regs *regs)
+{
+	struct rt_sigframe_x32 __user *frame;
+	sigset_t set;
+	unsigned long ax;
+	struct pt_regs tregs;
+
+	frame = (struct rt_sigframe_x32 __user *)(regs->sp - 8);
+
+	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
+		goto badframe;
+	if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
+		goto badframe;
+
+	sigdelsetmask(&set, ~_BLOCKABLE);
+	set_current_blocked(&set);
+
+	if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &ax))
+		goto badframe;
+
+	tregs = *regs;
+	if (sys32_sigaltstack(&frame->uc.uc_stack, NULL, &tregs) == -EFAULT)
+		goto badframe;
+
+	return ax;
+
+badframe:
+	signal_fault(regs, frame, "x32 rt_sigreturn");
+	return 0;
+}
+#endif
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 5104a2b..ce13315 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -219,14 +219,9 @@
 	 * Update loops_per_jiffy in cpu_data. Previous call to
 	 * smp_store_cpu_info() stored a value that is close but not as
 	 * accurate as the value just calculated.
-	 *
-	 * Need to enable IRQs because it can take longer and then
-	 * the NMI watchdog might kill us.
 	 */
-	local_irq_enable();
 	calibrate_delay();
 	cpu_data(cpuid).loops_per_jiffy = loops_per_jiffy;
-	local_irq_disable();
 	pr_debug("Stack at about %p\n", &cpuid);
 
 	/*
diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c
index ef59642..b4d3c39 100644
--- a/arch/x86/kernel/sys_x86_64.c
+++ b/arch/x86/kernel/sys_x86_64.c
@@ -98,7 +98,7 @@
 static void find_start_end(unsigned long flags, unsigned long *begin,
 			   unsigned long *end)
 {
-	if (!test_thread_flag(TIF_IA32) && (flags & MAP_32BIT)) {
+	if (!test_thread_flag(TIF_ADDR32) && (flags & MAP_32BIT)) {
 		unsigned long new_begin;
 		/* This is usually used needed to map code in small
 		   model, so it needs to be in the first 31bit. Limit
@@ -144,7 +144,7 @@
 		    (!vma || addr + len <= vma->vm_start))
 			return addr;
 	}
-	if (((flags & MAP_32BIT) || test_thread_flag(TIF_IA32))
+	if (((flags & MAP_32BIT) || test_thread_flag(TIF_ADDR32))
 	    && len <= mm->cached_hole_size) {
 		mm->cached_hole_size = 0;
 		mm->free_area_cache = begin;
@@ -205,7 +205,7 @@
 		return addr;
 
 	/* for MAP_32BIT mappings we force the legact mmap base */
-	if (!test_thread_flag(TIF_IA32) && (flags & MAP_32BIT))
+	if (!test_thread_flag(TIF_ADDR32) && (flags & MAP_32BIT))
 		goto bottomup;
 
 	/* requesting a specific address */
diff --git a/arch/x86/kernel/syscall_64.c b/arch/x86/kernel/syscall_64.c
index 7ac7943..5c7f8c2 100644
--- a/arch/x86/kernel/syscall_64.c
+++ b/arch/x86/kernel/syscall_64.c
@@ -5,6 +5,14 @@
 #include <linux/cache.h>
 #include <asm/asm-offsets.h>
 
+#define __SYSCALL_COMMON(nr, sym, compat) __SYSCALL_64(nr, sym, compat)
+
+#ifdef CONFIG_X86_X32_ABI
+# define __SYSCALL_X32(nr, sym, compat) __SYSCALL_64(nr, sym, compat)
+#else
+# define __SYSCALL_X32(nr, sym, compat) /* nothing */
+#endif
+
 #define __SYSCALL_64(nr, sym, compat) extern asmlinkage void sym(void) ;
 #include <asm/syscalls_64.h>
 #undef __SYSCALL_64
diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c
index 73920e4..9d9d2f9 100644
--- a/arch/x86/kernel/tls.c
+++ b/arch/x86/kernel/tls.c
@@ -162,7 +162,7 @@
 {
 	const struct desc_struct *tls;
 
-	if (pos > GDT_ENTRY_TLS_ENTRIES * sizeof(struct user_desc) ||
+	if (pos >= GDT_ENTRY_TLS_ENTRIES * sizeof(struct user_desc) ||
 	    (pos % sizeof(struct user_desc)) != 0 ||
 	    (count % sizeof(struct user_desc)) != 0)
 		return -EINVAL;
@@ -197,7 +197,7 @@
 	struct user_desc infobuf[GDT_ENTRY_TLS_ENTRIES];
 	const struct user_desc *info;
 
-	if (pos > GDT_ENTRY_TLS_ENTRIES * sizeof(struct user_desc) ||
+	if (pos >= GDT_ENTRY_TLS_ENTRIES * sizeof(struct user_desc) ||
 	    (pos % sizeof(struct user_desc)) != 0 ||
 	    (count % sizeof(struct user_desc)) != 0)
 		return -EINVAL;
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 860f126..ff9281f1 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -119,7 +119,7 @@
 		 * traps 0, 1, 3, 4, and 5 should be forwarded to vm86.
 		 * On nmi (interrupt 2), do_trap should not be called.
 		 */
-		if (trapnr < 6)
+		if (trapnr < X86_TRAP_UD)
 			goto vm86_trap;
 		goto trap_signal;
 	}
@@ -132,7 +132,7 @@
 trap_signal:
 #endif
 	/*
-	 * We want error_code and trap_no set for userspace faults and
+	 * We want error_code and trap_nr set for userspace faults and
 	 * kernelspace faults which result in die(), but not
 	 * kernelspace faults which are fixed up.  die() gives the
 	 * process no chance to handle the signal and notice the
@@ -141,7 +141,7 @@
 	 * delivered, faults.  See also do_general_protection below.
 	 */
 	tsk->thread.error_code = error_code;
-	tsk->thread.trap_no = trapnr;
+	tsk->thread.trap_nr = trapnr;
 
 #ifdef CONFIG_X86_64
 	if (show_unhandled_signals && unhandled_signal(tsk, signr) &&
@@ -164,7 +164,7 @@
 kernel_trap:
 	if (!fixup_exception(regs)) {
 		tsk->thread.error_code = error_code;
-		tsk->thread.trap_no = trapnr;
+		tsk->thread.trap_nr = trapnr;
 		die(str, regs, error_code);
 	}
 	return;
@@ -203,27 +203,31 @@
 	do_trap(trapnr, signr, str, regs, error_code, &info);		\
 }
 
-DO_ERROR_INFO(0, SIGFPE, "divide error", divide_error, FPE_INTDIV, regs->ip)
-DO_ERROR(4, SIGSEGV, "overflow", overflow)
-DO_ERROR(5, SIGSEGV, "bounds", bounds)
-DO_ERROR_INFO(6, SIGILL, "invalid opcode", invalid_op, ILL_ILLOPN, regs->ip)
-DO_ERROR(9, SIGFPE, "coprocessor segment overrun", coprocessor_segment_overrun)
-DO_ERROR(10, SIGSEGV, "invalid TSS", invalid_TSS)
-DO_ERROR(11, SIGBUS, "segment not present", segment_not_present)
+DO_ERROR_INFO(X86_TRAP_DE, SIGFPE, "divide error", divide_error, FPE_INTDIV,
+		regs->ip)
+DO_ERROR(X86_TRAP_OF, SIGSEGV, "overflow", overflow)
+DO_ERROR(X86_TRAP_BR, SIGSEGV, "bounds", bounds)
+DO_ERROR_INFO(X86_TRAP_UD, SIGILL, "invalid opcode", invalid_op, ILL_ILLOPN,
+		regs->ip)
+DO_ERROR(X86_TRAP_OLD_MF, SIGFPE, "coprocessor segment overrun",
+		coprocessor_segment_overrun)
+DO_ERROR(X86_TRAP_TS, SIGSEGV, "invalid TSS", invalid_TSS)
+DO_ERROR(X86_TRAP_NP, SIGBUS, "segment not present", segment_not_present)
 #ifdef CONFIG_X86_32
-DO_ERROR(12, SIGBUS, "stack segment", stack_segment)
+DO_ERROR(X86_TRAP_SS, SIGBUS, "stack segment", stack_segment)
 #endif
-DO_ERROR_INFO(17, SIGBUS, "alignment check", alignment_check, BUS_ADRALN, 0)
+DO_ERROR_INFO(X86_TRAP_AC, SIGBUS, "alignment check", alignment_check,
+		BUS_ADRALN, 0)
 
 #ifdef CONFIG_X86_64
 /* Runs on IST stack */
 dotraplinkage void do_stack_segment(struct pt_regs *regs, long error_code)
 {
 	if (notify_die(DIE_TRAP, "stack segment", regs, error_code,
-			12, SIGBUS) == NOTIFY_STOP)
+			X86_TRAP_SS, SIGBUS) == NOTIFY_STOP)
 		return;
 	preempt_conditional_sti(regs);
-	do_trap(12, SIGBUS, "stack segment", regs, error_code, NULL);
+	do_trap(X86_TRAP_SS, SIGBUS, "stack segment", regs, error_code, NULL);
 	preempt_conditional_cli(regs);
 }
 
@@ -233,10 +237,10 @@
 	struct task_struct *tsk = current;
 
 	/* Return not checked because double check cannot be ignored */
-	notify_die(DIE_TRAP, str, regs, error_code, 8, SIGSEGV);
+	notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV);
 
 	tsk->thread.error_code = error_code;
-	tsk->thread.trap_no = 8;
+	tsk->thread.trap_nr = X86_TRAP_DF;
 
 	/*
 	 * This is always a kernel trap and never fixable (and thus must
@@ -264,7 +268,7 @@
 		goto gp_in_kernel;
 
 	tsk->thread.error_code = error_code;
-	tsk->thread.trap_no = 13;
+	tsk->thread.trap_nr = X86_TRAP_GP;
 
 	if (show_unhandled_signals && unhandled_signal(tsk, SIGSEGV) &&
 			printk_ratelimit()) {
@@ -291,9 +295,9 @@
 		return;
 
 	tsk->thread.error_code = error_code;
-	tsk->thread.trap_no = 13;
-	if (notify_die(DIE_GPF, "general protection fault", regs,
-				error_code, 13, SIGSEGV) == NOTIFY_STOP)
+	tsk->thread.trap_nr = X86_TRAP_GP;
+	if (notify_die(DIE_GPF, "general protection fault", regs, error_code,
+			X86_TRAP_GP, SIGSEGV) == NOTIFY_STOP)
 		return;
 	die("general protection fault", regs, error_code);
 }
@@ -302,13 +306,13 @@
 dotraplinkage void __kprobes do_int3(struct pt_regs *regs, long error_code)
 {
 #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP
-	if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, 3, SIGTRAP)
-			== NOTIFY_STOP)
+	if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP,
+				SIGTRAP) == NOTIFY_STOP)
 		return;
 #endif /* CONFIG_KGDB_LOW_LEVEL_TRAP */
 
-	if (notify_die(DIE_INT3, "int3", regs, error_code, 3, SIGTRAP)
-			== NOTIFY_STOP)
+	if (notify_die(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP,
+			SIGTRAP) == NOTIFY_STOP)
 		return;
 
 	/*
@@ -317,7 +321,7 @@
 	 */
 	debug_stack_usage_inc();
 	preempt_conditional_sti(regs);
-	do_trap(3, SIGTRAP, "int3", regs, error_code, NULL);
+	do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, NULL);
 	preempt_conditional_cli(regs);
 	debug_stack_usage_dec();
 }
@@ -422,8 +426,8 @@
 	preempt_conditional_sti(regs);
 
 	if (regs->flags & X86_VM_MASK) {
-		handle_vm86_trap((struct kernel_vm86_regs *) regs,
-				error_code, 1);
+		handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code,
+					X86_TRAP_DB);
 		preempt_conditional_cli(regs);
 		debug_stack_usage_dec();
 		return;
@@ -460,7 +464,8 @@
 	struct task_struct *task = current;
 	siginfo_t info;
 	unsigned short err;
-	char *str = (trapnr == 16) ? "fpu exception" : "simd exception";
+	char *str = (trapnr == X86_TRAP_MF) ? "fpu exception" :
+						"simd exception";
 
 	if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, SIGFPE) == NOTIFY_STOP)
 		return;
@@ -470,7 +475,7 @@
 	{
 		if (!fixup_exception(regs)) {
 			task->thread.error_code = error_code;
-			task->thread.trap_no = trapnr;
+			task->thread.trap_nr = trapnr;
 			die(str, regs, error_code);
 		}
 		return;
@@ -480,12 +485,12 @@
 	 * Save the info for the exception handler and clear the error.
 	 */
 	save_init_fpu(task);
-	task->thread.trap_no = trapnr;
+	task->thread.trap_nr = trapnr;
 	task->thread.error_code = error_code;
 	info.si_signo = SIGFPE;
 	info.si_errno = 0;
 	info.si_addr = (void __user *)regs->ip;
-	if (trapnr == 16) {
+	if (trapnr == X86_TRAP_MF) {
 		unsigned short cwd, swd;
 		/*
 		 * (~cwd & swd) will mask out exceptions that are not set to unmasked
@@ -529,10 +534,11 @@
 		info.si_code = FPE_FLTRES;
 	} else {
 		/*
-		 * If we're using IRQ 13, or supposedly even some trap 16
-		 * implementations, it's possible we get a spurious trap...
+		 * If we're using IRQ 13, or supposedly even some trap
+		 * X86_TRAP_MF implementations, it's possible
+		 * we get a spurious trap, which is not an error.
 		 */
-		return;		/* Spurious trap, no error */
+		return;
 	}
 	force_sig_info(SIGFPE, &info, task);
 }
@@ -543,13 +549,13 @@
 	ignore_fpu_irq = 1;
 #endif
 
-	math_error(regs, error_code, 16);
+	math_error(regs, error_code, X86_TRAP_MF);
 }
 
 dotraplinkage void
 do_simd_coprocessor_error(struct pt_regs *regs, long error_code)
 {
-	math_error(regs, error_code, 19);
+	math_error(regs, error_code, X86_TRAP_XF);
 }
 
 dotraplinkage void
@@ -643,20 +649,21 @@
 	info.si_errno = 0;
 	info.si_code = ILL_BADSTK;
 	info.si_addr = NULL;
-	if (notify_die(DIE_TRAP, "iret exception",
-			regs, error_code, 32, SIGILL) == NOTIFY_STOP)
+	if (notify_die(DIE_TRAP, "iret exception", regs, error_code,
+			X86_TRAP_IRET, SIGILL) == NOTIFY_STOP)
 		return;
-	do_trap(32, SIGILL, "iret exception", regs, error_code, &info);
+	do_trap(X86_TRAP_IRET, SIGILL, "iret exception", regs, error_code,
+		&info);
 }
 #endif
 
 /* Set of traps needed for early debugging. */
 void __init early_trap_init(void)
 {
-	set_intr_gate_ist(1, &debug, DEBUG_STACK);
+	set_intr_gate_ist(X86_TRAP_DB, &debug, DEBUG_STACK);
 	/* int3 can be called from all */
-	set_system_intr_gate_ist(3, &int3, DEBUG_STACK);
-	set_intr_gate(14, &page_fault);
+	set_system_intr_gate_ist(X86_TRAP_BP, &int3, DEBUG_STACK);
+	set_intr_gate(X86_TRAP_PF, &page_fault);
 	load_idt(&idt_descr);
 }
 
@@ -672,30 +679,30 @@
 	early_iounmap(p, 4);
 #endif
 
-	set_intr_gate(0, &divide_error);
-	set_intr_gate_ist(2, &nmi, NMI_STACK);
+	set_intr_gate(X86_TRAP_DE, &divide_error);
+	set_intr_gate_ist(X86_TRAP_NMI, &nmi, NMI_STACK);
 	/* int4 can be called from all */
-	set_system_intr_gate(4, &overflow);
-	set_intr_gate(5, &bounds);
-	set_intr_gate(6, &invalid_op);
-	set_intr_gate(7, &device_not_available);
+	set_system_intr_gate(X86_TRAP_OF, &overflow);
+	set_intr_gate(X86_TRAP_BR, &bounds);
+	set_intr_gate(X86_TRAP_UD, &invalid_op);
+	set_intr_gate(X86_TRAP_NM, &device_not_available);
 #ifdef CONFIG_X86_32
-	set_task_gate(8, GDT_ENTRY_DOUBLEFAULT_TSS);
+	set_task_gate(X86_TRAP_DF, GDT_ENTRY_DOUBLEFAULT_TSS);
 #else
-	set_intr_gate_ist(8, &double_fault, DOUBLEFAULT_STACK);
+	set_intr_gate_ist(X86_TRAP_DF, &double_fault, DOUBLEFAULT_STACK);
 #endif
-	set_intr_gate(9, &coprocessor_segment_overrun);
-	set_intr_gate(10, &invalid_TSS);
-	set_intr_gate(11, &segment_not_present);
-	set_intr_gate_ist(12, &stack_segment, STACKFAULT_STACK);
-	set_intr_gate(13, &general_protection);
-	set_intr_gate(15, &spurious_interrupt_bug);
-	set_intr_gate(16, &coprocessor_error);
-	set_intr_gate(17, &alignment_check);
+	set_intr_gate(X86_TRAP_OLD_MF, &coprocessor_segment_overrun);
+	set_intr_gate(X86_TRAP_TS, &invalid_TSS);
+	set_intr_gate(X86_TRAP_NP, &segment_not_present);
+	set_intr_gate_ist(X86_TRAP_SS, &stack_segment, STACKFAULT_STACK);
+	set_intr_gate(X86_TRAP_GP, &general_protection);
+	set_intr_gate(X86_TRAP_SPURIOUS, &spurious_interrupt_bug);
+	set_intr_gate(X86_TRAP_MF, &coprocessor_error);
+	set_intr_gate(X86_TRAP_AC, &alignment_check);
 #ifdef CONFIG_X86_MCE
-	set_intr_gate_ist(18, &machine_check, MCE_STACK);
+	set_intr_gate_ist(X86_TRAP_MC, &machine_check, MCE_STACK);
 #endif
-	set_intr_gate(19, &simd_coprocessor_error);
+	set_intr_gate(X86_TRAP_XF, &simd_coprocessor_error);
 
 	/* Reserve all the builtin and the syscall vector: */
 	for (i = 0; i < FIRST_EXTERNAL_VECTOR; i++)
@@ -720,7 +727,7 @@
 
 #ifdef CONFIG_X86_64
 	memcpy(&nmi_idt_table, &idt_table, IDT_ENTRIES * 16);
-	set_nmi_gate(1, &debug);
-	set_nmi_gate(3, &int3);
+	set_nmi_gate(X86_TRAP_DB, &debug);
+	set_nmi_gate(X86_TRAP_BP, &int3);
 #endif
 }
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 899a03f2..fc0a147e 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -933,6 +933,16 @@
 		clocksource_tsc.rating = 0;
 		clocksource_tsc.flags &= ~CLOCK_SOURCE_IS_CONTINUOUS;
 	}
+
+	/*
+	 * Trust the results of the earlier calibration on systems
+	 * exporting a reliable TSC.
+	 */
+	if (boot_cpu_has(X86_FEATURE_TSC_RELIABLE)) {
+		clocksource_register_khz(&clocksource_tsc, tsc_khz);
+		return 0;
+	}
+
 	schedule_delayed_work(&tsc_irqwork, 0);
 	return 0;
 }
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index 328cb37..255f58a 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -569,7 +569,7 @@
 	}
 	if (trapno != 1)
 		return 1; /* we let this handle by the calling routine */
-	current->thread.trap_no = trapno;
+	current->thread.trap_nr = trapno;
 	current->thread.error_code = error_code;
 	force_sig(SIGTRAP, current);
 	return 0;
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index b07ba93..f386dc4 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -52,10 +52,7 @@
 #include "vsyscall_trace.h"
 
 DEFINE_VVAR(int, vgetcpu_mode);
-DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data) =
-{
-	.lock = __SEQLOCK_UNLOCKED(__vsyscall_gtod_data.lock),
-};
+DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data);
 
 static enum { EMULATE, NATIVE, NONE } vsyscall_mode = EMULATE;
 
@@ -80,20 +77,15 @@
 
 void update_vsyscall_tz(void)
 {
-	unsigned long flags;
-
-	write_seqlock_irqsave(&vsyscall_gtod_data.lock, flags);
-	/* sys_tz has changed */
 	vsyscall_gtod_data.sys_tz = sys_tz;
-	write_sequnlock_irqrestore(&vsyscall_gtod_data.lock, flags);
 }
 
 void update_vsyscall(struct timespec *wall_time, struct timespec *wtm,
 			struct clocksource *clock, u32 mult)
 {
-	unsigned long flags;
+	struct timespec monotonic;
 
-	write_seqlock_irqsave(&vsyscall_gtod_data.lock, flags);
+	write_seqcount_begin(&vsyscall_gtod_data.seq);
 
 	/* copy vsyscall data */
 	vsyscall_gtod_data.clock.vclock_mode	= clock->archdata.vclock_mode;
@@ -101,12 +93,19 @@
 	vsyscall_gtod_data.clock.mask		= clock->mask;
 	vsyscall_gtod_data.clock.mult		= mult;
 	vsyscall_gtod_data.clock.shift		= clock->shift;
+
 	vsyscall_gtod_data.wall_time_sec	= wall_time->tv_sec;
 	vsyscall_gtod_data.wall_time_nsec	= wall_time->tv_nsec;
-	vsyscall_gtod_data.wall_to_monotonic	= *wtm;
-	vsyscall_gtod_data.wall_time_coarse	= __current_kernel_time();
 
-	write_sequnlock_irqrestore(&vsyscall_gtod_data.lock, flags);
+	monotonic = timespec_add(*wall_time, *wtm);
+	vsyscall_gtod_data.monotonic_time_sec	= monotonic.tv_sec;
+	vsyscall_gtod_data.monotonic_time_nsec	= monotonic.tv_nsec;
+
+	vsyscall_gtod_data.wall_time_coarse	= __current_kernel_time();
+	vsyscall_gtod_data.monotonic_time_coarse =
+		timespec_add(vsyscall_gtod_data.wall_time_coarse, *wtm);
+
+	write_seqcount_end(&vsyscall_gtod_data.seq);
 }
 
 static void warn_bad_vsyscall(const char *level, struct pt_regs *regs,
@@ -153,7 +152,7 @@
 
 		thread->error_code	= 6;  /* user fault, no page, write */
 		thread->cr2		= ptr;
-		thread->trap_no		= 14;
+		thread->trap_nr		= X86_TRAP_PF;
 
 		memset(&info, 0, sizeof(info));
 		info.si_signo		= SIGSEGV;
diff --git a/arch/x86/math-emu/fpu_entry.c b/arch/x86/math-emu/fpu_entry.c
index 7718541..9b86812 100644
--- a/arch/x86/math-emu/fpu_entry.c
+++ b/arch/x86/math-emu/fpu_entry.c
@@ -28,6 +28,7 @@
 #include <linux/regset.h>
 
 #include <asm/uaccess.h>
+#include <asm/traps.h>
 #include <asm/desc.h>
 #include <asm/user.h>
 #include <asm/i387.h>
@@ -269,7 +270,7 @@
 			FPU_EIP = FPU_ORIG_EIP;	/* Point to current FPU instruction. */
 
 			RE_ENTRANT_CHECK_OFF;
-			current->thread.trap_no = 16;
+			current->thread.trap_nr = X86_TRAP_MF;
 			current->thread.error_code = 0;
 			send_sig(SIGFPE, current, 1);
 			return;
@@ -662,7 +663,7 @@
 void math_abort(struct math_emu_info *info, unsigned int signal)
 {
 	FPU_EIP = FPU_ORIG_EIP;
-	current->thread.trap_no = 16;
+	current->thread.trap_nr = X86_TRAP_MF;
 	current->thread.error_code = 0;
 	send_sig(signal, current, 1);
 	RE_ENTRANT_CHECK_OFF;
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index f0b4caf..3ecfd1aa 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -615,7 +615,7 @@
 	dump_pagetable(address);
 
 	tsk->thread.cr2		= address;
-	tsk->thread.trap_no	= 14;
+	tsk->thread.trap_nr	= X86_TRAP_PF;
 	tsk->thread.error_code	= error_code;
 
 	if (__die("Bad pagetable", regs, error_code))
@@ -636,7 +636,7 @@
 	/* Are we prepared to handle this kernel fault? */
 	if (fixup_exception(regs)) {
 		if (current_thread_info()->sig_on_uaccess_error && signal) {
-			tsk->thread.trap_no = 14;
+			tsk->thread.trap_nr = X86_TRAP_PF;
 			tsk->thread.error_code = error_code | PF_USER;
 			tsk->thread.cr2 = address;
 
@@ -676,7 +676,7 @@
 		printk(KERN_EMERG "Thread overran stack, or stack corrupted\n");
 
 	tsk->thread.cr2		= address;
-	tsk->thread.trap_no	= 14;
+	tsk->thread.trap_nr	= X86_TRAP_PF;
 	tsk->thread.error_code	= error_code;
 
 	sig = SIGKILL;
@@ -754,7 +754,7 @@
 		/* Kernel addresses are always protection faults: */
 		tsk->thread.cr2		= address;
 		tsk->thread.error_code	= error_code | (address >= TASK_SIZE);
-		tsk->thread.trap_no	= 14;
+		tsk->thread.trap_nr	= X86_TRAP_PF;
 
 		force_sig_info_fault(SIGSEGV, si_code, address, tsk, 0);
 
@@ -838,7 +838,7 @@
 
 	tsk->thread.cr2		= address;
 	tsk->thread.error_code	= error_code;
-	tsk->thread.trap_no	= 14;
+	tsk->thread.trap_nr	= X86_TRAP_PF;
 
 #ifdef CONFIG_MEMORY_FAILURE
 	if (fault & (VM_FAULT_HWPOISON|VM_FAULT_HWPOISON_LARGE)) {
diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c
index 1c1c4f4..efb5b4b 100644
--- a/arch/x86/mm/srat.c
+++ b/arch/x86/mm/srat.c
@@ -70,7 +70,7 @@
 		return;
 	pxm = pa->proximity_domain;
 	apic_id = pa->apic_id;
-	if (!cpu_has_x2apic && (apic_id >= 0xff)) {
+	if (!apic->apic_id_valid(apic_id)) {
 		printk(KERN_INFO "SRAT: PXM %u -> X2APIC 0x%04x ignored\n",
 			 pxm, apic_id);
 		return;
diff --git a/arch/x86/oprofile/backtrace.c b/arch/x86/oprofile/backtrace.c
index bff89df..d6aa6e8 100644
--- a/arch/x86/oprofile/backtrace.c
+++ b/arch/x86/oprofile/backtrace.c
@@ -67,7 +67,7 @@
 {
 	struct stack_frame_ia32 *head;
 
-	/* User process is 32-bit */
+	/* User process is IA32 */
 	if (!current || !test_thread_flag(TIF_IA32))
 		return 0;
 
diff --git a/arch/x86/platform/olpc/olpc.c b/arch/x86/platform/olpc/olpc.c
index 7cce722..a4bee53 100644
--- a/arch/x86/platform/olpc/olpc.c
+++ b/arch/x86/platform/olpc/olpc.c
@@ -20,6 +20,8 @@
 #include <linux/platform_device.h>
 #include <linux/of.h>
 #include <linux/syscore_ops.h>
+#include <linux/debugfs.h>
+#include <linux/mutex.h>
 
 #include <asm/geode.h>
 #include <asm/setup.h>
@@ -31,6 +33,15 @@
 
 static DEFINE_SPINLOCK(ec_lock);
 
+/* debugfs interface to EC commands */
+#define EC_MAX_CMD_ARGS (5 + 1)	/* cmd byte + 5 args */
+#define EC_MAX_CMD_REPLY (8)
+
+static struct dentry *ec_debugfs_dir;
+static DEFINE_MUTEX(ec_debugfs_cmd_lock);
+static unsigned char ec_debugfs_resp[EC_MAX_CMD_REPLY];
+static unsigned int ec_debugfs_resp_bytes;
+
 /* EC event mask to be applied during suspend (defining wakeup sources). */
 static u16 ec_wakeup_mask;
 
@@ -269,6 +280,91 @@
 }
 EXPORT_SYMBOL_GPL(olpc_ec_sci_query);
 
+static ssize_t ec_debugfs_cmd_write(struct file *file, const char __user *buf,
+				    size_t size, loff_t *ppos)
+{
+	int i, m;
+	unsigned char ec_cmd[EC_MAX_CMD_ARGS];
+	unsigned int ec_cmd_int[EC_MAX_CMD_ARGS];
+	char cmdbuf[64];
+	int ec_cmd_bytes;
+
+	mutex_lock(&ec_debugfs_cmd_lock);
+
+	size = simple_write_to_buffer(cmdbuf, sizeof(cmdbuf), ppos, buf, size);
+
+	m = sscanf(cmdbuf, "%x:%u %x %x %x %x %x", &ec_cmd_int[0],
+		   &ec_debugfs_resp_bytes,
+		   &ec_cmd_int[1], &ec_cmd_int[2], &ec_cmd_int[3],
+		   &ec_cmd_int[4], &ec_cmd_int[5]);
+	if (m < 2 || ec_debugfs_resp_bytes > EC_MAX_CMD_REPLY) {
+		/* reset to prevent overflow on read */
+		ec_debugfs_resp_bytes = 0;
+
+		printk(KERN_DEBUG "olpc-ec: bad ec cmd:  "
+		       "cmd:response-count [arg1 [arg2 ...]]\n");
+		size = -EINVAL;
+		goto out;
+	}
+
+	/* convert scanf'd ints to char */
+	ec_cmd_bytes = m - 2;
+	for (i = 0; i <= ec_cmd_bytes; i++)
+		ec_cmd[i] = ec_cmd_int[i];
+
+	printk(KERN_DEBUG "olpc-ec: debugfs cmd 0x%02x with %d args "
+	       "%02x %02x %02x %02x %02x, want %d returns\n",
+	       ec_cmd[0], ec_cmd_bytes, ec_cmd[1], ec_cmd[2], ec_cmd[3],
+	       ec_cmd[4], ec_cmd[5], ec_debugfs_resp_bytes);
+
+	olpc_ec_cmd(ec_cmd[0], (ec_cmd_bytes == 0) ? NULL : &ec_cmd[1],
+		    ec_cmd_bytes, ec_debugfs_resp, ec_debugfs_resp_bytes);
+
+	printk(KERN_DEBUG "olpc-ec: response "
+	       "%02x %02x %02x %02x %02x %02x %02x %02x (%d bytes expected)\n",
+	       ec_debugfs_resp[0], ec_debugfs_resp[1], ec_debugfs_resp[2],
+	       ec_debugfs_resp[3], ec_debugfs_resp[4], ec_debugfs_resp[5],
+	       ec_debugfs_resp[6], ec_debugfs_resp[7], ec_debugfs_resp_bytes);
+
+out:
+	mutex_unlock(&ec_debugfs_cmd_lock);
+	return size;
+}
+
+static ssize_t ec_debugfs_cmd_read(struct file *file, char __user *buf,
+				   size_t size, loff_t *ppos)
+{
+	unsigned int i, r;
+	char *rp;
+	char respbuf[64];
+
+	mutex_lock(&ec_debugfs_cmd_lock);
+	rp = respbuf;
+	rp += sprintf(rp, "%02x", ec_debugfs_resp[0]);
+	for (i = 1; i < ec_debugfs_resp_bytes; i++)
+		rp += sprintf(rp, ", %02x", ec_debugfs_resp[i]);
+	mutex_unlock(&ec_debugfs_cmd_lock);
+	rp += sprintf(rp, "\n");
+
+	r = rp - respbuf;
+	return simple_read_from_buffer(buf, size, ppos, respbuf, r);
+}
+
+static const struct file_operations ec_debugfs_genops = {
+	.write	 = ec_debugfs_cmd_write,
+	.read	 = ec_debugfs_cmd_read,
+};
+
+static void setup_debugfs(void)
+{
+	ec_debugfs_dir = debugfs_create_dir("olpc-ec", 0);
+	if (ec_debugfs_dir == ERR_PTR(-ENODEV))
+		return;
+
+	debugfs_create_file("cmd", 0600, ec_debugfs_dir, NULL,
+			    &ec_debugfs_genops);
+}
+
 static int olpc_ec_suspend(void)
 {
 	return olpc_ec_mask_write(ec_wakeup_mask);
@@ -372,6 +468,7 @@
 	}
 
 	register_syscore_ops(&olpc_syscore_ops);
+	setup_debugfs();
 
 	return 0;
 }
diff --git a/arch/x86/syscalls/Makefile b/arch/x86/syscalls/Makefile
index 564b247..3236aeb 100644
--- a/arch/x86/syscalls/Makefile
+++ b/arch/x86/syscalls/Makefile
@@ -10,8 +10,10 @@
 systbl := $(srctree)/$(src)/syscalltbl.sh
 
 quiet_cmd_syshdr = SYSHDR  $@
-      cmd_syshdr = $(CONFIG_SHELL) '$(syshdr)' $< $@ \
-		   $(syshdr_abi_$(basetarget)) $(syshdr_pfx_$(basetarget))
+      cmd_syshdr = $(CONFIG_SHELL) '$(syshdr)' '$<' '$@' \
+		   '$(syshdr_abi_$(basetarget))' \
+		   '$(syshdr_pfx_$(basetarget))' \
+		   '$(syshdr_offset_$(basetarget))'
 quiet_cmd_systbl = SYSTBL  $@
       cmd_systbl = $(CONFIG_SHELL) '$(systbl)' $< $@
 
@@ -24,18 +26,28 @@
 $(out)/unistd_32_ia32.h: $(syscall32) $(syshdr)
 	$(call if_changed,syshdr)
 
-syshdr_abi_unistd_64 := 64
+syshdr_abi_unistd_x32 := common,x32
+syshdr_offset_unistd_x32 := __X32_SYSCALL_BIT
+$(out)/unistd_x32.h: $(syscall64) $(syshdr)
+	$(call if_changed,syshdr)
+
+syshdr_abi_unistd_64 := common,64
 $(out)/unistd_64.h: $(syscall64) $(syshdr)
 	$(call if_changed,syshdr)
 
+syshdr_abi_unistd_64_x32 := x32
+syshdr_pfx_unistd_64_x32 := x32_
+$(out)/unistd_64_x32.h: $(syscall64) $(syshdr)
+	$(call if_changed,syshdr)
+
 $(out)/syscalls_32.h: $(syscall32) $(systbl)
 	$(call if_changed,systbl)
 $(out)/syscalls_64.h: $(syscall64) $(systbl)
 	$(call if_changed,systbl)
 
-syshdr-y			+= unistd_32.h unistd_64.h
+syshdr-y			+= unistd_32.h unistd_64.h unistd_x32.h
 syshdr-y			+= syscalls_32.h
-syshdr-$(CONFIG_X86_64)		+= unistd_32_ia32.h
+syshdr-$(CONFIG_X86_64)		+= unistd_32_ia32.h unistd_64_x32.h
 syshdr-$(CONFIG_X86_64)		+= syscalls_64.h
 
 targets	+= $(syshdr-y)
diff --git a/arch/x86/syscalls/syscall_32.tbl b/arch/x86/syscalls/syscall_32.tbl
index e7e67cc..29f9f05 100644
--- a/arch/x86/syscalls/syscall_32.tbl
+++ b/arch/x86/syscalls/syscall_32.tbl
@@ -181,7 +181,7 @@
 172	i386	prctl			sys_prctl
 173	i386	rt_sigreturn		ptregs_rt_sigreturn		stub32_rt_sigreturn
 174	i386	rt_sigaction		sys_rt_sigaction		sys32_rt_sigaction
-175	i386	rt_sigprocmask		sys_rt_sigprocmask		sys32_rt_sigprocmask
+175	i386	rt_sigprocmask		sys_rt_sigprocmask
 176	i386	rt_sigpending		sys_rt_sigpending		sys32_rt_sigpending
 177	i386	rt_sigtimedwait		sys_rt_sigtimedwait		compat_sys_rt_sigtimedwait
 178	i386	rt_sigqueueinfo		sys_rt_sigqueueinfo		sys32_rt_sigqueueinfo
diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl
index b440a8f..dd29a9e 100644
--- a/arch/x86/syscalls/syscall_64.tbl
+++ b/arch/x86/syscalls/syscall_64.tbl
@@ -4,317 +4,350 @@
 # The format is:
 # <number> <abi> <name> <entry point>
 #
-# The abi is always "64" for this file (for now.)
+# The abi is "common", "64" or "x32" for this file.
 #
-0	64	read			sys_read
-1	64	write			sys_write
-2	64	open			sys_open
-3	64	close			sys_close
-4	64	stat			sys_newstat
-5	64	fstat			sys_newfstat
-6	64	lstat			sys_newlstat
-7	64	poll			sys_poll
-8	64	lseek			sys_lseek
-9	64	mmap			sys_mmap
-10	64	mprotect		sys_mprotect
-11	64	munmap			sys_munmap
-12	64	brk			sys_brk
+0	common	read			sys_read
+1	common	write			sys_write
+2	common	open			sys_open
+3	common	close			sys_close
+4	common	stat			sys_newstat
+5	common	fstat			sys_newfstat
+6	common	lstat			sys_newlstat
+7	common	poll			sys_poll
+8	common	lseek			sys_lseek
+9	common	mmap			sys_mmap
+10	common	mprotect		sys_mprotect
+11	common	munmap			sys_munmap
+12	common	brk			sys_brk
 13	64	rt_sigaction		sys_rt_sigaction
-14	64	rt_sigprocmask		sys_rt_sigprocmask
+14	common	rt_sigprocmask		sys_rt_sigprocmask
 15	64	rt_sigreturn		stub_rt_sigreturn
 16	64	ioctl			sys_ioctl
-17	64	pread64			sys_pread64
-18	64	pwrite64		sys_pwrite64
+17	common	pread64			sys_pread64
+18	common	pwrite64		sys_pwrite64
 19	64	readv			sys_readv
 20	64	writev			sys_writev
-21	64	access			sys_access
-22	64	pipe			sys_pipe
-23	64	select			sys_select
-24	64	sched_yield		sys_sched_yield
-25	64	mremap			sys_mremap
-26	64	msync			sys_msync
-27	64	mincore			sys_mincore
-28	64	madvise			sys_madvise
-29	64	shmget			sys_shmget
-30	64	shmat			sys_shmat
-31	64	shmctl			sys_shmctl
-32	64	dup			sys_dup
-33	64	dup2			sys_dup2
-34	64	pause			sys_pause
-35	64	nanosleep		sys_nanosleep
-36	64	getitimer		sys_getitimer
-37	64	alarm			sys_alarm
-38	64	setitimer		sys_setitimer
-39	64	getpid			sys_getpid
-40	64	sendfile		sys_sendfile64
-41	64	socket			sys_socket
-42	64	connect			sys_connect
-43	64	accept			sys_accept
-44	64	sendto			sys_sendto
+21	common	access			sys_access
+22	common	pipe			sys_pipe
+23	common	select			sys_select
+24	common	sched_yield		sys_sched_yield
+25	common	mremap			sys_mremap
+26	common	msync			sys_msync
+27	common	mincore			sys_mincore
+28	common	madvise			sys_madvise
+29	common	shmget			sys_shmget
+30	common	shmat			sys_shmat
+31	common	shmctl			sys_shmctl
+32	common	dup			sys_dup
+33	common	dup2			sys_dup2
+34	common	pause			sys_pause
+35	common	nanosleep		sys_nanosleep
+36	common	getitimer		sys_getitimer
+37	common	alarm			sys_alarm
+38	common	setitimer		sys_setitimer
+39	common	getpid			sys_getpid
+40	common	sendfile		sys_sendfile64
+41	common	socket			sys_socket
+42	common	connect			sys_connect
+43	common	accept			sys_accept
+44	common	sendto			sys_sendto
 45	64	recvfrom		sys_recvfrom
 46	64	sendmsg			sys_sendmsg
 47	64	recvmsg			sys_recvmsg
-48	64	shutdown		sys_shutdown
-49	64	bind			sys_bind
-50	64	listen			sys_listen
-51	64	getsockname		sys_getsockname
-52	64	getpeername		sys_getpeername
-53	64	socketpair		sys_socketpair
-54	64	setsockopt		sys_setsockopt
-55	64	getsockopt		sys_getsockopt
-56	64	clone			stub_clone
-57	64	fork			stub_fork
-58	64	vfork			stub_vfork
+48	common	shutdown		sys_shutdown
+49	common	bind			sys_bind
+50	common	listen			sys_listen
+51	common	getsockname		sys_getsockname
+52	common	getpeername		sys_getpeername
+53	common	socketpair		sys_socketpair
+54	common	setsockopt		sys_setsockopt
+55	common	getsockopt		sys_getsockopt
+56	common	clone			stub_clone
+57	common	fork			stub_fork
+58	common	vfork			stub_vfork
 59	64	execve			stub_execve
-60	64	exit			sys_exit
-61	64	wait4			sys_wait4
-62	64	kill			sys_kill
-63	64	uname			sys_newuname
-64	64	semget			sys_semget
-65	64	semop			sys_semop
-66	64	semctl			sys_semctl
-67	64	shmdt			sys_shmdt
-68	64	msgget			sys_msgget
-69	64	msgsnd			sys_msgsnd
-70	64	msgrcv			sys_msgrcv
-71	64	msgctl			sys_msgctl
-72	64	fcntl			sys_fcntl
-73	64	flock			sys_flock
-74	64	fsync			sys_fsync
-75	64	fdatasync		sys_fdatasync
-76	64	truncate		sys_truncate
-77	64	ftruncate		sys_ftruncate
-78	64	getdents		sys_getdents
-79	64	getcwd			sys_getcwd
-80	64	chdir			sys_chdir
-81	64	fchdir			sys_fchdir
-82	64	rename			sys_rename
-83	64	mkdir			sys_mkdir
-84	64	rmdir			sys_rmdir
-85	64	creat			sys_creat
-86	64	link			sys_link
-87	64	unlink			sys_unlink
-88	64	symlink			sys_symlink
-89	64	readlink		sys_readlink
-90	64	chmod			sys_chmod
-91	64	fchmod			sys_fchmod
-92	64	chown			sys_chown
-93	64	fchown			sys_fchown
-94	64	lchown			sys_lchown
-95	64	umask			sys_umask
-96	64	gettimeofday		sys_gettimeofday
-97	64	getrlimit		sys_getrlimit
-98	64	getrusage		sys_getrusage
-99	64	sysinfo			sys_sysinfo
-100	64	times			sys_times
+60	common	exit			sys_exit
+61	common	wait4			sys_wait4
+62	common	kill			sys_kill
+63	common	uname			sys_newuname
+64	common	semget			sys_semget
+65	common	semop			sys_semop
+66	common	semctl			sys_semctl
+67	common	shmdt			sys_shmdt
+68	common	msgget			sys_msgget
+69	common	msgsnd			sys_msgsnd
+70	common	msgrcv			sys_msgrcv
+71	common	msgctl			sys_msgctl
+72	common	fcntl			sys_fcntl
+73	common	flock			sys_flock
+74	common	fsync			sys_fsync
+75	common	fdatasync		sys_fdatasync
+76	common	truncate		sys_truncate
+77	common	ftruncate		sys_ftruncate
+78	common	getdents		sys_getdents
+79	common	getcwd			sys_getcwd
+80	common	chdir			sys_chdir
+81	common	fchdir			sys_fchdir
+82	common	rename			sys_rename
+83	common	mkdir			sys_mkdir
+84	common	rmdir			sys_rmdir
+85	common	creat			sys_creat
+86	common	link			sys_link
+87	common	unlink			sys_unlink
+88	common	symlink			sys_symlink
+89	common	readlink		sys_readlink
+90	common	chmod			sys_chmod
+91	common	fchmod			sys_fchmod
+92	common	chown			sys_chown
+93	common	fchown			sys_fchown
+94	common	lchown			sys_lchown
+95	common	umask			sys_umask
+96	common	gettimeofday		sys_gettimeofday
+97	common	getrlimit		sys_getrlimit
+98	common	getrusage		sys_getrusage
+99	common	sysinfo			sys_sysinfo
+100	common	times			sys_times
 101	64	ptrace			sys_ptrace
-102	64	getuid			sys_getuid
-103	64	syslog			sys_syslog
-104	64	getgid			sys_getgid
-105	64	setuid			sys_setuid
-106	64	setgid			sys_setgid
-107	64	geteuid			sys_geteuid
-108	64	getegid			sys_getegid
-109	64	setpgid			sys_setpgid
-110	64	getppid			sys_getppid
-111	64	getpgrp			sys_getpgrp
-112	64	setsid			sys_setsid
-113	64	setreuid		sys_setreuid
-114	64	setregid		sys_setregid
-115	64	getgroups		sys_getgroups
-116	64	setgroups		sys_setgroups
-117	64	setresuid		sys_setresuid
-118	64	getresuid		sys_getresuid
-119	64	setresgid		sys_setresgid
-120	64	getresgid		sys_getresgid
-121	64	getpgid			sys_getpgid
-122	64	setfsuid		sys_setfsuid
-123	64	setfsgid		sys_setfsgid
-124	64	getsid			sys_getsid
-125	64	capget			sys_capget
-126	64	capset			sys_capset
+102	common	getuid			sys_getuid
+103	common	syslog			sys_syslog
+104	common	getgid			sys_getgid
+105	common	setuid			sys_setuid
+106	common	setgid			sys_setgid
+107	common	geteuid			sys_geteuid
+108	common	getegid			sys_getegid
+109	common	setpgid			sys_setpgid
+110	common	getppid			sys_getppid
+111	common	getpgrp			sys_getpgrp
+112	common	setsid			sys_setsid
+113	common	setreuid		sys_setreuid
+114	common	setregid		sys_setregid
+115	common	getgroups		sys_getgroups
+116	common	setgroups		sys_setgroups
+117	common	setresuid		sys_setresuid
+118	common	getresuid		sys_getresuid
+119	common	setresgid		sys_setresgid
+120	common	getresgid		sys_getresgid
+121	common	getpgid			sys_getpgid
+122	common	setfsuid		sys_setfsuid
+123	common	setfsgid		sys_setfsgid
+124	common	getsid			sys_getsid
+125	common	capget			sys_capget
+126	common	capset			sys_capset
 127	64	rt_sigpending		sys_rt_sigpending
 128	64	rt_sigtimedwait		sys_rt_sigtimedwait
 129	64	rt_sigqueueinfo		sys_rt_sigqueueinfo
-130	64	rt_sigsuspend		sys_rt_sigsuspend
+130	common	rt_sigsuspend		sys_rt_sigsuspend
 131	64	sigaltstack		stub_sigaltstack
-132	64	utime			sys_utime
-133	64	mknod			sys_mknod
+132	common	utime			sys_utime
+133	common	mknod			sys_mknod
 134	64	uselib
-135	64	personality		sys_personality
-136	64	ustat			sys_ustat
-137	64	statfs			sys_statfs
-138	64	fstatfs			sys_fstatfs
-139	64	sysfs			sys_sysfs
-140	64	getpriority		sys_getpriority
-141	64	setpriority		sys_setpriority
-142	64	sched_setparam		sys_sched_setparam
-143	64	sched_getparam		sys_sched_getparam
-144	64	sched_setscheduler	sys_sched_setscheduler
-145	64	sched_getscheduler	sys_sched_getscheduler
-146	64	sched_get_priority_max	sys_sched_get_priority_max
-147	64	sched_get_priority_min	sys_sched_get_priority_min
-148	64	sched_rr_get_interval	sys_sched_rr_get_interval
-149	64	mlock			sys_mlock
-150	64	munlock			sys_munlock
-151	64	mlockall		sys_mlockall
-152	64	munlockall		sys_munlockall
-153	64	vhangup			sys_vhangup
-154	64	modify_ldt		sys_modify_ldt
-155	64	pivot_root		sys_pivot_root
+135	common	personality		sys_personality
+136	common	ustat			sys_ustat
+137	common	statfs			sys_statfs
+138	common	fstatfs			sys_fstatfs
+139	common	sysfs			sys_sysfs
+140	common	getpriority		sys_getpriority
+141	common	setpriority		sys_setpriority
+142	common	sched_setparam		sys_sched_setparam
+143	common	sched_getparam		sys_sched_getparam
+144	common	sched_setscheduler	sys_sched_setscheduler
+145	common	sched_getscheduler	sys_sched_getscheduler
+146	common	sched_get_priority_max	sys_sched_get_priority_max
+147	common	sched_get_priority_min	sys_sched_get_priority_min
+148	common	sched_rr_get_interval	sys_sched_rr_get_interval
+149	common	mlock			sys_mlock
+150	common	munlock			sys_munlock
+151	common	mlockall		sys_mlockall
+152	common	munlockall		sys_munlockall
+153	common	vhangup			sys_vhangup
+154	common	modify_ldt		sys_modify_ldt
+155	common	pivot_root		sys_pivot_root
 156	64	_sysctl			sys_sysctl
-157	64	prctl			sys_prctl
-158	64	arch_prctl		sys_arch_prctl
-159	64	adjtimex		sys_adjtimex
-160	64	setrlimit		sys_setrlimit
-161	64	chroot			sys_chroot
-162	64	sync			sys_sync
-163	64	acct			sys_acct
-164	64	settimeofday		sys_settimeofday
-165	64	mount			sys_mount
-166	64	umount2			sys_umount
-167	64	swapon			sys_swapon
-168	64	swapoff			sys_swapoff
-169	64	reboot			sys_reboot
-170	64	sethostname		sys_sethostname
-171	64	setdomainname		sys_setdomainname
-172	64	iopl			stub_iopl
-173	64	ioperm			sys_ioperm
+157	common	prctl			sys_prctl
+158	common	arch_prctl		sys_arch_prctl
+159	common	adjtimex		sys_adjtimex
+160	common	setrlimit		sys_setrlimit
+161	common	chroot			sys_chroot
+162	common	sync			sys_sync
+163	common	acct			sys_acct
+164	common	settimeofday		sys_settimeofday
+165	common	mount			sys_mount
+166	common	umount2			sys_umount
+167	common	swapon			sys_swapon
+168	common	swapoff			sys_swapoff
+169	common	reboot			sys_reboot
+170	common	sethostname		sys_sethostname
+171	common	setdomainname		sys_setdomainname
+172	common	iopl			stub_iopl
+173	common	ioperm			sys_ioperm
 174	64	create_module
-175	64	init_module		sys_init_module
-176	64	delete_module		sys_delete_module
+175	common	init_module		sys_init_module
+176	common	delete_module		sys_delete_module
 177	64	get_kernel_syms
 178	64	query_module
-179	64	quotactl		sys_quotactl
+179	common	quotactl		sys_quotactl
 180	64	nfsservctl
-181	64	getpmsg
-182	64	putpmsg
-183	64	afs_syscall
-184	64	tuxcall
-185	64	security
-186	64	gettid			sys_gettid
-187	64	readahead		sys_readahead
-188	64	setxattr		sys_setxattr
-189	64	lsetxattr		sys_lsetxattr
-190	64	fsetxattr		sys_fsetxattr
-191	64	getxattr		sys_getxattr
-192	64	lgetxattr		sys_lgetxattr
-193	64	fgetxattr		sys_fgetxattr
-194	64	listxattr		sys_listxattr
-195	64	llistxattr		sys_llistxattr
-196	64	flistxattr		sys_flistxattr
-197	64	removexattr		sys_removexattr
-198	64	lremovexattr		sys_lremovexattr
-199	64	fremovexattr		sys_fremovexattr
-200	64	tkill			sys_tkill
-201	64	time			sys_time
-202	64	futex			sys_futex
-203	64	sched_setaffinity	sys_sched_setaffinity
-204	64	sched_getaffinity	sys_sched_getaffinity
+181	common	getpmsg
+182	common	putpmsg
+183	common	afs_syscall
+184	common	tuxcall
+185	common	security
+186	common	gettid			sys_gettid
+187	common	readahead		sys_readahead
+188	common	setxattr		sys_setxattr
+189	common	lsetxattr		sys_lsetxattr
+190	common	fsetxattr		sys_fsetxattr
+191	common	getxattr		sys_getxattr
+192	common	lgetxattr		sys_lgetxattr
+193	common	fgetxattr		sys_fgetxattr
+194	common	listxattr		sys_listxattr
+195	common	llistxattr		sys_llistxattr
+196	common	flistxattr		sys_flistxattr
+197	common	removexattr		sys_removexattr
+198	common	lremovexattr		sys_lremovexattr
+199	common	fremovexattr		sys_fremovexattr
+200	common	tkill			sys_tkill
+201	common	time			sys_time
+202	common	futex			sys_futex
+203	common	sched_setaffinity	sys_sched_setaffinity
+204	common	sched_getaffinity	sys_sched_getaffinity
 205	64	set_thread_area
-206	64	io_setup		sys_io_setup
-207	64	io_destroy		sys_io_destroy
-208	64	io_getevents		sys_io_getevents
-209	64	io_submit		sys_io_submit
-210	64	io_cancel		sys_io_cancel
+206	common	io_setup		sys_io_setup
+207	common	io_destroy		sys_io_destroy
+208	common	io_getevents		sys_io_getevents
+209	common	io_submit		sys_io_submit
+210	common	io_cancel		sys_io_cancel
 211	64	get_thread_area
-212	64	lookup_dcookie		sys_lookup_dcookie
-213	64	epoll_create		sys_epoll_create
+212	common	lookup_dcookie		sys_lookup_dcookie
+213	common	epoll_create		sys_epoll_create
 214	64	epoll_ctl_old
 215	64	epoll_wait_old
-216	64	remap_file_pages	sys_remap_file_pages
-217	64	getdents64		sys_getdents64
-218	64	set_tid_address		sys_set_tid_address
-219	64	restart_syscall		sys_restart_syscall
-220	64	semtimedop		sys_semtimedop
-221	64	fadvise64		sys_fadvise64
+216	common	remap_file_pages	sys_remap_file_pages
+217	common	getdents64		sys_getdents64
+218	common	set_tid_address		sys_set_tid_address
+219	common	restart_syscall		sys_restart_syscall
+220	common	semtimedop		sys_semtimedop
+221	common	fadvise64		sys_fadvise64
 222	64	timer_create		sys_timer_create
-223	64	timer_settime		sys_timer_settime
-224	64	timer_gettime		sys_timer_gettime
-225	64	timer_getoverrun	sys_timer_getoverrun
-226	64	timer_delete		sys_timer_delete
-227	64	clock_settime		sys_clock_settime
-228	64	clock_gettime		sys_clock_gettime
-229	64	clock_getres		sys_clock_getres
-230	64	clock_nanosleep		sys_clock_nanosleep
-231	64	exit_group		sys_exit_group
-232	64	epoll_wait		sys_epoll_wait
-233	64	epoll_ctl		sys_epoll_ctl
-234	64	tgkill			sys_tgkill
-235	64	utimes			sys_utimes
+223	common	timer_settime		sys_timer_settime
+224	common	timer_gettime		sys_timer_gettime
+225	common	timer_getoverrun	sys_timer_getoverrun
+226	common	timer_delete		sys_timer_delete
+227	common	clock_settime		sys_clock_settime
+228	common	clock_gettime		sys_clock_gettime
+229	common	clock_getres		sys_clock_getres
+230	common	clock_nanosleep		sys_clock_nanosleep
+231	common	exit_group		sys_exit_group
+232	common	epoll_wait		sys_epoll_wait
+233	common	epoll_ctl		sys_epoll_ctl
+234	common	tgkill			sys_tgkill
+235	common	utimes			sys_utimes
 236	64	vserver
-237	64	mbind			sys_mbind
-238	64	set_mempolicy		sys_set_mempolicy
-239	64	get_mempolicy		sys_get_mempolicy
-240	64	mq_open			sys_mq_open
-241	64	mq_unlink		sys_mq_unlink
-242	64	mq_timedsend		sys_mq_timedsend
-243	64	mq_timedreceive		sys_mq_timedreceive
+237	common	mbind			sys_mbind
+238	common	set_mempolicy		sys_set_mempolicy
+239	common	get_mempolicy		sys_get_mempolicy
+240	common	mq_open			sys_mq_open
+241	common	mq_unlink		sys_mq_unlink
+242	common	mq_timedsend		sys_mq_timedsend
+243	common	mq_timedreceive		sys_mq_timedreceive
 244	64	mq_notify		sys_mq_notify
-245	64	mq_getsetattr		sys_mq_getsetattr
+245	common	mq_getsetattr		sys_mq_getsetattr
 246	64	kexec_load		sys_kexec_load
 247	64	waitid			sys_waitid
-248	64	add_key			sys_add_key
-249	64	request_key		sys_request_key
-250	64	keyctl			sys_keyctl
-251	64	ioprio_set		sys_ioprio_set
-252	64	ioprio_get		sys_ioprio_get
-253	64	inotify_init		sys_inotify_init
-254	64	inotify_add_watch	sys_inotify_add_watch
-255	64	inotify_rm_watch	sys_inotify_rm_watch
-256	64	migrate_pages		sys_migrate_pages
-257	64	openat			sys_openat
-258	64	mkdirat			sys_mkdirat
-259	64	mknodat			sys_mknodat
-260	64	fchownat		sys_fchownat
-261	64	futimesat		sys_futimesat
-262	64	newfstatat		sys_newfstatat
-263	64	unlinkat		sys_unlinkat
-264	64	renameat		sys_renameat
-265	64	linkat			sys_linkat
-266	64	symlinkat		sys_symlinkat
-267	64	readlinkat		sys_readlinkat
-268	64	fchmodat		sys_fchmodat
-269	64	faccessat		sys_faccessat
-270	64	pselect6		sys_pselect6
-271	64	ppoll			sys_ppoll
-272	64	unshare			sys_unshare
+248	common	add_key			sys_add_key
+249	common	request_key		sys_request_key
+250	common	keyctl			sys_keyctl
+251	common	ioprio_set		sys_ioprio_set
+252	common	ioprio_get		sys_ioprio_get
+253	common	inotify_init		sys_inotify_init
+254	common	inotify_add_watch	sys_inotify_add_watch
+255	common	inotify_rm_watch	sys_inotify_rm_watch
+256	common	migrate_pages		sys_migrate_pages
+257	common	openat			sys_openat
+258	common	mkdirat			sys_mkdirat
+259	common	mknodat			sys_mknodat
+260	common	fchownat		sys_fchownat
+261	common	futimesat		sys_futimesat
+262	common	newfstatat		sys_newfstatat
+263	common	unlinkat		sys_unlinkat
+264	common	renameat		sys_renameat
+265	common	linkat			sys_linkat
+266	common	symlinkat		sys_symlinkat
+267	common	readlinkat		sys_readlinkat
+268	common	fchmodat		sys_fchmodat
+269	common	faccessat		sys_faccessat
+270	common	pselect6		sys_pselect6
+271	common	ppoll			sys_ppoll
+272	common	unshare			sys_unshare
 273	64	set_robust_list		sys_set_robust_list
 274	64	get_robust_list		sys_get_robust_list
-275	64	splice			sys_splice
-276	64	tee			sys_tee
-277	64	sync_file_range		sys_sync_file_range
+275	common	splice			sys_splice
+276	common	tee			sys_tee
+277	common	sync_file_range		sys_sync_file_range
 278	64	vmsplice		sys_vmsplice
 279	64	move_pages		sys_move_pages
-280	64	utimensat		sys_utimensat
-281	64	epoll_pwait		sys_epoll_pwait
-282	64	signalfd		sys_signalfd
-283	64	timerfd_create		sys_timerfd_create
-284	64	eventfd			sys_eventfd
-285	64	fallocate		sys_fallocate
-286	64	timerfd_settime		sys_timerfd_settime
-287	64	timerfd_gettime		sys_timerfd_gettime
-288	64	accept4			sys_accept4
-289	64	signalfd4		sys_signalfd4
-290	64	eventfd2		sys_eventfd2
-291	64	epoll_create1		sys_epoll_create1
-292	64	dup3			sys_dup3
-293	64	pipe2			sys_pipe2
-294	64	inotify_init1		sys_inotify_init1
+280	common	utimensat		sys_utimensat
+281	common	epoll_pwait		sys_epoll_pwait
+282	common	signalfd		sys_signalfd
+283	common	timerfd_create		sys_timerfd_create
+284	common	eventfd			sys_eventfd
+285	common	fallocate		sys_fallocate
+286	common	timerfd_settime		sys_timerfd_settime
+287	common	timerfd_gettime		sys_timerfd_gettime
+288	common	accept4			sys_accept4
+289	common	signalfd4		sys_signalfd4
+290	common	eventfd2		sys_eventfd2
+291	common	epoll_create1		sys_epoll_create1
+292	common	dup3			sys_dup3
+293	common	pipe2			sys_pipe2
+294	common	inotify_init1		sys_inotify_init1
 295	64	preadv			sys_preadv
 296	64	pwritev			sys_pwritev
 297	64	rt_tgsigqueueinfo	sys_rt_tgsigqueueinfo
-298	64	perf_event_open		sys_perf_event_open
+298	common	perf_event_open		sys_perf_event_open
 299	64	recvmmsg		sys_recvmmsg
-300	64	fanotify_init		sys_fanotify_init
-301	64	fanotify_mark		sys_fanotify_mark
-302	64	prlimit64		sys_prlimit64
-303	64	name_to_handle_at	sys_name_to_handle_at
-304	64	open_by_handle_at	sys_open_by_handle_at
-305	64	clock_adjtime		sys_clock_adjtime
-306	64	syncfs			sys_syncfs
+300	common	fanotify_init		sys_fanotify_init
+301	common	fanotify_mark		sys_fanotify_mark
+302	common	prlimit64		sys_prlimit64
+303	common	name_to_handle_at	sys_name_to_handle_at
+304	common	open_by_handle_at	sys_open_by_handle_at
+305	common	clock_adjtime		sys_clock_adjtime
+306	common	syncfs			sys_syncfs
 307	64	sendmmsg		sys_sendmmsg
-308	64	setns			sys_setns
-309	64	getcpu			sys_getcpu
+308	common	setns			sys_setns
+309	common	getcpu			sys_getcpu
 310	64	process_vm_readv	sys_process_vm_readv
 311	64	process_vm_writev	sys_process_vm_writev
+#
+# x32-specific system call numbers start at 512 to avoid cache impact
+# for native 64-bit operation.
+#
+512	x32	rt_sigaction		sys32_rt_sigaction
+513	x32	rt_sigreturn		stub_x32_rt_sigreturn
+514	x32	ioctl			compat_sys_ioctl
+515	x32	readv			compat_sys_readv
+516	x32	writev			compat_sys_writev
+517	x32	recvfrom		compat_sys_recvfrom
+518	x32	sendmsg			compat_sys_sendmsg
+519	x32	recvmsg			compat_sys_recvmsg
+520	x32	execve			stub_x32_execve
+521	x32	ptrace			compat_sys_ptrace
+522	x32	rt_sigpending		sys32_rt_sigpending
+523	x32	rt_sigtimedwait		compat_sys_rt_sigtimedwait
+524	x32	rt_sigqueueinfo		sys32_rt_sigqueueinfo
+525	x32	sigaltstack		stub_x32_sigaltstack
+526	x32	timer_create		compat_sys_timer_create
+527	x32	mq_notify		compat_sys_mq_notify
+528	x32	kexec_load		compat_sys_kexec_load
+529	x32	waitid			compat_sys_waitid
+530	x32	set_robust_list		compat_sys_set_robust_list
+531	x32	get_robust_list		compat_sys_get_robust_list
+532	x32	vmsplice		compat_sys_vmsplice
+533	x32	move_pages		compat_sys_move_pages
+534	x32	preadv			compat_sys_preadv64
+535	x32	pwritev			compat_sys_pwritev64
+536	x32	rt_tgsigqueueinfo	compat_sys_rt_tgsigqueueinfo
+537	x32	recvmmsg		compat_sys_recvmmsg
+538	x32	sendmmsg		compat_sys_sendmmsg
+539	x32	process_vm_readv	compat_sys_process_vm_readv
+540	x32	process_vm_writev	compat_sys_process_vm_writev
diff --git a/arch/x86/um/sys_call_table_64.c b/arch/x86/um/sys_call_table_64.c
index fe626c3..9924776 100644
--- a/arch/x86/um/sys_call_table_64.c
+++ b/arch/x86/um/sys_call_table_64.c
@@ -35,6 +35,9 @@
 #define stub_sigaltstack sys_sigaltstack
 #define stub_rt_sigreturn sys_rt_sigreturn
 
+#define __SYSCALL_COMMON(nr, sym, compat) __SYSCALL_64(nr, sym, compat)
+#define __SYSCALL_X32(nr, sym, compat) /* Not supported */
+
 #define __SYSCALL_64(nr, sym, compat) extern asmlinkage void sym(void) ;
 #include <asm/syscalls_64.h>
 
diff --git a/arch/x86/um/user-offsets.c b/arch/x86/um/user-offsets.c
index 5edf4f4..ce7e360 100644
--- a/arch/x86/um/user-offsets.c
+++ b/arch/x86/um/user-offsets.c
@@ -15,6 +15,8 @@
 };
 #else
 #define __SYSCALL_64(nr, sym, compat) [nr] = 1,
+#define __SYSCALL_COMMON(nr, sym, compat) [nr] = 1,
+#define __SYSCALL_X32(nr, sym, compat) /* Not supported */
 static char syscalls[] = {
 #include <asm/syscalls_64.h>
 };
diff --git a/arch/x86/vdso/.gitignore b/arch/x86/vdso/.gitignore
index 60274d5..3282874 100644
--- a/arch/x86/vdso/.gitignore
+++ b/arch/x86/vdso/.gitignore
@@ -1,5 +1,7 @@
 vdso.lds
 vdso-syms.lds
+vdsox32.lds
+vdsox32-syms.lds
 vdso32-syms.lds
 vdso32-syscall-syms.lds
 vdso32-sysenter-syms.lds
diff --git a/arch/x86/vdso/Makefile b/arch/x86/vdso/Makefile
index 5d17950..fd14be1 100644
--- a/arch/x86/vdso/Makefile
+++ b/arch/x86/vdso/Makefile
@@ -3,21 +3,29 @@
 #
 
 VDSO64-$(CONFIG_X86_64)		:= y
+VDSOX32-$(CONFIG_X86_X32_ABI)	:= y
 VDSO32-$(CONFIG_X86_32)		:= y
 VDSO32-$(CONFIG_COMPAT)		:= y
 
 vdso-install-$(VDSO64-y)	+= vdso.so
+vdso-install-$(VDSOX32-y)	+= vdsox32.so
 vdso-install-$(VDSO32-y)	+= $(vdso32-images)
 
 
 # files to link into the vdso
 vobjs-y := vdso-note.o vclock_gettime.o vgetcpu.o
 
+vobjs-$(VDSOX32-y) += $(vobjx32s-compat)
+
+# Filter out x32 objects.
+vobj64s := $(filter-out $(vobjx32s-compat),$(vobjs-y))
+
 # files to link into kernel
 obj-$(VDSO64-y)			+= vma.o vdso.o
+obj-$(VDSOX32-y)		+= vdsox32.o
 obj-$(VDSO32-y)			+= vdso32.o vdso32-setup.o
 
-vobjs := $(foreach F,$(vobjs-y),$(obj)/$F)
+vobjs := $(foreach F,$(vobj64s),$(obj)/$F)
 
 $(obj)/vdso.o: $(obj)/vdso.so
 
@@ -73,6 +81,42 @@
 	$(call if_changed,vdsosym)
 
 #
+# X32 processes use x32 vDSO to access 64bit kernel data.
+#
+# Build x32 vDSO image:
+# 1. Compile x32 vDSO as 64bit.
+# 2. Convert object files to x32.
+# 3. Build x32 VDSO image with x32 objects, which contains 64bit codes
+# so that it can reach 64bit address space with 64bit pointers.
+#
+
+targets += vdsox32-syms.lds
+obj-$(VDSOX32-y)		+= vdsox32-syms.lds
+
+CPPFLAGS_vdsox32.lds = $(CPPFLAGS_vdso.lds)
+VDSO_LDFLAGS_vdsox32.lds = -Wl,-m,elf32_x86_64 \
+			   -Wl,-soname=linux-vdso.so.1 \
+			   -Wl,-z,max-page-size=4096 \
+			   -Wl,-z,common-page-size=4096
+
+vobjx32s-y := $(vobj64s:.o=-x32.o)
+vobjx32s := $(foreach F,$(vobjx32s-y),$(obj)/$F)
+
+# Convert 64bit object file to x32 for x32 vDSO.
+quiet_cmd_x32 = X32     $@
+      cmd_x32 = $(OBJCOPY) -O elf32-x86-64 $< $@
+
+$(obj)/%-x32.o: $(obj)/%.o FORCE
+	$(call if_changed,x32)
+
+targets += vdsox32.so vdsox32.so.dbg vdsox32.lds $(vobjx32s-y)
+
+$(obj)/vdsox32.o: $(src)/vdsox32.S $(obj)/vdsox32.so
+
+$(obj)/vdsox32.so.dbg: $(src)/vdsox32.lds $(vobjx32s) FORCE
+	$(call if_changed,vdso)
+
+#
 # Build multiple 32-bit vDSO images to choose from at boot time.
 #
 obj-$(VDSO32-y)			+= vdso32-syms.lds
diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c
index 6bc0e72..885eff4 100644
--- a/arch/x86/vdso/vclock_gettime.c
+++ b/arch/x86/vdso/vclock_gettime.c
@@ -70,100 +70,98 @@
 	return ret;
 }
 
+notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz)
+{
+	long ret;
+
+	asm("syscall" : "=a" (ret) :
+	    "0" (__NR_gettimeofday), "D" (tv), "S" (tz) : "memory");
+	return ret;
+}
+
+
 notrace static inline long vgetns(void)
 {
 	long v;
 	cycles_t cycles;
 	if (gtod->clock.vclock_mode == VCLOCK_TSC)
 		cycles = vread_tsc();
-	else
+	else if (gtod->clock.vclock_mode == VCLOCK_HPET)
 		cycles = vread_hpet();
+	else
+		return 0;
 	v = (cycles - gtod->clock.cycle_last) & gtod->clock.mask;
 	return (v * gtod->clock.mult) >> gtod->clock.shift;
 }
 
-notrace static noinline int do_realtime(struct timespec *ts)
+/* Code size doesn't matter (vdso is 4k anyway) and this is faster. */
+notrace static int __always_inline do_realtime(struct timespec *ts)
 {
 	unsigned long seq, ns;
+	int mode;
+
 	do {
-		seq = read_seqbegin(&gtod->lock);
+		seq = read_seqcount_begin(&gtod->seq);
+		mode = gtod->clock.vclock_mode;
 		ts->tv_sec = gtod->wall_time_sec;
 		ts->tv_nsec = gtod->wall_time_nsec;
 		ns = vgetns();
-	} while (unlikely(read_seqretry(&gtod->lock, seq)));
+	} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
+
 	timespec_add_ns(ts, ns);
-	return 0;
+	return mode;
 }
 
-notrace static noinline int do_monotonic(struct timespec *ts)
+notrace static int do_monotonic(struct timespec *ts)
 {
-	unsigned long seq, ns, secs;
+	unsigned long seq, ns;
+	int mode;
+
 	do {
-		seq = read_seqbegin(&gtod->lock);
-		secs = gtod->wall_time_sec;
-		ns = gtod->wall_time_nsec + vgetns();
-		secs += gtod->wall_to_monotonic.tv_sec;
-		ns += gtod->wall_to_monotonic.tv_nsec;
-	} while (unlikely(read_seqretry(&gtod->lock, seq)));
+		seq = read_seqcount_begin(&gtod->seq);
+		mode = gtod->clock.vclock_mode;
+		ts->tv_sec = gtod->monotonic_time_sec;
+		ts->tv_nsec = gtod->monotonic_time_nsec;
+		ns = vgetns();
+	} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
+	timespec_add_ns(ts, ns);
 
-	/* wall_time_nsec, vgetns(), and wall_to_monotonic.tv_nsec
-	 * are all guaranteed to be nonnegative.
-	 */
-	while (ns >= NSEC_PER_SEC) {
-		ns -= NSEC_PER_SEC;
-		++secs;
-	}
-	ts->tv_sec = secs;
-	ts->tv_nsec = ns;
-
-	return 0;
+	return mode;
 }
 
-notrace static noinline int do_realtime_coarse(struct timespec *ts)
+notrace static int do_realtime_coarse(struct timespec *ts)
 {
 	unsigned long seq;
 	do {
-		seq = read_seqbegin(&gtod->lock);
+		seq = read_seqcount_begin(&gtod->seq);
 		ts->tv_sec = gtod->wall_time_coarse.tv_sec;
 		ts->tv_nsec = gtod->wall_time_coarse.tv_nsec;
-	} while (unlikely(read_seqretry(&gtod->lock, seq)));
+	} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
 	return 0;
 }
 
-notrace static noinline int do_monotonic_coarse(struct timespec *ts)
+notrace static int do_monotonic_coarse(struct timespec *ts)
 {
-	unsigned long seq, ns, secs;
+	unsigned long seq;
 	do {
-		seq = read_seqbegin(&gtod->lock);
-		secs = gtod->wall_time_coarse.tv_sec;
-		ns = gtod->wall_time_coarse.tv_nsec;
-		secs += gtod->wall_to_monotonic.tv_sec;
-		ns += gtod->wall_to_monotonic.tv_nsec;
-	} while (unlikely(read_seqretry(&gtod->lock, seq)));
-
-	/* wall_time_nsec and wall_to_monotonic.tv_nsec are
-	 * guaranteed to be between 0 and NSEC_PER_SEC.
-	 */
-	if (ns >= NSEC_PER_SEC) {
-		ns -= NSEC_PER_SEC;
-		++secs;
-	}
-	ts->tv_sec = secs;
-	ts->tv_nsec = ns;
+		seq = read_seqcount_begin(&gtod->seq);
+		ts->tv_sec = gtod->monotonic_time_coarse.tv_sec;
+		ts->tv_nsec = gtod->monotonic_time_coarse.tv_nsec;
+	} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
 
 	return 0;
 }
 
 notrace int __vdso_clock_gettime(clockid_t clock, struct timespec *ts)
 {
+	int ret = VCLOCK_NONE;
+
 	switch (clock) {
 	case CLOCK_REALTIME:
-		if (likely(gtod->clock.vclock_mode != VCLOCK_NONE))
-			return do_realtime(ts);
+		ret = do_realtime(ts);
 		break;
 	case CLOCK_MONOTONIC:
-		if (likely(gtod->clock.vclock_mode != VCLOCK_NONE))
-			return do_monotonic(ts);
+		ret = do_monotonic(ts);
 		break;
 	case CLOCK_REALTIME_COARSE:
 		return do_realtime_coarse(ts);
@@ -171,32 +169,33 @@
 		return do_monotonic_coarse(ts);
 	}
 
-	return vdso_fallback_gettime(clock, ts);
+	if (ret == VCLOCK_NONE)
+		return vdso_fallback_gettime(clock, ts);
+	return 0;
 }
 int clock_gettime(clockid_t, struct timespec *)
 	__attribute__((weak, alias("__vdso_clock_gettime")));
 
 notrace int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz)
 {
-	long ret;
-	if (likely(gtod->clock.vclock_mode != VCLOCK_NONE)) {
-		if (likely(tv != NULL)) {
-			BUILD_BUG_ON(offsetof(struct timeval, tv_usec) !=
-				     offsetof(struct timespec, tv_nsec) ||
-				     sizeof(*tv) != sizeof(struct timespec));
-			do_realtime((struct timespec *)tv);
-			tv->tv_usec /= 1000;
-		}
-		if (unlikely(tz != NULL)) {
-			/* Avoid memcpy. Some old compilers fail to inline it */
-			tz->tz_minuteswest = gtod->sys_tz.tz_minuteswest;
-			tz->tz_dsttime = gtod->sys_tz.tz_dsttime;
-		}
-		return 0;
+	long ret = VCLOCK_NONE;
+
+	if (likely(tv != NULL)) {
+		BUILD_BUG_ON(offsetof(struct timeval, tv_usec) !=
+			     offsetof(struct timespec, tv_nsec) ||
+			     sizeof(*tv) != sizeof(struct timespec));
+		ret = do_realtime((struct timespec *)tv);
+		tv->tv_usec /= 1000;
 	}
-	asm("syscall" : "=a" (ret) :
-	    "0" (__NR_gettimeofday), "D" (tv), "S" (tz) : "memory");
-	return ret;
+	if (unlikely(tz != NULL)) {
+		/* Avoid memcpy. Some old compilers fail to inline it */
+		tz->tz_minuteswest = gtod->sys_tz.tz_minuteswest;
+		tz->tz_dsttime = gtod->sys_tz.tz_dsttime;
+	}
+
+	if (ret == VCLOCK_NONE)
+		return vdso_fallback_gtod(tv, tz);
+	return 0;
 }
 int gettimeofday(struct timeval *, struct timezone *)
 	__attribute__((weak, alias("__vdso_gettimeofday")));
diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/vdso/vdso32-setup.c
index a944020..66e6d93 100644
--- a/arch/x86/vdso/vdso32-setup.c
+++ b/arch/x86/vdso/vdso32-setup.c
@@ -311,6 +311,11 @@
 	int ret = 0;
 	bool compat;
 
+#ifdef CONFIG_X86_X32_ABI
+	if (test_thread_flag(TIF_X32))
+		return x32_setup_additional_pages(bprm, uses_interp);
+#endif
+
 	if (vdso_enabled == VDSO_DISABLED)
 		return 0;
 
diff --git a/arch/x86/vdso/vdsox32.S b/arch/x86/vdso/vdsox32.S
new file mode 100644
index 0000000..d6b9a7f
--- /dev/null
+++ b/arch/x86/vdso/vdsox32.S
@@ -0,0 +1,22 @@
+#include <asm/page_types.h>
+#include <linux/linkage.h>
+#include <linux/init.h>
+
+__PAGE_ALIGNED_DATA
+
+	.globl vdsox32_start, vdsox32_end
+	.align PAGE_SIZE
+vdsox32_start:
+	.incbin "arch/x86/vdso/vdsox32.so"
+vdsox32_end:
+	.align PAGE_SIZE /* extra data here leaks to userspace. */
+
+.previous
+
+	.globl vdsox32_pages
+	.bss
+	.align 8
+	.type vdsox32_pages, @object
+vdsox32_pages:
+	.zero (vdsox32_end - vdsox32_start + PAGE_SIZE - 1) / PAGE_SIZE * 8
+	.size vdsox32_pages, .-vdsox32_pages
diff --git a/arch/x86/vdso/vdsox32.lds.S b/arch/x86/vdso/vdsox32.lds.S
new file mode 100644
index 0000000..62272aa
--- /dev/null
+++ b/arch/x86/vdso/vdsox32.lds.S
@@ -0,0 +1,28 @@
+/*
+ * Linker script for x32 vDSO.
+ * We #include the file to define the layout details.
+ * Here we only choose the prelinked virtual address.
+ *
+ * This file defines the version script giving the user-exported symbols in
+ * the DSO.  We can define local symbols here called VDSO* to make their
+ * values visible using the asm-x86/vdso.h macros from the kernel proper.
+ */
+
+#define VDSO_PRELINK 0
+#include "vdso-layout.lds.S"
+
+/*
+ * This controls what userland symbols we export from the vDSO.
+ */
+VERSION {
+	LINUX_2.6 {
+	global:
+		__vdso_clock_gettime;
+		__vdso_gettimeofday;
+		__vdso_getcpu;
+		__vdso_time;
+	local: *;
+	};
+}
+
+VDSOX32_PRELINK = VDSO_PRELINK;
diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c
index 17e1827..00aaf04 100644
--- a/arch/x86/vdso/vma.c
+++ b/arch/x86/vdso/vma.c
@@ -24,7 +24,44 @@
 extern struct page *vdso_pages[];
 static unsigned vdso_size;
 
-static void __init patch_vdso(void *vdso, size_t len)
+#ifdef CONFIG_X86_X32_ABI
+extern char vdsox32_start[], vdsox32_end[];
+extern struct page *vdsox32_pages[];
+static unsigned vdsox32_size;
+
+static void __init patch_vdsox32(void *vdso, size_t len)
+{
+	Elf32_Ehdr *hdr = vdso;
+	Elf32_Shdr *sechdrs, *alt_sec = 0;
+	char *secstrings;
+	void *alt_data;
+	int i;
+
+	BUG_ON(len < sizeof(Elf32_Ehdr));
+	BUG_ON(memcmp(hdr->e_ident, ELFMAG, SELFMAG) != 0);
+
+	sechdrs = (void *)hdr + hdr->e_shoff;
+	secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
+
+	for (i = 1; i < hdr->e_shnum; i++) {
+		Elf32_Shdr *shdr = &sechdrs[i];
+		if (!strcmp(secstrings + shdr->sh_name, ".altinstructions")) {
+			alt_sec = shdr;
+			goto found;
+		}
+	}
+
+	/* If we get here, it's probably a bug. */
+	pr_warning("patch_vdsox32: .altinstructions not found\n");
+	return;  /* nothing to patch */
+
+found:
+	alt_data = (void *)hdr + alt_sec->sh_offset;
+	apply_alternatives(alt_data, alt_data + alt_sec->sh_size);
+}
+#endif
+
+static void __init patch_vdso64(void *vdso, size_t len)
 {
 	Elf64_Ehdr *hdr = vdso;
 	Elf64_Shdr *sechdrs, *alt_sec = 0;
@@ -47,7 +84,7 @@
 	}
 
 	/* If we get here, it's probably a bug. */
-	pr_warning("patch_vdso: .altinstructions not found\n");
+	pr_warning("patch_vdso64: .altinstructions not found\n");
 	return;  /* nothing to patch */
 
 found:
@@ -60,12 +97,20 @@
 	int npages = (vdso_end - vdso_start + PAGE_SIZE - 1) / PAGE_SIZE;
 	int i;
 
-	patch_vdso(vdso_start, vdso_end - vdso_start);
+	patch_vdso64(vdso_start, vdso_end - vdso_start);
 
 	vdso_size = npages << PAGE_SHIFT;
 	for (i = 0; i < npages; i++)
 		vdso_pages[i] = virt_to_page(vdso_start + i*PAGE_SIZE);
 
+#ifdef CONFIG_X86_X32_ABI
+	patch_vdsox32(vdsox32_start, vdsox32_end - vdsox32_start);
+	npages = (vdsox32_end - vdsox32_start + PAGE_SIZE - 1) / PAGE_SIZE;
+	vdsox32_size = npages << PAGE_SHIFT;
+	for (i = 0; i < npages; i++)
+		vdsox32_pages[i] = virt_to_page(vdsox32_start + i*PAGE_SIZE);
+#endif
+
 	return 0;
 }
 subsys_initcall(init_vdso);
@@ -103,7 +148,10 @@
 
 /* Setup a VMA at program startup for the vsyscall page.
    Not called for compat tasks */
-int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
+static int setup_additional_pages(struct linux_binprm *bprm,
+				  int uses_interp,
+				  struct page **pages,
+				  unsigned size)
 {
 	struct mm_struct *mm = current->mm;
 	unsigned long addr;
@@ -113,8 +161,8 @@
 		return 0;
 
 	down_write(&mm->mmap_sem);
-	addr = vdso_addr(mm->start_stack, vdso_size);
-	addr = get_unmapped_area(NULL, addr, vdso_size, 0, 0);
+	addr = vdso_addr(mm->start_stack, size);
+	addr = get_unmapped_area(NULL, addr, size, 0, 0);
 	if (IS_ERR_VALUE(addr)) {
 		ret = addr;
 		goto up_fail;
@@ -122,10 +170,10 @@
 
 	current->mm->context.vdso = (void *)addr;
 
-	ret = install_special_mapping(mm, addr, vdso_size,
+	ret = install_special_mapping(mm, addr, size,
 				      VM_READ|VM_EXEC|
 				      VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
-				      vdso_pages);
+				      pages);
 	if (ret) {
 		current->mm->context.vdso = NULL;
 		goto up_fail;
@@ -136,6 +184,20 @@
 	return ret;
 }
 
+int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
+{
+	return setup_additional_pages(bprm, uses_interp, vdso_pages,
+				      vdso_size);
+}
+
+#ifdef CONFIG_X86_X32_ABI
+int x32_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
+{
+	return setup_additional_pages(bprm, uses_interp, vdsox32_pages,
+				      vdsox32_size);
+}
+#endif
+
 static __init int vdso_setup(char *s)
 {
 	vdso_enabled = simple_strtoul(s, NULL, 0);
diff --git a/arch/xtensa/configs/iss_defconfig b/arch/xtensa/configs/iss_defconfig
index f932b30..ddab37b 100644
--- a/arch/xtensa/configs/iss_defconfig
+++ b/arch/xtensa/configs/iss_defconfig
@@ -113,7 +113,7 @@
 # CONFIG_INLINE_SPIN_LOCK_BH is not set
 # CONFIG_INLINE_SPIN_LOCK_IRQ is not set
 # CONFIG_INLINE_SPIN_LOCK_IRQSAVE is not set
-CONFIG_INLINE_SPIN_UNLOCK=y
+# CONFIG_UNINLINE_SPIN_UNLOCK is not set
 # CONFIG_INLINE_SPIN_UNLOCK_BH is not set
 CONFIG_INLINE_SPIN_UNLOCK_IRQ=y
 # CONFIG_INLINE_SPIN_UNLOCK_IRQRESTORE is not set
diff --git a/arch/xtensa/include/asm/posix_types.h b/arch/xtensa/include/asm/posix_types.h
index 6b2190c..6e96be0 100644
--- a/arch/xtensa/include/asm/posix_types.h
+++ b/arch/xtensa/include/asm/posix_types.h
@@ -19,104 +19,21 @@
  * assume GCC is being used.
  */
 
-typedef unsigned long	__kernel_ino_t;
-typedef unsigned int	__kernel_mode_t;
-typedef unsigned long	__kernel_nlink_t;
-typedef long		__kernel_off_t;
-typedef int		__kernel_pid_t;
 typedef unsigned short	__kernel_ipc_pid_t;
-typedef unsigned int	__kernel_uid_t;
-typedef unsigned int	__kernel_gid_t;
+#define __kernel_ipc_pid_t __kernel_ipc_pid_t
+
 typedef unsigned int	__kernel_size_t;
 typedef int		__kernel_ssize_t;
 typedef long		__kernel_ptrdiff_t;
-typedef long		__kernel_time_t;
-typedef long		__kernel_suseconds_t;
-typedef long		__kernel_clock_t;
-typedef int		__kernel_timer_t;
-typedef int		__kernel_clockid_t;
-typedef int		__kernel_daddr_t;
-typedef char *		__kernel_caddr_t;
-typedef unsigned short	__kernel_uid16_t;
-typedef unsigned short	__kernel_gid16_t;
-typedef unsigned int	__kernel_uid32_t;
-typedef unsigned int	__kernel_gid32_t;
+#define __kernel_size_t __kernel_size_t
 
 typedef unsigned short	__kernel_old_uid_t;
 typedef unsigned short	__kernel_old_gid_t;
+#define __kernel_old_uid_t __kernel_old_uid_t
+
 typedef unsigned short	__kernel_old_dev_t;
+#define __kernel_old_dev_t __kernel_old_dev_t
 
-#ifdef __GNUC__
-typedef long long	__kernel_loff_t;
-#endif
+#include <asm-generic/posix_types.h>
 
-typedef struct {
-	int	val[2];
-} __kernel_fsid_t;
-
-#ifndef __GNUC__
-
-#define	__FD_SET(d, set)	((set)->fds_bits[__FDELT(d)] |= __FDMASK(d))
-#define	__FD_CLR(d, set)	((set)->fds_bits[__FDELT(d)] &= ~__FDMASK(d))
-#define	__FD_ISSET(d, set)	(!!((set)->fds_bits[__FDELT(d)] & __FDMASK(d)))
-#define	__FD_ZERO(set)	\
-  ((void) memset ((void *) (set), 0, sizeof (__kernel_fd_set)))
-
-#else /* __GNUC__ */
-
-#if defined(__KERNEL__)
-/* With GNU C, use inline functions instead so args are evaluated only once: */
-
-#undef __FD_SET
-static __inline__ void __FD_SET(unsigned long fd, __kernel_fd_set *fdsetp)
-{
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	fdsetp->fds_bits[_tmp] |= (1UL<<_rem);
-}
-
-#undef __FD_CLR
-static __inline__ void __FD_CLR(unsigned long fd, __kernel_fd_set *fdsetp)
-{
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	fdsetp->fds_bits[_tmp] &= ~(1UL<<_rem);
-}
-
-#undef __FD_ISSET
-static __inline__ int __FD_ISSET(unsigned long fd, __kernel_fd_set *p)
-{
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	return (p->fds_bits[_tmp] & (1UL<<_rem)) != 0;
-}
-
-/*
- * This will unroll the loop for the normal constant case (8 ints,
- * for a 256-bit fd_set)
- */
-#undef __FD_ZERO
-static __inline__ void __FD_ZERO(__kernel_fd_set *p)
-{
-	unsigned int *tmp = (unsigned int *)p->fds_bits;
-	int i;
-
-	if (__builtin_constant_p(__FDSET_LONGS)) {
-		switch (__FDSET_LONGS) {
-			case 8:
-				tmp[0] = 0; tmp[1] = 0; tmp[2] = 0; tmp[3] = 0;
-				tmp[4] = 0; tmp[5] = 0; tmp[6] = 0; tmp[7] = 0;
-				return;
-		}
-	}
-	i = __FDSET_LONGS;
-	while (i) {
-		i--;
-		*tmp = 0;
-		tmp++;
-	}
-}
-
-#endif /* defined(__KERNEL__) */
-#endif /* __GNUC__ */
 #endif /* _XTENSA_POSIX_TYPES_H */
diff --git a/drivers/char/lp.c b/drivers/char/lp.c
index 0fbf1a7..a741e41 100644
--- a/drivers/char/lp.c
+++ b/drivers/char/lp.c
@@ -705,16 +705,13 @@
 {
 	unsigned int minor;
 	struct timeval par_timeout;
-	struct compat_timeval __user *tc;
 	int ret;
 
 	minor = iminor(file->f_path.dentry->d_inode);
 	mutex_lock(&lp_mutex);
 	switch (cmd) {
 	case LPSETTIMEOUT:
-		tc = compat_ptr(arg);
-		if (get_user(par_timeout.tv_sec, &tc->tv_sec) ||
-		    get_user(par_timeout.tv_usec, &tc->tv_usec)) {
+		if (compat_get_timeval(&par_timeout, compat_ptr(arg))) {
 			ret = -EFAULT;
 			break;
 		}
diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index 999d6a0..5138927 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -26,7 +26,6 @@
 config CLKSRC_DBX500_PRCMU_SCHED_CLOCK
 	bool "Clocksource PRCMU Timer sched_clock"
 	depends on (CLKSRC_DBX500_PRCMU && !NOMADIK_MTU_SCHED_CLOCK)
-	select HAVE_SCHED_CLOCK
 	default y
 	help
 	  Use the always on PRCMU Timer as sched_clock
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index 4a6c46de..cf9da36 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -201,7 +201,6 @@
 	tristate "DMA API Driver for PL330"
 	select DMA_ENGINE
 	depends on ARM_AMBA
-	select PL330
 	help
 	  Select if your platform has one or more PL330 DMACs.
 	  You need to provide platform specific settings via
@@ -231,7 +230,7 @@
 
 config IMX_DMA
 	tristate "i.MX DMA support"
-	depends on IMX_HAVE_DMA_V1
+	depends on ARCH_MXC
 	select DMA_ENGINE
 	help
 	  Support the i.MX DMA engine. This engine is integrated into
diff --git a/drivers/dma/amba-pl08x.c b/drivers/dma/amba-pl08x.c
index 8a28158..c301a8e 100644
--- a/drivers/dma/amba-pl08x.c
+++ b/drivers/dma/amba-pl08x.c
@@ -85,6 +85,8 @@
 #include <linux/slab.h>
 #include <asm/hardware/pl080.h>
 
+#include "dmaengine.h"
+
 #define DRIVER_NAME	"pl08xdmac"
 
 static struct amba_driver pl08x_amba_driver;
@@ -649,7 +651,7 @@
 			}
 
 			if ((bd.srcbus.addr % bd.srcbus.buswidth) ||
-					(bd.srcbus.addr % bd.srcbus.buswidth)) {
+					(bd.dstbus.addr % bd.dstbus.buswidth)) {
 				dev_err(&pl08x->adev->dev,
 					"%s src & dst address must be aligned to src"
 					" & dst width if peripheral is flow controller",
@@ -919,13 +921,10 @@
 	struct pl08x_dma_chan *plchan = to_pl08x_chan(tx->chan);
 	struct pl08x_txd *txd = to_pl08x_txd(tx);
 	unsigned long flags;
+	dma_cookie_t cookie;
 
 	spin_lock_irqsave(&plchan->lock, flags);
-
-	plchan->chan.cookie += 1;
-	if (plchan->chan.cookie < 0)
-		plchan->chan.cookie = 1;
-	tx->cookie = plchan->chan.cookie;
+	cookie = dma_cookie_assign(tx);
 
 	/* Put this onto the pending list */
 	list_add_tail(&txd->node, &plchan->pend_list);
@@ -945,7 +944,7 @@
 
 	spin_unlock_irqrestore(&plchan->lock, flags);
 
-	return tx->cookie;
+	return cookie;
 }
 
 static struct dma_async_tx_descriptor *pl08x_prep_dma_interrupt(
@@ -965,31 +964,17 @@
 		dma_cookie_t cookie, struct dma_tx_state *txstate)
 {
 	struct pl08x_dma_chan *plchan = to_pl08x_chan(chan);
-	dma_cookie_t last_used;
-	dma_cookie_t last_complete;
 	enum dma_status ret;
-	u32 bytesleft = 0;
 
-	last_used = plchan->chan.cookie;
-	last_complete = plchan->lc;
-
-	ret = dma_async_is_complete(cookie, last_complete, last_used);
-	if (ret == DMA_SUCCESS) {
-		dma_set_tx_state(txstate, last_complete, last_used, 0);
+	ret = dma_cookie_status(chan, cookie, txstate);
+	if (ret == DMA_SUCCESS)
 		return ret;
-	}
 
 	/*
 	 * This cookie not complete yet
+	 * Get number of bytes left in the active transactions and queue
 	 */
-	last_used = plchan->chan.cookie;
-	last_complete = plchan->lc;
-
-	/* Get number of bytes left in the active transactions and queue */
-	bytesleft = pl08x_getbytes_chan(plchan);
-
-	dma_set_tx_state(txstate, last_complete, last_used,
-			 bytesleft);
+	dma_set_residue(txstate, pl08x_getbytes_chan(plchan));
 
 	if (plchan->state == PL08X_CHAN_PAUSED)
 		return DMA_PAUSED;
@@ -1139,6 +1124,8 @@
 	cctl |= burst << PL080_CONTROL_SB_SIZE_SHIFT;
 	cctl |= burst << PL080_CONTROL_DB_SIZE_SHIFT;
 
+	plchan->device_fc = config->device_fc;
+
 	if (plchan->runtime_direction == DMA_DEV_TO_MEM) {
 		plchan->src_addr = config->src_addr;
 		plchan->src_cctl = pl08x_cctl(cctl) | PL080_CONTROL_DST_INCR |
@@ -1326,7 +1313,7 @@
 static struct dma_async_tx_descriptor *pl08x_prep_slave_sg(
 		struct dma_chan *chan, struct scatterlist *sgl,
 		unsigned int sg_len, enum dma_transfer_direction direction,
-		unsigned long flags)
+		unsigned long flags, void *context)
 {
 	struct pl08x_dma_chan *plchan = to_pl08x_chan(chan);
 	struct pl08x_driver_data *pl08x = plchan->host;
@@ -1370,7 +1357,7 @@
 		return NULL;
 	}
 
-	if (plchan->cd->device_fc)
+	if (plchan->device_fc)
 		tmp = (direction == DMA_MEM_TO_DEV) ? PL080_FLOW_MEM2PER_PER :
 			PL080_FLOW_PER2MEM_PER;
 	else
@@ -1541,7 +1528,7 @@
 
 	if (txd) {
 		/* Update last completed */
-		plchan->lc = txd->tx.cookie;
+		dma_cookie_complete(&txd->tx);
 	}
 
 	/* If a new descriptor is queued, set it up plchan->at is NULL here */
@@ -1722,8 +1709,7 @@
 			 chan->name);
 
 		chan->chan.device = dmadev;
-		chan->chan.cookie = 0;
-		chan->lc = 0;
+		dma_cookie_init(&chan->chan);
 
 		spin_lock_init(&chan->lock);
 		INIT_LIST_HEAD(&chan->pend_list);
diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c
index f4aed5f..7aa58d2 100644
--- a/drivers/dma/at_hdmac.c
+++ b/drivers/dma/at_hdmac.c
@@ -27,6 +27,7 @@
 #include <linux/of_device.h>
 
 #include "at_hdmac_regs.h"
+#include "dmaengine.h"
 
 /*
  * Glossary
@@ -192,27 +193,6 @@
 }
 
 /**
- * atc_assign_cookie - compute and assign new cookie
- * @atchan: channel we work on
- * @desc: descriptor to assign cookie for
- *
- * Called with atchan->lock held and bh disabled
- */
-static dma_cookie_t
-atc_assign_cookie(struct at_dma_chan *atchan, struct at_desc *desc)
-{
-	dma_cookie_t cookie = atchan->chan_common.cookie;
-
-	if (++cookie < 0)
-		cookie = 1;
-
-	atchan->chan_common.cookie = cookie;
-	desc->txd.cookie = cookie;
-
-	return cookie;
-}
-
-/**
  * atc_dostart - starts the DMA engine for real
  * @atchan: the channel we want to start
  * @first: first descriptor in the list we want to begin with
@@ -269,7 +249,7 @@
 	dev_vdbg(chan2dev(&atchan->chan_common),
 		"descriptor %u complete\n", txd->cookie);
 
-	atchan->completed_cookie = txd->cookie;
+	dma_cookie_complete(txd);
 
 	/* move children to free_list */
 	list_splice_init(&desc->tx_list, &atchan->free_list);
@@ -547,7 +527,7 @@
 	unsigned long		flags;
 
 	spin_lock_irqsave(&atchan->lock, flags);
-	cookie = atc_assign_cookie(atchan, desc);
+	cookie = dma_cookie_assign(tx);
 
 	if (list_empty(&atchan->active_list)) {
 		dev_vdbg(chan2dev(tx->chan), "tx_submit: started %u\n",
@@ -659,14 +639,16 @@
  * @sg_len: number of entries in @scatterlist
  * @direction: DMA direction
  * @flags: tx descriptor status flags
+ * @context: transaction context (ignored)
  */
 static struct dma_async_tx_descriptor *
 atc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 		unsigned int sg_len, enum dma_transfer_direction direction,
-		unsigned long flags)
+		unsigned long flags, void *context)
 {
 	struct at_dma_chan	*atchan = to_at_dma_chan(chan);
 	struct at_dma_slave	*atslave = chan->private;
+	struct dma_slave_config	*sconfig = &atchan->dma_sconfig;
 	struct at_desc		*first = NULL;
 	struct at_desc		*prev = NULL;
 	u32			ctrla;
@@ -688,19 +670,18 @@
 		return NULL;
 	}
 
-	reg_width = atslave->reg_width;
-
 	ctrla = ATC_DEFAULT_CTRLA | atslave->ctrla;
 	ctrlb = ATC_IEN;
 
 	switch (direction) {
 	case DMA_MEM_TO_DEV:
+		reg_width = convert_buswidth(sconfig->dst_addr_width);
 		ctrla |=  ATC_DST_WIDTH(reg_width);
 		ctrlb |=  ATC_DST_ADDR_MODE_FIXED
 			| ATC_SRC_ADDR_MODE_INCR
 			| ATC_FC_MEM2PER
 			| ATC_SIF(AT_DMA_MEM_IF) | ATC_DIF(AT_DMA_PER_IF);
-		reg = atslave->tx_reg;
+		reg = sconfig->dst_addr;
 		for_each_sg(sgl, sg, sg_len, i) {
 			struct at_desc	*desc;
 			u32		len;
@@ -728,13 +709,14 @@
 		}
 		break;
 	case DMA_DEV_TO_MEM:
+		reg_width = convert_buswidth(sconfig->src_addr_width);
 		ctrla |=  ATC_SRC_WIDTH(reg_width);
 		ctrlb |=  ATC_DST_ADDR_MODE_INCR
 			| ATC_SRC_ADDR_MODE_FIXED
 			| ATC_FC_PER2MEM
 			| ATC_SIF(AT_DMA_PER_IF) | ATC_DIF(AT_DMA_MEM_IF);
 
-		reg = atslave->rx_reg;
+		reg = sconfig->src_addr;
 		for_each_sg(sgl, sg, sg_len, i) {
 			struct at_desc	*desc;
 			u32		len;
@@ -810,12 +792,15 @@
  * atc_dma_cyclic_fill_desc - Fill one period decriptor
  */
 static int
-atc_dma_cyclic_fill_desc(struct at_dma_slave *atslave, struct at_desc *desc,
+atc_dma_cyclic_fill_desc(struct dma_chan *chan, struct at_desc *desc,
 		unsigned int period_index, dma_addr_t buf_addr,
-		size_t period_len, enum dma_transfer_direction direction)
+		unsigned int reg_width, size_t period_len,
+		enum dma_transfer_direction direction)
 {
-	u32		ctrla;
-	unsigned int	reg_width = atslave->reg_width;
+	struct at_dma_chan	*atchan = to_at_dma_chan(chan);
+	struct at_dma_slave	*atslave = chan->private;
+	struct dma_slave_config	*sconfig = &atchan->dma_sconfig;
+	u32			ctrla;
 
 	/* prepare common CRTLA value */
 	ctrla =   ATC_DEFAULT_CTRLA | atslave->ctrla
@@ -826,7 +811,7 @@
 	switch (direction) {
 	case DMA_MEM_TO_DEV:
 		desc->lli.saddr = buf_addr + (period_len * period_index);
-		desc->lli.daddr = atslave->tx_reg;
+		desc->lli.daddr = sconfig->dst_addr;
 		desc->lli.ctrla = ctrla;
 		desc->lli.ctrlb = ATC_DST_ADDR_MODE_FIXED
 				| ATC_SRC_ADDR_MODE_INCR
@@ -836,7 +821,7 @@
 		break;
 
 	case DMA_DEV_TO_MEM:
-		desc->lli.saddr = atslave->rx_reg;
+		desc->lli.saddr = sconfig->src_addr;
 		desc->lli.daddr = buf_addr + (period_len * period_index);
 		desc->lli.ctrla = ctrla;
 		desc->lli.ctrlb = ATC_DST_ADDR_MODE_INCR
@@ -860,16 +845,20 @@
  * @buf_len: total number of bytes for the entire buffer
  * @period_len: number of bytes for each period
  * @direction: transfer direction, to or from device
+ * @context: transfer context (ignored)
  */
 static struct dma_async_tx_descriptor *
 atc_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len,
-		size_t period_len, enum dma_transfer_direction direction)
+		size_t period_len, enum dma_transfer_direction direction,
+		void *context)
 {
 	struct at_dma_chan	*atchan = to_at_dma_chan(chan);
 	struct at_dma_slave	*atslave = chan->private;
+	struct dma_slave_config	*sconfig = &atchan->dma_sconfig;
 	struct at_desc		*first = NULL;
 	struct at_desc		*prev = NULL;
 	unsigned long		was_cyclic;
+	unsigned int		reg_width;
 	unsigned int		periods = buf_len / period_len;
 	unsigned int		i;
 
@@ -889,8 +878,13 @@
 		return NULL;
 	}
 
+	if (sconfig->direction == DMA_MEM_TO_DEV)
+		reg_width = convert_buswidth(sconfig->dst_addr_width);
+	else
+		reg_width = convert_buswidth(sconfig->src_addr_width);
+
 	/* Check for too big/unaligned periods and unaligned DMA buffer */
-	if (atc_dma_cyclic_check_values(atslave->reg_width, buf_addr,
+	if (atc_dma_cyclic_check_values(reg_width, buf_addr,
 					period_len, direction))
 		goto err_out;
 
@@ -902,8 +896,8 @@
 		if (!desc)
 			goto err_desc_get;
 
-		if (atc_dma_cyclic_fill_desc(atslave, desc, i, buf_addr,
-						period_len, direction))
+		if (atc_dma_cyclic_fill_desc(chan, desc, i, buf_addr,
+					     reg_width, period_len, direction))
 			goto err_desc_get;
 
 		atc_desc_chain(&first, &prev, desc);
@@ -926,6 +920,23 @@
 	return NULL;
 }
 
+static int set_runtime_config(struct dma_chan *chan,
+			      struct dma_slave_config *sconfig)
+{
+	struct at_dma_chan	*atchan = to_at_dma_chan(chan);
+
+	/* Check if it is chan is configured for slave transfers */
+	if (!chan->private)
+		return -EINVAL;
+
+	memcpy(&atchan->dma_sconfig, sconfig, sizeof(*sconfig));
+
+	convert_burst(&atchan->dma_sconfig.src_maxburst);
+	convert_burst(&atchan->dma_sconfig.dst_maxburst);
+
+	return 0;
+}
+
 
 static int atc_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
 		       unsigned long arg)
@@ -986,6 +997,8 @@
 		clear_bit(ATC_IS_CYCLIC, &atchan->status);
 
 		spin_unlock_irqrestore(&atchan->lock, flags);
+	} else if (cmd == DMA_SLAVE_CONFIG) {
+		return set_runtime_config(chan, (struct dma_slave_config *)arg);
 	} else {
 		return -ENXIO;
 	}
@@ -1016,26 +1029,20 @@
 
 	spin_lock_irqsave(&atchan->lock, flags);
 
-	last_complete = atchan->completed_cookie;
-	last_used = chan->cookie;
-
-	ret = dma_async_is_complete(cookie, last_complete, last_used);
+	ret = dma_cookie_status(chan, cookie, txstate);
 	if (ret != DMA_SUCCESS) {
 		atc_cleanup_descriptors(atchan);
 
-		last_complete = atchan->completed_cookie;
-		last_used = chan->cookie;
-
-		ret = dma_async_is_complete(cookie, last_complete, last_used);
+		ret = dma_cookie_status(chan, cookie, txstate);
 	}
 
+	last_complete = chan->completed_cookie;
+	last_used = chan->cookie;
+
 	spin_unlock_irqrestore(&atchan->lock, flags);
 
 	if (ret != DMA_SUCCESS)
-		dma_set_tx_state(txstate, last_complete, last_used,
-			atc_first_active(atchan)->len);
-	else
-		dma_set_tx_state(txstate, last_complete, last_used, 0);
+		dma_set_residue(txstate, atc_first_active(atchan)->len);
 
 	if (atc_chan_is_paused(atchan))
 		ret = DMA_PAUSED;
@@ -1129,7 +1136,7 @@
 	spin_lock_irqsave(&atchan->lock, flags);
 	atchan->descs_allocated = i;
 	list_splice(&tmp_list, &atchan->free_list);
-	atchan->completed_cookie = chan->cookie = 1;
+	dma_cookie_init(chan);
 	spin_unlock_irqrestore(&atchan->lock, flags);
 
 	/* channel parameters */
@@ -1329,7 +1336,7 @@
 		struct at_dma_chan	*atchan = &atdma->chan[i];
 
 		atchan->chan_common.device = &atdma->dma_common;
-		atchan->chan_common.cookie = atchan->completed_cookie = 1;
+		dma_cookie_init(&atchan->chan_common);
 		list_add_tail(&atchan->chan_common.device_node,
 				&atdma->dma_common.channels);
 
diff --git a/drivers/dma/at_hdmac_regs.h b/drivers/dma/at_hdmac_regs.h
index a8d3277..897a8bc 100644
--- a/drivers/dma/at_hdmac_regs.h
+++ b/drivers/dma/at_hdmac_regs.h
@@ -207,8 +207,8 @@
  * @save_cfg: configuration register that is saved on suspend/resume cycle
  * @save_dscr: for cyclic operations, preserve next descriptor address in
  *             the cyclic list on suspend/resume cycle
+ * @dma_sconfig: configuration for slave transfers, passed via DMA_SLAVE_CONFIG
  * @lock: serializes enqueue/dequeue operations to descriptors lists
- * @completed_cookie: identifier for the most recently completed operation
  * @active_list: list of descriptors dmaengine is being running on
  * @queue: list of descriptors ready to be submitted to engine
  * @free_list: list of descriptors usable by the channel
@@ -223,11 +223,11 @@
 	struct tasklet_struct	tasklet;
 	u32			save_cfg;
 	u32			save_dscr;
+	struct dma_slave_config dma_sconfig;
 
 	spinlock_t		lock;
 
 	/* these other elements are all protected by lock */
-	dma_cookie_t		completed_cookie;
 	struct list_head	active_list;
 	struct list_head	queue;
 	struct list_head	free_list;
@@ -245,6 +245,36 @@
 	return container_of(dchan, struct at_dma_chan, chan_common);
 }
 
+/*
+ * Fix sconfig's burst size according to at_hdmac. We need to convert them as:
+ * 1 -> 0, 4 -> 1, 8 -> 2, 16 -> 3, 32 -> 4, 64 -> 5, 128 -> 6, 256 -> 7.
+ *
+ * This can be done by finding most significant bit set.
+ */
+static inline void convert_burst(u32 *maxburst)
+{
+	if (*maxburst > 1)
+		*maxburst = fls(*maxburst) - 2;
+	else
+		*maxburst = 0;
+}
+
+/*
+ * Fix sconfig's bus width according to at_hdmac.
+ * 1 byte -> 0, 2 bytes -> 1, 4 bytes -> 2.
+ */
+static inline u8 convert_buswidth(enum dma_slave_buswidth addr_width)
+{
+	switch (addr_width) {
+	case DMA_SLAVE_BUSWIDTH_2_BYTES:
+		return 1;
+	case DMA_SLAVE_BUSWIDTH_4_BYTES:
+		return 2;
+	default:
+		/* For 1 byte width or fallback */
+		return 0;
+	}
+}
 
 /*--  Controller  ------------------------------------------------------*/
 
diff --git a/drivers/dma/coh901318.c b/drivers/dma/coh901318.c
index d65a718..dc89455 100644
--- a/drivers/dma/coh901318.c
+++ b/drivers/dma/coh901318.c
@@ -24,6 +24,7 @@
 #include <mach/coh901318.h>
 
 #include "coh901318_lli.h"
+#include "dmaengine.h"
 
 #define COHC_2_DEV(cohc) (&cohc->chan.dev->device)
 
@@ -59,7 +60,6 @@
 struct coh901318_chan {
 	spinlock_t lock;
 	int allocated;
-	int completed;
 	int id;
 	int stopped;
 
@@ -318,20 +318,6 @@
 
 	return 0;
 }
-static dma_cookie_t
-coh901318_assign_cookie(struct coh901318_chan *cohc,
-			struct coh901318_desc *cohd)
-{
-	dma_cookie_t cookie = cohc->chan.cookie;
-
-	if (++cookie < 0)
-		cookie = 1;
-
-	cohc->chan.cookie = cookie;
-	cohd->desc.cookie = cookie;
-
-	return cookie;
-}
 
 static struct coh901318_desc *
 coh901318_desc_get(struct coh901318_chan *cohc)
@@ -705,7 +691,7 @@
 	callback_param = cohd_fin->desc.callback_param;
 
 	/* sign this job as completed on the channel */
-	cohc->completed = cohd_fin->desc.cookie;
+	dma_cookie_complete(&cohd_fin->desc);
 
 	/* release the lli allocation and remove the descriptor */
 	coh901318_lli_free(&cohc->base->pool, &cohd_fin->lli);
@@ -929,7 +915,7 @@
 	coh901318_config(cohc, NULL);
 
 	cohc->allocated = 1;
-	cohc->completed = chan->cookie = 1;
+	dma_cookie_init(chan);
 
 	spin_unlock_irqrestore(&cohc->lock, flags);
 
@@ -966,16 +952,16 @@
 						   desc);
 	struct coh901318_chan *cohc = to_coh901318_chan(tx->chan);
 	unsigned long flags;
+	dma_cookie_t cookie;
 
 	spin_lock_irqsave(&cohc->lock, flags);
-
-	tx->cookie = coh901318_assign_cookie(cohc, cohd);
+	cookie = dma_cookie_assign(tx);
 
 	coh901318_desc_queue(cohc, cohd);
 
 	spin_unlock_irqrestore(&cohc->lock, flags);
 
-	return tx->cookie;
+	return cookie;
 }
 
 static struct dma_async_tx_descriptor *
@@ -1035,7 +1021,7 @@
 static struct dma_async_tx_descriptor *
 coh901318_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 			unsigned int sg_len, enum dma_transfer_direction direction,
-			unsigned long flags)
+			unsigned long flags, void *context)
 {
 	struct coh901318_chan *cohc = to_coh901318_chan(chan);
 	struct coh901318_lli *lli;
@@ -1165,17 +1151,12 @@
 		 struct dma_tx_state *txstate)
 {
 	struct coh901318_chan *cohc = to_coh901318_chan(chan);
-	dma_cookie_t last_used;
-	dma_cookie_t last_complete;
-	int ret;
+	enum dma_status ret;
 
-	last_complete = cohc->completed;
-	last_used = chan->cookie;
+	ret = dma_cookie_status(chan, cookie, txstate);
+	/* FIXME: should be conditional on ret != DMA_SUCCESS? */
+	dma_set_residue(txstate, coh901318_get_bytes_left(chan));
 
-	ret = dma_async_is_complete(cookie, last_complete, last_used);
-
-	dma_set_tx_state(txstate, last_complete, last_used,
-			 coh901318_get_bytes_left(chan));
 	if (ret == DMA_IN_PROGRESS && cohc->stopped)
 		ret = DMA_PAUSED;
 
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index a6c6051..767bcc3 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -510,8 +510,8 @@
 					 dma_chan_name(chan));
 				list_del_rcu(&device->global_node);
 			} else if (err)
-				pr_debug("dmaengine: failed to get %s: (%d)\n",
-					 dma_chan_name(chan), err);
+				pr_debug("%s: failed to get %s: (%d)\n",
+					__func__, dma_chan_name(chan), err);
 			else
 				break;
 			if (--device->privatecnt == 0)
@@ -564,8 +564,8 @@
 				list_del_rcu(&device->global_node);
 				break;
 			} else if (err)
-				pr_err("dmaengine: failed to get %s: (%d)\n",
-				       dma_chan_name(chan), err);
+				pr_err("%s: failed to get %s: (%d)\n",
+					__func__, dma_chan_name(chan), err);
 		}
 	}
 
diff --git a/drivers/dma/dmaengine.h b/drivers/dma/dmaengine.h
new file mode 100644
index 0000000..17f983a
--- /dev/null
+++ b/drivers/dma/dmaengine.h
@@ -0,0 +1,89 @@
+/*
+ * The contents of this file are private to DMA engine drivers, and is not
+ * part of the API to be used by DMA engine users.
+ */
+#ifndef DMAENGINE_H
+#define DMAENGINE_H
+
+#include <linux/bug.h>
+#include <linux/dmaengine.h>
+
+/**
+ * dma_cookie_init - initialize the cookies for a DMA channel
+ * @chan: dma channel to initialize
+ */
+static inline void dma_cookie_init(struct dma_chan *chan)
+{
+	chan->cookie = DMA_MIN_COOKIE;
+	chan->completed_cookie = DMA_MIN_COOKIE;
+}
+
+/**
+ * dma_cookie_assign - assign a DMA engine cookie to the descriptor
+ * @tx: descriptor needing cookie
+ *
+ * Assign a unique non-zero per-channel cookie to the descriptor.
+ * Note: caller is expected to hold a lock to prevent concurrency.
+ */
+static inline dma_cookie_t dma_cookie_assign(struct dma_async_tx_descriptor *tx)
+{
+	struct dma_chan *chan = tx->chan;
+	dma_cookie_t cookie;
+
+	cookie = chan->cookie + 1;
+	if (cookie < DMA_MIN_COOKIE)
+		cookie = DMA_MIN_COOKIE;
+	tx->cookie = chan->cookie = cookie;
+
+	return cookie;
+}
+
+/**
+ * dma_cookie_complete - complete a descriptor
+ * @tx: descriptor to complete
+ *
+ * Mark this descriptor complete by updating the channels completed
+ * cookie marker.  Zero the descriptors cookie to prevent accidental
+ * repeated completions.
+ *
+ * Note: caller is expected to hold a lock to prevent concurrency.
+ */
+static inline void dma_cookie_complete(struct dma_async_tx_descriptor *tx)
+{
+	BUG_ON(tx->cookie < DMA_MIN_COOKIE);
+	tx->chan->completed_cookie = tx->cookie;
+	tx->cookie = 0;
+}
+
+/**
+ * dma_cookie_status - report cookie status
+ * @chan: dma channel
+ * @cookie: cookie we are interested in
+ * @state: dma_tx_state structure to return last/used cookies
+ *
+ * Report the status of the cookie, filling in the state structure if
+ * non-NULL.  No locking is required.
+ */
+static inline enum dma_status dma_cookie_status(struct dma_chan *chan,
+	dma_cookie_t cookie, struct dma_tx_state *state)
+{
+	dma_cookie_t used, complete;
+
+	used = chan->cookie;
+	complete = chan->completed_cookie;
+	barrier();
+	if (state) {
+		state->last = complete;
+		state->used = used;
+		state->residue = 0;
+	}
+	return dma_async_is_complete(cookie, complete, used);
+}
+
+static inline void dma_set_residue(struct dma_tx_state *state, u32 residue)
+{
+	if (state)
+		state->residue = residue;
+}
+
+#endif
diff --git a/drivers/dma/dw_dmac.c b/drivers/dma/dw_dmac.c
index 9b592b0..7439079 100644
--- a/drivers/dma/dw_dmac.c
+++ b/drivers/dma/dw_dmac.c
@@ -9,6 +9,7 @@
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
+#include <linux/bitops.h>
 #include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/dmaengine.h>
@@ -22,6 +23,7 @@
 #include <linux/slab.h>
 
 #include "dw_dmac_regs.h"
+#include "dmaengine.h"
 
 /*
  * This supports the Synopsys "DesignWare AHB Central DMA Controller",
@@ -33,19 +35,23 @@
  * which does not support descriptor writeback.
  */
 
-#define DWC_DEFAULT_CTLLO(private) ({				\
-		struct dw_dma_slave *__slave = (private);	\
-		int dms = __slave ? __slave->dst_master : 0;	\
-		int sms = __slave ? __slave->src_master : 1;	\
-		u8 smsize = __slave ? __slave->src_msize : DW_DMA_MSIZE_16; \
-		u8 dmsize = __slave ? __slave->dst_msize : DW_DMA_MSIZE_16; \
+#define DWC_DEFAULT_CTLLO(_chan) ({				\
+		struct dw_dma_slave *__slave = (_chan->private);	\
+		struct dw_dma_chan *_dwc = to_dw_dma_chan(_chan);	\
+		struct dma_slave_config	*_sconfig = &_dwc->dma_sconfig;	\
+		int _dms = __slave ? __slave->dst_master : 0;	\
+		int _sms = __slave ? __slave->src_master : 1;	\
+		u8 _smsize = __slave ? _sconfig->src_maxburst :	\
+			DW_DMA_MSIZE_16;			\
+		u8 _dmsize = __slave ? _sconfig->dst_maxburst :	\
+			DW_DMA_MSIZE_16;			\
 								\
-		(DWC_CTLL_DST_MSIZE(dmsize)			\
-		 | DWC_CTLL_SRC_MSIZE(smsize)			\
+		(DWC_CTLL_DST_MSIZE(_dmsize)			\
+		 | DWC_CTLL_SRC_MSIZE(_smsize)			\
 		 | DWC_CTLL_LLP_D_EN				\
 		 | DWC_CTLL_LLP_S_EN				\
-		 | DWC_CTLL_DMS(dms)				\
-		 | DWC_CTLL_SMS(sms));				\
+		 | DWC_CTLL_DMS(_dms)				\
+		 | DWC_CTLL_SMS(_sms));				\
 	})
 
 /*
@@ -151,21 +157,6 @@
 	}
 }
 
-/* Called with dwc->lock held and bh disabled */
-static dma_cookie_t
-dwc_assign_cookie(struct dw_dma_chan *dwc, struct dw_desc *desc)
-{
-	dma_cookie_t cookie = dwc->chan.cookie;
-
-	if (++cookie < 0)
-		cookie = 1;
-
-	dwc->chan.cookie = cookie;
-	desc->txd.cookie = cookie;
-
-	return cookie;
-}
-
 static void dwc_initialize(struct dw_dma_chan *dwc)
 {
 	struct dw_dma *dw = to_dw_dma(dwc->chan.device);
@@ -192,7 +183,6 @@
 
 	/* Enable interrupts */
 	channel_set_bit(dw, MASK.XFER, dwc->mask);
-	channel_set_bit(dw, MASK.BLOCK, dwc->mask);
 	channel_set_bit(dw, MASK.ERROR, dwc->mask);
 
 	dwc->initialized = true;
@@ -245,7 +235,7 @@
 	dev_vdbg(chan2dev(&dwc->chan), "descriptor %u complete\n", txd->cookie);
 
 	spin_lock_irqsave(&dwc->lock, flags);
-	dwc->completed = txd->cookie;
+	dma_cookie_complete(txd);
 	if (callback_required) {
 		callback = txd->callback;
 		param = txd->callback_param;
@@ -329,12 +319,6 @@
 	unsigned long flags;
 
 	spin_lock_irqsave(&dwc->lock, flags);
-	/*
-	 * Clear block interrupt flag before scanning so that we don't
-	 * miss any, and read LLP before RAW_XFER to ensure it is
-	 * valid if we decide to scan the list.
-	 */
-	dma_writel(dw, CLEAR.BLOCK, dwc->mask);
 	llp = channel_readl(dwc, LLP);
 	status_xfer = dma_readl(dw, RAW.XFER);
 
@@ -470,17 +454,16 @@
 
 /* called with dwc->lock held and all DMAC interrupts disabled */
 static void dwc_handle_cyclic(struct dw_dma *dw, struct dw_dma_chan *dwc,
-		u32 status_block, u32 status_err, u32 status_xfer)
+		u32 status_err, u32 status_xfer)
 {
 	unsigned long flags;
 
-	if (status_block & dwc->mask) {
+	if (dwc->mask) {
 		void (*callback)(void *param);
 		void *callback_param;
 
 		dev_vdbg(chan2dev(&dwc->chan), "new cyclic period llp 0x%08x\n",
 				channel_readl(dwc, LLP));
-		dma_writel(dw, CLEAR.BLOCK, dwc->mask);
 
 		callback = dwc->cdesc->period_callback;
 		callback_param = dwc->cdesc->period_callback_param;
@@ -520,7 +503,6 @@
 		channel_writel(dwc, CTL_LO, 0);
 		channel_writel(dwc, CTL_HI, 0);
 
-		dma_writel(dw, CLEAR.BLOCK, dwc->mask);
 		dma_writel(dw, CLEAR.ERROR, dwc->mask);
 		dma_writel(dw, CLEAR.XFER, dwc->mask);
 
@@ -537,36 +519,29 @@
 {
 	struct dw_dma *dw = (struct dw_dma *)data;
 	struct dw_dma_chan *dwc;
-	u32 status_block;
 	u32 status_xfer;
 	u32 status_err;
 	int i;
 
-	status_block = dma_readl(dw, RAW.BLOCK);
 	status_xfer = dma_readl(dw, RAW.XFER);
 	status_err = dma_readl(dw, RAW.ERROR);
 
-	dev_vdbg(dw->dma.dev, "tasklet: status_block=%x status_err=%x\n",
-			status_block, status_err);
+	dev_vdbg(dw->dma.dev, "tasklet: status_err=%x\n", status_err);
 
 	for (i = 0; i < dw->dma.chancnt; i++) {
 		dwc = &dw->chan[i];
 		if (test_bit(DW_DMA_IS_CYCLIC, &dwc->flags))
-			dwc_handle_cyclic(dw, dwc, status_block, status_err,
-					status_xfer);
+			dwc_handle_cyclic(dw, dwc, status_err, status_xfer);
 		else if (status_err & (1 << i))
 			dwc_handle_error(dw, dwc);
-		else if ((status_block | status_xfer) & (1 << i))
+		else if (status_xfer & (1 << i))
 			dwc_scan_descriptors(dw, dwc);
 	}
 
 	/*
-	 * Re-enable interrupts. Block Complete interrupts are only
-	 * enabled if the INT_EN bit in the descriptor is set. This
-	 * will trigger a scan before the whole list is done.
+	 * Re-enable interrupts.
 	 */
 	channel_set_bit(dw, MASK.XFER, dw->all_chan_mask);
-	channel_set_bit(dw, MASK.BLOCK, dw->all_chan_mask);
 	channel_set_bit(dw, MASK.ERROR, dw->all_chan_mask);
 }
 
@@ -583,7 +558,6 @@
 	 * softirq handler.
 	 */
 	channel_clear_bit(dw, MASK.XFER, dw->all_chan_mask);
-	channel_clear_bit(dw, MASK.BLOCK, dw->all_chan_mask);
 	channel_clear_bit(dw, MASK.ERROR, dw->all_chan_mask);
 
 	status = dma_readl(dw, STATUS_INT);
@@ -594,7 +568,6 @@
 
 		/* Try to recover */
 		channel_clear_bit(dw, MASK.XFER, (1 << 8) - 1);
-		channel_clear_bit(dw, MASK.BLOCK, (1 << 8) - 1);
 		channel_clear_bit(dw, MASK.SRC_TRAN, (1 << 8) - 1);
 		channel_clear_bit(dw, MASK.DST_TRAN, (1 << 8) - 1);
 		channel_clear_bit(dw, MASK.ERROR, (1 << 8) - 1);
@@ -615,7 +588,7 @@
 	unsigned long		flags;
 
 	spin_lock_irqsave(&dwc->lock, flags);
-	cookie = dwc_assign_cookie(dwc, desc);
+	cookie = dma_cookie_assign(tx);
 
 	/*
 	 * REVISIT: We should attempt to chain as many descriptors as
@@ -674,7 +647,7 @@
 	else
 		src_width = dst_width = 0;
 
-	ctllo = DWC_DEFAULT_CTLLO(chan->private)
+	ctllo = DWC_DEFAULT_CTLLO(chan)
 			| DWC_CTLL_DST_WIDTH(dst_width)
 			| DWC_CTLL_SRC_WIDTH(src_width)
 			| DWC_CTLL_DST_INC
@@ -731,10 +704,11 @@
 static struct dma_async_tx_descriptor *
 dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 		unsigned int sg_len, enum dma_transfer_direction direction,
-		unsigned long flags)
+		unsigned long flags, void *context)
 {
 	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
 	struct dw_dma_slave	*dws = chan->private;
+	struct dma_slave_config	*sconfig = &dwc->dma_sconfig;
 	struct dw_desc		*prev;
 	struct dw_desc		*first;
 	u32			ctllo;
@@ -750,25 +724,34 @@
 	if (unlikely(!dws || !sg_len))
 		return NULL;
 
-	reg_width = dws->reg_width;
 	prev = first = NULL;
 
 	switch (direction) {
 	case DMA_MEM_TO_DEV:
-		ctllo = (DWC_DEFAULT_CTLLO(chan->private)
+		reg_width = __fls(sconfig->dst_addr_width);
+		reg = sconfig->dst_addr;
+		ctllo = (DWC_DEFAULT_CTLLO(chan)
 				| DWC_CTLL_DST_WIDTH(reg_width)
 				| DWC_CTLL_DST_FIX
-				| DWC_CTLL_SRC_INC
-				| DWC_CTLL_FC(dws->fc));
-		reg = dws->tx_reg;
+				| DWC_CTLL_SRC_INC);
+
+		ctllo |= sconfig->device_fc ? DWC_CTLL_FC(DW_DMA_FC_P_M2P) :
+			DWC_CTLL_FC(DW_DMA_FC_D_M2P);
+
 		for_each_sg(sgl, sg, sg_len, i) {
 			struct dw_desc	*desc;
 			u32		len, dlen, mem;
 
 			mem = sg_phys(sg);
 			len = sg_dma_len(sg);
-			mem_width = 2;
-			if (unlikely(mem & 3 || len & 3))
+
+			if (!((mem | len) & 7))
+				mem_width = 3;
+			else if (!((mem | len) & 3))
+				mem_width = 2;
+			else if (!((mem | len) & 1))
+				mem_width = 1;
+			else
 				mem_width = 0;
 
 slave_sg_todev_fill_desc:
@@ -812,21 +795,30 @@
 		}
 		break;
 	case DMA_DEV_TO_MEM:
-		ctllo = (DWC_DEFAULT_CTLLO(chan->private)
+		reg_width = __fls(sconfig->src_addr_width);
+		reg = sconfig->src_addr;
+		ctllo = (DWC_DEFAULT_CTLLO(chan)
 				| DWC_CTLL_SRC_WIDTH(reg_width)
 				| DWC_CTLL_DST_INC
-				| DWC_CTLL_SRC_FIX
-				| DWC_CTLL_FC(dws->fc));
+				| DWC_CTLL_SRC_FIX);
 
-		reg = dws->rx_reg;
+		ctllo |= sconfig->device_fc ? DWC_CTLL_FC(DW_DMA_FC_P_P2M) :
+			DWC_CTLL_FC(DW_DMA_FC_D_P2M);
+
 		for_each_sg(sgl, sg, sg_len, i) {
 			struct dw_desc	*desc;
 			u32		len, dlen, mem;
 
 			mem = sg_phys(sg);
 			len = sg_dma_len(sg);
-			mem_width = 2;
-			if (unlikely(mem & 3 || len & 3))
+
+			if (!((mem | len) & 7))
+				mem_width = 3;
+			else if (!((mem | len) & 3))
+				mem_width = 2;
+			else if (!((mem | len) & 1))
+				mem_width = 1;
+			else
 				mem_width = 0;
 
 slave_sg_fromdev_fill_desc:
@@ -890,6 +882,39 @@
 	return NULL;
 }
 
+/*
+ * Fix sconfig's burst size according to dw_dmac. We need to convert them as:
+ * 1 -> 0, 4 -> 1, 8 -> 2, 16 -> 3.
+ *
+ * NOTE: burst size 2 is not supported by controller.
+ *
+ * This can be done by finding least significant bit set: n & (n - 1)
+ */
+static inline void convert_burst(u32 *maxburst)
+{
+	if (*maxburst > 1)
+		*maxburst = fls(*maxburst) - 2;
+	else
+		*maxburst = 0;
+}
+
+static int
+set_runtime_config(struct dma_chan *chan, struct dma_slave_config *sconfig)
+{
+	struct dw_dma_chan *dwc = to_dw_dma_chan(chan);
+
+	/* Check if it is chan is configured for slave transfers */
+	if (!chan->private)
+		return -EINVAL;
+
+	memcpy(&dwc->dma_sconfig, sconfig, sizeof(*sconfig));
+
+	convert_burst(&dwc->dma_sconfig.src_maxburst);
+	convert_burst(&dwc->dma_sconfig.dst_maxburst);
+
+	return 0;
+}
+
 static int dwc_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
 		       unsigned long arg)
 {
@@ -939,8 +964,11 @@
 		/* Flush all pending and queued descriptors */
 		list_for_each_entry_safe(desc, _desc, &list, desc_node)
 			dwc_descriptor_complete(dwc, desc, false);
-	} else
+	} else if (cmd == DMA_SLAVE_CONFIG) {
+		return set_runtime_config(chan, (struct dma_slave_config *)arg);
+	} else {
 		return -ENXIO;
+	}
 
 	return 0;
 }
@@ -951,28 +979,17 @@
 	      struct dma_tx_state *txstate)
 {
 	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
-	dma_cookie_t		last_used;
-	dma_cookie_t		last_complete;
-	int			ret;
+	enum dma_status		ret;
 
-	last_complete = dwc->completed;
-	last_used = chan->cookie;
-
-	ret = dma_async_is_complete(cookie, last_complete, last_used);
+	ret = dma_cookie_status(chan, cookie, txstate);
 	if (ret != DMA_SUCCESS) {
 		dwc_scan_descriptors(to_dw_dma(chan->device), dwc);
 
-		last_complete = dwc->completed;
-		last_used = chan->cookie;
-
-		ret = dma_async_is_complete(cookie, last_complete, last_used);
+		ret = dma_cookie_status(chan, cookie, txstate);
 	}
 
 	if (ret != DMA_SUCCESS)
-		dma_set_tx_state(txstate, last_complete, last_used,
-				dwc_first_active(dwc)->len);
-	else
-		dma_set_tx_state(txstate, last_complete, last_used, 0);
+		dma_set_residue(txstate, dwc_first_active(dwc)->len);
 
 	if (dwc->paused)
 		return DMA_PAUSED;
@@ -1004,7 +1021,7 @@
 		return -EIO;
 	}
 
-	dwc->completed = chan->cookie = 1;
+	dma_cookie_init(chan);
 
 	/*
 	 * NOTE: some controllers may have additional features that we
@@ -1068,7 +1085,6 @@
 
 	/* Disable interrupts */
 	channel_clear_bit(dw, MASK.XFER, dwc->mask);
-	channel_clear_bit(dw, MASK.BLOCK, dwc->mask);
 	channel_clear_bit(dw, MASK.ERROR, dwc->mask);
 
 	spin_unlock_irqrestore(&dwc->lock, flags);
@@ -1120,7 +1136,6 @@
 		return -EBUSY;
 	}
 
-	dma_writel(dw, CLEAR.BLOCK, dwc->mask);
 	dma_writel(dw, CLEAR.ERROR, dwc->mask);
 	dma_writel(dw, CLEAR.XFER, dwc->mask);
 
@@ -1175,11 +1190,11 @@
 		enum dma_transfer_direction direction)
 {
 	struct dw_dma_chan		*dwc = to_dw_dma_chan(chan);
+	struct dma_slave_config		*sconfig = &dwc->dma_sconfig;
 	struct dw_cyclic_desc		*cdesc;
 	struct dw_cyclic_desc		*retval = NULL;
 	struct dw_desc			*desc;
 	struct dw_desc			*last = NULL;
-	struct dw_dma_slave		*dws = chan->private;
 	unsigned long			was_cyclic;
 	unsigned int			reg_width;
 	unsigned int			periods;
@@ -1203,7 +1218,12 @@
 	}
 
 	retval = ERR_PTR(-EINVAL);
-	reg_width = dws->reg_width;
+
+	if (direction == DMA_MEM_TO_DEV)
+		reg_width = __ffs(sconfig->dst_addr_width);
+	else
+		reg_width = __ffs(sconfig->src_addr_width);
+
 	periods = buf_len / period_len;
 
 	/* Check for too big/unaligned periods and unaligned DMA buffer. */
@@ -1236,26 +1256,34 @@
 
 		switch (direction) {
 		case DMA_MEM_TO_DEV:
-			desc->lli.dar = dws->tx_reg;
+			desc->lli.dar = sconfig->dst_addr;
 			desc->lli.sar = buf_addr + (period_len * i);
-			desc->lli.ctllo = (DWC_DEFAULT_CTLLO(chan->private)
+			desc->lli.ctllo = (DWC_DEFAULT_CTLLO(chan)
 					| DWC_CTLL_DST_WIDTH(reg_width)
 					| DWC_CTLL_SRC_WIDTH(reg_width)
 					| DWC_CTLL_DST_FIX
 					| DWC_CTLL_SRC_INC
-					| DWC_CTLL_FC(dws->fc)
 					| DWC_CTLL_INT_EN);
+
+			desc->lli.ctllo |= sconfig->device_fc ?
+				DWC_CTLL_FC(DW_DMA_FC_P_M2P) :
+				DWC_CTLL_FC(DW_DMA_FC_D_M2P);
+
 			break;
 		case DMA_DEV_TO_MEM:
 			desc->lli.dar = buf_addr + (period_len * i);
-			desc->lli.sar = dws->rx_reg;
-			desc->lli.ctllo = (DWC_DEFAULT_CTLLO(chan->private)
+			desc->lli.sar = sconfig->src_addr;
+			desc->lli.ctllo = (DWC_DEFAULT_CTLLO(chan)
 					| DWC_CTLL_SRC_WIDTH(reg_width)
 					| DWC_CTLL_DST_WIDTH(reg_width)
 					| DWC_CTLL_DST_INC
 					| DWC_CTLL_SRC_FIX
-					| DWC_CTLL_FC(dws->fc)
 					| DWC_CTLL_INT_EN);
+
+			desc->lli.ctllo |= sconfig->device_fc ?
+				DWC_CTLL_FC(DW_DMA_FC_P_P2M) :
+				DWC_CTLL_FC(DW_DMA_FC_D_P2M);
+
 			break;
 		default:
 			break;
@@ -1322,7 +1350,6 @@
 	while (dma_readl(dw, CH_EN) & dwc->mask)
 		cpu_relax();
 
-	dma_writel(dw, CLEAR.BLOCK, dwc->mask);
 	dma_writel(dw, CLEAR.ERROR, dwc->mask);
 	dma_writel(dw, CLEAR.XFER, dwc->mask);
 
@@ -1347,7 +1374,6 @@
 	dma_writel(dw, CFG, 0);
 
 	channel_clear_bit(dw, MASK.XFER, dw->all_chan_mask);
-	channel_clear_bit(dw, MASK.BLOCK, dw->all_chan_mask);
 	channel_clear_bit(dw, MASK.SRC_TRAN, dw->all_chan_mask);
 	channel_clear_bit(dw, MASK.DST_TRAN, dw->all_chan_mask);
 	channel_clear_bit(dw, MASK.ERROR, dw->all_chan_mask);
@@ -1369,7 +1395,7 @@
 	int			err;
 	int			i;
 
-	pdata = pdev->dev.platform_data;
+	pdata = dev_get_platdata(&pdev->dev);
 	if (!pdata || pdata->nr_channels > DW_DMA_MAX_NR_CHANNELS)
 		return -EINVAL;
 
@@ -1423,7 +1449,7 @@
 		struct dw_dma_chan	*dwc = &dw->chan[i];
 
 		dwc->chan.device = &dw->dma;
-		dwc->chan.cookie = dwc->completed = 1;
+		dma_cookie_init(&dwc->chan);
 		if (pdata->chan_allocation_order == CHAN_ALLOCATION_ASCENDING)
 			list_add_tail(&dwc->chan.device_node,
 					&dw->dma.channels);
@@ -1432,7 +1458,7 @@
 
 		/* 7 is highest priority & 0 is lowest. */
 		if (pdata->chan_priority == CHAN_PRIORITY_ASCENDING)
-			dwc->priority = 7 - i;
+			dwc->priority = pdata->nr_channels - i - 1;
 		else
 			dwc->priority = i;
 
@@ -1449,13 +1475,11 @@
 
 	/* Clear/disable all interrupts on all channels. */
 	dma_writel(dw, CLEAR.XFER, dw->all_chan_mask);
-	dma_writel(dw, CLEAR.BLOCK, dw->all_chan_mask);
 	dma_writel(dw, CLEAR.SRC_TRAN, dw->all_chan_mask);
 	dma_writel(dw, CLEAR.DST_TRAN, dw->all_chan_mask);
 	dma_writel(dw, CLEAR.ERROR, dw->all_chan_mask);
 
 	channel_clear_bit(dw, MASK.XFER, dw->all_chan_mask);
-	channel_clear_bit(dw, MASK.BLOCK, dw->all_chan_mask);
 	channel_clear_bit(dw, MASK.SRC_TRAN, dw->all_chan_mask);
 	channel_clear_bit(dw, MASK.DST_TRAN, dw->all_chan_mask);
 	channel_clear_bit(dw, MASK.ERROR, dw->all_chan_mask);
@@ -1562,6 +1586,10 @@
 static const struct dev_pm_ops dw_dev_pm_ops = {
 	.suspend_noirq = dw_suspend_noirq,
 	.resume_noirq = dw_resume_noirq,
+	.freeze_noirq = dw_suspend_noirq,
+	.thaw_noirq = dw_resume_noirq,
+	.restore_noirq = dw_resume_noirq,
+	.poweroff_noirq = dw_suspend_noirq,
 };
 
 static struct platform_driver dw_driver = {
diff --git a/drivers/dma/dw_dmac_regs.h b/drivers/dma/dw_dmac_regs.h
index 5eef694..f298f69 100644
--- a/drivers/dma/dw_dmac_regs.h
+++ b/drivers/dma/dw_dmac_regs.h
@@ -13,6 +13,18 @@
 
 #define DW_DMA_MAX_NR_CHANNELS	8
 
+/* flow controller */
+enum dw_dma_fc {
+	DW_DMA_FC_D_M2M,
+	DW_DMA_FC_D_M2P,
+	DW_DMA_FC_D_P2M,
+	DW_DMA_FC_D_P2P,
+	DW_DMA_FC_P_P2M,
+	DW_DMA_FC_SP_P2P,
+	DW_DMA_FC_P_M2P,
+	DW_DMA_FC_DP_P2P,
+};
+
 /*
  * Redefine this macro to handle differences between 32- and 64-bit
  * addressing, big vs. little endian, etc.
@@ -146,13 +158,15 @@
 
 	/* these other elements are all protected by lock */
 	unsigned long		flags;
-	dma_cookie_t		completed;
 	struct list_head	active_list;
 	struct list_head	queue;
 	struct list_head	free_list;
 	struct dw_cyclic_desc	*cdesc;
 
 	unsigned int		descs_allocated;
+
+	/* configuration passed via DMA_SLAVE_CONFIG */
+	struct dma_slave_config dma_sconfig;
 };
 
 static inline struct dw_dma_chan_regs __iomem *
diff --git a/drivers/dma/ep93xx_dma.c b/drivers/dma/ep93xx_dma.c
index 59e7a96..e6f133b 100644
--- a/drivers/dma/ep93xx_dma.c
+++ b/drivers/dma/ep93xx_dma.c
@@ -28,6 +28,8 @@
 
 #include <mach/dma.h>
 
+#include "dmaengine.h"
+
 /* M2P registers */
 #define M2P_CONTROL			0x0000
 #define M2P_CONTROL_STALLINT		BIT(0)
@@ -122,7 +124,6 @@
  * @lock: lock protecting the fields following
  * @flags: flags for the channel
  * @buffer: which buffer to use next (0/1)
- * @last_completed: last completed cookie value
  * @active: flattened chain of descriptors currently being processed
  * @queue: pending descriptors which are handled next
  * @free_list: list of free descriptors which can be used
@@ -157,7 +158,6 @@
 #define EP93XX_DMA_IS_CYCLIC		0
 
 	int				buffer;
-	dma_cookie_t			last_completed;
 	struct list_head		active;
 	struct list_head		queue;
 	struct list_head		free_list;
@@ -703,7 +703,7 @@
 	desc = ep93xx_dma_get_active(edmac);
 	if (desc) {
 		if (desc->complete) {
-			edmac->last_completed = desc->txd.cookie;
+			dma_cookie_complete(&desc->txd);
 			list_splice_init(&edmac->active, &list);
 		}
 		callback = desc->txd.callback;
@@ -783,17 +783,10 @@
 	unsigned long flags;
 
 	spin_lock_irqsave(&edmac->lock, flags);
-
-	cookie = edmac->chan.cookie;
-
-	if (++cookie < 0)
-		cookie = 1;
+	cookie = dma_cookie_assign(tx);
 
 	desc = container_of(tx, struct ep93xx_dma_desc, txd);
 
-	edmac->chan.cookie = cookie;
-	desc->txd.cookie = cookie;
-
 	/*
 	 * If nothing is currently prosessed, we push this descriptor
 	 * directly to the hardware. Otherwise we put the descriptor
@@ -861,8 +854,7 @@
 		goto fail_clk_disable;
 
 	spin_lock_irq(&edmac->lock);
-	edmac->last_completed = 1;
-	edmac->chan.cookie = 1;
+	dma_cookie_init(&edmac->chan);
 	ret = edmac->edma->hw_setup(edmac);
 	spin_unlock_irq(&edmac->lock);
 
@@ -983,13 +975,14 @@
  * @sg_len: number of entries in @sgl
  * @dir: direction of tha DMA transfer
  * @flags: flags for the descriptor
+ * @context: operation context (ignored)
  *
  * Returns a valid DMA descriptor or %NULL in case of failure.
  */
 static struct dma_async_tx_descriptor *
 ep93xx_dma_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 			 unsigned int sg_len, enum dma_transfer_direction dir,
-			 unsigned long flags)
+			 unsigned long flags, void *context)
 {
 	struct ep93xx_dma_chan *edmac = to_ep93xx_dma_chan(chan);
 	struct ep93xx_dma_desc *desc, *first;
@@ -1056,6 +1049,7 @@
  * @buf_len: length of the buffer (in bytes)
  * @period_len: lenght of a single period
  * @dir: direction of the operation
+ * @context: operation context (ignored)
  *
  * Prepares a descriptor for cyclic DMA operation. This means that once the
  * descriptor is submitted, we will be submitting in a @period_len sized
@@ -1068,7 +1062,7 @@
 static struct dma_async_tx_descriptor *
 ep93xx_dma_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t dma_addr,
 			   size_t buf_len, size_t period_len,
-			   enum dma_transfer_direction dir)
+			   enum dma_transfer_direction dir, void *context)
 {
 	struct ep93xx_dma_chan *edmac = to_ep93xx_dma_chan(chan);
 	struct ep93xx_dma_desc *desc, *first;
@@ -1248,18 +1242,13 @@
 					    struct dma_tx_state *state)
 {
 	struct ep93xx_dma_chan *edmac = to_ep93xx_dma_chan(chan);
-	dma_cookie_t last_used, last_completed;
 	enum dma_status ret;
 	unsigned long flags;
 
 	spin_lock_irqsave(&edmac->lock, flags);
-	last_used = chan->cookie;
-	last_completed = edmac->last_completed;
+	ret = dma_cookie_status(chan, cookie, state);
 	spin_unlock_irqrestore(&edmac->lock, flags);
 
-	ret = dma_async_is_complete(cookie, last_completed, last_used);
-	dma_set_tx_state(state, last_completed, last_used, 0);
-
 	return ret;
 }
 
diff --git a/drivers/dma/fsldma.c b/drivers/dma/fsldma.c
index b98070c..8f84761 100644
--- a/drivers/dma/fsldma.c
+++ b/drivers/dma/fsldma.c
@@ -35,6 +35,7 @@
 #include <linux/dmapool.h>
 #include <linux/of_platform.h>
 
+#include "dmaengine.h"
 #include "fsldma.h"
 
 #define chan_dbg(chan, fmt, arg...)					\
@@ -413,17 +414,10 @@
 	 * assign cookies to all of the software descriptors
 	 * that make up this transaction
 	 */
-	cookie = chan->common.cookie;
 	list_for_each_entry(child, &desc->tx_list, node) {
-		cookie++;
-		if (cookie < DMA_MIN_COOKIE)
-			cookie = DMA_MIN_COOKIE;
-
-		child->async_tx.cookie = cookie;
+		cookie = dma_cookie_assign(&child->async_tx);
 	}
 
-	chan->common.cookie = cookie;
-
 	/* put this transaction onto the tail of the pending queue */
 	append_ld_queue(chan, desc);
 
@@ -765,6 +759,7 @@
  * @sg_len: number of entries in @scatterlist
  * @direction: DMA direction
  * @flags: DMAEngine flags
+ * @context: transaction context (ignored)
  *
  * Prepare a set of descriptors for a DMA_SLAVE transaction. Following the
  * DMA_SLAVE API, this gets the device-specific information from the
@@ -772,7 +767,8 @@
  */
 static struct dma_async_tx_descriptor *fsl_dma_prep_slave_sg(
 	struct dma_chan *dchan, struct scatterlist *sgl, unsigned int sg_len,
-	enum dma_transfer_direction direction, unsigned long flags)
+	enum dma_transfer_direction direction, unsigned long flags,
+	void *context)
 {
 	/*
 	 * This operation is not supported on the Freescale DMA controller
@@ -984,19 +980,14 @@
 					struct dma_tx_state *txstate)
 {
 	struct fsldma_chan *chan = to_fsl_chan(dchan);
-	dma_cookie_t last_complete;
-	dma_cookie_t last_used;
+	enum dma_status ret;
 	unsigned long flags;
 
 	spin_lock_irqsave(&chan->desc_lock, flags);
-
-	last_complete = chan->completed_cookie;
-	last_used = dchan->cookie;
-
+	ret = dma_cookie_status(dchan, cookie, txstate);
 	spin_unlock_irqrestore(&chan->desc_lock, flags);
 
-	dma_set_tx_state(txstate, last_complete, last_used, 0);
-	return dma_async_is_complete(cookie, last_complete, last_used);
+	return ret;
 }
 
 /*----------------------------------------------------------------------------*/
@@ -1087,8 +1078,8 @@
 
 		desc = to_fsl_desc(chan->ld_running.prev);
 		cookie = desc->async_tx.cookie;
+		dma_cookie_complete(&desc->async_tx);
 
-		chan->completed_cookie = cookie;
 		chan_dbg(chan, "completed_cookie=%d\n", cookie);
 	}
 
@@ -1303,6 +1294,7 @@
 	chan->idle = true;
 
 	chan->common.device = &fdev->common;
+	dma_cookie_init(&chan->common);
 
 	/* find the IRQ line, if it exists in the device tree */
 	chan->irq = irq_of_parse_and_map(node, 0);
diff --git a/drivers/dma/fsldma.h b/drivers/dma/fsldma.h
index 9cb5aa5..f5c3879 100644
--- a/drivers/dma/fsldma.h
+++ b/drivers/dma/fsldma.h
@@ -137,7 +137,6 @@
 struct fsldma_chan {
 	char name[8];			/* Channel name */
 	struct fsldma_chan_regs __iomem *regs;
-	dma_cookie_t completed_cookie;	/* The maximum cookie completed */
 	spinlock_t desc_lock;		/* Descriptor operation lock */
 	struct list_head ld_pending;	/* Link descriptors queue */
 	struct list_head ld_running;	/* Link descriptors queue */
diff --git a/drivers/dma/imx-dma.c b/drivers/dma/imx-dma.c
index 38586ba..a45b5d2 100644
--- a/drivers/dma/imx-dma.c
+++ b/drivers/dma/imx-dma.c
@@ -5,6 +5,7 @@
  * found on i.MX1/21/27
  *
  * Copyright 2010 Sascha Hauer, Pengutronix <s.hauer@pengutronix.de>
+ * Copyright 2012 Javier Martin, Vista Silicon <javier.martin@vista-silicon.com>
  *
  * The code contained herein is licensed under the GNU General Public
  * License. You may obtain a copy of the GNU General Public License
@@ -22,37 +23,159 @@
 #include <linux/dma-mapping.h>
 #include <linux/slab.h>
 #include <linux/platform_device.h>
+#include <linux/clk.h>
 #include <linux/dmaengine.h>
 #include <linux/module.h>
 
 #include <asm/irq.h>
-#include <mach/dma-v1.h>
+#include <mach/dma.h>
 #include <mach/hardware.h>
 
+#include "dmaengine.h"
+#define IMXDMA_MAX_CHAN_DESCRIPTORS	16
+#define IMX_DMA_CHANNELS  16
+
+#define IMX_DMA_2D_SLOTS	2
+#define IMX_DMA_2D_SLOT_A	0
+#define IMX_DMA_2D_SLOT_B	1
+
+#define IMX_DMA_LENGTH_LOOP	((unsigned int)-1)
+#define IMX_DMA_MEMSIZE_32	(0 << 4)
+#define IMX_DMA_MEMSIZE_8	(1 << 4)
+#define IMX_DMA_MEMSIZE_16	(2 << 4)
+#define IMX_DMA_TYPE_LINEAR	(0 << 10)
+#define IMX_DMA_TYPE_2D		(1 << 10)
+#define IMX_DMA_TYPE_FIFO	(2 << 10)
+
+#define IMX_DMA_ERR_BURST     (1 << 0)
+#define IMX_DMA_ERR_REQUEST   (1 << 1)
+#define IMX_DMA_ERR_TRANSFER  (1 << 2)
+#define IMX_DMA_ERR_BUFFER    (1 << 3)
+#define IMX_DMA_ERR_TIMEOUT   (1 << 4)
+
+#define DMA_DCR     0x00		/* Control Register */
+#define DMA_DISR    0x04		/* Interrupt status Register */
+#define DMA_DIMR    0x08		/* Interrupt mask Register */
+#define DMA_DBTOSR  0x0c		/* Burst timeout status Register */
+#define DMA_DRTOSR  0x10		/* Request timeout Register */
+#define DMA_DSESR   0x14		/* Transfer Error Status Register */
+#define DMA_DBOSR   0x18		/* Buffer overflow status Register */
+#define DMA_DBTOCR  0x1c		/* Burst timeout control Register */
+#define DMA_WSRA    0x40		/* W-Size Register A */
+#define DMA_XSRA    0x44		/* X-Size Register A */
+#define DMA_YSRA    0x48		/* Y-Size Register A */
+#define DMA_WSRB    0x4c		/* W-Size Register B */
+#define DMA_XSRB    0x50		/* X-Size Register B */
+#define DMA_YSRB    0x54		/* Y-Size Register B */
+#define DMA_SAR(x)  (0x80 + ((x) << 6))	/* Source Address Registers */
+#define DMA_DAR(x)  (0x84 + ((x) << 6))	/* Destination Address Registers */
+#define DMA_CNTR(x) (0x88 + ((x) << 6))	/* Count Registers */
+#define DMA_CCR(x)  (0x8c + ((x) << 6))	/* Control Registers */
+#define DMA_RSSR(x) (0x90 + ((x) << 6))	/* Request source select Registers */
+#define DMA_BLR(x)  (0x94 + ((x) << 6))	/* Burst length Registers */
+#define DMA_RTOR(x) (0x98 + ((x) << 6))	/* Request timeout Registers */
+#define DMA_BUCR(x) (0x98 + ((x) << 6))	/* Bus Utilization Registers */
+#define DMA_CCNR(x) (0x9C + ((x) << 6))	/* Channel counter Registers */
+
+#define DCR_DRST           (1<<1)
+#define DCR_DEN            (1<<0)
+#define DBTOCR_EN          (1<<15)
+#define DBTOCR_CNT(x)      ((x) & 0x7fff)
+#define CNTR_CNT(x)        ((x) & 0xffffff)
+#define CCR_ACRPT          (1<<14)
+#define CCR_DMOD_LINEAR    (0x0 << 12)
+#define CCR_DMOD_2D        (0x1 << 12)
+#define CCR_DMOD_FIFO      (0x2 << 12)
+#define CCR_DMOD_EOBFIFO   (0x3 << 12)
+#define CCR_SMOD_LINEAR    (0x0 << 10)
+#define CCR_SMOD_2D        (0x1 << 10)
+#define CCR_SMOD_FIFO      (0x2 << 10)
+#define CCR_SMOD_EOBFIFO   (0x3 << 10)
+#define CCR_MDIR_DEC       (1<<9)
+#define CCR_MSEL_B         (1<<8)
+#define CCR_DSIZ_32        (0x0 << 6)
+#define CCR_DSIZ_8         (0x1 << 6)
+#define CCR_DSIZ_16        (0x2 << 6)
+#define CCR_SSIZ_32        (0x0 << 4)
+#define CCR_SSIZ_8         (0x1 << 4)
+#define CCR_SSIZ_16        (0x2 << 4)
+#define CCR_REN            (1<<3)
+#define CCR_RPT            (1<<2)
+#define CCR_FRC            (1<<1)
+#define CCR_CEN            (1<<0)
+#define RTOR_EN            (1<<15)
+#define RTOR_CLK           (1<<14)
+#define RTOR_PSC           (1<<13)
+
+enum  imxdma_prep_type {
+	IMXDMA_DESC_MEMCPY,
+	IMXDMA_DESC_INTERLEAVED,
+	IMXDMA_DESC_SLAVE_SG,
+	IMXDMA_DESC_CYCLIC,
+};
+
+struct imx_dma_2d_config {
+	u16		xsr;
+	u16		ysr;
+	u16		wsr;
+	int		count;
+};
+
+struct imxdma_desc {
+	struct list_head		node;
+	struct dma_async_tx_descriptor	desc;
+	enum dma_status			status;
+	dma_addr_t			src;
+	dma_addr_t			dest;
+	size_t				len;
+	enum dma_transfer_direction	direction;
+	enum imxdma_prep_type		type;
+	/* For memcpy and interleaved */
+	unsigned int			config_port;
+	unsigned int			config_mem;
+	/* For interleaved transfers */
+	unsigned int			x;
+	unsigned int			y;
+	unsigned int			w;
+	/* For slave sg and cyclic */
+	struct scatterlist		*sg;
+	unsigned int			sgcount;
+};
+
 struct imxdma_channel {
+	int				hw_chaining;
+	struct timer_list		watchdog;
 	struct imxdma_engine		*imxdma;
 	unsigned int			channel;
-	unsigned int			imxdma_channel;
 
+	struct tasklet_struct		dma_tasklet;
+	struct list_head		ld_free;
+	struct list_head		ld_queue;
+	struct list_head		ld_active;
+	int				descs_allocated;
 	enum dma_slave_buswidth		word_size;
 	dma_addr_t			per_address;
 	u32				watermark_level;
 	struct dma_chan			chan;
-	spinlock_t			lock;
 	struct dma_async_tx_descriptor	desc;
-	dma_cookie_t			last_completed;
 	enum dma_status			status;
 	int				dma_request;
 	struct scatterlist		*sg_list;
+	u32				ccr_from_device;
+	u32				ccr_to_device;
+	bool				enabled_2d;
+	int				slot_2d;
 };
 
-#define MAX_DMA_CHANNELS 8
-
 struct imxdma_engine {
 	struct device			*dev;
 	struct device_dma_parameters	dma_parms;
 	struct dma_device		dma_device;
-	struct imxdma_channel		channel[MAX_DMA_CHANNELS];
+	void __iomem			*base;
+	struct clk			*dma_clk;
+	spinlock_t			lock;
+	struct imx_dma_2d_config	slots_2d[IMX_DMA_2D_SLOTS];
+	struct imxdma_channel		channel[IMX_DMA_CHANNELS];
 };
 
 static struct imxdma_channel *to_imxdma_chan(struct dma_chan *chan)
@@ -60,36 +183,418 @@
 	return container_of(chan, struct imxdma_channel, chan);
 }
 
-static void imxdma_handle(struct imxdma_channel *imxdmac)
+static inline bool imxdma_chan_is_doing_cyclic(struct imxdma_channel *imxdmac)
 {
-	if (imxdmac->desc.callback)
-		imxdmac->desc.callback(imxdmac->desc.callback_param);
-	imxdmac->last_completed = imxdmac->desc.cookie;
+	struct imxdma_desc *desc;
+
+	if (!list_empty(&imxdmac->ld_active)) {
+		desc = list_first_entry(&imxdmac->ld_active, struct imxdma_desc,
+					node);
+		if (desc->type == IMXDMA_DESC_CYCLIC)
+			return true;
+	}
+	return false;
 }
 
-static void imxdma_irq_handler(int channel, void *data)
-{
-	struct imxdma_channel *imxdmac = data;
 
-	imxdmac->status = DMA_SUCCESS;
-	imxdma_handle(imxdmac);
+
+static void imx_dmav1_writel(struct imxdma_engine *imxdma, unsigned val,
+			     unsigned offset)
+{
+	__raw_writel(val, imxdma->base + offset);
 }
 
-static void imxdma_err_handler(int channel, void *data, int error)
+static unsigned imx_dmav1_readl(struct imxdma_engine *imxdma, unsigned offset)
 {
-	struct imxdma_channel *imxdmac = data;
-
-	imxdmac->status = DMA_ERROR;
-	imxdma_handle(imxdmac);
+	return __raw_readl(imxdma->base + offset);
 }
 
-static void imxdma_progression(int channel, void *data,
-		struct scatterlist *sg)
+static int imxdma_hw_chain(struct imxdma_channel *imxdmac)
 {
-	struct imxdma_channel *imxdmac = data;
+	if (cpu_is_mx27())
+		return imxdmac->hw_chaining;
+	else
+		return 0;
+}
 
-	imxdmac->status = DMA_SUCCESS;
-	imxdma_handle(imxdmac);
+/*
+ * imxdma_sg_next - prepare next chunk for scatter-gather DMA emulation
+ */
+static inline int imxdma_sg_next(struct imxdma_desc *d)
+{
+	struct imxdma_channel *imxdmac = to_imxdma_chan(d->desc.chan);
+	struct imxdma_engine *imxdma = imxdmac->imxdma;
+	struct scatterlist *sg = d->sg;
+	unsigned long now;
+
+	now = min(d->len, sg->length);
+	if (d->len != IMX_DMA_LENGTH_LOOP)
+		d->len -= now;
+
+	if (d->direction == DMA_DEV_TO_MEM)
+		imx_dmav1_writel(imxdma, sg->dma_address,
+				 DMA_DAR(imxdmac->channel));
+	else
+		imx_dmav1_writel(imxdma, sg->dma_address,
+				 DMA_SAR(imxdmac->channel));
+
+	imx_dmav1_writel(imxdma, now, DMA_CNTR(imxdmac->channel));
+
+	dev_dbg(imxdma->dev, " %s channel: %d dst 0x%08x, src 0x%08x, "
+		"size 0x%08x\n", __func__, imxdmac->channel,
+		 imx_dmav1_readl(imxdma, DMA_DAR(imxdmac->channel)),
+		 imx_dmav1_readl(imxdma, DMA_SAR(imxdmac->channel)),
+		 imx_dmav1_readl(imxdma, DMA_CNTR(imxdmac->channel)));
+
+	return now;
+}
+
+static void imxdma_enable_hw(struct imxdma_desc *d)
+{
+	struct imxdma_channel *imxdmac = to_imxdma_chan(d->desc.chan);
+	struct imxdma_engine *imxdma = imxdmac->imxdma;
+	int channel = imxdmac->channel;
+	unsigned long flags;
+
+	dev_dbg(imxdma->dev, "%s channel %d\n", __func__, channel);
+
+	local_irq_save(flags);
+
+	imx_dmav1_writel(imxdma, 1 << channel, DMA_DISR);
+	imx_dmav1_writel(imxdma, imx_dmav1_readl(imxdma, DMA_DIMR) &
+			 ~(1 << channel), DMA_DIMR);
+	imx_dmav1_writel(imxdma, imx_dmav1_readl(imxdma, DMA_CCR(channel)) |
+			 CCR_CEN | CCR_ACRPT, DMA_CCR(channel));
+
+	if ((cpu_is_mx21() || cpu_is_mx27()) &&
+			d->sg && imxdma_hw_chain(imxdmac)) {
+		d->sg = sg_next(d->sg);
+		if (d->sg) {
+			u32 tmp;
+			imxdma_sg_next(d);
+			tmp = imx_dmav1_readl(imxdma, DMA_CCR(channel));
+			imx_dmav1_writel(imxdma, tmp | CCR_RPT | CCR_ACRPT,
+					 DMA_CCR(channel));
+		}
+	}
+
+	local_irq_restore(flags);
+}
+
+static void imxdma_disable_hw(struct imxdma_channel *imxdmac)
+{
+	struct imxdma_engine *imxdma = imxdmac->imxdma;
+	int channel = imxdmac->channel;
+	unsigned long flags;
+
+	dev_dbg(imxdma->dev, "%s channel %d\n", __func__, channel);
+
+	if (imxdma_hw_chain(imxdmac))
+		del_timer(&imxdmac->watchdog);
+
+	local_irq_save(flags);
+	imx_dmav1_writel(imxdma, imx_dmav1_readl(imxdma, DMA_DIMR) |
+			 (1 << channel), DMA_DIMR);
+	imx_dmav1_writel(imxdma, imx_dmav1_readl(imxdma, DMA_CCR(channel)) &
+			 ~CCR_CEN, DMA_CCR(channel));
+	imx_dmav1_writel(imxdma, 1 << channel, DMA_DISR);
+	local_irq_restore(flags);
+}
+
+static void imxdma_watchdog(unsigned long data)
+{
+	struct imxdma_channel *imxdmac = (struct imxdma_channel *)data;
+	struct imxdma_engine *imxdma = imxdmac->imxdma;
+	int channel = imxdmac->channel;
+
+	imx_dmav1_writel(imxdma, 0, DMA_CCR(channel));
+
+	/* Tasklet watchdog error handler */
+	tasklet_schedule(&imxdmac->dma_tasklet);
+	dev_dbg(imxdma->dev, "channel %d: watchdog timeout!\n",
+		imxdmac->channel);
+}
+
+static irqreturn_t imxdma_err_handler(int irq, void *dev_id)
+{
+	struct imxdma_engine *imxdma = dev_id;
+	unsigned int err_mask;
+	int i, disr;
+	int errcode;
+
+	disr = imx_dmav1_readl(imxdma, DMA_DISR);
+
+	err_mask = imx_dmav1_readl(imxdma, DMA_DBTOSR) |
+		   imx_dmav1_readl(imxdma, DMA_DRTOSR) |
+		   imx_dmav1_readl(imxdma, DMA_DSESR)  |
+		   imx_dmav1_readl(imxdma, DMA_DBOSR);
+
+	if (!err_mask)
+		return IRQ_HANDLED;
+
+	imx_dmav1_writel(imxdma, disr & err_mask, DMA_DISR);
+
+	for (i = 0; i < IMX_DMA_CHANNELS; i++) {
+		if (!(err_mask & (1 << i)))
+			continue;
+		errcode = 0;
+
+		if (imx_dmav1_readl(imxdma, DMA_DBTOSR) & (1 << i)) {
+			imx_dmav1_writel(imxdma, 1 << i, DMA_DBTOSR);
+			errcode |= IMX_DMA_ERR_BURST;
+		}
+		if (imx_dmav1_readl(imxdma, DMA_DRTOSR) & (1 << i)) {
+			imx_dmav1_writel(imxdma, 1 << i, DMA_DRTOSR);
+			errcode |= IMX_DMA_ERR_REQUEST;
+		}
+		if (imx_dmav1_readl(imxdma, DMA_DSESR) & (1 << i)) {
+			imx_dmav1_writel(imxdma, 1 << i, DMA_DSESR);
+			errcode |= IMX_DMA_ERR_TRANSFER;
+		}
+		if (imx_dmav1_readl(imxdma, DMA_DBOSR) & (1 << i)) {
+			imx_dmav1_writel(imxdma, 1 << i, DMA_DBOSR);
+			errcode |= IMX_DMA_ERR_BUFFER;
+		}
+		/* Tasklet error handler */
+		tasklet_schedule(&imxdma->channel[i].dma_tasklet);
+
+		printk(KERN_WARNING
+		       "DMA timeout on channel %d -%s%s%s%s\n", i,
+		       errcode & IMX_DMA_ERR_BURST ?    " burst" : "",
+		       errcode & IMX_DMA_ERR_REQUEST ?  " request" : "",
+		       errcode & IMX_DMA_ERR_TRANSFER ? " transfer" : "",
+		       errcode & IMX_DMA_ERR_BUFFER ?   " buffer" : "");
+	}
+	return IRQ_HANDLED;
+}
+
+static void dma_irq_handle_channel(struct imxdma_channel *imxdmac)
+{
+	struct imxdma_engine *imxdma = imxdmac->imxdma;
+	int chno = imxdmac->channel;
+	struct imxdma_desc *desc;
+
+	spin_lock(&imxdma->lock);
+	if (list_empty(&imxdmac->ld_active)) {
+		spin_unlock(&imxdma->lock);
+		goto out;
+	}
+
+	desc = list_first_entry(&imxdmac->ld_active,
+				struct imxdma_desc,
+				node);
+	spin_unlock(&imxdma->lock);
+
+	if (desc->sg) {
+		u32 tmp;
+		desc->sg = sg_next(desc->sg);
+
+		if (desc->sg) {
+			imxdma_sg_next(desc);
+
+			tmp = imx_dmav1_readl(imxdma, DMA_CCR(chno));
+
+			if (imxdma_hw_chain(imxdmac)) {
+				/* FIXME: The timeout should probably be
+				 * configurable
+				 */
+				mod_timer(&imxdmac->watchdog,
+					jiffies + msecs_to_jiffies(500));
+
+				tmp |= CCR_CEN | CCR_RPT | CCR_ACRPT;
+				imx_dmav1_writel(imxdma, tmp, DMA_CCR(chno));
+			} else {
+				imx_dmav1_writel(imxdma, tmp & ~CCR_CEN,
+						 DMA_CCR(chno));
+				tmp |= CCR_CEN;
+			}
+
+			imx_dmav1_writel(imxdma, tmp, DMA_CCR(chno));
+
+			if (imxdma_chan_is_doing_cyclic(imxdmac))
+				/* Tasklet progression */
+				tasklet_schedule(&imxdmac->dma_tasklet);
+
+			return;
+		}
+
+		if (imxdma_hw_chain(imxdmac)) {
+			del_timer(&imxdmac->watchdog);
+			return;
+		}
+	}
+
+out:
+	imx_dmav1_writel(imxdma, 0, DMA_CCR(chno));
+	/* Tasklet irq */
+	tasklet_schedule(&imxdmac->dma_tasklet);
+}
+
+static irqreturn_t dma_irq_handler(int irq, void *dev_id)
+{
+	struct imxdma_engine *imxdma = dev_id;
+	int i, disr;
+
+	if (cpu_is_mx21() || cpu_is_mx27())
+		imxdma_err_handler(irq, dev_id);
+
+	disr = imx_dmav1_readl(imxdma, DMA_DISR);
+
+	dev_dbg(imxdma->dev, "%s called, disr=0x%08x\n", __func__, disr);
+
+	imx_dmav1_writel(imxdma, disr, DMA_DISR);
+	for (i = 0; i < IMX_DMA_CHANNELS; i++) {
+		if (disr & (1 << i))
+			dma_irq_handle_channel(&imxdma->channel[i]);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int imxdma_xfer_desc(struct imxdma_desc *d)
+{
+	struct imxdma_channel *imxdmac = to_imxdma_chan(d->desc.chan);
+	struct imxdma_engine *imxdma = imxdmac->imxdma;
+	unsigned long flags;
+	int slot = -1;
+	int i;
+
+	/* Configure and enable */
+	switch (d->type) {
+	case IMXDMA_DESC_INTERLEAVED:
+		/* Try to get a free 2D slot */
+		spin_lock_irqsave(&imxdma->lock, flags);
+		for (i = 0; i < IMX_DMA_2D_SLOTS; i++) {
+			if ((imxdma->slots_2d[i].count > 0) &&
+			((imxdma->slots_2d[i].xsr != d->x) ||
+			(imxdma->slots_2d[i].ysr != d->y) ||
+			(imxdma->slots_2d[i].wsr != d->w)))
+				continue;
+			slot = i;
+			break;
+		}
+		if (slot < 0)
+			return -EBUSY;
+
+		imxdma->slots_2d[slot].xsr = d->x;
+		imxdma->slots_2d[slot].ysr = d->y;
+		imxdma->slots_2d[slot].wsr = d->w;
+		imxdma->slots_2d[slot].count++;
+
+		imxdmac->slot_2d = slot;
+		imxdmac->enabled_2d = true;
+		spin_unlock_irqrestore(&imxdma->lock, flags);
+
+		if (slot == IMX_DMA_2D_SLOT_A) {
+			d->config_mem &= ~CCR_MSEL_B;
+			d->config_port &= ~CCR_MSEL_B;
+			imx_dmav1_writel(imxdma, d->x, DMA_XSRA);
+			imx_dmav1_writel(imxdma, d->y, DMA_YSRA);
+			imx_dmav1_writel(imxdma, d->w, DMA_WSRA);
+		} else {
+			d->config_mem |= CCR_MSEL_B;
+			d->config_port |= CCR_MSEL_B;
+			imx_dmav1_writel(imxdma, d->x, DMA_XSRB);
+			imx_dmav1_writel(imxdma, d->y, DMA_YSRB);
+			imx_dmav1_writel(imxdma, d->w, DMA_WSRB);
+		}
+		/*
+		 * We fall-through here intentionally, since a 2D transfer is
+		 * similar to MEMCPY just adding the 2D slot configuration.
+		 */
+	case IMXDMA_DESC_MEMCPY:
+		imx_dmav1_writel(imxdma, d->src, DMA_SAR(imxdmac->channel));
+		imx_dmav1_writel(imxdma, d->dest, DMA_DAR(imxdmac->channel));
+		imx_dmav1_writel(imxdma, d->config_mem | (d->config_port << 2),
+			 DMA_CCR(imxdmac->channel));
+
+		imx_dmav1_writel(imxdma, d->len, DMA_CNTR(imxdmac->channel));
+
+		dev_dbg(imxdma->dev, "%s channel: %d dest=0x%08x src=0x%08x "
+			"dma_length=%d\n", __func__, imxdmac->channel,
+			d->dest, d->src, d->len);
+
+		break;
+	/* Cyclic transfer is the same as slave_sg with special sg configuration. */
+	case IMXDMA_DESC_CYCLIC:
+	case IMXDMA_DESC_SLAVE_SG:
+		if (d->direction == DMA_DEV_TO_MEM) {
+			imx_dmav1_writel(imxdma, imxdmac->per_address,
+					 DMA_SAR(imxdmac->channel));
+			imx_dmav1_writel(imxdma, imxdmac->ccr_from_device,
+					 DMA_CCR(imxdmac->channel));
+
+			dev_dbg(imxdma->dev, "%s channel: %d sg=%p sgcount=%d "
+				"total length=%d dev_addr=0x%08x (dev2mem)\n",
+				__func__, imxdmac->channel, d->sg, d->sgcount,
+				d->len, imxdmac->per_address);
+		} else if (d->direction == DMA_MEM_TO_DEV) {
+			imx_dmav1_writel(imxdma, imxdmac->per_address,
+					 DMA_DAR(imxdmac->channel));
+			imx_dmav1_writel(imxdma, imxdmac->ccr_to_device,
+					 DMA_CCR(imxdmac->channel));
+
+			dev_dbg(imxdma->dev, "%s channel: %d sg=%p sgcount=%d "
+				"total length=%d dev_addr=0x%08x (mem2dev)\n",
+				__func__, imxdmac->channel, d->sg, d->sgcount,
+				d->len, imxdmac->per_address);
+		} else {
+			dev_err(imxdma->dev, "%s channel: %d bad dma mode\n",
+				__func__, imxdmac->channel);
+			return -EINVAL;
+		}
+
+		imxdma_sg_next(d);
+
+		break;
+	default:
+		return -EINVAL;
+	}
+	imxdma_enable_hw(d);
+	return 0;
+}
+
+static void imxdma_tasklet(unsigned long data)
+{
+	struct imxdma_channel *imxdmac = (void *)data;
+	struct imxdma_engine *imxdma = imxdmac->imxdma;
+	struct imxdma_desc *desc;
+
+	spin_lock(&imxdma->lock);
+
+	if (list_empty(&imxdmac->ld_active)) {
+		/* Someone might have called terminate all */
+		goto out;
+	}
+	desc = list_first_entry(&imxdmac->ld_active, struct imxdma_desc, node);
+
+	if (desc->desc.callback)
+		desc->desc.callback(desc->desc.callback_param);
+
+	dma_cookie_complete(&desc->desc);
+
+	/* If we are dealing with a cyclic descriptor keep it on ld_active */
+	if (imxdma_chan_is_doing_cyclic(imxdmac))
+		goto out;
+
+	/* Free 2D slot if it was an interleaved transfer */
+	if (imxdmac->enabled_2d) {
+		imxdma->slots_2d[imxdmac->slot_2d].count--;
+		imxdmac->enabled_2d = false;
+	}
+
+	list_move_tail(imxdmac->ld_active.next, &imxdmac->ld_free);
+
+	if (!list_empty(&imxdmac->ld_queue)) {
+		desc = list_first_entry(&imxdmac->ld_queue, struct imxdma_desc,
+					node);
+		list_move_tail(imxdmac->ld_queue.next, &imxdmac->ld_active);
+		if (imxdma_xfer_desc(desc) < 0)
+			dev_warn(imxdma->dev, "%s: channel: %d couldn't xfer desc\n",
+				 __func__, imxdmac->channel);
+	}
+out:
+	spin_unlock(&imxdma->lock);
 }
 
 static int imxdma_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
@@ -97,13 +602,18 @@
 {
 	struct imxdma_channel *imxdmac = to_imxdma_chan(chan);
 	struct dma_slave_config *dmaengine_cfg = (void *)arg;
-	int ret;
+	struct imxdma_engine *imxdma = imxdmac->imxdma;
+	unsigned long flags;
 	unsigned int mode = 0;
 
 	switch (cmd) {
 	case DMA_TERMINATE_ALL:
-		imxdmac->status = DMA_ERROR;
-		imx_dma_disable(imxdmac->imxdma_channel);
+		imxdma_disable_hw(imxdmac);
+
+		spin_lock_irqsave(&imxdma->lock, flags);
+		list_splice_tail_init(&imxdmac->ld_active, &imxdmac->ld_free);
+		list_splice_tail_init(&imxdmac->ld_queue, &imxdmac->ld_free);
+		spin_unlock_irqrestore(&imxdma->lock, flags);
 		return 0;
 	case DMA_SLAVE_CONFIG:
 		if (dmaengine_cfg->direction == DMA_DEV_TO_MEM) {
@@ -128,16 +638,22 @@
 			mode = IMX_DMA_MEMSIZE_32;
 			break;
 		}
-		ret = imx_dma_config_channel(imxdmac->imxdma_channel,
-				mode | IMX_DMA_TYPE_FIFO,
-				IMX_DMA_MEMSIZE_32 | IMX_DMA_TYPE_LINEAR,
-				imxdmac->dma_request, 1);
 
-		if (ret)
-			return ret;
+		imxdmac->hw_chaining = 1;
+		if (!imxdma_hw_chain(imxdmac))
+			return -EINVAL;
+		imxdmac->ccr_from_device = (mode | IMX_DMA_TYPE_FIFO) |
+			((IMX_DMA_MEMSIZE_32 | IMX_DMA_TYPE_LINEAR) << 2) |
+			CCR_REN;
+		imxdmac->ccr_to_device =
+			(IMX_DMA_MEMSIZE_32 | IMX_DMA_TYPE_LINEAR) |
+			((mode | IMX_DMA_TYPE_FIFO) << 2) | CCR_REN;
+		imx_dmav1_writel(imxdma, imxdmac->dma_request,
+				 DMA_RSSR(imxdmac->channel));
 
-		imx_dma_config_burstlen(imxdmac->imxdma_channel,
-				imxdmac->watermark_level * imxdmac->word_size);
+		/* Set burst length */
+		imx_dmav1_writel(imxdma, imxdmac->watermark_level *
+				imxdmac->word_size, DMA_BLR(imxdmac->channel));
 
 		return 0;
 	default:
@@ -151,43 +667,20 @@
 					    dma_cookie_t cookie,
 					    struct dma_tx_state *txstate)
 {
-	struct imxdma_channel *imxdmac = to_imxdma_chan(chan);
-	dma_cookie_t last_used;
-	enum dma_status ret;
-
-	last_used = chan->cookie;
-
-	ret = dma_async_is_complete(cookie, imxdmac->last_completed, last_used);
-	dma_set_tx_state(txstate, imxdmac->last_completed, last_used, 0);
-
-	return ret;
-}
-
-static dma_cookie_t imxdma_assign_cookie(struct imxdma_channel *imxdma)
-{
-	dma_cookie_t cookie = imxdma->chan.cookie;
-
-	if (++cookie < 0)
-		cookie = 1;
-
-	imxdma->chan.cookie = cookie;
-	imxdma->desc.cookie = cookie;
-
-	return cookie;
+	return dma_cookie_status(chan, cookie, txstate);
 }
 
 static dma_cookie_t imxdma_tx_submit(struct dma_async_tx_descriptor *tx)
 {
 	struct imxdma_channel *imxdmac = to_imxdma_chan(tx->chan);
+	struct imxdma_engine *imxdma = imxdmac->imxdma;
 	dma_cookie_t cookie;
+	unsigned long flags;
 
-	spin_lock_irq(&imxdmac->lock);
-
-	cookie = imxdma_assign_cookie(imxdmac);
-
-	imx_dma_enable(imxdmac->imxdma_channel);
-
-	spin_unlock_irq(&imxdmac->lock);
+	spin_lock_irqsave(&imxdma->lock, flags);
+	list_move_tail(imxdmac->ld_free.next, &imxdmac->ld_queue);
+	cookie = dma_cookie_assign(tx);
+	spin_unlock_irqrestore(&imxdma->lock, flags);
 
 	return cookie;
 }
@@ -197,23 +690,52 @@
 	struct imxdma_channel *imxdmac = to_imxdma_chan(chan);
 	struct imx_dma_data *data = chan->private;
 
-	imxdmac->dma_request = data->dma_request;
+	if (data != NULL)
+		imxdmac->dma_request = data->dma_request;
 
-	dma_async_tx_descriptor_init(&imxdmac->desc, chan);
-	imxdmac->desc.tx_submit = imxdma_tx_submit;
-	/* txd.flags will be overwritten in prep funcs */
-	imxdmac->desc.flags = DMA_CTRL_ACK;
+	while (imxdmac->descs_allocated < IMXDMA_MAX_CHAN_DESCRIPTORS) {
+		struct imxdma_desc *desc;
 
-	imxdmac->status = DMA_SUCCESS;
+		desc = kzalloc(sizeof(*desc), GFP_KERNEL);
+		if (!desc)
+			break;
+		__memzero(&desc->desc, sizeof(struct dma_async_tx_descriptor));
+		dma_async_tx_descriptor_init(&desc->desc, chan);
+		desc->desc.tx_submit = imxdma_tx_submit;
+		/* txd.flags will be overwritten in prep funcs */
+		desc->desc.flags = DMA_CTRL_ACK;
+		desc->status = DMA_SUCCESS;
 
-	return 0;
+		list_add_tail(&desc->node, &imxdmac->ld_free);
+		imxdmac->descs_allocated++;
+	}
+
+	if (!imxdmac->descs_allocated)
+		return -ENOMEM;
+
+	return imxdmac->descs_allocated;
 }
 
 static void imxdma_free_chan_resources(struct dma_chan *chan)
 {
 	struct imxdma_channel *imxdmac = to_imxdma_chan(chan);
+	struct imxdma_engine *imxdma = imxdmac->imxdma;
+	struct imxdma_desc *desc, *_desc;
+	unsigned long flags;
 
-	imx_dma_disable(imxdmac->imxdma_channel);
+	spin_lock_irqsave(&imxdma->lock, flags);
+
+	imxdma_disable_hw(imxdmac);
+	list_splice_tail_init(&imxdmac->ld_active, &imxdmac->ld_free);
+	list_splice_tail_init(&imxdmac->ld_queue, &imxdmac->ld_free);
+
+	spin_unlock_irqrestore(&imxdma->lock, flags);
+
+	list_for_each_entry_safe(desc, _desc, &imxdmac->ld_free, node) {
+		kfree(desc);
+		imxdmac->descs_allocated--;
+	}
+	INIT_LIST_HEAD(&imxdmac->ld_free);
 
 	if (imxdmac->sg_list) {
 		kfree(imxdmac->sg_list);
@@ -224,27 +746,23 @@
 static struct dma_async_tx_descriptor *imxdma_prep_slave_sg(
 		struct dma_chan *chan, struct scatterlist *sgl,
 		unsigned int sg_len, enum dma_transfer_direction direction,
-		unsigned long flags)
+		unsigned long flags, void *context)
 {
 	struct imxdma_channel *imxdmac = to_imxdma_chan(chan);
 	struct scatterlist *sg;
-	int i, ret, dma_length = 0;
-	unsigned int dmamode;
+	int i, dma_length = 0;
+	struct imxdma_desc *desc;
 
-	if (imxdmac->status == DMA_IN_PROGRESS)
+	if (list_empty(&imxdmac->ld_free) ||
+	    imxdma_chan_is_doing_cyclic(imxdmac))
 		return NULL;
 
-	imxdmac->status = DMA_IN_PROGRESS;
+	desc = list_first_entry(&imxdmac->ld_free, struct imxdma_desc, node);
 
 	for_each_sg(sgl, sg, sg_len, i) {
 		dma_length += sg->length;
 	}
 
-	if (direction == DMA_DEV_TO_MEM)
-		dmamode = DMA_MODE_READ;
-	else
-		dmamode = DMA_MODE_WRITE;
-
 	switch (imxdmac->word_size) {
 	case DMA_SLAVE_BUSWIDTH_4_BYTES:
 		if (sgl->length & 3 || sgl->dma_address & 3)
@@ -260,37 +778,41 @@
 		return NULL;
 	}
 
-	ret = imx_dma_setup_sg(imxdmac->imxdma_channel, sgl, sg_len,
-		 dma_length, imxdmac->per_address, dmamode);
-	if (ret)
-		return NULL;
+	desc->type = IMXDMA_DESC_SLAVE_SG;
+	desc->sg = sgl;
+	desc->sgcount = sg_len;
+	desc->len = dma_length;
+	desc->direction = direction;
+	if (direction == DMA_DEV_TO_MEM) {
+		desc->src = imxdmac->per_address;
+	} else {
+		desc->dest = imxdmac->per_address;
+	}
+	desc->desc.callback = NULL;
+	desc->desc.callback_param = NULL;
 
-	return &imxdmac->desc;
+	return &desc->desc;
 }
 
 static struct dma_async_tx_descriptor *imxdma_prep_dma_cyclic(
 		struct dma_chan *chan, dma_addr_t dma_addr, size_t buf_len,
-		size_t period_len, enum dma_transfer_direction direction)
+		size_t period_len, enum dma_transfer_direction direction,
+		void *context)
 {
 	struct imxdma_channel *imxdmac = to_imxdma_chan(chan);
 	struct imxdma_engine *imxdma = imxdmac->imxdma;
-	int i, ret;
+	struct imxdma_desc *desc;
+	int i;
 	unsigned int periods = buf_len / period_len;
-	unsigned int dmamode;
 
 	dev_dbg(imxdma->dev, "%s channel: %d buf_len=%d period_len=%d\n",
 			__func__, imxdmac->channel, buf_len, period_len);
 
-	if (imxdmac->status == DMA_IN_PROGRESS)
+	if (list_empty(&imxdmac->ld_free) ||
+	    imxdma_chan_is_doing_cyclic(imxdmac))
 		return NULL;
-	imxdmac->status = DMA_IN_PROGRESS;
 
-	ret = imx_dma_setup_progression_handler(imxdmac->imxdma_channel,
-			imxdma_progression);
-	if (ret) {
-		dev_err(imxdma->dev, "Failed to setup the DMA handler\n");
-		return NULL;
-	}
+	desc = list_first_entry(&imxdmac->ld_free, struct imxdma_desc, node);
 
 	if (imxdmac->sg_list)
 		kfree(imxdmac->sg_list);
@@ -316,62 +838,221 @@
 	imxdmac->sg_list[periods].page_link =
 		((unsigned long)imxdmac->sg_list | 0x01) & ~0x02;
 
-	if (direction == DMA_DEV_TO_MEM)
-		dmamode = DMA_MODE_READ;
-	else
-		dmamode = DMA_MODE_WRITE;
+	desc->type = IMXDMA_DESC_CYCLIC;
+	desc->sg = imxdmac->sg_list;
+	desc->sgcount = periods;
+	desc->len = IMX_DMA_LENGTH_LOOP;
+	desc->direction = direction;
+	if (direction == DMA_DEV_TO_MEM) {
+		desc->src = imxdmac->per_address;
+	} else {
+		desc->dest = imxdmac->per_address;
+	}
+	desc->desc.callback = NULL;
+	desc->desc.callback_param = NULL;
 
-	ret = imx_dma_setup_sg(imxdmac->imxdma_channel, imxdmac->sg_list, periods,
-		 IMX_DMA_LENGTH_LOOP, imxdmac->per_address, dmamode);
-	if (ret)
+	return &desc->desc;
+}
+
+static struct dma_async_tx_descriptor *imxdma_prep_dma_memcpy(
+	struct dma_chan *chan, dma_addr_t dest,
+	dma_addr_t src, size_t len, unsigned long flags)
+{
+	struct imxdma_channel *imxdmac = to_imxdma_chan(chan);
+	struct imxdma_engine *imxdma = imxdmac->imxdma;
+	struct imxdma_desc *desc;
+
+	dev_dbg(imxdma->dev, "%s channel: %d src=0x%x dst=0x%x len=%d\n",
+			__func__, imxdmac->channel, src, dest, len);
+
+	if (list_empty(&imxdmac->ld_free) ||
+	    imxdma_chan_is_doing_cyclic(imxdmac))
 		return NULL;
 
-	return &imxdmac->desc;
+	desc = list_first_entry(&imxdmac->ld_free, struct imxdma_desc, node);
+
+	desc->type = IMXDMA_DESC_MEMCPY;
+	desc->src = src;
+	desc->dest = dest;
+	desc->len = len;
+	desc->direction = DMA_MEM_TO_MEM;
+	desc->config_port = IMX_DMA_MEMSIZE_32 | IMX_DMA_TYPE_LINEAR;
+	desc->config_mem = IMX_DMA_MEMSIZE_32 | IMX_DMA_TYPE_LINEAR;
+	desc->desc.callback = NULL;
+	desc->desc.callback_param = NULL;
+
+	return &desc->desc;
+}
+
+static struct dma_async_tx_descriptor *imxdma_prep_dma_interleaved(
+	struct dma_chan *chan, struct dma_interleaved_template *xt,
+	unsigned long flags)
+{
+	struct imxdma_channel *imxdmac = to_imxdma_chan(chan);
+	struct imxdma_engine *imxdma = imxdmac->imxdma;
+	struct imxdma_desc *desc;
+
+	dev_dbg(imxdma->dev, "%s channel: %d src_start=0x%x dst_start=0x%x\n"
+		"   src_sgl=%s dst_sgl=%s numf=%d frame_size=%d\n", __func__,
+		imxdmac->channel, xt->src_start, xt->dst_start,
+		xt->src_sgl ? "true" : "false", xt->dst_sgl ? "true" : "false",
+		xt->numf, xt->frame_size);
+
+	if (list_empty(&imxdmac->ld_free) ||
+	    imxdma_chan_is_doing_cyclic(imxdmac))
+		return NULL;
+
+	if (xt->frame_size != 1 || xt->numf <= 0 || xt->dir != DMA_MEM_TO_MEM)
+		return NULL;
+
+	desc = list_first_entry(&imxdmac->ld_free, struct imxdma_desc, node);
+
+	desc->type = IMXDMA_DESC_INTERLEAVED;
+	desc->src = xt->src_start;
+	desc->dest = xt->dst_start;
+	desc->x = xt->sgl[0].size;
+	desc->y = xt->numf;
+	desc->w = xt->sgl[0].icg + desc->x;
+	desc->len = desc->x * desc->y;
+	desc->direction = DMA_MEM_TO_MEM;
+	desc->config_port = IMX_DMA_MEMSIZE_32;
+	desc->config_mem = IMX_DMA_MEMSIZE_32;
+	if (xt->src_sgl)
+		desc->config_mem |= IMX_DMA_TYPE_2D;
+	if (xt->dst_sgl)
+		desc->config_port |= IMX_DMA_TYPE_2D;
+	desc->desc.callback = NULL;
+	desc->desc.callback_param = NULL;
+
+	return &desc->desc;
 }
 
 static void imxdma_issue_pending(struct dma_chan *chan)
 {
-	/*
-	 * Nothing to do. We only have a single descriptor
-	 */
+	struct imxdma_channel *imxdmac = to_imxdma_chan(chan);
+	struct imxdma_engine *imxdma = imxdmac->imxdma;
+	struct imxdma_desc *desc;
+	unsigned long flags;
+
+	spin_lock_irqsave(&imxdma->lock, flags);
+	if (list_empty(&imxdmac->ld_active) &&
+	    !list_empty(&imxdmac->ld_queue)) {
+		desc = list_first_entry(&imxdmac->ld_queue,
+					struct imxdma_desc, node);
+
+		if (imxdma_xfer_desc(desc) < 0) {
+			dev_warn(imxdma->dev,
+				 "%s: channel: %d couldn't issue DMA xfer\n",
+				 __func__, imxdmac->channel);
+		} else {
+			list_move_tail(imxdmac->ld_queue.next,
+				       &imxdmac->ld_active);
+		}
+	}
+	spin_unlock_irqrestore(&imxdma->lock, flags);
 }
 
 static int __init imxdma_probe(struct platform_device *pdev)
-{
+	{
 	struct imxdma_engine *imxdma;
 	int ret, i;
 
+
 	imxdma = kzalloc(sizeof(*imxdma), GFP_KERNEL);
 	if (!imxdma)
 		return -ENOMEM;
 
+	if (cpu_is_mx1()) {
+		imxdma->base = MX1_IO_ADDRESS(MX1_DMA_BASE_ADDR);
+	} else if (cpu_is_mx21()) {
+		imxdma->base = MX21_IO_ADDRESS(MX21_DMA_BASE_ADDR);
+	} else if (cpu_is_mx27()) {
+		imxdma->base = MX27_IO_ADDRESS(MX27_DMA_BASE_ADDR);
+	} else {
+		kfree(imxdma);
+		return 0;
+	}
+
+	imxdma->dma_clk = clk_get(NULL, "dma");
+	if (IS_ERR(imxdma->dma_clk))
+		return PTR_ERR(imxdma->dma_clk);
+	clk_enable(imxdma->dma_clk);
+
+	/* reset DMA module */
+	imx_dmav1_writel(imxdma, DCR_DRST, DMA_DCR);
+
+	if (cpu_is_mx1()) {
+		ret = request_irq(MX1_DMA_INT, dma_irq_handler, 0, "DMA", imxdma);
+		if (ret) {
+			dev_warn(imxdma->dev, "Can't register IRQ for DMA\n");
+			kfree(imxdma);
+			return ret;
+		}
+
+		ret = request_irq(MX1_DMA_ERR, imxdma_err_handler, 0, "DMA", imxdma);
+		if (ret) {
+			dev_warn(imxdma->dev, "Can't register ERRIRQ for DMA\n");
+			free_irq(MX1_DMA_INT, NULL);
+			kfree(imxdma);
+			return ret;
+		}
+	}
+
+	/* enable DMA module */
+	imx_dmav1_writel(imxdma, DCR_DEN, DMA_DCR);
+
+	/* clear all interrupts */
+	imx_dmav1_writel(imxdma, (1 << IMX_DMA_CHANNELS) - 1, DMA_DISR);
+
+	/* disable interrupts */
+	imx_dmav1_writel(imxdma, (1 << IMX_DMA_CHANNELS) - 1, DMA_DIMR);
+
 	INIT_LIST_HEAD(&imxdma->dma_device.channels);
 
 	dma_cap_set(DMA_SLAVE, imxdma->dma_device.cap_mask);
 	dma_cap_set(DMA_CYCLIC, imxdma->dma_device.cap_mask);
+	dma_cap_set(DMA_MEMCPY, imxdma->dma_device.cap_mask);
+	dma_cap_set(DMA_INTERLEAVE, imxdma->dma_device.cap_mask);
+
+	/* Initialize 2D global parameters */
+	for (i = 0; i < IMX_DMA_2D_SLOTS; i++)
+		imxdma->slots_2d[i].count = 0;
+
+	spin_lock_init(&imxdma->lock);
 
 	/* Initialize channel parameters */
-	for (i = 0; i < MAX_DMA_CHANNELS; i++) {
+	for (i = 0; i < IMX_DMA_CHANNELS; i++) {
 		struct imxdma_channel *imxdmac = &imxdma->channel[i];
 
-		imxdmac->imxdma_channel = imx_dma_request_by_prio("dmaengine",
-				DMA_PRIO_MEDIUM);
-		if ((int)imxdmac->channel < 0) {
-			ret = -ENODEV;
-			goto err_init;
+		if (cpu_is_mx21() || cpu_is_mx27()) {
+			ret = request_irq(MX2x_INT_DMACH0 + i,
+					dma_irq_handler, 0, "DMA", imxdma);
+			if (ret) {
+				dev_warn(imxdma->dev, "Can't register IRQ %d "
+					 "for DMA channel %d\n",
+					 MX2x_INT_DMACH0 + i, i);
+				goto err_init;
+			}
+			init_timer(&imxdmac->watchdog);
+			imxdmac->watchdog.function = &imxdma_watchdog;
+			imxdmac->watchdog.data = (unsigned long)imxdmac;
 		}
 
-		imx_dma_setup_handlers(imxdmac->imxdma_channel,
-		       imxdma_irq_handler, imxdma_err_handler, imxdmac);
-
 		imxdmac->imxdma = imxdma;
-		spin_lock_init(&imxdmac->lock);
 
+		INIT_LIST_HEAD(&imxdmac->ld_queue);
+		INIT_LIST_HEAD(&imxdmac->ld_free);
+		INIT_LIST_HEAD(&imxdmac->ld_active);
+
+		tasklet_init(&imxdmac->dma_tasklet, imxdma_tasklet,
+			     (unsigned long)imxdmac);
 		imxdmac->chan.device = &imxdma->dma_device;
+		dma_cookie_init(&imxdmac->chan);
 		imxdmac->channel = i;
 
 		/* Add the channel to the DMAC list */
-		list_add_tail(&imxdmac->chan.device_node, &imxdma->dma_device.channels);
+		list_add_tail(&imxdmac->chan.device_node,
+			      &imxdma->dma_device.channels);
 	}
 
 	imxdma->dev = &pdev->dev;
@@ -382,11 +1063,14 @@
 	imxdma->dma_device.device_tx_status = imxdma_tx_status;
 	imxdma->dma_device.device_prep_slave_sg = imxdma_prep_slave_sg;
 	imxdma->dma_device.device_prep_dma_cyclic = imxdma_prep_dma_cyclic;
+	imxdma->dma_device.device_prep_dma_memcpy = imxdma_prep_dma_memcpy;
+	imxdma->dma_device.device_prep_interleaved_dma = imxdma_prep_dma_interleaved;
 	imxdma->dma_device.device_control = imxdma_control;
 	imxdma->dma_device.device_issue_pending = imxdma_issue_pending;
 
 	platform_set_drvdata(pdev, imxdma);
 
+	imxdma->dma_device.copy_align = 2; /* 2^2 = 4 bytes alignment */
 	imxdma->dma_device.dev->dma_parms = &imxdma->dma_parms;
 	dma_set_max_seg_size(imxdma->dma_device.dev, 0xffffff);
 
@@ -399,9 +1083,13 @@
 	return 0;
 
 err_init:
-	while (--i >= 0) {
-		struct imxdma_channel *imxdmac = &imxdma->channel[i];
-		imx_dma_free(imxdmac->imxdma_channel);
+
+	if (cpu_is_mx21() || cpu_is_mx27()) {
+		while (--i >= 0)
+			free_irq(MX2x_INT_DMACH0 + i, NULL);
+	} else if cpu_is_mx1() {
+		free_irq(MX1_DMA_INT, NULL);
+		free_irq(MX1_DMA_ERR, NULL);
 	}
 
 	kfree(imxdma);
@@ -415,10 +1103,12 @@
 
         dma_async_device_unregister(&imxdma->dma_device);
 
-	for (i = 0; i < MAX_DMA_CHANNELS; i++) {
-		struct imxdma_channel *imxdmac = &imxdma->channel[i];
-
-		 imx_dma_free(imxdmac->imxdma_channel);
+	if (cpu_is_mx21() || cpu_is_mx27()) {
+		for (i = 0; i < IMX_DMA_CHANNELS; i++)
+			free_irq(MX2x_INT_DMACH0 + i, NULL);
+	} else if cpu_is_mx1() {
+		free_irq(MX1_DMA_INT, NULL);
+		free_irq(MX1_DMA_ERR, NULL);
 	}
 
         kfree(imxdma);
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index 63540d3..d3e38e2 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -20,6 +20,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/types.h>
+#include <linux/bitops.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
 #include <linux/clk.h>
@@ -41,6 +42,8 @@
 #include <mach/dma.h>
 #include <mach/hardware.h>
 
+#include "dmaengine.h"
+
 /* SDMA registers */
 #define SDMA_H_C0PTR		0x000
 #define SDMA_H_INTR		0x004
@@ -259,19 +262,18 @@
 	unsigned int			pc_from_device, pc_to_device;
 	unsigned long			flags;
 	dma_addr_t			per_address;
-	u32				event_mask0, event_mask1;
-	u32				watermark_level;
+	unsigned long			event_mask[2];
+	unsigned long			watermark_level;
 	u32				shp_addr, per_addr;
 	struct dma_chan			chan;
 	spinlock_t			lock;
 	struct dma_async_tx_descriptor	desc;
-	dma_cookie_t			last_completed;
 	enum dma_status			status;
 	unsigned int			chn_count;
 	unsigned int			chn_real_count;
 };
 
-#define IMX_DMA_SG_LOOP		(1 << 0)
+#define IMX_DMA_SG_LOOP		BIT(0)
 
 #define MAX_DMA_CHANNELS 32
 #define MXC_SDMA_DEFAULT_PRIORITY 1
@@ -345,9 +347,9 @@
 };
 MODULE_DEVICE_TABLE(of, sdma_dt_ids);
 
-#define SDMA_H_CONFIG_DSPDMA	(1 << 12) /* indicates if the DSPDMA is used */
-#define SDMA_H_CONFIG_RTD_PINS	(1 << 11) /* indicates if Real-Time Debug pins are enabled */
-#define SDMA_H_CONFIG_ACR	(1 << 4)  /* indicates if AHB freq /core freq = 2 or 1 */
+#define SDMA_H_CONFIG_DSPDMA	BIT(12) /* indicates if the DSPDMA is used */
+#define SDMA_H_CONFIG_RTD_PINS	BIT(11) /* indicates if Real-Time Debug pins are enabled */
+#define SDMA_H_CONFIG_ACR	BIT(4)  /* indicates if AHB freq /core freq = 2 or 1 */
 #define SDMA_H_CONFIG_CSM	(3)       /* indicates which context switch mode is selected*/
 
 static inline u32 chnenbl_ofs(struct sdma_engine *sdma, unsigned int event)
@@ -362,37 +364,42 @@
 {
 	struct sdma_engine *sdma = sdmac->sdma;
 	int channel = sdmac->channel;
-	u32 evt, mcu, dsp;
+	unsigned long evt, mcu, dsp;
 
 	if (event_override && mcu_override && dsp_override)
 		return -EINVAL;
 
-	evt = __raw_readl(sdma->regs + SDMA_H_EVTOVR);
-	mcu = __raw_readl(sdma->regs + SDMA_H_HOSTOVR);
-	dsp = __raw_readl(sdma->regs + SDMA_H_DSPOVR);
+	evt = readl_relaxed(sdma->regs + SDMA_H_EVTOVR);
+	mcu = readl_relaxed(sdma->regs + SDMA_H_HOSTOVR);
+	dsp = readl_relaxed(sdma->regs + SDMA_H_DSPOVR);
 
 	if (dsp_override)
-		dsp &= ~(1 << channel);
+		__clear_bit(channel, &dsp);
 	else
-		dsp |= (1 << channel);
+		__set_bit(channel, &dsp);
 
 	if (event_override)
-		evt &= ~(1 << channel);
+		__clear_bit(channel, &evt);
 	else
-		evt |= (1 << channel);
+		__set_bit(channel, &evt);
 
 	if (mcu_override)
-		mcu &= ~(1 << channel);
+		__clear_bit(channel, &mcu);
 	else
-		mcu |= (1 << channel);
+		__set_bit(channel, &mcu);
 
-	__raw_writel(evt, sdma->regs + SDMA_H_EVTOVR);
-	__raw_writel(mcu, sdma->regs + SDMA_H_HOSTOVR);
-	__raw_writel(dsp, sdma->regs + SDMA_H_DSPOVR);
+	writel_relaxed(evt, sdma->regs + SDMA_H_EVTOVR);
+	writel_relaxed(mcu, sdma->regs + SDMA_H_HOSTOVR);
+	writel_relaxed(dsp, sdma->regs + SDMA_H_DSPOVR);
 
 	return 0;
 }
 
+static void sdma_enable_channel(struct sdma_engine *sdma, int channel)
+{
+	writel(BIT(channel), sdma->regs + SDMA_H_START);
+}
+
 /*
  * sdma_run_channel - run a channel and wait till it's done
  */
@@ -404,7 +411,7 @@
 
 	init_completion(&sdmac->done);
 
-	__raw_writel(1 << channel, sdma->regs + SDMA_H_START);
+	sdma_enable_channel(sdma, channel);
 
 	ret = wait_for_completion_timeout(&sdmac->done, HZ);
 
@@ -451,12 +458,12 @@
 {
 	struct sdma_engine *sdma = sdmac->sdma;
 	int channel = sdmac->channel;
-	u32 val;
+	unsigned long val;
 	u32 chnenbl = chnenbl_ofs(sdma, event);
 
-	val = __raw_readl(sdma->regs + chnenbl);
-	val |= (1 << channel);
-	__raw_writel(val, sdma->regs + chnenbl);
+	val = readl_relaxed(sdma->regs + chnenbl);
+	__set_bit(channel, &val);
+	writel_relaxed(val, sdma->regs + chnenbl);
 }
 
 static void sdma_event_disable(struct sdma_channel *sdmac, unsigned int event)
@@ -464,11 +471,11 @@
 	struct sdma_engine *sdma = sdmac->sdma;
 	int channel = sdmac->channel;
 	u32 chnenbl = chnenbl_ofs(sdma, event);
-	u32 val;
+	unsigned long val;
 
-	val = __raw_readl(sdma->regs + chnenbl);
-	val &= ~(1 << channel);
-	__raw_writel(val, sdma->regs + chnenbl);
+	val = readl_relaxed(sdma->regs + chnenbl);
+	__clear_bit(channel, &val);
+	writel_relaxed(val, sdma->regs + chnenbl);
 }
 
 static void sdma_handle_channel_loop(struct sdma_channel *sdmac)
@@ -522,7 +529,7 @@
 	else
 		sdmac->status = DMA_SUCCESS;
 
-	sdmac->last_completed = sdmac->desc.cookie;
+	dma_cookie_complete(&sdmac->desc);
 	if (sdmac->desc.callback)
 		sdmac->desc.callback(sdmac->desc.callback_param);
 }
@@ -544,10 +551,10 @@
 static irqreturn_t sdma_int_handler(int irq, void *dev_id)
 {
 	struct sdma_engine *sdma = dev_id;
-	u32 stat;
+	unsigned long stat;
 
-	stat = __raw_readl(sdma->regs + SDMA_H_INTR);
-	__raw_writel(stat, sdma->regs + SDMA_H_INTR);
+	stat = readl_relaxed(sdma->regs + SDMA_H_INTR);
+	writel_relaxed(stat, sdma->regs + SDMA_H_INTR);
 
 	while (stat) {
 		int channel = fls(stat) - 1;
@@ -555,7 +562,7 @@
 
 		mxc_sdma_handle_channel(sdmac);
 
-		stat &= ~(1 << channel);
+		__clear_bit(channel, &stat);
 	}
 
 	return IRQ_HANDLED;
@@ -663,11 +670,11 @@
 		return load_address;
 
 	dev_dbg(sdma->dev, "load_address = %d\n", load_address);
-	dev_dbg(sdma->dev, "wml = 0x%08x\n", sdmac->watermark_level);
+	dev_dbg(sdma->dev, "wml = 0x%08x\n", (u32)sdmac->watermark_level);
 	dev_dbg(sdma->dev, "shp_addr = 0x%08x\n", sdmac->shp_addr);
 	dev_dbg(sdma->dev, "per_addr = 0x%08x\n", sdmac->per_addr);
-	dev_dbg(sdma->dev, "event_mask0 = 0x%08x\n", sdmac->event_mask0);
-	dev_dbg(sdma->dev, "event_mask1 = 0x%08x\n", sdmac->event_mask1);
+	dev_dbg(sdma->dev, "event_mask0 = 0x%08x\n", (u32)sdmac->event_mask[0]);
+	dev_dbg(sdma->dev, "event_mask1 = 0x%08x\n", (u32)sdmac->event_mask[1]);
 
 	mutex_lock(&sdma->channel_0_lock);
 
@@ -677,8 +684,8 @@
 	/* Send by context the event mask,base address for peripheral
 	 * and watermark level
 	 */
-	context->gReg[0] = sdmac->event_mask1;
-	context->gReg[1] = sdmac->event_mask0;
+	context->gReg[0] = sdmac->event_mask[1];
+	context->gReg[1] = sdmac->event_mask[0];
 	context->gReg[2] = sdmac->per_addr;
 	context->gReg[6] = sdmac->shp_addr;
 	context->gReg[7] = sdmac->watermark_level;
@@ -701,7 +708,7 @@
 	struct sdma_engine *sdma = sdmac->sdma;
 	int channel = sdmac->channel;
 
-	__raw_writel(1 << channel, sdma->regs + SDMA_H_STATSTOP);
+	writel_relaxed(BIT(channel), sdma->regs + SDMA_H_STATSTOP);
 	sdmac->status = DMA_ERROR;
 }
 
@@ -711,13 +718,13 @@
 
 	sdma_disable_channel(sdmac);
 
-	sdmac->event_mask0 = 0;
-	sdmac->event_mask1 = 0;
+	sdmac->event_mask[0] = 0;
+	sdmac->event_mask[1] = 0;
 	sdmac->shp_addr = 0;
 	sdmac->per_addr = 0;
 
 	if (sdmac->event_id0) {
-		if (sdmac->event_id0 > 32)
+		if (sdmac->event_id0 >= sdmac->sdma->num_events)
 			return -EINVAL;
 		sdma_event_enable(sdmac, sdmac->event_id0);
 	}
@@ -740,15 +747,14 @@
 			(sdmac->peripheral_type != IMX_DMATYPE_DSP)) {
 		/* Handle multiple event channels differently */
 		if (sdmac->event_id1) {
-			sdmac->event_mask1 = 1 << (sdmac->event_id1 % 32);
+			sdmac->event_mask[1] = BIT(sdmac->event_id1 % 32);
 			if (sdmac->event_id1 > 31)
-				sdmac->watermark_level |= 1 << 31;
-			sdmac->event_mask0 = 1 << (sdmac->event_id0 % 32);
+				__set_bit(31, &sdmac->watermark_level);
+			sdmac->event_mask[0] = BIT(sdmac->event_id0 % 32);
 			if (sdmac->event_id0 > 31)
-				sdmac->watermark_level |= 1 << 30;
+				__set_bit(30, &sdmac->watermark_level);
 		} else {
-			sdmac->event_mask0 = 1 << sdmac->event_id0;
-			sdmac->event_mask1 = 1 << (sdmac->event_id0 - 32);
+			__set_bit(sdmac->event_id0, sdmac->event_mask);
 		}
 		/* Watermark Level */
 		sdmac->watermark_level |= sdmac->watermark_level;
@@ -774,7 +780,7 @@
 		return -EINVAL;
 	}
 
-	__raw_writel(priority, sdma->regs + SDMA_CHNPRI_0 + 4 * channel);
+	writel_relaxed(priority, sdma->regs + SDMA_CHNPRI_0 + 4 * channel);
 
 	return 0;
 }
@@ -796,8 +802,6 @@
 	sdma->channel_control[channel].base_bd_ptr = sdmac->bd_phys;
 	sdma->channel_control[channel].current_bd_ptr = sdmac->bd_phys;
 
-	clk_enable(sdma->clk);
-
 	sdma_set_channel_priority(sdmac, MXC_SDMA_DEFAULT_PRIORITY);
 
 	init_completion(&sdmac->done);
@@ -810,24 +814,6 @@
 	return ret;
 }
 
-static void sdma_enable_channel(struct sdma_engine *sdma, int channel)
-{
-	__raw_writel(1 << channel, sdma->regs + SDMA_H_START);
-}
-
-static dma_cookie_t sdma_assign_cookie(struct sdma_channel *sdmac)
-{
-	dma_cookie_t cookie = sdmac->chan.cookie;
-
-	if (++cookie < 0)
-		cookie = 1;
-
-	sdmac->chan.cookie = cookie;
-	sdmac->desc.cookie = cookie;
-
-	return cookie;
-}
-
 static struct sdma_channel *to_sdma_chan(struct dma_chan *chan)
 {
 	return container_of(chan, struct sdma_channel, chan);
@@ -837,14 +823,11 @@
 {
 	unsigned long flags;
 	struct sdma_channel *sdmac = to_sdma_chan(tx->chan);
-	struct sdma_engine *sdma = sdmac->sdma;
 	dma_cookie_t cookie;
 
 	spin_lock_irqsave(&sdmac->lock, flags);
 
-	cookie = sdma_assign_cookie(sdmac);
-
-	sdma_enable_channel(sdma, sdmac->channel);
+	cookie = dma_cookie_assign(tx);
 
 	spin_unlock_irqrestore(&sdmac->lock, flags);
 
@@ -875,11 +858,14 @@
 
 	sdmac->peripheral_type = data->peripheral_type;
 	sdmac->event_id0 = data->dma_request;
-	ret = sdma_set_channel_priority(sdmac, prio);
+
+	clk_enable(sdmac->sdma->clk);
+
+	ret = sdma_request_channel(sdmac);
 	if (ret)
 		return ret;
 
-	ret = sdma_request_channel(sdmac);
+	ret = sdma_set_channel_priority(sdmac, prio);
 	if (ret)
 		return ret;
 
@@ -916,7 +902,7 @@
 static struct dma_async_tx_descriptor *sdma_prep_slave_sg(
 		struct dma_chan *chan, struct scatterlist *sgl,
 		unsigned int sg_len, enum dma_transfer_direction direction,
-		unsigned long flags)
+		unsigned long flags, void *context)
 {
 	struct sdma_channel *sdmac = to_sdma_chan(chan);
 	struct sdma_engine *sdma = sdmac->sdma;
@@ -1014,7 +1000,8 @@
 
 static struct dma_async_tx_descriptor *sdma_prep_dma_cyclic(
 		struct dma_chan *chan, dma_addr_t dma_addr, size_t buf_len,
-		size_t period_len, enum dma_transfer_direction direction)
+		size_t period_len, enum dma_transfer_direction direction,
+		void *context)
 {
 	struct sdma_channel *sdmac = to_sdma_chan(chan);
 	struct sdma_engine *sdma = sdmac->sdma;
@@ -1128,7 +1115,7 @@
 
 	last_used = chan->cookie;
 
-	dma_set_tx_state(txstate, sdmac->last_completed, last_used,
+	dma_set_tx_state(txstate, chan->completed_cookie, last_used,
 			sdmac->chn_count - sdmac->chn_real_count);
 
 	return sdmac->status;
@@ -1136,9 +1123,11 @@
 
 static void sdma_issue_pending(struct dma_chan *chan)
 {
-	/*
-	 * Nothing to do. We only have a single descriptor
-	 */
+	struct sdma_channel *sdmac = to_sdma_chan(chan);
+	struct sdma_engine *sdma = sdmac->sdma;
+
+	if (sdmac->status == DMA_IN_PROGRESS)
+		sdma_enable_channel(sdma, sdmac->channel);
 }
 
 #define SDMA_SCRIPT_ADDRS_ARRAY_SIZE_V1	34
@@ -1230,7 +1219,7 @@
 	clk_enable(sdma->clk);
 
 	/* Be sure SDMA has not started yet */
-	__raw_writel(0, sdma->regs + SDMA_H_C0PTR);
+	writel_relaxed(0, sdma->regs + SDMA_H_C0PTR);
 
 	sdma->channel_control = dma_alloc_coherent(NULL,
 			MAX_DMA_CHANNELS * sizeof (struct sdma_channel_control) +
@@ -1253,11 +1242,11 @@
 
 	/* disable all channels */
 	for (i = 0; i < sdma->num_events; i++)
-		__raw_writel(0, sdma->regs + chnenbl_ofs(sdma, i));
+		writel_relaxed(0, sdma->regs + chnenbl_ofs(sdma, i));
 
 	/* All channels have priority 0 */
 	for (i = 0; i < MAX_DMA_CHANNELS; i++)
-		__raw_writel(0, sdma->regs + SDMA_CHNPRI_0 + i * 4);
+		writel_relaxed(0, sdma->regs + SDMA_CHNPRI_0 + i * 4);
 
 	ret = sdma_request_channel(&sdma->channel[0]);
 	if (ret)
@@ -1266,16 +1255,16 @@
 	sdma_config_ownership(&sdma->channel[0], false, true, false);
 
 	/* Set Command Channel (Channel Zero) */
-	__raw_writel(0x4050, sdma->regs + SDMA_CHN0ADDR);
+	writel_relaxed(0x4050, sdma->regs + SDMA_CHN0ADDR);
 
 	/* Set bits of CONFIG register but with static context switching */
 	/* FIXME: Check whether to set ACR bit depending on clock ratios */
-	__raw_writel(0, sdma->regs + SDMA_H_CONFIG);
+	writel_relaxed(0, sdma->regs + SDMA_H_CONFIG);
 
-	__raw_writel(ccb_phys, sdma->regs + SDMA_H_C0PTR);
+	writel_relaxed(ccb_phys, sdma->regs + SDMA_H_C0PTR);
 
 	/* Set bits of CONFIG register with given context switching mode */
-	__raw_writel(SDMA_H_CONFIG_CSM, sdma->regs + SDMA_H_CONFIG);
+	writel_relaxed(SDMA_H_CONFIG_CSM, sdma->regs + SDMA_H_CONFIG);
 
 	/* Initializes channel's priorities */
 	sdma_set_channel_priority(&sdma->channel[0], 7);
@@ -1367,6 +1356,7 @@
 		spin_lock_init(&sdmac->lock);
 
 		sdmac->chan.device = &sdma->dma_device;
+		dma_cookie_init(&sdmac->chan);
 		sdmac->channel = i;
 
 		/*
@@ -1387,7 +1377,9 @@
 		sdma_add_scripts(sdma, pdata->script_addrs);
 
 	if (pdata) {
-		sdma_get_firmware(sdma, pdata->fw_name);
+		ret = sdma_get_firmware(sdma, pdata->fw_name);
+		if (ret)
+			dev_warn(&pdev->dev, "failed to get firmware from platform data\n");
 	} else {
 		/*
 		 * Because that device tree does not encode ROM script address,
@@ -1396,15 +1388,12 @@
 		 */
 		ret = of_property_read_string(np, "fsl,sdma-ram-script-name",
 					      &fw_name);
-		if (ret) {
-			dev_err(&pdev->dev, "failed to get firmware name\n");
-			goto err_init;
-		}
-
-		ret = sdma_get_firmware(sdma, fw_name);
-		if (ret) {
-			dev_err(&pdev->dev, "failed to get firmware\n");
-			goto err_init;
+		if (ret)
+			dev_warn(&pdev->dev, "failed to get firmware name\n");
+		else {
+			ret = sdma_get_firmware(sdma, fw_name);
+			if (ret)
+				dev_warn(&pdev->dev, "failed to get firmware from device tree\n");
 		}
 	}
 
diff --git a/drivers/dma/intel_mid_dma.c b/drivers/dma/intel_mid_dma.c
index 74f70aa..c900ca7 100644
--- a/drivers/dma/intel_mid_dma.c
+++ b/drivers/dma/intel_mid_dma.c
@@ -29,6 +29,8 @@
 #include <linux/intel_mid_dma.h>
 #include <linux/module.h>
 
+#include "dmaengine.h"
+
 #define MAX_CHAN	4 /*max ch across controllers*/
 #include "intel_mid_dma_regs.h"
 
@@ -288,7 +290,7 @@
 	struct intel_mid_dma_lli	*llitem;
 	void *param_txd = NULL;
 
-	midc->completed = txd->cookie;
+	dma_cookie_complete(txd);
 	callback_txd = txd->callback;
 	param_txd = txd->callback_param;
 
@@ -434,14 +436,7 @@
 	dma_cookie_t		cookie;
 
 	spin_lock_bh(&midc->lock);
-	cookie = midc->chan.cookie;
-
-	if (++cookie < 0)
-		cookie = 1;
-
-	midc->chan.cookie = cookie;
-	desc->txd.cookie = cookie;
-
+	cookie = dma_cookie_assign(tx);
 
 	if (list_empty(&midc->active_list))
 		list_add_tail(&desc->desc_node, &midc->active_list);
@@ -482,31 +477,18 @@
 						dma_cookie_t cookie,
 						struct dma_tx_state *txstate)
 {
-	struct intel_mid_dma_chan	*midc = to_intel_mid_dma_chan(chan);
-	dma_cookie_t		last_used;
-	dma_cookie_t		last_complete;
-	int				ret;
+	struct intel_mid_dma_chan *midc = to_intel_mid_dma_chan(chan);
+	enum dma_status ret;
 
-	last_complete = midc->completed;
-	last_used = chan->cookie;
-
-	ret = dma_async_is_complete(cookie, last_complete, last_used);
+	ret = dma_cookie_status(chan, cookie, txstate);
 	if (ret != DMA_SUCCESS) {
 		spin_lock_bh(&midc->lock);
 		midc_scan_descriptors(to_middma_device(chan->device), midc);
 		spin_unlock_bh(&midc->lock);
 
-		last_complete = midc->completed;
-		last_used = chan->cookie;
-
-		ret = dma_async_is_complete(cookie, last_complete, last_used);
+		ret = dma_cookie_status(chan, cookie, txstate);
 	}
 
-	if (txstate) {
-		txstate->last = last_complete;
-		txstate->used = last_used;
-		txstate->residue = 0;
-	}
 	return ret;
 }
 
@@ -732,13 +714,14 @@
  * @sg_len: length of sg txn
  * @direction: DMA transfer dirtn
  * @flags: DMA flags
+ * @context: transfer context (ignored)
  *
  * Prepares LLI based periphral transfer
  */
 static struct dma_async_tx_descriptor *intel_mid_dma_prep_slave_sg(
 			struct dma_chan *chan, struct scatterlist *sgl,
 			unsigned int sg_len, enum dma_transfer_direction direction,
-			unsigned long flags)
+			unsigned long flags, void *context)
 {
 	struct intel_mid_dma_chan *midc = NULL;
 	struct intel_mid_dma_slave *mids = NULL;
@@ -832,7 +815,6 @@
 		/*trying to free ch in use!!!!!*/
 		pr_err("ERR_MDMA: trying to free ch in use\n");
 	}
-	pm_runtime_put(&mid->pdev->dev);
 	spin_lock_bh(&midc->lock);
 	midc->descs_allocated = 0;
 	list_for_each_entry_safe(desc, _desc, &midc->active_list, desc_node) {
@@ -853,6 +835,7 @@
 	/* Disable CH interrupts */
 	iowrite32(MASK_INTR_REG(midc->ch_id), mid->dma_base + MASK_BLOCK);
 	iowrite32(MASK_INTR_REG(midc->ch_id), mid->dma_base + MASK_ERR);
+	pm_runtime_put(&mid->pdev->dev);
 }
 
 /**
@@ -886,7 +869,7 @@
 		pm_runtime_put(&mid->pdev->dev);
 		return -EIO;
 	}
-	midc->completed = chan->cookie = 1;
+	dma_cookie_init(chan);
 
 	spin_lock_bh(&midc->lock);
 	while (midc->descs_allocated < DESCS_PER_CHANNEL) {
@@ -1056,7 +1039,8 @@
 	}
 	err_status &= mid->intr_mask;
 	if (err_status) {
-		iowrite32(MASK_INTR_REG(err_status), mid->dma_base + MASK_ERR);
+		iowrite32((err_status << INT_MASK_WE),
+			  mid->dma_base + MASK_ERR);
 		call_tasklet = 1;
 	}
 	if (call_tasklet)
@@ -1118,7 +1102,7 @@
 		struct intel_mid_dma_chan *midch = &dma->ch[i];
 
 		midch->chan.device = &dma->common;
-		midch->chan.cookie =  1;
+		dma_cookie_init(&midch->chan);
 		midch->ch_id = dma->chan_base + i;
 		pr_debug("MDMA:Init CH %d, ID %d\n", i, midch->ch_id);
 
diff --git a/drivers/dma/intel_mid_dma_regs.h b/drivers/dma/intel_mid_dma_regs.h
index c83d35b..1bfa926 100644
--- a/drivers/dma/intel_mid_dma_regs.h
+++ b/drivers/dma/intel_mid_dma_regs.h
@@ -165,7 +165,6 @@
  * @dma_base: MMIO register space DMA engine base pointer
  * @ch_id: DMA channel id
  * @lock: channel spinlock
- * @completed: DMA cookie
  * @active_list: current active descriptors
  * @queue: current queued up descriptors
  * @free_list: current free descriptors
@@ -183,7 +182,6 @@
 	void __iomem		*dma_base;
 	int			ch_id;
 	spinlock_t		lock;
-	dma_cookie_t		completed;
 	struct list_head	active_list;
 	struct list_head	queue;
 	struct list_head	free_list;
diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c
index a4d6cb0..31493d8 100644
--- a/drivers/dma/ioat/dma.c
+++ b/drivers/dma/ioat/dma.c
@@ -40,6 +40,8 @@
 #include "registers.h"
 #include "hw.h"
 
+#include "../dmaengine.h"
+
 int ioat_pending_level = 4;
 module_param(ioat_pending_level, int, 0644);
 MODULE_PARM_DESC(ioat_pending_level,
@@ -107,6 +109,7 @@
 	chan->reg_base = device->reg_base + (0x80 * (idx + 1));
 	spin_lock_init(&chan->cleanup_lock);
 	chan->common.device = dma;
+	dma_cookie_init(&chan->common);
 	list_add_tail(&chan->common.device_node, &dma->channels);
 	device->idx[idx] = chan;
 	init_timer(&chan->timer);
@@ -235,12 +238,7 @@
 
 	spin_lock_bh(&ioat->desc_lock);
 	/* cookie incr and addition to used_list must be atomic */
-	cookie = c->cookie;
-	cookie++;
-	if (cookie < 0)
-		cookie = 1;
-	c->cookie = cookie;
-	tx->cookie = cookie;
+	cookie = dma_cookie_assign(tx);
 	dev_dbg(to_dev(&ioat->base), "%s: cookie: %d\n", __func__, cookie);
 
 	/* write address into NextDescriptor field of last desc in chain */
@@ -603,8 +601,7 @@
 		 */
 		dump_desc_dbg(ioat, desc);
 		if (tx->cookie) {
-			chan->completed_cookie = tx->cookie;
-			tx->cookie = 0;
+			dma_cookie_complete(tx);
 			ioat_dma_unmap(chan, tx->flags, desc->len, desc->hw);
 			ioat->active -= desc->hw->tx_cnt;
 			if (tx->callback) {
@@ -733,13 +730,15 @@
 {
 	struct ioat_chan_common *chan = to_chan_common(c);
 	struct ioatdma_device *device = chan->device;
+	enum dma_status ret;
 
-	if (ioat_tx_status(c, cookie, txstate) == DMA_SUCCESS)
-		return DMA_SUCCESS;
+	ret = dma_cookie_status(c, cookie, txstate);
+	if (ret == DMA_SUCCESS)
+		return ret;
 
 	device->cleanup_fn((unsigned long) c);
 
-	return ioat_tx_status(c, cookie, txstate);
+	return dma_cookie_status(c, cookie, txstate);
 }
 
 static void ioat1_dma_start_null_desc(struct ioat_dma_chan *ioat)
diff --git a/drivers/dma/ioat/dma.h b/drivers/dma/ioat/dma.h
index 5216c8a..c7888bc 100644
--- a/drivers/dma/ioat/dma.h
+++ b/drivers/dma/ioat/dma.h
@@ -90,7 +90,6 @@
 	void __iomem *reg_base;
 	unsigned long last_completion;
 	spinlock_t cleanup_lock;
-	dma_cookie_t completed_cookie;
 	unsigned long state;
 	#define IOAT_COMPLETION_PENDING 0
 	#define IOAT_COMPLETION_ACK 1
@@ -143,28 +142,6 @@
 	return container_of(chan, struct ioat_dma_chan, base);
 }
 
-/**
- * ioat_tx_status - poll the status of an ioat transaction
- * @c: channel handle
- * @cookie: transaction identifier
- * @txstate: if set, updated with the transaction state
- */
-static inline enum dma_status
-ioat_tx_status(struct dma_chan *c, dma_cookie_t cookie,
-		 struct dma_tx_state *txstate)
-{
-	struct ioat_chan_common *chan = to_chan_common(c);
-	dma_cookie_t last_used;
-	dma_cookie_t last_complete;
-
-	last_used = c->cookie;
-	last_complete = chan->completed_cookie;
-
-	dma_set_tx_state(txstate, last_complete, last_used, 0);
-
-	return dma_async_is_complete(cookie, last_complete, last_used);
-}
-
 /* wrapper around hardware descriptor format + additional software fields */
 
 /**
diff --git a/drivers/dma/ioat/dma_v2.c b/drivers/dma/ioat/dma_v2.c
index 5d65f83..e8e110f 100644
--- a/drivers/dma/ioat/dma_v2.c
+++ b/drivers/dma/ioat/dma_v2.c
@@ -41,6 +41,8 @@
 #include "registers.h"
 #include "hw.h"
 
+#include "../dmaengine.h"
+
 int ioat_ring_alloc_order = 8;
 module_param(ioat_ring_alloc_order, int, 0644);
 MODULE_PARM_DESC(ioat_ring_alloc_order,
@@ -147,8 +149,7 @@
 		dump_desc_dbg(ioat, desc);
 		if (tx->cookie) {
 			ioat_dma_unmap(chan, tx->flags, desc->len, desc->hw);
-			chan->completed_cookie = tx->cookie;
-			tx->cookie = 0;
+			dma_cookie_complete(tx);
 			if (tx->callback) {
 				tx->callback(tx->callback_param);
 				tx->callback = NULL;
@@ -398,13 +399,9 @@
 	struct dma_chan *c = tx->chan;
 	struct ioat2_dma_chan *ioat = to_ioat2_chan(c);
 	struct ioat_chan_common *chan = &ioat->base;
-	dma_cookie_t cookie = c->cookie;
+	dma_cookie_t cookie;
 
-	cookie++;
-	if (cookie < 0)
-		cookie = 1;
-	tx->cookie = cookie;
-	c->cookie = cookie;
+	cookie = dma_cookie_assign(tx);
 	dev_dbg(to_dev(&ioat->base), "%s: cookie: %d\n", __func__, cookie);
 
 	if (!test_and_set_bit(IOAT_COMPLETION_PENDING, &chan->state))
diff --git a/drivers/dma/ioat/dma_v3.c b/drivers/dma/ioat/dma_v3.c
index f519c93..2c4476c 100644
--- a/drivers/dma/ioat/dma_v3.c
+++ b/drivers/dma/ioat/dma_v3.c
@@ -61,6 +61,7 @@
 #include <linux/dmaengine.h>
 #include <linux/dma-mapping.h>
 #include <linux/prefetch.h>
+#include "../dmaengine.h"
 #include "registers.h"
 #include "hw.h"
 #include "dma.h"
@@ -277,9 +278,8 @@
 		dump_desc_dbg(ioat, desc);
 		tx = &desc->txd;
 		if (tx->cookie) {
-			chan->completed_cookie = tx->cookie;
+			dma_cookie_complete(tx);
 			ioat3_dma_unmap(ioat, desc, idx + i);
-			tx->cookie = 0;
 			if (tx->callback) {
 				tx->callback(tx->callback_param);
 				tx->callback = NULL;
@@ -411,13 +411,15 @@
 		struct dma_tx_state *txstate)
 {
 	struct ioat2_dma_chan *ioat = to_ioat2_chan(c);
+	enum dma_status ret;
 
-	if (ioat_tx_status(c, cookie, txstate) == DMA_SUCCESS)
-		return DMA_SUCCESS;
+	ret = dma_cookie_status(c, cookie, txstate);
+	if (ret == DMA_SUCCESS)
+		return ret;
 
 	ioat3_cleanup(ioat);
 
-	return ioat_tx_status(c, cookie, txstate);
+	return dma_cookie_status(c, cookie, txstate);
 }
 
 static struct dma_async_tx_descriptor *
diff --git a/drivers/dma/iop-adma.c b/drivers/dma/iop-adma.c
index faf88b7..da6c4c2 100644
--- a/drivers/dma/iop-adma.c
+++ b/drivers/dma/iop-adma.c
@@ -36,6 +36,8 @@
 
 #include <mach/adma.h>
 
+#include "dmaengine.h"
+
 #define to_iop_adma_chan(chan) container_of(chan, struct iop_adma_chan, common)
 #define to_iop_adma_device(dev) \
 	container_of(dev, struct iop_adma_device, common)
@@ -317,7 +319,7 @@
 	}
 
 	if (cookie > 0) {
-		iop_chan->completed_cookie = cookie;
+		iop_chan->common.completed_cookie = cookie;
 		pr_debug("\tcompleted cookie %d\n", cookie);
 	}
 }
@@ -438,18 +440,6 @@
 	return NULL;
 }
 
-static dma_cookie_t
-iop_desc_assign_cookie(struct iop_adma_chan *iop_chan,
-	struct iop_adma_desc_slot *desc)
-{
-	dma_cookie_t cookie = iop_chan->common.cookie;
-	cookie++;
-	if (cookie < 0)
-		cookie = 1;
-	iop_chan->common.cookie = desc->async_tx.cookie = cookie;
-	return cookie;
-}
-
 static void iop_adma_check_threshold(struct iop_adma_chan *iop_chan)
 {
 	dev_dbg(iop_chan->device->common.dev, "pending: %d\n",
@@ -477,7 +467,7 @@
 	slots_per_op = grp_start->slots_per_op;
 
 	spin_lock_bh(&iop_chan->lock);
-	cookie = iop_desc_assign_cookie(iop_chan, sw_desc);
+	cookie = dma_cookie_assign(tx);
 
 	old_chain_tail = list_entry(iop_chan->chain.prev,
 		struct iop_adma_desc_slot, chain_node);
@@ -904,24 +894,15 @@
 					struct dma_tx_state *txstate)
 {
 	struct iop_adma_chan *iop_chan = to_iop_adma_chan(chan);
-	dma_cookie_t last_used;
-	dma_cookie_t last_complete;
-	enum dma_status ret;
+	int ret;
 
-	last_used = chan->cookie;
-	last_complete = iop_chan->completed_cookie;
-	dma_set_tx_state(txstate, last_complete, last_used, 0);
-	ret = dma_async_is_complete(cookie, last_complete, last_used);
+	ret = dma_cookie_status(chan, cookie, txstate);
 	if (ret == DMA_SUCCESS)
 		return ret;
 
 	iop_adma_slot_cleanup(iop_chan);
 
-	last_used = chan->cookie;
-	last_complete = iop_chan->completed_cookie;
-	dma_set_tx_state(txstate, last_complete, last_used, 0);
-
-	return dma_async_is_complete(cookie, last_complete, last_used);
+	return dma_cookie_status(chan, cookie, txstate);
 }
 
 static irqreturn_t iop_adma_eot_handler(int irq, void *data)
@@ -1565,6 +1546,7 @@
 	INIT_LIST_HEAD(&iop_chan->chain);
 	INIT_LIST_HEAD(&iop_chan->all_slots);
 	iop_chan->common.device = dma_dev;
+	dma_cookie_init(&iop_chan->common);
 	list_add_tail(&iop_chan->common.device_node, &dma_dev->channels);
 
 	if (dma_has_cap(DMA_MEMCPY, dma_dev->cap_mask)) {
@@ -1642,16 +1624,12 @@
 		iop_desc_set_dest_addr(grp_start, iop_chan, 0);
 		iop_desc_set_memcpy_src_addr(grp_start, 0);
 
-		cookie = iop_chan->common.cookie;
-		cookie++;
-		if (cookie <= 1)
-			cookie = 2;
+		cookie = dma_cookie_assign(&sw_desc->async_tx);
 
 		/* initialize the completed cookie to be less than
 		 * the most recently used cookie
 		 */
-		iop_chan->completed_cookie = cookie - 1;
-		iop_chan->common.cookie = sw_desc->async_tx.cookie = cookie;
+		iop_chan->common.completed_cookie = cookie - 1;
 
 		/* channel should not be busy */
 		BUG_ON(iop_chan_is_busy(iop_chan));
@@ -1699,16 +1677,12 @@
 		iop_desc_set_xor_src_addr(grp_start, 0, 0);
 		iop_desc_set_xor_src_addr(grp_start, 1, 0);
 
-		cookie = iop_chan->common.cookie;
-		cookie++;
-		if (cookie <= 1)
-			cookie = 2;
+		cookie = dma_cookie_assign(&sw_desc->async_tx);
 
 		/* initialize the completed cookie to be less than
 		 * the most recently used cookie
 		 */
-		iop_chan->completed_cookie = cookie - 1;
-		iop_chan->common.cookie = sw_desc->async_tx.cookie = cookie;
+		iop_chan->common.completed_cookie = cookie - 1;
 
 		/* channel should not be busy */
 		BUG_ON(iop_chan_is_busy(iop_chan));
diff --git a/drivers/dma/ipu/ipu_idmac.c b/drivers/dma/ipu/ipu_idmac.c
index 6212b16..62e3f8e 100644
--- a/drivers/dma/ipu/ipu_idmac.c
+++ b/drivers/dma/ipu/ipu_idmac.c
@@ -25,6 +25,7 @@
 
 #include <mach/ipu.h>
 
+#include "../dmaengine.h"
 #include "ipu_intern.h"
 
 #define FS_VF_IN_VALID	0x00000002
@@ -866,14 +867,7 @@
 
 	dev_dbg(dev, "Submitting sg %p\n", &desc->sg[0]);
 
-	cookie = ichan->dma_chan.cookie;
-
-	if (++cookie < 0)
-		cookie = 1;
-
-	/* from dmaengine.h: "last cookie value returned to client" */
-	ichan->dma_chan.cookie = cookie;
-	tx->cookie = cookie;
+	cookie = dma_cookie_assign(tx);
 
 	/* ipu->lock can be taken under ichan->lock, but not v.v. */
 	spin_lock_irqsave(&ichan->lock, flags);
@@ -1295,7 +1289,7 @@
 	/* Flip the active buffer - even if update above failed */
 	ichan->active_buffer = !ichan->active_buffer;
 	if (done)
-		ichan->completed = desc->txd.cookie;
+		dma_cookie_complete(&desc->txd);
 
 	callback = desc->txd.callback;
 	callback_param = desc->txd.callback_param;
@@ -1341,7 +1335,8 @@
 /* Allocate and initialise a transfer descriptor. */
 static struct dma_async_tx_descriptor *idmac_prep_slave_sg(struct dma_chan *chan,
 		struct scatterlist *sgl, unsigned int sg_len,
-		enum dma_transfer_direction direction, unsigned long tx_flags)
+		enum dma_transfer_direction direction, unsigned long tx_flags,
+		void *context)
 {
 	struct idmac_channel *ichan = to_idmac_chan(chan);
 	struct idmac_tx_desc *desc = NULL;
@@ -1510,8 +1505,7 @@
 	BUG_ON(chan->client_count > 1);
 	WARN_ON(ichan->status != IPU_CHANNEL_FREE);
 
-	chan->cookie		= 1;
-	ichan->completed	= -ENXIO;
+	dma_cookie_init(chan);
 
 	ret = ipu_irq_map(chan->chan_id);
 	if (ret < 0)
@@ -1600,9 +1594,7 @@
 static enum dma_status idmac_tx_status(struct dma_chan *chan,
 		       dma_cookie_t cookie, struct dma_tx_state *txstate)
 {
-	struct idmac_channel *ichan = to_idmac_chan(chan);
-
-	dma_set_tx_state(txstate, ichan->completed, chan->cookie, 0);
+	dma_set_tx_state(txstate, chan->completed_cookie, chan->cookie, 0);
 	if (cookie != chan->cookie)
 		return DMA_ERROR;
 	return DMA_SUCCESS;
@@ -1638,11 +1630,10 @@
 
 		ichan->status		= IPU_CHANNEL_FREE;
 		ichan->sec_chan_en	= false;
-		ichan->completed	= -ENXIO;
 		snprintf(ichan->eof_name, sizeof(ichan->eof_name), "IDMAC EOF %d", i);
 
 		dma_chan->device	= &idmac->dma;
-		dma_chan->cookie	= 1;
+		dma_cookie_init(dma_chan);
 		dma_chan->chan_id	= i;
 		list_add_tail(&dma_chan->device_node, &dma->channels);
 	}
diff --git a/drivers/dma/mpc512x_dma.c b/drivers/dma/mpc512x_dma.c
index 4d6d4cf..2ab0a3d 100644
--- a/drivers/dma/mpc512x_dma.c
+++ b/drivers/dma/mpc512x_dma.c
@@ -44,6 +44,8 @@
 
 #include <linux/random.h>
 
+#include "dmaengine.h"
+
 /* Number of DMA Transfer descriptors allocated per channel */
 #define MPC_DMA_DESCRIPTORS	64
 
@@ -188,7 +190,6 @@
 	struct list_head		completed;
 	struct mpc_dma_tcd		*tcd;
 	dma_addr_t			tcd_paddr;
-	dma_cookie_t			completed_cookie;
 
 	/* Lock for this structure */
 	spinlock_t			lock;
@@ -365,7 +366,7 @@
 		/* Free descriptors */
 		spin_lock_irqsave(&mchan->lock, flags);
 		list_splice_tail_init(&list, &mchan->free);
-		mchan->completed_cookie = last_cookie;
+		mchan->chan.completed_cookie = last_cookie;
 		spin_unlock_irqrestore(&mchan->lock, flags);
 	}
 }
@@ -438,13 +439,7 @@
 		mpc_dma_execute(mchan);
 
 	/* Update cookie */
-	cookie = mchan->chan.cookie + 1;
-	if (cookie <= 0)
-		cookie = 1;
-
-	mchan->chan.cookie = cookie;
-	mdesc->desc.cookie = cookie;
-
+	cookie = dma_cookie_assign(txd);
 	spin_unlock_irqrestore(&mchan->lock, flags);
 
 	return cookie;
@@ -562,17 +557,14 @@
 	       struct dma_tx_state *txstate)
 {
 	struct mpc_dma_chan *mchan = dma_chan_to_mpc_dma_chan(chan);
+	enum dma_status ret;
 	unsigned long flags;
-	dma_cookie_t last_used;
-	dma_cookie_t last_complete;
 
 	spin_lock_irqsave(&mchan->lock, flags);
-	last_used = mchan->chan.cookie;
-	last_complete = mchan->completed_cookie;
+	ret = dma_cookie_status(chan, cookie, txstate);
 	spin_unlock_irqrestore(&mchan->lock, flags);
 
-	dma_set_tx_state(txstate, last_complete, last_used, 0);
-	return dma_async_is_complete(cookie, last_complete, last_used);
+	return ret;
 }
 
 /* Prepare descriptor for memory to memory copy */
@@ -741,8 +733,7 @@
 		mchan = &mdma->channels[i];
 
 		mchan->chan.device = dma;
-		mchan->chan.cookie = 1;
-		mchan->completed_cookie = mchan->chan.cookie;
+		dma_cookie_init(&mchan->chan);
 
 		INIT_LIST_HEAD(&mchan->free);
 		INIT_LIST_HEAD(&mchan->prepared);
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index e779b43..fa5d55f 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -26,6 +26,8 @@
 #include <linux/platform_device.h>
 #include <linux/memory.h>
 #include <plat/mv_xor.h>
+
+#include "dmaengine.h"
 #include "mv_xor.h"
 
 static void mv_xor_issue_pending(struct dma_chan *chan);
@@ -435,7 +437,7 @@
 	}
 
 	if (cookie > 0)
-		mv_chan->completed_cookie = cookie;
+		mv_chan->common.completed_cookie = cookie;
 }
 
 static void
@@ -534,18 +536,6 @@
 	return NULL;
 }
 
-static dma_cookie_t
-mv_desc_assign_cookie(struct mv_xor_chan *mv_chan,
-		      struct mv_xor_desc_slot *desc)
-{
-	dma_cookie_t cookie = mv_chan->common.cookie;
-
-	if (++cookie < 0)
-		cookie = 1;
-	mv_chan->common.cookie = desc->async_tx.cookie = cookie;
-	return cookie;
-}
-
 /************************ DMA engine API functions ****************************/
 static dma_cookie_t
 mv_xor_tx_submit(struct dma_async_tx_descriptor *tx)
@@ -563,7 +553,7 @@
 	grp_start = sw_desc->group_head;
 
 	spin_lock_bh(&mv_chan->lock);
-	cookie = mv_desc_assign_cookie(mv_chan, sw_desc);
+	cookie = dma_cookie_assign(tx);
 
 	if (list_empty(&mv_chan->chain))
 		list_splice_init(&sw_desc->tx_list, &mv_chan->chain);
@@ -820,27 +810,16 @@
 					  struct dma_tx_state *txstate)
 {
 	struct mv_xor_chan *mv_chan = to_mv_xor_chan(chan);
-	dma_cookie_t last_used;
-	dma_cookie_t last_complete;
 	enum dma_status ret;
 
-	last_used = chan->cookie;
-	last_complete = mv_chan->completed_cookie;
-	mv_chan->is_complete_cookie = cookie;
-	dma_set_tx_state(txstate, last_complete, last_used, 0);
-
-	ret = dma_async_is_complete(cookie, last_complete, last_used);
+	ret = dma_cookie_status(chan, cookie, txstate);
 	if (ret == DMA_SUCCESS) {
 		mv_xor_clean_completed_slots(mv_chan);
 		return ret;
 	}
 	mv_xor_slot_cleanup(mv_chan);
 
-	last_used = chan->cookie;
-	last_complete = mv_chan->completed_cookie;
-
-	dma_set_tx_state(txstate, last_complete, last_used, 0);
-	return dma_async_is_complete(cookie, last_complete, last_used);
+	return dma_cookie_status(chan, cookie, txstate);
 }
 
 static void mv_dump_xor_regs(struct mv_xor_chan *chan)
@@ -1214,6 +1193,7 @@
 	INIT_LIST_HEAD(&mv_chan->completed_slots);
 	INIT_LIST_HEAD(&mv_chan->all_slots);
 	mv_chan->common.device = dma_dev;
+	dma_cookie_init(&mv_chan->common);
 
 	list_add_tail(&mv_chan->common.device_node, &dma_dev->channels);
 
diff --git a/drivers/dma/mv_xor.h b/drivers/dma/mv_xor.h
index 977b592..654876b 100644
--- a/drivers/dma/mv_xor.h
+++ b/drivers/dma/mv_xor.h
@@ -78,7 +78,6 @@
 /**
  * struct mv_xor_chan - internal representation of a XOR channel
  * @pending: allows batching of hardware operations
- * @completed_cookie: identifier for the most recently completed operation
  * @lock: serializes enqueue/dequeue operations to the descriptors pool
  * @mmr_base: memory mapped register base
  * @idx: the index of the xor channel
@@ -93,7 +92,6 @@
  */
 struct mv_xor_chan {
 	int			pending;
-	dma_cookie_t		completed_cookie;
 	spinlock_t		lock; /* protects the descriptor slot pool */
 	void __iomem		*mmr_base;
 	unsigned int		idx;
@@ -109,7 +107,6 @@
 #ifdef USE_TIMER
 	unsigned long		cleanup_time;
 	u32			current_on_last_cleanup;
-	dma_cookie_t		is_complete_cookie;
 #endif
 };
 
diff --git a/drivers/dma/mxs-dma.c b/drivers/dma/mxs-dma.c
index b06cd4c..65334c4 100644
--- a/drivers/dma/mxs-dma.c
+++ b/drivers/dma/mxs-dma.c
@@ -28,6 +28,8 @@
 #include <mach/dma.h>
 #include <mach/common.h>
 
+#include "dmaengine.h"
+
 /*
  * NOTE: The term "PIO" throughout the mxs-dma implementation means
  * PIO mode of mxs apbh-dma and apbx-dma.  With this working mode,
@@ -111,7 +113,6 @@
 	struct mxs_dma_ccw		*ccw;
 	dma_addr_t			ccw_phys;
 	int				desc_count;
-	dma_cookie_t			last_completed;
 	enum dma_status			status;
 	unsigned int			flags;
 #define MXS_DMA_SG_LOOP			(1 << 0)
@@ -193,19 +194,6 @@
 	mxs_chan->status = DMA_IN_PROGRESS;
 }
 
-static dma_cookie_t mxs_dma_assign_cookie(struct mxs_dma_chan *mxs_chan)
-{
-	dma_cookie_t cookie = mxs_chan->chan.cookie;
-
-	if (++cookie < 0)
-		cookie = 1;
-
-	mxs_chan->chan.cookie = cookie;
-	mxs_chan->desc.cookie = cookie;
-
-	return cookie;
-}
-
 static struct mxs_dma_chan *to_mxs_dma_chan(struct dma_chan *chan)
 {
 	return container_of(chan, struct mxs_dma_chan, chan);
@@ -217,7 +205,7 @@
 
 	mxs_dma_enable_chan(mxs_chan);
 
-	return mxs_dma_assign_cookie(mxs_chan);
+	return dma_cookie_assign(tx);
 }
 
 static void mxs_dma_tasklet(unsigned long data)
@@ -274,7 +262,7 @@
 		stat1 &= ~(1 << channel);
 
 		if (mxs_chan->status == DMA_SUCCESS)
-			mxs_chan->last_completed = mxs_chan->desc.cookie;
+			dma_cookie_complete(&mxs_chan->desc);
 
 		/* schedule tasklet on this channel */
 		tasklet_schedule(&mxs_chan->tasklet);
@@ -352,7 +340,7 @@
 static struct dma_async_tx_descriptor *mxs_dma_prep_slave_sg(
 		struct dma_chan *chan, struct scatterlist *sgl,
 		unsigned int sg_len, enum dma_transfer_direction direction,
-		unsigned long append)
+		unsigned long append, void *context)
 {
 	struct mxs_dma_chan *mxs_chan = to_mxs_dma_chan(chan);
 	struct mxs_dma_engine *mxs_dma = mxs_chan->mxs_dma;
@@ -447,7 +435,8 @@
 
 static struct dma_async_tx_descriptor *mxs_dma_prep_dma_cyclic(
 		struct dma_chan *chan, dma_addr_t dma_addr, size_t buf_len,
-		size_t period_len, enum dma_transfer_direction direction)
+		size_t period_len, enum dma_transfer_direction direction,
+		void *context)
 {
 	struct mxs_dma_chan *mxs_chan = to_mxs_dma_chan(chan);
 	struct mxs_dma_engine *mxs_dma = mxs_chan->mxs_dma;
@@ -538,7 +527,7 @@
 	dma_cookie_t last_used;
 
 	last_used = chan->cookie;
-	dma_set_tx_state(txstate, mxs_chan->last_completed, last_used, 0);
+	dma_set_tx_state(txstate, chan->completed_cookie, last_used, 0);
 
 	return mxs_chan->status;
 }
@@ -630,6 +619,7 @@
 
 		mxs_chan->mxs_dma = mxs_dma;
 		mxs_chan->chan.device = &mxs_dma->dma_device;
+		dma_cookie_init(&mxs_chan->chan);
 
 		tasklet_init(&mxs_chan->tasklet, mxs_dma_tasklet,
 			     (unsigned long) mxs_chan);
diff --git a/drivers/dma/pch_dma.c b/drivers/dma/pch_dma.c
index 823f581..65c0495 100644
--- a/drivers/dma/pch_dma.c
+++ b/drivers/dma/pch_dma.c
@@ -25,6 +25,8 @@
 #include <linux/module.h>
 #include <linux/pch_dma.h>
 
+#include "dmaengine.h"
+
 #define DRV_NAME "pch-dma"
 
 #define DMA_CTL0_DISABLE		0x0
@@ -105,7 +107,6 @@
 
 	spinlock_t		lock;
 
-	dma_cookie_t		completed_cookie;
 	struct list_head	active_list;
 	struct list_head	queue;
 	struct list_head	free_list;
@@ -416,20 +417,6 @@
 	}
 }
 
-static dma_cookie_t pdc_assign_cookie(struct pch_dma_chan *pd_chan,
-				      struct pch_dma_desc *desc)
-{
-	dma_cookie_t cookie = pd_chan->chan.cookie;
-
-	if (++cookie < 0)
-		cookie = 1;
-
-	pd_chan->chan.cookie = cookie;
-	desc->txd.cookie = cookie;
-
-	return cookie;
-}
-
 static dma_cookie_t pd_tx_submit(struct dma_async_tx_descriptor *txd)
 {
 	struct pch_dma_desc *desc = to_pd_desc(txd);
@@ -437,7 +424,7 @@
 	dma_cookie_t cookie;
 
 	spin_lock(&pd_chan->lock);
-	cookie = pdc_assign_cookie(pd_chan, desc);
+	cookie = dma_cookie_assign(txd);
 
 	if (list_empty(&pd_chan->active_list)) {
 		list_add_tail(&desc->desc_node, &pd_chan->active_list);
@@ -544,7 +531,7 @@
 	spin_lock_irq(&pd_chan->lock);
 	list_splice(&tmp_list, &pd_chan->free_list);
 	pd_chan->descs_allocated = i;
-	pd_chan->completed_cookie = chan->cookie = 1;
+	dma_cookie_init(chan);
 	spin_unlock_irq(&pd_chan->lock);
 
 	pdc_enable_irq(chan, 1);
@@ -578,19 +565,12 @@
 				    struct dma_tx_state *txstate)
 {
 	struct pch_dma_chan *pd_chan = to_pd_chan(chan);
-	dma_cookie_t last_used;
-	dma_cookie_t last_completed;
-	int ret;
+	enum dma_status ret;
 
 	spin_lock_irq(&pd_chan->lock);
-	last_completed = pd_chan->completed_cookie;
-	last_used = chan->cookie;
+	ret = dma_cookie_status(chan, cookie, txstate);
 	spin_unlock_irq(&pd_chan->lock);
 
-	ret = dma_async_is_complete(cookie, last_completed, last_used);
-
-	dma_set_tx_state(txstate, last_completed, last_used, 0);
-
 	return ret;
 }
 
@@ -607,7 +587,8 @@
 
 static struct dma_async_tx_descriptor *pd_prep_slave_sg(struct dma_chan *chan,
 			struct scatterlist *sgl, unsigned int sg_len,
-			enum dma_transfer_direction direction, unsigned long flags)
+			enum dma_transfer_direction direction, unsigned long flags,
+			void *context)
 {
 	struct pch_dma_chan *pd_chan = to_pd_chan(chan);
 	struct pch_dma_slave *pd_slave = chan->private;
@@ -932,7 +913,7 @@
 		struct pch_dma_chan *pd_chan = &pd->channels[i];
 
 		pd_chan->chan.device = &pd->dma;
-		pd_chan->chan.cookie = 1;
+		dma_cookie_init(&pd_chan->chan);
 
 		pd_chan->membase = &regs->desc[i];
 
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index 16b66c8..282caf1 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -1,4 +1,6 @@
-/* linux/drivers/dma/pl330.c
+/*
+ * Copyright (c) 2012 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
  *
  * Copyright (C) 2010 Samsung Electronics Co. Ltd.
  *	Jaswinder Singh <jassi.brar@samsung.com>
@@ -9,10 +11,15 @@
  * (at your option) any later version.
  */
 
+#include <linux/kernel.h>
 #include <linux/io.h>
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/module.h>
+#include <linux/string.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/dma-mapping.h>
 #include <linux/dmaengine.h>
 #include <linux/interrupt.h>
 #include <linux/amba/bus.h>
@@ -21,8 +28,497 @@
 #include <linux/scatterlist.h>
 #include <linux/of.h>
 
+#include "dmaengine.h"
+#define PL330_MAX_CHAN		8
+#define PL330_MAX_IRQS		32
+#define PL330_MAX_PERI		32
+
+enum pl330_srccachectrl {
+	SCCTRL0,	/* Noncacheable and nonbufferable */
+	SCCTRL1,	/* Bufferable only */
+	SCCTRL2,	/* Cacheable, but do not allocate */
+	SCCTRL3,	/* Cacheable and bufferable, but do not allocate */
+	SINVALID1,
+	SINVALID2,
+	SCCTRL6,	/* Cacheable write-through, allocate on reads only */
+	SCCTRL7,	/* Cacheable write-back, allocate on reads only */
+};
+
+enum pl330_dstcachectrl {
+	DCCTRL0,	/* Noncacheable and nonbufferable */
+	DCCTRL1,	/* Bufferable only */
+	DCCTRL2,	/* Cacheable, but do not allocate */
+	DCCTRL3,	/* Cacheable and bufferable, but do not allocate */
+	DINVALID1,	/* AWCACHE = 0x1000 */
+	DINVALID2,
+	DCCTRL6,	/* Cacheable write-through, allocate on writes only */
+	DCCTRL7,	/* Cacheable write-back, allocate on writes only */
+};
+
+enum pl330_byteswap {
+	SWAP_NO,
+	SWAP_2,
+	SWAP_4,
+	SWAP_8,
+	SWAP_16,
+};
+
+enum pl330_reqtype {
+	MEMTOMEM,
+	MEMTODEV,
+	DEVTOMEM,
+	DEVTODEV,
+};
+
+/* Register and Bit field Definitions */
+#define DS			0x0
+#define DS_ST_STOP		0x0
+#define DS_ST_EXEC		0x1
+#define DS_ST_CMISS		0x2
+#define DS_ST_UPDTPC		0x3
+#define DS_ST_WFE		0x4
+#define DS_ST_ATBRR		0x5
+#define DS_ST_QBUSY		0x6
+#define DS_ST_WFP		0x7
+#define DS_ST_KILL		0x8
+#define DS_ST_CMPLT		0x9
+#define DS_ST_FLTCMP		0xe
+#define DS_ST_FAULT		0xf
+
+#define DPC			0x4
+#define INTEN			0x20
+#define ES			0x24
+#define INTSTATUS		0x28
+#define INTCLR			0x2c
+#define FSM			0x30
+#define FSC			0x34
+#define FTM			0x38
+
+#define _FTC			0x40
+#define FTC(n)			(_FTC + (n)*0x4)
+
+#define _CS			0x100
+#define CS(n)			(_CS + (n)*0x8)
+#define CS_CNS			(1 << 21)
+
+#define _CPC			0x104
+#define CPC(n)			(_CPC + (n)*0x8)
+
+#define _SA			0x400
+#define SA(n)			(_SA + (n)*0x20)
+
+#define _DA			0x404
+#define DA(n)			(_DA + (n)*0x20)
+
+#define _CC			0x408
+#define CC(n)			(_CC + (n)*0x20)
+
+#define CC_SRCINC		(1 << 0)
+#define CC_DSTINC		(1 << 14)
+#define CC_SRCPRI		(1 << 8)
+#define CC_DSTPRI		(1 << 22)
+#define CC_SRCNS		(1 << 9)
+#define CC_DSTNS		(1 << 23)
+#define CC_SRCIA		(1 << 10)
+#define CC_DSTIA		(1 << 24)
+#define CC_SRCBRSTLEN_SHFT	4
+#define CC_DSTBRSTLEN_SHFT	18
+#define CC_SRCBRSTSIZE_SHFT	1
+#define CC_DSTBRSTSIZE_SHFT	15
+#define CC_SRCCCTRL_SHFT	11
+#define CC_SRCCCTRL_MASK	0x7
+#define CC_DSTCCTRL_SHFT	25
+#define CC_DRCCCTRL_MASK	0x7
+#define CC_SWAP_SHFT		28
+
+#define _LC0			0x40c
+#define LC0(n)			(_LC0 + (n)*0x20)
+
+#define _LC1			0x410
+#define LC1(n)			(_LC1 + (n)*0x20)
+
+#define DBGSTATUS		0xd00
+#define DBG_BUSY		(1 << 0)
+
+#define DBGCMD			0xd04
+#define DBGINST0		0xd08
+#define DBGINST1		0xd0c
+
+#define CR0			0xe00
+#define CR1			0xe04
+#define CR2			0xe08
+#define CR3			0xe0c
+#define CR4			0xe10
+#define CRD			0xe14
+
+#define PERIPH_ID		0xfe0
+#define PERIPH_REV_SHIFT	20
+#define PERIPH_REV_MASK		0xf
+#define PERIPH_REV_R0P0		0
+#define PERIPH_REV_R1P0		1
+#define PERIPH_REV_R1P1		2
+#define PCELL_ID		0xff0
+
+#define CR0_PERIPH_REQ_SET	(1 << 0)
+#define CR0_BOOT_EN_SET		(1 << 1)
+#define CR0_BOOT_MAN_NS		(1 << 2)
+#define CR0_NUM_CHANS_SHIFT	4
+#define CR0_NUM_CHANS_MASK	0x7
+#define CR0_NUM_PERIPH_SHIFT	12
+#define CR0_NUM_PERIPH_MASK	0x1f
+#define CR0_NUM_EVENTS_SHIFT	17
+#define CR0_NUM_EVENTS_MASK	0x1f
+
+#define CR1_ICACHE_LEN_SHIFT	0
+#define CR1_ICACHE_LEN_MASK	0x7
+#define CR1_NUM_ICACHELINES_SHIFT	4
+#define CR1_NUM_ICACHELINES_MASK	0xf
+
+#define CRD_DATA_WIDTH_SHIFT	0
+#define CRD_DATA_WIDTH_MASK	0x7
+#define CRD_WR_CAP_SHIFT	4
+#define CRD_WR_CAP_MASK		0x7
+#define CRD_WR_Q_DEP_SHIFT	8
+#define CRD_WR_Q_DEP_MASK	0xf
+#define CRD_RD_CAP_SHIFT	12
+#define CRD_RD_CAP_MASK		0x7
+#define CRD_RD_Q_DEP_SHIFT	16
+#define CRD_RD_Q_DEP_MASK	0xf
+#define CRD_DATA_BUFF_SHIFT	20
+#define CRD_DATA_BUFF_MASK	0x3ff
+
+#define PART			0x330
+#define DESIGNER		0x41
+#define REVISION		0x0
+#define INTEG_CFG		0x0
+#define PERIPH_ID_VAL		((PART << 0) | (DESIGNER << 12))
+
+#define PCELL_ID_VAL		0xb105f00d
+
+#define PL330_STATE_STOPPED		(1 << 0)
+#define PL330_STATE_EXECUTING		(1 << 1)
+#define PL330_STATE_WFE			(1 << 2)
+#define PL330_STATE_FAULTING		(1 << 3)
+#define PL330_STATE_COMPLETING		(1 << 4)
+#define PL330_STATE_WFP			(1 << 5)
+#define PL330_STATE_KILLING		(1 << 6)
+#define PL330_STATE_FAULT_COMPLETING	(1 << 7)
+#define PL330_STATE_CACHEMISS		(1 << 8)
+#define PL330_STATE_UPDTPC		(1 << 9)
+#define PL330_STATE_ATBARRIER		(1 << 10)
+#define PL330_STATE_QUEUEBUSY		(1 << 11)
+#define PL330_STATE_INVALID		(1 << 15)
+
+#define PL330_STABLE_STATES (PL330_STATE_STOPPED | PL330_STATE_EXECUTING \
+				| PL330_STATE_WFE | PL330_STATE_FAULTING)
+
+#define CMD_DMAADDH		0x54
+#define CMD_DMAEND		0x00
+#define CMD_DMAFLUSHP		0x35
+#define CMD_DMAGO		0xa0
+#define CMD_DMALD		0x04
+#define CMD_DMALDP		0x25
+#define CMD_DMALP		0x20
+#define CMD_DMALPEND		0x28
+#define CMD_DMAKILL		0x01
+#define CMD_DMAMOV		0xbc
+#define CMD_DMANOP		0x18
+#define CMD_DMARMB		0x12
+#define CMD_DMASEV		0x34
+#define CMD_DMAST		0x08
+#define CMD_DMASTP		0x29
+#define CMD_DMASTZ		0x0c
+#define CMD_DMAWFE		0x36
+#define CMD_DMAWFP		0x30
+#define CMD_DMAWMB		0x13
+
+#define SZ_DMAADDH		3
+#define SZ_DMAEND		1
+#define SZ_DMAFLUSHP		2
+#define SZ_DMALD		1
+#define SZ_DMALDP		2
+#define SZ_DMALP		2
+#define SZ_DMALPEND		2
+#define SZ_DMAKILL		1
+#define SZ_DMAMOV		6
+#define SZ_DMANOP		1
+#define SZ_DMARMB		1
+#define SZ_DMASEV		2
+#define SZ_DMAST		1
+#define SZ_DMASTP		2
+#define SZ_DMASTZ		1
+#define SZ_DMAWFE		2
+#define SZ_DMAWFP		2
+#define SZ_DMAWMB		1
+#define SZ_DMAGO		6
+
+#define BRST_LEN(ccr)		((((ccr) >> CC_SRCBRSTLEN_SHFT) & 0xf) + 1)
+#define BRST_SIZE(ccr)		(1 << (((ccr) >> CC_SRCBRSTSIZE_SHFT) & 0x7))
+
+#define BYTE_TO_BURST(b, ccr)	((b) / BRST_SIZE(ccr) / BRST_LEN(ccr))
+#define BURST_TO_BYTE(c, ccr)	((c) * BRST_SIZE(ccr) * BRST_LEN(ccr))
+
+/*
+ * With 256 bytes, we can do more than 2.5MB and 5MB xfers per req
+ * at 1byte/burst for P<->M and M<->M respectively.
+ * For typical scenario, at 1word/burst, 10MB and 20MB xfers per req
+ * should be enough for P<->M and M<->M respectively.
+ */
+#define MCODE_BUFF_PER_REQ	256
+
+/* If the _pl330_req is available to the client */
+#define IS_FREE(req)	(*((u8 *)((req)->mc_cpu)) == CMD_DMAEND)
+
+/* Use this _only_ to wait on transient states */
+#define UNTIL(t, s)	while (!(_state(t) & (s))) cpu_relax();
+
+#ifdef PL330_DEBUG_MCGEN
+static unsigned cmd_line;
+#define PL330_DBGCMD_DUMP(off, x...)	do { \
+						printk("%x:", cmd_line); \
+						printk(x); \
+						cmd_line += off; \
+					} while (0)
+#define PL330_DBGMC_START(addr)		(cmd_line = addr)
+#else
+#define PL330_DBGCMD_DUMP(off, x...)	do {} while (0)
+#define PL330_DBGMC_START(addr)		do {} while (0)
+#endif
+
+/* The number of default descriptors */
+
 #define NR_DEFAULT_DESC	16
 
+/* Populated by the PL330 core driver for DMA API driver's info */
+struct pl330_config {
+	u32	periph_id;
+	u32	pcell_id;
+#define DMAC_MODE_NS	(1 << 0)
+	unsigned int	mode;
+	unsigned int	data_bus_width:10; /* In number of bits */
+	unsigned int	data_buf_dep:10;
+	unsigned int	num_chan:4;
+	unsigned int	num_peri:6;
+	u32		peri_ns;
+	unsigned int	num_events:6;
+	u32		irq_ns;
+};
+
+/* Handle to the DMAC provided to the PL330 core */
+struct pl330_info {
+	/* Owning device */
+	struct device *dev;
+	/* Size of MicroCode buffers for each channel. */
+	unsigned mcbufsz;
+	/* ioremap'ed address of PL330 registers. */
+	void __iomem	*base;
+	/* Client can freely use it. */
+	void	*client_data;
+	/* PL330 core data, Client must not touch it. */
+	void	*pl330_data;
+	/* Populated by the PL330 core driver during pl330_add */
+	struct pl330_config	pcfg;
+	/*
+	 * If the DMAC has some reset mechanism, then the
+	 * client may want to provide pointer to the method.
+	 */
+	void (*dmac_reset)(struct pl330_info *pi);
+};
+
+/**
+ * Request Configuration.
+ * The PL330 core does not modify this and uses the last
+ * working configuration if the request doesn't provide any.
+ *
+ * The Client may want to provide this info only for the
+ * first request and a request with new settings.
+ */
+struct pl330_reqcfg {
+	/* Address Incrementing */
+	unsigned dst_inc:1;
+	unsigned src_inc:1;
+
+	/*
+	 * For now, the SRC & DST protection levels
+	 * and burst size/length are assumed same.
+	 */
+	bool nonsecure;
+	bool privileged;
+	bool insnaccess;
+	unsigned brst_len:5;
+	unsigned brst_size:3; /* in power of 2 */
+
+	enum pl330_dstcachectrl dcctl;
+	enum pl330_srccachectrl scctl;
+	enum pl330_byteswap swap;
+	struct pl330_config *pcfg;
+};
+
+/*
+ * One cycle of DMAC operation.
+ * There may be more than one xfer in a request.
+ */
+struct pl330_xfer {
+	u32 src_addr;
+	u32 dst_addr;
+	/* Size to xfer */
+	u32 bytes;
+	/*
+	 * Pointer to next xfer in the list.
+	 * The last xfer in the req must point to NULL.
+	 */
+	struct pl330_xfer *next;
+};
+
+/* The xfer callbacks are made with one of these arguments. */
+enum pl330_op_err {
+	/* The all xfers in the request were success. */
+	PL330_ERR_NONE,
+	/* If req aborted due to global error. */
+	PL330_ERR_ABORT,
+	/* If req failed due to problem with Channel. */
+	PL330_ERR_FAIL,
+};
+
+/* A request defining Scatter-Gather List ending with NULL xfer. */
+struct pl330_req {
+	enum pl330_reqtype rqtype;
+	/* Index of peripheral for the xfer. */
+	unsigned peri:5;
+	/* Unique token for this xfer, set by the client. */
+	void *token;
+	/* Callback to be called after xfer. */
+	void (*xfer_cb)(void *token, enum pl330_op_err err);
+	/* If NULL, req will be done at last set parameters. */
+	struct pl330_reqcfg *cfg;
+	/* Pointer to first xfer in the request. */
+	struct pl330_xfer *x;
+};
+
+/*
+ * To know the status of the channel and DMAC, the client
+ * provides a pointer to this structure. The PL330 core
+ * fills it with current information.
+ */
+struct pl330_chanstatus {
+	/*
+	 * If the DMAC engine halted due to some error,
+	 * the client should remove-add DMAC.
+	 */
+	bool dmac_halted;
+	/*
+	 * If channel is halted due to some error,
+	 * the client should ABORT/FLUSH and START the channel.
+	 */
+	bool faulting;
+	/* Location of last load */
+	u32 src_addr;
+	/* Location of last store */
+	u32 dst_addr;
+	/*
+	 * Pointer to the currently active req, NULL if channel is
+	 * inactive, even though the requests may be present.
+	 */
+	struct pl330_req *top_req;
+	/* Pointer to req waiting second in the queue if any. */
+	struct pl330_req *wait_req;
+};
+
+enum pl330_chan_op {
+	/* Start the channel */
+	PL330_OP_START,
+	/* Abort the active xfer */
+	PL330_OP_ABORT,
+	/* Stop xfer and flush queue */
+	PL330_OP_FLUSH,
+};
+
+struct _xfer_spec {
+	u32 ccr;
+	struct pl330_req *r;
+	struct pl330_xfer *x;
+};
+
+enum dmamov_dst {
+	SAR = 0,
+	CCR,
+	DAR,
+};
+
+enum pl330_dst {
+	SRC = 0,
+	DST,
+};
+
+enum pl330_cond {
+	SINGLE,
+	BURST,
+	ALWAYS,
+};
+
+struct _pl330_req {
+	u32 mc_bus;
+	void *mc_cpu;
+	/* Number of bytes taken to setup MC for the req */
+	u32 mc_len;
+	struct pl330_req *r;
+	/* Hook to attach to DMAC's list of reqs with due callback */
+	struct list_head rqd;
+};
+
+/* ToBeDone for tasklet */
+struct _pl330_tbd {
+	bool reset_dmac;
+	bool reset_mngr;
+	u8 reset_chan;
+};
+
+/* A DMAC Thread */
+struct pl330_thread {
+	u8 id;
+	int ev;
+	/* If the channel is not yet acquired by any client */
+	bool free;
+	/* Parent DMAC */
+	struct pl330_dmac *dmac;
+	/* Only two at a time */
+	struct _pl330_req req[2];
+	/* Index of the last enqueued request */
+	unsigned lstenq;
+	/* Index of the last submitted request or -1 if the DMA is stopped */
+	int req_running;
+};
+
+enum pl330_dmac_state {
+	UNINIT,
+	INIT,
+	DYING,
+};
+
+/* A DMAC */
+struct pl330_dmac {
+	spinlock_t		lock;
+	/* Holds list of reqs with due callbacks */
+	struct list_head	req_done;
+	/* Pointer to platform specific stuff */
+	struct pl330_info	*pinfo;
+	/* Maximum possible events/irqs */
+	int			events[32];
+	/* BUS address of MicroCode buffer */
+	u32			mcode_bus;
+	/* CPU address of MicroCode buffer */
+	void			*mcode_cpu;
+	/* List of all Channel threads */
+	struct pl330_thread	*channels;
+	/* Pointer to the MANAGER thread */
+	struct pl330_thread	*manager;
+	/* To handle bad news in interrupt */
+	struct tasklet_struct	tasks;
+	struct _pl330_tbd	dmac_tbd;
+	/* State of DMAC operation */
+	enum pl330_dmac_state	state;
+};
+
 enum desc_status {
 	/* In the DMAC pool */
 	FREE,
@@ -51,9 +547,6 @@
 	/* DMA-Engine Channel */
 	struct dma_chan chan;
 
-	/* Last completed cookie */
-	dma_cookie_t completed;
-
 	/* List of to be xfered descriptors */
 	struct list_head work_list;
 
@@ -117,6 +610,1599 @@
 	struct dma_pl330_chan *pchan;
 };
 
+static inline void _callback(struct pl330_req *r, enum pl330_op_err err)
+{
+	if (r && r->xfer_cb)
+		r->xfer_cb(r->token, err);
+}
+
+static inline bool _queue_empty(struct pl330_thread *thrd)
+{
+	return (IS_FREE(&thrd->req[0]) && IS_FREE(&thrd->req[1]))
+		? true : false;
+}
+
+static inline bool _queue_full(struct pl330_thread *thrd)
+{
+	return (IS_FREE(&thrd->req[0]) || IS_FREE(&thrd->req[1]))
+		? false : true;
+}
+
+static inline bool is_manager(struct pl330_thread *thrd)
+{
+	struct pl330_dmac *pl330 = thrd->dmac;
+
+	/* MANAGER is indexed at the end */
+	if (thrd->id == pl330->pinfo->pcfg.num_chan)
+		return true;
+	else
+		return false;
+}
+
+/* If manager of the thread is in Non-Secure mode */
+static inline bool _manager_ns(struct pl330_thread *thrd)
+{
+	struct pl330_dmac *pl330 = thrd->dmac;
+
+	return (pl330->pinfo->pcfg.mode & DMAC_MODE_NS) ? true : false;
+}
+
+static inline u32 get_id(struct pl330_info *pi, u32 off)
+{
+	void __iomem *regs = pi->base;
+	u32 id = 0;
+
+	id |= (readb(regs + off + 0x0) << 0);
+	id |= (readb(regs + off + 0x4) << 8);
+	id |= (readb(regs + off + 0x8) << 16);
+	id |= (readb(regs + off + 0xc) << 24);
+
+	return id;
+}
+
+static inline u32 get_revision(u32 periph_id)
+{
+	return (periph_id >> PERIPH_REV_SHIFT) & PERIPH_REV_MASK;
+}
+
+static inline u32 _emit_ADDH(unsigned dry_run, u8 buf[],
+		enum pl330_dst da, u16 val)
+{
+	if (dry_run)
+		return SZ_DMAADDH;
+
+	buf[0] = CMD_DMAADDH;
+	buf[0] |= (da << 1);
+	*((u16 *)&buf[1]) = val;
+
+	PL330_DBGCMD_DUMP(SZ_DMAADDH, "\tDMAADDH %s %u\n",
+		da == 1 ? "DA" : "SA", val);
+
+	return SZ_DMAADDH;
+}
+
+static inline u32 _emit_END(unsigned dry_run, u8 buf[])
+{
+	if (dry_run)
+		return SZ_DMAEND;
+
+	buf[0] = CMD_DMAEND;
+
+	PL330_DBGCMD_DUMP(SZ_DMAEND, "\tDMAEND\n");
+
+	return SZ_DMAEND;
+}
+
+static inline u32 _emit_FLUSHP(unsigned dry_run, u8 buf[], u8 peri)
+{
+	if (dry_run)
+		return SZ_DMAFLUSHP;
+
+	buf[0] = CMD_DMAFLUSHP;
+
+	peri &= 0x1f;
+	peri <<= 3;
+	buf[1] = peri;
+
+	PL330_DBGCMD_DUMP(SZ_DMAFLUSHP, "\tDMAFLUSHP %u\n", peri >> 3);
+
+	return SZ_DMAFLUSHP;
+}
+
+static inline u32 _emit_LD(unsigned dry_run, u8 buf[],	enum pl330_cond cond)
+{
+	if (dry_run)
+		return SZ_DMALD;
+
+	buf[0] = CMD_DMALD;
+
+	if (cond == SINGLE)
+		buf[0] |= (0 << 1) | (1 << 0);
+	else if (cond == BURST)
+		buf[0] |= (1 << 1) | (1 << 0);
+
+	PL330_DBGCMD_DUMP(SZ_DMALD, "\tDMALD%c\n",
+		cond == SINGLE ? 'S' : (cond == BURST ? 'B' : 'A'));
+
+	return SZ_DMALD;
+}
+
+static inline u32 _emit_LDP(unsigned dry_run, u8 buf[],
+		enum pl330_cond cond, u8 peri)
+{
+	if (dry_run)
+		return SZ_DMALDP;
+
+	buf[0] = CMD_DMALDP;
+
+	if (cond == BURST)
+		buf[0] |= (1 << 1);
+
+	peri &= 0x1f;
+	peri <<= 3;
+	buf[1] = peri;
+
+	PL330_DBGCMD_DUMP(SZ_DMALDP, "\tDMALDP%c %u\n",
+		cond == SINGLE ? 'S' : 'B', peri >> 3);
+
+	return SZ_DMALDP;
+}
+
+static inline u32 _emit_LP(unsigned dry_run, u8 buf[],
+		unsigned loop, u8 cnt)
+{
+	if (dry_run)
+		return SZ_DMALP;
+
+	buf[0] = CMD_DMALP;
+
+	if (loop)
+		buf[0] |= (1 << 1);
+
+	cnt--; /* DMAC increments by 1 internally */
+	buf[1] = cnt;
+
+	PL330_DBGCMD_DUMP(SZ_DMALP, "\tDMALP_%c %u\n", loop ? '1' : '0', cnt);
+
+	return SZ_DMALP;
+}
+
+struct _arg_LPEND {
+	enum pl330_cond cond;
+	bool forever;
+	unsigned loop;
+	u8 bjump;
+};
+
+static inline u32 _emit_LPEND(unsigned dry_run, u8 buf[],
+		const struct _arg_LPEND *arg)
+{
+	enum pl330_cond cond = arg->cond;
+	bool forever = arg->forever;
+	unsigned loop = arg->loop;
+	u8 bjump = arg->bjump;
+
+	if (dry_run)
+		return SZ_DMALPEND;
+
+	buf[0] = CMD_DMALPEND;
+
+	if (loop)
+		buf[0] |= (1 << 2);
+
+	if (!forever)
+		buf[0] |= (1 << 4);
+
+	if (cond == SINGLE)
+		buf[0] |= (0 << 1) | (1 << 0);
+	else if (cond == BURST)
+		buf[0] |= (1 << 1) | (1 << 0);
+
+	buf[1] = bjump;
+
+	PL330_DBGCMD_DUMP(SZ_DMALPEND, "\tDMALP%s%c_%c bjmpto_%x\n",
+			forever ? "FE" : "END",
+			cond == SINGLE ? 'S' : (cond == BURST ? 'B' : 'A'),
+			loop ? '1' : '0',
+			bjump);
+
+	return SZ_DMALPEND;
+}
+
+static inline u32 _emit_KILL(unsigned dry_run, u8 buf[])
+{
+	if (dry_run)
+		return SZ_DMAKILL;
+
+	buf[0] = CMD_DMAKILL;
+
+	return SZ_DMAKILL;
+}
+
+static inline u32 _emit_MOV(unsigned dry_run, u8 buf[],
+		enum dmamov_dst dst, u32 val)
+{
+	if (dry_run)
+		return SZ_DMAMOV;
+
+	buf[0] = CMD_DMAMOV;
+	buf[1] = dst;
+	*((u32 *)&buf[2]) = val;
+
+	PL330_DBGCMD_DUMP(SZ_DMAMOV, "\tDMAMOV %s 0x%x\n",
+		dst == SAR ? "SAR" : (dst == DAR ? "DAR" : "CCR"), val);
+
+	return SZ_DMAMOV;
+}
+
+static inline u32 _emit_NOP(unsigned dry_run, u8 buf[])
+{
+	if (dry_run)
+		return SZ_DMANOP;
+
+	buf[0] = CMD_DMANOP;
+
+	PL330_DBGCMD_DUMP(SZ_DMANOP, "\tDMANOP\n");
+
+	return SZ_DMANOP;
+}
+
+static inline u32 _emit_RMB(unsigned dry_run, u8 buf[])
+{
+	if (dry_run)
+		return SZ_DMARMB;
+
+	buf[0] = CMD_DMARMB;
+
+	PL330_DBGCMD_DUMP(SZ_DMARMB, "\tDMARMB\n");
+
+	return SZ_DMARMB;
+}
+
+static inline u32 _emit_SEV(unsigned dry_run, u8 buf[], u8 ev)
+{
+	if (dry_run)
+		return SZ_DMASEV;
+
+	buf[0] = CMD_DMASEV;
+
+	ev &= 0x1f;
+	ev <<= 3;
+	buf[1] = ev;
+
+	PL330_DBGCMD_DUMP(SZ_DMASEV, "\tDMASEV %u\n", ev >> 3);
+
+	return SZ_DMASEV;
+}
+
+static inline u32 _emit_ST(unsigned dry_run, u8 buf[], enum pl330_cond cond)
+{
+	if (dry_run)
+		return SZ_DMAST;
+
+	buf[0] = CMD_DMAST;
+
+	if (cond == SINGLE)
+		buf[0] |= (0 << 1) | (1 << 0);
+	else if (cond == BURST)
+		buf[0] |= (1 << 1) | (1 << 0);
+
+	PL330_DBGCMD_DUMP(SZ_DMAST, "\tDMAST%c\n",
+		cond == SINGLE ? 'S' : (cond == BURST ? 'B' : 'A'));
+
+	return SZ_DMAST;
+}
+
+static inline u32 _emit_STP(unsigned dry_run, u8 buf[],
+		enum pl330_cond cond, u8 peri)
+{
+	if (dry_run)
+		return SZ_DMASTP;
+
+	buf[0] = CMD_DMASTP;
+
+	if (cond == BURST)
+		buf[0] |= (1 << 1);
+
+	peri &= 0x1f;
+	peri <<= 3;
+	buf[1] = peri;
+
+	PL330_DBGCMD_DUMP(SZ_DMASTP, "\tDMASTP%c %u\n",
+		cond == SINGLE ? 'S' : 'B', peri >> 3);
+
+	return SZ_DMASTP;
+}
+
+static inline u32 _emit_STZ(unsigned dry_run, u8 buf[])
+{
+	if (dry_run)
+		return SZ_DMASTZ;
+
+	buf[0] = CMD_DMASTZ;
+
+	PL330_DBGCMD_DUMP(SZ_DMASTZ, "\tDMASTZ\n");
+
+	return SZ_DMASTZ;
+}
+
+static inline u32 _emit_WFE(unsigned dry_run, u8 buf[], u8 ev,
+		unsigned invalidate)
+{
+	if (dry_run)
+		return SZ_DMAWFE;
+
+	buf[0] = CMD_DMAWFE;
+
+	ev &= 0x1f;
+	ev <<= 3;
+	buf[1] = ev;
+
+	if (invalidate)
+		buf[1] |= (1 << 1);
+
+	PL330_DBGCMD_DUMP(SZ_DMAWFE, "\tDMAWFE %u%s\n",
+		ev >> 3, invalidate ? ", I" : "");
+
+	return SZ_DMAWFE;
+}
+
+static inline u32 _emit_WFP(unsigned dry_run, u8 buf[],
+		enum pl330_cond cond, u8 peri)
+{
+	if (dry_run)
+		return SZ_DMAWFP;
+
+	buf[0] = CMD_DMAWFP;
+
+	if (cond == SINGLE)
+		buf[0] |= (0 << 1) | (0 << 0);
+	else if (cond == BURST)
+		buf[0] |= (1 << 1) | (0 << 0);
+	else
+		buf[0] |= (0 << 1) | (1 << 0);
+
+	peri &= 0x1f;
+	peri <<= 3;
+	buf[1] = peri;
+
+	PL330_DBGCMD_DUMP(SZ_DMAWFP, "\tDMAWFP%c %u\n",
+		cond == SINGLE ? 'S' : (cond == BURST ? 'B' : 'P'), peri >> 3);
+
+	return SZ_DMAWFP;
+}
+
+static inline u32 _emit_WMB(unsigned dry_run, u8 buf[])
+{
+	if (dry_run)
+		return SZ_DMAWMB;
+
+	buf[0] = CMD_DMAWMB;
+
+	PL330_DBGCMD_DUMP(SZ_DMAWMB, "\tDMAWMB\n");
+
+	return SZ_DMAWMB;
+}
+
+struct _arg_GO {
+	u8 chan;
+	u32 addr;
+	unsigned ns;
+};
+
+static inline u32 _emit_GO(unsigned dry_run, u8 buf[],
+		const struct _arg_GO *arg)
+{
+	u8 chan = arg->chan;
+	u32 addr = arg->addr;
+	unsigned ns = arg->ns;
+
+	if (dry_run)
+		return SZ_DMAGO;
+
+	buf[0] = CMD_DMAGO;
+	buf[0] |= (ns << 1);
+
+	buf[1] = chan & 0x7;
+
+	*((u32 *)&buf[2]) = addr;
+
+	return SZ_DMAGO;
+}
+
+#define msecs_to_loops(t) (loops_per_jiffy / 1000 * HZ * t)
+
+/* Returns Time-Out */
+static bool _until_dmac_idle(struct pl330_thread *thrd)
+{
+	void __iomem *regs = thrd->dmac->pinfo->base;
+	unsigned long loops = msecs_to_loops(5);
+
+	do {
+		/* Until Manager is Idle */
+		if (!(readl(regs + DBGSTATUS) & DBG_BUSY))
+			break;
+
+		cpu_relax();
+	} while (--loops);
+
+	if (!loops)
+		return true;
+
+	return false;
+}
+
+static inline void _execute_DBGINSN(struct pl330_thread *thrd,
+		u8 insn[], bool as_manager)
+{
+	void __iomem *regs = thrd->dmac->pinfo->base;
+	u32 val;
+
+	val = (insn[0] << 16) | (insn[1] << 24);
+	if (!as_manager) {
+		val |= (1 << 0);
+		val |= (thrd->id << 8); /* Channel Number */
+	}
+	writel(val, regs + DBGINST0);
+
+	val = *((u32 *)&insn[2]);
+	writel(val, regs + DBGINST1);
+
+	/* If timed out due to halted state-machine */
+	if (_until_dmac_idle(thrd)) {
+		dev_err(thrd->dmac->pinfo->dev, "DMAC halted!\n");
+		return;
+	}
+
+	/* Get going */
+	writel(0, regs + DBGCMD);
+}
+
+/*
+ * Mark a _pl330_req as free.
+ * We do it by writing DMAEND as the first instruction
+ * because no valid request is going to have DMAEND as
+ * its first instruction to execute.
+ */
+static void mark_free(struct pl330_thread *thrd, int idx)
+{
+	struct _pl330_req *req = &thrd->req[idx];
+
+	_emit_END(0, req->mc_cpu);
+	req->mc_len = 0;
+
+	thrd->req_running = -1;
+}
+
+static inline u32 _state(struct pl330_thread *thrd)
+{
+	void __iomem *regs = thrd->dmac->pinfo->base;
+	u32 val;
+
+	if (is_manager(thrd))
+		val = readl(regs + DS) & 0xf;
+	else
+		val = readl(regs + CS(thrd->id)) & 0xf;
+
+	switch (val) {
+	case DS_ST_STOP:
+		return PL330_STATE_STOPPED;
+	case DS_ST_EXEC:
+		return PL330_STATE_EXECUTING;
+	case DS_ST_CMISS:
+		return PL330_STATE_CACHEMISS;
+	case DS_ST_UPDTPC:
+		return PL330_STATE_UPDTPC;
+	case DS_ST_WFE:
+		return PL330_STATE_WFE;
+	case DS_ST_FAULT:
+		return PL330_STATE_FAULTING;
+	case DS_ST_ATBRR:
+		if (is_manager(thrd))
+			return PL330_STATE_INVALID;
+		else
+			return PL330_STATE_ATBARRIER;
+	case DS_ST_QBUSY:
+		if (is_manager(thrd))
+			return PL330_STATE_INVALID;
+		else
+			return PL330_STATE_QUEUEBUSY;
+	case DS_ST_WFP:
+		if (is_manager(thrd))
+			return PL330_STATE_INVALID;
+		else
+			return PL330_STATE_WFP;
+	case DS_ST_KILL:
+		if (is_manager(thrd))
+			return PL330_STATE_INVALID;
+		else
+			return PL330_STATE_KILLING;
+	case DS_ST_CMPLT:
+		if (is_manager(thrd))
+			return PL330_STATE_INVALID;
+		else
+			return PL330_STATE_COMPLETING;
+	case DS_ST_FLTCMP:
+		if (is_manager(thrd))
+			return PL330_STATE_INVALID;
+		else
+			return PL330_STATE_FAULT_COMPLETING;
+	default:
+		return PL330_STATE_INVALID;
+	}
+}
+
+static void _stop(struct pl330_thread *thrd)
+{
+	void __iomem *regs = thrd->dmac->pinfo->base;
+	u8 insn[6] = {0, 0, 0, 0, 0, 0};
+
+	if (_state(thrd) == PL330_STATE_FAULT_COMPLETING)
+		UNTIL(thrd, PL330_STATE_FAULTING | PL330_STATE_KILLING);
+
+	/* Return if nothing needs to be done */
+	if (_state(thrd) == PL330_STATE_COMPLETING
+		  || _state(thrd) == PL330_STATE_KILLING
+		  || _state(thrd) == PL330_STATE_STOPPED)
+		return;
+
+	_emit_KILL(0, insn);
+
+	/* Stop generating interrupts for SEV */
+	writel(readl(regs + INTEN) & ~(1 << thrd->ev), regs + INTEN);
+
+	_execute_DBGINSN(thrd, insn, is_manager(thrd));
+}
+
+/* Start doing req 'idx' of thread 'thrd' */
+static bool _trigger(struct pl330_thread *thrd)
+{
+	void __iomem *regs = thrd->dmac->pinfo->base;
+	struct _pl330_req *req;
+	struct pl330_req *r;
+	struct _arg_GO go;
+	unsigned ns;
+	u8 insn[6] = {0, 0, 0, 0, 0, 0};
+	int idx;
+
+	/* Return if already ACTIVE */
+	if (_state(thrd) != PL330_STATE_STOPPED)
+		return true;
+
+	idx = 1 - thrd->lstenq;
+	if (!IS_FREE(&thrd->req[idx]))
+		req = &thrd->req[idx];
+	else {
+		idx = thrd->lstenq;
+		if (!IS_FREE(&thrd->req[idx]))
+			req = &thrd->req[idx];
+		else
+			req = NULL;
+	}
+
+	/* Return if no request */
+	if (!req || !req->r)
+		return true;
+
+	r = req->r;
+
+	if (r->cfg)
+		ns = r->cfg->nonsecure ? 1 : 0;
+	else if (readl(regs + CS(thrd->id)) & CS_CNS)
+		ns = 1;
+	else
+		ns = 0;
+
+	/* See 'Abort Sources' point-4 at Page 2-25 */
+	if (_manager_ns(thrd) && !ns)
+		dev_info(thrd->dmac->pinfo->dev, "%s:%d Recipe for ABORT!\n",
+			__func__, __LINE__);
+
+	go.chan = thrd->id;
+	go.addr = req->mc_bus;
+	go.ns = ns;
+	_emit_GO(0, insn, &go);
+
+	/* Set to generate interrupts for SEV */
+	writel(readl(regs + INTEN) | (1 << thrd->ev), regs + INTEN);
+
+	/* Only manager can execute GO */
+	_execute_DBGINSN(thrd, insn, true);
+
+	thrd->req_running = idx;
+
+	return true;
+}
+
+static bool _start(struct pl330_thread *thrd)
+{
+	switch (_state(thrd)) {
+	case PL330_STATE_FAULT_COMPLETING:
+		UNTIL(thrd, PL330_STATE_FAULTING | PL330_STATE_KILLING);
+
+		if (_state(thrd) == PL330_STATE_KILLING)
+			UNTIL(thrd, PL330_STATE_STOPPED)
+
+	case PL330_STATE_FAULTING:
+		_stop(thrd);
+
+	case PL330_STATE_KILLING:
+	case PL330_STATE_COMPLETING:
+		UNTIL(thrd, PL330_STATE_STOPPED)
+
+	case PL330_STATE_STOPPED:
+		return _trigger(thrd);
+
+	case PL330_STATE_WFP:
+	case PL330_STATE_QUEUEBUSY:
+	case PL330_STATE_ATBARRIER:
+	case PL330_STATE_UPDTPC:
+	case PL330_STATE_CACHEMISS:
+	case PL330_STATE_EXECUTING:
+		return true;
+
+	case PL330_STATE_WFE: /* For RESUME, nothing yet */
+	default:
+		return false;
+	}
+}
+
+static inline int _ldst_memtomem(unsigned dry_run, u8 buf[],
+		const struct _xfer_spec *pxs, int cyc)
+{
+	int off = 0;
+	struct pl330_config *pcfg = pxs->r->cfg->pcfg;
+
+	/* check lock-up free version */
+	if (get_revision(pcfg->periph_id) >= PERIPH_REV_R1P0) {
+		while (cyc--) {
+			off += _emit_LD(dry_run, &buf[off], ALWAYS);
+			off += _emit_ST(dry_run, &buf[off], ALWAYS);
+		}
+	} else {
+		while (cyc--) {
+			off += _emit_LD(dry_run, &buf[off], ALWAYS);
+			off += _emit_RMB(dry_run, &buf[off]);
+			off += _emit_ST(dry_run, &buf[off], ALWAYS);
+			off += _emit_WMB(dry_run, &buf[off]);
+		}
+	}
+
+	return off;
+}
+
+static inline int _ldst_devtomem(unsigned dry_run, u8 buf[],
+		const struct _xfer_spec *pxs, int cyc)
+{
+	int off = 0;
+
+	while (cyc--) {
+		off += _emit_WFP(dry_run, &buf[off], SINGLE, pxs->r->peri);
+		off += _emit_LDP(dry_run, &buf[off], SINGLE, pxs->r->peri);
+		off += _emit_ST(dry_run, &buf[off], ALWAYS);
+		off += _emit_FLUSHP(dry_run, &buf[off], pxs->r->peri);
+	}
+
+	return off;
+}
+
+static inline int _ldst_memtodev(unsigned dry_run, u8 buf[],
+		const struct _xfer_spec *pxs, int cyc)
+{
+	int off = 0;
+
+	while (cyc--) {
+		off += _emit_WFP(dry_run, &buf[off], SINGLE, pxs->r->peri);
+		off += _emit_LD(dry_run, &buf[off], ALWAYS);
+		off += _emit_STP(dry_run, &buf[off], SINGLE, pxs->r->peri);
+		off += _emit_FLUSHP(dry_run, &buf[off], pxs->r->peri);
+	}
+
+	return off;
+}
+
+static int _bursts(unsigned dry_run, u8 buf[],
+		const struct _xfer_spec *pxs, int cyc)
+{
+	int off = 0;
+
+	switch (pxs->r->rqtype) {
+	case MEMTODEV:
+		off += _ldst_memtodev(dry_run, &buf[off], pxs, cyc);
+		break;
+	case DEVTOMEM:
+		off += _ldst_devtomem(dry_run, &buf[off], pxs, cyc);
+		break;
+	case MEMTOMEM:
+		off += _ldst_memtomem(dry_run, &buf[off], pxs, cyc);
+		break;
+	default:
+		off += 0x40000000; /* Scare off the Client */
+		break;
+	}
+
+	return off;
+}
+
+/* Returns bytes consumed and updates bursts */
+static inline int _loop(unsigned dry_run, u8 buf[],
+		unsigned long *bursts, const struct _xfer_spec *pxs)
+{
+	int cyc, cycmax, szlp, szlpend, szbrst, off;
+	unsigned lcnt0, lcnt1, ljmp0, ljmp1;
+	struct _arg_LPEND lpend;
+
+	/* Max iterations possible in DMALP is 256 */
+	if (*bursts >= 256*256) {
+		lcnt1 = 256;
+		lcnt0 = 256;
+		cyc = *bursts / lcnt1 / lcnt0;
+	} else if (*bursts > 256) {
+		lcnt1 = 256;
+		lcnt0 = *bursts / lcnt1;
+		cyc = 1;
+	} else {
+		lcnt1 = *bursts;
+		lcnt0 = 0;
+		cyc = 1;
+	}
+
+	szlp = _emit_LP(1, buf, 0, 0);
+	szbrst = _bursts(1, buf, pxs, 1);
+
+	lpend.cond = ALWAYS;
+	lpend.forever = false;
+	lpend.loop = 0;
+	lpend.bjump = 0;
+	szlpend = _emit_LPEND(1, buf, &lpend);
+
+	if (lcnt0) {
+		szlp *= 2;
+		szlpend *= 2;
+	}
+
+	/*
+	 * Max bursts that we can unroll due to limit on the
+	 * size of backward jump that can be encoded in DMALPEND
+	 * which is 8-bits and hence 255
+	 */
+	cycmax = (255 - (szlp + szlpend)) / szbrst;
+
+	cyc = (cycmax < cyc) ? cycmax : cyc;
+
+	off = 0;
+
+	if (lcnt0) {
+		off += _emit_LP(dry_run, &buf[off], 0, lcnt0);
+		ljmp0 = off;
+	}
+
+	off += _emit_LP(dry_run, &buf[off], 1, lcnt1);
+	ljmp1 = off;
+
+	off += _bursts(dry_run, &buf[off], pxs, cyc);
+
+	lpend.cond = ALWAYS;
+	lpend.forever = false;
+	lpend.loop = 1;
+	lpend.bjump = off - ljmp1;
+	off += _emit_LPEND(dry_run, &buf[off], &lpend);
+
+	if (lcnt0) {
+		lpend.cond = ALWAYS;
+		lpend.forever = false;
+		lpend.loop = 0;
+		lpend.bjump = off - ljmp0;
+		off += _emit_LPEND(dry_run, &buf[off], &lpend);
+	}
+
+	*bursts = lcnt1 * cyc;
+	if (lcnt0)
+		*bursts *= lcnt0;
+
+	return off;
+}
+
+static inline int _setup_loops(unsigned dry_run, u8 buf[],
+		const struct _xfer_spec *pxs)
+{
+	struct pl330_xfer *x = pxs->x;
+	u32 ccr = pxs->ccr;
+	unsigned long c, bursts = BYTE_TO_BURST(x->bytes, ccr);
+	int off = 0;
+
+	while (bursts) {
+		c = bursts;
+		off += _loop(dry_run, &buf[off], &c, pxs);
+		bursts -= c;
+	}
+
+	return off;
+}
+
+static inline int _setup_xfer(unsigned dry_run, u8 buf[],
+		const struct _xfer_spec *pxs)
+{
+	struct pl330_xfer *x = pxs->x;
+	int off = 0;
+
+	/* DMAMOV SAR, x->src_addr */
+	off += _emit_MOV(dry_run, &buf[off], SAR, x->src_addr);
+	/* DMAMOV DAR, x->dst_addr */
+	off += _emit_MOV(dry_run, &buf[off], DAR, x->dst_addr);
+
+	/* Setup Loop(s) */
+	off += _setup_loops(dry_run, &buf[off], pxs);
+
+	return off;
+}
+
+/*
+ * A req is a sequence of one or more xfer units.
+ * Returns the number of bytes taken to setup the MC for the req.
+ */
+static int _setup_req(unsigned dry_run, struct pl330_thread *thrd,
+		unsigned index, struct _xfer_spec *pxs)
+{
+	struct _pl330_req *req = &thrd->req[index];
+	struct pl330_xfer *x;
+	u8 *buf = req->mc_cpu;
+	int off = 0;
+
+	PL330_DBGMC_START(req->mc_bus);
+
+	/* DMAMOV CCR, ccr */
+	off += _emit_MOV(dry_run, &buf[off], CCR, pxs->ccr);
+
+	x = pxs->r->x;
+	do {
+		/* Error if xfer length is not aligned at burst size */
+		if (x->bytes % (BRST_SIZE(pxs->ccr) * BRST_LEN(pxs->ccr)))
+			return -EINVAL;
+
+		pxs->x = x;
+		off += _setup_xfer(dry_run, &buf[off], pxs);
+
+		x = x->next;
+	} while (x);
+
+	/* DMASEV peripheral/event */
+	off += _emit_SEV(dry_run, &buf[off], thrd->ev);
+	/* DMAEND */
+	off += _emit_END(dry_run, &buf[off]);
+
+	return off;
+}
+
+static inline u32 _prepare_ccr(const struct pl330_reqcfg *rqc)
+{
+	u32 ccr = 0;
+
+	if (rqc->src_inc)
+		ccr |= CC_SRCINC;
+
+	if (rqc->dst_inc)
+		ccr |= CC_DSTINC;
+
+	/* We set same protection levels for Src and DST for now */
+	if (rqc->privileged)
+		ccr |= CC_SRCPRI | CC_DSTPRI;
+	if (rqc->nonsecure)
+		ccr |= CC_SRCNS | CC_DSTNS;
+	if (rqc->insnaccess)
+		ccr |= CC_SRCIA | CC_DSTIA;
+
+	ccr |= (((rqc->brst_len - 1) & 0xf) << CC_SRCBRSTLEN_SHFT);
+	ccr |= (((rqc->brst_len - 1) & 0xf) << CC_DSTBRSTLEN_SHFT);
+
+	ccr |= (rqc->brst_size << CC_SRCBRSTSIZE_SHFT);
+	ccr |= (rqc->brst_size << CC_DSTBRSTSIZE_SHFT);
+
+	ccr |= (rqc->scctl << CC_SRCCCTRL_SHFT);
+	ccr |= (rqc->dcctl << CC_DSTCCTRL_SHFT);
+
+	ccr |= (rqc->swap << CC_SWAP_SHFT);
+
+	return ccr;
+}
+
+static inline bool _is_valid(u32 ccr)
+{
+	enum pl330_dstcachectrl dcctl;
+	enum pl330_srccachectrl scctl;
+
+	dcctl = (ccr >> CC_DSTCCTRL_SHFT) & CC_DRCCCTRL_MASK;
+	scctl = (ccr >> CC_SRCCCTRL_SHFT) & CC_SRCCCTRL_MASK;
+
+	if (dcctl == DINVALID1 || dcctl == DINVALID2
+			|| scctl == SINVALID1 || scctl == SINVALID2)
+		return false;
+	else
+		return true;
+}
+
+/*
+ * Submit a list of xfers after which the client wants notification.
+ * Client is not notified after each xfer unit, just once after all
+ * xfer units are done or some error occurs.
+ */
+static int pl330_submit_req(void *ch_id, struct pl330_req *r)
+{
+	struct pl330_thread *thrd = ch_id;
+	struct pl330_dmac *pl330;
+	struct pl330_info *pi;
+	struct _xfer_spec xs;
+	unsigned long flags;
+	void __iomem *regs;
+	unsigned idx;
+	u32 ccr;
+	int ret = 0;
+
+	/* No Req or Unacquired Channel or DMAC */
+	if (!r || !thrd || thrd->free)
+		return -EINVAL;
+
+	pl330 = thrd->dmac;
+	pi = pl330->pinfo;
+	regs = pi->base;
+
+	if (pl330->state == DYING
+		|| pl330->dmac_tbd.reset_chan & (1 << thrd->id)) {
+		dev_info(thrd->dmac->pinfo->dev, "%s:%d\n",
+			__func__, __LINE__);
+		return -EAGAIN;
+	}
+
+	/* If request for non-existing peripheral */
+	if (r->rqtype != MEMTOMEM && r->peri >= pi->pcfg.num_peri) {
+		dev_info(thrd->dmac->pinfo->dev,
+				"%s:%d Invalid peripheral(%u)!\n",
+				__func__, __LINE__, r->peri);
+		return -EINVAL;
+	}
+
+	spin_lock_irqsave(&pl330->lock, flags);
+
+	if (_queue_full(thrd)) {
+		ret = -EAGAIN;
+		goto xfer_exit;
+	}
+
+	/* Prefer Secure Channel */
+	if (!_manager_ns(thrd))
+		r->cfg->nonsecure = 0;
+	else
+		r->cfg->nonsecure = 1;
+
+	/* Use last settings, if not provided */
+	if (r->cfg)
+		ccr = _prepare_ccr(r->cfg);
+	else
+		ccr = readl(regs + CC(thrd->id));
+
+	/* If this req doesn't have valid xfer settings */
+	if (!_is_valid(ccr)) {
+		ret = -EINVAL;
+		dev_info(thrd->dmac->pinfo->dev, "%s:%d Invalid CCR(%x)!\n",
+			__func__, __LINE__, ccr);
+		goto xfer_exit;
+	}
+
+	idx = IS_FREE(&thrd->req[0]) ? 0 : 1;
+
+	xs.ccr = ccr;
+	xs.r = r;
+
+	/* First dry run to check if req is acceptable */
+	ret = _setup_req(1, thrd, idx, &xs);
+	if (ret < 0)
+		goto xfer_exit;
+
+	if (ret > pi->mcbufsz / 2) {
+		dev_info(thrd->dmac->pinfo->dev,
+			"%s:%d Trying increasing mcbufsz\n",
+				__func__, __LINE__);
+		ret = -ENOMEM;
+		goto xfer_exit;
+	}
+
+	/* Hook the request */
+	thrd->lstenq = idx;
+	thrd->req[idx].mc_len = _setup_req(0, thrd, idx, &xs);
+	thrd->req[idx].r = r;
+
+	ret = 0;
+
+xfer_exit:
+	spin_unlock_irqrestore(&pl330->lock, flags);
+
+	return ret;
+}
+
+static void pl330_dotask(unsigned long data)
+{
+	struct pl330_dmac *pl330 = (struct pl330_dmac *) data;
+	struct pl330_info *pi = pl330->pinfo;
+	unsigned long flags;
+	int i;
+
+	spin_lock_irqsave(&pl330->lock, flags);
+
+	/* The DMAC itself gone nuts */
+	if (pl330->dmac_tbd.reset_dmac) {
+		pl330->state = DYING;
+		/* Reset the manager too */
+		pl330->dmac_tbd.reset_mngr = true;
+		/* Clear the reset flag */
+		pl330->dmac_tbd.reset_dmac = false;
+	}
+
+	if (pl330->dmac_tbd.reset_mngr) {
+		_stop(pl330->manager);
+		/* Reset all channels */
+		pl330->dmac_tbd.reset_chan = (1 << pi->pcfg.num_chan) - 1;
+		/* Clear the reset flag */
+		pl330->dmac_tbd.reset_mngr = false;
+	}
+
+	for (i = 0; i < pi->pcfg.num_chan; i++) {
+
+		if (pl330->dmac_tbd.reset_chan & (1 << i)) {
+			struct pl330_thread *thrd = &pl330->channels[i];
+			void __iomem *regs = pi->base;
+			enum pl330_op_err err;
+
+			_stop(thrd);
+
+			if (readl(regs + FSC) & (1 << thrd->id))
+				err = PL330_ERR_FAIL;
+			else
+				err = PL330_ERR_ABORT;
+
+			spin_unlock_irqrestore(&pl330->lock, flags);
+
+			_callback(thrd->req[1 - thrd->lstenq].r, err);
+			_callback(thrd->req[thrd->lstenq].r, err);
+
+			spin_lock_irqsave(&pl330->lock, flags);
+
+			thrd->req[0].r = NULL;
+			thrd->req[1].r = NULL;
+			mark_free(thrd, 0);
+			mark_free(thrd, 1);
+
+			/* Clear the reset flag */
+			pl330->dmac_tbd.reset_chan &= ~(1 << i);
+		}
+	}
+
+	spin_unlock_irqrestore(&pl330->lock, flags);
+
+	return;
+}
+
+/* Returns 1 if state was updated, 0 otherwise */
+static int pl330_update(const struct pl330_info *pi)
+{
+	struct _pl330_req *rqdone;
+	struct pl330_dmac *pl330;
+	unsigned long flags;
+	void __iomem *regs;
+	u32 val;
+	int id, ev, ret = 0;
+
+	if (!pi || !pi->pl330_data)
+		return 0;
+
+	regs = pi->base;
+	pl330 = pi->pl330_data;
+
+	spin_lock_irqsave(&pl330->lock, flags);
+
+	val = readl(regs + FSM) & 0x1;
+	if (val)
+		pl330->dmac_tbd.reset_mngr = true;
+	else
+		pl330->dmac_tbd.reset_mngr = false;
+
+	val = readl(regs + FSC) & ((1 << pi->pcfg.num_chan) - 1);
+	pl330->dmac_tbd.reset_chan |= val;
+	if (val) {
+		int i = 0;
+		while (i < pi->pcfg.num_chan) {
+			if (val & (1 << i)) {
+				dev_info(pi->dev,
+					"Reset Channel-%d\t CS-%x FTC-%x\n",
+						i, readl(regs + CS(i)),
+						readl(regs + FTC(i)));
+				_stop(&pl330->channels[i]);
+			}
+			i++;
+		}
+	}
+
+	/* Check which event happened i.e, thread notified */
+	val = readl(regs + ES);
+	if (pi->pcfg.num_events < 32
+			&& val & ~((1 << pi->pcfg.num_events) - 1)) {
+		pl330->dmac_tbd.reset_dmac = true;
+		dev_err(pi->dev, "%s:%d Unexpected!\n", __func__, __LINE__);
+		ret = 1;
+		goto updt_exit;
+	}
+
+	for (ev = 0; ev < pi->pcfg.num_events; ev++) {
+		if (val & (1 << ev)) { /* Event occurred */
+			struct pl330_thread *thrd;
+			u32 inten = readl(regs + INTEN);
+			int active;
+
+			/* Clear the event */
+			if (inten & (1 << ev))
+				writel(1 << ev, regs + INTCLR);
+
+			ret = 1;
+
+			id = pl330->events[ev];
+
+			thrd = &pl330->channels[id];
+
+			active = thrd->req_running;
+			if (active == -1) /* Aborted */
+				continue;
+
+			rqdone = &thrd->req[active];
+			mark_free(thrd, active);
+
+			/* Get going again ASAP */
+			_start(thrd);
+
+			/* For now, just make a list of callbacks to be done */
+			list_add_tail(&rqdone->rqd, &pl330->req_done);
+		}
+	}
+
+	/* Now that we are in no hurry, do the callbacks */
+	while (!list_empty(&pl330->req_done)) {
+		struct pl330_req *r;
+
+		rqdone = container_of(pl330->req_done.next,
+					struct _pl330_req, rqd);
+
+		list_del_init(&rqdone->rqd);
+
+		/* Detach the req */
+		r = rqdone->r;
+		rqdone->r = NULL;
+
+		spin_unlock_irqrestore(&pl330->lock, flags);
+		_callback(r, PL330_ERR_NONE);
+		spin_lock_irqsave(&pl330->lock, flags);
+	}
+
+updt_exit:
+	spin_unlock_irqrestore(&pl330->lock, flags);
+
+	if (pl330->dmac_tbd.reset_dmac
+			|| pl330->dmac_tbd.reset_mngr
+			|| pl330->dmac_tbd.reset_chan) {
+		ret = 1;
+		tasklet_schedule(&pl330->tasks);
+	}
+
+	return ret;
+}
+
+static int pl330_chan_ctrl(void *ch_id, enum pl330_chan_op op)
+{
+	struct pl330_thread *thrd = ch_id;
+	struct pl330_dmac *pl330;
+	unsigned long flags;
+	int ret = 0, active;
+
+	if (!thrd || thrd->free || thrd->dmac->state == DYING)
+		return -EINVAL;
+
+	pl330 = thrd->dmac;
+	active = thrd->req_running;
+
+	spin_lock_irqsave(&pl330->lock, flags);
+
+	switch (op) {
+	case PL330_OP_FLUSH:
+		/* Make sure the channel is stopped */
+		_stop(thrd);
+
+		thrd->req[0].r = NULL;
+		thrd->req[1].r = NULL;
+		mark_free(thrd, 0);
+		mark_free(thrd, 1);
+		break;
+
+	case PL330_OP_ABORT:
+		/* Make sure the channel is stopped */
+		_stop(thrd);
+
+		/* ABORT is only for the active req */
+		if (active == -1)
+			break;
+
+		thrd->req[active].r = NULL;
+		mark_free(thrd, active);
+
+		/* Start the next */
+	case PL330_OP_START:
+		if ((active == -1) && !_start(thrd))
+			ret = -EIO;
+		break;
+
+	default:
+		ret = -EINVAL;
+	}
+
+	spin_unlock_irqrestore(&pl330->lock, flags);
+	return ret;
+}
+
+/* Reserve an event */
+static inline int _alloc_event(struct pl330_thread *thrd)
+{
+	struct pl330_dmac *pl330 = thrd->dmac;
+	struct pl330_info *pi = pl330->pinfo;
+	int ev;
+
+	for (ev = 0; ev < pi->pcfg.num_events; ev++)
+		if (pl330->events[ev] == -1) {
+			pl330->events[ev] = thrd->id;
+			return ev;
+		}
+
+	return -1;
+}
+
+static bool _chan_ns(const struct pl330_info *pi, int i)
+{
+	return pi->pcfg.irq_ns & (1 << i);
+}
+
+/* Upon success, returns IdentityToken for the
+ * allocated channel, NULL otherwise.
+ */
+static void *pl330_request_channel(const struct pl330_info *pi)
+{
+	struct pl330_thread *thrd = NULL;
+	struct pl330_dmac *pl330;
+	unsigned long flags;
+	int chans, i;
+
+	if (!pi || !pi->pl330_data)
+		return NULL;
+
+	pl330 = pi->pl330_data;
+
+	if (pl330->state == DYING)
+		return NULL;
+
+	chans = pi->pcfg.num_chan;
+
+	spin_lock_irqsave(&pl330->lock, flags);
+
+	for (i = 0; i < chans; i++) {
+		thrd = &pl330->channels[i];
+		if ((thrd->free) && (!_manager_ns(thrd) ||
+					_chan_ns(pi, i))) {
+			thrd->ev = _alloc_event(thrd);
+			if (thrd->ev >= 0) {
+				thrd->free = false;
+				thrd->lstenq = 1;
+				thrd->req[0].r = NULL;
+				mark_free(thrd, 0);
+				thrd->req[1].r = NULL;
+				mark_free(thrd, 1);
+				break;
+			}
+		}
+		thrd = NULL;
+	}
+
+	spin_unlock_irqrestore(&pl330->lock, flags);
+
+	return thrd;
+}
+
+/* Release an event */
+static inline void _free_event(struct pl330_thread *thrd, int ev)
+{
+	struct pl330_dmac *pl330 = thrd->dmac;
+	struct pl330_info *pi = pl330->pinfo;
+
+	/* If the event is valid and was held by the thread */
+	if (ev >= 0 && ev < pi->pcfg.num_events
+			&& pl330->events[ev] == thrd->id)
+		pl330->events[ev] = -1;
+}
+
+static void pl330_release_channel(void *ch_id)
+{
+	struct pl330_thread *thrd = ch_id;
+	struct pl330_dmac *pl330;
+	unsigned long flags;
+
+	if (!thrd || thrd->free)
+		return;
+
+	_stop(thrd);
+
+	_callback(thrd->req[1 - thrd->lstenq].r, PL330_ERR_ABORT);
+	_callback(thrd->req[thrd->lstenq].r, PL330_ERR_ABORT);
+
+	pl330 = thrd->dmac;
+
+	spin_lock_irqsave(&pl330->lock, flags);
+	_free_event(thrd, thrd->ev);
+	thrd->free = true;
+	spin_unlock_irqrestore(&pl330->lock, flags);
+}
+
+/* Initialize the structure for PL330 configuration, that can be used
+ * by the client driver the make best use of the DMAC
+ */
+static void read_dmac_config(struct pl330_info *pi)
+{
+	void __iomem *regs = pi->base;
+	u32 val;
+
+	val = readl(regs + CRD) >> CRD_DATA_WIDTH_SHIFT;
+	val &= CRD_DATA_WIDTH_MASK;
+	pi->pcfg.data_bus_width = 8 * (1 << val);
+
+	val = readl(regs + CRD) >> CRD_DATA_BUFF_SHIFT;
+	val &= CRD_DATA_BUFF_MASK;
+	pi->pcfg.data_buf_dep = val + 1;
+
+	val = readl(regs + CR0) >> CR0_NUM_CHANS_SHIFT;
+	val &= CR0_NUM_CHANS_MASK;
+	val += 1;
+	pi->pcfg.num_chan = val;
+
+	val = readl(regs + CR0);
+	if (val & CR0_PERIPH_REQ_SET) {
+		val = (val >> CR0_NUM_PERIPH_SHIFT) & CR0_NUM_PERIPH_MASK;
+		val += 1;
+		pi->pcfg.num_peri = val;
+		pi->pcfg.peri_ns = readl(regs + CR4);
+	} else {
+		pi->pcfg.num_peri = 0;
+	}
+
+	val = readl(regs + CR0);
+	if (val & CR0_BOOT_MAN_NS)
+		pi->pcfg.mode |= DMAC_MODE_NS;
+	else
+		pi->pcfg.mode &= ~DMAC_MODE_NS;
+
+	val = readl(regs + CR0) >> CR0_NUM_EVENTS_SHIFT;
+	val &= CR0_NUM_EVENTS_MASK;
+	val += 1;
+	pi->pcfg.num_events = val;
+
+	pi->pcfg.irq_ns = readl(regs + CR3);
+
+	pi->pcfg.periph_id = get_id(pi, PERIPH_ID);
+	pi->pcfg.pcell_id = get_id(pi, PCELL_ID);
+}
+
+static inline void _reset_thread(struct pl330_thread *thrd)
+{
+	struct pl330_dmac *pl330 = thrd->dmac;
+	struct pl330_info *pi = pl330->pinfo;
+
+	thrd->req[0].mc_cpu = pl330->mcode_cpu
+				+ (thrd->id * pi->mcbufsz);
+	thrd->req[0].mc_bus = pl330->mcode_bus
+				+ (thrd->id * pi->mcbufsz);
+	thrd->req[0].r = NULL;
+	mark_free(thrd, 0);
+
+	thrd->req[1].mc_cpu = thrd->req[0].mc_cpu
+				+ pi->mcbufsz / 2;
+	thrd->req[1].mc_bus = thrd->req[0].mc_bus
+				+ pi->mcbufsz / 2;
+	thrd->req[1].r = NULL;
+	mark_free(thrd, 1);
+}
+
+static int dmac_alloc_threads(struct pl330_dmac *pl330)
+{
+	struct pl330_info *pi = pl330->pinfo;
+	int chans = pi->pcfg.num_chan;
+	struct pl330_thread *thrd;
+	int i;
+
+	/* Allocate 1 Manager and 'chans' Channel threads */
+	pl330->channels = kzalloc((1 + chans) * sizeof(*thrd),
+					GFP_KERNEL);
+	if (!pl330->channels)
+		return -ENOMEM;
+
+	/* Init Channel threads */
+	for (i = 0; i < chans; i++) {
+		thrd = &pl330->channels[i];
+		thrd->id = i;
+		thrd->dmac = pl330;
+		_reset_thread(thrd);
+		thrd->free = true;
+	}
+
+	/* MANAGER is indexed at the end */
+	thrd = &pl330->channels[chans];
+	thrd->id = chans;
+	thrd->dmac = pl330;
+	thrd->free = false;
+	pl330->manager = thrd;
+
+	return 0;
+}
+
+static int dmac_alloc_resources(struct pl330_dmac *pl330)
+{
+	struct pl330_info *pi = pl330->pinfo;
+	int chans = pi->pcfg.num_chan;
+	int ret;
+
+	/*
+	 * Alloc MicroCode buffer for 'chans' Channel threads.
+	 * A channel's buffer offset is (Channel_Id * MCODE_BUFF_PERCHAN)
+	 */
+	pl330->mcode_cpu = dma_alloc_coherent(pi->dev,
+				chans * pi->mcbufsz,
+				&pl330->mcode_bus, GFP_KERNEL);
+	if (!pl330->mcode_cpu) {
+		dev_err(pi->dev, "%s:%d Can't allocate memory!\n",
+			__func__, __LINE__);
+		return -ENOMEM;
+	}
+
+	ret = dmac_alloc_threads(pl330);
+	if (ret) {
+		dev_err(pi->dev, "%s:%d Can't to create channels for DMAC!\n",
+			__func__, __LINE__);
+		dma_free_coherent(pi->dev,
+				chans * pi->mcbufsz,
+				pl330->mcode_cpu, pl330->mcode_bus);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int pl330_add(struct pl330_info *pi)
+{
+	struct pl330_dmac *pl330;
+	void __iomem *regs;
+	int i, ret;
+
+	if (!pi || !pi->dev)
+		return -EINVAL;
+
+	/* If already added */
+	if (pi->pl330_data)
+		return -EINVAL;
+
+	/*
+	 * If the SoC can perform reset on the DMAC, then do it
+	 * before reading its configuration.
+	 */
+	if (pi->dmac_reset)
+		pi->dmac_reset(pi);
+
+	regs = pi->base;
+
+	/* Check if we can handle this DMAC */
+	if ((get_id(pi, PERIPH_ID) & 0xfffff) != PERIPH_ID_VAL
+	   || get_id(pi, PCELL_ID) != PCELL_ID_VAL) {
+		dev_err(pi->dev, "PERIPH_ID 0x%x, PCELL_ID 0x%x !\n",
+			get_id(pi, PERIPH_ID), get_id(pi, PCELL_ID));
+		return -EINVAL;
+	}
+
+	/* Read the configuration of the DMAC */
+	read_dmac_config(pi);
+
+	if (pi->pcfg.num_events == 0) {
+		dev_err(pi->dev, "%s:%d Can't work without events!\n",
+			__func__, __LINE__);
+		return -EINVAL;
+	}
+
+	pl330 = kzalloc(sizeof(*pl330), GFP_KERNEL);
+	if (!pl330) {
+		dev_err(pi->dev, "%s:%d Can't allocate memory!\n",
+			__func__, __LINE__);
+		return -ENOMEM;
+	}
+
+	/* Assign the info structure and private data */
+	pl330->pinfo = pi;
+	pi->pl330_data = pl330;
+
+	spin_lock_init(&pl330->lock);
+
+	INIT_LIST_HEAD(&pl330->req_done);
+
+	/* Use default MC buffer size if not provided */
+	if (!pi->mcbufsz)
+		pi->mcbufsz = MCODE_BUFF_PER_REQ * 2;
+
+	/* Mark all events as free */
+	for (i = 0; i < pi->pcfg.num_events; i++)
+		pl330->events[i] = -1;
+
+	/* Allocate resources needed by the DMAC */
+	ret = dmac_alloc_resources(pl330);
+	if (ret) {
+		dev_err(pi->dev, "Unable to create channels for DMAC\n");
+		kfree(pl330);
+		return ret;
+	}
+
+	tasklet_init(&pl330->tasks, pl330_dotask, (unsigned long) pl330);
+
+	pl330->state = INIT;
+
+	return 0;
+}
+
+static int dmac_free_threads(struct pl330_dmac *pl330)
+{
+	struct pl330_info *pi = pl330->pinfo;
+	int chans = pi->pcfg.num_chan;
+	struct pl330_thread *thrd;
+	int i;
+
+	/* Release Channel threads */
+	for (i = 0; i < chans; i++) {
+		thrd = &pl330->channels[i];
+		pl330_release_channel((void *)thrd);
+	}
+
+	/* Free memory */
+	kfree(pl330->channels);
+
+	return 0;
+}
+
+static void dmac_free_resources(struct pl330_dmac *pl330)
+{
+	struct pl330_info *pi = pl330->pinfo;
+	int chans = pi->pcfg.num_chan;
+
+	dmac_free_threads(pl330);
+
+	dma_free_coherent(pi->dev, chans * pi->mcbufsz,
+				pl330->mcode_cpu, pl330->mcode_bus);
+}
+
+static void pl330_del(struct pl330_info *pi)
+{
+	struct pl330_dmac *pl330;
+
+	if (!pi || !pi->pl330_data)
+		return;
+
+	pl330 = pi->pl330_data;
+
+	pl330->state = UNINIT;
+
+	tasklet_kill(&pl330->tasks);
+
+	/* Free DMAC resources */
+	dmac_free_resources(pl330);
+
+	kfree(pl330);
+	pi->pl330_data = NULL;
+}
+
 /* forward declaration */
 static struct amba_driver pl330_driver;
 
@@ -234,7 +2320,7 @@
 	/* Pick up ripe tomatoes */
 	list_for_each_entry_safe(desc, _dt, &pch->work_list, node)
 		if (desc->status == DONE) {
-			pch->completed = desc->txd.cookie;
+			dma_cookie_complete(&desc->txd);
 			list_move_tail(&desc->node, &list);
 		}
 
@@ -305,7 +2391,7 @@
 
 	spin_lock_irqsave(&pch->lock, flags);
 
-	pch->completed = chan->cookie = 1;
+	dma_cookie_init(chan);
 	pch->cyclic = false;
 
 	pch->pl330_chid = pl330_request_channel(&pdmac->pif);
@@ -340,7 +2426,6 @@
 		/* Mark all desc done */
 		list_for_each_entry_safe(desc, _dt, &pch->work_list , node) {
 			desc->status = DONE;
-			pch->completed = desc->txd.cookie;
 			list_move_tail(&desc->node, &list);
 		}
 
@@ -396,18 +2481,7 @@
 pl330_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 		 struct dma_tx_state *txstate)
 {
-	struct dma_pl330_chan *pch = to_pchan(chan);
-	dma_cookie_t last_done, last_used;
-	int ret;
-
-	last_done = pch->completed;
-	last_used = chan->cookie;
-
-	ret = dma_async_is_complete(cookie, last_done, last_used);
-
-	dma_set_tx_state(txstate, last_done, last_used, 0);
-
-	return ret;
+	return dma_cookie_status(chan, cookie, txstate);
 }
 
 static void pl330_issue_pending(struct dma_chan *chan)
@@ -430,26 +2504,16 @@
 	spin_lock_irqsave(&pch->lock, flags);
 
 	/* Assign cookies to all nodes */
-	cookie = tx->chan->cookie;
-
 	while (!list_empty(&last->node)) {
 		desc = list_entry(last->node.next, struct dma_pl330_desc, node);
 
-		if (++cookie < 0)
-			cookie = 1;
-		desc->txd.cookie = cookie;
+		dma_cookie_assign(&desc->txd);
 
 		list_move_tail(&desc->node, &pch->work_list);
 	}
 
-	if (++cookie < 0)
-		cookie = 1;
-	last->txd.cookie = cookie;
-
+	cookie = dma_cookie_assign(&last->txd);
 	list_add_tail(&last->node, &pch->work_list);
-
-	tx->chan->cookie = cookie;
-
 	spin_unlock_irqrestore(&pch->lock, flags);
 
 	return cookie;
@@ -553,6 +2617,7 @@
 	async_tx_ack(&desc->txd);
 
 	desc->req.peri = peri_id ? pch->chan.chan_id : 0;
+	desc->rqcfg.pcfg = &pch->dmac->pif.pcfg;
 
 	dma_async_tx_descriptor_init(&desc->txd, &pch->chan);
 
@@ -621,7 +2686,8 @@
 
 static struct dma_async_tx_descriptor *pl330_prep_dma_cyclic(
 		struct dma_chan *chan, dma_addr_t dma_addr, size_t len,
-		size_t period_len, enum dma_transfer_direction direction)
+		size_t period_len, enum dma_transfer_direction direction,
+		void *context)
 {
 	struct dma_pl330_desc *desc;
 	struct dma_pl330_chan *pch = to_pchan(chan);
@@ -711,7 +2777,7 @@
 static struct dma_async_tx_descriptor *
 pl330_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 		unsigned int sg_len, enum dma_transfer_direction direction,
-		unsigned long flg)
+		unsigned long flg, void *context)
 {
 	struct dma_pl330_desc *first, *desc = NULL;
 	struct dma_pl330_chan *pch = to_pchan(chan);
@@ -829,7 +2895,7 @@
 	if (IS_ERR(pdmac->clk)) {
 		dev_err(&adev->dev, "Cannot get operation clock.\n");
 		ret = -EINVAL;
-		goto probe_err1;
+		goto probe_err2;
 	}
 
 	amba_set_drvdata(adev, pdmac);
@@ -843,11 +2909,11 @@
 	ret = request_irq(irq, pl330_irq_handler, 0,
 			dev_name(&adev->dev), pi);
 	if (ret)
-		goto probe_err2;
+		goto probe_err3;
 
 	ret = pl330_add(pi);
 	if (ret)
-		goto probe_err3;
+		goto probe_err4;
 
 	INIT_LIST_HEAD(&pdmac->desc_pool);
 	spin_lock_init(&pdmac->pool_lock);
@@ -904,7 +2970,7 @@
 	ret = dma_async_device_register(pd);
 	if (ret) {
 		dev_err(&adev->dev, "unable to register DMAC\n");
-		goto probe_err4;
+		goto probe_err5;
 	}
 
 	dev_info(&adev->dev,
@@ -917,10 +2983,15 @@
 
 	return 0;
 
-probe_err4:
+probe_err5:
 	pl330_del(pi);
-probe_err3:
+probe_err4:
 	free_irq(irq, pi);
+probe_err3:
+#ifndef CONFIG_PM_RUNTIME
+	clk_disable(pdmac->clk);
+#endif
+	clk_put(pdmac->clk);
 probe_err2:
 	iounmap(pi->base);
 probe_err1:
diff --git a/drivers/dma/ppc4xx/adma.c b/drivers/dma/ppc4xx/adma.c
index fc457a7..ced9882 100644
--- a/drivers/dma/ppc4xx/adma.c
+++ b/drivers/dma/ppc4xx/adma.c
@@ -46,6 +46,7 @@
 #include <asm/dcr.h>
 #include <asm/dcr-regs.h>
 #include "adma.h"
+#include "../dmaengine.h"
 
 enum ppc_adma_init_code {
 	PPC_ADMA_INIT_OK = 0,
@@ -1930,7 +1931,7 @@
 				if (end_of_chain && slot_cnt) {
 					/* Should wait for ZeroSum completion */
 					if (cookie > 0)
-						chan->completed_cookie = cookie;
+						chan->common.completed_cookie = cookie;
 					return;
 				}
 
@@ -1960,7 +1961,7 @@
 	BUG_ON(!seen_current);
 
 	if (cookie > 0) {
-		chan->completed_cookie = cookie;
+		chan->common.completed_cookie = cookie;
 		pr_debug("\tcompleted cookie %d\n", cookie);
 	}
 
@@ -2150,22 +2151,6 @@
 }
 
 /**
- * ppc440spe_desc_assign_cookie - assign a cookie
- */
-static dma_cookie_t ppc440spe_desc_assign_cookie(
-		struct ppc440spe_adma_chan *chan,
-		struct ppc440spe_adma_desc_slot *desc)
-{
-	dma_cookie_t cookie = chan->common.cookie;
-
-	cookie++;
-	if (cookie < 0)
-		cookie = 1;
-	chan->common.cookie = desc->async_tx.cookie = cookie;
-	return cookie;
-}
-
-/**
  * ppc440spe_rxor_set_region_data -
  */
 static void ppc440spe_rxor_set_region(struct ppc440spe_adma_desc_slot *desc,
@@ -2235,8 +2220,7 @@
 	slots_per_op = group_start->slots_per_op;
 
 	spin_lock_bh(&chan->lock);
-
-	cookie = ppc440spe_desc_assign_cookie(chan, sw_desc);
+	cookie = dma_cookie_assign(tx);
 
 	if (unlikely(list_empty(&chan->chain))) {
 		/* first peer */
@@ -3944,28 +3928,16 @@
 			dma_cookie_t cookie, struct dma_tx_state *txstate)
 {
 	struct ppc440spe_adma_chan *ppc440spe_chan;
-	dma_cookie_t last_used;
-	dma_cookie_t last_complete;
 	enum dma_status ret;
 
 	ppc440spe_chan = to_ppc440spe_adma_chan(chan);
-	last_used = chan->cookie;
-	last_complete = ppc440spe_chan->completed_cookie;
-
-	dma_set_tx_state(txstate, last_complete, last_used, 0);
-
-	ret = dma_async_is_complete(cookie, last_complete, last_used);
+	ret = dma_cookie_status(chan, cookie, txstate);
 	if (ret == DMA_SUCCESS)
 		return ret;
 
 	ppc440spe_adma_slot_cleanup(ppc440spe_chan);
 
-	last_used = chan->cookie;
-	last_complete = ppc440spe_chan->completed_cookie;
-
-	dma_set_tx_state(txstate, last_complete, last_used, 0);
-
-	return dma_async_is_complete(cookie, last_complete, last_used);
+	return dma_cookie_status(chan, cookie, txstate);
 }
 
 /**
@@ -4050,16 +4022,12 @@
 		async_tx_ack(&sw_desc->async_tx);
 		ppc440spe_desc_init_null_xor(group_start);
 
-		cookie = chan->common.cookie;
-		cookie++;
-		if (cookie <= 1)
-			cookie = 2;
+		cookie = dma_cookie_assign(&sw_desc->async_tx);
 
 		/* initialize the completed cookie to be less than
 		 * the most recently used cookie
 		 */
-		chan->completed_cookie = cookie - 1;
-		chan->common.cookie = sw_desc->async_tx.cookie = cookie;
+		chan->common.completed_cookie = cookie - 1;
 
 		/* channel should not be busy */
 		BUG_ON(ppc440spe_chan_is_busy(chan));
@@ -4529,6 +4497,7 @@
 	INIT_LIST_HEAD(&chan->all_slots);
 	chan->device = adev;
 	chan->common.device = &adev->common;
+	dma_cookie_init(&chan->common);
 	list_add_tail(&chan->common.device_node, &adev->common.channels);
 	tasklet_init(&chan->irq_tasklet, ppc440spe_adma_tasklet,
 		     (unsigned long)chan);
diff --git a/drivers/dma/ppc4xx/adma.h b/drivers/dma/ppc4xx/adma.h
index 8ada5a81..26b7a5e 100644
--- a/drivers/dma/ppc4xx/adma.h
+++ b/drivers/dma/ppc4xx/adma.h
@@ -81,7 +81,6 @@
  * @common: common dmaengine channel object members
  * @all_slots: complete domain of slots usable by the channel
  * @pending: allows batching of hardware operations
- * @completed_cookie: identifier for the most recently completed operation
  * @slots_allocated: records the actual size of the descriptor slot pool
  * @hw_chain_inited: h/w descriptor chain initialization flag
  * @irq_tasklet: bottom half where ppc440spe_adma_slot_cleanup runs
@@ -99,7 +98,6 @@
 	struct list_head all_slots;
 	struct ppc440spe_adma_desc_slot *last_used;
 	int pending;
-	dma_cookie_t completed_cookie;
 	int slots_allocated;
 	int hw_chain_inited;
 	struct tasklet_struct irq_tasklet;
diff --git a/drivers/dma/shdma.c b/drivers/dma/shdma.c
index 812fd76..19d7a8d 100644
--- a/drivers/dma/shdma.c
+++ b/drivers/dma/shdma.c
@@ -30,6 +30,8 @@
 #include <linux/kdebug.h>
 #include <linux/spinlock.h>
 #include <linux/rculist.h>
+
+#include "dmaengine.h"
 #include "shdma.h"
 
 /* DMA descriptor control */
@@ -296,13 +298,7 @@
 	else
 		power_up = false;
 
-	cookie = sh_chan->common.cookie;
-	cookie++;
-	if (cookie < 0)
-		cookie = 1;
-
-	sh_chan->common.cookie = cookie;
-	tx->cookie = cookie;
+	cookie = dma_cookie_assign(tx);
 
 	/* Mark all chunks of this descriptor as submitted, move to the queue */
 	list_for_each_entry_safe(chunk, c, desc->node.prev, node) {
@@ -673,7 +669,8 @@
 
 static struct dma_async_tx_descriptor *sh_dmae_prep_slave_sg(
 	struct dma_chan *chan, struct scatterlist *sgl, unsigned int sg_len,
-	enum dma_transfer_direction direction, unsigned long flags)
+	enum dma_transfer_direction direction, unsigned long flags,
+	void *context)
 {
 	struct sh_dmae_slave *param;
 	struct sh_dmae_chan *sh_chan;
@@ -764,12 +761,12 @@
 			cookie = tx->cookie;
 
 		if (desc->mark == DESC_COMPLETED && desc->chunks == 1) {
-			if (sh_chan->completed_cookie != desc->cookie - 1)
+			if (sh_chan->common.completed_cookie != desc->cookie - 1)
 				dev_dbg(sh_chan->dev,
 					"Completing cookie %d, expected %d\n",
 					desc->cookie,
-					sh_chan->completed_cookie + 1);
-			sh_chan->completed_cookie = desc->cookie;
+					sh_chan->common.completed_cookie + 1);
+			sh_chan->common.completed_cookie = desc->cookie;
 		}
 
 		/* Call callback on the last chunk */
@@ -823,7 +820,7 @@
 		 * Terminating and the loop completed normally: forgive
 		 * uncompleted cookies
 		 */
-		sh_chan->completed_cookie = sh_chan->common.cookie;
+		sh_chan->common.completed_cookie = sh_chan->common.cookie;
 
 	spin_unlock_irqrestore(&sh_chan->desc_lock, flags);
 
@@ -883,23 +880,14 @@
 					struct dma_tx_state *txstate)
 {
 	struct sh_dmae_chan *sh_chan = to_sh_chan(chan);
-	dma_cookie_t last_used;
-	dma_cookie_t last_complete;
 	enum dma_status status;
 	unsigned long flags;
 
 	sh_dmae_chan_ld_cleanup(sh_chan, false);
 
-	/* First read completed cookie to avoid a skew */
-	last_complete = sh_chan->completed_cookie;
-	rmb();
-	last_used = chan->cookie;
-	BUG_ON(last_complete < 0);
-	dma_set_tx_state(txstate, last_complete, last_used, 0);
-
 	spin_lock_irqsave(&sh_chan->desc_lock, flags);
 
-	status = dma_async_is_complete(cookie, last_complete, last_used);
+	status = dma_cookie_status(chan, cookie, txstate);
 
 	/*
 	 * If we don't find cookie on the queue, it has been aborted and we have
@@ -1102,6 +1090,7 @@
 
 	/* reference struct dma_device */
 	new_sh_chan->common.device = &shdev->common;
+	dma_cookie_init(&new_sh_chan->common);
 
 	new_sh_chan->dev = shdev->common.dev;
 	new_sh_chan->id = id;
diff --git a/drivers/dma/shdma.h b/drivers/dma/shdma.h
index 2b55a27..0b1d2c1 100644
--- a/drivers/dma/shdma.h
+++ b/drivers/dma/shdma.h
@@ -30,7 +30,6 @@
 };
 
 struct sh_dmae_chan {
-	dma_cookie_t completed_cookie;	/* The maximum cookie completed */
 	spinlock_t desc_lock;		/* Descriptor operation lock */
 	struct list_head ld_queue;	/* Link descriptors queue */
 	struct list_head ld_free;	/* Link descriptors free */
diff --git a/drivers/dma/sirf-dma.c b/drivers/dma/sirf-dma.c
index 2333810..434ad31 100644
--- a/drivers/dma/sirf-dma.c
+++ b/drivers/dma/sirf-dma.c
@@ -18,6 +18,8 @@
 #include <linux/of_platform.h>
 #include <linux/sirfsoc_dma.h>
 
+#include "dmaengine.h"
+
 #define SIRFSOC_DMA_DESCRIPTORS                 16
 #define SIRFSOC_DMA_CHANNELS                    16
 
@@ -59,7 +61,6 @@
 	struct list_head		queued;
 	struct list_head		active;
 	struct list_head		completed;
-	dma_cookie_t			completed_cookie;
 	unsigned long			happened_cyclic;
 	unsigned long			completed_cyclic;
 
@@ -208,7 +209,7 @@
 			/* Free descriptors */
 			spin_lock_irqsave(&schan->lock, flags);
 			list_splice_tail_init(&list, &schan->free);
-			schan->completed_cookie = last_cookie;
+			schan->chan.completed_cookie = last_cookie;
 			spin_unlock_irqrestore(&schan->lock, flags);
 		} else {
 			/* for cyclic channel, desc is always in active list */
@@ -258,13 +259,7 @@
 	/* Move descriptor to queue */
 	list_move_tail(&sdesc->node, &schan->queued);
 
-	/* Update cookie */
-	cookie = schan->chan.cookie + 1;
-	if (cookie <= 0)
-		cookie = 1;
-
-	schan->chan.cookie = cookie;
-	sdesc->desc.cookie = cookie;
+	cookie = dma_cookie_assign(txd);
 
 	spin_unlock_irqrestore(&schan->lock, flags);
 
@@ -414,16 +409,13 @@
 {
 	struct sirfsoc_dma_chan *schan = dma_chan_to_sirfsoc_dma_chan(chan);
 	unsigned long flags;
-	dma_cookie_t last_used;
-	dma_cookie_t last_complete;
+	enum dma_status ret;
 
 	spin_lock_irqsave(&schan->lock, flags);
-	last_used = schan->chan.cookie;
-	last_complete = schan->completed_cookie;
+	ret = dma_cookie_status(chan, cookie, txstate);
 	spin_unlock_irqrestore(&schan->lock, flags);
 
-	dma_set_tx_state(txstate, last_complete, last_used, 0);
-	return dma_async_is_complete(cookie, last_complete, last_used);
+	return ret;
 }
 
 static struct dma_async_tx_descriptor *sirfsoc_dma_prep_interleaved(
@@ -497,7 +489,7 @@
 static struct dma_async_tx_descriptor *
 sirfsoc_dma_prep_cyclic(struct dma_chan *chan, dma_addr_t addr,
 	size_t buf_len, size_t period_len,
-	enum dma_transfer_direction direction)
+	enum dma_transfer_direction direction, void *context)
 {
 	struct sirfsoc_dma_chan *schan = dma_chan_to_sirfsoc_dma_chan(chan);
 	struct sirfsoc_dma_desc *sdesc = NULL;
@@ -635,8 +627,7 @@
 		schan = &sdma->channels[i];
 
 		schan->chan.device = dma;
-		schan->chan.cookie = 1;
-		schan->completed_cookie = schan->chan.cookie;
+		dma_cookie_init(&schan->chan);
 
 		INIT_LIST_HEAD(&schan->free);
 		INIT_LIST_HEAD(&schan->prepared);
diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c
index cc5ecbc..bdd41d4 100644
--- a/drivers/dma/ste_dma40.c
+++ b/drivers/dma/ste_dma40.c
@@ -21,6 +21,7 @@
 
 #include <plat/ste_dma40.h>
 
+#include "dmaengine.h"
 #include "ste_dma40_ll.h"
 
 #define D40_NAME "dma40"
@@ -220,8 +221,6 @@
  *
  * @lock: A spinlock to protect this struct.
  * @log_num: The logical number, if any of this channel.
- * @completed: Starts with 1, after first interrupt it is set to dma engine's
- * current cookie.
  * @pending_tx: The number of pending transfers. Used between interrupt handler
  * and tasklet.
  * @busy: Set to true when transfer is ongoing on this channel.
@@ -250,8 +249,6 @@
 struct d40_chan {
 	spinlock_t			 lock;
 	int				 log_num;
-	/* ID of the most recent completed transfer */
-	int				 completed;
 	int				 pending_tx;
 	bool				 busy;
 	struct d40_phy_res		*phy_chan;
@@ -1223,21 +1220,14 @@
 					     chan);
 	struct d40_desc *d40d = container_of(tx, struct d40_desc, txd);
 	unsigned long flags;
+	dma_cookie_t cookie;
 
 	spin_lock_irqsave(&d40c->lock, flags);
-
-	d40c->chan.cookie++;
-
-	if (d40c->chan.cookie < 0)
-		d40c->chan.cookie = 1;
-
-	d40d->txd.cookie = d40c->chan.cookie;
-
+	cookie = dma_cookie_assign(tx);
 	d40_desc_queue(d40c, d40d);
-
 	spin_unlock_irqrestore(&d40c->lock, flags);
 
-	return tx->cookie;
+	return cookie;
 }
 
 static int d40_start(struct d40_chan *d40c)
@@ -1357,7 +1347,7 @@
 		goto err;
 
 	if (!d40d->cyclic)
-		d40c->completed = d40d->txd.cookie;
+		dma_cookie_complete(&d40d->txd);
 
 	/*
 	 * If terminating a channel pending_tx is set to zero.
@@ -2182,7 +2172,7 @@
 	bool is_free_phy;
 	spin_lock_irqsave(&d40c->lock, flags);
 
-	d40c->completed = chan->cookie = 1;
+	dma_cookie_init(chan);
 
 	/* If no dma configuration is set use default configuration (memcpy) */
 	if (!d40c->configured) {
@@ -2299,7 +2289,8 @@
 							 struct scatterlist *sgl,
 							 unsigned int sg_len,
 							 enum dma_transfer_direction direction,
-							 unsigned long dma_flags)
+							 unsigned long dma_flags,
+							 void *context)
 {
 	if (direction != DMA_DEV_TO_MEM && direction != DMA_MEM_TO_DEV)
 		return NULL;
@@ -2310,7 +2301,7 @@
 static struct dma_async_tx_descriptor *
 dma40_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t dma_addr,
 		     size_t buf_len, size_t period_len,
-		     enum dma_transfer_direction direction)
+		     enum dma_transfer_direction direction, void *context)
 {
 	unsigned int periods = buf_len / period_len;
 	struct dma_async_tx_descriptor *txd;
@@ -2342,25 +2333,19 @@
 				     struct dma_tx_state *txstate)
 {
 	struct d40_chan *d40c = container_of(chan, struct d40_chan, chan);
-	dma_cookie_t last_used;
-	dma_cookie_t last_complete;
-	int ret;
+	enum dma_status ret;
 
 	if (d40c->phy_chan == NULL) {
 		chan_err(d40c, "Cannot read status of unallocated channel\n");
 		return -EINVAL;
 	}
 
-	last_complete = d40c->completed;
-	last_used = chan->cookie;
+	ret = dma_cookie_status(chan, cookie, txstate);
+	if (ret != DMA_SUCCESS)
+		dma_set_residue(txstate, stedma40_residue(chan));
 
 	if (d40_is_paused(d40c))
 		ret = DMA_PAUSED;
-	else
-		ret = dma_async_is_complete(cookie, last_complete, last_used);
-
-	dma_set_tx_state(txstate, last_complete, last_used,
-			 stedma40_residue(chan));
 
 	return ret;
 }
diff --git a/drivers/dma/timb_dma.c b/drivers/dma/timb_dma.c
index a6f9c16..4e0dff5 100644
--- a/drivers/dma/timb_dma.c
+++ b/drivers/dma/timb_dma.c
@@ -31,6 +31,8 @@
 
 #include <linux/timb_dma.h>
 
+#include "dmaengine.h"
+
 #define DRIVER_NAME "timb-dma"
 
 /* Global DMA registers */
@@ -84,7 +86,6 @@
 					especially the lists and descriptors,
 					from races between the tasklet and calls
 					from above */
-	dma_cookie_t		last_completed_cookie;
 	bool			ongoing;
 	struct list_head	active_list;
 	struct list_head	queue;
@@ -284,7 +285,7 @@
 	else
 		iowrite32(0, td_chan->membase + TIMBDMA_OFFS_TX_DLAR);
 */
-	td_chan->last_completed_cookie = txd->cookie;
+	dma_cookie_complete(txd);
 	td_chan->ongoing = false;
 
 	callback = txd->callback;
@@ -349,12 +350,7 @@
 	dma_cookie_t cookie;
 
 	spin_lock_bh(&td_chan->lock);
-
-	cookie = txd->chan->cookie;
-	if (++cookie < 0)
-		cookie = 1;
-	txd->chan->cookie = cookie;
-	txd->cookie = cookie;
+	cookie = dma_cookie_assign(txd);
 
 	if (list_empty(&td_chan->active_list)) {
 		dev_dbg(chan2dev(txd->chan), "%s: started %u\n", __func__,
@@ -481,8 +477,7 @@
 	}
 
 	spin_lock_bh(&td_chan->lock);
-	td_chan->last_completed_cookie = 1;
-	chan->cookie = 1;
+	dma_cookie_init(chan);
 	spin_unlock_bh(&td_chan->lock);
 
 	return 0;
@@ -515,24 +510,13 @@
 static enum dma_status td_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 				    struct dma_tx_state *txstate)
 {
-	struct timb_dma_chan *td_chan =
-		container_of(chan, struct timb_dma_chan, chan);
-	dma_cookie_t		last_used;
-	dma_cookie_t		last_complete;
-	int			ret;
+	enum dma_status ret;
 
 	dev_dbg(chan2dev(chan), "%s: Entry\n", __func__);
 
-	last_complete = td_chan->last_completed_cookie;
-	last_used = chan->cookie;
+	ret = dma_cookie_status(chan, cookie, txstate);
 
-	ret = dma_async_is_complete(cookie, last_complete, last_used);
-
-	dma_set_tx_state(txstate, last_complete, last_used, 0);
-
-	dev_dbg(chan2dev(chan),
-		"%s: exit, ret: %d, last_complete: %d, last_used: %d\n",
-		__func__, ret, last_complete, last_used);
+	dev_dbg(chan2dev(chan), "%s: exit, ret: %d\n", 	__func__, ret);
 
 	return ret;
 }
@@ -558,7 +542,8 @@
 
 static struct dma_async_tx_descriptor *td_prep_slave_sg(struct dma_chan *chan,
 	struct scatterlist *sgl, unsigned int sg_len,
-	enum dma_transfer_direction direction, unsigned long flags)
+	enum dma_transfer_direction direction, unsigned long flags,
+	void *context)
 {
 	struct timb_dma_chan *td_chan =
 		container_of(chan, struct timb_dma_chan, chan);
@@ -766,7 +751,7 @@
 		}
 
 		td_chan->chan.device = &td->dma;
-		td_chan->chan.cookie = 1;
+		dma_cookie_init(&td_chan->chan);
 		spin_lock_init(&td_chan->lock);
 		INIT_LIST_HEAD(&td_chan->active_list);
 		INIT_LIST_HEAD(&td_chan->queue);
diff --git a/drivers/dma/txx9dmac.c b/drivers/dma/txx9dmac.c
index 6122c36..913f55c 100644
--- a/drivers/dma/txx9dmac.c
+++ b/drivers/dma/txx9dmac.c
@@ -15,6 +15,8 @@
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/scatterlist.h>
+
+#include "dmaengine.h"
 #include "txx9dmac.h"
 
 static struct txx9dmac_chan *to_txx9dmac_chan(struct dma_chan *chan)
@@ -279,21 +281,6 @@
 	}
 }
 
-/* Called with dc->lock held and bh disabled */
-static dma_cookie_t
-txx9dmac_assign_cookie(struct txx9dmac_chan *dc, struct txx9dmac_desc *desc)
-{
-	dma_cookie_t cookie = dc->chan.cookie;
-
-	if (++cookie < 0)
-		cookie = 1;
-
-	dc->chan.cookie = cookie;
-	desc->txd.cookie = cookie;
-
-	return cookie;
-}
-
 /*----------------------------------------------------------------------*/
 
 static void txx9dmac_dump_regs(struct txx9dmac_chan *dc)
@@ -424,7 +411,7 @@
 	dev_vdbg(chan2dev(&dc->chan), "descriptor %u %p complete\n",
 		 txd->cookie, desc);
 
-	dc->completed = txd->cookie;
+	dma_cookie_complete(txd);
 	callback = txd->callback;
 	param = txd->callback_param;
 
@@ -738,7 +725,7 @@
 	dma_cookie_t cookie;
 
 	spin_lock_bh(&dc->lock);
-	cookie = txx9dmac_assign_cookie(dc, desc);
+	cookie = dma_cookie_assign(tx);
 
 	dev_vdbg(chan2dev(tx->chan), "tx_submit: queued %u %p\n",
 		 desc->txd.cookie, desc);
@@ -846,7 +833,7 @@
 static struct dma_async_tx_descriptor *
 txx9dmac_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 		unsigned int sg_len, enum dma_transfer_direction direction,
-		unsigned long flags)
+		unsigned long flags, void *context)
 {
 	struct txx9dmac_chan *dc = to_txx9dmac_chan(chan);
 	struct txx9dmac_dev *ddev = dc->ddev;
@@ -972,27 +959,17 @@
 		   struct dma_tx_state *txstate)
 {
 	struct txx9dmac_chan *dc = to_txx9dmac_chan(chan);
-	dma_cookie_t last_used;
-	dma_cookie_t last_complete;
-	int ret;
+	enum dma_status ret;
 
-	last_complete = dc->completed;
-	last_used = chan->cookie;
-
-	ret = dma_async_is_complete(cookie, last_complete, last_used);
+	ret = dma_cookie_status(chan, cookie, txstate);
 	if (ret != DMA_SUCCESS) {
 		spin_lock_bh(&dc->lock);
 		txx9dmac_scan_descriptors(dc);
 		spin_unlock_bh(&dc->lock);
 
-		last_complete = dc->completed;
-		last_used = chan->cookie;
-
-		ret = dma_async_is_complete(cookie, last_complete, last_used);
+		ret = dma_cookie_status(chan, cookie, txstate);
 	}
 
-	dma_set_tx_state(txstate, last_complete, last_used, 0);
-
 	return ret;
 }
 
@@ -1057,7 +1034,7 @@
 		return -EIO;
 	}
 
-	dc->completed = chan->cookie = 1;
+	dma_cookie_init(chan);
 
 	dc->ccr = TXX9_DMA_CCR_IMMCHN | TXX9_DMA_CCR_INTENE | CCR_LE;
 	txx9dmac_chan_set_SMPCHN(dc);
@@ -1186,7 +1163,7 @@
 	dc->ddev->chan[ch] = dc;
 	dc->chan.device = &dc->dma;
 	list_add_tail(&dc->chan.device_node, &dc->chan.device->channels);
-	dc->chan.cookie = dc->completed = 1;
+	dma_cookie_init(&dc->chan);
 
 	if (is_dmac64(dc))
 		dc->ch_regs = &__txx9dmac_regs(dc->ddev)->CHAN[ch];
diff --git a/drivers/dma/txx9dmac.h b/drivers/dma/txx9dmac.h
index 365d423..f5a7605 100644
--- a/drivers/dma/txx9dmac.h
+++ b/drivers/dma/txx9dmac.h
@@ -172,7 +172,6 @@
 	spinlock_t		lock;
 
 	/* these other elements are all protected by lock */
-	dma_cookie_t		completed;
 	struct list_head	active_list;
 	struct list_head	queue;
 	struct list_head	free_list;
diff --git a/drivers/gpio/gpio-pxa.c b/drivers/gpio/gpio-pxa.c
index b2d3ee1..5689ce6 100644
--- a/drivers/gpio/gpio-pxa.c
+++ b/drivers/gpio/gpio-pxa.c
@@ -22,6 +22,8 @@
 #include <linux/syscore_ops.h>
 #include <linux/slab.h>
 
+#include <mach/irqs.h>
+
 /*
  * We handle the GPIOs by banks, each bank covers up to 32 GPIOs with
  * one set of registers. The register offsets are organized below:
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 0694e17..1a7559b 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -467,6 +467,10 @@
 	/* Modeset on resume, not lid events */
 	dev_priv->modeset_on_lid = 0;
 
+	console_lock();
+	intel_fbdev_set_suspend(dev, 1);
+	console_unlock();
+
 	return 0;
 }
 
@@ -539,6 +543,9 @@
 
 	dev_priv->modeset_on_lid = 0;
 
+	console_lock();
+	intel_fbdev_set_suspend(dev, 0);
+	console_unlock();
 	return error;
 }
 
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 9cec6c3..5a14149 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -382,7 +382,7 @@
 				  struct drm_i915_gem_object *obj);
 extern int intel_fbdev_init(struct drm_device *dev);
 extern void intel_fbdev_fini(struct drm_device *dev);
-
+extern void intel_fbdev_set_suspend(struct drm_device *dev, int state);
 extern void intel_prepare_page_flip(struct drm_device *dev, int plane);
 extern void intel_finish_page_flip(struct drm_device *dev, int pipe);
 extern void intel_finish_page_flip_plane(struct drm_device *dev, int plane);
diff --git a/drivers/gpu/drm/i915/intel_fb.c b/drivers/gpu/drm/i915/intel_fb.c
index 2d87669..19ecd78 100644
--- a/drivers/gpu/drm/i915/intel_fb.c
+++ b/drivers/gpu/drm/i915/intel_fb.c
@@ -254,6 +254,16 @@
 	kfree(dev_priv->fbdev);
 	dev_priv->fbdev = NULL;
 }
+
+void intel_fbdev_set_suspend(struct drm_device *dev, int state)
+{
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	if (!dev_priv->fbdev)
+		return;
+
+	fb_set_suspend(dev_priv->fbdev->helper.fbdev, state);
+}
+
 MODULE_LICENSE("GPL and additional rights");
 
 void intel_fb_output_poll_changed(struct drm_device *dev)
diff --git a/drivers/input/input-compat.c b/drivers/input/input-compat.c
index e46a867..64ca711 100644
--- a/drivers/input/input-compat.c
+++ b/drivers/input/input-compat.c
@@ -17,7 +17,7 @@
 int input_event_from_user(const char __user *buffer,
 			  struct input_event *event)
 {
-	if (INPUT_COMPAT_TEST) {
+	if (INPUT_COMPAT_TEST && !COMPAT_USE_64BIT_TIME) {
 		struct input_event_compat compat_event;
 
 		if (copy_from_user(&compat_event, buffer,
@@ -41,7 +41,7 @@
 int input_event_to_user(char __user *buffer,
 			const struct input_event *event)
 {
-	if (INPUT_COMPAT_TEST) {
+	if (INPUT_COMPAT_TEST && !COMPAT_USE_64BIT_TIME) {
 		struct input_event_compat compat_event;
 
 		compat_event.time.tv_sec = event->time.tv_sec;
diff --git a/drivers/input/input-compat.h b/drivers/input/input-compat.h
index 22be27b..148f66f 100644
--- a/drivers/input/input-compat.h
+++ b/drivers/input/input-compat.h
@@ -67,7 +67,7 @@
 
 static inline size_t input_event_size(void)
 {
-	return INPUT_COMPAT_TEST ?
+	return (INPUT_COMPAT_TEST && !COMPAT_USE_64BIT_TIME) ?
 		sizeof(struct input_event_compat) : sizeof(struct input_event);
 }
 
diff --git a/drivers/input/serio/ams_delta_serio.c b/drivers/input/serio/ams_delta_serio.c
index bd5b10e..f5fbdf9 100644
--- a/drivers/input/serio/ams_delta_serio.c
+++ b/drivers/input/serio/ams_delta_serio.c
@@ -184,7 +184,7 @@
 static void __exit ams_delta_serio_exit(void)
 {
 	serio_unregister_port(ams_delta_serio);
-	free_irq(OMAP_GPIO_IRQ(AMS_DELTA_GPIO_PIN_KEYBRD_CLK), 0);
+	free_irq(gpio_to_irq(AMS_DELTA_GPIO_PIN_KEYBRD_CLK), 0);
 	gpio_free_array(ams_delta_gpios,
 			ARRAY_SIZE(ams_delta_gpios));
 }
diff --git a/drivers/media/video/davinci/vpbe_osd.c b/drivers/media/video/davinci/vpbe_osd.c
index d6488b7..bba299d 100644
--- a/drivers/media/video/davinci/vpbe_osd.c
+++ b/drivers/media/video/davinci/vpbe_osd.c
@@ -28,7 +28,6 @@
 #include <linux/clk.h>
 #include <linux/slab.h>
 
-#include <mach/io.h>
 #include <mach/cputype.h>
 #include <mach/hardware.h>
 
diff --git a/drivers/media/video/davinci/vpbe_venc.c b/drivers/media/video/davinci/vpbe_venc.c
index 00e80f5..b21ecc8 100644
--- a/drivers/media/video/davinci/vpbe_venc.c
+++ b/drivers/media/video/davinci/vpbe_venc.c
@@ -27,7 +27,6 @@
 
 #include <mach/hardware.h>
 #include <mach/mux.h>
-#include <mach/io.h>
 #include <mach/i2c.h>
 
 #include <linux/io.h>
diff --git a/drivers/media/video/mx3_camera.c b/drivers/media/video/mx3_camera.c
index 7452277..93c35ef 100644
--- a/drivers/media/video/mx3_camera.c
+++ b/drivers/media/video/mx3_camera.c
@@ -286,7 +286,7 @@
 		sg_dma_address(sg)	= vb2_dma_contig_plane_dma_addr(vb, 0);
 		sg_dma_len(sg)		= new_size;
 
-		txd = ichan->dma_chan.device->device_prep_slave_sg(
+		txd = dmaengine_prep_slave_sg(
 			&ichan->dma_chan, sg, 1, DMA_DEV_TO_MEM,
 			DMA_PREP_INTERRUPT);
 		if (!txd)
diff --git a/drivers/media/video/timblogiw.c b/drivers/media/video/timblogiw.c
index 4ed1c7c2..02194c0 100644
--- a/drivers/media/video/timblogiw.c
+++ b/drivers/media/video/timblogiw.c
@@ -564,7 +564,7 @@
 
 	spin_unlock_irq(&fh->queue_lock);
 
-	desc = fh->chan->device->device_prep_slave_sg(fh->chan,
+	desc = dmaengine_prep_slave_sg(fh->chan,
 		buf->sg, sg_elems, DMA_DEV_TO_MEM,
 		DMA_PREP_INTERRUPT | DMA_COMPL_SKIP_SRC_UNMAP);
 	if (!desc) {
diff --git a/drivers/mmc/host/atmel-mci.c b/drivers/mmc/host/atmel-mci.c
index 390863e..9819dc0 100644
--- a/drivers/mmc/host/atmel-mci.c
+++ b/drivers/mmc/host/atmel-mci.c
@@ -24,6 +24,7 @@
 #include <linux/seq_file.h>
 #include <linux/slab.h>
 #include <linux/stat.h>
+#include <linux/types.h>
 
 #include <linux/mmc/host.h>
 #include <linux/mmc/sdio.h>
@@ -173,6 +174,7 @@
 
 	struct atmel_mci_dma	dma;
 	struct dma_chan		*data_chan;
+	struct dma_slave_config	dma_conf;
 
 	u32			cmd_status;
 	u32			data_status;
@@ -863,16 +865,17 @@
 
 	if (data->flags & MMC_DATA_READ) {
 		direction = DMA_FROM_DEVICE;
-		slave_dirn = DMA_DEV_TO_MEM;
+		host->dma_conf.direction = slave_dirn = DMA_DEV_TO_MEM;
 	} else {
 		direction = DMA_TO_DEVICE;
-		slave_dirn = DMA_MEM_TO_DEV;
+		host->dma_conf.direction = slave_dirn = DMA_MEM_TO_DEV;
 	}
 
 	sglen = dma_map_sg(chan->device->dev, data->sg,
 			data->sg_len, direction);
 
-	desc = chan->device->device_prep_slave_sg(chan,
+	dmaengine_slave_config(chan, &host->dma_conf);
+	desc = dmaengine_prep_slave_sg(chan,
 			data->sg, sglen, slave_dirn,
 			DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	if (!desc)
@@ -1960,10 +1963,6 @@
 	if (pdata && find_slave_dev(pdata->dma_slave)) {
 		dma_cap_mask_t mask;
 
-		setup_dma_addr(pdata->dma_slave,
-			       host->mapbase + ATMCI_TDR,
-			       host->mapbase + ATMCI_RDR);
-
 		/* Try to grab a DMA channel */
 		dma_cap_zero(mask);
 		dma_cap_set(DMA_SLAVE, mask);
@@ -1977,6 +1976,14 @@
 		dev_info(&host->pdev->dev,
 					"using %s for DMA transfers\n",
 					dma_chan_name(host->dma.chan));
+
+		host->dma_conf.src_addr = host->mapbase + ATMCI_RDR;
+		host->dma_conf.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+		host->dma_conf.src_maxburst = 1;
+		host->dma_conf.dst_addr = host->mapbase + ATMCI_TDR;
+		host->dma_conf.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+		host->dma_conf.dst_maxburst = 1;
+		host->dma_conf.device_fc = false;
 		return true;
 	}
 }
diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c
index 983e244e..032b847 100644
--- a/drivers/mmc/host/mmci.c
+++ b/drivers/mmc/host/mmci.c
@@ -30,6 +30,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/amba/mmci.h>
 #include <linux/pm_runtime.h>
+#include <linux/types.h>
 
 #include <asm/div64.h>
 #include <asm/io.h>
@@ -400,6 +401,7 @@
 		.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES,
 		.src_maxburst = variant->fifohalfsize >> 2, /* # of words */
 		.dst_maxburst = variant->fifohalfsize >> 2, /* # of words */
+		.device_fc = false,
 	};
 	struct dma_chan *chan;
 	struct dma_device *device;
@@ -441,7 +443,7 @@
 		return -EINVAL;
 
 	dmaengine_slave_config(chan, &conf);
-	desc = device->device_prep_slave_sg(chan, data->sg, nr_sg,
+	desc = dmaengine_prep_slave_sg(chan, data->sg, nr_sg,
 					    conf.direction, DMA_CTRL_ACK);
 	if (!desc)
 		goto unmap_exit;
diff --git a/drivers/mmc/host/mxcmmc.c b/drivers/mmc/host/mxcmmc.c
index 4184b79..b2058b4 100644
--- a/drivers/mmc/host/mxcmmc.c
+++ b/drivers/mmc/host/mxcmmc.c
@@ -33,6 +33,7 @@
 #include <linux/gpio.h>
 #include <linux/regulator/consumer.h>
 #include <linux/dmaengine.h>
+#include <linux/types.h>
 
 #include <asm/dma.h>
 #include <asm/irq.h>
@@ -254,7 +255,7 @@
 	if (nents != data->sg_len)
 		return -EINVAL;
 
-	host->desc = host->dma->device->device_prep_slave_sg(host->dma,
+	host->desc = dmaengine_prep_slave_sg(host->dma,
 		data->sg, data->sg_len, slave_dirn,
 		DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 
@@ -267,6 +268,7 @@
 	wmb();
 
 	dmaengine_submit(host->desc);
+	dma_async_issue_pending(host->dma);
 
 	return 0;
 }
@@ -710,6 +712,7 @@
 	config->src_addr_width = 4;
 	config->dst_maxburst = host->burstlen;
 	config->src_maxburst = host->burstlen;
+	config->device_fc = false;
 
 	return dmaengine_slave_config(host->dma, config);
 }
diff --git a/drivers/mmc/host/mxs-mmc.c b/drivers/mmc/host/mxs-mmc.c
index 382c835..65f36cf 100644
--- a/drivers/mmc/host/mxs-mmc.c
+++ b/drivers/mmc/host/mxs-mmc.c
@@ -324,7 +324,7 @@
 		sg_len = SSP_PIO_NUM;
 	}
 
-	desc = host->dmach->device->device_prep_slave_sg(host->dmach,
+	desc = dmaengine_prep_slave_sg(host->dmach,
 				sgl, sg_len, host->slave_dirn, append);
 	if (desc) {
 		desc->callback = mxs_mmc_dma_irq_callback;
diff --git a/drivers/mmc/host/sh_mmcif.c b/drivers/mmc/host/sh_mmcif.c
index 60f2057..aafaf0b 100644
--- a/drivers/mmc/host/sh_mmcif.c
+++ b/drivers/mmc/host/sh_mmcif.c
@@ -286,7 +286,7 @@
 			 DMA_FROM_DEVICE);
 	if (ret > 0) {
 		host->dma_active = true;
-		desc = chan->device->device_prep_slave_sg(chan, sg, ret,
+		desc = dmaengine_prep_slave_sg(chan, sg, ret,
 			DMA_DEV_TO_MEM, DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	}
 
@@ -335,7 +335,7 @@
 			 DMA_TO_DEVICE);
 	if (ret > 0) {
 		host->dma_active = true;
-		desc = chan->device->device_prep_slave_sg(chan, sg, ret,
+		desc = dmaengine_prep_slave_sg(chan, sg, ret,
 			DMA_MEM_TO_DEV, DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	}
 
diff --git a/drivers/mmc/host/tmio_mmc_dma.c b/drivers/mmc/host/tmio_mmc_dma.c
index 8253ec1..fff9286 100644
--- a/drivers/mmc/host/tmio_mmc_dma.c
+++ b/drivers/mmc/host/tmio_mmc_dma.c
@@ -88,7 +88,7 @@
 
 	ret = dma_map_sg(chan->device->dev, sg, host->sg_len, DMA_FROM_DEVICE);
 	if (ret > 0)
-		desc = chan->device->device_prep_slave_sg(chan, sg, ret,
+		desc = dmaengine_prep_slave_sg(chan, sg, ret,
 			DMA_DEV_TO_MEM, DMA_CTRL_ACK);
 
 	if (desc) {
@@ -169,7 +169,7 @@
 
 	ret = dma_map_sg(chan->device->dev, sg, host->sg_len, DMA_TO_DEVICE);
 	if (ret > 0)
-		desc = chan->device->device_prep_slave_sg(chan, sg, ret,
+		desc = dmaengine_prep_slave_sg(chan, sg, ret,
 			DMA_MEM_TO_DEV, DMA_CTRL_ACK);
 
 	if (desc) {
diff --git a/drivers/mtd/nand/gpmi-nand/gpmi-lib.c b/drivers/mtd/nand/gpmi-nand/gpmi-lib.c
index 7db6555..590dd5c 100644
--- a/drivers/mtd/nand/gpmi-nand/gpmi-lib.c
+++ b/drivers/mtd/nand/gpmi-nand/gpmi-lib.c
@@ -835,7 +835,7 @@
 		| BM_GPMI_CTRL0_ADDRESS_INCREMENT
 		| BF_GPMI_CTRL0_XFER_COUNT(this->command_length);
 	pio[1] = pio[2] = 0;
-	desc = channel->device->device_prep_slave_sg(channel,
+	desc = dmaengine_prep_slave_sg(channel,
 					(struct scatterlist *)pio,
 					ARRAY_SIZE(pio), DMA_TRANS_NONE, 0);
 	if (!desc) {
@@ -848,8 +848,7 @@
 
 	sg_init_one(sgl, this->cmd_buffer, this->command_length);
 	dma_map_sg(this->dev, sgl, 1, DMA_TO_DEVICE);
-	desc = channel->device->device_prep_slave_sg(channel,
-					sgl, 1, DMA_MEM_TO_DEV, 1);
+	desc = dmaengine_prep_slave_sg(channel, sgl, 1, DMA_MEM_TO_DEV, 1);
 	if (!desc) {
 		pr_err("step 2 error\n");
 		return -1;
@@ -880,8 +879,7 @@
 		| BF_GPMI_CTRL0_ADDRESS(address)
 		| BF_GPMI_CTRL0_XFER_COUNT(this->upper_len);
 	pio[1] = 0;
-	desc = channel->device->device_prep_slave_sg(channel,
-					(struct scatterlist *)pio,
+	desc = dmaengine_prep_slave_sg(channel, (struct scatterlist *)pio,
 					ARRAY_SIZE(pio), DMA_TRANS_NONE, 0);
 	if (!desc) {
 		pr_err("step 1 error\n");
@@ -890,7 +888,7 @@
 
 	/* [2] send DMA request */
 	prepare_data_dma(this, DMA_TO_DEVICE);
-	desc = channel->device->device_prep_slave_sg(channel, &this->data_sgl,
+	desc = dmaengine_prep_slave_sg(channel, &this->data_sgl,
 						1, DMA_MEM_TO_DEV, 1);
 	if (!desc) {
 		pr_err("step 2 error\n");
@@ -916,7 +914,7 @@
 		| BF_GPMI_CTRL0_ADDRESS(BV_GPMI_CTRL0_ADDRESS__NAND_DATA)
 		| BF_GPMI_CTRL0_XFER_COUNT(this->upper_len);
 	pio[1] = 0;
-	desc = channel->device->device_prep_slave_sg(channel,
+	desc = dmaengine_prep_slave_sg(channel,
 					(struct scatterlist *)pio,
 					ARRAY_SIZE(pio), DMA_TRANS_NONE, 0);
 	if (!desc) {
@@ -926,8 +924,8 @@
 
 	/* [2] : send DMA request */
 	prepare_data_dma(this, DMA_FROM_DEVICE);
-	desc = channel->device->device_prep_slave_sg(channel, &this->data_sgl,
-						1, DMA_DEV_TO_MEM, 1);
+	desc = dmaengine_prep_slave_sg(channel, &this->data_sgl,
+					1, DMA_DEV_TO_MEM, 1);
 	if (!desc) {
 		pr_err("step 2 error\n");
 		return -1;
@@ -972,8 +970,7 @@
 	pio[4] = payload;
 	pio[5] = auxiliary;
 
-	desc = channel->device->device_prep_slave_sg(channel,
-					(struct scatterlist *)pio,
+	desc = dmaengine_prep_slave_sg(channel, (struct scatterlist *)pio,
 					ARRAY_SIZE(pio), DMA_TRANS_NONE, 0);
 	if (!desc) {
 		pr_err("step 2 error\n");
@@ -1007,7 +1004,7 @@
 		| BF_GPMI_CTRL0_ADDRESS(address)
 		| BF_GPMI_CTRL0_XFER_COUNT(0);
 	pio[1] = 0;
-	desc = channel->device->device_prep_slave_sg(channel,
+	desc = dmaengine_prep_slave_sg(channel,
 				(struct scatterlist *)pio, 2,
 				DMA_TRANS_NONE, 0);
 	if (!desc) {
@@ -1036,7 +1033,7 @@
 	pio[3] = geo->page_size;
 	pio[4] = payload;
 	pio[5] = auxiliary;
-	desc = channel->device->device_prep_slave_sg(channel,
+	desc = dmaengine_prep_slave_sg(channel,
 					(struct scatterlist *)pio,
 					ARRAY_SIZE(pio), DMA_TRANS_NONE, 1);
 	if (!desc) {
@@ -1055,7 +1052,7 @@
 		| BF_GPMI_CTRL0_ADDRESS(address)
 		| BF_GPMI_CTRL0_XFER_COUNT(geo->page_size);
 	pio[1] = 0;
-	desc = channel->device->device_prep_slave_sg(channel,
+	desc = dmaengine_prep_slave_sg(channel,
 				(struct scatterlist *)pio, 2,
 				DMA_TRANS_NONE, 1);
 	if (!desc) {
diff --git a/drivers/net/ethernet/micrel/ks8842.c b/drivers/net/ethernet/micrel/ks8842.c
index 0686b93..f84dd2d 100644
--- a/drivers/net/ethernet/micrel/ks8842.c
+++ b/drivers/net/ethernet/micrel/ks8842.c
@@ -458,7 +458,7 @@
 	if (sg_dma_len(&ctl->sg) % 4)
 		sg_dma_len(&ctl->sg) += 4 - sg_dma_len(&ctl->sg) % 4;
 
-	ctl->adesc = ctl->chan->device->device_prep_slave_sg(ctl->chan,
+	ctl->adesc = dmaengine_prep_slave_sg(ctl->chan,
 		&ctl->sg, 1, DMA_MEM_TO_DEV,
 		DMA_PREP_INTERRUPT | DMA_COMPL_SKIP_SRC_UNMAP);
 	if (!ctl->adesc)
@@ -570,7 +570,7 @@
 
 		sg_dma_len(sg) = DMA_BUFFER_SIZE;
 
-		ctl->adesc = ctl->chan->device->device_prep_slave_sg(ctl->chan,
+		ctl->adesc = dmaengine_prep_slave_sg(ctl->chan,
 			sg, 1, DMA_DEV_TO_MEM,
 			DMA_PREP_INTERRUPT | DMA_COMPL_SKIP_SRC_UNMAP);
 
diff --git a/drivers/pcmcia/at91_cf.c b/drivers/pcmcia/at91_cf.c
index 1dd68f5..9694c1e 100644
--- a/drivers/pcmcia/at91_cf.c
+++ b/drivers/pcmcia/at91_cf.c
@@ -16,13 +16,13 @@
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/slab.h>
+#include <linux/gpio.h>
 
 #include <pcmcia/ss.h>
 
 #include <mach/hardware.h>
 #include <asm/io.h>
 #include <asm/sizes.h>
-#include <asm/gpio.h>
 
 #include <mach/board.h>
 #include <mach/at91rm9200_mc.h>
@@ -70,7 +70,7 @@
 {
 	struct at91_cf_socket *cf = _cf;
 
-	if (irq == cf->board->det_pin) {
+	if (irq == gpio_to_irq(cf->board->det_pin)) {
 		unsigned present = at91_cf_present(cf);
 
 		/* kick pccard as needed */
@@ -96,8 +96,8 @@
 
 	/* NOTE: CF is always 3VCARD */
 	if (at91_cf_present(cf)) {
-		int rdy	= cf->board->irq_pin;	/* RDY/nIRQ */
-		int vcc	= cf->board->vcc_pin;
+		int rdy	= gpio_is_valid(cf->board->irq_pin);	/* RDY/nIRQ */
+		int vcc	= gpio_is_valid(cf->board->vcc_pin);
 
 		*sp = SS_DETECT | SS_3VCARD;
 		if (!rdy || gpio_get_value(rdy))
@@ -118,7 +118,7 @@
 	cf = container_of(sock, struct at91_cf_socket, socket);
 
 	/* switch Vcc if needed and possible */
-	if (cf->board->vcc_pin) {
+	if (gpio_is_valid(cf->board->vcc_pin)) {
 		switch (s->Vcc) {
 			case 0:
 				gpio_set_value(cf->board->vcc_pin, 0);
@@ -222,7 +222,7 @@
 	struct resource		*io;
 	int			status;
 
-	if (!board || !board->det_pin || !board->rst_pin)
+	if (!board || !gpio_is_valid(board->det_pin) || !gpio_is_valid(board->rst_pin))
 		return -ENODEV;
 
 	io = platform_get_resource(pdev, IORESOURCE_MEM, 0);
@@ -242,7 +242,7 @@
 	status = gpio_request(board->det_pin, "cf_det");
 	if (status < 0)
 		goto fail0;
-	status = request_irq(board->det_pin, at91_cf_irq, 0, driver_name, cf);
+	status = request_irq(gpio_to_irq(board->det_pin), at91_cf_irq, 0, driver_name, cf);
 	if (status < 0)
 		goto fail00;
 	device_init_wakeup(&pdev->dev, 1);
@@ -251,7 +251,7 @@
 	if (status < 0)
 		goto fail0a;
 
-	if (board->vcc_pin) {
+	if (gpio_is_valid(board->vcc_pin)) {
 		status = gpio_request(board->vcc_pin, "cf_vcc");
 		if (status < 0)
 			goto fail0b;
@@ -263,15 +263,15 @@
 	 * unless we report that we handle everything (sigh).
 	 * (Note:  DK board doesn't wire the IRQ pin...)
 	 */
-	if (board->irq_pin) {
+	if (gpio_is_valid(board->irq_pin)) {
 		status = gpio_request(board->irq_pin, "cf_irq");
 		if (status < 0)
 			goto fail0c;
-		status = request_irq(board->irq_pin, at91_cf_irq,
+		status = request_irq(gpio_to_irq(board->irq_pin), at91_cf_irq,
 				IRQF_SHARED, driver_name, cf);
 		if (status < 0)
 			goto fail0d;
-		cf->socket.pci_irq = board->irq_pin;
+		cf->socket.pci_irq = gpio_to_irq(board->irq_pin);
 	} else
 		cf->socket.pci_irq = nr_irqs + 1;
 
@@ -290,7 +290,7 @@
 	}
 
 	pr_info("%s: irqs det #%d, io #%d\n", driver_name,
-		board->det_pin, board->irq_pin);
+		gpio_to_irq(board->det_pin), gpio_to_irq(board->irq_pin));
 
 	cf->socket.owner = THIS_MODULE;
 	cf->socket.dev.parent = &pdev->dev;
@@ -312,19 +312,19 @@
 fail1:
 	if (cf->socket.io_offset)
 		iounmap((void __iomem *) cf->socket.io_offset);
-	if (board->irq_pin) {
-		free_irq(board->irq_pin, cf);
+	if (gpio_is_valid(board->irq_pin)) {
+		free_irq(gpio_to_irq(board->irq_pin), cf);
 fail0d:
 		gpio_free(board->irq_pin);
 	}
 fail0c:
-	if (board->vcc_pin)
+	if (gpio_is_valid(board->vcc_pin))
 		gpio_free(board->vcc_pin);
 fail0b:
 	gpio_free(board->rst_pin);
 fail0a:
 	device_init_wakeup(&pdev->dev, 0);
-	free_irq(board->det_pin, cf);
+	free_irq(gpio_to_irq(board->det_pin), cf);
 fail00:
 	gpio_free(board->det_pin);
 fail0:
@@ -341,15 +341,15 @@
 	pcmcia_unregister_socket(&cf->socket);
 	release_mem_region(io->start, resource_size(io));
 	iounmap((void __iomem *) cf->socket.io_offset);
-	if (board->irq_pin) {
-		free_irq(board->irq_pin, cf);
+	if (gpio_is_valid(board->irq_pin)) {
+		free_irq(gpio_to_irq(board->irq_pin), cf);
 		gpio_free(board->irq_pin);
 	}
-	if (board->vcc_pin)
+	if (gpio_is_valid(board->vcc_pin))
 		gpio_free(board->vcc_pin);
 	gpio_free(board->rst_pin);
 	device_init_wakeup(&pdev->dev, 0);
-	free_irq(board->det_pin, cf);
+	free_irq(gpio_to_irq(board->det_pin), cf);
 	gpio_free(board->det_pin);
 	kfree(cf);
 	return 0;
@@ -363,9 +363,9 @@
 	struct at91_cf_data	*board = cf->board;
 
 	if (device_may_wakeup(&pdev->dev)) {
-		enable_irq_wake(board->det_pin);
-		if (board->irq_pin)
-			enable_irq_wake(board->irq_pin);
+		enable_irq_wake(gpio_to_irq(board->det_pin));
+		if (gpio_is_valid(board->irq_pin))
+			enable_irq_wake(gpio_to_irq(board->irq_pin));
 	}
 	return 0;
 }
@@ -376,9 +376,9 @@
 	struct at91_cf_data	*board = cf->board;
 
 	if (device_may_wakeup(&pdev->dev)) {
-		disable_irq_wake(board->det_pin);
-		if (board->irq_pin)
-			disable_irq_wake(board->irq_pin);
+		disable_irq_wake(gpio_to_irq(board->det_pin));
+		if (gpio_is_valid(board->irq_pin))
+			disable_irq_wake(gpio_to_irq(board->irq_pin));
 	}
 
 	return 0;
diff --git a/drivers/pcmcia/bcm63xx_pcmcia.c b/drivers/pcmcia/bcm63xx_pcmcia.c
index 693577e..c2e997a 100644
--- a/drivers/pcmcia/bcm63xx_pcmcia.c
+++ b/drivers/pcmcia/bcm63xx_pcmcia.c
@@ -475,7 +475,7 @@
 	bcm63xx_cb_dev = NULL;
 }
 
-static struct pci_device_id bcm63xx_cb_table[] = {
+static DEFINE_PCI_DEVICE_TABLE(bcm63xx_cb_table) = {
 	{
 		.vendor		= PCI_VENDOR_ID_BROADCOM,
 		.device		= BCM6348_CPU_ID,
diff --git a/drivers/pcmcia/bfin_cf_pcmcia.c b/drivers/pcmcia/bfin_cf_pcmcia.c
index 4922139..ac1a223 100644
--- a/drivers/pcmcia/bfin_cf_pcmcia.c
+++ b/drivers/pcmcia/bfin_cf_pcmcia.c
@@ -310,18 +310,7 @@
 	.remove = __devexit_p(bfin_cf_remove),
 };
 
-static int __init bfin_cf_init(void)
-{
-	return platform_driver_register(&bfin_cf_driver);
-}
-
-static void __exit bfin_cf_exit(void)
-{
-	platform_driver_unregister(&bfin_cf_driver);
-}
-
-module_init(bfin_cf_init);
-module_exit(bfin_cf_exit);
+module_platform_driver(bfin_cf_driver);
 
 MODULE_AUTHOR("Michael Hennerich <hennerich@blackfin.uclinux.org>");
 MODULE_DESCRIPTION("BFIN CF/PCMCIA Driver");
diff --git a/drivers/pcmcia/db1xxx_ss.c b/drivers/pcmcia/db1xxx_ss.c
index 5b7c227..a484b1f 100644
--- a/drivers/pcmcia/db1xxx_ss.c
+++ b/drivers/pcmcia/db1xxx_ss.c
@@ -172,12 +172,12 @@
 	if ((sock->board_type == BOARD_TYPE_DB1200) ||
 	    (sock->board_type == BOARD_TYPE_DB1300)) {
 		ret = request_irq(sock->insert_irq, db1200_pcmcia_cdirq,
-				  IRQF_DISABLED, "pcmcia_insert", sock);
+				  0, "pcmcia_insert", sock);
 		if (ret)
 			goto out1;
 
 		ret = request_irq(sock->eject_irq, db1200_pcmcia_cdirq,
-				  IRQF_DISABLED, "pcmcia_eject", sock);
+				  0, "pcmcia_eject", sock);
 		if (ret) {
 			free_irq(sock->insert_irq, sock);
 			goto out1;
@@ -580,18 +580,7 @@
 	.remove		= __devexit_p(db1x_pcmcia_socket_remove),
 };
 
-int __init db1x_pcmcia_socket_load(void)
-{
-	return platform_driver_register(&db1x_pcmcia_socket_driver);
-}
-
-void  __exit db1x_pcmcia_socket_unload(void)
-{
-	platform_driver_unregister(&db1x_pcmcia_socket_driver);
-}
-
-module_init(db1x_pcmcia_socket_load);
-module_exit(db1x_pcmcia_socket_unload);
+module_platform_driver(db1x_pcmcia_socket_driver);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("PCMCIA Socket Services for Alchemy Db/Pb1x00 boards");
diff --git a/drivers/pcmcia/electra_cf.c b/drivers/pcmcia/electra_cf.c
index 06ad3e5..7647d23 100644
--- a/drivers/pcmcia/electra_cf.c
+++ b/drivers/pcmcia/electra_cf.c
@@ -365,17 +365,7 @@
 	.remove   = electra_cf_remove,
 };
 
-static int __init electra_cf_init(void)
-{
-	return platform_driver_register(&electra_cf_driver);
-}
-module_init(electra_cf_init);
-
-static void __exit electra_cf_exit(void)
-{
-	platform_driver_unregister(&electra_cf_driver);
-}
-module_exit(electra_cf_exit);
+module_platform_driver(electra_cf_driver);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR ("Olof Johansson <olof@lixom.net>");
diff --git a/drivers/pcmcia/i82092.c b/drivers/pcmcia/i82092.c
index 0b66bfc..4e8831b 100644
--- a/drivers/pcmcia/i82092.c
+++ b/drivers/pcmcia/i82092.c
@@ -25,14 +25,9 @@
 MODULE_LICENSE("GPL");
 
 /* PCI core routines */
-static struct pci_device_id i82092aa_pci_ids[] = {
-	{
-	      .vendor = PCI_VENDOR_ID_INTEL,
-	      .device = PCI_DEVICE_ID_INTEL_82092AA_0,
-	      .subvendor = PCI_ANY_ID,
-	      .subdevice = PCI_ANY_ID,
-	 },
-	 {} 
+static DEFINE_PCI_DEVICE_TABLE(i82092aa_pci_ids) = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82092AA_0) },
+	{ }
 };
 MODULE_DEVICE_TABLE(pci, i82092aa_pci_ids);
 
diff --git a/drivers/pcmcia/m8xx_pcmcia.c b/drivers/pcmcia/m8xx_pcmcia.c
index a317def..a3a851e 100644
--- a/drivers/pcmcia/m8xx_pcmcia.c
+++ b/drivers/pcmcia/m8xx_pcmcia.c
@@ -1303,15 +1303,4 @@
 	.remove = m8xx_remove,
 };
 
-static int __init m8xx_init(void)
-{
-	return platform_driver_register(&m8xx_pcmcia_driver);
-}
-
-static void __exit m8xx_exit(void)
-{
-	platform_driver_unregister(&m8xx_pcmcia_driver);
-}
-
-module_init(m8xx_init);
-module_exit(m8xx_exit);
+module_platform_driver(m8xx_pcmcia_driver);
diff --git a/drivers/pcmcia/pd6729.c b/drivers/pcmcia/pd6729.c
index 0f8b70b..253e386 100644
--- a/drivers/pcmcia/pd6729.c
+++ b/drivers/pcmcia/pd6729.c
@@ -762,13 +762,8 @@
 	kfree(socket);
 }
 
-static struct pci_device_id pd6729_pci_ids[] = {
-	{
-		.vendor		= PCI_VENDOR_ID_CIRRUS,
-		.device		= PCI_DEVICE_ID_CIRRUS_6729,
-		.subvendor	= PCI_ANY_ID,
-		.subdevice	= PCI_ANY_ID,
-	},
+static DEFINE_PCI_DEVICE_TABLE(pd6729_pci_ids) = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_CIRRUS, PCI_DEVICE_ID_CIRRUS_6729) },
 	{ }
 };
 MODULE_DEVICE_TABLE(pci, pd6729_pci_ids);
diff --git a/drivers/pcmcia/pxa2xx_viper.c b/drivers/pcmcia/pxa2xx_viper.c
index adfae49..cb0c37e 100644
--- a/drivers/pcmcia/pxa2xx_viper.c
+++ b/drivers/pcmcia/pxa2xx_viper.c
@@ -177,18 +177,7 @@
 	.id_table	= viper_pcmcia_id_table,
 };
 
-static int __init viper_pcmcia_init(void)
-{
-	return platform_driver_register(&viper_pcmcia_driver);
-}
-
-static void __exit viper_pcmcia_exit(void)
-{
-	return platform_driver_unregister(&viper_pcmcia_driver);
-}
-
-module_init(viper_pcmcia_init);
-module_exit(viper_pcmcia_exit);
+module_platform_driver(viper_pcmcia_driver);
 
 MODULE_DEVICE_TABLE(platform, viper_pcmcia_id_table);
 MODULE_LICENSE("GPL");
diff --git a/drivers/pcmcia/vrc4173_cardu.c b/drivers/pcmcia/vrc4173_cardu.c
index c6d36b3..cd0a315 100644
--- a/drivers/pcmcia/vrc4173_cardu.c
+++ b/drivers/pcmcia/vrc4173_cardu.c
@@ -563,11 +563,8 @@
 
 __setup("vrc4173_cardu=", vrc4173_cardu_setup);
 
-static struct pci_device_id vrc4173_cardu_id_table[] __devinitdata = {
-	{	.vendor		= PCI_VENDOR_ID_NEC,
-		.device		= PCI_DEVICE_ID_NEC_NAPCCARD,
-		.subvendor	= PCI_ANY_ID,
-		.subdevice	= PCI_ANY_ID, },
+static DEFINE_PCI_DEVICE_TABLE(vrc4173_cardu_id_table) = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_NEC, PCI_DEVICE_ID_NEC_NAPCCARD) },
         {0, }
 };
 
diff --git a/drivers/pcmcia/xxs1500_ss.c b/drivers/pcmcia/xxs1500_ss.c
index 8f66980..fd5fbd1 100644
--- a/drivers/pcmcia/xxs1500_ss.c
+++ b/drivers/pcmcia/xxs1500_ss.c
@@ -320,18 +320,7 @@
 	.remove		= __devexit_p(xxs1500_pcmcia_remove),
 };
 
-int __init xxs1500_pcmcia_socket_load(void)
-{
-	return platform_driver_register(&xxs1500_pcmcia_socket_driver);
-}
-
-void  __exit xxs1500_pcmcia_socket_unload(void)
-{
-	platform_driver_unregister(&xxs1500_pcmcia_socket_driver);
-}
-
-module_init(xxs1500_pcmcia_socket_load);
-module_exit(xxs1500_pcmcia_socket_unload);
+module_platform_driver(xxs1500_pcmcia_socket_driver);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("PCMCIA Socket Services for MyCable XXS1500 systems");
diff --git a/drivers/pcmcia/yenta_socket.c b/drivers/pcmcia/yenta_socket.c
index 849c0c1..d07f9ac 100644
--- a/drivers/pcmcia/yenta_socket.c
+++ b/drivers/pcmcia/yenta_socket.c
@@ -1352,7 +1352,7 @@
 		.driver_data	= CARDBUS_TYPE_##type,	\
 	}
 
-static struct pci_device_id yenta_table[] = {
+static DEFINE_PCI_DEVICE_TABLE(yenta_table) = {
 	CB_ID(PCI_VENDOR_ID_TI, PCI_DEVICE_ID_TI_1031, TI),
 
 	/*
diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c
index dc87eda..eb415bd 100644
--- a/drivers/rtc/interface.c
+++ b/drivers/rtc/interface.c
@@ -458,6 +458,11 @@
 	if (rtc->uie_rtctimer.enabled == enabled)
 		goto out;
 
+	if (rtc->uie_unsupported) {
+		err = -EINVAL;
+		goto out;
+	}
+
 	if (enabled) {
 		struct rtc_time tm;
 		ktime_t now, onesec;
diff --git a/drivers/rtc/rtc-mpc5121.c b/drivers/rtc/rtc-mpc5121.c
index e954a75..42f5f82 100644
--- a/drivers/rtc/rtc-mpc5121.c
+++ b/drivers/rtc/rtc-mpc5121.c
@@ -360,6 +360,8 @@
 						&mpc5200_rtc_ops, THIS_MODULE);
 	}
 
+	rtc->rtc->uie_unsupported = 1;
+
 	if (IS_ERR(rtc->rtc)) {
 		err = PTR_ERR(rtc->rtc);
 		goto out_free_irq;
diff --git a/drivers/rtc/rtc-sa1100.c b/drivers/rtc/rtc-sa1100.c
index 4940fa8..50a5c4a 100644
--- a/drivers/rtc/rtc-sa1100.c
+++ b/drivers/rtc/rtc-sa1100.c
@@ -33,6 +33,7 @@
 #include <linux/of.h>
 #include <linux/pm.h>
 #include <linux/bitops.h>
+#include <linux/io.h>
 
 #include <mach/hardware.h>
 #include <mach/irqs.h>
diff --git a/drivers/sh/intc/balancing.c b/drivers/sh/intc/balancing.c
index cec7a96..bc78080 100644
--- a/drivers/sh/intc/balancing.c
+++ b/drivers/sh/intc/balancing.c
@@ -9,7 +9,7 @@
  */
 #include "internals.h"
 
-static unsigned long dist_handle[NR_IRQS];
+static unsigned long dist_handle[INTC_NR_IRQS];
 
 void intc_balancing_enable(unsigned int irq)
 {
diff --git a/drivers/sh/intc/core.c b/drivers/sh/intc/core.c
index e53e449..2fde897 100644
--- a/drivers/sh/intc/core.c
+++ b/drivers/sh/intc/core.c
@@ -42,7 +42,7 @@
  * - this needs to be at least 2 for 5-bit priorities on 7780
  */
 static unsigned int default_prio_level = 2;	/* 2 - 16 */
-static unsigned int intc_prio_level[NR_IRQS];	/* for now */
+static unsigned int intc_prio_level[INTC_NR_IRQS];	/* for now */
 
 unsigned int intc_get_dfl_prio_level(void)
 {
diff --git a/drivers/sh/intc/handle.c b/drivers/sh/intc/handle.c
index 057ce56..f461d53 100644
--- a/drivers/sh/intc/handle.c
+++ b/drivers/sh/intc/handle.c
@@ -13,7 +13,7 @@
 #include <linux/spinlock.h>
 #include "internals.h"
 
-static unsigned long ack_handle[NR_IRQS];
+static unsigned long ack_handle[INTC_NR_IRQS];
 
 static intc_enum __init intc_grp_id(struct intc_desc *desc,
 				    intc_enum enum_id)
diff --git a/drivers/sh/intc/virq.c b/drivers/sh/intc/virq.c
index c7ec49f..93cec21 100644
--- a/drivers/sh/intc/virq.c
+++ b/drivers/sh/intc/virq.c
@@ -17,7 +17,7 @@
 #include <linux/export.h>
 #include "internals.h"
 
-static struct intc_map_entry intc_irq_xlate[NR_IRQS];
+static struct intc_map_entry intc_irq_xlate[INTC_NR_IRQS];
 
 struct intc_virq_list {
 	unsigned int irq;
diff --git a/drivers/spi/spi-dw-mid.c b/drivers/spi/spi-dw-mid.c
index 8418eb0..b9f0192 100644
--- a/drivers/spi/spi-dw-mid.c
+++ b/drivers/spi/spi-dw-mid.c
@@ -22,6 +22,7 @@
 #include <linux/interrupt.h>
 #include <linux/slab.h>
 #include <linux/spi/spi.h>
+#include <linux/types.h>
 
 #include "spi-dw.h"
 
@@ -136,6 +137,7 @@
 	txconf.dst_maxburst = LNW_DMA_MSIZE_16;
 	txconf.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
 	txconf.dst_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES;
+	txconf.device_fc = false;
 
 	txchan->device->device_control(txchan, DMA_SLAVE_CONFIG,
 				       (unsigned long) &txconf);
@@ -144,7 +146,7 @@
 	dws->tx_sgl.dma_address = dws->tx_dma;
 	dws->tx_sgl.length = dws->len;
 
-	txdesc = txchan->device->device_prep_slave_sg(txchan,
+	txdesc = dmaengine_prep_slave_sg(txchan,
 				&dws->tx_sgl,
 				1,
 				DMA_MEM_TO_DEV,
@@ -158,6 +160,7 @@
 	rxconf.src_maxburst = LNW_DMA_MSIZE_16;
 	rxconf.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
 	rxconf.src_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES;
+	rxconf.device_fc = false;
 
 	rxchan->device->device_control(rxchan, DMA_SLAVE_CONFIG,
 				       (unsigned long) &rxconf);
@@ -166,7 +169,7 @@
 	dws->rx_sgl.dma_address = dws->rx_dma;
 	dws->rx_sgl.length = dws->len;
 
-	rxdesc = rxchan->device->device_prep_slave_sg(rxchan,
+	rxdesc = dmaengine_prep_slave_sg(rxchan,
 				&dws->rx_sgl,
 				1,
 				DMA_DEV_TO_MEM,
diff --git a/drivers/spi/spi-ep93xx.c b/drivers/spi/spi-ep93xx.c
index d46e55c..6db2887 100644
--- a/drivers/spi/spi-ep93xx.c
+++ b/drivers/spi/spi-ep93xx.c
@@ -633,8 +633,8 @@
 	if (!nents)
 		return ERR_PTR(-ENOMEM);
 
-	txd = chan->device->device_prep_slave_sg(chan, sgt->sgl, nents,
-						 slave_dirn, DMA_CTRL_ACK);
+	txd = dmaengine_prep_slave_sg(chan, sgt->sgl, nents,
+					slave_dirn, DMA_CTRL_ACK);
 	if (!txd) {
 		dma_unmap_sg(chan->device->dev, sgt->sgl, sgt->nents, dir);
 		return ERR_PTR(-ENOMEM);
diff --git a/drivers/spi/spi-pl022.c b/drivers/spi/spi-pl022.c
index dc8485d..96f0da6 100644
--- a/drivers/spi/spi-pl022.c
+++ b/drivers/spi/spi-pl022.c
@@ -880,10 +880,12 @@
 	struct dma_slave_config rx_conf = {
 		.src_addr = SSP_DR(pl022->phybase),
 		.direction = DMA_DEV_TO_MEM,
+		.device_fc = false,
 	};
 	struct dma_slave_config tx_conf = {
 		.dst_addr = SSP_DR(pl022->phybase),
 		.direction = DMA_MEM_TO_DEV,
+		.device_fc = false,
 	};
 	unsigned int pages;
 	int ret;
@@ -1017,7 +1019,7 @@
 		goto err_tx_sgmap;
 
 	/* Send both scatterlists */
-	rxdesc = rxchan->device->device_prep_slave_sg(rxchan,
+	rxdesc = dmaengine_prep_slave_sg(rxchan,
 				      pl022->sgt_rx.sgl,
 				      rx_sglen,
 				      DMA_DEV_TO_MEM,
@@ -1025,7 +1027,7 @@
 	if (!rxdesc)
 		goto err_rxdesc;
 
-	txdesc = txchan->device->device_prep_slave_sg(txchan,
+	txdesc = dmaengine_prep_slave_sg(txchan,
 				      pl022->sgt_tx.sgl,
 				      tx_sglen,
 				      DMA_MEM_TO_DEV,
diff --git a/drivers/spi/spi-topcliff-pch.c b/drivers/spi/spi-topcliff-pch.c
index 5c6fa5e..ec47d3b 100644
--- a/drivers/spi/spi-topcliff-pch.c
+++ b/drivers/spi/spi-topcliff-pch.c
@@ -1099,7 +1099,7 @@
 		sg_dma_address(sg) = dma->rx_buf_dma + sg->offset;
 	}
 	sg = dma->sg_rx_p;
-	desc_rx = dma->chan_rx->device->device_prep_slave_sg(dma->chan_rx, sg,
+	desc_rx = dmaengine_prep_slave_sg(dma->chan_rx, sg,
 					num, DMA_DEV_TO_MEM,
 					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	if (!desc_rx) {
@@ -1158,7 +1158,7 @@
 		sg_dma_address(sg) = dma->tx_buf_dma + sg->offset;
 	}
 	sg = dma->sg_tx_p;
-	desc_tx = dma->chan_tx->device->device_prep_slave_sg(dma->chan_tx,
+	desc_tx = dmaengine_prep_slave_sg(dma->chan_tx,
 					sg, num, DMA_MEM_TO_DEV,
 					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	if (!desc_tx) {
diff --git a/drivers/staging/android/binder.c b/drivers/staging/android/binder.c
index 59e0953..c283212 100644
--- a/drivers/staging/android/binder.c
+++ b/drivers/staging/android/binder.c
@@ -381,8 +381,7 @@
 
 repeat:
 	fdt = files_fdtable(files);
-	fd = find_next_zero_bit(fdt->open_fds->fds_bits, fdt->max_fds,
-				files->next_fd);
+	fd = find_next_zero_bit(fdt->open_fds, fdt->max_fds, files->next_fd);
 
 	/*
 	 * N.B. For clone tasks sharing a files structure, this test
@@ -410,11 +409,11 @@
 		goto repeat;
 	}
 
-	FD_SET(fd, fdt->open_fds);
+	__set_open_fd(fd, fdt);
 	if (flags & O_CLOEXEC)
-		FD_SET(fd, fdt->close_on_exec);
+		__set_close_on_exec(fd, fdt);
 	else
-		FD_CLR(fd, fdt->close_on_exec);
+		__clear_close_on_exec(fd, fdt);
 	files->next_fd = fd + 1;
 #if 1
 	/* Sanity check */
@@ -455,7 +454,7 @@
 static void __put_unused_fd(struct files_struct *files, unsigned int fd)
 {
 	struct fdtable *fdt = files_fdtable(files);
-	__FD_CLR(fd, fdt->open_fds);
+	__clear_open_fd(fd, fdt);
 	if (fd < files->next_fd)
 		files->next_fd = fd;
 }
@@ -481,7 +480,7 @@
 	if (!filp)
 		goto out_unlock;
 	rcu_assign_pointer(fdt->fd[fd], NULL);
-	FD_CLR(fd, fdt->close_on_exec);
+	__clear_close_on_exec(fd, fdt);
 	__put_unused_fd(files, fd);
 	spin_unlock(&files->file_lock);
 	retval = filp_close(filp, files);
diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c
index 20d795d..0c65c9e 100644
--- a/drivers/tty/serial/amba-pl011.c
+++ b/drivers/tty/serial/amba-pl011.c
@@ -51,6 +51,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/scatterlist.h>
 #include <linux/delay.h>
+#include <linux/types.h>
 
 #include <asm/io.h>
 #include <asm/sizes.h>
@@ -271,6 +272,7 @@
 		.dst_addr_width = DMA_SLAVE_BUSWIDTH_1_BYTE,
 		.direction = DMA_MEM_TO_DEV,
 		.dst_maxburst = uap->fifosize >> 1,
+		.device_fc = false,
 	};
 	struct dma_chan *chan;
 	dma_cap_mask_t mask;
@@ -304,6 +306,7 @@
 			.src_addr_width = DMA_SLAVE_BUSWIDTH_1_BYTE,
 			.direction = DMA_DEV_TO_MEM,
 			.src_maxburst = uap->fifosize >> 1,
+			.device_fc = false,
 		};
 
 		chan = dma_request_channel(mask, plat->dma_filter, plat->dma_rx_param);
@@ -481,7 +484,7 @@
 		return -EBUSY;
 	}
 
-	desc = dma_dev->device_prep_slave_sg(chan, &dmatx->sg, 1, DMA_MEM_TO_DEV,
+	desc = dmaengine_prep_slave_sg(chan, &dmatx->sg, 1, DMA_MEM_TO_DEV,
 					     DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	if (!desc) {
 		dma_unmap_sg(dma_dev->dev, &dmatx->sg, 1, DMA_TO_DEVICE);
@@ -664,7 +667,6 @@
 static int pl011_dma_rx_trigger_dma(struct uart_amba_port *uap)
 {
 	struct dma_chan *rxchan = uap->dmarx.chan;
-	struct dma_device *dma_dev;
 	struct pl011_dmarx_data *dmarx = &uap->dmarx;
 	struct dma_async_tx_descriptor *desc;
 	struct pl011_sgbuf *sgbuf;
@@ -675,8 +677,7 @@
 	/* Start the RX DMA job */
 	sgbuf = uap->dmarx.use_buf_b ?
 		&uap->dmarx.sgbuf_b : &uap->dmarx.sgbuf_a;
-	dma_dev = rxchan->device;
-	desc = rxchan->device->device_prep_slave_sg(rxchan, &sgbuf->sg, 1,
+	desc = dmaengine_prep_slave_sg(rxchan, &sgbuf->sg, 1,
 					DMA_DEV_TO_MEM,
 					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	/*
diff --git a/drivers/tty/serial/pch_uart.c b/drivers/tty/serial/pch_uart.c
index 332f2eb..e825460 100644
--- a/drivers/tty/serial/pch_uart.c
+++ b/drivers/tty/serial/pch_uart.c
@@ -844,7 +844,7 @@
 
 	sg_dma_address(sg) = priv->rx_buf_dma;
 
-	desc = priv->chan_rx->device->device_prep_slave_sg(priv->chan_rx,
+	desc = dmaengine_prep_slave_sg(priv->chan_rx,
 			sg, 1, DMA_DEV_TO_MEM,
 			DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 
@@ -1003,7 +1003,7 @@
 			sg_dma_len(sg) = size;
 	}
 
-	desc = priv->chan_tx->device->device_prep_slave_sg(priv->chan_tx,
+	desc = dmaengine_prep_slave_sg(priv->chan_tx,
 					priv->sg_tx_p, nent, DMA_MEM_TO_DEV,
 					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	if (!desc) {
diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c
index 61b7fd2..f8db8a7 100644
--- a/drivers/tty/serial/sh-sci.c
+++ b/drivers/tty/serial/sh-sci.c
@@ -1338,7 +1338,7 @@
 		struct scatterlist *sg = &s->sg_rx[i];
 		struct dma_async_tx_descriptor *desc;
 
-		desc = chan->device->device_prep_slave_sg(chan,
+		desc = dmaengine_prep_slave_sg(chan,
 			sg, 1, DMA_DEV_TO_MEM, DMA_PREP_INTERRUPT);
 
 		if (desc) {
@@ -1453,7 +1453,7 @@
 
 	BUG_ON(!sg_dma_len(sg));
 
-	desc = chan->device->device_prep_slave_sg(chan,
+	desc = dmaengine_prep_slave_sg(chan,
 			sg, s->sg_len_tx, DMA_MEM_TO_DEV,
 			DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	if (!desc) {
diff --git a/drivers/usb/musb/ux500_dma.c b/drivers/usb/musb/ux500_dma.c
index 97cb459..d05c7fb 100644
--- a/drivers/usb/musb/ux500_dma.c
+++ b/drivers/usb/musb/ux500_dma.c
@@ -115,12 +115,12 @@
 	slave_conf.dst_addr = usb_fifo_addr;
 	slave_conf.dst_addr_width = addr_width;
 	slave_conf.dst_maxburst = 16;
+	slave_conf.device_fc = false;
 
 	dma_chan->device->device_control(dma_chan, DMA_SLAVE_CONFIG,
 					     (unsigned long) &slave_conf);
 
-	dma_desc = dma_chan->device->
-			device_prep_slave_sg(dma_chan, &sg, 1, direction,
+	dma_desc = dmaengine_prep_slave_sg(dma_chan, &sg, 1, direction,
 					     DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	if (!dma_desc)
 		return false;
diff --git a/drivers/usb/renesas_usbhs/fifo.c b/drivers/usb/renesas_usbhs/fifo.c
index 3648c82..6ec7f83 100644
--- a/drivers/usb/renesas_usbhs/fifo.c
+++ b/drivers/usb/renesas_usbhs/fifo.c
@@ -786,9 +786,8 @@
 	sg_dma_address(&sg) = pkt->dma + pkt->actual;
 	sg_dma_len(&sg) = pkt->trans;
 
-	desc = chan->device->device_prep_slave_sg(chan, &sg, 1, dir,
-						  DMA_PREP_INTERRUPT |
-						  DMA_CTRL_ACK);
+	desc = dmaengine_prep_slave_sg(chan, &sg, 1, dir,
+					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	if (!desc)
 		return;
 
diff --git a/drivers/video/mx3fb.c b/drivers/video/mx3fb.c
index 727a514..eec0d7b 100644
--- a/drivers/video/mx3fb.c
+++ b/drivers/video/mx3fb.c
@@ -337,7 +337,7 @@
 
 	/* This enables the channel */
 	if (mx3_fbi->cookie < 0) {
-		mx3_fbi->txd = dma_chan->device->device_prep_slave_sg(dma_chan,
+		mx3_fbi->txd = dmaengine_prep_slave_sg(dma_chan,
 		      &mx3_fbi->sg[0], 1, DMA_MEM_TO_DEV, DMA_PREP_INTERRUPT);
 		if (!mx3_fbi->txd) {
 			dev_err(mx3fb->dev, "Cannot allocate descriptor on %d\n",
@@ -1091,7 +1091,7 @@
 	if (mx3_fbi->txd)
 		async_tx_ack(mx3_fbi->txd);
 
-	txd = dma_chan->device->device_prep_slave_sg(dma_chan, sg +
+	txd = dmaengine_prep_slave_sg(dma_chan, sg +
 		mx3_fbi->cur_ipu_buf, 1, DMA_MEM_TO_DEV, DMA_PREP_INTERRUPT);
 	if (!txd) {
 		dev_err(fbi->device,
diff --git a/drivers/video/omap2/vrfb.c b/drivers/video/omap2/vrfb.c
index fd22716..4e5b960 100644
--- a/drivers/video/omap2/vrfb.c
+++ b/drivers/video/omap2/vrfb.c
@@ -27,7 +27,6 @@
 #include <linux/bitops.h>
 #include <linux/mutex.h>
 
-#include <mach/io.h>
 #include <plat/vrfb.h>
 #include <plat/sdrc.h>
 
diff --git a/drivers/watchdog/sa1100_wdt.c b/drivers/watchdog/sa1100_wdt.c
index d54e04d..54984de 100644
--- a/drivers/watchdog/sa1100_wdt.c
+++ b/drivers/watchdog/sa1100_wdt.c
@@ -28,6 +28,7 @@
 #include <linux/miscdevice.h>
 #include <linux/watchdog.h>
 #include <linux/init.h>
+#include <linux/io.h>
 #include <linux/bitops.h>
 #include <linux/uaccess.h>
 #include <linux/timex.h>
diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c
index 85f1fcd..9dacb85 100644
--- a/fs/autofs4/dev-ioctl.c
+++ b/fs/autofs4/dev-ioctl.c
@@ -230,7 +230,7 @@
 	fdt = files_fdtable(files);
 	BUG_ON(fdt->fd[fd] != NULL);
 	rcu_assign_pointer(fdt->fd[fd], file);
-	FD_SET(fd, fdt->close_on_exec);
+	__set_close_on_exec(fd, fdt);
 	spin_unlock(&files->file_lock);
 }
 
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 7d7ff20..48ffb3d 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1415,6 +1415,22 @@
 		regset->writeback(task, regset, 1);
 }
 
+#ifndef PR_REG_SIZE
+#define PR_REG_SIZE(S) sizeof(S)
+#endif
+
+#ifndef PRSTATUS_SIZE
+#define PRSTATUS_SIZE(S) sizeof(S)
+#endif
+
+#ifndef PR_REG_PTR
+#define PR_REG_PTR(S) (&((S)->pr_reg))
+#endif
+
+#ifndef SET_PR_FPVALID
+#define SET_PR_FPVALID(S, V) ((S)->pr_fpvalid = (V))
+#endif
+
 static int fill_thread_core_info(struct elf_thread_core_info *t,
 				 const struct user_regset_view *view,
 				 long signr, size_t *total)
@@ -1429,11 +1445,11 @@
 	 */
 	fill_prstatus(&t->prstatus, t->task, signr);
 	(void) view->regsets[0].get(t->task, &view->regsets[0],
-				    0, sizeof(t->prstatus.pr_reg),
-				    &t->prstatus.pr_reg, NULL);
+				    0, PR_REG_SIZE(t->prstatus.pr_reg),
+				    PR_REG_PTR(&t->prstatus), NULL);
 
 	fill_note(&t->notes[0], "CORE", NT_PRSTATUS,
-		  sizeof(t->prstatus), &t->prstatus);
+		  PRSTATUS_SIZE(t->prstatus), &t->prstatus);
 	*total += notesize(&t->notes[0]);
 
 	do_thread_regset_writeback(t->task, &view->regsets[0]);
@@ -1463,7 +1479,7 @@
 						  regset->core_note_type,
 						  size, data);
 				else {
-					t->prstatus.pr_fpvalid = 1;
+					SET_PR_FPVALID(&t->prstatus, 1);
 					fill_note(&t->notes[i], "CORE",
 						  NT_PRFPREG, size, data);
 				}
diff --git a/fs/compat.c b/fs/compat.c
index 14483a7..f2944ac 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -1170,10 +1170,9 @@
 }
 
 asmlinkage ssize_t
-compat_sys_preadv(unsigned long fd, const struct compat_iovec __user *vec,
-		  unsigned long vlen, u32 pos_low, u32 pos_high)
+compat_sys_preadv64(unsigned long fd, const struct compat_iovec __user *vec,
+		    unsigned long vlen, loff_t pos)
 {
-	loff_t pos = ((loff_t)pos_high << 32) | pos_low;
 	struct file *file;
 	int fput_needed;
 	ssize_t ret;
@@ -1190,6 +1189,14 @@
 	return ret;
 }
 
+asmlinkage ssize_t
+compat_sys_preadv(unsigned long fd, const struct compat_iovec __user *vec,
+		  unsigned long vlen, u32 pos_low, u32 pos_high)
+{
+	loff_t pos = ((loff_t)pos_high << 32) | pos_low;
+	return compat_sys_preadv64(fd, vec, vlen, pos);
+}
+
 static size_t compat_writev(struct file *file,
 			    const struct compat_iovec __user *vec,
 			    unsigned long vlen, loff_t *pos)
@@ -1229,10 +1236,9 @@
 }
 
 asmlinkage ssize_t
-compat_sys_pwritev(unsigned long fd, const struct compat_iovec __user *vec,
-		   unsigned long vlen, u32 pos_low, u32 pos_high)
+compat_sys_pwritev64(unsigned long fd, const struct compat_iovec __user *vec,
+		     unsigned long vlen, loff_t pos)
 {
-	loff_t pos = ((loff_t)pos_high << 32) | pos_low;
 	struct file *file;
 	int fput_needed;
 	ssize_t ret;
@@ -1249,6 +1255,14 @@
 	return ret;
 }
 
+asmlinkage ssize_t
+compat_sys_pwritev(unsigned long fd, const struct compat_iovec __user *vec,
+		   unsigned long vlen, u32 pos_low, u32 pos_high)
+{
+	loff_t pos = ((loff_t)pos_high << 32) | pos_low;
+	return compat_sys_pwritev64(fd, vec, vlen, pos);
+}
+
 asmlinkage long
 compat_sys_vmsplice(int fd, const struct compat_iovec __user *iov32,
 		    unsigned int nr_segs, unsigned int flags)
diff --git a/fs/exec.c b/fs/exec.c
index c8b63d1..9a1d9f0 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1028,10 +1028,10 @@
 		fdt = files_fdtable(files);
 		if (i >= fdt->max_fds)
 			break;
-		set = fdt->close_on_exec->fds_bits[j];
+		set = fdt->close_on_exec[j];
 		if (!set)
 			continue;
-		fdt->close_on_exec->fds_bits[j] = 0;
+		fdt->close_on_exec[j] = 0;
 		spin_unlock(&files->file_lock);
 		for ( ; set ; i++,set >>= 1) {
 			if (set & 1) {
@@ -2067,8 +2067,8 @@
 	fd_install(0, rp);
 	spin_lock(&cf->file_lock);
 	fdt = files_fdtable(cf);
-	FD_SET(0, fdt->open_fds);
-	FD_CLR(0, fdt->close_on_exec);
+	__set_open_fd(0, fdt);
+	__clear_close_on_exec(0, fdt);
 	spin_unlock(&cf->file_lock);
 
 	/* and disallow core files too */
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index ad56866..b867862 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -32,24 +32,8 @@
 	DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK
 };
 
-static int ext4_readdir(struct file *, void *, filldir_t);
 static int ext4_dx_readdir(struct file *filp,
 			   void *dirent, filldir_t filldir);
-static int ext4_release_dir(struct inode *inode,
-				struct file *filp);
-
-const struct file_operations ext4_dir_operations = {
-	.llseek		= ext4_llseek,
-	.read		= generic_read_dir,
-	.readdir	= ext4_readdir,		/* we take BKL. needed?*/
-	.unlocked_ioctl = ext4_ioctl,
-#ifdef CONFIG_COMPAT
-	.compat_ioctl	= ext4_compat_ioctl,
-#endif
-	.fsync		= ext4_sync_file,
-	.release	= ext4_release_dir,
-};
-
 
 static unsigned char get_dtype(struct super_block *sb, int filetype)
 {
@@ -60,6 +44,26 @@
 	return (ext4_filetype_table[filetype]);
 }
 
+/**
+ * Check if the given dir-inode refers to an htree-indexed directory
+ * (or a directory which chould potentially get coverted to use htree
+ * indexing).
+ *
+ * Return 1 if it is a dx dir, 0 if not
+ */
+static int is_dx_dir(struct inode *inode)
+{
+	struct super_block *sb = inode->i_sb;
+
+	if (EXT4_HAS_COMPAT_FEATURE(inode->i_sb,
+		     EXT4_FEATURE_COMPAT_DIR_INDEX) &&
+	    ((ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) ||
+	     ((inode->i_size >> sb->s_blocksize_bits) == 1)))
+		return 1;
+
+	return 0;
+}
+
 /*
  * Return 0 if the directory entry is OK, and 1 if there is a problem
  *
@@ -115,18 +119,13 @@
 	unsigned int offset;
 	int i, stored;
 	struct ext4_dir_entry_2 *de;
-	struct super_block *sb;
 	int err;
 	struct inode *inode = filp->f_path.dentry->d_inode;
+	struct super_block *sb = inode->i_sb;
 	int ret = 0;
 	int dir_has_error = 0;
 
-	sb = inode->i_sb;
-
-	if (EXT4_HAS_COMPAT_FEATURE(inode->i_sb,
-				    EXT4_FEATURE_COMPAT_DIR_INDEX) &&
-	    ((ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) ||
-	     ((inode->i_size >> sb->s_blocksize_bits) == 1))) {
+	if (is_dx_dir(inode)) {
 		err = ext4_dx_readdir(filp, dirent, filldir);
 		if (err != ERR_BAD_DX_DIR) {
 			ret = err;
@@ -254,22 +253,134 @@
 	return ret;
 }
 
+static inline int is_32bit_api(void)
+{
+#ifdef CONFIG_COMPAT
+	return is_compat_task();
+#else
+	return (BITS_PER_LONG == 32);
+#endif
+}
+
 /*
  * These functions convert from the major/minor hash to an f_pos
- * value.
+ * value for dx directories
  *
- * Currently we only use major hash numer.  This is unfortunate, but
- * on 32-bit machines, the same VFS interface is used for lseek and
- * llseek, so if we use the 64 bit offset, then the 32-bit versions of
- * lseek/telldir/seekdir will blow out spectacularly, and from within
- * the ext2 low-level routine, we don't know if we're being called by
- * a 64-bit version of the system call or the 32-bit version of the
- * system call.  Worse yet, NFSv2 only allows for a 32-bit readdir
- * cookie.  Sigh.
+ * Upper layer (for example NFS) should specify FMODE_32BITHASH or
+ * FMODE_64BITHASH explicitly. On the other hand, we allow ext4 to be mounted
+ * directly on both 32-bit and 64-bit nodes, under such case, neither
+ * FMODE_32BITHASH nor FMODE_64BITHASH is specified.
  */
-#define hash2pos(major, minor)	(major >> 1)
-#define pos2maj_hash(pos)	((pos << 1) & 0xffffffff)
-#define pos2min_hash(pos)	(0)
+static inline loff_t hash2pos(struct file *filp, __u32 major, __u32 minor)
+{
+	if ((filp->f_mode & FMODE_32BITHASH) ||
+	    (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api()))
+		return major >> 1;
+	else
+		return ((__u64)(major >> 1) << 32) | (__u64)minor;
+}
+
+static inline __u32 pos2maj_hash(struct file *filp, loff_t pos)
+{
+	if ((filp->f_mode & FMODE_32BITHASH) ||
+	    (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api()))
+		return (pos << 1) & 0xffffffff;
+	else
+		return ((pos >> 32) << 1) & 0xffffffff;
+}
+
+static inline __u32 pos2min_hash(struct file *filp, loff_t pos)
+{
+	if ((filp->f_mode & FMODE_32BITHASH) ||
+	    (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api()))
+		return 0;
+	else
+		return pos & 0xffffffff;
+}
+
+/*
+ * Return 32- or 64-bit end-of-file for dx directories
+ */
+static inline loff_t ext4_get_htree_eof(struct file *filp)
+{
+	if ((filp->f_mode & FMODE_32BITHASH) ||
+	    (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api()))
+		return EXT4_HTREE_EOF_32BIT;
+	else
+		return EXT4_HTREE_EOF_64BIT;
+}
+
+
+/*
+ * ext4_dir_llseek() based on generic_file_llseek() to handle both
+ * non-htree and htree directories, where the "offset" is in terms
+ * of the filename hash value instead of the byte offset.
+ *
+ * NOTE: offsets obtained *before* ext4_set_inode_flag(dir, EXT4_INODE_INDEX)
+ *       will be invalid once the directory was converted into a dx directory
+ */
+loff_t ext4_dir_llseek(struct file *file, loff_t offset, int origin)
+{
+	struct inode *inode = file->f_mapping->host;
+	loff_t ret = -EINVAL;
+	int dx_dir = is_dx_dir(inode);
+
+	mutex_lock(&inode->i_mutex);
+
+	/* NOTE: relative offsets with dx directories might not work
+	 *       as expected, as it is difficult to figure out the
+	 *       correct offset between dx hashes */
+
+	switch (origin) {
+	case SEEK_END:
+		if (unlikely(offset > 0))
+			goto out_err; /* not supported for directories */
+
+		/* so only negative offsets are left, does that have a
+		 * meaning for directories at all? */
+		if (dx_dir)
+			offset += ext4_get_htree_eof(file);
+		else
+			offset += inode->i_size;
+		break;
+	case SEEK_CUR:
+		/*
+		 * Here we special-case the lseek(fd, 0, SEEK_CUR)
+		 * position-querying operation.  Avoid rewriting the "same"
+		 * f_pos value back to the file because a concurrent read(),
+		 * write() or lseek() might have altered it
+		 */
+		if (offset == 0) {
+			offset = file->f_pos;
+			goto out_ok;
+		}
+
+		offset += file->f_pos;
+		break;
+	}
+
+	if (unlikely(offset < 0))
+		goto out_err;
+
+	if (!dx_dir) {
+		if (offset > inode->i_sb->s_maxbytes)
+			goto out_err;
+	} else if (offset > ext4_get_htree_eof(file))
+		goto out_err;
+
+	/* Special lock needed here? */
+	if (offset != file->f_pos) {
+		file->f_pos = offset;
+		file->f_version = 0;
+	}
+
+out_ok:
+	ret = offset;
+out_err:
+	mutex_unlock(&inode->i_mutex);
+
+	return ret;
+}
 
 /*
  * This structure holds the nodes of the red-black tree used to store
@@ -330,15 +441,16 @@
 }
 
 
-static struct dir_private_info *ext4_htree_create_dir_info(loff_t pos)
+static struct dir_private_info *ext4_htree_create_dir_info(struct file *filp,
+							   loff_t pos)
 {
 	struct dir_private_info *p;
 
 	p = kzalloc(sizeof(struct dir_private_info), GFP_KERNEL);
 	if (!p)
 		return NULL;
-	p->curr_hash = pos2maj_hash(pos);
-	p->curr_minor_hash = pos2min_hash(pos);
+	p->curr_hash = pos2maj_hash(filp, pos);
+	p->curr_minor_hash = pos2min_hash(filp, pos);
 	return p;
 }
 
@@ -430,7 +542,7 @@
 			 inode->i_ino, current->comm);
 		return 0;
 	}
-	curr_pos = hash2pos(fname->hash, fname->minor_hash);
+	curr_pos = hash2pos(filp, fname->hash, fname->minor_hash);
 	while (fname) {
 		error = filldir(dirent, fname->name,
 				fname->name_len, curr_pos,
@@ -455,13 +567,13 @@
 	int	ret;
 
 	if (!info) {
-		info = ext4_htree_create_dir_info(filp->f_pos);
+		info = ext4_htree_create_dir_info(filp, filp->f_pos);
 		if (!info)
 			return -ENOMEM;
 		filp->private_data = info;
 	}
 
-	if (filp->f_pos == EXT4_HTREE_EOF)
+	if (filp->f_pos == ext4_get_htree_eof(filp))
 		return 0;	/* EOF */
 
 	/* Some one has messed with f_pos; reset the world */
@@ -469,8 +581,8 @@
 		free_rb_tree_fname(&info->root);
 		info->curr_node = NULL;
 		info->extra_fname = NULL;
-		info->curr_hash = pos2maj_hash(filp->f_pos);
-		info->curr_minor_hash = pos2min_hash(filp->f_pos);
+		info->curr_hash = pos2maj_hash(filp, filp->f_pos);
+		info->curr_minor_hash = pos2min_hash(filp, filp->f_pos);
 	}
 
 	/*
@@ -502,7 +614,7 @@
 			if (ret < 0)
 				return ret;
 			if (ret == 0) {
-				filp->f_pos = EXT4_HTREE_EOF;
+				filp->f_pos = ext4_get_htree_eof(filp);
 				break;
 			}
 			info->curr_node = rb_first(&info->root);
@@ -522,7 +634,7 @@
 			info->curr_minor_hash = fname->minor_hash;
 		} else {
 			if (info->next_hash == ~0) {
-				filp->f_pos = EXT4_HTREE_EOF;
+				filp->f_pos = ext4_get_htree_eof(filp);
 				break;
 			}
 			info->curr_hash = info->next_hash;
@@ -541,3 +653,15 @@
 
 	return 0;
 }
+
+const struct file_operations ext4_dir_operations = {
+	.llseek		= ext4_dir_llseek,
+	.read		= generic_read_dir,
+	.readdir	= ext4_readdir,
+	.unlocked_ioctl = ext4_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= ext4_compat_ioctl,
+#endif
+	.fsync		= ext4_sync_file,
+	.release	= ext4_release_dir,
+};
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index ded731a..ab2594a 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1623,7 +1623,11 @@
 	u32		*seed;
 };
 
-#define EXT4_HTREE_EOF	0x7fffffff
+
+/* 32 and 64 bit signed EOF for dx directories */
+#define EXT4_HTREE_EOF_32BIT   ((1UL  << (32 - 1)) - 1)
+#define EXT4_HTREE_EOF_64BIT   ((1ULL << (64 - 1)) - 1)
+
 
 /*
  * Control parameters used by ext4_htree_next_block
diff --git a/fs/ext4/hash.c b/fs/ext4/hash.c
index ac8f168..fa8e491 100644
--- a/fs/ext4/hash.c
+++ b/fs/ext4/hash.c
@@ -200,8 +200,8 @@
 		return -1;
 	}
 	hash = hash & ~1;
-	if (hash == (EXT4_HTREE_EOF << 1))
-		hash = (EXT4_HTREE_EOF-1) << 1;
+	if (hash == (EXT4_HTREE_EOF_32BIT << 1))
+		hash = (EXT4_HTREE_EOF_32BIT - 1) << 1;
 	hinfo->hash = hash;
 	hinfo->minor_hash = minor_hash;
 	return 0;
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 74cd1f7..dcdeef1 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -60,6 +60,7 @@
 static void put_io_page(struct ext4_io_page *io_page)
 {
 	if (atomic_dec_and_test(&io_page->p_count)) {
+		end_page_writeback(io_page->p_page);
 		put_page(io_page->p_page);
 		kmem_cache_free(io_page_cachep, io_page);
 	}
@@ -233,9 +234,9 @@
 			} while (bh != head);
 		}
 
-		if (atomic_read(&io_end->pages[i]->p_count) == 1)
-			end_page_writeback(io_end->pages[i]->p_page);
+		put_io_page(io_end->pages[i]);
 	}
+	io_end->num_io_pages = 0;
 	inode = io_end->inode;
 
 	if (error) {
@@ -427,8 +428,6 @@
 	 * PageWriteback bit from the page to prevent the system from
 	 * wedging later on.
 	 */
-	if (atomic_read(&io_page->p_count) == 1)
-		end_page_writeback(page);
 	put_io_page(io_page);
 	return ret;
 }
diff --git a/fs/fcntl.c b/fs/fcntl.c
index 22764c7..75e7c1f 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -32,20 +32,20 @@
 	spin_lock(&files->file_lock);
 	fdt = files_fdtable(files);
 	if (flag)
-		FD_SET(fd, fdt->close_on_exec);
+		__set_close_on_exec(fd, fdt);
 	else
-		FD_CLR(fd, fdt->close_on_exec);
+		__clear_close_on_exec(fd, fdt);
 	spin_unlock(&files->file_lock);
 }
 
-static int get_close_on_exec(unsigned int fd)
+static bool get_close_on_exec(unsigned int fd)
 {
 	struct files_struct *files = current->files;
 	struct fdtable *fdt;
-	int res;
+	bool res;
 	rcu_read_lock();
 	fdt = files_fdtable(files);
-	res = FD_ISSET(fd, fdt->close_on_exec);
+	res = close_on_exec(fd, fdt);
 	rcu_read_unlock();
 	return res;
 }
@@ -90,15 +90,15 @@
 	err = -EBUSY;
 	fdt = files_fdtable(files);
 	tofree = fdt->fd[newfd];
-	if (!tofree && FD_ISSET(newfd, fdt->open_fds))
+	if (!tofree && fd_is_open(newfd, fdt))
 		goto out_unlock;
 	get_file(file);
 	rcu_assign_pointer(fdt->fd[newfd], file);
-	FD_SET(newfd, fdt->open_fds);
+	__set_open_fd(newfd, fdt);
 	if (flags & O_CLOEXEC)
-		FD_SET(newfd, fdt->close_on_exec);
+		__set_close_on_exec(newfd, fdt);
 	else
-		FD_CLR(newfd, fdt->close_on_exec);
+		__clear_close_on_exec(newfd, fdt);
 	spin_unlock(&files->file_lock);
 
 	if (tofree)
diff --git a/fs/file.c b/fs/file.c
index 3c426de..ba3f605 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -40,7 +40,7 @@
  */
 static DEFINE_PER_CPU(struct fdtable_defer, fdtable_defer_list);
 
-static void *alloc_fdmem(unsigned int size)
+static void *alloc_fdmem(size_t size)
 {
 	/*
 	 * Very large allocations can stress page reclaim, so fall back to
@@ -142,7 +142,7 @@
 static struct fdtable * alloc_fdtable(unsigned int nr)
 {
 	struct fdtable *fdt;
-	char *data;
+	void *data;
 
 	/*
 	 * Figure out how many fds we actually want to support in this fdtable.
@@ -172,14 +172,15 @@
 	data = alloc_fdmem(nr * sizeof(struct file *));
 	if (!data)
 		goto out_fdt;
-	fdt->fd = (struct file **)data;
-	data = alloc_fdmem(max_t(unsigned int,
+	fdt->fd = data;
+
+	data = alloc_fdmem(max_t(size_t,
 				 2 * nr / BITS_PER_BYTE, L1_CACHE_BYTES));
 	if (!data)
 		goto out_arr;
-	fdt->open_fds = (fd_set *)data;
+	fdt->open_fds = data;
 	data += nr / BITS_PER_BYTE;
-	fdt->close_on_exec = (fd_set *)data;
+	fdt->close_on_exec = data;
 	fdt->next = NULL;
 
 	return fdt;
@@ -275,11 +276,11 @@
 	int i;
 
 	/* Find the last open fd */
-	for (i = size/(8*sizeof(long)); i > 0; ) {
-		if (fdt->open_fds->fds_bits[--i])
+	for (i = size / BITS_PER_LONG; i > 0; ) {
+		if (fdt->open_fds[--i])
 			break;
 	}
-	i = (i+1) * 8 * sizeof(long);
+	i = (i + 1) * BITS_PER_LONG;
 	return i;
 }
 
@@ -306,8 +307,8 @@
 	newf->next_fd = 0;
 	new_fdt = &newf->fdtab;
 	new_fdt->max_fds = NR_OPEN_DEFAULT;
-	new_fdt->close_on_exec = (fd_set *)&newf->close_on_exec_init;
-	new_fdt->open_fds = (fd_set *)&newf->open_fds_init;
+	new_fdt->close_on_exec = newf->close_on_exec_init;
+	new_fdt->open_fds = newf->open_fds_init;
 	new_fdt->fd = &newf->fd_array[0];
 	new_fdt->next = NULL;
 
@@ -350,10 +351,8 @@
 	old_fds = old_fdt->fd;
 	new_fds = new_fdt->fd;
 
-	memcpy(new_fdt->open_fds->fds_bits,
-		old_fdt->open_fds->fds_bits, open_files/8);
-	memcpy(new_fdt->close_on_exec->fds_bits,
-		old_fdt->close_on_exec->fds_bits, open_files/8);
+	memcpy(new_fdt->open_fds, old_fdt->open_fds, open_files / 8);
+	memcpy(new_fdt->close_on_exec, old_fdt->close_on_exec, open_files / 8);
 
 	for (i = open_files; i != 0; i--) {
 		struct file *f = *old_fds++;
@@ -366,7 +365,7 @@
 			 * is partway through open().  So make sure that this
 			 * fd is available to the new process.
 			 */
-			FD_CLR(open_files - i, new_fdt->open_fds);
+			__clear_open_fd(open_files - i, new_fdt);
 		}
 		rcu_assign_pointer(*new_fds++, f);
 	}
@@ -379,11 +378,11 @@
 	memset(new_fds, 0, size);
 
 	if (new_fdt->max_fds > open_files) {
-		int left = (new_fdt->max_fds-open_files)/8;
-		int start = open_files / (8 * sizeof(unsigned long));
+		int left = (new_fdt->max_fds - open_files) / 8;
+		int start = open_files / BITS_PER_LONG;
 
-		memset(&new_fdt->open_fds->fds_bits[start], 0, left);
-		memset(&new_fdt->close_on_exec->fds_bits[start], 0, left);
+		memset(&new_fdt->open_fds[start], 0, left);
+		memset(&new_fdt->close_on_exec[start], 0, left);
 	}
 
 	rcu_assign_pointer(newf->fdt, new_fdt);
@@ -419,8 +418,8 @@
 	.fdtab		= {
 		.max_fds	= NR_OPEN_DEFAULT,
 		.fd		= &init_files.fd_array[0],
-		.close_on_exec	= (fd_set *)&init_files.close_on_exec_init,
-		.open_fds	= (fd_set *)&init_files.open_fds_init,
+		.close_on_exec	= init_files.close_on_exec_init,
+		.open_fds	= init_files.open_fds_init,
 	},
 	.file_lock	= __SPIN_LOCK_UNLOCKED(init_task.file_lock),
 };
@@ -443,8 +442,7 @@
 		fd = files->next_fd;
 
 	if (fd < fdt->max_fds)
-		fd = find_next_zero_bit(fdt->open_fds->fds_bits,
-					   fdt->max_fds, fd);
+		fd = find_next_zero_bit(fdt->open_fds, fdt->max_fds, fd);
 
 	error = expand_files(files, fd);
 	if (error < 0)
@@ -460,11 +458,11 @@
 	if (start <= files->next_fd)
 		files->next_fd = fd + 1;
 
-	FD_SET(fd, fdt->open_fds);
+	__set_open_fd(fd, fdt);
 	if (flags & O_CLOEXEC)
-		FD_SET(fd, fdt->close_on_exec);
+		__set_close_on_exec(fd, fdt);
 	else
-		FD_CLR(fd, fdt->close_on_exec);
+		__clear_close_on_exec(fd, fdt);
 	error = fd;
 #if 1
 	/* Sanity check */
diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index 2774e10..f49b9af 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -496,7 +496,7 @@
 	__typeof__(type) num = which_strtol(val, &endp, 0);		\
 	if (endp == val || *endp || num < (min) || num > (max))		\
 		return -EINVAL;						\
-	*((int *) kp->arg) = num;					\
+	*((type *) kp->arg) = num;					\
 	return 0;							\
 }
 
diff --git a/fs/nfsd/current_stateid.h b/fs/nfsd/current_stateid.h
new file mode 100644
index 0000000..4123551
--- /dev/null
+++ b/fs/nfsd/current_stateid.h
@@ -0,0 +1,28 @@
+#ifndef _NFSD4_CURRENT_STATE_H
+#define _NFSD4_CURRENT_STATE_H
+
+#include "state.h"
+#include "xdr4.h"
+
+extern void clear_current_stateid(struct nfsd4_compound_state *cstate);
+/*
+ * functions to set current state id
+ */
+extern void nfsd4_set_opendowngradestateid(struct nfsd4_compound_state *cstate, struct nfsd4_open_downgrade *);
+extern void nfsd4_set_openstateid(struct nfsd4_compound_state *, struct nfsd4_open *);
+extern void nfsd4_set_lockstateid(struct nfsd4_compound_state *, struct nfsd4_lock *);
+extern void nfsd4_set_closestateid(struct nfsd4_compound_state *, struct nfsd4_close *);
+
+/*
+ * functions to consume current state id
+ */
+extern void nfsd4_get_opendowngradestateid(struct nfsd4_compound_state *cstate, struct nfsd4_open_downgrade *);
+extern void nfsd4_get_delegreturnstateid(struct nfsd4_compound_state *, struct nfsd4_delegreturn *);
+extern void nfsd4_get_freestateid(struct nfsd4_compound_state *, struct nfsd4_free_stateid *);
+extern void nfsd4_get_setattrstateid(struct nfsd4_compound_state *, struct nfsd4_setattr *);
+extern void nfsd4_get_closestateid(struct nfsd4_compound_state *, struct nfsd4_close *);
+extern void nfsd4_get_lockustateid(struct nfsd4_compound_state *, struct nfsd4_locku *);
+extern void nfsd4_get_readstateid(struct nfsd4_compound_state *, struct nfsd4_read *);
+extern void nfsd4_get_writestateid(struct nfsd4_compound_state *, struct nfsd4_write *);
+
+#endif   /* _NFSD4_CURRENT_STATE_H */
diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index cf8a6bd..8e9689a 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -87,7 +87,7 @@
 	struct svc_expkey key;
 	struct svc_expkey *ek = NULL;
 
-	if (mlen < 1 || mesg[mlen-1] != '\n')
+	if (mesg[mlen - 1] != '\n')
 		return -EINVAL;
 	mesg[mlen-1] = 0;
 
diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h
new file mode 100644
index 0000000..12e0cff
--- /dev/null
+++ b/fs/nfsd/netns.h
@@ -0,0 +1,34 @@
+/*
+ * per net namespace data structures for nfsd
+ *
+ * Copyright (C) 2012, Jeff Layton <jlayton@redhat.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., 51
+ * Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+ */
+
+#ifndef __NFSD_NETNS_H__
+#define __NFSD_NETNS_H__
+
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+
+struct cld_net;
+
+struct nfsd_net {
+	struct cld_net *cld_net;
+};
+
+extern int nfsd_net_id;
+#endif /* __NFSD_NETNS_H__ */
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 0e262f3..c8e9f63 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -645,7 +645,6 @@
 		.timeout	= &timeparms,
 		.program	= &cb_program,
 		.version	= 0,
-		.authflavor	= clp->cl_flavor,
 		.flags		= (RPC_CLNT_CREATE_NOPING | RPC_CLNT_CREATE_QUIET),
 	};
 	struct rpc_clnt *client;
@@ -656,6 +655,7 @@
 		args.client_name = clp->cl_principal;
 		args.prognumber	= conn->cb_prog,
 		args.protocol = XPRT_TRANSPORT_TCP;
+		args.authflavor = clp->cl_flavor;
 		clp->cl_cb_ident = conn->cb_ident;
 	} else {
 		if (!conn->cb_xprt)
@@ -665,6 +665,7 @@
 		args.bc_xprt = conn->cb_xprt;
 		args.prognumber = clp->cl_cb_session->se_cb_prog;
 		args.protocol = XPRT_TRANSPORT_BC_TCP;
+		args.authflavor = RPC_AUTH_UNIX;
 	}
 	/* Create RPC client */
 	client = rpc_create(&args);
@@ -754,9 +755,9 @@
  */
 void nfsd4_probe_callback(struct nfs4_client *clp)
 {
-	/* XXX: atomicity?  Also, should we be using cl_cb_flags? */
+	/* XXX: atomicity?  Also, should we be using cl_flags? */
 	clp->cl_cb_state = NFSD4_CB_UNKNOWN;
-	set_bit(NFSD4_CLIENT_CB_UPDATE, &clp->cl_cb_flags);
+	set_bit(NFSD4_CLIENT_CB_UPDATE, &clp->cl_flags);
 	do_probe_callback(clp);
 }
 
@@ -915,7 +916,7 @@
 /* must be called under the state lock */
 void nfsd4_shutdown_callback(struct nfs4_client *clp)
 {
-	set_bit(NFSD4_CLIENT_KILL, &clp->cl_cb_flags);
+	set_bit(NFSD4_CLIENT_CB_KILL, &clp->cl_flags);
 	/*
 	 * Note this won't actually result in a null callback;
 	 * instead, nfsd4_do_callback_rpc() will detect the killed
@@ -966,15 +967,15 @@
 		svc_xprt_put(clp->cl_cb_conn.cb_xprt);
 		clp->cl_cb_conn.cb_xprt = NULL;
 	}
-	if (test_bit(NFSD4_CLIENT_KILL, &clp->cl_cb_flags))
+	if (test_bit(NFSD4_CLIENT_CB_KILL, &clp->cl_flags))
 		return;
 	spin_lock(&clp->cl_lock);
 	/*
 	 * Only serialized callback code is allowed to clear these
 	 * flags; main nfsd code can only set them:
 	 */
-	BUG_ON(!clp->cl_cb_flags);
-	clear_bit(NFSD4_CLIENT_CB_UPDATE, &clp->cl_cb_flags);
+	BUG_ON(!(clp->cl_flags & NFSD4_CLIENT_CB_FLAG_MASK));
+	clear_bit(NFSD4_CLIENT_CB_UPDATE, &clp->cl_flags);
 	memcpy(&conn, &cb->cb_clp->cl_cb_conn, sizeof(struct nfs4_cb_conn));
 	c = __nfsd4_find_backchannel(clp);
 	if (c) {
@@ -986,7 +987,7 @@
 
 	err = setup_callback_client(clp, &conn, ses);
 	if (err) {
-		warn_no_callback_path(clp, err);
+		nfsd4_mark_cb_down(clp, err);
 		return;
 	}
 	/* Yay, the callback channel's back! Restart any callbacks: */
@@ -1000,7 +1001,7 @@
 	struct nfs4_client *clp = cb->cb_clp;
 	struct rpc_clnt *clnt;
 
-	if (clp->cl_cb_flags)
+	if (clp->cl_flags & NFSD4_CLIENT_CB_FLAG_MASK)
 		nfsd4_process_cb_update(cb);
 
 	clnt = clp->cl_cb_client;
diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c
index 9409627..322d11c 100644
--- a/fs/nfsd/nfs4idmap.c
+++ b/fs/nfsd/nfs4idmap.c
@@ -41,6 +41,14 @@
 #include "nfsd.h"
 
 /*
+ * Turn off idmapping when using AUTH_SYS.
+ */
+static bool nfs4_disable_idmapping = true;
+module_param(nfs4_disable_idmapping, bool, 0644);
+MODULE_PARM_DESC(nfs4_disable_idmapping,
+		"Turn off server's NFSv4 idmapping when using 'sec=sys'");
+
+/*
  * Cache entry
  */
 
@@ -561,28 +569,65 @@
 	return ret;
 }
 
+static bool
+numeric_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen, uid_t *id)
+{
+	int ret;
+	char buf[11];
+
+	if (namelen + 1 > sizeof(buf))
+		/* too long to represent a 32-bit id: */
+		return false;
+	/* Just to make sure it's null-terminated: */
+	memcpy(buf, name, namelen);
+	buf[namelen] = '\0';
+	ret = kstrtouint(name, 10, id);
+	return ret == 0;
+}
+
+static __be32
+do_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen, uid_t *id)
+{
+	if (nfs4_disable_idmapping && rqstp->rq_flavor < RPC_AUTH_GSS)
+		if (numeric_name_to_id(rqstp, type, name, namelen, id))
+			return 0;
+		/*
+		 * otherwise, fall through and try idmapping, for
+		 * backwards compatibility with clients sending names:
+		 */
+	return idmap_name_to_id(rqstp, type, name, namelen, id);
+}
+
+static int
+do_id_to_name(struct svc_rqst *rqstp, int type, uid_t id, char *name)
+{
+	if (nfs4_disable_idmapping && rqstp->rq_flavor < RPC_AUTH_GSS)
+		return sprintf(name, "%u", id);
+	return idmap_id_to_name(rqstp, type, id, name);
+}
+
 __be32
 nfsd_map_name_to_uid(struct svc_rqst *rqstp, const char *name, size_t namelen,
 		__u32 *id)
 {
-	return idmap_name_to_id(rqstp, IDMAP_TYPE_USER, name, namelen, id);
+	return do_name_to_id(rqstp, IDMAP_TYPE_USER, name, namelen, id);
 }
 
 __be32
 nfsd_map_name_to_gid(struct svc_rqst *rqstp, const char *name, size_t namelen,
 		__u32 *id)
 {
-	return idmap_name_to_id(rqstp, IDMAP_TYPE_GROUP, name, namelen, id);
+	return do_name_to_id(rqstp, IDMAP_TYPE_GROUP, name, namelen, id);
 }
 
 int
 nfsd_map_uid_to_name(struct svc_rqst *rqstp, __u32 id, char *name)
 {
-	return idmap_id_to_name(rqstp, IDMAP_TYPE_USER, id, name);
+	return do_id_to_name(rqstp, IDMAP_TYPE_USER, id, name);
 }
 
 int
 nfsd_map_gid_to_name(struct svc_rqst *rqstp, __u32 id, char *name)
 {
-	return idmap_id_to_name(rqstp, IDMAP_TYPE_GROUP, id, name);
+	return do_id_to_name(rqstp, IDMAP_TYPE_GROUP, id, name);
 }
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 896da74..2ed14df 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -39,6 +39,7 @@
 #include "cache.h"
 #include "xdr4.h"
 #include "vfs.h"
+#include "current_stateid.h"
 
 #define NFSDDBG_FACILITY		NFSDDBG_PROC
 
@@ -192,10 +193,13 @@
 static __be32
 do_open_lookup(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_open *open)
 {
-	struct svc_fh resfh;
+	struct svc_fh *resfh;
 	__be32 status;
 
-	fh_init(&resfh, NFS4_FHSIZE);
+	resfh = kmalloc(sizeof(struct svc_fh), GFP_KERNEL);
+	if (!resfh)
+		return nfserr_jukebox;
+	fh_init(resfh, NFS4_FHSIZE);
 	open->op_truncate = 0;
 
 	if (open->op_create) {
@@ -220,7 +224,7 @@
 		 */
 		status = do_nfsd_create(rqstp, current_fh, open->op_fname.data,
 					open->op_fname.len, &open->op_iattr,
-					&resfh, open->op_createmode,
+					resfh, open->op_createmode,
 					(u32 *)open->op_verf.data,
 					&open->op_truncate, &open->op_created);
 
@@ -234,30 +238,29 @@
 						FATTR4_WORD1_TIME_MODIFY);
 	} else {
 		status = nfsd_lookup(rqstp, current_fh,
-				     open->op_fname.data, open->op_fname.len, &resfh);
+				     open->op_fname.data, open->op_fname.len, resfh);
 		fh_unlock(current_fh);
 		if (status)
 			goto out;
-		status = nfsd_check_obj_isreg(&resfh);
+		status = nfsd_check_obj_isreg(resfh);
 	}
 	if (status)
 		goto out;
 
 	if (is_create_with_attrs(open) && open->op_acl != NULL)
-		do_set_nfs4_acl(rqstp, &resfh, open->op_acl, open->op_bmval);
-
-	set_change_info(&open->op_cinfo, current_fh);
-	fh_dup2(current_fh, &resfh);
+		do_set_nfs4_acl(rqstp, resfh, open->op_acl, open->op_bmval);
 
 	/* set reply cache */
 	fh_copy_shallow(&open->op_openowner->oo_owner.so_replay.rp_openfh,
-			&resfh.fh_handle);
+			&resfh->fh_handle);
 	if (!open->op_created)
-		status = do_open_permission(rqstp, current_fh, open,
+		status = do_open_permission(rqstp, resfh, open,
 					    NFSD_MAY_NOP);
-
+	set_change_info(&open->op_cinfo, current_fh);
+	fh_dup2(current_fh, resfh);
 out:
-	fh_put(&resfh);
+	fh_put(resfh);
+	kfree(resfh);
 	return status;
 }
 
@@ -310,16 +313,14 @@
 	if (open->op_create && open->op_claim_type != NFS4_OPEN_CLAIM_NULL)
 		return nfserr_inval;
 
-	/* We don't yet support WANT bits: */
-	open->op_share_access &= NFS4_SHARE_ACCESS_MASK;
-
 	open->op_created = 0;
 	/*
 	 * RFC5661 18.51.3
 	 * Before RECLAIM_COMPLETE done, server should deny new lock
 	 */
 	if (nfsd4_has_session(cstate) &&
-	    !cstate->session->se_client->cl_firststate &&
+	    !test_bit(NFSD4_CLIENT_RECLAIM_COMPLETE,
+		      &cstate->session->se_client->cl_flags) &&
 	    open->op_claim_type != NFS4_OPEN_CLAIM_PREVIOUS)
 		return nfserr_grace;
 
@@ -452,6 +453,10 @@
 		return nfserr_restorefh;
 
 	fh_dup2(&cstate->current_fh, &cstate->save_fh);
+	if (HAS_STATE_ID(cstate, SAVED_STATE_ID_FLAG)) {
+		memcpy(&cstate->current_stateid, &cstate->save_stateid, sizeof(stateid_t));
+		SET_STATE_ID(cstate, CURRENT_STATE_ID_FLAG);
+	}
 	return nfs_ok;
 }
 
@@ -463,6 +468,10 @@
 		return nfserr_nofilehandle;
 
 	fh_dup2(&cstate->save_fh, &cstate->current_fh);
+	if (HAS_STATE_ID(cstate, CURRENT_STATE_ID_FLAG)) {
+		memcpy(&cstate->save_stateid, &cstate->current_stateid, sizeof(stateid_t));
+		SET_STATE_ID(cstate, SAVED_STATE_ID_FLAG);
+	}
 	return nfs_ok;
 }
 
@@ -481,14 +490,20 @@
 			   &access->ac_supported);
 }
 
+static void gen_boot_verifier(nfs4_verifier *verifier)
+{
+	__be32 verf[2];
+
+	verf[0] = (__be32)nfssvc_boot.tv_sec;
+	verf[1] = (__be32)nfssvc_boot.tv_usec;
+	memcpy(verifier->data, verf, sizeof(verifier->data));
+}
+
 static __be32
 nfsd4_commit(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	     struct nfsd4_commit *commit)
 {
-	u32 *p = (u32 *)commit->co_verf.data;
-	*p++ = nfssvc_boot.tv_sec;
-	*p++ = nfssvc_boot.tv_usec;
-
+	gen_boot_verifier(&commit->co_verf);
 	return nfsd_commit(rqstp, &cstate->current_fh, commit->co_offset,
 			     commit->co_count);
 }
@@ -865,7 +880,6 @@
 {
 	stateid_t *stateid = &write->wr_stateid;
 	struct file *filp = NULL;
-	u32 *p;
 	__be32 status = nfs_ok;
 	unsigned long cnt;
 
@@ -887,9 +901,7 @@
 
 	cnt = write->wr_buflen;
 	write->wr_how_written = write->wr_stable_how;
-	p = (u32 *)write->wr_verifier.data;
-	*p++ = nfssvc_boot.tv_sec;
-	*p++ = nfssvc_boot.tv_usec;
+	gen_boot_verifier(&write->wr_verifier);
 
 	status =  nfsd_write(rqstp, &cstate->current_fh, filp,
 			     write->wr_offset, rqstp->rq_vec, write->wr_vlen,
@@ -1000,6 +1012,8 @@
 typedef __be32(*nfsd4op_func)(struct svc_rqst *, struct nfsd4_compound_state *,
 			      void *);
 typedef u32(*nfsd4op_rsize)(struct svc_rqst *, struct nfsd4_op *op);
+typedef void(*stateid_setter)(struct nfsd4_compound_state *, void *);
+typedef void(*stateid_getter)(struct nfsd4_compound_state *, void *);
 
 enum nfsd4_op_flags {
 	ALLOWED_WITHOUT_FH = 1 << 0,	/* No current filehandle required */
@@ -1025,6 +1039,10 @@
 	 * the v4.0 case).
 	 */
 	OP_CACHEME = 1 << 6,
+	/*
+	 * These are ops which clear current state id.
+	 */
+	OP_CLEAR_STATEID = 1 << 7,
 };
 
 struct nfsd4_operation {
@@ -1033,11 +1051,15 @@
 	char *op_name;
 	/* Try to get response size before operation */
 	nfsd4op_rsize op_rsize_bop;
+	stateid_setter op_get_currentstateid;
+	stateid_getter op_set_currentstateid;
 };
 
 static struct nfsd4_operation nfsd4_ops[];
 
+#ifdef NFSD_DEBUG
 static const char *nfsd4_op_name(unsigned opnum);
+#endif
 
 /*
  * Enforce NFSv4.1 COMPOUND ordering rules:
@@ -1215,13 +1237,23 @@
 		if (op->status)
 			goto encode_op;
 
-		if (opdesc->op_func)
+		if (opdesc->op_func) {
+			if (opdesc->op_get_currentstateid)
+				opdesc->op_get_currentstateid(cstate, &op->u);
 			op->status = opdesc->op_func(rqstp, cstate, &op->u);
-		else
+		} else
 			BUG_ON(op->status == nfs_ok);
 
-		if (!op->status && need_wrongsec_check(rqstp))
-			op->status = check_nfsd_access(cstate->current_fh.fh_export, rqstp);
+		if (!op->status) {
+			if (opdesc->op_set_currentstateid)
+				opdesc->op_set_currentstateid(cstate, &op->u);
+
+			if (opdesc->op_flags & OP_CLEAR_STATEID)
+				clear_current_stateid(cstate);
+
+			if (need_wrongsec_check(rqstp))
+				op->status = check_nfsd_access(cstate->current_fh.fh_export, rqstp);
+		}
 
 encode_op:
 		/* Only from SEQUENCE */
@@ -1413,6 +1445,8 @@
 		.op_flags = OP_MODIFIES_SOMETHING,
 		.op_name = "OP_CLOSE",
 		.op_rsize_bop = (nfsd4op_rsize)nfsd4_status_stateid_rsize,
+		.op_get_currentstateid = (stateid_getter)nfsd4_get_closestateid,
+		.op_set_currentstateid = (stateid_setter)nfsd4_set_closestateid,
 	},
 	[OP_COMMIT] = {
 		.op_func = (nfsd4op_func)nfsd4_commit,
@@ -1422,7 +1456,7 @@
 	},
 	[OP_CREATE] = {
 		.op_func = (nfsd4op_func)nfsd4_create,
-		.op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME,
+		.op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME | OP_CLEAR_STATEID,
 		.op_name = "OP_CREATE",
 		.op_rsize_bop = (nfsd4op_rsize)nfsd4_create_rsize,
 	},
@@ -1431,6 +1465,7 @@
 		.op_flags = OP_MODIFIES_SOMETHING,
 		.op_name = "OP_DELEGRETURN",
 		.op_rsize_bop = nfsd4_only_status_rsize,
+		.op_get_currentstateid = (stateid_getter)nfsd4_get_delegreturnstateid,
 	},
 	[OP_GETATTR] = {
 		.op_func = (nfsd4op_func)nfsd4_getattr,
@@ -1453,6 +1488,7 @@
 		.op_flags = OP_MODIFIES_SOMETHING,
 		.op_name = "OP_LOCK",
 		.op_rsize_bop = (nfsd4op_rsize)nfsd4_lock_rsize,
+		.op_set_currentstateid = (stateid_setter)nfsd4_set_lockstateid,
 	},
 	[OP_LOCKT] = {
 		.op_func = (nfsd4op_func)nfsd4_lockt,
@@ -1463,15 +1499,16 @@
 		.op_flags = OP_MODIFIES_SOMETHING,
 		.op_name = "OP_LOCKU",
 		.op_rsize_bop = (nfsd4op_rsize)nfsd4_status_stateid_rsize,
+		.op_get_currentstateid = (stateid_getter)nfsd4_get_lockustateid,
 	},
 	[OP_LOOKUP] = {
 		.op_func = (nfsd4op_func)nfsd4_lookup,
-		.op_flags = OP_HANDLES_WRONGSEC,
+		.op_flags = OP_HANDLES_WRONGSEC | OP_CLEAR_STATEID,
 		.op_name = "OP_LOOKUP",
 	},
 	[OP_LOOKUPP] = {
 		.op_func = (nfsd4op_func)nfsd4_lookupp,
-		.op_flags = OP_HANDLES_WRONGSEC,
+		.op_flags = OP_HANDLES_WRONGSEC | OP_CLEAR_STATEID,
 		.op_name = "OP_LOOKUPP",
 	},
 	[OP_NVERIFY] = {
@@ -1483,6 +1520,7 @@
 		.op_flags = OP_HANDLES_WRONGSEC | OP_MODIFIES_SOMETHING,
 		.op_name = "OP_OPEN",
 		.op_rsize_bop = (nfsd4op_rsize)nfsd4_open_rsize,
+		.op_set_currentstateid = (stateid_setter)nfsd4_set_openstateid,
 	},
 	[OP_OPEN_CONFIRM] = {
 		.op_func = (nfsd4op_func)nfsd4_open_confirm,
@@ -1495,25 +1533,30 @@
 		.op_flags = OP_MODIFIES_SOMETHING,
 		.op_name = "OP_OPEN_DOWNGRADE",
 		.op_rsize_bop = (nfsd4op_rsize)nfsd4_status_stateid_rsize,
+		.op_get_currentstateid = (stateid_getter)nfsd4_get_opendowngradestateid,
+		.op_set_currentstateid = (stateid_setter)nfsd4_set_opendowngradestateid,
 	},
 	[OP_PUTFH] = {
 		.op_func = (nfsd4op_func)nfsd4_putfh,
 		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS
-				| OP_IS_PUTFH_LIKE | OP_MODIFIES_SOMETHING,
+				| OP_IS_PUTFH_LIKE | OP_MODIFIES_SOMETHING
+				| OP_CLEAR_STATEID,
 		.op_name = "OP_PUTFH",
 		.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
 	},
 	[OP_PUTPUBFH] = {
 		.op_func = (nfsd4op_func)nfsd4_putrootfh,
 		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS
-				| OP_IS_PUTFH_LIKE | OP_MODIFIES_SOMETHING,
+				| OP_IS_PUTFH_LIKE | OP_MODIFIES_SOMETHING
+				| OP_CLEAR_STATEID,
 		.op_name = "OP_PUTPUBFH",
 		.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
 	},
 	[OP_PUTROOTFH] = {
 		.op_func = (nfsd4op_func)nfsd4_putrootfh,
 		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS
-				| OP_IS_PUTFH_LIKE | OP_MODIFIES_SOMETHING,
+				| OP_IS_PUTFH_LIKE | OP_MODIFIES_SOMETHING
+				| OP_CLEAR_STATEID,
 		.op_name = "OP_PUTROOTFH",
 		.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
 	},
@@ -1522,6 +1565,7 @@
 		.op_flags = OP_MODIFIES_SOMETHING,
 		.op_name = "OP_READ",
 		.op_rsize_bop = (nfsd4op_rsize)nfsd4_read_rsize,
+		.op_get_currentstateid = (stateid_getter)nfsd4_get_readstateid,
 	},
 	[OP_READDIR] = {
 		.op_func = (nfsd4op_func)nfsd4_readdir,
@@ -1576,6 +1620,7 @@
 		.op_name = "OP_SETATTR",
 		.op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME,
 		.op_rsize_bop = (nfsd4op_rsize)nfsd4_setattr_rsize,
+		.op_get_currentstateid = (stateid_getter)nfsd4_get_setattrstateid,
 	},
 	[OP_SETCLIENTID] = {
 		.op_func = (nfsd4op_func)nfsd4_setclientid,
@@ -1600,6 +1645,7 @@
 		.op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME,
 		.op_name = "OP_WRITE",
 		.op_rsize_bop = (nfsd4op_rsize)nfsd4_write_rsize,
+		.op_get_currentstateid = (stateid_getter)nfsd4_get_writestateid,
 	},
 	[OP_RELEASE_LOCKOWNER] = {
 		.op_func = (nfsd4op_func)nfsd4_release_lockowner,
@@ -1674,12 +1720,14 @@
 	},
 };
 
+#ifdef NFSD_DEBUG
 static const char *nfsd4_op_name(unsigned opnum)
 {
 	if (opnum < ARRAY_SIZE(nfsd4_ops))
 		return nfsd4_ops[opnum].op_name;
 	return "unknown_operation";
 }
+#endif
 
 #define nfsd4_voidres			nfsd4_voidargs
 struct nfsd4_voidargs { int dummy; };
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index 0b3e875..4767429 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -1,5 +1,6 @@
 /*
 *  Copyright (c) 2004 The Regents of the University of Michigan.
+*  Copyright (c) 2012 Jeff Layton <jlayton@redhat.com>
 *  All rights reserved.
 *
 *  Andy Adamson <andros@citi.umich.edu>
@@ -36,16 +37,34 @@
 #include <linux/namei.h>
 #include <linux/crypto.h>
 #include <linux/sched.h>
+#include <linux/fs.h>
+#include <linux/module.h>
+#include <net/net_namespace.h>
+#include <linux/sunrpc/rpc_pipe_fs.h>
+#include <linux/sunrpc/clnt.h>
+#include <linux/nfsd/cld.h>
 
 #include "nfsd.h"
 #include "state.h"
 #include "vfs.h"
+#include "netns.h"
 
 #define NFSDDBG_FACILITY                NFSDDBG_PROC
 
+/* Declarations */
+struct nfsd4_client_tracking_ops {
+	int (*init)(struct net *);
+	void (*exit)(struct net *);
+	void (*create)(struct nfs4_client *);
+	void (*remove)(struct nfs4_client *);
+	int (*check)(struct nfs4_client *);
+	void (*grace_done)(struct net *, time_t);
+};
+
 /* Globals */
 static struct file *rec_file;
 static char user_recovery_dirname[PATH_MAX] = "/var/lib/nfs/v4recovery";
+static struct nfsd4_client_tracking_ops *client_tracking_ops;
 
 static int
 nfs4_save_creds(const struct cred **original_creds)
@@ -117,7 +136,8 @@
 	return status;
 }
 
-void nfsd4_create_clid_dir(struct nfs4_client *clp)
+static void
+nfsd4_create_clid_dir(struct nfs4_client *clp)
 {
 	const struct cred *original_cred;
 	char *dname = clp->cl_recdir;
@@ -126,9 +146,8 @@
 
 	dprintk("NFSD: nfsd4_create_clid_dir for \"%s\"\n", dname);
 
-	if (clp->cl_firststate)
+	if (test_and_set_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags))
 		return;
-	clp->cl_firststate = 1;
 	if (!rec_file)
 		return;
 	status = nfs4_save_creds(&original_cred);
@@ -265,19 +284,19 @@
 	return status;
 }
 
-void
+static void
 nfsd4_remove_clid_dir(struct nfs4_client *clp)
 {
 	const struct cred *original_cred;
 	int status;
 
-	if (!rec_file || !clp->cl_firststate)
+	if (!rec_file || !test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags))
 		return;
 
 	status = mnt_want_write_file(rec_file);
 	if (status)
 		goto out;
-	clp->cl_firststate = 0;
+	clear_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags);
 
 	status = nfs4_save_creds(&original_cred);
 	if (status < 0)
@@ -292,7 +311,6 @@
 	if (status)
 		printk("NFSD: Failed to remove expired client state directory"
 				" %.*s\n", HEXDIR_LEN, clp->cl_recdir);
-	return;
 }
 
 static int
@@ -311,8 +329,9 @@
 	return 0;
 }
 
-void
-nfsd4_recdir_purge_old(void) {
+static void
+nfsd4_recdir_purge_old(struct net *net, time_t boot_time)
+{
 	int status;
 
 	if (!rec_file)
@@ -343,7 +362,7 @@
 	return 0;
 }
 
-int
+static int
 nfsd4_recdir_load(void) {
 	int status;
 
@@ -361,8 +380,8 @@
  * Hold reference to the recovery directory.
  */
 
-void
-nfsd4_init_recdir()
+static int
+nfsd4_init_recdir(void)
 {
 	const struct cred *original_cred;
 	int status;
@@ -377,20 +396,44 @@
 		printk("NFSD: Unable to change credentials to find recovery"
 		       " directory: error %d\n",
 		       status);
-		return;
+		return status;
 	}
 
 	rec_file = filp_open(user_recovery_dirname, O_RDONLY | O_DIRECTORY, 0);
 	if (IS_ERR(rec_file)) {
 		printk("NFSD: unable to find recovery directory %s\n",
 				user_recovery_dirname);
+		status = PTR_ERR(rec_file);
 		rec_file = NULL;
 	}
 
 	nfs4_reset_creds(original_cred);
+	return status;
 }
 
-void
+static int
+nfsd4_load_reboot_recovery_data(struct net *net)
+{
+	int status;
+
+	/* XXX: The legacy code won't work in a container */
+	if (net != &init_net) {
+		WARN(1, KERN_ERR "NFSD: attempt to initialize legacy client "
+			"tracking in a container!\n");
+		return -EINVAL;
+	}
+
+	nfs4_lock_state();
+	status = nfsd4_init_recdir();
+	if (!status)
+		status = nfsd4_recdir_load();
+	nfs4_unlock_state();
+	if (status)
+		printk(KERN_ERR "NFSD: Failure reading reboot recovery data\n");
+	return status;
+}
+
+static void
 nfsd4_shutdown_recdir(void)
 {
 	if (!rec_file)
@@ -399,6 +442,13 @@
 	rec_file = NULL;
 }
 
+static void
+nfsd4_legacy_tracking_exit(struct net *net)
+{
+	nfs4_release_reclaim();
+	nfsd4_shutdown_recdir();
+}
+
 /*
  * Change the NFSv4 recovery directory to recdir.
  */
@@ -425,3 +475,572 @@
 {
 	return user_recovery_dirname;
 }
+
+static int
+nfsd4_check_legacy_client(struct nfs4_client *clp)
+{
+	/* did we already find that this client is stable? */
+	if (test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags))
+		return 0;
+
+	/* look for it in the reclaim hashtable otherwise */
+	if (nfsd4_find_reclaim_client(clp)) {
+		set_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags);
+		return 0;
+	}
+
+	return -ENOENT;
+}
+
+static struct nfsd4_client_tracking_ops nfsd4_legacy_tracking_ops = {
+	.init		= nfsd4_load_reboot_recovery_data,
+	.exit		= nfsd4_legacy_tracking_exit,
+	.create		= nfsd4_create_clid_dir,
+	.remove		= nfsd4_remove_clid_dir,
+	.check		= nfsd4_check_legacy_client,
+	.grace_done	= nfsd4_recdir_purge_old,
+};
+
+/* Globals */
+#define NFSD_PIPE_DIR		"nfsd"
+#define NFSD_CLD_PIPE		"cld"
+
+/* per-net-ns structure for holding cld upcall info */
+struct cld_net {
+	struct rpc_pipe		*cn_pipe;
+	spinlock_t		 cn_lock;
+	struct list_head	 cn_list;
+	unsigned int		 cn_xid;
+};
+
+struct cld_upcall {
+	struct list_head	 cu_list;
+	struct cld_net		*cu_net;
+	struct task_struct	*cu_task;
+	struct cld_msg		 cu_msg;
+};
+
+static int
+__cld_pipe_upcall(struct rpc_pipe *pipe, struct cld_msg *cmsg)
+{
+	int ret;
+	struct rpc_pipe_msg msg;
+
+	memset(&msg, 0, sizeof(msg));
+	msg.data = cmsg;
+	msg.len = sizeof(*cmsg);
+
+	/*
+	 * Set task state before we queue the upcall. That prevents
+	 * wake_up_process in the downcall from racing with schedule.
+	 */
+	set_current_state(TASK_UNINTERRUPTIBLE);
+	ret = rpc_queue_upcall(pipe, &msg);
+	if (ret < 0) {
+		set_current_state(TASK_RUNNING);
+		goto out;
+	}
+
+	schedule();
+	set_current_state(TASK_RUNNING);
+
+	if (msg.errno < 0)
+		ret = msg.errno;
+out:
+	return ret;
+}
+
+static int
+cld_pipe_upcall(struct rpc_pipe *pipe, struct cld_msg *cmsg)
+{
+	int ret;
+
+	/*
+	 * -EAGAIN occurs when pipe is closed and reopened while there are
+	 *  upcalls queued.
+	 */
+	do {
+		ret = __cld_pipe_upcall(pipe, cmsg);
+	} while (ret == -EAGAIN);
+
+	return ret;
+}
+
+static ssize_t
+cld_pipe_downcall(struct file *filp, const char __user *src, size_t mlen)
+{
+	struct cld_upcall *tmp, *cup;
+	struct cld_msg *cmsg = (struct cld_msg *)src;
+	uint32_t xid;
+	struct nfsd_net *nn = net_generic(filp->f_dentry->d_sb->s_fs_info,
+						nfsd_net_id);
+	struct cld_net *cn = nn->cld_net;
+
+	if (mlen != sizeof(*cmsg)) {
+		dprintk("%s: got %lu bytes, expected %lu\n", __func__, mlen,
+			sizeof(*cmsg));
+		return -EINVAL;
+	}
+
+	/* copy just the xid so we can try to find that */
+	if (copy_from_user(&xid, &cmsg->cm_xid, sizeof(xid)) != 0) {
+		dprintk("%s: error when copying xid from userspace", __func__);
+		return -EFAULT;
+	}
+
+	/* walk the list and find corresponding xid */
+	cup = NULL;
+	spin_lock(&cn->cn_lock);
+	list_for_each_entry(tmp, &cn->cn_list, cu_list) {
+		if (get_unaligned(&tmp->cu_msg.cm_xid) == xid) {
+			cup = tmp;
+			list_del_init(&cup->cu_list);
+			break;
+		}
+	}
+	spin_unlock(&cn->cn_lock);
+
+	/* couldn't find upcall? */
+	if (!cup) {
+		dprintk("%s: couldn't find upcall -- xid=%u\n", __func__, xid);
+		return -EINVAL;
+	}
+
+	if (copy_from_user(&cup->cu_msg, src, mlen) != 0)
+		return -EFAULT;
+
+	wake_up_process(cup->cu_task);
+	return mlen;
+}
+
+static void
+cld_pipe_destroy_msg(struct rpc_pipe_msg *msg)
+{
+	struct cld_msg *cmsg = msg->data;
+	struct cld_upcall *cup = container_of(cmsg, struct cld_upcall,
+						 cu_msg);
+
+	/* errno >= 0 means we got a downcall */
+	if (msg->errno >= 0)
+		return;
+
+	wake_up_process(cup->cu_task);
+}
+
+static const struct rpc_pipe_ops cld_upcall_ops = {
+	.upcall		= rpc_pipe_generic_upcall,
+	.downcall	= cld_pipe_downcall,
+	.destroy_msg	= cld_pipe_destroy_msg,
+};
+
+static struct dentry *
+nfsd4_cld_register_sb(struct super_block *sb, struct rpc_pipe *pipe)
+{
+	struct dentry *dir, *dentry;
+
+	dir = rpc_d_lookup_sb(sb, NFSD_PIPE_DIR);
+	if (dir == NULL)
+		return ERR_PTR(-ENOENT);
+	dentry = rpc_mkpipe_dentry(dir, NFSD_CLD_PIPE, NULL, pipe);
+	dput(dir);
+	return dentry;
+}
+
+static void
+nfsd4_cld_unregister_sb(struct rpc_pipe *pipe)
+{
+	if (pipe->dentry)
+		rpc_unlink(pipe->dentry);
+}
+
+static struct dentry *
+nfsd4_cld_register_net(struct net *net, struct rpc_pipe *pipe)
+{
+	struct super_block *sb;
+	struct dentry *dentry;
+
+	sb = rpc_get_sb_net(net);
+	if (!sb)
+		return NULL;
+	dentry = nfsd4_cld_register_sb(sb, pipe);
+	rpc_put_sb_net(net);
+	return dentry;
+}
+
+static void
+nfsd4_cld_unregister_net(struct net *net, struct rpc_pipe *pipe)
+{
+	struct super_block *sb;
+
+	sb = rpc_get_sb_net(net);
+	if (sb) {
+		nfsd4_cld_unregister_sb(pipe);
+		rpc_put_sb_net(net);
+	}
+}
+
+/* Initialize rpc_pipefs pipe for communication with client tracking daemon */
+static int
+nfsd4_init_cld_pipe(struct net *net)
+{
+	int ret;
+	struct dentry *dentry;
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	struct cld_net *cn;
+
+	if (nn->cld_net)
+		return 0;
+
+	cn = kzalloc(sizeof(*cn), GFP_KERNEL);
+	if (!cn) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	cn->cn_pipe = rpc_mkpipe_data(&cld_upcall_ops, RPC_PIPE_WAIT_FOR_OPEN);
+	if (IS_ERR(cn->cn_pipe)) {
+		ret = PTR_ERR(cn->cn_pipe);
+		goto err;
+	}
+	spin_lock_init(&cn->cn_lock);
+	INIT_LIST_HEAD(&cn->cn_list);
+
+	dentry = nfsd4_cld_register_net(net, cn->cn_pipe);
+	if (IS_ERR(dentry)) {
+		ret = PTR_ERR(dentry);
+		goto err_destroy_data;
+	}
+
+	cn->cn_pipe->dentry = dentry;
+	nn->cld_net = cn;
+	return 0;
+
+err_destroy_data:
+	rpc_destroy_pipe_data(cn->cn_pipe);
+err:
+	kfree(cn);
+	printk(KERN_ERR "NFSD: unable to create nfsdcld upcall pipe (%d)\n",
+			ret);
+	return ret;
+}
+
+static void
+nfsd4_remove_cld_pipe(struct net *net)
+{
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	struct cld_net *cn = nn->cld_net;
+
+	nfsd4_cld_unregister_net(net, cn->cn_pipe);
+	rpc_destroy_pipe_data(cn->cn_pipe);
+	kfree(nn->cld_net);
+	nn->cld_net = NULL;
+}
+
+static struct cld_upcall *
+alloc_cld_upcall(struct cld_net *cn)
+{
+	struct cld_upcall *new, *tmp;
+
+	new = kzalloc(sizeof(*new), GFP_KERNEL);
+	if (!new)
+		return new;
+
+	/* FIXME: hard cap on number in flight? */
+restart_search:
+	spin_lock(&cn->cn_lock);
+	list_for_each_entry(tmp, &cn->cn_list, cu_list) {
+		if (tmp->cu_msg.cm_xid == cn->cn_xid) {
+			cn->cn_xid++;
+			spin_unlock(&cn->cn_lock);
+			goto restart_search;
+		}
+	}
+	new->cu_task = current;
+	new->cu_msg.cm_vers = CLD_UPCALL_VERSION;
+	put_unaligned(cn->cn_xid++, &new->cu_msg.cm_xid);
+	new->cu_net = cn;
+	list_add(&new->cu_list, &cn->cn_list);
+	spin_unlock(&cn->cn_lock);
+
+	dprintk("%s: allocated xid %u\n", __func__, new->cu_msg.cm_xid);
+
+	return new;
+}
+
+static void
+free_cld_upcall(struct cld_upcall *victim)
+{
+	struct cld_net *cn = victim->cu_net;
+
+	spin_lock(&cn->cn_lock);
+	list_del(&victim->cu_list);
+	spin_unlock(&cn->cn_lock);
+	kfree(victim);
+}
+
+/* Ask daemon to create a new record */
+static void
+nfsd4_cld_create(struct nfs4_client *clp)
+{
+	int ret;
+	struct cld_upcall *cup;
+	/* FIXME: determine net from clp */
+	struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id);
+	struct cld_net *cn = nn->cld_net;
+
+	/* Don't upcall if it's already stored */
+	if (test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags))
+		return;
+
+	cup = alloc_cld_upcall(cn);
+	if (!cup) {
+		ret = -ENOMEM;
+		goto out_err;
+	}
+
+	cup->cu_msg.cm_cmd = Cld_Create;
+	cup->cu_msg.cm_u.cm_name.cn_len = clp->cl_name.len;
+	memcpy(cup->cu_msg.cm_u.cm_name.cn_id, clp->cl_name.data,
+			clp->cl_name.len);
+
+	ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_msg);
+	if (!ret) {
+		ret = cup->cu_msg.cm_status;
+		set_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags);
+	}
+
+	free_cld_upcall(cup);
+out_err:
+	if (ret)
+		printk(KERN_ERR "NFSD: Unable to create client "
+				"record on stable storage: %d\n", ret);
+}
+
+/* Ask daemon to create a new record */
+static void
+nfsd4_cld_remove(struct nfs4_client *clp)
+{
+	int ret;
+	struct cld_upcall *cup;
+	/* FIXME: determine net from clp */
+	struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id);
+	struct cld_net *cn = nn->cld_net;
+
+	/* Don't upcall if it's already removed */
+	if (!test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags))
+		return;
+
+	cup = alloc_cld_upcall(cn);
+	if (!cup) {
+		ret = -ENOMEM;
+		goto out_err;
+	}
+
+	cup->cu_msg.cm_cmd = Cld_Remove;
+	cup->cu_msg.cm_u.cm_name.cn_len = clp->cl_name.len;
+	memcpy(cup->cu_msg.cm_u.cm_name.cn_id, clp->cl_name.data,
+			clp->cl_name.len);
+
+	ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_msg);
+	if (!ret) {
+		ret = cup->cu_msg.cm_status;
+		clear_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags);
+	}
+
+	free_cld_upcall(cup);
+out_err:
+	if (ret)
+		printk(KERN_ERR "NFSD: Unable to remove client "
+				"record from stable storage: %d\n", ret);
+}
+
+/* Check for presence of a record, and update its timestamp */
+static int
+nfsd4_cld_check(struct nfs4_client *clp)
+{
+	int ret;
+	struct cld_upcall *cup;
+	/* FIXME: determine net from clp */
+	struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id);
+	struct cld_net *cn = nn->cld_net;
+
+	/* Don't upcall if one was already stored during this grace pd */
+	if (test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags))
+		return 0;
+
+	cup = alloc_cld_upcall(cn);
+	if (!cup) {
+		printk(KERN_ERR "NFSD: Unable to check client record on "
+				"stable storage: %d\n", -ENOMEM);
+		return -ENOMEM;
+	}
+
+	cup->cu_msg.cm_cmd = Cld_Check;
+	cup->cu_msg.cm_u.cm_name.cn_len = clp->cl_name.len;
+	memcpy(cup->cu_msg.cm_u.cm_name.cn_id, clp->cl_name.data,
+			clp->cl_name.len);
+
+	ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_msg);
+	if (!ret) {
+		ret = cup->cu_msg.cm_status;
+		set_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags);
+	}
+
+	free_cld_upcall(cup);
+	return ret;
+}
+
+static void
+nfsd4_cld_grace_done(struct net *net, time_t boot_time)
+{
+	int ret;
+	struct cld_upcall *cup;
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	struct cld_net *cn = nn->cld_net;
+
+	cup = alloc_cld_upcall(cn);
+	if (!cup) {
+		ret = -ENOMEM;
+		goto out_err;
+	}
+
+	cup->cu_msg.cm_cmd = Cld_GraceDone;
+	cup->cu_msg.cm_u.cm_gracetime = (int64_t)boot_time;
+	ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_msg);
+	if (!ret)
+		ret = cup->cu_msg.cm_status;
+
+	free_cld_upcall(cup);
+out_err:
+	if (ret)
+		printk(KERN_ERR "NFSD: Unable to end grace period: %d\n", ret);
+}
+
+static struct nfsd4_client_tracking_ops nfsd4_cld_tracking_ops = {
+	.init		= nfsd4_init_cld_pipe,
+	.exit		= nfsd4_remove_cld_pipe,
+	.create		= nfsd4_cld_create,
+	.remove		= nfsd4_cld_remove,
+	.check		= nfsd4_cld_check,
+	.grace_done	= nfsd4_cld_grace_done,
+};
+
+int
+nfsd4_client_tracking_init(struct net *net)
+{
+	int status;
+	struct path path;
+
+	if (!client_tracking_ops) {
+		client_tracking_ops = &nfsd4_cld_tracking_ops;
+		status = kern_path(nfs4_recoverydir(), LOOKUP_FOLLOW, &path);
+		if (!status) {
+			if (S_ISDIR(path.dentry->d_inode->i_mode))
+				client_tracking_ops =
+						&nfsd4_legacy_tracking_ops;
+			path_put(&path);
+		}
+	}
+
+	status = client_tracking_ops->init(net);
+	if (status) {
+		printk(KERN_WARNING "NFSD: Unable to initialize client "
+				    "recovery tracking! (%d)\n", status);
+		client_tracking_ops = NULL;
+	}
+	return status;
+}
+
+void
+nfsd4_client_tracking_exit(struct net *net)
+{
+	if (client_tracking_ops) {
+		client_tracking_ops->exit(net);
+		client_tracking_ops = NULL;
+	}
+}
+
+void
+nfsd4_client_record_create(struct nfs4_client *clp)
+{
+	if (client_tracking_ops)
+		client_tracking_ops->create(clp);
+}
+
+void
+nfsd4_client_record_remove(struct nfs4_client *clp)
+{
+	if (client_tracking_ops)
+		client_tracking_ops->remove(clp);
+}
+
+int
+nfsd4_client_record_check(struct nfs4_client *clp)
+{
+	if (client_tracking_ops)
+		return client_tracking_ops->check(clp);
+
+	return -EOPNOTSUPP;
+}
+
+void
+nfsd4_record_grace_done(struct net *net, time_t boot_time)
+{
+	if (client_tracking_ops)
+		client_tracking_ops->grace_done(net, boot_time);
+}
+
+static int
+rpc_pipefs_event(struct notifier_block *nb, unsigned long event, void *ptr)
+{
+	struct super_block *sb = ptr;
+	struct net *net = sb->s_fs_info;
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	struct cld_net *cn = nn->cld_net;
+	struct dentry *dentry;
+	int ret = 0;
+
+	if (!try_module_get(THIS_MODULE))
+		return 0;
+
+	if (!cn) {
+		module_put(THIS_MODULE);
+		return 0;
+	}
+
+	switch (event) {
+	case RPC_PIPEFS_MOUNT:
+		dentry = nfsd4_cld_register_sb(sb, cn->cn_pipe);
+		if (IS_ERR(dentry)) {
+			ret = PTR_ERR(dentry);
+			break;
+		}
+		cn->cn_pipe->dentry = dentry;
+		break;
+	case RPC_PIPEFS_UMOUNT:
+		if (cn->cn_pipe->dentry)
+			nfsd4_cld_unregister_sb(cn->cn_pipe);
+		break;
+	default:
+		ret = -ENOTSUPP;
+		break;
+	}
+	module_put(THIS_MODULE);
+	return ret;
+}
+
+struct notifier_block nfsd4_cld_block = {
+	.notifier_call = rpc_pipefs_event,
+};
+
+int
+register_cld_notifier(void)
+{
+	return rpc_pipefs_notifier_register(&nfsd4_cld_block);
+}
+
+void
+unregister_cld_notifier(void)
+{
+	rpc_pipefs_notifier_unregister(&nfsd4_cld_block);
+}
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index c5cddd6..1841f8b 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -58,11 +58,15 @@
 static const stateid_t zero_stateid = {
 	/* all fields zero */
 };
+static const stateid_t currentstateid = {
+	.si_generation = 1,
+};
 
 static u64 current_sessionid = 1;
 
 #define ZERO_STATEID(stateid) (!memcmp((stateid), &zero_stateid, sizeof(stateid_t)))
 #define ONE_STATEID(stateid)  (!memcmp((stateid), &one_stateid, sizeof(stateid_t)))
+#define CURRENT_STATEID(stateid) (!memcmp((stateid), &currentstateid, sizeof(stateid_t)))
 
 /* forward declarations */
 static int check_for_locks(struct nfs4_file *filp, struct nfs4_lockowner *lowner);
@@ -91,6 +95,19 @@
 	mutex_lock(&client_mutex);
 }
 
+static void free_session(struct kref *);
+
+/* Must be called under the client_lock */
+static void nfsd4_put_session_locked(struct nfsd4_session *ses)
+{
+	kref_put(&ses->se_ref, free_session);
+}
+
+static void nfsd4_get_session(struct nfsd4_session *ses)
+{
+	kref_get(&ses->se_ref);
+}
+
 void
 nfs4_unlock_state(void)
 {
@@ -605,12 +622,20 @@
 	return sid->sequence % SESSION_HASH_SIZE;
 }
 
+#ifdef NFSD_DEBUG
 static inline void
 dump_sessionid(const char *fn, struct nfs4_sessionid *sessionid)
 {
 	u32 *ptr = (u32 *)(&sessionid->data[0]);
 	dprintk("%s: %u:%u:%u:%u\n", fn, ptr[0], ptr[1], ptr[2], ptr[3]);
 }
+#else
+static inline void
+dump_sessionid(const char *fn, struct nfs4_sessionid *sessionid)
+{
+}
+#endif
+
 
 static void
 gen_sessionid(struct nfsd4_session *ses)
@@ -832,11 +857,12 @@
 	spin_unlock(&clp->cl_lock);
 }
 
-void free_session(struct kref *kref)
+static void free_session(struct kref *kref)
 {
 	struct nfsd4_session *ses;
 	int mem;
 
+	BUG_ON(!spin_is_locked(&client_lock));
 	ses = container_of(kref, struct nfsd4_session, se_ref);
 	nfsd4_del_conns(ses);
 	spin_lock(&nfsd_drc_lock);
@@ -847,6 +873,13 @@
 	kfree(ses);
 }
 
+void nfsd4_put_session(struct nfsd4_session *ses)
+{
+	spin_lock(&client_lock);
+	nfsd4_put_session_locked(ses);
+	spin_unlock(&client_lock);
+}
+
 static struct nfsd4_session *alloc_init_session(struct svc_rqst *rqstp, struct nfs4_client *clp, struct nfsd4_create_session *cses)
 {
 	struct nfsd4_session *new;
@@ -894,7 +927,9 @@
 	status = nfsd4_new_conn_from_crses(rqstp, new);
 	/* whoops: benny points out, status is ignored! (err, or bogus) */
 	if (status) {
+		spin_lock(&client_lock);
 		free_session(&new->se_ref);
+		spin_unlock(&client_lock);
 		return NULL;
 	}
 	if (cses->flags & SESSION4_BACK_CHAN) {
@@ -1006,12 +1041,13 @@
 static inline void
 free_client(struct nfs4_client *clp)
 {
+	BUG_ON(!spin_is_locked(&client_lock));
 	while (!list_empty(&clp->cl_sessions)) {
 		struct nfsd4_session *ses;
 		ses = list_entry(clp->cl_sessions.next, struct nfsd4_session,
 				se_perclnt);
 		list_del(&ses->se_perclnt);
-		nfsd4_put_session(ses);
+		nfsd4_put_session_locked(ses);
 	}
 	if (clp->cl_cred.cr_group_info)
 		put_group_info(clp->cl_cred.cr_group_info);
@@ -1138,12 +1174,12 @@
 
 static void gen_confirm(struct nfs4_client *clp)
 {
+	__be32 verf[2];
 	static u32 i;
-	u32 *p;
 
-	p = (u32 *)clp->cl_confirm.data;
-	*p++ = get_seconds();
-	*p++ = i++;
+	verf[0] = (__be32)get_seconds();
+	verf[1] = (__be32)i++;
+	memcpy(clp->cl_confirm.data, verf, sizeof(clp->cl_confirm.data));
 }
 
 static struct nfs4_stid *find_stateid(struct nfs4_client *cl, stateid_t *t)
@@ -1180,7 +1216,9 @@
 	if (princ) {
 		clp->cl_principal = kstrdup(princ, GFP_KERNEL);
 		if (clp->cl_principal == NULL) {
+			spin_lock(&client_lock);
 			free_client(clp);
+			spin_unlock(&client_lock);
 			return NULL;
 		}
 	}
@@ -1347,6 +1385,7 @@
 	slot->sl_opcnt = resp->opcnt;
 	slot->sl_status = resp->cstate.status;
 
+	slot->sl_flags |= NFSD4_SLOT_INITIALIZED;
 	if (nfsd4_not_cached(resp)) {
 		slot->sl_datalen = 0;
 		return;
@@ -1374,15 +1413,12 @@
 	struct nfsd4_op *op;
 	struct nfsd4_slot *slot = resp->cstate.slot;
 
-	dprintk("--> %s resp->opcnt %d cachethis %u \n", __func__,
-		resp->opcnt, resp->cstate.slot->sl_cachethis);
-
 	/* Encode the replayed sequence operation */
 	op = &args->ops[resp->opcnt - 1];
 	nfsd4_encode_operation(resp, op);
 
 	/* Return nfserr_retry_uncached_rep in next operation. */
-	if (args->opcnt > 1 && slot->sl_cachethis == 0) {
+	if (args->opcnt > 1 && !(slot->sl_flags & NFSD4_SLOT_CACHETHIS)) {
 		op = &args->ops[resp->opcnt++];
 		op->status = nfserr_retry_uncached_rep;
 		nfsd4_encode_operation(resp, op);
@@ -1575,16 +1611,11 @@
 		else
 			return nfserr_seq_misordered;
 	}
-	/* Normal */
+	/* Note unsigned 32-bit arithmetic handles wraparound: */
 	if (likely(seqid == slot_seqid + 1))
 		return nfs_ok;
-	/* Replay */
 	if (seqid == slot_seqid)
 		return nfserr_replay_cache;
-	/* Wraparound */
-	if (seqid == 1 && (slot_seqid + 1) == 0)
-		return nfs_ok;
-	/* Misordered replay or misordered new request */
 	return nfserr_seq_misordered;
 }
 
@@ -1815,9 +1846,10 @@
 	nfsd4_probe_callback_sync(ses->se_client);
 	nfs4_unlock_state();
 
+	spin_lock(&client_lock);
 	nfsd4_del_conns(ses);
-
-	nfsd4_put_session(ses);
+	nfsd4_put_session_locked(ses);
+	spin_unlock(&client_lock);
 	status = nfs_ok;
 out:
 	dprintk("%s returns %d\n", __func__, ntohl(status));
@@ -1921,8 +1953,12 @@
 	 * sr_highest_slotid and the sr_target_slot id to maxslots */
 	seq->maxslots = session->se_fchannel.maxreqs;
 
-	status = check_slot_seqid(seq->seqid, slot->sl_seqid, slot->sl_inuse);
+	status = check_slot_seqid(seq->seqid, slot->sl_seqid,
+					slot->sl_flags & NFSD4_SLOT_INUSE);
 	if (status == nfserr_replay_cache) {
+		status = nfserr_seq_misordered;
+		if (!(slot->sl_flags & NFSD4_SLOT_INITIALIZED))
+			goto out;
 		cstate->slot = slot;
 		cstate->session = session;
 		/* Return the cached reply status and set cstate->status
@@ -1938,9 +1974,12 @@
 	conn = NULL;
 
 	/* Success! bump slot seqid */
-	slot->sl_inuse = true;
 	slot->sl_seqid = seq->seqid;
-	slot->sl_cachethis = seq->cachethis;
+	slot->sl_flags |= NFSD4_SLOT_INUSE;
+	if (seq->cachethis)
+		slot->sl_flags |= NFSD4_SLOT_CACHETHIS;
+	else
+		slot->sl_flags &= ~NFSD4_SLOT_CACHETHIS;
 
 	cstate->slot = slot;
 	cstate->session = session;
@@ -2030,7 +2069,8 @@
 
 	nfs4_lock_state();
 	status = nfserr_complete_already;
-	if (cstate->session->se_client->cl_firststate)
+	if (test_and_set_bit(NFSD4_CLIENT_RECLAIM_COMPLETE,
+			     &cstate->session->se_client->cl_flags))
 		goto out;
 
 	status = nfserr_stale_clientid;
@@ -2045,7 +2085,7 @@
 		goto out;
 
 	status = nfs_ok;
-	nfsd4_create_clid_dir(cstate->session->se_client);
+	nfsd4_client_record_create(cstate->session->se_client);
 out:
 	nfs4_unlock_state();
 	return status;
@@ -2240,7 +2280,7 @@
 			conf = find_confirmed_client_by_str(unconf->cl_recdir,
 							    hash);
 			if (conf) {
-				nfsd4_remove_clid_dir(conf);
+				nfsd4_client_record_remove(conf);
 				expire_client(conf);
 			}
 			move_to_confirmed(unconf);
@@ -2633,8 +2673,6 @@
 
 static int share_access_to_flags(u32 share_access)
 {
-	share_access &= ~NFS4_SHARE_WANT_MASK;
-
 	return share_access == NFS4_SHARE_ACCESS_READ ? RD_STATE : WR_STATE;
 }
 
@@ -2776,10 +2814,9 @@
 
 
 static void
-nfs4_set_claim_prev(struct nfsd4_open *open)
+nfs4_set_claim_prev(struct nfsd4_open *open, bool has_session)
 {
 	open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED;
-	open->op_openowner->oo_owner.so_client->cl_firststate = 1;
 }
 
 /* Should we give out recallable state?: */
@@ -2855,6 +2892,27 @@
 	return 0;
 }
 
+static void nfsd4_open_deleg_none_ext(struct nfsd4_open *open, int status)
+{
+	open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE_EXT;
+	if (status == -EAGAIN)
+		open->op_why_no_deleg = WND4_CONTENTION;
+	else {
+		open->op_why_no_deleg = WND4_RESOURCE;
+		switch (open->op_deleg_want) {
+		case NFS4_SHARE_WANT_READ_DELEG:
+		case NFS4_SHARE_WANT_WRITE_DELEG:
+		case NFS4_SHARE_WANT_ANY_DELEG:
+			break;
+		case NFS4_SHARE_WANT_CANCEL:
+			open->op_why_no_deleg = WND4_CANCELLED;
+			break;
+		case NFS4_SHARE_WANT_NO_DELEG:
+			BUG();	/* not supposed to get here */
+		}
+	}
+}
+
 /*
  * Attempt to hand out a delegation.
  */
@@ -2864,7 +2922,7 @@
 	struct nfs4_delegation *dp;
 	struct nfs4_openowner *oo = container_of(stp->st_stateowner, struct nfs4_openowner, oo_owner);
 	int cb_up;
-	int status, flag = 0;
+	int status = 0, flag = 0;
 
 	cb_up = nfsd4_cb_channel_good(oo->oo_owner.so_client);
 	flag = NFS4_OPEN_DELEGATE_NONE;
@@ -2905,11 +2963,16 @@
 	dprintk("NFSD: delegation stateid=" STATEID_FMT "\n",
 		STATEID_VAL(&dp->dl_stid.sc_stateid));
 out:
-	if (open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS
-			&& flag == NFS4_OPEN_DELEGATE_NONE
-			&& open->op_delegate_type != NFS4_OPEN_DELEGATE_NONE)
-		dprintk("NFSD: WARNING: refusing delegation reclaim\n");
 	open->op_delegate_type = flag;
+	if (flag == NFS4_OPEN_DELEGATE_NONE) {
+		if (open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS &&
+		    open->op_delegate_type != NFS4_OPEN_DELEGATE_NONE)
+			dprintk("NFSD: WARNING: refusing delegation reclaim\n");
+
+		/* 4.1 client asking for a delegation? */
+		if (open->op_deleg_want)
+			nfsd4_open_deleg_none_ext(open, status);
+	}
 	return;
 out_free:
 	nfs4_put_delegation(dp);
@@ -2918,6 +2981,24 @@
 	goto out;
 }
 
+static void nfsd4_deleg_xgrade_none_ext(struct nfsd4_open *open,
+					struct nfs4_delegation *dp)
+{
+	if (open->op_deleg_want == NFS4_SHARE_WANT_READ_DELEG &&
+	    dp->dl_type == NFS4_OPEN_DELEGATE_WRITE) {
+		open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE_EXT;
+		open->op_why_no_deleg = WND4_NOT_SUPP_DOWNGRADE;
+	} else if (open->op_deleg_want == NFS4_SHARE_WANT_WRITE_DELEG &&
+		   dp->dl_type == NFS4_OPEN_DELEGATE_WRITE) {
+		open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE_EXT;
+		open->op_why_no_deleg = WND4_NOT_SUPP_UPGRADE;
+	}
+	/* Otherwise the client must be confused wanting a delegation
+	 * it already has, therefore we don't return
+	 * NFS4_OPEN_DELEGATE_NONE_EXT and reason.
+	 */
+}
+
 /*
  * called with nfs4_lock_state() held.
  */
@@ -2979,24 +3060,36 @@
 	update_stateid(&stp->st_stid.sc_stateid);
 	memcpy(&open->op_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t));
 
-	if (nfsd4_has_session(&resp->cstate))
+	if (nfsd4_has_session(&resp->cstate)) {
 		open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED;
 
+		if (open->op_deleg_want & NFS4_SHARE_WANT_NO_DELEG) {
+			open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE_EXT;
+			open->op_why_no_deleg = WND4_NOT_WANTED;
+			goto nodeleg;
+		}
+	}
+
 	/*
 	* Attempt to hand out a delegation. No error return, because the
 	* OPEN succeeds even if we fail.
 	*/
 	nfs4_open_delegation(current_fh, open, stp);
-
+nodeleg:
 	status = nfs_ok;
 
 	dprintk("%s: stateid=" STATEID_FMT "\n", __func__,
 		STATEID_VAL(&stp->st_stid.sc_stateid));
 out:
+	/* 4.1 client trying to upgrade/downgrade delegation? */
+	if (open->op_delegate_type == NFS4_OPEN_DELEGATE_NONE && dp &&
+	    open->op_deleg_want)
+		nfsd4_deleg_xgrade_none_ext(open, dp);
+
 	if (fp)
 		put_nfs4_file(fp);
 	if (status == 0 && open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS)
-		nfs4_set_claim_prev(open);
+		nfs4_set_claim_prev(open, nfsd4_has_session(&resp->cstate));
 	/*
 	* To finish the open response, we just need to set the rflags.
 	*/
@@ -3066,7 +3159,7 @@
 nfsd4_end_grace(void)
 {
 	dprintk("NFSD: end of grace period\n");
-	nfsd4_recdir_purge_old();
+	nfsd4_record_grace_done(&init_net, boot_time);
 	locks_end_grace(&nfsd4_manager);
 	/*
 	 * Now that every NFSv4 client has had the chance to recover and
@@ -3115,7 +3208,7 @@
 		clp = list_entry(pos, struct nfs4_client, cl_lru);
 		dprintk("NFSD: purging unused client (clientid %08x)\n",
 			clp->cl_clientid.cl_id);
-		nfsd4_remove_clid_dir(clp);
+		nfsd4_client_record_remove(clp);
 		expire_client(clp);
 	}
 	spin_lock(&recall_lock);
@@ -3400,7 +3493,14 @@
 nfsd4_test_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		   struct nfsd4_test_stateid *test_stateid)
 {
-	/* real work is done during encoding */
+	struct nfsd4_test_stateid_id *stateid;
+	struct nfs4_client *cl = cstate->session->se_client;
+
+	nfs4_lock_state();
+	list_for_each_entry(stateid, &test_stateid->ts_stateid_list, ts_id_list)
+		stateid->ts_id_status = nfs4_validate_stateid(cl, &stateid->ts_id_stateid);
+	nfs4_unlock_state();
+
 	return nfs_ok;
 }
 
@@ -3539,7 +3639,7 @@
 	dprintk("NFSD: %s: success, seqid=%d stateid=" STATEID_FMT "\n",
 		__func__, oc->oc_seqid, STATEID_VAL(&stp->st_stid.sc_stateid));
 
-	nfsd4_create_clid_dir(oo->oo_owner.so_client);
+	nfsd4_client_record_create(oo->oo_owner.so_client);
 	status = nfs_ok;
 out:
 	if (!cstate->replay_owner)
@@ -3596,7 +3696,9 @@
 			cstate->current_fh.fh_dentry->d_name.name);
 
 	/* We don't yet support WANT bits: */
-	od->od_share_access &= NFS4_SHARE_ACCESS_MASK;
+	if (od->od_deleg_want)
+		dprintk("NFSD: %s: od_deleg_want=0x%x ignored\n", __func__,
+			od->od_deleg_want);
 
 	nfs4_lock_state();
 	status = nfs4_preprocess_confirmed_seqid_op(cstate, od->od_seqid,
@@ -4353,7 +4455,9 @@
 	struct nfs4_client *clp;
 
 	clp = find_confirmed_client_by_str(name, strhashval);
-	return clp ? 1 : 0;
+	if (!clp)
+		return 0;
+	return test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags);
 }
 
 /*
@@ -4377,7 +4481,7 @@
 	return 1;
 }
 
-static void
+void
 nfs4_release_reclaim(void)
 {
 	struct nfs4_client_reclaim *crp = NULL;
@@ -4397,19 +4501,12 @@
 
 /*
  * called from OPEN, CLAIM_PREVIOUS with a new clientid. */
-static struct nfs4_client_reclaim *
-nfs4_find_reclaim_client(clientid_t *clid)
+struct nfs4_client_reclaim *
+nfsd4_find_reclaim_client(struct nfs4_client *clp)
 {
 	unsigned int strhashval;
-	struct nfs4_client *clp;
 	struct nfs4_client_reclaim *crp = NULL;
 
-
-	/* find clientid in conf_id_hashtbl */
-	clp = find_confirmed_client(clid);
-	if (clp == NULL)
-		return NULL;
-
 	dprintk("NFSD: nfs4_find_reclaim_client for %.*s with recdir %s\n",
 		            clp->cl_name.len, clp->cl_name.data,
 			    clp->cl_recdir);
@@ -4430,7 +4527,14 @@
 __be32
 nfs4_check_open_reclaim(clientid_t *clid)
 {
-	return nfs4_find_reclaim_client(clid) ? nfs_ok : nfserr_reclaim_bad;
+	struct nfs4_client *clp;
+
+	/* find clientid in conf_id_hashtbl */
+	clp = find_confirmed_client(clid);
+	if (clp == NULL)
+		return nfserr_reclaim_bad;
+
+	return nfsd4_client_record_check(clp) ? nfserr_reclaim_bad : nfs_ok;
 }
 
 #ifdef CONFIG_NFSD_FAULT_INJECTION
@@ -4442,7 +4546,7 @@
 
 	nfs4_lock_state();
 	list_for_each_entry_safe(clp, next, &client_lru, cl_lru) {
-		nfsd4_remove_clid_dir(clp);
+		nfsd4_client_record_remove(clp);
 		expire_client(clp);
 		if (++count == num)
 			break;
@@ -4577,19 +4681,6 @@
 	reclaim_str_hashtbl_size = 0;
 }
 
-static void
-nfsd4_load_reboot_recovery_data(void)
-{
-	int status;
-
-	nfs4_lock_state();
-	nfsd4_init_recdir();
-	status = nfsd4_recdir_load();
-	nfs4_unlock_state();
-	if (status)
-		printk("NFSD: Failure reading reboot recovery data\n");
-}
-
 /*
  * Since the lifetime of a delegation isn't limited to that of an open, a
  * client may quite reasonably hang on to a delegation as long as it has
@@ -4613,21 +4704,34 @@
 
 /* initialization to perform when the nfsd service is started: */
 
-static int
-__nfs4_state_start(void)
+int
+nfs4_state_start(void)
 {
 	int ret;
 
+	/*
+	 * FIXME: For now, we hang most of the pernet global stuff off of
+	 * init_net until nfsd is fully containerized. Eventually, we'll
+	 * need to pass a net pointer into this function, take a reference
+	 * to that instead and then do most of the rest of this on a per-net
+	 * basis.
+	 */
+	get_net(&init_net);
+	nfsd4_client_tracking_init(&init_net);
 	boot_time = get_seconds();
 	locks_start_grace(&nfsd4_manager);
 	printk(KERN_INFO "NFSD: starting %ld-second grace period\n",
 	       nfsd4_grace);
 	ret = set_callback_cred();
-	if (ret)
-		return -ENOMEM;
+	if (ret) {
+		ret = -ENOMEM;
+		goto out_recovery;
+	}
 	laundry_wq = create_singlethread_workqueue("nfsd4");
-	if (laundry_wq == NULL)
-		return -ENOMEM;
+	if (laundry_wq == NULL) {
+		ret = -ENOMEM;
+		goto out_recovery;
+	}
 	ret = nfsd4_create_callback_queue();
 	if (ret)
 		goto out_free_laundry;
@@ -4636,16 +4740,12 @@
 	return 0;
 out_free_laundry:
 	destroy_workqueue(laundry_wq);
+out_recovery:
+	nfsd4_client_tracking_exit(&init_net);
+	put_net(&init_net);
 	return ret;
 }
 
-int
-nfs4_state_start(void)
-{
-	nfsd4_load_reboot_recovery_data();
-	return __nfs4_state_start();
-}
-
 static void
 __nfs4_state_shutdown(void)
 {
@@ -4676,7 +4776,8 @@
 		unhash_delegation(dp);
 	}
 
-	nfsd4_shutdown_recdir();
+	nfsd4_client_tracking_exit(&init_net);
+	put_net(&init_net);
 }
 
 void
@@ -4686,8 +4787,108 @@
 	destroy_workqueue(laundry_wq);
 	locks_end_grace(&nfsd4_manager);
 	nfs4_lock_state();
-	nfs4_release_reclaim();
 	__nfs4_state_shutdown();
 	nfs4_unlock_state();
 	nfsd4_destroy_callback_queue();
 }
+
+static void
+get_stateid(struct nfsd4_compound_state *cstate, stateid_t *stateid)
+{
+	if (HAS_STATE_ID(cstate, CURRENT_STATE_ID_FLAG) && CURRENT_STATEID(stateid))
+		memcpy(stateid, &cstate->current_stateid, sizeof(stateid_t));
+}
+
+static void
+put_stateid(struct nfsd4_compound_state *cstate, stateid_t *stateid)
+{
+	if (cstate->minorversion) {
+		memcpy(&cstate->current_stateid, stateid, sizeof(stateid_t));
+		SET_STATE_ID(cstate, CURRENT_STATE_ID_FLAG);
+	}
+}
+
+void
+clear_current_stateid(struct nfsd4_compound_state *cstate)
+{
+	CLEAR_STATE_ID(cstate, CURRENT_STATE_ID_FLAG);
+}
+
+/*
+ * functions to set current state id
+ */
+void
+nfsd4_set_opendowngradestateid(struct nfsd4_compound_state *cstate, struct nfsd4_open_downgrade *odp)
+{
+	put_stateid(cstate, &odp->od_stateid);
+}
+
+void
+nfsd4_set_openstateid(struct nfsd4_compound_state *cstate, struct nfsd4_open *open)
+{
+	put_stateid(cstate, &open->op_stateid);
+}
+
+void
+nfsd4_set_closestateid(struct nfsd4_compound_state *cstate, struct nfsd4_close *close)
+{
+	put_stateid(cstate, &close->cl_stateid);
+}
+
+void
+nfsd4_set_lockstateid(struct nfsd4_compound_state *cstate, struct nfsd4_lock *lock)
+{
+	put_stateid(cstate, &lock->lk_resp_stateid);
+}
+
+/*
+ * functions to consume current state id
+ */
+
+void
+nfsd4_get_opendowngradestateid(struct nfsd4_compound_state *cstate, struct nfsd4_open_downgrade *odp)
+{
+	get_stateid(cstate, &odp->od_stateid);
+}
+
+void
+nfsd4_get_delegreturnstateid(struct nfsd4_compound_state *cstate, struct nfsd4_delegreturn *drp)
+{
+	get_stateid(cstate, &drp->dr_stateid);
+}
+
+void
+nfsd4_get_freestateid(struct nfsd4_compound_state *cstate, struct nfsd4_free_stateid *fsp)
+{
+	get_stateid(cstate, &fsp->fr_stateid);
+}
+
+void
+nfsd4_get_setattrstateid(struct nfsd4_compound_state *cstate, struct nfsd4_setattr *setattr)
+{
+	get_stateid(cstate, &setattr->sa_stateid);
+}
+
+void
+nfsd4_get_closestateid(struct nfsd4_compound_state *cstate, struct nfsd4_close *close)
+{
+	get_stateid(cstate, &close->cl_stateid);
+}
+
+void
+nfsd4_get_lockustateid(struct nfsd4_compound_state *cstate, struct nfsd4_locku *locku)
+{
+	get_stateid(cstate, &locku->lu_stateid);
+}
+
+void
+nfsd4_get_readstateid(struct nfsd4_compound_state *cstate, struct nfsd4_read *read)
+{
+	get_stateid(cstate, &read->rd_stateid);
+}
+
+void
+nfsd4_get_writestateid(struct nfsd4_compound_state *cstate, struct nfsd4_write *write)
+{
+	get_stateid(cstate, &write->wr_stateid);
+}
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 0ec5a1b..bcd8904 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -133,22 +133,6 @@
 	}					\
 } while (0)
 
-static void save_buf(struct nfsd4_compoundargs *argp, struct nfsd4_saved_compoundargs *savep)
-{
-	savep->p        = argp->p;
-	savep->end      = argp->end;
-	savep->pagelen  = argp->pagelen;
-	savep->pagelist = argp->pagelist;
-}
-
-static void restore_buf(struct nfsd4_compoundargs *argp, struct nfsd4_saved_compoundargs *savep)
-{
-	argp->p        = savep->p;
-	argp->end      = savep->end;
-	argp->pagelen  = savep->pagelen;
-	argp->pagelist = savep->pagelist;
-}
-
 static __be32 *read_buf(struct nfsd4_compoundargs *argp, u32 nbytes)
 {
 	/* We want more bytes than seem to be available.
@@ -638,14 +622,18 @@
 	DECODE_TAIL;
 }
 
-static __be32 nfsd4_decode_share_access(struct nfsd4_compoundargs *argp, u32 *x)
+static __be32 nfsd4_decode_share_access(struct nfsd4_compoundargs *argp, u32 *share_access, u32 *deleg_want, u32 *deleg_when)
 {
 	__be32 *p;
 	u32 w;
 
 	READ_BUF(4);
 	READ32(w);
-	*x = w;
+	*share_access = w & NFS4_SHARE_ACCESS_MASK;
+	*deleg_want = w & NFS4_SHARE_WANT_MASK;
+	if (deleg_when)
+		*deleg_when = w & NFS4_SHARE_WHEN_MASK;
+
 	switch (w & NFS4_SHARE_ACCESS_MASK) {
 	case NFS4_SHARE_ACCESS_READ:
 	case NFS4_SHARE_ACCESS_WRITE:
@@ -673,6 +661,9 @@
 	w &= ~NFS4_SHARE_WANT_MASK;
 	if (!w)
 		return nfs_ok;
+
+	if (!deleg_when)	/* open_downgrade */
+		return nfserr_inval;
 	switch (w) {
 	case NFS4_SHARE_SIGNAL_DELEG_WHEN_RESRC_AVAIL:
 	case NFS4_SHARE_PUSH_DELEG_WHEN_UNCONTENDED:
@@ -719,6 +710,7 @@
 nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open)
 {
 	DECODE_HEAD;
+	u32 dummy;
 
 	memset(open->op_bmval, 0, sizeof(open->op_bmval));
 	open->op_iattr.ia_valid = 0;
@@ -727,7 +719,9 @@
 	/* seqid, share_access, share_deny, clientid, ownerlen */
 	READ_BUF(4);
 	READ32(open->op_seqid);
-	status = nfsd4_decode_share_access(argp, &open->op_share_access);
+	/* decode, yet ignore deleg_when until supported */
+	status = nfsd4_decode_share_access(argp, &open->op_share_access,
+					   &open->op_deleg_want, &dummy);
 	if (status)
 		goto xdr_error;
 	status = nfsd4_decode_share_deny(argp, &open->op_share_deny);
@@ -755,14 +749,14 @@
 				goto out;
 			break;
 		case NFS4_CREATE_EXCLUSIVE:
-			READ_BUF(8);
-			COPYMEM(open->op_verf.data, 8);
+			READ_BUF(NFS4_VERIFIER_SIZE);
+			COPYMEM(open->op_verf.data, NFS4_VERIFIER_SIZE);
 			break;
 		case NFS4_CREATE_EXCLUSIVE4_1:
 			if (argp->minorversion < 1)
 				goto xdr_error;
-			READ_BUF(8);
-			COPYMEM(open->op_verf.data, 8);
+			READ_BUF(NFS4_VERIFIER_SIZE);
+			COPYMEM(open->op_verf.data, NFS4_VERIFIER_SIZE);
 			status = nfsd4_decode_fattr(argp, open->op_bmval,
 				&open->op_iattr, &open->op_acl);
 			if (status)
@@ -848,7 +842,8 @@
 		return status;
 	READ_BUF(4);
 	READ32(open_down->od_seqid);
-	status = nfsd4_decode_share_access(argp, &open_down->od_share_access);
+	status = nfsd4_decode_share_access(argp, &open_down->od_share_access,
+					   &open_down->od_deleg_want, NULL);
 	if (status)
 		return status;
 	status = nfsd4_decode_share_deny(argp, &open_down->od_share_deny);
@@ -994,8 +989,8 @@
 {
 	DECODE_HEAD;
 
-	READ_BUF(8);
-	COPYMEM(setclientid->se_verf.data, 8);
+	READ_BUF(NFS4_VERIFIER_SIZE);
+	COPYMEM(setclientid->se_verf.data, NFS4_VERIFIER_SIZE);
 
 	status = nfsd4_decode_opaque(argp, &setclientid->se_name);
 	if (status)
@@ -1020,9 +1015,9 @@
 {
 	DECODE_HEAD;
 
-	READ_BUF(8 + sizeof(nfs4_verifier));
+	READ_BUF(8 + NFS4_VERIFIER_SIZE);
 	COPYMEM(&scd_c->sc_clientid, 8);
-	COPYMEM(&scd_c->sc_confirm, sizeof(nfs4_verifier));
+	COPYMEM(&scd_c->sc_confirm, NFS4_VERIFIER_SIZE);
 
 	DECODE_TAIL;
 }
@@ -1385,26 +1380,29 @@
 static __be32
 nfsd4_decode_test_stateid(struct nfsd4_compoundargs *argp, struct nfsd4_test_stateid *test_stateid)
 {
-	unsigned int nbytes;
-	stateid_t si;
 	int i;
-	__be32 *p;
-	__be32 status;
+	__be32 *p, status;
+	struct nfsd4_test_stateid_id *stateid;
 
 	READ_BUF(4);
 	test_stateid->ts_num_ids = ntohl(*p++);
 
-	nbytes = test_stateid->ts_num_ids * sizeof(stateid_t);
-	if (nbytes > (u32)((char *)argp->end - (char *)argp->p))
-		goto xdr_error;
-
-	test_stateid->ts_saved_args = argp;
-	save_buf(argp, &test_stateid->ts_savedp);
+	INIT_LIST_HEAD(&test_stateid->ts_stateid_list);
 
 	for (i = 0; i < test_stateid->ts_num_ids; i++) {
-		status = nfsd4_decode_stateid(argp, &si);
+		stateid = kmalloc(sizeof(struct nfsd4_test_stateid_id), GFP_KERNEL);
+		if (!stateid) {
+			status = PTR_ERR(stateid);
+			goto out;
+		}
+
+		defer_free(argp, kfree, stateid);
+		INIT_LIST_HEAD(&stateid->ts_id_list);
+		list_add_tail(&stateid->ts_id_list, &test_stateid->ts_stateid_list);
+
+		status = nfsd4_decode_stateid(argp, &stateid->ts_id_stateid);
 		if (status)
-			return status;
+			goto out;
 	}
 
 	status = 0;
@@ -2661,8 +2659,8 @@
 	__be32 *p;
 
 	if (!nfserr) {
-		RESERVE_SPACE(8);
-		WRITEMEM(commit->co_verf.data, 8);
+		RESERVE_SPACE(NFS4_VERIFIER_SIZE);
+		WRITEMEM(commit->co_verf.data, NFS4_VERIFIER_SIZE);
 		ADJUST_ARGS();
 	}
 	return nfserr;
@@ -2851,6 +2849,20 @@
 		WRITE32(0);   /* XXX: is NULL principal ok? */
 		ADJUST_ARGS();
 		break;
+	case NFS4_OPEN_DELEGATE_NONE_EXT: /* 4.1 */
+		switch (open->op_why_no_deleg) {
+		case WND4_CONTENTION:
+		case WND4_RESOURCE:
+			RESERVE_SPACE(8);
+			WRITE32(open->op_why_no_deleg);
+			WRITE32(0);	/* deleg signaling not supported yet */
+			break;
+		default:
+			RESERVE_SPACE(4);
+			WRITE32(open->op_why_no_deleg);
+		}
+		ADJUST_ARGS();
+		break;
 	default:
 		BUG();
 	}
@@ -3008,7 +3020,7 @@
 	if (resp->xbuf->page_len)
 		return nfserr_resource;
 
-	RESERVE_SPACE(8);  /* verifier */
+	RESERVE_SPACE(NFS4_VERIFIER_SIZE);
 	savep = p;
 
 	/* XXX: Following NFSv3, we ignore the READDIR verifier for now. */
@@ -3209,9 +3221,9 @@
 	__be32 *p;
 
 	if (!nfserr) {
-		RESERVE_SPACE(8 + sizeof(nfs4_verifier));
+		RESERVE_SPACE(8 + NFS4_VERIFIER_SIZE);
 		WRITEMEM(&scd->se_clientid, 8);
-		WRITEMEM(&scd->se_confirm, sizeof(nfs4_verifier));
+		WRITEMEM(&scd->se_confirm, NFS4_VERIFIER_SIZE);
 		ADJUST_ARGS();
 	}
 	else if (nfserr == nfserr_clid_inuse) {
@@ -3232,7 +3244,7 @@
 		RESERVE_SPACE(16);
 		WRITE32(write->wr_bytes_written);
 		WRITE32(write->wr_how_written);
-		WRITEMEM(write->wr_verifier.data, 8);
+		WRITEMEM(write->wr_verifier.data, NFS4_VERIFIER_SIZE);
 		ADJUST_ARGS();
 	}
 	return nfserr;
@@ -3391,30 +3403,17 @@
 nfsd4_encode_test_stateid(struct nfsd4_compoundres *resp, int nfserr,
 			  struct nfsd4_test_stateid *test_stateid)
 {
-	struct nfsd4_compoundargs *argp;
-	struct nfs4_client *cl = resp->cstate.session->se_client;
-	stateid_t si;
+	struct nfsd4_test_stateid_id *stateid, *next;
 	__be32 *p;
-	int i;
-	int valid;
 
-	restore_buf(test_stateid->ts_saved_args, &test_stateid->ts_savedp);
-	argp = test_stateid->ts_saved_args;
-
-	RESERVE_SPACE(4);
+	RESERVE_SPACE(4 + (4 * test_stateid->ts_num_ids));
 	*p++ = htonl(test_stateid->ts_num_ids);
-	resp->p = p;
 
-	nfs4_lock_state();
-	for (i = 0; i < test_stateid->ts_num_ids; i++) {
-		nfsd4_decode_stateid(argp, &si);
-		valid = nfs4_validate_stateid(cl, &si);
-		RESERVE_SPACE(4);
-		*p++ = htonl(valid);
-		resp->p = p;
+	list_for_each_entry_safe(stateid, next, &test_stateid->ts_stateid_list, ts_id_list) {
+		*p++ = htonl(stateid->ts_id_status);
 	}
-	nfs4_unlock_state();
 
+	ADJUST_ARGS();
 	return nfserr;
 }
 
@@ -3532,7 +3531,7 @@
 	if (length > session->se_fchannel.maxresp_sz)
 		return nfserr_rep_too_big;
 
-	if (slot->sl_cachethis == 1 &&
+	if ((slot->sl_flags & NFSD4_SLOT_CACHETHIS) &&
 	    length > session->se_fchannel.maxresp_cached)
 		return nfserr_rep_too_big_to_cache;
 
@@ -3656,8 +3655,7 @@
 	if (nfsd4_has_session(cs)) {
 		if (cs->status != nfserr_replay_cache) {
 			nfsd4_store_cache_entry(resp);
-			dprintk("%s: SET SLOT STATE TO AVAILABLE\n", __func__);
-			cs->slot->sl_inuse = false;
+			cs->slot->sl_flags &= ~NFSD4_SLOT_INUSE;
 		}
 		/* Renew the clientid on success and on replay */
 		release_session_client(cs->session);
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 64c24af..2c53be6 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -13,12 +13,14 @@
 #include <linux/sunrpc/clnt.h>
 #include <linux/sunrpc/gss_api.h>
 #include <linux/sunrpc/gss_krb5_enctypes.h>
+#include <linux/sunrpc/rpc_pipe_fs.h>
 #include <linux/module.h>
 
 #include "idmap.h"
 #include "nfsd.h"
 #include "cache.h"
 #include "fault_inject.h"
+#include "netns.h"
 
 /*
  *	We have a single directory with several nodes in it.
@@ -1124,14 +1126,26 @@
 }
 #endif
 
+int nfsd_net_id;
+static struct pernet_operations nfsd_net_ops = {
+	.id   = &nfsd_net_id,
+	.size = sizeof(struct nfsd_net),
+};
+
 static int __init init_nfsd(void)
 {
 	int retval;
 	printk(KERN_INFO "Installing knfsd (copyright (C) 1996 okir@monad.swb.de).\n");
 
-	retval = nfsd4_init_slabs();
+	retval = register_cld_notifier();
 	if (retval)
 		return retval;
+	retval = register_pernet_subsys(&nfsd_net_ops);
+	if (retval < 0)
+		goto out_unregister_notifier;
+	retval = nfsd4_init_slabs();
+	if (retval)
+		goto out_unregister_pernet;
 	nfs4_state_init();
 	retval = nfsd_fault_inject_init(); /* nfsd fault injection controls */
 	if (retval)
@@ -1169,6 +1183,10 @@
 	nfsd_fault_inject_cleanup();
 out_free_slabs:
 	nfsd4_free_slabs();
+out_unregister_pernet:
+	unregister_pernet_subsys(&nfsd_net_ops);
+out_unregister_notifier:
+	unregister_cld_notifier();
 	return retval;
 }
 
@@ -1184,6 +1202,8 @@
 	nfsd4_free_slabs();
 	nfsd_fault_inject_cleanup();
 	unregister_filesystem(&nfsd_fs_type);
+	unregister_pernet_subsys(&nfsd_net_ops);
+	unregister_cld_notifier();
 }
 
 MODULE_AUTHOR("Olaf Kirch <okir@monad.swb.de>");
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index 1d1e858..1671429 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -364,12 +364,17 @@
 	NFSD_WRITEABLE_ATTRS_WORD2
 
 extern int nfsd4_is_junction(struct dentry *dentry);
-#else
+extern int register_cld_notifier(void);
+extern void unregister_cld_notifier(void);
+#else /* CONFIG_NFSD_V4 */
 static inline int nfsd4_is_junction(struct dentry *dentry)
 {
 	return 0;
 }
 
+#define register_cld_notifier() 0
+#define unregister_cld_notifier() do { } while(0)
+
 #endif /* CONFIG_NFSD_V4 */
 
 #endif /* LINUX_NFSD_NFSD_H */
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index fce472f..28dfad3 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -307,33 +307,37 @@
 	dprintk("%s nfsd_drc_max_mem %u \n", __func__, nfsd_drc_max_mem);
 }
 
+static int nfsd_get_default_max_blksize(void)
+{
+	struct sysinfo i;
+	unsigned long long target;
+	unsigned long ret;
+
+	si_meminfo(&i);
+	target = (i.totalram - i.totalhigh) << PAGE_SHIFT;
+	/*
+	 * Aim for 1/4096 of memory per thread This gives 1MB on 4Gig
+	 * machines, but only uses 32K on 128M machines.  Bottom out at
+	 * 8K on 32M and smaller.  Of course, this is only a default.
+	 */
+	target >>= 12;
+
+	ret = NFSSVC_MAXBLKSIZE;
+	while (ret > target && ret >= 8*1024*2)
+		ret /= 2;
+	return ret;
+}
+
 int nfsd_create_serv(void)
 {
-	int err = 0;
-
 	WARN_ON(!mutex_is_locked(&nfsd_mutex));
 	if (nfsd_serv) {
 		svc_get(nfsd_serv);
 		return 0;
 	}
-	if (nfsd_max_blksize == 0) {
-		/* choose a suitable default */
-		struct sysinfo i;
-		si_meminfo(&i);
-		/* Aim for 1/4096 of memory per thread
-		 * This gives 1MB on 4Gig machines
-		 * But only uses 32K on 128M machines.
-		 * Bottom out at 8K on 32M and smaller.
-		 * Of course, this is only a default.
-		 */
-		nfsd_max_blksize = NFSSVC_MAXBLKSIZE;
-		i.totalram <<= PAGE_SHIFT - 12;
-		while (nfsd_max_blksize > i.totalram &&
-		       nfsd_max_blksize >= 8*1024*2)
-			nfsd_max_blksize /= 2;
-	}
+	if (nfsd_max_blksize == 0)
+		nfsd_max_blksize = nfsd_get_default_max_blksize();
 	nfsd_reset_versions();
-
 	nfsd_serv = svc_create_pooled(&nfsd_program, nfsd_max_blksize,
 				      nfsd_last_thread, nfsd, THIS_MODULE);
 	if (nfsd_serv == NULL)
@@ -341,7 +345,7 @@
 
 	set_max_drc();
 	do_gettimeofday(&nfssvc_boot);		/* record boot time */
-	return err;
+	return 0;
 }
 
 int nfsd_nrpools(void)
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index ffb5df1..89ab137 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -128,12 +128,14 @@
 		(NFSD_CACHE_SIZE_SLOTS_PER_SESSION * NFSD_SLOT_CACHE_SIZE)
 
 struct nfsd4_slot {
-	bool	sl_inuse;
-	bool	sl_cachethis;
-	u16	sl_opcnt;
 	u32	sl_seqid;
 	__be32	sl_status;
 	u32	sl_datalen;
+	u16	sl_opcnt;
+#define NFSD4_SLOT_INUSE	(1 << 0)
+#define NFSD4_SLOT_CACHETHIS	(1 << 1)
+#define NFSD4_SLOT_INITIALIZED	(1 << 2)
+	u8	sl_flags;
 	char	sl_data[];
 };
 
@@ -196,18 +198,7 @@
 	struct nfsd4_slot	*se_slots[];	/* forward channel slots */
 };
 
-static inline void
-nfsd4_put_session(struct nfsd4_session *ses)
-{
-	extern void free_session(struct kref *kref);
-	kref_put(&ses->se_ref, free_session);
-}
-
-static inline void
-nfsd4_get_session(struct nfsd4_session *ses)
-{
-	kref_get(&ses->se_ref);
-}
+extern void nfsd4_put_session(struct nfsd4_session *ses);
 
 /* formatted contents of nfs4_sessionid */
 struct nfsd4_sessionid {
@@ -245,14 +236,17 @@
 	struct svc_cred		cl_cred; 	/* setclientid principal */
 	clientid_t		cl_clientid;	/* generated by server */
 	nfs4_verifier		cl_confirm;	/* generated by server */
-	u32			cl_firststate;	/* recovery dir creation */
 	u32			cl_minorversion;
 
 	/* for v4.0 and v4.1 callbacks: */
 	struct nfs4_cb_conn	cl_cb_conn;
-#define NFSD4_CLIENT_CB_UPDATE	1
-#define NFSD4_CLIENT_KILL	2
-	unsigned long		cl_cb_flags;
+#define NFSD4_CLIENT_CB_UPDATE		(0)
+#define NFSD4_CLIENT_CB_KILL		(1)
+#define NFSD4_CLIENT_STABLE		(2)	/* client on stable storage */
+#define NFSD4_CLIENT_RECLAIM_COMPLETE	(3)	/* reclaim_complete done */
+#define NFSD4_CLIENT_CB_FLAG_MASK	(1 << NFSD4_CLIENT_CB_UPDATE | \
+					 1 << NFSD4_CLIENT_CB_KILL)
+	unsigned long		cl_flags;
 	struct rpc_clnt		*cl_cb_client;
 	u32			cl_cb_ident;
 #define NFSD4_CB_UP		0
@@ -463,6 +457,8 @@
 extern void nfs4_lock_state(void);
 extern void nfs4_unlock_state(void);
 extern int nfs4_in_grace(void);
+extern void nfs4_release_reclaim(void);
+extern struct nfs4_client_reclaim *nfsd4_find_reclaim_client(struct nfs4_client *crp);
 extern __be32 nfs4_check_open_reclaim(clientid_t *clid);
 extern void nfs4_free_openowner(struct nfs4_openowner *);
 extern void nfs4_free_lockowner(struct nfs4_lockowner *);
@@ -477,16 +473,17 @@
 extern void nfsd4_shutdown_callback(struct nfs4_client *);
 extern void nfs4_put_delegation(struct nfs4_delegation *dp);
 extern __be32 nfs4_make_rec_clidname(char *clidname, struct xdr_netobj *clname);
-extern void nfsd4_init_recdir(void);
-extern int nfsd4_recdir_load(void);
-extern void nfsd4_shutdown_recdir(void);
 extern int nfs4_client_to_reclaim(const char *name);
 extern int nfs4_has_reclaimed_state(const char *name, bool use_exchange_id);
-extern void nfsd4_recdir_purge_old(void);
-extern void nfsd4_create_clid_dir(struct nfs4_client *clp);
-extern void nfsd4_remove_clid_dir(struct nfs4_client *clp);
 extern void release_session_client(struct nfsd4_session *);
 extern __be32 nfs4_validate_stateid(struct nfs4_client *, stateid_t *);
 extern void nfsd4_purge_closed_stateid(struct nfs4_stateowner *);
 
+/* nfs4recover operations */
+extern int nfsd4_client_tracking_init(struct net *net);
+extern void nfsd4_client_tracking_exit(struct net *net);
+extern void nfsd4_client_record_create(struct nfs4_client *clp);
+extern void nfsd4_client_record_remove(struct nfs4_client *clp);
+extern int nfsd4_client_record_check(struct nfs4_client *clp);
+extern void nfsd4_record_grace_done(struct net *net, time_t boot_time);
 #endif   /* NFSD4_STATE_H */
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index e59f71d..296d671 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -737,12 +737,13 @@
 
 /*
  * Open an existing file or directory.
- * The access argument indicates the type of open (read/write/lock)
+ * The may_flags argument indicates the type of open (read/write/lock)
+ * and additional flags.
  * N.B. After this call fhp needs an fh_put
  */
 __be32
 nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type,
-			int access, struct file **filp)
+			int may_flags, struct file **filp)
 {
 	struct dentry	*dentry;
 	struct inode	*inode;
@@ -757,7 +758,7 @@
 	 * and (hopefully) checked permission - so allow OWNER_OVERRIDE
 	 * in case a chmod has now revoked permission.
 	 */
-	err = fh_verify(rqstp, fhp, type, access | NFSD_MAY_OWNER_OVERRIDE);
+	err = fh_verify(rqstp, fhp, type, may_flags | NFSD_MAY_OWNER_OVERRIDE);
 	if (err)
 		goto out;
 
@@ -768,7 +769,7 @@
 	 * or any access when mandatory locking enabled
 	 */
 	err = nfserr_perm;
-	if (IS_APPEND(inode) && (access & NFSD_MAY_WRITE))
+	if (IS_APPEND(inode) && (may_flags & NFSD_MAY_WRITE))
 		goto out;
 	/*
 	 * We must ignore files (but only files) which might have mandatory
@@ -781,12 +782,12 @@
 	if (!inode->i_fop)
 		goto out;
 
-	host_err = nfsd_open_break_lease(inode, access);
+	host_err = nfsd_open_break_lease(inode, may_flags);
 	if (host_err) /* NOMEM or WOULDBLOCK */
 		goto out_nfserr;
 
-	if (access & NFSD_MAY_WRITE) {
-		if (access & NFSD_MAY_READ)
+	if (may_flags & NFSD_MAY_WRITE) {
+		if (may_flags & NFSD_MAY_READ)
 			flags = O_RDWR|O_LARGEFILE;
 		else
 			flags = O_WRONLY|O_LARGEFILE;
@@ -795,8 +796,15 @@
 			    flags, current_cred());
 	if (IS_ERR(*filp))
 		host_err = PTR_ERR(*filp);
-	else
-		host_err = ima_file_check(*filp, access);
+	else {
+		host_err = ima_file_check(*filp, may_flags);
+
+		if (may_flags & NFSD_MAY_64BIT_COOKIE)
+			(*filp)->f_mode |= FMODE_64BITHASH;
+		else
+			(*filp)->f_mode |= FMODE_32BITHASH;
+	}
+
 out_nfserr:
 	err = nfserrno(host_err);
 out:
@@ -2021,8 +2029,13 @@
 	__be32		err;
 	struct file	*file;
 	loff_t		offset = *offsetp;
+	int             may_flags = NFSD_MAY_READ;
 
-	err = nfsd_open(rqstp, fhp, S_IFDIR, NFSD_MAY_READ, &file);
+	/* NFSv2 only supports 32 bit cookies */
+	if (rqstp->rq_vers > 2)
+		may_flags |= NFSD_MAY_64BIT_COOKIE;
+
+	err = nfsd_open(rqstp, fhp, S_IFDIR, may_flags, &file);
 	if (err)
 		goto out;
 
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index 1dcd238..ec0611b 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -27,6 +27,8 @@
 #define NFSD_MAY_BYPASS_GSS		0x400
 #define NFSD_MAY_READ_IF_EXEC		0x800
 
+#define NFSD_MAY_64BIT_COOKIE		0x1000 /* 64 bit readdir cookies for >= NFSv3 */
+
 #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/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index 2364747..1b35015 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -43,6 +43,13 @@
 #define NFSD4_MAX_TAGLEN	128
 #define XDR_LEN(n)                     (((n) + 3) & ~3)
 
+#define CURRENT_STATE_ID_FLAG (1<<0)
+#define SAVED_STATE_ID_FLAG (1<<1)
+
+#define SET_STATE_ID(c, f) ((c)->sid_flags |= (f))
+#define HAS_STATE_ID(c, f) ((c)->sid_flags & (f))
+#define CLEAR_STATE_ID(c, f) ((c)->sid_flags &= ~(f))
+
 struct nfsd4_compound_state {
 	struct svc_fh		current_fh;
 	struct svc_fh		save_fh;
@@ -54,6 +61,10 @@
 	size_t			iovlen;
 	u32			minorversion;
 	u32			status;
+	stateid_t	current_stateid;
+	stateid_t	save_stateid;
+	/* to indicate current and saved state id presents */
+	u32		sid_flags;
 };
 
 static inline bool nfsd4_has_session(struct nfsd4_compound_state *cs)
@@ -212,16 +223,19 @@
 	struct xdr_netobj op_fname;	    /* request - everything but CLAIM_PREV */
 	u32		op_delegate_type;   /* request - CLAIM_PREV only */
 	stateid_t       op_delegate_stateid; /* request - response */
+	u32		op_why_no_deleg;    /* response - DELEG_NONE_EXT only */
 	u32		op_create;     	    /* request */
 	u32		op_createmode;      /* request */
 	u32		op_bmval[3];        /* request */
 	struct iattr	iattr;              /* UNCHECKED4, GUARDED4, EXCLUSIVE4_1 */
-	nfs4_verifier	verf;               /* EXCLUSIVE4 */
+	nfs4_verifier	op_verf __attribute__((aligned(32)));
+					    /* EXCLUSIVE4 */
 	clientid_t	op_clientid;        /* request */
 	struct xdr_netobj op_owner;           /* request */
 	u32		op_seqid;           /* request */
 	u32		op_share_access;    /* request */
 	u32		op_share_deny;      /* request */
+	u32		op_deleg_want;      /* request */
 	stateid_t	op_stateid;         /* response */
 	u32		op_recall;          /* recall */
 	struct nfsd4_change_info  op_cinfo; /* response */
@@ -234,7 +248,6 @@
 	struct nfs4_acl *op_acl;
 };
 #define op_iattr	iattr
-#define op_verf		verf
 
 struct nfsd4_open_confirm {
 	stateid_t	oc_req_stateid		/* request */;
@@ -245,8 +258,9 @@
 struct nfsd4_open_downgrade {
 	stateid_t       od_stateid;
 	u32             od_seqid;
-	u32             od_share_access;
-	u32             od_share_deny;
+	u32             od_share_access;	/* request */
+	u32		od_deleg_want;		/* request */
+	u32             od_share_deny;		/* request */
 };
 
 
@@ -343,10 +357,15 @@
 	struct page **pagelist;
 };
 
+struct nfsd4_test_stateid_id {
+	__be32			ts_id_status;
+	stateid_t		ts_id_stateid;
+	struct list_head	ts_id_list;
+};
+
 struct nfsd4_test_stateid {
 	__be32		ts_num_ids;
-	struct nfsd4_compoundargs *ts_saved_args;
-	struct nfsd4_saved_compoundargs ts_savedp;
+	struct list_head ts_stateid_list;
 };
 
 struct nfsd4_free_stateid {
@@ -503,7 +522,8 @@
 
 static inline bool nfsd4_not_cached(struct nfsd4_compoundres *resp)
 {
-	return !resp->cstate.slot->sl_cachethis || nfsd4_is_solo_sequence(resp);
+	return !(resp->cstate.slot->sl_flags & NFSD4_SLOT_CACHETHIS)
+		|| nfsd4_is_solo_sequence(resp);
 }
 
 #define NFS4_SVC_XDRSIZE		sizeof(struct nfsd4_compoundargs)
diff --git a/fs/open.c b/fs/open.c
index 77becc0..5720854 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -836,7 +836,7 @@
 static void __put_unused_fd(struct files_struct *files, unsigned int fd)
 {
 	struct fdtable *fdt = files_fdtable(files);
-	__FD_CLR(fd, fdt->open_fds);
+	__clear_open_fd(fd, fdt);
 	if (fd < files->next_fd)
 		files->next_fd = fd;
 }
@@ -1080,7 +1080,7 @@
 	if (!filp)
 		goto out_unlock;
 	rcu_assign_pointer(fdt->fd[fd], NULL);
-	FD_CLR(fd, fdt->close_on_exec);
+	__clear_close_on_exec(fd, fdt);
 	__put_unused_fd(files, fd);
 	spin_unlock(&files->file_lock);
 	retval = filp_close(filp, files);
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 3b42c14..1c8b280 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1753,7 +1753,7 @@
 
 			fdt = files_fdtable(files);
 			f_flags = file->f_flags & ~O_CLOEXEC;
-			if (FD_ISSET(fd, fdt->close_on_exec))
+			if (close_on_exec(fd, fdt))
 				f_flags |= O_CLOEXEC;
 
 			if (path) {
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index c283832..2b9a760 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -783,7 +783,6 @@
 
 	/* find the first VMA at or above 'addr' */
 	vma = find_vma(walk->mm, addr);
-	spin_lock(&walk->mm->page_table_lock);
 	if (pmd_trans_huge_lock(pmd, vma) == 1) {
 		for (; addr != end; addr += PAGE_SIZE) {
 			unsigned long offset;
diff --git a/fs/select.c b/fs/select.c
index 6fb8943..17d33d0 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -348,7 +348,7 @@
 	set = ~(~0UL << (n & (__NFDBITS-1)));
 	n /= __NFDBITS;
 	fdt = files_fdtable(current->files);
-	open_fds = fdt->open_fds->fds_bits+n;
+	open_fds = fdt->open_fds + n;
 	max = 0;
 	if (set) {
 		set &= BITS(fds, n);
diff --git a/include/asm-generic/posix_types.h b/include/asm-generic/posix_types.h
index 3dab0086..91d44bd 100644
--- a/include/asm-generic/posix_types.h
+++ b/include/asm-generic/posix_types.h
@@ -10,8 +10,13 @@
  * architectures, so that you can override them.
  */
 
+#ifndef __kernel_long_t
+typedef long		__kernel_long_t;
+typedef unsigned long	__kernel_ulong_t;
+#endif
+
 #ifndef __kernel_ino_t
-typedef unsigned long	__kernel_ino_t;
+typedef __kernel_ulong_t __kernel_ino_t;
 #endif
 
 #ifndef __kernel_mode_t
@@ -19,7 +24,7 @@
 #endif
 
 #ifndef __kernel_nlink_t
-typedef unsigned long	__kernel_nlink_t;
+typedef __kernel_ulong_t __kernel_nlink_t;
 #endif
 
 #ifndef __kernel_pid_t
@@ -36,7 +41,7 @@
 #endif
 
 #ifndef __kernel_suseconds_t
-typedef long		__kernel_suseconds_t;
+typedef __kernel_long_t		__kernel_suseconds_t;
 #endif
 
 #ifndef __kernel_daddr_t
@@ -44,8 +49,8 @@
 #endif
 
 #ifndef __kernel_uid32_t
-typedef __kernel_uid_t	__kernel_uid32_t;
-typedef __kernel_gid_t	__kernel_gid32_t;
+typedef unsigned int	__kernel_uid32_t;
+typedef unsigned int	__kernel_gid32_t;
 #endif
 
 #ifndef __kernel_old_uid_t
@@ -67,99 +72,29 @@
 typedef int		__kernel_ssize_t;
 typedef int		__kernel_ptrdiff_t;
 #else
-typedef unsigned long	__kernel_size_t;
-typedef long		__kernel_ssize_t;
-typedef long		__kernel_ptrdiff_t;
+typedef __kernel_ulong_t __kernel_size_t;
+typedef __kernel_long_t	__kernel_ssize_t;
+typedef __kernel_long_t	__kernel_ptrdiff_t;
 #endif
 #endif
 
+#ifndef __kernel_fsid_t
+typedef struct {
+	int	val[2];
+} __kernel_fsid_t;
+#endif
+
 /*
  * anything below here should be completely generic
  */
-typedef long		__kernel_off_t;
+typedef __kernel_long_t	__kernel_off_t;
 typedef long long	__kernel_loff_t;
-typedef long		__kernel_time_t;
-typedef long		__kernel_clock_t;
+typedef __kernel_long_t	__kernel_time_t;
+typedef __kernel_long_t	__kernel_clock_t;
 typedef int		__kernel_timer_t;
 typedef int		__kernel_clockid_t;
 typedef char *		__kernel_caddr_t;
 typedef unsigned short	__kernel_uid16_t;
 typedef unsigned short	__kernel_gid16_t;
 
-typedef struct {
-	int	val[2];
-} __kernel_fsid_t;
-
-#ifdef __KERNEL__
-
-#undef __FD_SET
-static inline void __FD_SET(unsigned long __fd, __kernel_fd_set *__fdsetp)
-{
-	unsigned long __tmp = __fd / __NFDBITS;
-	unsigned long __rem = __fd % __NFDBITS;
-	__fdsetp->fds_bits[__tmp] |= (1UL<<__rem);
-}
-
-#undef __FD_CLR
-static inline void __FD_CLR(unsigned long __fd, __kernel_fd_set *__fdsetp)
-{
-	unsigned long __tmp = __fd / __NFDBITS;
-	unsigned long __rem = __fd % __NFDBITS;
-	__fdsetp->fds_bits[__tmp] &= ~(1UL<<__rem);
-}
-
-#undef __FD_ISSET
-static inline int __FD_ISSET(unsigned long __fd, const __kernel_fd_set *__p)
-{
-	unsigned long __tmp = __fd / __NFDBITS;
-	unsigned long __rem = __fd % __NFDBITS;
-	return (__p->fds_bits[__tmp] & (1UL<<__rem)) != 0;
-}
-
-/*
- * This will unroll the loop for the normal constant case (8 ints,
- * for a 256-bit fd_set)
- */
-#undef __FD_ZERO
-static inline void __FD_ZERO(__kernel_fd_set *__p)
-{
-	unsigned long *__tmp = __p->fds_bits;
-	int __i;
-
-	if (__builtin_constant_p(__FDSET_LONGS)) {
-		switch (__FDSET_LONGS) {
-		case 16:
-			__tmp[ 0] = 0; __tmp[ 1] = 0;
-			__tmp[ 2] = 0; __tmp[ 3] = 0;
-			__tmp[ 4] = 0; __tmp[ 5] = 0;
-			__tmp[ 6] = 0; __tmp[ 7] = 0;
-			__tmp[ 8] = 0; __tmp[ 9] = 0;
-			__tmp[10] = 0; __tmp[11] = 0;
-			__tmp[12] = 0; __tmp[13] = 0;
-			__tmp[14] = 0; __tmp[15] = 0;
-			return;
-
-		case 8:
-			__tmp[ 0] = 0; __tmp[ 1] = 0;
-			__tmp[ 2] = 0; __tmp[ 3] = 0;
-			__tmp[ 4] = 0; __tmp[ 5] = 0;
-			__tmp[ 6] = 0; __tmp[ 7] = 0;
-			return;
-
-		case 4:
-			__tmp[ 0] = 0; __tmp[ 1] = 0;
-			__tmp[ 2] = 0; __tmp[ 3] = 0;
-			return;
-		}
-	}
-	__i = __FDSET_LONGS;
-	while (__i) {
-		__i--;
-		*__tmp = 0;
-		__tmp++;
-	}
-}
-
-#endif /* __KERNEL__ */
-
 #endif /* __ASM_GENERIC_POSIX_TYPES_H */
diff --git a/include/asm-generic/unistd.h b/include/asm-generic/unistd.h
index 2292d1a..991ef01 100644
--- a/include/asm-generic/unistd.h
+++ b/include/asm-generic/unistd.h
@@ -218,7 +218,7 @@
 
 /* fs/sendfile.c */
 #define __NR3264_sendfile 71
-__SC_3264(__NR3264_sendfile, sys_sendfile64, sys_sendfile)
+__SYSCALL(__NR3264_sendfile, sys_sendfile64)
 
 /* fs/select.c */
 #define __NR_pselect6 72
diff --git a/include/linux/Kbuild b/include/linux/Kbuild
index a255553..a4b5da2 100644
--- a/include/linux/Kbuild
+++ b/include/linux/Kbuild
@@ -357,6 +357,7 @@
 header-y += swab.h
 header-y += synclink.h
 header-y += sysctl.h
+header-y += sysinfo.h
 header-y += taskstats.h
 header-y += tcp.h
 header-y += telephony.h
diff --git a/include/linux/aio_abi.h b/include/linux/aio_abi.h
index 2c87316..86fa7a7 100644
--- a/include/linux/aio_abi.h
+++ b/include/linux/aio_abi.h
@@ -30,7 +30,7 @@
 #include <linux/types.h>
 #include <asm/byteorder.h>
 
-typedef unsigned long	aio_context_t;
+typedef __kernel_ulong_t aio_context_t;
 
 enum {
 	IOCB_CMD_PREAD = 0,
diff --git a/include/linux/amba/pl08x.h b/include/linux/amba/pl08x.h
index 033f6aa..e64ce2c 100644
--- a/include/linux/amba/pl08x.h
+++ b/include/linux/amba/pl08x.h
@@ -47,9 +47,6 @@
  * @muxval: a number usually used to poke into some mux regiser to
  * mux in the signal to this channel
  * @cctl_opt: default options for the channel control register
- * @device_fc: Flow Controller Settings for ccfg register. Only valid for slave
- * channels. Fill with 'true' if peripheral should be flow controller. Direction
- * will be selected at Runtime.
  * @addr: source/target address in physical memory for this DMA channel,
  * can be the address of a FIFO register for burst requests for example.
  * This can be left undefined if the PrimeCell API is used for configuring
@@ -68,7 +65,6 @@
 	int max_signal;
 	u32 muxval;
 	u32 cctl;
-	bool device_fc;
 	dma_addr_t addr;
 	bool circular_buffer;
 	bool single;
@@ -176,13 +172,15 @@
  * @runtime_addr: address for RX/TX according to the runtime config
  * @runtime_direction: current direction of this channel according to
  * runtime config
- * @lc: last completed transaction on this channel
  * @pend_list: queued transactions pending on this channel
  * @at: active transaction on this channel
  * @lock: a lock for this channel data
  * @host: a pointer to the host (internal use)
  * @state: whether the channel is idle, paused, running etc
  * @slave: whether this channel is a device (slave) or for memcpy
+ * @device_fc: Flow Controller Settings for ccfg register. Only valid for slave
+ * channels. Fill with 'true' if peripheral should be flow controller. Direction
+ * will be selected at Runtime.
  * @waiting: a TX descriptor on this channel which is waiting for a physical
  * channel to become available
  */
@@ -198,13 +196,13 @@
 	u32 src_cctl;
 	u32 dst_cctl;
 	enum dma_transfer_direction runtime_direction;
-	dma_cookie_t lc;
 	struct list_head pend_list;
 	struct pl08x_txd *at;
 	spinlock_t lock;
 	struct pl08x_driver_data *host;
 	enum pl08x_dma_chan_state state;
 	bool slave;
+	bool device_fc;
 	struct pl08x_txd *waiting;
 };
 
diff --git a/include/linux/amba/pl330.h b/include/linux/amba/pl330.h
index 12e023c..fe93758 100644
--- a/include/linux/amba/pl330.h
+++ b/include/linux/amba/pl330.h
@@ -13,7 +13,6 @@
 #define	__AMBA_PL330_H_
 
 #include <linux/dmaengine.h>
-#include <asm/hardware/pl330.h>
 
 struct dma_pl330_platdata {
 	/*
diff --git a/include/linux/compat.h b/include/linux/compat.h
index 7e05fce..5d46217 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -19,6 +19,10 @@
 #include <asm/siginfo.h>
 #include <asm/signal.h>
 
+#ifndef COMPAT_USE_64BIT_TIME
+#define COMPAT_USE_64BIT_TIME 0
+#endif
+
 #define compat_jiffies_to_clock_t(x)	\
 		(((unsigned long)(x) * COMPAT_USER_HZ) / HZ)
 
@@ -83,10 +87,26 @@
 	compat_sigset_word	sig[_COMPAT_NSIG_WORDS];
 } compat_sigset_t;
 
+/*
+ * These functions operate strictly on struct compat_time*
+ */
 extern int get_compat_timespec(struct timespec *,
 			       const struct compat_timespec __user *);
 extern int put_compat_timespec(const struct timespec *,
 			       struct compat_timespec __user *);
+extern int get_compat_timeval(struct timeval *,
+			      const struct compat_timeval __user *);
+extern int put_compat_timeval(const struct timeval *,
+			      struct compat_timeval __user *);
+/*
+ * These functions operate on 32- or 64-bit specs depending on
+ * COMPAT_USE_64BIT_TIME, hence the void user pointer arguments and the
+ * naming as compat_get/put_ rather than get/put_compat_.
+ */
+extern int compat_get_timespec(struct timespec *, const void __user *);
+extern int compat_put_timespec(const struct timespec *, void __user *);
+extern int compat_get_timeval(struct timeval *, const void __user *);
+extern int compat_put_timeval(const struct timeval *, void __user *);
 
 struct compat_iovec {
 	compat_uptr_t	iov_base;
@@ -224,6 +244,7 @@
 struct compat_sysctl_args;
 struct compat_kexec_segment;
 struct compat_mq_attr;
+struct compat_msgbuf;
 
 extern void compat_exit_robust_list(struct task_struct *curr);
 
@@ -234,13 +255,22 @@
 compat_sys_get_robust_list(int pid, compat_uptr_t __user *head_ptr,
 			   compat_size_t __user *len_ptr);
 
+#ifdef CONFIG_ARCH_WANT_OLD_COMPAT_IPC
 long compat_sys_semctl(int first, int second, int third, void __user *uptr);
 long compat_sys_msgsnd(int first, int second, int third, void __user *uptr);
 long compat_sys_msgrcv(int first, int second, int msgtyp, int third,
 		int version, void __user *uptr);
-long compat_sys_msgctl(int first, int second, void __user *uptr);
 long compat_sys_shmat(int first, int second, compat_uptr_t third, int version,
 		void __user *uptr);
+#else
+long compat_sys_semctl(int semid, int semnum, int cmd, int arg);
+long compat_sys_msgsnd(int msqid, struct compat_msgbuf __user *msgp,
+		size_t msgsz, int msgflg);
+long compat_sys_msgrcv(int msqid, struct compat_msgbuf __user *msgp,
+		size_t msgsz, long msgtyp, int msgflg);
+long compat_sys_shmat(int shmid, compat_uptr_t shmaddr, int shmflg);
+#endif
+long compat_sys_msgctl(int first, int second, void __user *uptr);
 long compat_sys_shmctl(int first, int second, void __user *uptr);
 long compat_sys_semtimedop(int semid, struct sembuf __user *tsems,
 		unsigned nsems, const struct compat_timespec __user *timeout);
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 7a7e5fd..668f66b 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -22,7 +22,7 @@
 extern void cpuset_init_smp(void);
 extern void cpuset_update_active_cpus(void);
 extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask);
-extern int cpuset_cpus_allowed_fallback(struct task_struct *p);
+extern void cpuset_cpus_allowed_fallback(struct task_struct *p);
 extern nodemask_t cpuset_mems_allowed(struct task_struct *p);
 #define cpuset_current_mems_allowed (current->mems_allowed)
 void cpuset_init_current_mems_allowed(void);
@@ -135,10 +135,8 @@
 	cpumask_copy(mask, cpu_possible_mask);
 }
 
-static inline int cpuset_cpus_allowed_fallback(struct task_struct *p)
+static inline void cpuset_cpus_allowed_fallback(struct task_struct *p)
 {
-	do_set_cpus_allowed(p, cpu_possible_mask);
-	return cpumask_any(cpu_active_mask);
 }
 
 static inline nodemask_t cpuset_mems_allowed(struct task_struct *p)
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index e13117c..5a736af 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -77,7 +77,7 @@
 	return DMA_BIT_MASK(32);
 }
 
-#ifdef ARCH_HAS_DMA_SET_COHERENT_MASK
+#ifdef CONFIG_ARCH_HAS_DMA_SET_COHERENT_MASK
 int dma_set_coherent_mask(struct device *dev, u64 mask);
 #else
 static inline int dma_set_coherent_mask(struct device *dev, u64 mask)
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index a5966f6..676f967 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -18,14 +18,15 @@
  * The full GNU General Public License is included in this distribution in the
  * file called COPYING.
  */
-#ifndef DMAENGINE_H
-#define DMAENGINE_H
+#ifndef LINUX_DMAENGINE_H
+#define LINUX_DMAENGINE_H
 
 #include <linux/device.h>
 #include <linux/uio.h>
 #include <linux/bug.h>
 #include <linux/scatterlist.h>
 #include <linux/bitmap.h>
+#include <linux/types.h>
 #include <asm/page.h>
 
 /**
@@ -258,6 +259,7 @@
  * struct dma_chan - devices supply DMA channels, clients use them
  * @device: ptr to the dma device who supplies this channel, always !%NULL
  * @cookie: last cookie value returned to client
+ * @completed_cookie: last completed cookie for this channel
  * @chan_id: channel ID for sysfs
  * @dev: class device for sysfs
  * @device_node: used to add this to the device chan list
@@ -269,6 +271,7 @@
 struct dma_chan {
 	struct dma_device *device;
 	dma_cookie_t cookie;
+	dma_cookie_t completed_cookie;
 
 	/* sysfs */
 	int chan_id;
@@ -332,6 +335,9 @@
  * may or may not be applicable on memory sources.
  * @dst_maxburst: same as src_maxburst but for destination target
  * mutatis mutandis.
+ * @device_fc: Flow Controller Settings. Only valid for slave channels. Fill
+ * with 'true' if peripheral should be flow controller. Direction will be
+ * selected at Runtime.
  *
  * This struct is passed in as configuration data to a DMA engine
  * in order to set up a certain channel for DMA transport at runtime.
@@ -358,6 +364,7 @@
 	enum dma_slave_buswidth dst_addr_width;
 	u32 src_maxburst;
 	u32 dst_maxburst;
+	bool device_fc;
 };
 
 static inline const char *dma_chan_name(struct dma_chan *chan)
@@ -576,10 +583,11 @@
 	struct dma_async_tx_descriptor *(*device_prep_slave_sg)(
 		struct dma_chan *chan, struct scatterlist *sgl,
 		unsigned int sg_len, enum dma_transfer_direction direction,
-		unsigned long flags);
+		unsigned long flags, void *context);
 	struct dma_async_tx_descriptor *(*device_prep_dma_cyclic)(
 		struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len,
-		size_t period_len, enum dma_transfer_direction direction);
+		size_t period_len, enum dma_transfer_direction direction,
+		void *context);
 	struct dma_async_tx_descriptor *(*device_prep_interleaved_dma)(
 		struct dma_chan *chan, struct dma_interleaved_template *xt,
 		unsigned long flags);
@@ -613,7 +621,24 @@
 	struct scatterlist sg;
 	sg_init_one(&sg, buf, len);
 
-	return chan->device->device_prep_slave_sg(chan, &sg, 1, dir, flags);
+	return chan->device->device_prep_slave_sg(chan, &sg, 1,
+						  dir, flags, NULL);
+}
+
+static inline struct dma_async_tx_descriptor *dmaengine_prep_slave_sg(
+	struct dma_chan *chan, struct scatterlist *sgl,	unsigned int sg_len,
+	enum dma_transfer_direction dir, unsigned long flags)
+{
+	return chan->device->device_prep_slave_sg(chan, sgl, sg_len,
+						  dir, flags, NULL);
+}
+
+static inline struct dma_async_tx_descriptor *dmaengine_prep_dma_cyclic(
+		struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len,
+		size_t period_len, enum dma_transfer_direction dir)
+{
+	return chan->device->device_prep_dma_cyclic(chan, buf_addr, buf_len,
+						period_len, dir, NULL);
 }
 
 static inline int dmaengine_terminate_all(struct dma_chan *chan)
diff --git a/include/linux/dw_dmac.h b/include/linux/dw_dmac.h
index f2c64f9..2412e02 100644
--- a/include/linux/dw_dmac.h
+++ b/include/linux/dw_dmac.h
@@ -31,18 +31,6 @@
 	unsigned char	chan_priority;
 };
 
-/**
- * enum dw_dma_slave_width - DMA slave register access width.
- * @DMA_SLAVE_WIDTH_8BIT: Do 8-bit slave register accesses
- * @DMA_SLAVE_WIDTH_16BIT: Do 16-bit slave register accesses
- * @DMA_SLAVE_WIDTH_32BIT: Do 32-bit slave register accesses
- */
-enum dw_dma_slave_width {
-	DW_DMA_SLAVE_WIDTH_8BIT,
-	DW_DMA_SLAVE_WIDTH_16BIT,
-	DW_DMA_SLAVE_WIDTH_32BIT,
-};
-
 /* bursts size */
 enum dw_dma_msize {
 	DW_DMA_MSIZE_1,
@@ -55,47 +43,21 @@
 	DW_DMA_MSIZE_256,
 };
 
-/* flow controller */
-enum dw_dma_fc {
-	DW_DMA_FC_D_M2M,
-	DW_DMA_FC_D_M2P,
-	DW_DMA_FC_D_P2M,
-	DW_DMA_FC_D_P2P,
-	DW_DMA_FC_P_P2M,
-	DW_DMA_FC_SP_P2P,
-	DW_DMA_FC_P_M2P,
-	DW_DMA_FC_DP_P2P,
-};
-
 /**
  * struct dw_dma_slave - Controller-specific information about a slave
  *
  * @dma_dev: required DMA master device
- * @tx_reg: physical address of data register used for
- *	memory-to-peripheral transfers
- * @rx_reg: physical address of data register used for
- *	peripheral-to-memory transfers
- * @reg_width: peripheral register width
  * @cfg_hi: Platform-specific initializer for the CFG_HI register
  * @cfg_lo: Platform-specific initializer for the CFG_LO register
  * @src_master: src master for transfers on allocated channel.
  * @dst_master: dest master for transfers on allocated channel.
- * @src_msize: src burst size.
- * @dst_msize: dest burst size.
- * @fc: flow controller for DMA transfer
  */
 struct dw_dma_slave {
 	struct device		*dma_dev;
-	dma_addr_t		tx_reg;
-	dma_addr_t		rx_reg;
-	enum dw_dma_slave_width	reg_width;
 	u32			cfg_hi;
 	u32			cfg_lo;
 	u8			src_master;
 	u8			dst_master;
-	u8			src_msize;
-	u8			dst_msize;
-	u8			fc;
 };
 
 /* Platform-configurable bits in CFG_HI */
diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h
index 82163c4..158a41e 100644
--- a/include/linux/fdtable.h
+++ b/include/linux/fdtable.h
@@ -21,23 +21,45 @@
  */
 #define NR_OPEN_DEFAULT BITS_PER_LONG
 
-/*
- * The embedded_fd_set is a small fd_set,
- * suitable for most tasks (which open <= BITS_PER_LONG files)
- */
-struct embedded_fd_set {
-	unsigned long fds_bits[1];
-};
-
 struct fdtable {
 	unsigned int max_fds;
 	struct file __rcu **fd;      /* current fd array */
-	fd_set *close_on_exec;
-	fd_set *open_fds;
+	unsigned long *close_on_exec;
+	unsigned long *open_fds;
 	struct rcu_head rcu;
 	struct fdtable *next;
 };
 
+static inline void __set_close_on_exec(int fd, struct fdtable *fdt)
+{
+	__set_bit(fd, fdt->close_on_exec);
+}
+
+static inline void __clear_close_on_exec(int fd, struct fdtable *fdt)
+{
+	__clear_bit(fd, fdt->close_on_exec);
+}
+
+static inline bool close_on_exec(int fd, const struct fdtable *fdt)
+{
+	return test_bit(fd, fdt->close_on_exec);
+}
+
+static inline void __set_open_fd(int fd, struct fdtable *fdt)
+{
+	__set_bit(fd, fdt->open_fds);
+}
+
+static inline void __clear_open_fd(int fd, struct fdtable *fdt)
+{
+	__clear_bit(fd, fdt->open_fds);
+}
+
+static inline bool fd_is_open(int fd, const struct fdtable *fdt)
+{
+	return test_bit(fd, fdt->open_fds);
+}
+
 /*
  * Open file table structure
  */
@@ -53,8 +75,8 @@
    */
 	spinlock_t file_lock ____cacheline_aligned_in_smp;
 	int next_fd;
-	struct embedded_fd_set close_on_exec_init;
-	struct embedded_fd_set open_fds_init;
+	unsigned long close_on_exec_init[1];
+	unsigned long open_fds_init[1];
 	struct file __rcu * fd_array[NR_OPEN_DEFAULT];
 };
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index c437f91..135693e 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -92,6 +92,10 @@
 /* File is opened using open(.., 3, ..) and is writeable only for ioctls
    (specialy hack for floppy.c) */
 #define FMODE_WRITE_IOCTL	((__force fmode_t)0x100)
+/* 32bit hashes as llseek() offset (for directories) */
+#define FMODE_32BITHASH         ((__force fmode_t)0x200)
+/* 64bit hashes as llseek() offset (for directories) */
+#define FMODE_64BITHASH         ((__force fmode_t)0x400)
 
 /*
  * Don't update ctime and mtime.
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 5db52d0..a5375e7 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -1,6 +1,8 @@
 #ifndef _LINUX_KERNEL_H
 #define _LINUX_KERNEL_H
 
+#include <linux/sysinfo.h>
+
 /*
  * 'kernel.h' contains some often-used function prototypes etc
  */
@@ -698,27 +700,8 @@
 # define REBUILD_DUE_TO_FTRACE_MCOUNT_RECORD
 #endif
 
-struct sysinfo;
 extern int do_sysinfo(struct sysinfo *info);
 
 #endif /* __KERNEL__ */
 
-#define SI_LOAD_SHIFT	16
-struct sysinfo {
-	long uptime;			/* Seconds since boot */
-	unsigned long loads[3];		/* 1, 5, and 15 minute load averages */
-	unsigned long totalram;		/* Total usable main memory size */
-	unsigned long freeram;		/* Available memory size */
-	unsigned long sharedram;	/* Amount of shared memory */
-	unsigned long bufferram;	/* Memory used by buffers */
-	unsigned long totalswap;	/* Total swap space size */
-	unsigned long freeswap;		/* swap space still available */
-	unsigned short procs;		/* Number of current processes */
-	unsigned short pad;		/* explicit padding for m68k */
-	unsigned long totalhigh;	/* Total high memory size */
-	unsigned long freehigh;		/* Available high memory size */
-	unsigned int mem_unit;		/* Memory unit size in bytes */
-	char _f[20-2*sizeof(long)-sizeof(int)];	/* Padding: libc5 uses this.. */
-};
-
 #endif
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 834df8b..0987146 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -438,7 +438,20 @@
 enum open_delegation_type4 {
 	NFS4_OPEN_DELEGATE_NONE = 0,
 	NFS4_OPEN_DELEGATE_READ = 1,
-	NFS4_OPEN_DELEGATE_WRITE = 2
+	NFS4_OPEN_DELEGATE_WRITE = 2,
+	NFS4_OPEN_DELEGATE_NONE_EXT = 3, /* 4.1 */
+};
+
+enum why_no_delegation4 { /* new to v4.1 */
+	WND4_NOT_WANTED = 0,
+	WND4_CONTENTION = 1,
+	WND4_RESOURCE = 2,
+	WND4_NOT_SUPP_FTYPE = 3,
+	WND4_WRITE_DELEG_NOT_SUPP_FTYPE = 4,
+	WND4_NOT_SUPP_UPGRADE = 5,
+	WND4_NOT_SUPP_DOWNGRADE = 6,
+	WND4_CANCELLED = 7,
+	WND4_IS_DIR = 8,
 };
 
 enum lock_type4 {
diff --git a/include/linux/nfsd/cld.h b/include/linux/nfsd/cld.h
new file mode 100644
index 0000000..f14a9ab
--- /dev/null
+++ b/include/linux/nfsd/cld.h
@@ -0,0 +1,56 @@
+/*
+ * Upcall description for nfsdcld communication
+ *
+ * Copyright (c) 2012 Red Hat, Inc.
+ * Author(s): Jeff Layton <jlayton@redhat.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., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#ifndef _NFSD_CLD_H
+#define _NFSD_CLD_H
+
+/* latest upcall version available */
+#define CLD_UPCALL_VERSION 1
+
+/* defined by RFC3530 */
+#define NFS4_OPAQUE_LIMIT 1024
+
+enum cld_command {
+	Cld_Create,		/* create a record for this cm_id */
+	Cld_Remove,		/* remove record of this cm_id */
+	Cld_Check,		/* is this cm_id allowed? */
+	Cld_GraceDone,		/* grace period is complete */
+};
+
+/* representation of long-form NFSv4 client ID */
+struct cld_name {
+	uint16_t	cn_len;				/* length of cm_id */
+	unsigned char	cn_id[NFS4_OPAQUE_LIMIT];	/* client-provided */
+} __attribute__((packed));
+
+/* message struct for communication with userspace */
+struct cld_msg {
+	uint8_t		cm_vers;		/* upcall version */
+	uint8_t		cm_cmd;			/* upcall command */
+	int16_t		cm_status;		/* return code */
+	uint32_t	cm_xid;			/* transaction id */
+	union {
+		int64_t		cm_gracetime;	/* grace period start time */
+		struct cld_name	cm_name;
+	} __attribute__((packed)) cm_u;
+} __attribute__((packed));
+
+#endif /* !_NFSD_CLD_H */
diff --git a/include/linux/rtc.h b/include/linux/rtc.h
index 93f4d03..fcabfb4 100644
--- a/include/linux/rtc.h
+++ b/include/linux/rtc.h
@@ -202,7 +202,8 @@
 	struct hrtimer pie_timer; /* sub second exp, so needs hrtimer */
 	int pie_enabled;
 	struct work_struct irqwork;
-
+	/* Some hardware can't support UIE mode */
+	int uie_unsupported;
 
 #ifdef CONFIG_RTC_INTF_DEV_UIE_EMUL
 	struct work_struct uie_task;
diff --git a/include/linux/sh_intc.h b/include/linux/sh_intc.h
index b160645..6aed080 100644
--- a/include/linux/sh_intc.h
+++ b/include/linux/sh_intc.h
@@ -3,6 +3,23 @@
 
 #include <linux/ioport.h>
 
+#ifdef CONFIG_SUPERH
+#define INTC_NR_IRQS	512
+#else
+#define INTC_NR_IRQS	1024
+#endif
+
+/*
+ * Convert back and forth between INTEVT and IRQ values.
+ */
+#ifdef CONFIG_CPU_HAS_INTEVT
+#define evt2irq(evt)		(((evt) >> 5) - 16)
+#define irq2evt(irq)		(((irq) + 16) << 5)
+#else
+#define evt2irq(evt)		(evt)
+#define irq2evt(irq)		(irq)
+#endif
+
 typedef unsigned char intc_enum;
 
 struct intc_vect {
diff --git a/include/linux/spinlock_api_smp.h b/include/linux/spinlock_api_smp.h
index e253ccd..51df117a 100644
--- a/include/linux/spinlock_api_smp.h
+++ b/include/linux/spinlock_api_smp.h
@@ -67,7 +67,7 @@
 #define _raw_spin_trylock_bh(lock) __raw_spin_trylock_bh(lock)
 #endif
 
-#ifdef CONFIG_INLINE_SPIN_UNLOCK
+#ifndef CONFIG_UNINLINE_SPIN_UNLOCK
 #define _raw_spin_unlock(lock) __raw_spin_unlock(lock)
 #endif
 
diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index c14fe86..0b8e3e6 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -190,7 +190,7 @@
 extern void svc_rdma_xdr_encode_write_list(struct rpcrdma_msg *, int);
 extern void svc_rdma_xdr_encode_reply_array(struct rpcrdma_write_array *, int);
 extern void svc_rdma_xdr_encode_array_chunk(struct rpcrdma_write_array *, int,
-					    u32, u64, u32);
+					    __be32, __be64, u32);
 extern void svc_rdma_xdr_encode_reply_header(struct svcxprt_rdma *,
 					     struct rpcrdma_msg *,
 					     struct rpcrdma_msg *,
@@ -292,7 +292,7 @@
 	if (wr_ary) {
 		rp_ary = (struct rpcrdma_write_array *)
 			&wr_ary->
-			wc_array[wr_ary->wc_nchunks].wc_target.rs_length;
+			wc_array[ntohl(wr_ary->wc_nchunks)].wc_target.rs_length;
 
 		goto found_it;
 	}
diff --git a/include/linux/sysinfo.h b/include/linux/sysinfo.h
new file mode 100644
index 0000000..934335a
--- /dev/null
+++ b/include/linux/sysinfo.h
@@ -0,0 +1,24 @@
+#ifndef _LINUX_SYSINFO_H
+#define _LINUX_SYSINFO_H
+
+#include <linux/types.h>
+
+#define SI_LOAD_SHIFT	16
+struct sysinfo {
+	__kernel_long_t uptime;		/* Seconds since boot */
+	__kernel_ulong_t loads[3];	/* 1, 5, and 15 minute load averages */
+	__kernel_ulong_t totalram;	/* Total usable main memory size */
+	__kernel_ulong_t freeram;	/* Available memory size */
+	__kernel_ulong_t sharedram;	/* Amount of shared memory */
+	__kernel_ulong_t bufferram;	/* Memory used by buffers */
+	__kernel_ulong_t totalswap;	/* Total swap space size */
+	__kernel_ulong_t freeswap;	/* swap space still available */
+	__u16 procs;		   	/* Number of current processes */
+	__u16 pad;		   	/* Explicit padding for m68k */
+	__kernel_ulong_t totalhigh;	/* Total high memory size */
+	__kernel_ulong_t freehigh;	/* Available high memory size */
+	__u32 mem_unit;			/* Memory unit size in bytes */
+	char _f[20-2*sizeof(__kernel_ulong_t)-sizeof(__u32)];	/* Padding: libc5 uses this.. */
+};
+
+#endif /* _LINUX_SYSINFO_H */
diff --git a/include/linux/time.h b/include/linux/time.h
index b306178..33a92ea 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -116,7 +116,6 @@
 extern void read_persistent_clock(struct timespec *ts);
 extern void read_boot_clock(struct timespec *ts);
 extern int update_persistent_clock(struct timespec now);
-extern int no_sync_cmos_clock __read_mostly;
 void timekeeping_init(void);
 extern int timekeeping_suspended;
 
@@ -256,6 +255,7 @@
 	a->tv_sec += __iter_div_u64_rem(a->tv_nsec + ns, NSEC_PER_SEC, &ns);
 	a->tv_nsec = ns;
 }
+
 #endif /* __KERNEL__ */
 
 #define NFDBITS			__NFDBITS
diff --git a/include/linux/timex.h b/include/linux/timex.h
index b75e186..99bc88b 100644
--- a/include/linux/timex.h
+++ b/include/linux/timex.h
@@ -252,7 +252,7 @@
 /* Returns how long ticks are at present, in ns / 2^NTP_SCALE_SHIFT. */
 extern u64 ntp_tick_length(void);
 
-extern void second_overflow(void);
+extern int second_overflow(unsigned long secs);
 extern int do_adjtimex(struct timex *);
 extern void hardpps(const struct timespec *, const struct timespec *);
 
diff --git a/ipc/compat.c b/ipc/compat.c
index 845a287..a6df704 100644
--- a/ipc/compat.c
+++ b/ipc/compat.c
@@ -27,6 +27,7 @@
 #include <linux/msg.h>
 #include <linux/shm.h>
 #include <linux/syscalls.h>
+#include <linux/ptrace.h>
 
 #include <linux/mutex.h>
 #include <asm/uaccess.h>
@@ -117,6 +118,7 @@
 
 static inline int compat_ipc_parse_version(int *cmd)
 {
+#ifdef CONFIG_ARCH_WANT_OLD_COMPAT_IPC
 	int version = *cmd & IPC_64;
 
 	/* this is tricky: architectures that have support for the old
@@ -128,6 +130,10 @@
 	*cmd &= ~IPC_64;
 #endif
 	return version;
+#else
+	/* With the asm-generic APIs, we always use the 64-bit versions. */
+	return IPC_64;
+#endif
 }
 
 static inline int __get_compat_ipc64_perm(struct ipc64_perm *p64,
@@ -232,10 +238,9 @@
 	return err;
 }
 
-long compat_sys_semctl(int first, int second, int third, void __user *uptr)
+static long do_compat_semctl(int first, int second, int third, u32 pad)
 {
 	union semun fourth;
-	u32 pad;
 	int err, err2;
 	struct semid64_ds s64;
 	struct semid64_ds __user *up64;
@@ -243,10 +248,6 @@
 
 	memset(&s64, 0, sizeof(s64));
 
-	if (!uptr)
-		return -EINVAL;
-	if (get_user(pad, (u32 __user *) uptr))
-		return -EFAULT;
 	if ((third & (~IPC_64)) == SETVAL)
 		fourth.val = (int) pad;
 	else
@@ -305,6 +306,18 @@
 	return err;
 }
 
+#ifdef CONFIG_ARCH_WANT_OLD_COMPAT_IPC
+long compat_sys_semctl(int first, int second, int third, void __user *uptr)
+{
+	u32 pad;
+
+	if (!uptr)
+		return -EINVAL;
+	if (get_user(pad, (u32 __user *) uptr))
+		return -EFAULT;
+	return do_compat_semctl(first, second, third, pad);
+}
+
 long compat_sys_msgsnd(int first, int second, int third, void __user *uptr)
 {
 	struct compat_msgbuf __user *up = uptr;
@@ -353,6 +366,37 @@
 out:
 	return err;
 }
+#else
+long compat_sys_semctl(int semid, int semnum, int cmd, int arg)
+{
+	return do_compat_semctl(semid, semnum, cmd, arg);
+}
+
+long compat_sys_msgsnd(int msqid, struct compat_msgbuf __user *msgp,
+		       size_t msgsz, int msgflg)
+{
+	compat_long_t mtype;
+
+	if (get_user(mtype, &msgp->mtype))
+		return -EFAULT;
+	return do_msgsnd(msqid, mtype, msgp->mtext, msgsz, msgflg);
+}
+
+long compat_sys_msgrcv(int msqid, struct compat_msgbuf __user *msgp,
+		       size_t msgsz, long msgtyp, int msgflg)
+{
+	long err, mtype;
+
+	err =  do_msgrcv(msqid, &mtype, msgp->mtext, msgsz, msgtyp, msgflg);
+	if (err < 0)
+		goto out;
+
+	if (put_user(mtype, &msgp->mtype))
+		err = -EFAULT;
+ out:
+	return err;
+}
+#endif
 
 static inline int get_compat_msqid64(struct msqid64_ds *m64,
 				     struct compat_msqid64_ds __user *up64)
@@ -470,6 +514,7 @@
 	return err;
 }
 
+#ifdef CONFIG_ARCH_WANT_OLD_COMPAT_IPC
 long compat_sys_shmat(int first, int second, compat_uptr_t third, int version,
 			void __user *uptr)
 {
@@ -485,6 +530,19 @@
 	uaddr = compat_ptr(third);
 	return put_user(raddr, uaddr);
 }
+#else
+long compat_sys_shmat(int shmid, compat_uptr_t shmaddr, int shmflg)
+{
+	unsigned long ret;
+	long err;
+
+	err = do_shmat(shmid, compat_ptr(shmaddr), shmflg, &ret);
+	if (err)
+		return err;
+	force_successful_syscall_return();
+	return (long)ret;
+}
+#endif
 
 static inline int get_compat_shmid64_ds(struct shmid64_ds *s64,
 					struct compat_shmid64_ds __user *up64)
diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks
index 5068e2a..2251882 100644
--- a/kernel/Kconfig.locks
+++ b/kernel/Kconfig.locks
@@ -124,8 +124,8 @@
 	def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \
 		 ARCH_INLINE_SPIN_LOCK_IRQSAVE
 
-config INLINE_SPIN_UNLOCK
-	def_bool !DEBUG_SPINLOCK && (!PREEMPT || ARCH_INLINE_SPIN_UNLOCK)
+config UNINLINE_SPIN_UNLOCK
+	bool
 
 config INLINE_SPIN_UNLOCK_BH
 	def_bool !DEBUG_SPINLOCK && ARCH_INLINE_SPIN_UNLOCK_BH
diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt
index 24e7cb0..3f9c974 100644
--- a/kernel/Kconfig.preempt
+++ b/kernel/Kconfig.preempt
@@ -36,6 +36,7 @@
 config PREEMPT
 	bool "Preemptible Kernel (Low-Latency Desktop)"
 	select PREEMPT_COUNT
+	select UNINLINE_SPIN_UNLOCK if !ARCH_INLINE_SPIN_UNLOCK
 	help
 	  This option reduces the latency of the kernel by making
 	  all kernel code (that is not executing in a critical section)
diff --git a/kernel/compat.c b/kernel/compat.c
index f346ced..74ff849 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -31,11 +31,10 @@
 #include <asm/uaccess.h>
 
 /*
- * Note that the native side is already converted to a timespec, because
- * that's what we want anyway.
+ * Get/set struct timeval with struct timespec on the native side
  */
-static int compat_get_timeval(struct timespec *o,
-		struct compat_timeval __user *i)
+static int compat_get_timeval_convert(struct timespec *o,
+				      struct compat_timeval __user *i)
 {
 	long usec;
 
@@ -46,8 +45,8 @@
 	return 0;
 }
 
-static int compat_put_timeval(struct compat_timeval __user *o,
-		struct timeval *i)
+static int compat_put_timeval_convert(struct compat_timeval __user *o,
+				      struct timeval *i)
 {
 	return (put_user(i->tv_sec, &o->tv_sec) ||
 		put_user(i->tv_usec, &o->tv_usec)) ? -EFAULT : 0;
@@ -117,7 +116,7 @@
 	if (tv) {
 		struct timeval ktv;
 		do_gettimeofday(&ktv);
-		if (compat_put_timeval(tv, &ktv))
+		if (compat_put_timeval_convert(tv, &ktv))
 			return -EFAULT;
 	}
 	if (tz) {
@@ -135,7 +134,7 @@
 	struct timezone ktz;
 
 	if (tv) {
-		if (compat_get_timeval(&kts, tv))
+		if (compat_get_timeval_convert(&kts, tv))
 			return -EFAULT;
 	}
 	if (tz) {
@@ -146,12 +145,29 @@
 	return do_sys_settimeofday(tv ? &kts : NULL, tz ? &ktz : NULL);
 }
 
+int get_compat_timeval(struct timeval *tv, const struct compat_timeval __user *ctv)
+{
+	return (!access_ok(VERIFY_READ, ctv, sizeof(*ctv)) ||
+			__get_user(tv->tv_sec, &ctv->tv_sec) ||
+			__get_user(tv->tv_usec, &ctv->tv_usec)) ? -EFAULT : 0;
+}
+EXPORT_SYMBOL_GPL(get_compat_timeval);
+
+int put_compat_timeval(const struct timeval *tv, struct compat_timeval __user *ctv)
+{
+	return (!access_ok(VERIFY_WRITE, ctv, sizeof(*ctv)) ||
+			__put_user(tv->tv_sec, &ctv->tv_sec) ||
+			__put_user(tv->tv_usec, &ctv->tv_usec)) ? -EFAULT : 0;
+}
+EXPORT_SYMBOL_GPL(put_compat_timeval);
+
 int get_compat_timespec(struct timespec *ts, const struct compat_timespec __user *cts)
 {
 	return (!access_ok(VERIFY_READ, cts, sizeof(*cts)) ||
 			__get_user(ts->tv_sec, &cts->tv_sec) ||
 			__get_user(ts->tv_nsec, &cts->tv_nsec)) ? -EFAULT : 0;
 }
+EXPORT_SYMBOL_GPL(get_compat_timespec);
 
 int put_compat_timespec(const struct timespec *ts, struct compat_timespec __user *cts)
 {
@@ -161,6 +177,42 @@
 }
 EXPORT_SYMBOL_GPL(put_compat_timespec);
 
+int compat_get_timeval(struct timeval *tv, const void __user *utv)
+{
+	if (COMPAT_USE_64BIT_TIME)
+		return copy_from_user(tv, utv, sizeof *tv) ? -EFAULT : 0;
+	else
+		return get_compat_timeval(tv, utv);
+}
+EXPORT_SYMBOL_GPL(compat_get_timeval);
+
+int compat_put_timeval(const struct timeval *tv, void __user *utv)
+{
+	if (COMPAT_USE_64BIT_TIME)
+		return copy_to_user(utv, tv, sizeof *tv) ? -EFAULT : 0;
+	else
+		return put_compat_timeval(tv, utv);
+}
+EXPORT_SYMBOL_GPL(compat_put_timeval);
+
+int compat_get_timespec(struct timespec *ts, const void __user *uts)
+{
+	if (COMPAT_USE_64BIT_TIME)
+		return copy_from_user(ts, uts, sizeof *ts) ? -EFAULT : 0;
+	else
+		return get_compat_timespec(ts, uts);
+}
+EXPORT_SYMBOL_GPL(compat_get_timespec);
+
+int compat_put_timespec(const struct timespec *ts, void __user *uts)
+{
+	if (COMPAT_USE_64BIT_TIME)
+		return copy_to_user(uts, ts, sizeof *ts) ? -EFAULT : 0;
+	else
+		return put_compat_timespec(ts, uts);
+}
+EXPORT_SYMBOL_GPL(compat_put_timespec);
+
 static long compat_nanosleep_restart(struct restart_block *restart)
 {
 	struct compat_timespec __user *rmtp;
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 1010cc6..b96ad75 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -2162,10 +2162,9 @@
 	mutex_unlock(&callback_mutex);
 }
 
-int cpuset_cpus_allowed_fallback(struct task_struct *tsk)
+void cpuset_cpus_allowed_fallback(struct task_struct *tsk)
 {
 	const struct cpuset *cs;
-	int cpu;
 
 	rcu_read_lock();
 	cs = task_cs(tsk);
@@ -2186,22 +2185,10 @@
 	 * changes in tsk_cs()->cpus_allowed. Otherwise we can temporary
 	 * set any mask even if it is not right from task_cs() pov,
 	 * the pending set_cpus_allowed_ptr() will fix things.
+	 *
+	 * select_fallback_rq() will fix things ups and set cpu_possible_mask
+	 * if required.
 	 */
-
-	cpu = cpumask_any_and(&tsk->cpus_allowed, cpu_active_mask);
-	if (cpu >= nr_cpu_ids) {
-		/*
-		 * Either tsk->cpus_allowed is wrong (see above) or it
-		 * is actually empty. The latter case is only possible
-		 * if we are racing with remove_tasks_in_empty_cpuset().
-		 * Like above we can temporary set any mask and rely on
-		 * set_cpus_allowed_ptr() as synchronization point.
-		 */
-		do_set_cpus_allowed(tsk, cpu_possible_mask);
-		cpu = cpumask_any(cpu_active_mask);
-	}
-
-	return cpu;
 }
 
 void cpuset_init_current_mems_allowed(void)
diff --git a/kernel/exit.c b/kernel/exit.c
index 3db1909..d8bd3b42 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -474,7 +474,7 @@
 		i = j * __NFDBITS;
 		if (i >= fdt->max_fds)
 			break;
-		set = fdt->open_fds->fds_bits[j++];
+		set = fdt->open_fds[j++];
 		while (set) {
 			if (set & 1) {
 				struct file * file = xchg(&fdt->fd[i], NULL);
diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig
index 5a38bf4..cf1a4a6 100644
--- a/kernel/irq/Kconfig
+++ b/kernel/irq/Kconfig
@@ -13,7 +13,7 @@
 # Options selectable by the architecture code
 
 # Make sparse irq Kconfig switch below available
-config HAVE_SPARSE_IRQ
+config MAY_HAVE_SPARSE_IRQ
        bool
 
 # Enable the generic irq autoprobe mechanism
@@ -56,13 +56,22 @@
 config IRQ_DOMAIN
 	bool
 
+config IRQ_DOMAIN_DEBUG
+	bool "Expose hardware/virtual IRQ mapping via debugfs"
+	depends on IRQ_DOMAIN && DEBUG_FS
+	help
+	  This option will show the mapping relationship between hardware irq
+	  numbers and Linux irq numbers. The mapping is exposed via debugfs
+	  in the file "virq_mapping".
+
+	  If you don't know what this means you don't need it.
+
 # Support forced irq threading
 config IRQ_FORCED_THREADING
        bool
 
 config SPARSE_IRQ
-	bool "Support sparse irq numbering"
-	depends on HAVE_SPARSE_IRQ
+	bool "Support sparse irq numbering" if MAY_HAVE_SPARSE_IRQ
 	---help---
 
 	  Sparse irq numbering is useful for distro kernels that want
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index af48e59..3601f3f 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -632,7 +632,7 @@
 	return revmap[hwirq];
 }
 
-#ifdef CONFIG_VIRQ_DEBUG
+#ifdef CONFIG_IRQ_DOMAIN_DEBUG
 static int virq_debug_show(struct seq_file *m, void *private)
 {
 	unsigned long flags;
@@ -668,7 +668,7 @@
 			data = irq_desc_get_chip_data(desc);
 			seq_printf(m, "0x%16p  ", data);
 
-			if (desc->irq_data.domain->of_node)
+			if (desc->irq_data.domain && desc->irq_data.domain->of_node)
 				p = desc->irq_data.domain->of_node->full_name;
 			else
 				p = none;
@@ -695,14 +695,14 @@
 
 static int __init irq_debugfs_init(void)
 {
-	if (debugfs_create_file("virq_mapping", S_IRUGO, powerpc_debugfs_root,
+	if (debugfs_create_file("irq_domain_mapping", S_IRUGO, NULL,
 				 NULL, &virq_debug_fops) == NULL)
 		return -ENOMEM;
 
 	return 0;
 }
 __initcall(irq_debugfs_init);
-#endif /* CONFIG_VIRQ_DEBUG */
+#endif /* CONFIG_IRQ_DOMAIN_DEBUG */
 
 int irq_domain_simple_map(struct irq_domain *d, unsigned int irq,
 			  irq_hw_number_t hwirq)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 157fb9b..e3ed0ec 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1265,29 +1265,59 @@
  */
 static int select_fallback_rq(int cpu, struct task_struct *p)
 {
-	int dest_cpu;
 	const struct cpumask *nodemask = cpumask_of_node(cpu_to_node(cpu));
+	enum { cpuset, possible, fail } state = cpuset;
+	int dest_cpu;
 
 	/* Look for allowed, online CPU in same node. */
-	for_each_cpu_and(dest_cpu, nodemask, cpu_active_mask)
+	for_each_cpu_mask(dest_cpu, *nodemask) {
+		if (!cpu_online(dest_cpu))
+			continue;
+		if (!cpu_active(dest_cpu))
+			continue;
 		if (cpumask_test_cpu(dest_cpu, tsk_cpus_allowed(p)))
 			return dest_cpu;
+	}
 
-	/* Any allowed, online CPU? */
-	dest_cpu = cpumask_any_and(tsk_cpus_allowed(p), cpu_active_mask);
-	if (dest_cpu < nr_cpu_ids)
-		return dest_cpu;
+	for (;;) {
+		/* Any allowed, online CPU? */
+		for_each_cpu_mask(dest_cpu, *tsk_cpus_allowed(p)) {
+			if (!cpu_online(dest_cpu))
+				continue;
+			if (!cpu_active(dest_cpu))
+				continue;
+			goto out;
+		}
 
-	/* No more Mr. Nice Guy. */
-	dest_cpu = cpuset_cpus_allowed_fallback(p);
-	/*
-	 * Don't tell them about moving exiting tasks or
-	 * kernel threads (both mm NULL), since they never
-	 * leave kernel.
-	 */
-	if (p->mm && printk_ratelimit()) {
-		printk_sched("process %d (%s) no longer affine to cpu%d\n",
-				task_pid_nr(p), p->comm, cpu);
+		switch (state) {
+		case cpuset:
+			/* No more Mr. Nice Guy. */
+			cpuset_cpus_allowed_fallback(p);
+			state = possible;
+			break;
+
+		case possible:
+			do_set_cpus_allowed(p, cpu_possible_mask);
+			state = fail;
+			break;
+
+		case fail:
+			BUG();
+			break;
+		}
+	}
+
+out:
+	if (state != cpuset) {
+		/*
+		 * Don't tell them about moving exiting tasks or
+		 * kernel threads (both mm NULL), since they never
+		 * leave kernel.
+		 */
+		if (p->mm && printk_ratelimit()) {
+			printk_sched("process %d (%s) no longer affine to cpu%d\n",
+					task_pid_nr(p), p->comm, cpu);
+		}
 	}
 
 	return dest_cpu;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 94340c7..0d97ebd 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -416,8 +416,8 @@
 
 #endif	/* CONFIG_FAIR_GROUP_SCHED */
 
-static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq,
-				   unsigned long delta_exec);
+static __always_inline
+void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, unsigned long delta_exec);
 
 /**************************************************************
  * Scheduling class tree data structure manipulation methods:
@@ -1162,7 +1162,7 @@
 		__clear_buddies_skip(se);
 }
 
-static void return_cfs_rq_runtime(struct cfs_rq *cfs_rq);
+static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq);
 
 static void
 dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
@@ -1546,8 +1546,8 @@
 		resched_task(rq_of(cfs_rq)->curr);
 }
 
-static __always_inline void account_cfs_rq_runtime(struct cfs_rq *cfs_rq,
-						   unsigned long delta_exec)
+static __always_inline
+void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, unsigned long delta_exec)
 {
 	if (!cfs_bandwidth_used() || !cfs_rq->runtime_enabled)
 		return;
@@ -2073,11 +2073,11 @@
 }
 
 #else /* CONFIG_CFS_BANDWIDTH */
-static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq,
-				     unsigned long delta_exec) {}
+static __always_inline
+void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, unsigned long delta_exec) {}
 static void check_cfs_rq_runtime(struct cfs_rq *cfs_rq) {}
 static void check_enqueue_throttle(struct cfs_rq *cfs_rq) {}
-static void return_cfs_rq_runtime(struct cfs_rq *cfs_rq) {}
+static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq) {}
 
 static inline int cfs_rq_throttled(struct cfs_rq *cfs_rq)
 {
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index b60dad7..44af55e 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1428,7 +1428,7 @@
 next_idx:
 		if (idx >= MAX_RT_PRIO)
 			continue;
-		if (next && next->prio < idx)
+		if (next && next->prio <= idx)
 			continue;
 		list_for_each_entry(rt_se, array->queue + idx, run_list) {
 			struct task_struct *p;
diff --git a/kernel/spinlock.c b/kernel/spinlock.c
index 84c7d96..5cdd806 100644
--- a/kernel/spinlock.c
+++ b/kernel/spinlock.c
@@ -163,7 +163,7 @@
 EXPORT_SYMBOL(_raw_spin_lock_bh);
 #endif
 
-#ifndef CONFIG_INLINE_SPIN_UNLOCK
+#ifdef CONFIG_UNINLINE_SPIN_UNLOCK
 void __lockfunc _raw_spin_unlock(raw_spinlock_t *lock)
 {
 	__raw_spin_unlock(lock);
diff --git a/kernel/time.c b/kernel/time.c
index 73e416d..ba744cf 100644
--- a/kernel/time.c
+++ b/kernel/time.c
@@ -163,7 +163,6 @@
 		return error;
 
 	if (tz) {
-		/* SMP safe, global irq locking makes it work. */
 		sys_tz = *tz;
 		update_vsyscall_tz();
 		if (firsttime) {
@@ -173,12 +172,7 @@
 		}
 	}
 	if (tv)
-	{
-		/* SMP safe, again the code in arch/foo/time.c should
-		 * globally block out interrupts when it runs.
-		 */
 		return do_settimeofday(tv);
-	}
 	return 0;
 }
 
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index 8a46f5d..8a538c5 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -96,6 +96,11 @@
 	return 0;
 }
 
+static inline void alarmtimer_rtc_timer_init(void)
+{
+	rtc_timer_init(&rtctimer, NULL, NULL);
+}
+
 static struct class_interface alarmtimer_rtc_interface = {
 	.add_dev = &alarmtimer_rtc_add_device,
 };
@@ -117,6 +122,7 @@
 #define rtcdev (NULL)
 static inline int alarmtimer_rtc_interface_setup(void) { return 0; }
 static inline void alarmtimer_rtc_interface_remove(void) { }
+static inline void alarmtimer_rtc_timer_init(void) { }
 #endif
 
 /**
@@ -783,6 +789,8 @@
 		.nsleep		= alarm_timer_nsleep,
 	};
 
+	alarmtimer_rtc_timer_init();
+
 	posix_timers_register_clock(CLOCK_REALTIME_ALARM, &alarm_clock);
 	posix_timers_register_clock(CLOCK_BOOTTIME_ALARM, &alarm_clock);
 
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index a45ca16..c958338 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -500,7 +500,7 @@
 {
 	u64 ret;
 	/*
-	 * We won't try to correct for more then 11% adjustments (110,000 ppm),
+	 * We won't try to correct for more than 11% adjustments (110,000 ppm),
 	 */
 	ret = (u64)cs->mult * 11;
 	do_div(ret,100);
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 6e039b1..f03fd83 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -34,8 +34,6 @@
 static u64			tick_length;
 static u64			tick_length_base;
 
-static struct hrtimer		leap_timer;
-
 #define MAX_TICKADJ		500LL		/* usecs */
 #define MAX_TICKADJ_SCALED \
 	(((MAX_TICKADJ * NSEC_PER_USEC) << NTP_SCALE_SHIFT) / NTP_INTERVAL_FREQ)
@@ -381,71 +379,64 @@
 
 
 /*
- * Leap second processing. If in leap-insert state at the end of the
- * day, the system clock is set back one second; if in leap-delete
- * state, the system clock is set ahead one second.
- */
-static enum hrtimer_restart ntp_leap_second(struct hrtimer *timer)
-{
-	enum hrtimer_restart res = HRTIMER_NORESTART;
-	unsigned long flags;
-	int leap = 0;
-
-	spin_lock_irqsave(&ntp_lock, flags);
-	switch (time_state) {
-	case TIME_OK:
-		break;
-	case TIME_INS:
-		leap = -1;
-		time_state = TIME_OOP;
-		printk(KERN_NOTICE
-			"Clock: inserting leap second 23:59:60 UTC\n");
-		hrtimer_add_expires_ns(&leap_timer, NSEC_PER_SEC);
-		res = HRTIMER_RESTART;
-		break;
-	case TIME_DEL:
-		leap = 1;
-		time_tai--;
-		time_state = TIME_WAIT;
-		printk(KERN_NOTICE
-			"Clock: deleting leap second 23:59:59 UTC\n");
-		break;
-	case TIME_OOP:
-		time_tai++;
-		time_state = TIME_WAIT;
-		/* fall through */
-	case TIME_WAIT:
-		if (!(time_status & (STA_INS | STA_DEL)))
-			time_state = TIME_OK;
-		break;
-	}
-	spin_unlock_irqrestore(&ntp_lock, flags);
-
-	/*
-	 * We have to call this outside of the ntp_lock to keep
-	 * the proper locking hierarchy
-	 */
-	if (leap)
-		timekeeping_leap_insert(leap);
-
-	return res;
-}
-
-/*
  * this routine handles the overflow of the microsecond field
  *
  * The tricky bits of code to handle the accurate clock support
  * were provided by Dave Mills (Mills@UDEL.EDU) of NTP fame.
  * They were originally developed for SUN and DEC kernels.
  * All the kudos should go to Dave for this stuff.
+ *
+ * Also handles leap second processing, and returns leap offset
  */
-void second_overflow(void)
+int second_overflow(unsigned long secs)
 {
 	s64 delta;
+	int leap = 0;
 	unsigned long flags;
 
 	spin_lock_irqsave(&ntp_lock, flags);
 
+	/*
+	 * Leap second processing. If in leap-insert state at the end of the
+	 * day, the system clock is set back one second; if in leap-delete
+	 * state, the system clock is set ahead one second.
+	 */
+	switch (time_state) {
+	case TIME_OK:
+		if (time_status & STA_INS)
+			time_state = TIME_INS;
+		else if (time_status & STA_DEL)
+			time_state = TIME_DEL;
+		break;
+	case TIME_INS:
+		if (secs % 86400 == 0) {
+			leap = -1;
+			time_state = TIME_OOP;
+			printk(KERN_NOTICE
+				"Clock: inserting leap second 23:59:60 UTC\n");
+		}
+		break;
+	case TIME_DEL:
+		if ((secs + 1) % 86400 == 0) {
+			leap = 1;
+			time_tai--;
+			time_state = TIME_WAIT;
+			printk(KERN_NOTICE
+				"Clock: deleting leap second 23:59:59 UTC\n");
+		}
+		break;
+	case TIME_OOP:
+		time_tai++;
+		time_state = TIME_WAIT;
+		break;
+
+	case TIME_WAIT:
+		if (!(time_status & (STA_INS | STA_DEL)))
+			time_state = TIME_OK;
+		break;
+	}
+
+
 	/* Bump the maxerror field */
 	time_maxerror += MAXFREQ / NSEC_PER_USEC;
 	if (time_maxerror > NTP_PHASE_LIMIT) {
@@ -481,15 +472,17 @@
 	tick_length += (s64)(time_adjust * NSEC_PER_USEC / NTP_INTERVAL_FREQ)
 							 << NTP_SCALE_SHIFT;
 	time_adjust = 0;
+
+
+
 out:
 	spin_unlock_irqrestore(&ntp_lock, flags);
+
+	return leap;
 }
 
 #ifdef CONFIG_GENERIC_CMOS_UPDATE
 
-/* Disable the cmos update - used by virtualization and embedded */
-int no_sync_cmos_clock  __read_mostly;
-
 static void sync_cmos_clock(struct work_struct *work);
 
 static DECLARE_DELAYED_WORK(sync_cmos_work, sync_cmos_clock);
@@ -536,35 +529,13 @@
 
 static void notify_cmos_timer(void)
 {
-	if (!no_sync_cmos_clock)
-		schedule_delayed_work(&sync_cmos_work, 0);
+	schedule_delayed_work(&sync_cmos_work, 0);
 }
 
 #else
 static inline void notify_cmos_timer(void) { }
 #endif
 
-/*
- * Start the leap seconds timer:
- */
-static inline void ntp_start_leap_timer(struct timespec *ts)
-{
-	long now = ts->tv_sec;
-
-	if (time_status & STA_INS) {
-		time_state = TIME_INS;
-		now += 86400 - now % 86400;
-		hrtimer_start(&leap_timer, ktime_set(now, 0), HRTIMER_MODE_ABS);
-
-		return;
-	}
-
-	if (time_status & STA_DEL) {
-		time_state = TIME_DEL;
-		now += 86400 - (now + 1) % 86400;
-		hrtimer_start(&leap_timer, ktime_set(now, 0), HRTIMER_MODE_ABS);
-	}
-}
 
 /*
  * Propagate a new txc->status value into the NTP state:
@@ -589,22 +560,6 @@
 	time_status &= STA_RONLY;
 	time_status |= txc->status & ~STA_RONLY;
 
-	switch (time_state) {
-	case TIME_OK:
-		ntp_start_leap_timer(ts);
-		break;
-	case TIME_INS:
-	case TIME_DEL:
-		time_state = TIME_OK;
-		ntp_start_leap_timer(ts);
-	case TIME_WAIT:
-		if (!(time_status & (STA_INS | STA_DEL)))
-			time_state = TIME_OK;
-		break;
-	case TIME_OOP:
-		hrtimer_restart(&leap_timer);
-		break;
-	}
 }
 /*
  * Called with the xtime lock held, so we can access and modify
@@ -686,9 +641,6 @@
 		    (txc->tick <  900000/USER_HZ ||
 		     txc->tick > 1100000/USER_HZ))
 			return -EINVAL;
-
-		if (txc->modes & ADJ_STATUS && time_state != TIME_OK)
-			hrtimer_cancel(&leap_timer);
 	}
 
 	if (txc->modes & ADJ_SETOFFSET) {
@@ -1010,6 +962,4 @@
 void __init ntp_init(void)
 {
 	ntp_clear();
-	hrtimer_init(&leap_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
-	leap_timer.function = ntp_leap_second;
 }
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 15be32e..d66b213 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -184,18 +184,6 @@
 }
 
 
-void timekeeping_leap_insert(int leapsecond)
-{
-	unsigned long flags;
-
-	write_seqlock_irqsave(&timekeeper.lock, flags);
-	timekeeper.xtime.tv_sec += leapsecond;
-	timekeeper.wall_to_monotonic.tv_sec -= leapsecond;
-	timekeeping_update(false);
-	write_sequnlock_irqrestore(&timekeeper.lock, flags);
-
-}
-
 /**
  * timekeeping_forward_now - update clock to the current time
  *
@@ -448,9 +436,12 @@
 static int change_clocksource(void *data)
 {
 	struct clocksource *new, *old;
+	unsigned long flags;
 
 	new = (struct clocksource *) data;
 
+	write_seqlock_irqsave(&timekeeper.lock, flags);
+
 	timekeeping_forward_now();
 	if (!new->enable || new->enable(new) == 0) {
 		old = timekeeper.clock;
@@ -458,6 +449,10 @@
 		if (old->disable)
 			old->disable(old);
 	}
+	timekeeping_update(true);
+
+	write_sequnlock_irqrestore(&timekeeper.lock, flags);
+
 	return 0;
 }
 
@@ -827,7 +822,7 @@
 	int adj;
 
 	/*
-	 * The point of this is to check if the error is greater then half
+	 * The point of this is to check if the error is greater than half
 	 * an interval.
 	 *
 	 * First we shift it down from NTP_SHIFT to clocksource->shifted nsecs.
@@ -835,7 +830,7 @@
 	 * Note we subtract one in the shift, so that error is really error*2.
 	 * This "saves" dividing(shifting) interval twice, but keeps the
 	 * (error > interval) comparison as still measuring if error is
-	 * larger then half an interval.
+	 * larger than half an interval.
 	 *
 	 * Note: It does not "save" on aggravation when reading the code.
 	 */
@@ -843,7 +838,7 @@
 	if (error > interval) {
 		/*
 		 * We now divide error by 4(via shift), which checks if
-		 * the error is greater then twice the interval.
+		 * the error is greater than twice the interval.
 		 * If it is greater, we need a bigadjust, if its smaller,
 		 * we can adjust by 1.
 		 */
@@ -874,13 +869,15 @@
 	} else /* No adjustment needed */
 		return;
 
-	WARN_ONCE(timekeeper.clock->maxadj &&
-			(timekeeper.mult + adj > timekeeper.clock->mult +
-						timekeeper.clock->maxadj),
-			"Adjusting %s more then 11%% (%ld vs %ld)\n",
+	if (unlikely(timekeeper.clock->maxadj &&
+			(timekeeper.mult + adj >
+			timekeeper.clock->mult + timekeeper.clock->maxadj))) {
+		printk_once(KERN_WARNING
+			"Adjusting %s more than 11%% (%ld vs %ld)\n",
 			timekeeper.clock->name, (long)timekeeper.mult + adj,
 			(long)timekeeper.clock->mult +
 				timekeeper.clock->maxadj);
+	}
 	/*
 	 * So the following can be confusing.
 	 *
@@ -952,7 +949,7 @@
 	u64 nsecps = (u64)NSEC_PER_SEC << timekeeper.shift;
 	u64 raw_nsecs;
 
-	/* If the offset is smaller then a shifted interval, do nothing */
+	/* If the offset is smaller than a shifted interval, do nothing */
 	if (offset < timekeeper.cycle_interval<<shift)
 		return offset;
 
@@ -962,9 +959,11 @@
 
 	timekeeper.xtime_nsec += timekeeper.xtime_interval << shift;
 	while (timekeeper.xtime_nsec >= nsecps) {
+		int leap;
 		timekeeper.xtime_nsec -= nsecps;
 		timekeeper.xtime.tv_sec++;
-		second_overflow();
+		leap = second_overflow(timekeeper.xtime.tv_sec);
+		timekeeper.xtime.tv_sec += leap;
 	}
 
 	/* Accumulate raw time */
@@ -1018,13 +1017,13 @@
 	 * With NO_HZ we may have to accumulate many cycle_intervals
 	 * (think "ticks") worth of time at once. To do this efficiently,
 	 * we calculate the largest doubling multiple of cycle_intervals
-	 * that is smaller then the offset. We then accumulate that
+	 * that is smaller than the offset.  We then accumulate that
 	 * chunk in one go, and then try to consume the next smaller
 	 * doubled multiple.
 	 */
 	shift = ilog2(offset) - ilog2(timekeeper.cycle_interval);
 	shift = max(0, shift);
-	/* Bound shift to one less then what overflows tick_length */
+	/* Bound shift to one less than what overflows tick_length */
 	maxshift = (64 - (ilog2(ntp_tick_length())+1)) - 1;
 	shift = min(shift, maxshift);
 	while (offset >= timekeeper.cycle_interval) {
@@ -1072,12 +1071,14 @@
 
 	/*
 	 * Finally, make sure that after the rounding
-	 * xtime.tv_nsec isn't larger then NSEC_PER_SEC
+	 * xtime.tv_nsec isn't larger than NSEC_PER_SEC
 	 */
 	if (unlikely(timekeeper.xtime.tv_nsec >= NSEC_PER_SEC)) {
+		int leap;
 		timekeeper.xtime.tv_nsec -= NSEC_PER_SEC;
 		timekeeper.xtime.tv_sec++;
-		second_overflow();
+		leap = second_overflow(timekeeper.xtime.tv_sec);
+		timekeeper.xtime.tv_sec += leap;
 	}
 
 	timekeeping_update(false);
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index f7af95d..6777153 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -499,6 +499,7 @@
 config DEBUG_SPINLOCK
 	bool "Spinlock and rw-lock debugging: basic checks"
 	depends on DEBUG_KERNEL
+	select UNINLINE_SPIN_UNLOCK
 	help
 	  Say Y here and build SMP to catch missing spinlock initialization
 	  and certain other kinds of spinlock errors commonly made.  This is
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index 4914261..5914623 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -733,7 +733,8 @@
 		data = &tv;
 		len = sizeof(tv);
 #ifdef CONFIG_COMPAT
-		if (msg->msg_flags & MSG_CMSG_COMPAT) {
+		if (!COMPAT_USE_64BIT_TIME &&
+		    (msg->msg_flags & MSG_CMSG_COMPAT)) {
 			ctv.tv_sec = tv.tv_sec;
 			ctv.tv_usec = tv.tv_usec;
 			data = &ctv;
diff --git a/net/compat.c b/net/compat.c
index 64b4515..e055708 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -219,8 +219,6 @@
 
 int put_cmsg_compat(struct msghdr *kmsg, int level, int type, int len, void *data)
 {
-	struct compat_timeval ctv;
-	struct compat_timespec cts[3];
 	struct compat_cmsghdr __user *cm = (struct compat_cmsghdr __user *) kmsg->msg_control;
 	struct compat_cmsghdr cmhdr;
 	int cmlen;
@@ -230,24 +228,28 @@
 		return 0; /* XXX: return error? check spec. */
 	}
 
-	if (level == SOL_SOCKET && type == SCM_TIMESTAMP) {
-		struct timeval *tv = (struct timeval *)data;
-		ctv.tv_sec = tv->tv_sec;
-		ctv.tv_usec = tv->tv_usec;
-		data = &ctv;
-		len = sizeof(ctv);
-	}
-	if (level == SOL_SOCKET &&
-	    (type == SCM_TIMESTAMPNS || type == SCM_TIMESTAMPING)) {
-		int count = type == SCM_TIMESTAMPNS ? 1 : 3;
-		int i;
-		struct timespec *ts = (struct timespec *)data;
-		for (i = 0; i < count; i++) {
-			cts[i].tv_sec = ts[i].tv_sec;
-			cts[i].tv_nsec = ts[i].tv_nsec;
+	if (!COMPAT_USE_64BIT_TIME) {
+		struct compat_timeval ctv;
+		struct compat_timespec cts[3];
+		if (level == SOL_SOCKET && type == SCM_TIMESTAMP) {
+			struct timeval *tv = (struct timeval *)data;
+			ctv.tv_sec = tv->tv_sec;
+			ctv.tv_usec = tv->tv_usec;
+			data = &ctv;
+			len = sizeof(ctv);
 		}
-		data = &cts;
-		len = sizeof(cts[0]) * count;
+		if (level == SOL_SOCKET &&
+		    (type == SCM_TIMESTAMPNS || type == SCM_TIMESTAMPING)) {
+			int count = type == SCM_TIMESTAMPNS ? 1 : 3;
+			int i;
+			struct timespec *ts = (struct timespec *)data;
+			for (i = 0; i < count; i++) {
+				cts[i].tv_sec = ts[i].tv_sec;
+				cts[i].tv_nsec = ts[i].tv_nsec;
+			}
+			data = &cts;
+			len = sizeof(cts[0]) * count;
+		}
 	}
 
 	cmlen = CMSG_COMPAT_LEN(len);
@@ -454,11 +456,15 @@
 
 int compat_sock_get_timestamp(struct sock *sk, struct timeval __user *userstamp)
 {
-	struct compat_timeval __user *ctv =
-			(struct compat_timeval __user *) userstamp;
-	int err = -ENOENT;
+	struct compat_timeval __user *ctv;
+	int err;
 	struct timeval tv;
 
+	if (COMPAT_USE_64BIT_TIME)
+		return sock_get_timestamp(sk, userstamp);
+
+	ctv = (struct compat_timeval __user *) userstamp;
+	err = -ENOENT;
 	if (!sock_flag(sk, SOCK_TIMESTAMP))
 		sock_enable_timestamp(sk, SOCK_TIMESTAMP);
 	tv = ktime_to_timeval(sk->sk_stamp);
@@ -478,11 +484,15 @@
 
 int compat_sock_get_timestampns(struct sock *sk, struct timespec __user *userstamp)
 {
-	struct compat_timespec __user *ctv =
-			(struct compat_timespec __user *) userstamp;
-	int err = -ENOENT;
+	struct compat_timespec __user *ctv;
+	int err;
 	struct timespec ts;
 
+	if (COMPAT_USE_64BIT_TIME)
+		return sock_get_timestampns (sk, userstamp);
+
+	ctv = (struct compat_timespec __user *) userstamp;
+	err = -ENOENT;
 	if (!sock_flag(sk, SOCK_TIMESTAMP))
 		sock_enable_timestamp(sk, SOCK_TIMESTAMP);
 	ts = ktime_to_timespec(sk->sk_stamp);
@@ -767,6 +777,11 @@
 	int datagrams;
 	struct timespec ktspec;
 
+	if (COMPAT_USE_64BIT_TIME)
+		return __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen,
+				      flags | MSG_CMSG_COMPAT,
+				      (struct timespec *) timeout);
+
 	if (timeout == NULL)
 		return __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen,
 				      flags | MSG_CMSG_COMPAT, NULL);
diff --git a/net/socket.c b/net/socket.c
index 12a48d8..484cc69 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2592,7 +2592,7 @@
 
 #ifdef CONFIG_COMPAT
 static int do_siocgstamp(struct net *net, struct socket *sock,
-			 unsigned int cmd, struct compat_timeval __user *up)
+			 unsigned int cmd, void __user *up)
 {
 	mm_segment_t old_fs = get_fs();
 	struct timeval ktv;
@@ -2601,15 +2601,14 @@
 	set_fs(KERNEL_DS);
 	err = sock_do_ioctl(net, sock, cmd, (unsigned long)&ktv);
 	set_fs(old_fs);
-	if (!err) {
-		err = put_user(ktv.tv_sec, &up->tv_sec);
-		err |= __put_user(ktv.tv_usec, &up->tv_usec);
-	}
+	if (!err)
+		err = compat_put_timeval(up, &ktv);
+
 	return err;
 }
 
 static int do_siocgstampns(struct net *net, struct socket *sock,
-			 unsigned int cmd, struct compat_timespec __user *up)
+			   unsigned int cmd, void __user *up)
 {
 	mm_segment_t old_fs = get_fs();
 	struct timespec kts;
@@ -2618,10 +2617,9 @@
 	set_fs(KERNEL_DS);
 	err = sock_do_ioctl(net, sock, cmd, (unsigned long)&kts);
 	set_fs(old_fs);
-	if (!err) {
-		err = put_user(kts.tv_sec, &up->tv_sec);
-		err |= __put_user(kts.tv_nsec, &up->tv_nsec);
-	}
+	if (!err)
+		err = compat_put_timespec(up, &kts);
+
 	return err;
 }
 
diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index f21ece0..de0b0f3 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -830,6 +830,8 @@
 {
 	ssize_t ret;
 
+	if (count == 0)
+		return -EINVAL;
 	if (copy_from_user(kaddr, buf, count))
 		return -EFAULT;
 	kaddr[count] = '\0';
diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c
index c84c0e0..0af37fc 100644
--- a/net/sunrpc/rpc_pipe.c
+++ b/net/sunrpc/rpc_pipe.c
@@ -1014,6 +1014,7 @@
 	RPCAUTH_statd,
 	RPCAUTH_nfsd4_cb,
 	RPCAUTH_cache,
+	RPCAUTH_nfsd,
 	RPCAUTH_RootEOF
 };
 
@@ -1046,6 +1047,10 @@
 		.name = "cache",
 		.mode = S_IFDIR | S_IRUGO | S_IXUGO,
 	},
+	[RPCAUTH_nfsd] = {
+		.name = "nfsd",
+		.mode = S_IFDIR | S_IRUGO | S_IXUGO,
+	},
 };
 
 /*
diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c
index bcd574f..521d8f7 100644
--- a/net/sunrpc/svcauth_unix.c
+++ b/net/sunrpc/svcauth_unix.c
@@ -507,7 +507,7 @@
 	time_t expiry;
 	struct unix_gid ug, *ugp;
 
-	if (mlen <= 0 || mesg[mlen-1] != '\n')
+	if (mesg[mlen - 1] != '\n')
 		return -EINVAL;
 	mesg[mlen-1] = 0;
 
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 40ae884..824d32f 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -1381,8 +1381,6 @@
 	spin_lock_bh(&serv->sv_lock);
 	list_for_each_entry(svsk, &serv->sv_permsocks, sk_xprt.xpt_list)
 		set_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags);
-	list_for_each_entry(svsk, &serv->sv_tempsocks, sk_xprt.xpt_list)
-		set_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags);
 	spin_unlock_bh(&serv->sv_lock);
 }
 EXPORT_SYMBOL_GPL(svc_sock_update_bufs);
diff --git a/net/sunrpc/xprtrdma/svc_rdma.c b/net/sunrpc/xprtrdma/svc_rdma.c
index 09af4fa..8343737 100644
--- a/net/sunrpc/xprtrdma/svc_rdma.c
+++ b/net/sunrpc/xprtrdma/svc_rdma.c
@@ -47,6 +47,7 @@
 #include <linux/sunrpc/clnt.h>
 #include <linux/sunrpc/sched.h>
 #include <linux/sunrpc/svc_rdma.h>
+#include "xprt_rdma.h"
 
 #define RPCDBG_FACILITY	RPCDBG_SVCXPRT
 
diff --git a/net/sunrpc/xprtrdma/svc_rdma_marshal.c b/net/sunrpc/xprtrdma/svc_rdma_marshal.c
index 9530ef2..8d2eddd 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_marshal.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_marshal.c
@@ -60,21 +60,11 @@
 	struct rpcrdma_read_chunk *ch = (struct rpcrdma_read_chunk *)va;
 
 	while (ch->rc_discrim != xdr_zero) {
-		u64 ch_offset;
-
 		if (((unsigned long)ch + sizeof(struct rpcrdma_read_chunk)) >
 		    (unsigned long)vaend) {
 			dprintk("svcrdma: vaend=%p, ch=%p\n", vaend, ch);
 			return NULL;
 		}
-
-		ch->rc_discrim = ntohl(ch->rc_discrim);
-		ch->rc_position = ntohl(ch->rc_position);
-		ch->rc_target.rs_handle = ntohl(ch->rc_target.rs_handle);
-		ch->rc_target.rs_length = ntohl(ch->rc_target.rs_length);
-		va = (u32 *)&ch->rc_target.rs_offset;
-		xdr_decode_hyper(va, &ch_offset);
-		put_unaligned(ch_offset, (u64 *)va);
 		ch++;
 	}
 	return (u32 *)&ch->rc_position;
@@ -91,7 +81,7 @@
 	*byte_count = 0;
 	*ch_count = 0;
 	for (; ch->rc_discrim != 0; ch++) {
-		*byte_count = *byte_count + ch->rc_target.rs_length;
+		*byte_count = *byte_count + ntohl(ch->rc_target.rs_length);
 		*ch_count = *ch_count + 1;
 	}
 }
@@ -108,7 +98,8 @@
  */
 static u32 *decode_write_list(u32 *va, u32 *vaend)
 {
-	int ch_no;
+	int nchunks;
+
 	struct rpcrdma_write_array *ary =
 		(struct rpcrdma_write_array *)va;
 
@@ -121,37 +112,24 @@
 		dprintk("svcrdma: ary=%p, vaend=%p\n", ary, vaend);
 		return NULL;
 	}
-	ary->wc_discrim = ntohl(ary->wc_discrim);
-	ary->wc_nchunks = ntohl(ary->wc_nchunks);
+	nchunks = ntohl(ary->wc_nchunks);
 	if (((unsigned long)&ary->wc_array[0] +
-	     (sizeof(struct rpcrdma_write_chunk) * ary->wc_nchunks)) >
+	     (sizeof(struct rpcrdma_write_chunk) * nchunks)) >
 	    (unsigned long)vaend) {
 		dprintk("svcrdma: ary=%p, wc_nchunks=%d, vaend=%p\n",
-			ary, ary->wc_nchunks, vaend);
+			ary, nchunks, vaend);
 		return NULL;
 	}
-	for (ch_no = 0; ch_no < ary->wc_nchunks; ch_no++) {
-		u64 ch_offset;
-
-		ary->wc_array[ch_no].wc_target.rs_handle =
-			ntohl(ary->wc_array[ch_no].wc_target.rs_handle);
-		ary->wc_array[ch_no].wc_target.rs_length =
-			ntohl(ary->wc_array[ch_no].wc_target.rs_length);
-		va = (u32 *)&ary->wc_array[ch_no].wc_target.rs_offset;
-		xdr_decode_hyper(va, &ch_offset);
-		put_unaligned(ch_offset, (u64 *)va);
-	}
-
 	/*
 	 * rs_length is the 2nd 4B field in wc_target and taking its
 	 * address skips the list terminator
 	 */
-	return (u32 *)&ary->wc_array[ch_no].wc_target.rs_length;
+	return (u32 *)&ary->wc_array[nchunks].wc_target.rs_length;
 }
 
 static u32 *decode_reply_array(u32 *va, u32 *vaend)
 {
-	int ch_no;
+	int nchunks;
 	struct rpcrdma_write_array *ary =
 		(struct rpcrdma_write_array *)va;
 
@@ -164,28 +142,15 @@
 		dprintk("svcrdma: ary=%p, vaend=%p\n", ary, vaend);
 		return NULL;
 	}
-	ary->wc_discrim = ntohl(ary->wc_discrim);
-	ary->wc_nchunks = ntohl(ary->wc_nchunks);
+	nchunks = ntohl(ary->wc_nchunks);
 	if (((unsigned long)&ary->wc_array[0] +
-	     (sizeof(struct rpcrdma_write_chunk) * ary->wc_nchunks)) >
+	     (sizeof(struct rpcrdma_write_chunk) * nchunks)) >
 	    (unsigned long)vaend) {
 		dprintk("svcrdma: ary=%p, wc_nchunks=%d, vaend=%p\n",
-			ary, ary->wc_nchunks, vaend);
+			ary, nchunks, vaend);
 		return NULL;
 	}
-	for (ch_no = 0; ch_no < ary->wc_nchunks; ch_no++) {
-		u64 ch_offset;
-
-		ary->wc_array[ch_no].wc_target.rs_handle =
-			ntohl(ary->wc_array[ch_no].wc_target.rs_handle);
-		ary->wc_array[ch_no].wc_target.rs_length =
-			ntohl(ary->wc_array[ch_no].wc_target.rs_length);
-		va = (u32 *)&ary->wc_array[ch_no].wc_target.rs_offset;
-		xdr_decode_hyper(va, &ch_offset);
-		put_unaligned(ch_offset, (u64 *)va);
-	}
-
-	return (u32 *)&ary->wc_array[ch_no];
+	return (u32 *)&ary->wc_array[nchunks];
 }
 
 int svc_rdma_xdr_decode_req(struct rpcrdma_msg **rdma_req,
@@ -386,13 +351,14 @@
 
 void svc_rdma_xdr_encode_array_chunk(struct rpcrdma_write_array *ary,
 				     int chunk_no,
-				     u32 rs_handle, u64 rs_offset,
+				     __be32 rs_handle,
+				     __be64 rs_offset,
 				     u32 write_len)
 {
 	struct rpcrdma_segment *seg = &ary->wc_array[chunk_no].wc_target;
-	seg->rs_handle = htonl(rs_handle);
+	seg->rs_handle = rs_handle;
+	seg->rs_offset = rs_offset;
 	seg->rs_length = htonl(write_len);
-	xdr_encode_hyper((u32 *) &seg->rs_offset, rs_offset);
 }
 
 void svc_rdma_xdr_encode_reply_header(struct svcxprt_rdma *xprt,
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index df67211..41cb63b 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -147,7 +147,7 @@
 	page_off = 0;
 	ch = (struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0];
 	ch_no = 0;
-	ch_bytes = ch->rc_target.rs_length;
+	ch_bytes = ntohl(ch->rc_target.rs_length);
 	head->arg.head[0] = rqstp->rq_arg.head[0];
 	head->arg.tail[0] = rqstp->rq_arg.tail[0];
 	head->arg.pages = &head->pages[head->count];
@@ -183,7 +183,7 @@
 			ch_no++;
 			ch++;
 			chl_map->ch[ch_no].start = sge_no;
-			ch_bytes = ch->rc_target.rs_length;
+			ch_bytes = ntohl(ch->rc_target.rs_length);
 			/* If bytes remaining account for next chunk */
 			if (byte_count) {
 				head->arg.page_len += ch_bytes;
@@ -281,11 +281,12 @@
 	offset = 0;
 	ch = (struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0];
 	for (ch_no = 0; ch_no < ch_count; ch_no++) {
+		int len = ntohl(ch->rc_target.rs_length);
 		rpl_map->sge[ch_no].iov_base = frmr->kva + offset;
-		rpl_map->sge[ch_no].iov_len = ch->rc_target.rs_length;
+		rpl_map->sge[ch_no].iov_len = len;
 		chl_map->ch[ch_no].count = 1;
 		chl_map->ch[ch_no].start = ch_no;
-		offset += ch->rc_target.rs_length;
+		offset += len;
 		ch++;
 	}
 
@@ -316,7 +317,7 @@
 	for (i = 0; i < count; i++) {
 		ctxt->sge[i].length = 0; /* in case map fails */
 		if (!frmr) {
-			BUG_ON(0 == virt_to_page(vec[i].iov_base));
+			BUG_ON(!virt_to_page(vec[i].iov_base));
 			off = (unsigned long)vec[i].iov_base & ~PAGE_MASK;
 			ctxt->sge[i].addr =
 				ib_dma_map_page(xprt->sc_cm_id->device,
@@ -426,6 +427,7 @@
 
 	for (ch = (struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0];
 	     ch->rc_discrim != 0; ch++, ch_no++) {
+		u64 rs_offset;
 next_sge:
 		ctxt = svc_rdma_get_context(xprt);
 		ctxt->direction = DMA_FROM_DEVICE;
@@ -440,10 +442,10 @@
 		read_wr.opcode = IB_WR_RDMA_READ;
 		ctxt->wr_op = read_wr.opcode;
 		read_wr.send_flags = IB_SEND_SIGNALED;
-		read_wr.wr.rdma.rkey = ch->rc_target.rs_handle;
-		read_wr.wr.rdma.remote_addr =
-			get_unaligned(&(ch->rc_target.rs_offset)) +
-			sgl_offset;
+		read_wr.wr.rdma.rkey = ntohl(ch->rc_target.rs_handle);
+		xdr_decode_hyper((__be32 *)&ch->rc_target.rs_offset,
+				 &rs_offset);
+		read_wr.wr.rdma.remote_addr = rs_offset + sgl_offset;
 		read_wr.sg_list = ctxt->sge;
 		read_wr.num_sge =
 			rdma_read_max_sge(xprt, chl_map->ch[ch_no].count);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index 249a835..42eb7ba 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -409,21 +409,21 @@
 		u64 rs_offset;
 
 		arg_ch = &arg_ary->wc_array[chunk_no].wc_target;
-		write_len = min(xfer_len, arg_ch->rs_length);
+		write_len = min(xfer_len, ntohl(arg_ch->rs_length));
 
 		/* Prepare the response chunk given the length actually
 		 * written */
-		rs_offset = get_unaligned(&(arg_ch->rs_offset));
+		xdr_decode_hyper((__be32 *)&arg_ch->rs_offset, &rs_offset);
 		svc_rdma_xdr_encode_array_chunk(res_ary, chunk_no,
-					    arg_ch->rs_handle,
-					    rs_offset,
-					    write_len);
+						arg_ch->rs_handle,
+						arg_ch->rs_offset,
+						write_len);
 		chunk_off = 0;
 		while (write_len) {
 			int this_write;
 			this_write = min(write_len, max_write);
 			ret = send_write(xprt, rqstp,
-					 arg_ch->rs_handle,
+					 ntohl(arg_ch->rs_handle),
 					 rs_offset + chunk_off,
 					 xdr_off,
 					 this_write,
@@ -457,6 +457,7 @@
 	u32 xdr_off;
 	int chunk_no;
 	int chunk_off;
+	int nchunks;
 	struct rpcrdma_segment *ch;
 	struct rpcrdma_write_array *arg_ary;
 	struct rpcrdma_write_array *res_ary;
@@ -476,26 +477,27 @@
 		max_write = xprt->sc_max_sge * PAGE_SIZE;
 
 	/* xdr offset starts at RPC message */
+	nchunks = ntohl(arg_ary->wc_nchunks);
 	for (xdr_off = 0, chunk_no = 0;
-	     xfer_len && chunk_no < arg_ary->wc_nchunks;
+	     xfer_len && chunk_no < nchunks;
 	     chunk_no++) {
 		u64 rs_offset;
 		ch = &arg_ary->wc_array[chunk_no].wc_target;
-		write_len = min(xfer_len, ch->rs_length);
+		write_len = min(xfer_len, htonl(ch->rs_length));
 
 		/* Prepare the reply chunk given the length actually
 		 * written */
-		rs_offset = get_unaligned(&(ch->rs_offset));
+		xdr_decode_hyper((__be32 *)&ch->rs_offset, &rs_offset);
 		svc_rdma_xdr_encode_array_chunk(res_ary, chunk_no,
-					    ch->rs_handle, rs_offset,
-					    write_len);
+						ch->rs_handle, ch->rs_offset,
+						write_len);
 		chunk_off = 0;
 		while (write_len) {
 			int this_write;
 
 			this_write = min(write_len, max_write);
 			ret = send_write(xprt, rqstp,
-					 ch->rs_handle,
+					 ntohl(ch->rs_handle),
 					 rs_offset + chunk_off,
 					 xdr_off,
 					 this_write,
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 894cb42..73b428b 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -51,6 +51,7 @@
 #include <rdma/rdma_cm.h>
 #include <linux/sunrpc/svc_rdma.h>
 #include <linux/export.h>
+#include "xprt_rdma.h"
 
 #define RPCDBG_FACILITY	RPCDBG_SVCXPRT
 
@@ -90,12 +91,6 @@
 	.xcl_max_payload = RPCSVC_MAXPAYLOAD_TCP,
 };
 
-/* WR context cache. Created in svc_rdma.c  */
-extern struct kmem_cache *svc_rdma_ctxt_cachep;
-
-/* Workqueue created in svc_rdma.c */
-extern struct workqueue_struct *svc_rdma_wq;
-
 struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *xprt)
 {
 	struct svc_rdma_op_ctxt *ctxt;
@@ -150,9 +145,6 @@
 	atomic_dec(&xprt->sc_ctxt_used);
 }
 
-/* Temporary NFS request map cache. Created in svc_rdma.c  */
-extern struct kmem_cache *svc_rdma_map_cachep;
-
 /*
  * Temporary NFS req mappings are shared across all transport
  * instances. These are short lived and should be bounded by the number
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index 08c5d5a..9a66c95 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -343,4 +343,11 @@
  */
 int rpcrdma_marshal_req(struct rpc_rqst *);
 
+/* Temporary NFS request map cache. Created in svc_rdma.c  */
+extern struct kmem_cache *svc_rdma_map_cachep;
+/* WR context cache. Created in svc_rdma.c  */
+extern struct kmem_cache *svc_rdma_ctxt_cachep;
+/* Workqueue created in svc_rdma.c */
+extern struct workqueue_struct *svc_rdma_wq;
+
 #endif				/* _LINUX_SUNRPC_XPRT_RDMA_H */
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 92bc518..890b03f 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -2475,6 +2475,7 @@
 static struct rpc_xprt_ops bc_tcp_ops = {
 	.reserve_xprt		= xprt_reserve_xprt,
 	.release_xprt		= xprt_release_xprt,
+	.rpcbind		= xs_local_rpcbind,
 	.buf_alloc		= bc_malloc,
 	.buf_free		= bc_free,
 	.send_request		= bc_send_request,
diff --git a/scripts/gcc-goto.sh b/scripts/gcc-goto.sh
index 98cffcb9..a2af2e8 100644
--- a/scripts/gcc-goto.sh
+++ b/scripts/gcc-goto.sh
@@ -2,4 +2,20 @@
 # Test for gcc 'asm goto' support
 # Copyright (C) 2010, Jason Baron <jbaron@redhat.com>
 
-echo "int main(void) { entry: asm goto (\"\"::::entry); return 0; }" | $@ -x c - -c -o /dev/null >/dev/null 2>&1 && echo "y"
+cat << "END" | $@ -x c - -c -o /dev/null >/dev/null 2>&1 && echo "y"
+int main(void)
+{
+#ifdef __arm__
+	/*
+	 * Not related to asm goto, but used by jump label
+	 * and broken on some ARM GCC versions (see GCC Bug 48637).
+	 */
+	static struct { int dummy; int state; } tp;
+	asm (".long %c0" :: "i" (&tp.state));
+#endif
+
+entry:
+	asm goto ("" :::: entry);
+	return 0;
+}
+END
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 3049299..15c6c56 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -2147,7 +2147,7 @@
 		fdt = files_fdtable(files);
 		if (i >= fdt->max_fds)
 			break;
-		set = fdt->open_fds->fds_bits[j];
+		set = fdt->open_fds[j];
 		if (!set)
 			continue;
 		spin_unlock(&files->file_lock);
diff --git a/sound/arm/pxa2xx-ac97-lib.c b/sound/arm/pxa2xx-ac97-lib.c
index d1aa421..48d7c0a 100644
--- a/sound/arm/pxa2xx-ac97-lib.c
+++ b/sound/arm/pxa2xx-ac97-lib.c
@@ -17,11 +17,12 @@
 #include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/module.h>
+#include <linux/io.h>
 
 #include <sound/ac97_codec.h>
 #include <sound/pxa2xx-lib.h>
 
-#include <asm/irq.h>
+#include <mach/irqs.h>
 #include <mach/regs-ac97.h>
 #include <mach/audio.h>
 
diff --git a/sound/arm/pxa2xx-ac97.c b/sound/arm/pxa2xx-ac97.c
index 3a39626..afef72c 100644
--- a/sound/arm/pxa2xx-ac97.c
+++ b/sound/arm/pxa2xx-ac97.c
@@ -11,6 +11,7 @@
  */
 
 #include <linux/init.h>
+#include <linux/io.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
 
diff --git a/sound/atmel/abdac.c b/sound/atmel/abdac.c
index 4fa1dbd..f7c2bb0 100644
--- a/sound/atmel/abdac.c
+++ b/sound/atmel/abdac.c
@@ -16,6 +16,7 @@
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/types.h>
 #include <linux/io.h>
 
 #include <sound/core.h>
@@ -467,15 +468,24 @@
 	snd_card_set_dev(card, &pdev->dev);
 
 	if (pdata->dws.dma_dev) {
-		struct dw_dma_slave *dws = &pdata->dws;
 		dma_cap_mask_t mask;
 
-		dws->tx_reg = regs->start + DAC_DATA;
-
 		dma_cap_zero(mask);
 		dma_cap_set(DMA_SLAVE, mask);
 
-		dac->dma.chan = dma_request_channel(mask, filter, dws);
+		dac->dma.chan = dma_request_channel(mask, filter, &pdata->dws);
+		if (dac->dma.chan) {
+			struct dma_slave_config dma_conf = {
+				.dst_addr = regs->start + DAC_DATA,
+				.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES,
+				.src_maxburst = 1,
+				.dst_maxburst = 1,
+				.direction = DMA_MEM_TO_DEV,
+				.device_fc = false,
+			};
+
+			dmaengine_slave_config(dac->dma.chan, &dma_conf);
+		}
 	}
 	if (!pdata->dws.dma_dev || !dac->dma.chan) {
 		dev_dbg(&pdev->dev, "DMA not available\n");
diff --git a/sound/atmel/ac97c.c b/sound/atmel/ac97c.c
index 61dade6..115313e 100644
--- a/sound/atmel/ac97c.c
+++ b/sound/atmel/ac97c.c
@@ -20,6 +20,7 @@
 #include <linux/platform_device.h>
 #include <linux/mutex.h>
 #include <linux/gpio.h>
+#include <linux/types.h>
 #include <linux/io.h>
 
 #include <sound/core.h>
@@ -1014,16 +1015,28 @@
 
 	if (cpu_is_at32ap7000()) {
 		if (pdata->rx_dws.dma_dev) {
-			struct dw_dma_slave *dws = &pdata->rx_dws;
 			dma_cap_mask_t mask;
 
-			dws->rx_reg = regs->start + AC97C_CARHR + 2;
-
 			dma_cap_zero(mask);
 			dma_cap_set(DMA_SLAVE, mask);
 
 			chip->dma.rx_chan = dma_request_channel(mask, filter,
-								dws);
+								&pdata->rx_dws);
+			if (chip->dma.rx_chan) {
+				struct dma_slave_config dma_conf = {
+					.src_addr = regs->start + AC97C_CARHR +
+						2,
+					.src_addr_width =
+						DMA_SLAVE_BUSWIDTH_2_BYTES,
+					.src_maxburst = 1,
+					.dst_maxburst = 1,
+					.direction = DMA_DEV_TO_MEM,
+					.device_fc = false,
+				};
+
+				dmaengine_slave_config(chip->dma.rx_chan,
+						&dma_conf);
+			}
 
 			dev_info(&chip->pdev->dev, "using %s for DMA RX\n",
 				dev_name(&chip->dma.rx_chan->dev->device));
@@ -1031,16 +1044,28 @@
 		}
 
 		if (pdata->tx_dws.dma_dev) {
-			struct dw_dma_slave *dws = &pdata->tx_dws;
 			dma_cap_mask_t mask;
 
-			dws->tx_reg = regs->start + AC97C_CATHR + 2;
-
 			dma_cap_zero(mask);
 			dma_cap_set(DMA_SLAVE, mask);
 
 			chip->dma.tx_chan = dma_request_channel(mask, filter,
-								dws);
+								&pdata->tx_dws);
+			if (chip->dma.tx_chan) {
+				struct dma_slave_config dma_conf = {
+					.dst_addr = regs->start + AC97C_CATHR +
+						2,
+					.dst_addr_width =
+						DMA_SLAVE_BUSWIDTH_2_BYTES,
+					.src_maxburst = 1,
+					.dst_maxburst = 1,
+					.direction = DMA_MEM_TO_DEV,
+					.device_fc = false,
+				};
+
+				dmaengine_slave_config(chip->dma.tx_chan,
+						&dma_conf);
+			}
 
 			dev_info(&chip->pdev->dev, "using %s for DMA TX\n",
 				dev_name(&chip->dma.tx_chan->dev->device));
diff --git a/sound/soc/imx/imx-pcm-dma-mx2.c b/sound/soc/imx/imx-pcm-dma-mx2.c
index e43c8fa..6b818de 100644
--- a/sound/soc/imx/imx-pcm-dma-mx2.c
+++ b/sound/soc/imx/imx-pcm-dma-mx2.c
@@ -21,6 +21,7 @@
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/dmaengine.h>
+#include <linux/types.h>
 
 #include <sound/core.h>
 #include <sound/initval.h>
@@ -58,6 +59,8 @@
 	if (ret)
 		return ret;
 
+	slave_config.device_fc = false;
+
 	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
 		slave_config.dst_addr = dma_params->dma_addr;
 		slave_config.dst_maxburst = dma_params->burstsize;
diff --git a/sound/soc/pxa/pxa2xx-ac97.c b/sound/soc/pxa/pxa2xx-ac97.c
index 4800d5f..06ea274 100644
--- a/sound/soc/pxa/pxa2xx-ac97.c
+++ b/sound/soc/pxa/pxa2xx-ac97.c
@@ -11,6 +11,7 @@
  */
 
 #include <linux/init.h>
+#include <linux/io.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
 
diff --git a/sound/soc/sh/siu_pcm.c b/sound/soc/sh/siu_pcm.c
index 0193e59..5cfcc65 100644
--- a/sound/soc/sh/siu_pcm.c
+++ b/sound/soc/sh/siu_pcm.c
@@ -130,7 +130,7 @@
 	sg_dma_len(&sg) = size;
 	sg_dma_address(&sg) = buff;
 
-	desc = siu_stream->chan->device->device_prep_slave_sg(siu_stream->chan,
+	desc = dmaengine_prep_slave_sg(siu_stream->chan,
 		&sg, 1, DMA_MEM_TO_DEV, DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	if (!desc) {
 		dev_err(dev, "Failed to allocate a dma descriptor\n");
@@ -180,7 +180,7 @@
 	sg_dma_len(&sg) = size;
 	sg_dma_address(&sg) = buff;
 
-	desc = siu_stream->chan->device->device_prep_slave_sg(siu_stream->chan,
+	desc = dmaengine_prep_slave_sg(siu_stream->chan,
 		&sg, 1, DMA_DEV_TO_MEM, DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	if (!desc) {
 		dev_err(dev, "Failed to allocate dma descriptor\n");
diff --git a/sound/soc/txx9/txx9aclc.c b/sound/soc/txx9/txx9aclc.c
index 2155461..b609d2c 100644
--- a/sound/soc/txx9/txx9aclc.c
+++ b/sound/soc/txx9/txx9aclc.c
@@ -132,7 +132,7 @@
 	sg_set_page(&sg, pfn_to_page(PFN_DOWN(buf_dma_addr)),
 		    dmadata->frag_bytes, buf_dma_addr & (PAGE_SIZE - 1));
 	sg_dma_address(&sg) = buf_dma_addr;
-	desc = chan->device->device_prep_slave_sg(chan, &sg, 1,
+	desc = dmaengine_prep_slave_sg(chan, &sg, 1,
 		dmadata->substream->stream == SNDRV_PCM_STREAM_PLAYBACK ?
 		DMA_MEM_TO_DEV : DMA_DEV_TO_MEM,
 		DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
diff --git a/tools/power/cpupower/Makefile b/tools/power/cpupower/Makefile
index e8a03ac..a93e06c 100644
--- a/tools/power/cpupower/Makefile
+++ b/tools/power/cpupower/Makefile
@@ -19,6 +19,16 @@
 # along with this program; if not, write to the Free Software
 # Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
 #
+OUTPUT=./
+ifeq ("$(origin O)", "command line")
+	OUTPUT := $(O)/
+endif
+
+ifneq ($(OUTPUT),)
+# check that the output directory actually exists
+OUTDIR := $(shell cd $(OUTPUT) && /bin/pwd)
+$(if $(OUTDIR),, $(error output directory "$(OUTPUT)" does not exist))
+endif
 
 # --- CONFIGURATION BEGIN ---
 
@@ -87,6 +97,7 @@
 STRIP = $(CROSS)strip
 RANLIB = $(CROSS)ranlib
 HOSTCC = gcc
+MKDIR = mkdir
 
 
 # Now we set up the build system
@@ -95,7 +106,7 @@
 # set up PWD so that older versions of make will work with our build.
 PWD = $(shell pwd)
 
-GMO_FILES = ${shell for HLANG in ${LANGUAGES}; do echo po/$$HLANG.gmo; done;}
+GMO_FILES = ${shell for HLANG in ${LANGUAGES}; do echo $(OUTPUT)po/$$HLANG.gmo; done;}
 
 export CROSS CC AR STRIP RANLIB CFLAGS LDFLAGS LIB_OBJS
 
@@ -122,15 +133,18 @@
 	utils/cpupower.o utils/cpufreq-info.o utils/cpufreq-set.o \
 	utils/cpupower-set.o utils/cpupower-info.o utils/cpuidle-info.o
 
+UTIL_SRC := $(UTIL_OBJS:.o=.c)
+
+UTIL_OBJS := $(addprefix $(OUTPUT),$(UTIL_OBJS))
+
 UTIL_HEADERS = utils/helpers/helpers.h utils/idle_monitor/cpupower-monitor.h \
 	utils/helpers/bitmask.h \
 	utils/idle_monitor/idle_monitors.h utils/idle_monitor/idle_monitors.def
 
-UTIL_SRC := $(UTIL_OBJS:.o=.c)
-
 LIB_HEADERS = 	lib/cpufreq.h lib/sysfs.h
 LIB_SRC = 	lib/cpufreq.c lib/sysfs.c
 LIB_OBJS = 	lib/cpufreq.o lib/sysfs.o
+LIB_OBJS :=	$(addprefix $(OUTPUT),$(LIB_OBJS))
 
 CFLAGS +=	-pipe
 
@@ -168,83 +182,90 @@
 
 # the actual make rules
 
-all: libcpupower cpupower $(COMPILE_NLS) $(COMPILE_BENCH)
+all: libcpupower $(OUTPUT)cpupower $(COMPILE_NLS) $(COMPILE_BENCH)
 
-lib/%.o: $(LIB_SRC) $(LIB_HEADERS)
+$(OUTPUT)lib/%.o: $(LIB_SRC) $(LIB_HEADERS)
 	$(ECHO) "  CC      " $@
 	$(QUIET) $(CC) $(CFLAGS) -fPIC -o $@ -c lib/$*.c
 
-libcpupower.so.$(LIB_MAJ): $(LIB_OBJS)
+$(OUTPUT)libcpupower.so.$(LIB_MAJ): $(LIB_OBJS)
 	$(ECHO) "  LD      " $@
 	$(QUIET) $(CC) -shared $(CFLAGS) $(LDFLAGS) -o $@ \
 		-Wl,-soname,libcpupower.so.$(LIB_MIN) $(LIB_OBJS)
-	@ln -sf $@ libcpupower.so
-	@ln -sf $@ libcpupower.so.$(LIB_MIN)
+	@ln -sf $(@F) $(OUTPUT)libcpupower.so
+	@ln -sf $(@F) $(OUTPUT)libcpupower.so.$(LIB_MIN)
 
-libcpupower: libcpupower.so.$(LIB_MAJ)
+libcpupower: $(OUTPUT)libcpupower.so.$(LIB_MAJ)
 
 # Let all .o files depend on its .c file and all headers
 # Might be worth to put this into utils/Makefile at some point of time
 $(UTIL_OBJS): $(UTIL_HEADERS)
 
-.c.o:
+$(OUTPUT)%.o: %.c
 	$(ECHO) "  CC      " $@
 	$(QUIET) $(CC) $(CFLAGS) -I./lib -I ./utils -o $@ -c $*.c
 
-cpupower: $(UTIL_OBJS) libcpupower.so.$(LIB_MAJ)
+$(OUTPUT)cpupower: $(UTIL_OBJS) $(OUTPUT)libcpupower.so.$(LIB_MAJ)
 	$(ECHO) "  CC      " $@
-	$(QUIET) $(CC) $(CFLAGS) $(LDFLAGS) -lcpupower -lrt -lpci -L. -o $@ $(UTIL_OBJS)
+	$(QUIET) $(CC) $(CFLAGS) $(LDFLAGS) $(UTIL_OBJS) -lcpupower -lrt -lpci -L$(OUTPUT) -o $@
 	$(QUIET) $(STRIPCMD) $@
 
-po/$(PACKAGE).pot: $(UTIL_SRC)
+$(OUTPUT)po/$(PACKAGE).pot: $(UTIL_SRC)
 	$(ECHO) "  GETTEXT " $@
 	$(QUIET) xgettext --default-domain=$(PACKAGE) --add-comments \
-		--keyword=_ --keyword=N_ $(UTIL_SRC) && \
-	test -f $(PACKAGE).po && \
-	mv -f $(PACKAGE).po po/$(PACKAGE).pot
+		--keyword=_ --keyword=N_ $(UTIL_SRC) -p $(@D) -o $(@F)
 
-po/%.gmo: po/%.po
+$(OUTPUT)po/%.gmo: po/%.po
 	$(ECHO) "  MSGFMT  " $@
 	$(QUIET) msgfmt -o $@ po/$*.po
 
 create-gmo: ${GMO_FILES}
 
-update-po: po/$(PACKAGE).pot
+update-po: $(OUTPUT)po/$(PACKAGE).pot
 	$(ECHO) "  MSGMRG  " $@
 	$(QUIET) @for HLANG in $(LANGUAGES); do \
 		echo -n "Updating $$HLANG "; \
-		if msgmerge po/$$HLANG.po po/$(PACKAGE).pot -o \
-		   po/$$HLANG.new.po; then \
-			mv -f po/$$HLANG.new.po po/$$HLANG.po; \
+		if msgmerge po/$$HLANG.po $< -o \
+		   $(OUTPUT)po/$$HLANG.new.po; then \
+			mv -f $(OUTPUT)po/$$HLANG.new.po $(OUTPUT)po/$$HLANG.po; \
 		else \
 			echo "msgmerge for $$HLANG failed!"; \
-			rm -f po/$$HLANG.new.po; \
+			rm -f $(OUTPUT)po/$$HLANG.new.po; \
 		fi; \
 	done;
 
-compile-bench: libcpupower.so.$(LIB_MAJ)
-	@V=$(V) confdir=$(confdir) $(MAKE) -C bench
+compile-bench: $(OUTPUT)libcpupower.so.$(LIB_MAJ)
+	@V=$(V) confdir=$(confdir) $(MAKE) -C bench O=$(OUTPUT)
+
+# we compile into subdirectories. if the target directory is not the
+# source directory, they might not exists. So we depend the various
+# files onto their directories.
+DIRECTORY_DEPS = $(LIB_OBJS) $(UTIL_OBJS) $(GMO_FILES)
+$(DIRECTORY_DEPS): | $(sort $(dir $(DIRECTORY_DEPS)))
+
+# In the second step, we make a rule to actually create these directories
+$(sort $(dir $(DIRECTORY_DEPS))):
+	$(ECHO) "  MKDIR      " $@
+	$(QUIET) $(MKDIR) -p $@ 2>/dev/null
 
 clean:
-	-find . \( -not -type d \) -and \( -name '*~' -o -name '*.[oas]' \) -type f -print \
+	-find $(OUTPUT) \( -not -type d \) -and \( -name '*~' -o -name '*.[oas]' \) -type f -print \
 	 | xargs rm -f
-	-rm -f $(UTIL_BINS)
-	-rm -f $(IDLE_OBJS)
-	-rm -f cpupower
-	-rm -f libcpupower.so*
-	-rm -rf po/*.gmo po/*.pot
-	$(MAKE) -C bench clean
+	-rm -f $(OUTPUT)cpupower
+	-rm -f $(OUTPUT)libcpupower.so*
+	-rm -rf $(OUTPUT)po/*.{gmo,pot}
+	$(MAKE) -C bench O=$(OUTPUT) clean
 
 
 install-lib:
 	$(INSTALL) -d $(DESTDIR)${libdir}
-	$(CP) libcpupower.so* $(DESTDIR)${libdir}/
+	$(CP) $(OUTPUT)libcpupower.so* $(DESTDIR)${libdir}/
 	$(INSTALL) -d $(DESTDIR)${includedir}
 	$(INSTALL_DATA) lib/cpufreq.h $(DESTDIR)${includedir}/cpufreq.h
 
 install-tools:
 	$(INSTALL) -d $(DESTDIR)${bindir}
-	$(INSTALL_PROGRAM) cpupower $(DESTDIR)${bindir}
+	$(INSTALL_PROGRAM) $(OUTPUT)cpupower $(DESTDIR)${bindir}
 
 install-man:
 	$(INSTALL_DATA) -D man/cpupower.1 $(DESTDIR)${mandir}/man1/cpupower.1
@@ -257,13 +278,13 @@
 install-gmo:
 	$(INSTALL) -d $(DESTDIR)${localedir}
 	for HLANG in $(LANGUAGES); do \
-		echo '$(INSTALL_DATA) -D po/$$HLANG.gmo $(DESTDIR)${localedir}/$$HLANG/LC_MESSAGES/cpupower.mo'; \
-		$(INSTALL_DATA) -D po/$$HLANG.gmo $(DESTDIR)${localedir}/$$HLANG/LC_MESSAGES/cpupower.mo; \
+		echo '$(INSTALL_DATA) -D $(OUTPUT)po/$$HLANG.gmo $(DESTDIR)${localedir}/$$HLANG/LC_MESSAGES/cpupower.mo'; \
+		$(INSTALL_DATA) -D $(OUTPUT)po/$$HLANG.gmo $(DESTDIR)${localedir}/$$HLANG/LC_MESSAGES/cpupower.mo; \
 	done;
 
 install-bench:
 	@#DESTDIR must be set from outside to survive
-	@sbindir=$(sbindir) bindir=$(bindir) docdir=$(docdir) confdir=$(confdir) $(MAKE) -C bench install
+	@sbindir=$(sbindir) bindir=$(bindir) docdir=$(docdir) confdir=$(confdir) $(MAKE) -C bench O=$(OUTPUT) install
 
 install: all install-lib install-tools install-man $(INSTALL_NLS) $(INSTALL_BENCH)
 
diff --git a/tools/power/cpupower/bench/Makefile b/tools/power/cpupower/bench/Makefile
index 2b67606..7ec7021 100644
--- a/tools/power/cpupower/bench/Makefile
+++ b/tools/power/cpupower/bench/Makefile
@@ -1,29 +1,36 @@
-LIBS = -L../ -lm -lcpupower
+OUTPUT := ./
+ifeq ("$(origin O)", "command line")
+ifneq ($(O),)
+	OUTPUT := $(O)/
+endif
+endif
 
-OBJS = main.o parse.o system.o benchmark.o
+LIBS = -L../ -L$(OUTPUT) -lm -lcpupower
+
+OBJS = $(OUTPUT)main.o $(OUTPUT)parse.o $(OUTPUT)system.o $(OUTPUT)benchmark.o
 CFLAGS += -D_GNU_SOURCE -I../lib -DDEFAULT_CONFIG_FILE=\"$(confdir)/cpufreq-bench.conf\"
 
-%.o : %.c
+$(OUTPUT)%.o : %.c
 	$(ECHO) "  CC      " $@
 	$(QUIET) $(CC) -c $(CFLAGS) $< -o $@
 
-cpufreq-bench: $(OBJS)
+$(OUTPUT)cpufreq-bench: $(OBJS)
 	$(ECHO) "  CC      " $@
 	$(QUIET) $(CC) -o $@ $(CFLAGS) $(OBJS) $(LIBS)
 
-all: cpufreq-bench
+all: $(OUTPUT)cpufreq-bench
 
 install:
 	mkdir -p $(DESTDIR)/$(sbindir)
 	mkdir -p $(DESTDIR)/$(bindir)
 	mkdir -p $(DESTDIR)/$(docdir)
 	mkdir -p $(DESTDIR)/$(confdir)
-	install -m 755 cpufreq-bench $(DESTDIR)/$(sbindir)/cpufreq-bench
+	install -m 755 $(OUTPUT)cpufreq-bench $(DESTDIR)/$(sbindir)/cpufreq-bench
 	install -m 755 cpufreq-bench_plot.sh $(DESTDIR)/$(bindir)/cpufreq-bench_plot.sh
 	install -m 644 README-BENCH $(DESTDIR)/$(docdir)/README-BENCH
 	install -m 755 cpufreq-bench_script.sh $(DESTDIR)/$(docdir)/cpufreq-bench_script.sh
 	install -m 644 example.cfg $(DESTDIR)/$(confdir)/cpufreq-bench.conf
 
 clean:
-	rm -f *.o
-	rm -f cpufreq-bench
+	rm -f $(OUTPUT)*.o
+	rm -f $(OUTPUT)cpufreq-bench
diff --git a/tools/power/cpupower/debug/i386/Makefile b/tools/power/cpupower/debug/i386/Makefile
index d08cc1e..3ba158f 100644
--- a/tools/power/cpupower/debug/i386/Makefile
+++ b/tools/power/cpupower/debug/i386/Makefile
@@ -1,20 +1,38 @@
+OUTPUT=./
+ifeq ("$(origin O)", "command line")
+	OUTPUT := $(O)/
+endif
+
+DESTDIR =
+bindir  = /usr/bin
+
+INSTALL = /usr/bin/install
+
+
 default: all
 
-centrino-decode: centrino-decode.c
-	$(CC) $(CFLAGS) -o centrino-decode centrino-decode.c
+$(OUTPUT)centrino-decode: centrino-decode.c
+	$(CC) $(CFLAGS) -o $@ centrino-decode.c
 
-dump_psb: dump_psb.c
-	$(CC) $(CFLAGS) -o dump_psb dump_psb.c
+$(OUTPUT)dump_psb: dump_psb.c
+	$(CC) $(CFLAGS) -o $@ dump_psb.c
 
-intel_gsic: intel_gsic.c
-	$(CC) $(CFLAGS) -o intel_gsic -llrmi intel_gsic.c
+$(OUTPUT)intel_gsic: intel_gsic.c
+	$(CC) $(CFLAGS) -o $@ -llrmi intel_gsic.c
 
-powernow-k8-decode: powernow-k8-decode.c
-	$(CC) $(CFLAGS) -o powernow-k8-decode powernow-k8-decode.c
+$(OUTPUT)powernow-k8-decode: powernow-k8-decode.c
+	$(CC) $(CFLAGS) -o $@ powernow-k8-decode.c
 
-all: centrino-decode dump_psb intel_gsic powernow-k8-decode
+all: $(OUTPUT)centrino-decode $(OUTPUT)dump_psb $(OUTPUT)intel_gsic $(OUTPUT)powernow-k8-decode
 
 clean:
-	rm -rf centrino-decode dump_psb intel_gsic powernow-k8-decode
+	rm -rf $(OUTPUT){centrino-decode,dump_psb,intel_gsic,powernow-k8-decode}
 
-.PHONY: all default clean
+install:
+	$(INSTALL) -d $(DESTDIR)${bindir}
+	$(INSTALL) $(OUTPUT)centrino-decode $(DESTDIR)${bindir}
+	$(INSTALL) $(OUTPUT)powernow-k8-decode $(DESTDIR)${bindir}
+	$(INSTALL) $(OUTPUT)dump_psb $(DESTDIR)${bindir}
+	$(INSTALL) $(OUTPUT)intel_gsic $(DESTDIR)${bindir}
+
+.PHONY: all default clean install
diff --git a/tools/power/cpupower/debug/x86_64/Makefile b/tools/power/cpupower/debug/x86_64/Makefile
index 3326217..1c52145 100644
--- a/tools/power/cpupower/debug/x86_64/Makefile
+++ b/tools/power/cpupower/debug/x86_64/Makefile
@@ -1,14 +1,30 @@
+OUTPUT=./
+ifeq ("$(origin O)", "command line")
+	OUTPUT := $(O)/
+endif
+
+DESTDIR =
+bindir  = /usr/bin
+
+INSTALL = /usr/bin/install
+
+
 default: all
 
-centrino-decode: ../i386/centrino-decode.c
+$(OUTPUT)centrino-decode: ../i386/centrino-decode.c
 	$(CC) $(CFLAGS) -o $@ $<
 
-powernow-k8-decode: ../i386/powernow-k8-decode.c
+$(OUTPUT)powernow-k8-decode: ../i386/powernow-k8-decode.c
 	$(CC) $(CFLAGS) -o $@ $<
 
-all: centrino-decode powernow-k8-decode
+all: $(OUTPUT)centrino-decode $(OUTPUT)powernow-k8-decode
 
 clean:
-	rm -rf centrino-decode powernow-k8-decode
+	rm -rf $(OUTPUT)centrino-decode $(OUTPUT)powernow-k8-decode
 
-.PHONY: all default clean
+install:
+	$(INSTALL) -d $(DESTDIR)${bindir}
+	$(INSTALL) $(OUTPUT)centrino-decode $(DESTDIR)${bindir}
+	$(INSTALL) $(OUTPUT)powernow-k8-decode $(DESTDIR)${bindir}
+
+.PHONY: all default clean install
diff --git a/tools/power/cpupower/man/cpupower-frequency-info.1 b/tools/power/cpupower/man/cpupower-frequency-info.1
index bb60a8d..4a1918e 100644
--- a/tools/power/cpupower/man/cpupower-frequency-info.1
+++ b/tools/power/cpupower/man/cpupower-frequency-info.1
@@ -1,4 +1,4 @@
-.TH "cpupower-frequency-info" "1" "0.1" "Mattia Dongili" ""
+.TH "CPUPOWER\-FREQUENCY\-INFO" "1" "0.1" "" "cpupower Manual"
 .SH "NAME"
 .LP 
 cpupower frequency\-info \- Utility to retrieve cpufreq kernel information
@@ -50,8 +50,6 @@
 \fB\-m\fR \fB\-\-human\fR
 human\-readable output for the \-f, \-w, \-s and \-y parameters.
 .TP  
-\fB\-h\fR \fB\-\-help\fR
-Prints out the help screen.
 .SH "REMARKS"
 .LP 
 By default only values of core zero are displayed. How to display settings of
diff --git a/tools/power/cpupower/man/cpupower-frequency-set.1 b/tools/power/cpupower/man/cpupower-frequency-set.1
index 685f469..3eacc8d 100644
--- a/tools/power/cpupower/man/cpupower-frequency-set.1
+++ b/tools/power/cpupower/man/cpupower-frequency-set.1
@@ -1,4 +1,4 @@
-.TH "cpupower-freqency-set" "1" "0.1" "Mattia Dongili" ""
+.TH "CPUPOWER\-FREQUENCY\-SET" "1" "0.1" "" "cpupower Manual"
 .SH "NAME"
 .LP 
 cpupower frequency\-set \- A small tool which allows to modify cpufreq settings.
@@ -26,8 +26,6 @@
 \fB\-r\fR \fB\-\-related\fR
 modify all hardware-related CPUs at the same time
 .TP 
-\fB\-h\fR \fB\-\-help\fR
-Prints out the help screen.
 .SH "REMARKS"
 .LP 
 By default values are applied on all cores. How to modify single core
diff --git a/tools/power/cpupower/man/cpupower-idle-info.1 b/tools/power/cpupower/man/cpupower-idle-info.1
new file mode 100644
index 0000000..4178eff
--- /dev/null
+++ b/tools/power/cpupower/man/cpupower-idle-info.1
@@ -0,0 +1,90 @@
+.TH "CPUPOWER-IDLE-INFO" "1" "0.1" "" "cpupower Manual"
+.SH "NAME"
+.LP
+cpupower idle\-info \- Utility to retrieve cpu idle kernel information
+.SH "SYNTAX"
+.LP
+cpupower [ \-c cpulist ] idle\-info [\fIoptions\fP]
+.SH "DESCRIPTION"
+.LP
+A tool which prints out per cpu idle information helpful to developers and interested users.
+.SH "OPTIONS"
+.LP
+.TP
+\fB\-f\fR \fB\-\-silent\fR
+Only print a summary of all available C-states in the system.
+.TP
+\fB\-e\fR \fB\-\-proc\fR
+deprecated.
+Prints out idle information in old /proc/acpi/processor/*/power format. This
+interface has been removed from the kernel for quite some time, do not let
+further code depend on this option, best do not use it.
+
+.SH IDLE\-INFO DESCRIPTIONS
+CPU sleep state statistics and descriptions are retrieved from sysfs files,
+exported by the cpuidle kernel subsystem. The kernel only updates these
+statistics when it enters or leaves an idle state, therefore on a very idle or
+a very busy system, these statistics may not be accurate. They still provide a
+good overview about the usage and availability of processor sleep states on
+the platform.
+
+Be aware that the sleep states as exported by the hardware or BIOS and used by
+the Linux kernel may not exactly reflect the capabilities of the
+processor. This often is the case on the X86 architecture when the acpi_idle
+driver is used. It is also possible that the hardware overrules the kernel
+requests, due to internal activity monitors or other reasons.
+On recent X86 platforms it is often possible to read out hardware registers
+which monitor the duration of sleep states the processor resided in. The
+cpupower monitor tool (cpupower\-monitor(1)) can be used to show real sleep
+state residencies. Please refer to the architecture specific description
+section below.
+
+.SH IDLE\-INFO ARCHITECTURE SPECIFIC DESCRIPTIONS
+.SS "X86"
+POLL idle state
+
+If cpuidle is active, X86 platforms have one special idle state.
+The POLL idle state is not a real idle state, it does not save any
+power. Instead, a busy\-loop is executed doing nothing for a short period of
+time. This state is used if the kernel knows that work has to be processed
+very soon and entering any real hardware idle state may result in a slight
+performance penalty.
+
+There exist two different cpuidle drivers on the X86 architecture platform:
+
+"acpi_idle" cpuidle driver
+
+The acpi_idle cpuidle driver retrieves available sleep states (C\-states) from
+the ACPI BIOS tables (from the _CST ACPI function on recent platforms or from
+the FADT BIOS table on older ones).
+The C1 state is not retrieved from ACPI tables. If the C1 state is entered,
+the kernel will call the hlt instruction (or mwait on Intel).
+
+"intel_idle" cpuidle driver
+
+In kernel 2.6.36 the intel_idle driver was introduced.
+It only serves recent Intel CPUs (Nehalem, Westmere, Sandybridge, Atoms or
+newer). On older Intel CPUs the acpi_idle driver is still used (if the BIOS
+provides C\-state ACPI tables).
+The intel_idle driver knows the sleep state capabilities of the processor and
+ignores ACPI BIOS exported processor sleep states tables.
+
+.SH "REMARKS"
+.LP
+By default only values of core zero are displayed. How to display settings of
+other cores is described in the cpupower(1) manpage in the \-\-cpu option
+section.
+.SH REFERENCES
+http://www.acpi.info/spec.htm
+.SH "FILES"
+.nf
+\fI/sys/devices/system/cpu/cpu*/cpuidle/state*\fP
+\fI/sys/devices/system/cpu/cpuidle/*\fP
+.fi
+.SH "AUTHORS"
+.nf
+Thomas Renninger <trenn@suse.de>
+.fi
+.SH "SEE ALSO"
+.LP
+cpupower(1), cpupower\-monitor(1), cpupower\-info(1), cpupower\-set(1)
diff --git a/tools/power/cpupower/man/cpupower-monitor.1 b/tools/power/cpupower/man/cpupower-monitor.1
index d5cfa26..1141c20 100644
--- a/tools/power/cpupower/man/cpupower-monitor.1
+++ b/tools/power/cpupower/man/cpupower-monitor.1
@@ -107,7 +107,7 @@
 sleep states and can only be entered if all cores are idle. Look up Intel
 manuals (some are provided in the References section) for further details.
 
-.SS "Ontario" "Liano"
+.SS "Fam_12h" "Fam_14h"
 AMD laptop and desktop processor (family 12h and 14h) sleep state counters.
 The registers are accessed via PCI and therefore can still be read out while
 cores have been offlined.
diff --git a/tools/power/cpupower/utils/cpuidle-info.c b/tools/power/cpupower/utils/cpuidle-info.c
index b028267..8145af5 100644
--- a/tools/power/cpupower/utils/cpuidle-info.c
+++ b/tools/power/cpupower/utils/cpuidle-info.c
@@ -35,17 +35,9 @@
 		printf(_("CPU %u: Can't read idle state info\n"), cpu);
 		return;
 	}
-	tmp = sysfs_get_idlestate_name(cpu, idlestates - 1);
-	if (!tmp) {
-		printf(_("Could not determine max idle state %u\n"),
-		       idlestates - 1);
-		return;
-	}
-
 	printf(_("Number of idle states: %d\n"), idlestates);
-
 	printf(_("Available idle states:"));
-	for (idlestate = 1; idlestate < idlestates; idlestate++) {
+	for (idlestate = 0; idlestate < idlestates; idlestate++) {
 		tmp = sysfs_get_idlestate_name(cpu, idlestate);
 		if (!tmp)
 			continue;
@@ -57,7 +49,7 @@
 	if (!verbose)
 		return;
 
-	for (idlestate = 1; idlestate < idlestates; idlestate++) {
+	for (idlestate = 0; idlestate < idlestates; idlestate++) {
 		tmp = sysfs_get_idlestate_name(cpu, idlestate);
 		if (!tmp)
 			continue;
diff --git a/tools/power/cpupower/utils/helpers/amd.c b/tools/power/cpupower/utils/helpers/amd.c
index 87d5605..6437ef3 100644
--- a/tools/power/cpupower/utils/helpers/amd.c
+++ b/tools/power/cpupower/utils/helpers/amd.c
@@ -112,14 +112,12 @@
 int amd_pci_get_num_boost_states(int *active, int *states)
 {
 	struct pci_access *pci_acc;
-	int vendor_id = 0x1022;
-	int boost_dev_ids[4] = {0x1204, 0x1604, 0x1704, 0};
 	struct pci_dev *device;
 	uint8_t val = 0;
 
 	*active = *states = 0;
 
-	device = pci_acc_init(&pci_acc, vendor_id, boost_dev_ids);
+	device = pci_slot_func_init(&pci_acc, 0x18, 4);
 
 	if (device == NULL)
 		return -ENODEV;
diff --git a/tools/power/cpupower/utils/helpers/helpers.h b/tools/power/cpupower/utils/helpers/helpers.h
index 2747e73..2eb584c 100644
--- a/tools/power/cpupower/utils/helpers/helpers.h
+++ b/tools/power/cpupower/utils/helpers/helpers.h
@@ -66,8 +66,8 @@
 #define CPUPOWER_CAP_AMD_CBP		0x00000004
 #define CPUPOWER_CAP_PERF_BIAS		0x00000008
 #define CPUPOWER_CAP_HAS_TURBO_RATIO	0x00000010
-#define CPUPOWER_CAP_IS_SNB		0x00000011
-#define CPUPOWER_CAP_INTEL_IDA		0x00000012
+#define CPUPOWER_CAP_IS_SNB		0x00000020
+#define CPUPOWER_CAP_INTEL_IDA		0x00000040
 
 #define MAX_HW_PSTATES 10
 
@@ -132,8 +132,11 @@
 
 /* PCI stuff ****************************/
 extern int amd_pci_get_num_boost_states(int *active, int *states);
-extern struct pci_dev *pci_acc_init(struct pci_access **pacc, int vendor_id,
-				    int *dev_ids);
+extern struct pci_dev *pci_acc_init(struct pci_access **pacc, int domain,
+				    int bus, int slot, int func, int vendor,
+				    int dev);
+extern struct pci_dev *pci_slot_func_init(struct pci_access **pacc,
+					      int slot, int func);
 
 /* PCI stuff ****************************/
 
diff --git a/tools/power/cpupower/utils/helpers/pci.c b/tools/power/cpupower/utils/helpers/pci.c
index cd2eb6f..9690798 100644
--- a/tools/power/cpupower/utils/helpers/pci.c
+++ b/tools/power/cpupower/utils/helpers/pci.c
@@ -10,19 +10,24 @@
  * **pacc : if a valid pci_dev is returned
  *         *pacc must be passed to pci_acc_cleanup to free it
  *
- * vendor_id : the pci vendor id matching the pci device to access
- * dev_ids :   device ids matching the pci device to access
+ * domain: domain
+ * bus:    bus
+ * slot:   slot
+ * func:   func
+ * vendor: vendor
+ * device: device
+ * Pass -1 for one of the six above to match any
  *
  * Returns :
  * struct pci_dev which can be used with pci_{read,write}_* functions
  *                to access the PCI config space of matching pci devices
  */
-struct pci_dev *pci_acc_init(struct pci_access **pacc, int vendor_id,
-				    int *dev_ids)
+struct pci_dev *pci_acc_init(struct pci_access **pacc, int domain, int bus,
+			     int slot, int func, int vendor, int dev)
 {
-	struct pci_filter filter_nb_link = { -1, -1, -1, -1, vendor_id, 0};
+	struct pci_filter filter_nb_link = { domain, bus, slot, func,
+					     vendor, dev };
 	struct pci_dev *device;
-	unsigned int i;
 
 	*pacc = pci_alloc();
 	if (*pacc == NULL)
@@ -31,14 +36,20 @@
 	pci_init(*pacc);
 	pci_scan_bus(*pacc);
 
-	for (i = 0; dev_ids[i] != 0; i++) {
-		filter_nb_link.device = dev_ids[i];
-		for (device = (*pacc)->devices; device; device = device->next) {
-			if (pci_filter_match(&filter_nb_link, device))
-				return device;
-		}
+	for (device = (*pacc)->devices; device; device = device->next) {
+		if (pci_filter_match(&filter_nb_link, device))
+			return device;
 	}
 	pci_cleanup(*pacc);
 	return NULL;
 }
+
+/* Typically one wants to get a specific slot(device)/func of the root domain
+   and bus */
+struct pci_dev *pci_slot_func_init(struct pci_access **pacc, int slot,
+				       int func)
+{
+	return pci_acc_init(pacc, 0, 0, slot, func, -1, -1);
+}
+
 #endif /* defined(__i386__) || defined(__x86_64__) */
diff --git a/tools/power/cpupower/utils/idle_monitor/amd_fam14h_idle.c b/tools/power/cpupower/utils/idle_monitor/amd_fam14h_idle.c
index 202e555..2116df9 100644
--- a/tools/power/cpupower/utils/idle_monitor/amd_fam14h_idle.c
+++ b/tools/power/cpupower/utils/idle_monitor/amd_fam14h_idle.c
@@ -20,8 +20,6 @@
 #include "idle_monitor/cpupower-monitor.h"
 #include "helpers/helpers.h"
 
-/******** PCI parts could go into own file and get shared ***************/
-
 #define PCI_NON_PC0_OFFSET	0xb0
 #define PCI_PC1_OFFSET		0xb4
 #define PCI_PC6_OFFSET		0xb8
@@ -82,10 +80,7 @@
 };
 
 static struct pci_access *pci_acc;
-static int pci_vendor_id = 0x1022;
-static int pci_dev_ids[2] = {0x1716, 0};
 static struct pci_dev *amd_fam14h_pci_dev;
-
 static int nbp1_entered;
 
 struct timespec start_time;
@@ -286,13 +281,13 @@
 	if (cpupower_cpu_info.vendor != X86_VENDOR_AMD)
 		return NULL;
 
-	if (cpupower_cpu_info.family == 0x14) {
-		if (cpu_count <= 0 || cpu_count > 2) {
-			fprintf(stderr, "AMD fam14h: Invalid cpu count: %d\n",
-				cpu_count);
-			return NULL;
-		}
-	} else
+	if (cpupower_cpu_info.family == 0x14)
+		strncpy(amd_fam14h_monitor.name, "Fam_14h",
+			MONITOR_NAME_LEN - 1);
+	else if (cpupower_cpu_info.family == 0x12)
+		strncpy(amd_fam14h_monitor.name, "Fam_12h",
+			MONITOR_NAME_LEN - 1);
+	else
 		return NULL;
 
 	/* We do not alloc for nbp1 machine wide counter */
@@ -303,7 +298,9 @@
 					      sizeof(unsigned long long));
 	}
 
-	amd_fam14h_pci_dev = pci_acc_init(&pci_acc, pci_vendor_id, pci_dev_ids);
+	/* We need PCI device: Slot 18, Func 6, compare with BKDG
+	   for fam 12h/14h */
+	amd_fam14h_pci_dev = pci_slot_func_init(&pci_acc, 0x18, 6);
 	if (amd_fam14h_pci_dev == NULL || pci_acc == NULL)
 		return NULL;
 
@@ -325,7 +322,7 @@
 }
 
 struct cpuidle_monitor amd_fam14h_monitor = {
-	.name			= "Ontario",
+	.name			= "",
 	.hw_states		= amd_fam14h_cstates,
 	.hw_states_num		= AMD_FAM14H_STATE_NUM,
 	.start			= amd_fam14h_start,