Merge tag 'arc-v3.9-rc1-late' of git://git.kernel.org/pub/scm/linux/kernel/git/vgupta/arc

Pull new ARC architecture from Vineet Gupta:
 "Initial ARC Linux port with some fixes on top for 3.9-rc1:

  I would like to introduce the Linux port to ARC Processors (from
  Synopsys) for 3.9-rc1.  The patch-set has been discussed on the public
  lists since Nov and has received a fair bit of review, specially from
  Arnd, tglx, Al and other subsystem maintainers for DeviceTree, kgdb...

  The arch bits are in arch/arc, some asm-generic changes (acked by
  Arnd), a minor change to PARISC (acked by Helge).

  The series is a touch bigger for a new port for 2 main reasons:

   1. It enables a basic kernel in first sub-series and adds
      ptrace/kgdb/.. later

   2. Some of the fallout of review (DeviceTree support, multi-platform-
      image support) were added on top of orig series, primarily to
      record the revision history.

  This updated pull request additionally contains

   - fixes due to our GNU tools catching up with the new syscall/ptrace
     ABI

   - some (minor) cross-arch Kconfig updates."

* tag 'arc-v3.9-rc1-late' of git://git.kernel.org/pub/scm/linux/kernel/git/vgupta/arc: (82 commits)
  ARC: split elf.h into uapi and export it for userspace
  ARC: Fixup the current ABI version
  ARC: gdbserver using regset interface possibly broken
  ARC: Kconfig cleanup tracking cross-arch Kconfig pruning in merge window
  ARC: make a copy of flat DT
  ARC: [plat-arcfpga] DT arc-uart bindings change: "baud" => "current-speed"
  ARC: Ensure CONFIG_VIRT_TO_BUS is not enabled
  ARC: Fix pt_orig_r8 access
  ARC: [3.9] Fallout of hlist iterator update
  ARC: 64bit RTSC timestamp hardware issue
  ARC: Don't fiddle with non-existent caches
  ARC: Add self to MAINTAINERS
  ARC: Provide a default serial.h for uart drivers needing BASE_BAUD
  ARC: [plat-arcfpga] defconfig for fully loaded ARC Linux
  ARC: [Review] Multi-platform image #8: platform registers SMP callbacks
  ARC: [Review] Multi-platform image #7: SMP common code to use callbacks
  ARC: [Review] Multi-platform image #6: cpu-to-dma-addr optional
  ARC: [Review] Multi-platform image #5: NR_IRQS defined by ARC core
  ARC: [Review] Multi-platform image #4: Isolate platform headers
  ARC: [Review] Multi-platform image #3: switch to board callback
  ...

147 files changed, 19552 insertions, 1 deletions

diff --git a/Documentation/devicetree/bindings/arc/interrupts.txt b/Documentation/devicetree/bindings/arc/interrupts.txt
new file mode 100644
index 000000000000..9a5d562435ea
--- /dev/null
+++ b/Documentation/devicetree/bindings/arc/interrupts.txt
@@ -0,0 +1,24 @@
+* ARC700 incore Interrupt Controller
+
+  The core interrupt controller provides 32 prioritised interrupts (2 levels)
+  to ARC700 core.
+
+Properties:
+
+- compatible: "snps,arc700-intc"
+- interrupt-controller: This is an interrupt controller.
+- #interrupt-cells: Must be <1>.
+
+  Single Cell "interrupts" property of a device specifies the IRQ number
+  between 0 to 31
+
+  intc accessed via the special ARC AUX register interface, hence "reg" property
+  is not specified.
+
+Example:
+
+	intc: interrupt-controller {
+		compatible = "snps,arc700-intc";
+		interrupt-controller;
+		#interrupt-cells = <1>;
+	};
diff --git a/MAINTAINERS b/MAINTAINERS
index 6db1c6bdf015..aea0adf414dc 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -7682,6 +7682,12 @@ F:	lib/swiotlb.c
 F:	arch/*/kernel/pci-swiotlb.c
 F:	include/linux/swiotlb.h
 
+SYNOPSYS ARC ARCHITECTURE
+M:	Vineet Gupta <vgupta@synopsys.com>
+L:	linux-snps-arc@vger.kernel.org
+S:	Supported
+F:	arch/arc/
+
 SYSV FILESYSTEM
 M:	Christoph Hellwig <hch@infradead.org>
 S:	Maintained
diff --git a/arch/arc/Kbuild b/arch/arc/Kbuild
new file mode 100644
index 000000000000..082d329d3245
--- /dev/null
+++ b/arch/arc/Kbuild
@@ -0,0 +1,2 @@
+obj-y += kernel/
+obj-y += mm/
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
new file mode 100644
index 000000000000..e6f4eca09ee3
--- /dev/null
+++ b/arch/arc/Kconfig
@@ -0,0 +1,453 @@
+#
+# Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License version 2 as
+# published by the Free Software Foundation.
+#
+
+config ARC
+	def_bool y
+	select CLONE_BACKWARDS
+	# ARC Busybox based initramfs absolutely relies on DEVTMPFS for /dev
+	select DEVTMPFS if !INITRAMFS_SOURCE=""
+	select GENERIC_ATOMIC64
+	select GENERIC_CLOCKEVENTS
+	select GENERIC_FIND_FIRST_BIT
+	# for now, we don't need GENERIC_IRQ_PROBE, CONFIG_GENERIC_IRQ_CHIP
+	select GENERIC_IRQ_SHOW
+	select GENERIC_KERNEL_EXECVE
+	select GENERIC_KERNEL_THREAD
+	select GENERIC_PENDING_IRQ if SMP
+	select GENERIC_SMP_IDLE_THREAD
+	select HAVE_ARCH_KGDB
+	select HAVE_ARCH_TRACEHOOK
+	select HAVE_GENERIC_HARDIRQS
+	select HAVE_IOREMAP_PROT
+	select HAVE_KPROBES
+	select HAVE_KRETPROBES
+	select HAVE_MEMBLOCK
+	select HAVE_MOD_ARCH_SPECIFIC if ARC_DW2_UNWIND
+	select HAVE_OPROFILE
+	select HAVE_PERF_EVENTS
+	select IRQ_DOMAIN
+	select MODULES_USE_ELF_RELA
+	select NO_BOOTMEM
+	select OF
+	select OF_EARLY_FLATTREE
+	select PERF_USE_VMALLOC
+
+config SCHED_OMIT_FRAME_POINTER
+	def_bool y
+
+config GENERIC_CSUM
+	def_bool y
+
+config RWSEM_GENERIC_SPINLOCK
+	def_bool y
+
+config ARCH_FLATMEM_ENABLE
+	def_bool y
+
+config MMU
+	def_bool y
+
+config NO_IOPORT
+	def_bool y
+
+config GENERIC_CALIBRATE_DELAY
+	def_bool y
+
+config GENERIC_HWEIGHT
+	def_bool y
+
+config BINFMT_ELF
+	def_bool y
+
+config STACKTRACE_SUPPORT
+	def_bool y
+	select STACKTRACE
+
+config HAVE_LATENCYTOP_SUPPORT
+	def_bool y
+
+config NO_DMA
+	def_bool n
+
+source "init/Kconfig"
+source "kernel/Kconfig.freezer"
+
+menu "ARC Architecture Configuration"
+
+menu "ARC Platform/SoC/Board"
+
+source "arch/arc/plat-arcfpga/Kconfig"
+#New platform adds here
+
+endmenu
+
+menu "ARC CPU Configuration"
+
+choice
+	prompt "ARC Core"
+	default ARC_CPU_770
+
+config ARC_CPU_750D
+	bool "ARC750D"
+	help
+	  Support for ARC750 core
+
+config ARC_CPU_770
+	bool "ARC770"
+	select ARC_CPU_REL_4_10
+	help
+	  Support for ARC770 core introduced with Rel 4.10 (Summer 2011)
+	  This core has a bunch of cool new features:
+	  -MMU-v3: Variable Page Sz (4k, 8k, 16k), bigger J-TLB (128x4)
+                   Shared Address Spaces (for sharing TLB entires in MMU)
+	  -Caches: New Prog Model, Region Flush
+	  -Insns: endian swap, load-locked/store-conditional, time-stamp-ctr
+
+endchoice
+
+config CPU_BIG_ENDIAN
+	bool "Enable Big Endian Mode"
+	default n
+	help
+	  Build kernel for Big Endian Mode of ARC CPU
+
+# If a platform can't work with 0x8000_0000 based dma_addr_t
+config ARC_PLAT_NEEDS_CPU_TO_DMA
+	bool
+
+config SMP
+	bool "Symmetric Multi-Processing (Incomplete)"
+	default n
+	select USE_GENERIC_SMP_HELPERS
+	help
+	  This enables support for systems with more than one CPU. If you have
+	  a system with only one CPU, like most personal computers, say N. If
+	  you have a system with more than one CPU, say Y.
+
+if SMP
+
+config ARC_HAS_COH_CACHES
+	def_bool n
+
+config ARC_HAS_COH_LLSC
+	def_bool n
+
+config ARC_HAS_COH_RTSC
+	def_bool n
+
+config ARC_HAS_REENTRANT_IRQ_LV2
+	def_bool n
+
+endif
+
+config NR_CPUS
+	int "Maximum number of CPUs (2-32)"
+	range 2 32
+	depends on SMP
+	default "2"
+
+menuconfig ARC_CACHE
+	bool "Enable Cache Support"
+	default y
+	# if SMP, cache enabled ONLY if ARC implementation has cache coherency
+	depends on !SMP || ARC_HAS_COH_CACHES
+
+if ARC_CACHE
+
+config ARC_CACHE_LINE_SHIFT
+	int "Cache Line Length (as power of 2)"
+	range 5 7
+	default "6"
+	help
+	  Starting with ARC700 4.9, Cache line length is configurable,
+	  This option specifies "N", with Line-len = 2 power N
+	  So line lengths of 32, 64, 128 are specified by 5,6,7, respectively
+	  Linux only supports same line lengths for I and D caches.
+
+config ARC_HAS_ICACHE
+	bool "Use Instruction Cache"
+	default y
+
+config ARC_HAS_DCACHE
+	bool "Use Data Cache"
+	default y
+
+config ARC_CACHE_PAGES
+	bool "Per Page Cache Control"
+	default y
+	depends on ARC_HAS_ICACHE || ARC_HAS_DCACHE
+	help
+	  This can be used to over-ride the global I/D Cache Enable on a
+	  per-page basis (but only for pages accessed via MMU such as
+	  Kernel Virtual address or User Virtual Address)
+	  TLB entries have a per-page Cache Enable Bit.
+	  Note that Global I/D ENABLE + Per Page DISABLE works but corollary
+	  Global DISABLE + Per Page ENABLE won't work
+
+endif	#ARC_CACHE
+
+config ARC_HAS_ICCM
+	bool "Use ICCM"
+	help
+	  Single Cycle RAMS to store Fast Path Code
+	default n
+
+config ARC_ICCM_SZ
+	int "ICCM Size in KB"
+	default "64"
+	depends on ARC_HAS_ICCM
+
+config ARC_HAS_DCCM
+	bool "Use DCCM"
+	help
+	  Single Cycle RAMS to store Fast Path Data
+	default n
+
+config ARC_DCCM_SZ
+	int "DCCM Size in KB"
+	default "64"
+	depends on ARC_HAS_DCCM
+
+config ARC_DCCM_BASE
+	hex "DCCM map address"
+	default "0xA0000000"
+	depends on ARC_HAS_DCCM
+
+config ARC_HAS_HW_MPY
+	bool "Use Hardware Multiplier (Normal or Faster XMAC)"
+	default y
+	help
+	  Influences how gcc generates code for MPY operations.
+	  If enabled, MPYxx insns are generated, provided by Standard/XMAC
+	  Multipler. Otherwise software multipy lib is used
+
+choice
+	prompt "ARC700 MMU Version"
+	default ARC_MMU_V3 if ARC_CPU_770
+	default ARC_MMU_V2 if ARC_CPU_750D
+
+config ARC_MMU_V1
+	bool "MMU v1"
+	help
+	  Orig ARC700 MMU
+
+config ARC_MMU_V2
+	bool "MMU v2"
+	help
+	  Fixed the deficiency of v1 - possible thrashing in memcpy sceanrio
+	  when 2 D-TLB and 1 I-TLB entries index into same 2way set.
+
+config ARC_MMU_V3
+	bool "MMU v3"
+	depends on ARC_CPU_770
+	help
+	  Introduced with ARC700 4.10: New Features
+	  Variable Page size (1k-16k), var JTLB size 128 x (2 or 4)
+	  Shared Address Spaces (SASID)
+
+endchoice
+
+
+choice
+	prompt "MMU Page Size"
+	default ARC_PAGE_SIZE_8K
+
+config ARC_PAGE_SIZE_8K
+	bool "8KB"
+	help
+	  Choose between 8k vs 16k
+
+config ARC_PAGE_SIZE_16K
+	bool "16KB"
+	depends on ARC_MMU_V3
+
+config ARC_PAGE_SIZE_4K
+	bool "4KB"
+	depends on ARC_MMU_V3
+
+endchoice
+
+config ARC_COMPACT_IRQ_LEVELS
+	bool "ARCompact IRQ Priorities: High(2)/Low(1)"
+	default n
+	# Timer HAS to be high priority, for any other high priority config
+	select ARC_IRQ3_LV2
+	# if SMP, LV2 enabled ONLY if ARC implementation has LV2 re-entrancy
+	depends on !SMP || ARC_HAS_REENTRANT_IRQ_LV2
+
+if ARC_COMPACT_IRQ_LEVELS
+
+config ARC_IRQ3_LV2
+	bool
+
+config ARC_IRQ5_LV2
+	bool
+
+config ARC_IRQ6_LV2
+	bool
+
+endif
+
+config ARC_FPU_SAVE_RESTORE
+	bool "Enable FPU state persistence across context switch"
+	default n
+	help
+	  Double Precision Floating Point unit had dedictaed regs which
+	  need to be saved/restored across context-switch.
+	  Note that ARC FPU is overly simplistic, unlike say x86, which has
+	  hardware pieces to allow software to conditionally save/restore,
+	  based on actual usage of FPU by a task. Thus our implemn does
+	  this for all tasks in system.
+
+menuconfig ARC_CPU_REL_4_10
+	bool "Enable support for Rel 4.10 features"
+	default n
+	help
+	  -ARC770 (and dependent features) enabled
+	  -ARC750 also shares some of the new features with 770
+
+config ARC_HAS_LLSC
+	bool "Insn: LLOCK/SCOND (efficient atomic ops)"
+	default y
+	depends on ARC_CPU_770
+	# if SMP, enable LLSC ONLY if ARC implementation has coherent atomics
+	depends on !SMP || ARC_HAS_COH_LLSC
+
+config ARC_HAS_SWAPE
+	bool "Insn: SWAPE (endian-swap)"
+	default y
+	depends on ARC_CPU_REL_4_10
+
+config ARC_HAS_RTSC
+	bool "Insn: RTSC (64-bit r/o cycle counter)"
+	default y
+	depends on ARC_CPU_REL_4_10
+	# if SMP, enable RTSC only if counter is coherent across cores
+	depends on !SMP || ARC_HAS_COH_RTSC
+
+endmenu   # "ARC CPU Configuration"
+
+config LINUX_LINK_BASE
+	hex "Linux Link Address"
+	default "0x80000000"
+	help
+	  ARC700 divides the 32 bit phy address space into two equal halves
+	  -Lower 2G (0 - 0x7FFF_FFFF ) is user virtual, translated by MMU
+	  -Upper 2G (0x8000_0000 onwards) is untranslated, for kernel
+	  Typically Linux kernel is linked at the start of untransalted addr,
+	  hence the default value of 0x8zs.
+	  However some customers have peripherals mapped at this addr, so
+	  Linux needs to be scooted a bit.
+	  If you don't know what the above means, leave this setting alone.
+
+config ARC_CURR_IN_REG
+	bool "Dedicate Register r25 for current_task pointer"
+	default y
+	help
+	  This reserved Register R25 to point to Current Task in
+	  kernel mode. This saves memory access for each such access
+
+
+config ARC_MISALIGN_ACCESS
+	bool "Emulate unaligned memory access (userspace only)"
+	default N
+	select SYSCTL_ARCH_UNALIGN_NO_WARN
+	select SYSCTL_ARCH_UNALIGN_ALLOW
+	help
+	  This enables misaligned 16 & 32 bit memory access from user space.
+	  Use ONLY-IF-ABS-NECESSARY as it will be very slow and also can hide
+	  potential bugs in code
+
+config ARC_STACK_NONEXEC
+	bool "Make stack non-executable"
+	default n
+	help
+	  To disable the execute permissions of stack/heap of processes
+	  which are enabled by default.
+
+config HZ
+	int "Timer Frequency"
+	default 100
+
+config ARC_METAWARE_HLINK
+	bool "Support for Metaware debugger assisted Host access"
+	default n
+	help
+	  This options allows a Linux userland apps to directly access
+	  host file system (open/creat/read/write etc) with help from
+	  Metaware Debugger. This can come in handy for Linux-host communication
+	  when there is no real usable peripheral such as EMAC.
+
+menuconfig ARC_DBG
+	bool "ARC debugging"
+	default y
+
+config ARC_DW2_UNWIND
+	bool "Enable DWARF specific kernel stack unwind"
+	depends on ARC_DBG
+	default y
+	select KALLSYMS
+	help
+	  Compiles the kernel with DWARF unwind information and can be used
+	  to get stack backtraces.
+
+	  If you say Y here the resulting kernel image will be slightly larger
+	  but not slower, and it will give very useful debugging information.
+	  If you don't debug the kernel, you can say N, but we may not be able
+	  to solve problems without frame unwind information
+
+config ARC_DBG_TLB_PARANOIA
+	bool "Paranoia Checks in Low Level TLB Handlers"
+	depends on ARC_DBG
+	default n
+
+config ARC_DBG_TLB_MISS_COUNT
+	bool "Profile TLB Misses"
+	default n
+	select DEBUG_FS
+	depends on ARC_DBG
+	help
+	  Counts number of I and D TLB Misses and exports them via Debugfs
+	  The counters can be cleared via Debugfs as well
+
+config CMDLINE
+	string "Kernel command line to built-in"
+	default "print-fatal-signals=1"
+	help
+	  The default command line which will be appended to the optional
+	  u-boot provided command line (see below)
+
+config CMDLINE_UBOOT
+	bool "Support U-boot kernel command line passing"
+	default n
+	help
+	  If you are using U-boot (www.denx.de) and wish to pass the kernel
+	  command line from the U-boot environment to the Linux kernel then
+	  switch this option on.
+	  ARC U-boot will setup the cmdline in RAM/flash and set r2 to point
+	  to it. kernel startup code will copy the string into cmdline buffer
+	  and also append CONFIG_CMDLINE.
+
+config ARC_BUILTIN_DTB_NAME
+	string "Built in DTB"
+	help
+	  Set the name of the DTB to embed in the vmlinux binary
+	  Leaving it blank selects the minimal "skeleton" dtb
+
+source "kernel/Kconfig.preempt"
+
+endmenu	 # "ARC Architecture Configuration"
+
+source "mm/Kconfig"
+source "net/Kconfig"
+source "drivers/Kconfig"
+source "fs/Kconfig"
+source "arch/arc/Kconfig.debug"
+source "security/Kconfig"
+source "crypto/Kconfig"
+source "lib/Kconfig"
diff --git a/arch/arc/Kconfig.debug b/arch/arc/Kconfig.debug
new file mode 100644
index 000000000000..962c6099659e
--- /dev/null
+++ b/arch/arc/Kconfig.debug
@@ -0,0 +1,34 @@
+menu "Kernel hacking"
+
+source "lib/Kconfig.debug"
+
+config EARLY_PRINTK
+	bool "Early printk" if EMBEDDED
+	default y
+	help
+	  Write kernel log output directly into the VGA buffer or to a serial
+	  port.
+
+	  This is useful for kernel debugging when your machine crashes very
+	  early before the console code is initialized. For normal operation
+	  it is not recommended because it looks ugly and doesn't cooperate
+	  with klogd/syslogd or the X server. You should normally N here,
+	  unless you want to debug such a crash.
+
+config DEBUG_STACKOVERFLOW
+	bool "Check for stack overflows"
+	depends on DEBUG_KERNEL
+	help
+	  This option will cause messages to be printed if free stack space
+	  drops below a certain limit.
+
+config 16KSTACKS
+	bool "Use 16Kb for kernel stacks instead of 8Kb"
+	help
+	  If you say Y here the kernel will use a  16Kb stacksize for the
+	  kernel stack attached to each process/thread. The default is 8K.
+	  This increases the resident kernel footprint and will cause less
+	  threads to run on the system and also increase the pressure
+	  on the VM subsystem for higher order allocations.
+
+endmenu
diff --git a/arch/arc/Makefile b/arch/arc/Makefile
new file mode 100644
index 000000000000..92379c7cbc1a
--- /dev/null
+++ b/arch/arc/Makefile
@@ -0,0 +1,126 @@
+#
+# Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License version 2 as
+# published by the Free Software Foundation.
+#
+
+UTS_MACHINE := arc
+
+KBUILD_DEFCONFIG := fpga_defconfig
+
+cflags-y	+= -mA7 -fno-common -pipe -fno-builtin -D__linux__
+
+LINUXINCLUDE	+=  -include ${src}/arch/arc/include/asm/defines.h
+
+ifdef CONFIG_ARC_CURR_IN_REG
+# For a global register defintion, make sure it gets passed to every file
+# We had a customer reported bug where some code built in kernel was NOT using
+# any kernel headers, and missing the r25 global register
+# Can't do unconditionally (like above) because of recursive include issues
+# due to <linux/thread_info.h>
+LINUXINCLUDE	+=  -include ${src}/arch/arc/include/asm/current.h
+endif
+
+atleast_gcc44 :=  $(call cc-ifversion, -gt, 0402, y)
+cflags-$(atleast_gcc44)			+= -fsection-anchors
+
+cflags-$(CONFIG_ARC_HAS_LLSC)		+= -mlock
+cflags-$(CONFIG_ARC_HAS_SWAPE)		+= -mswape
+cflags-$(CONFIG_ARC_HAS_RTSC)		+= -mrtsc
+cflags-$(CONFIG_ARC_DW2_UNWIND)		+= -fasynchronous-unwind-tables
+
+ifndef CONFIG_CC_OPTIMIZE_FOR_SIZE
+# Generic build system uses -O2, we want -O3
+cflags-y  += -O3
+endif
+
+# small data is default for elf32 tool-chain. If not usable, disable it
+# This also allows repurposing GP as scratch reg to gcc reg allocator
+disable_small_data := y
+cflags-$(disable_small_data)		+= -mno-sdata -fcall-used-gp
+
+cflags-$(CONFIG_CPU_BIG_ENDIAN)		+= -mbig-endian
+ldflags-$(CONFIG_CPU_BIG_ENDIAN)	+= -EB
+
+# STAR 9000518362:
+# arc-linux-uclibc-ld (buildroot) or arceb-elf32-ld (EZChip) don't accept
+# --build-id w/o "-marclinux".
+# Default arc-elf32-ld is OK
+ldflags-y				+= -marclinux
+
+ARC_LIBGCC				:= -mA7
+cflags-$(CONFIG_ARC_HAS_HW_MPY)		+= -multcost=16
+
+ifndef CONFIG_ARC_HAS_HW_MPY
+	cflags-y	+= -mno-mpy
+
+# newlib for ARC700 assumes MPY to be always present, which is generally true
+# However, if someone really doesn't want MPY, we need to use the 600 ver
+# which coupled with -mno-mpy will use mpy emulation
+# With gcc 4.4.7, -mno-mpy is enough to make any other related adjustments,
+# e.g. increased cost of MPY. With gcc 4.2.1 this had to be explicitly hinted
+
+	ARC_LIBGCC		:= -marc600
+	ifneq ($(atleast_gcc44),y)
+		cflags-y	+= -multcost=30
+	endif
+endif
+
+LIBGCC	:= $(shell $(CC) $(ARC_LIBGCC) $(cflags-y) --print-libgcc-file-name)
+
+# Modules with short calls might break for calls into builtin-kernel
+KBUILD_CFLAGS_MODULE	+= -mlong-calls
+
+# Finally dump eveything into kernel build system
+KBUILD_CFLAGS	+= $(cflags-y)
+KBUILD_AFLAGS	+= $(KBUILD_CFLAGS)
+LDFLAGS		+= $(ldflags-y)
+
+head-y		:= arch/arc/kernel/head.o
+
+# See arch/arc/Kbuild for content of core part of the kernel
+core-y		+= arch/arc/
+
+# w/o this dtb won't embed into kernel binary
+core-y		+= arch/arc/boot/dts/
+
+core-$(CONFIG_ARC_PLAT_FPGA_LEGACY)	+= arch/arc/plat-arcfpga/
+
+drivers-$(CONFIG_OPROFILE)	+= arch/arc/oprofile/
+
+libs-y		+= arch/arc/lib/ $(LIBGCC)
+
+#default target for make without any arguements.
+KBUILD_IMAGE := bootpImage
+
+all:	$(KBUILD_IMAGE)
+boot	:= arch/arc/boot
+
+bootpImage: vmlinux
+
+uImage: vmlinux
+	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
+
+%.dtb %.dtb.S %.dtb.o: scripts
+	$(Q)$(MAKE) $(build)=$(boot)/dts $(boot)/dts/$@
+
+dtbs: scripts
+	$(Q)$(MAKE) $(build)=$(boot)/dts dtbs
+
+archclean:
+	$(Q)$(MAKE) $(clean)=$(boot)
+
+# Hacks to enable final link due to absence of link-time branch relexation
+# and gcc choosing optimal(shorter) branches at -O3
+#
+# vineetg Feb 2010: -mlong-calls switched off for overall kernel build
+# However lib/decompress_inflate.o (.init.text) calls
+# zlib_inflate_workspacesize (.text) causing relocation errors.
+# Thus forcing all exten calls in this file to be long calls
+export CFLAGS_decompress_inflate.o = -mmedium-calls
+export CFLAGS_initramfs.o = -mmedium-calls
+ifdef CONFIG_SMP
+export CFLAGS_core.o = -mmedium-calls
+endif
diff --git a/arch/arc/boot/Makefile b/arch/arc/boot/Makefile
new file mode 100644
index 000000000000..7d514c24e095
--- /dev/null
+++ b/arch/arc/boot/Makefile
@@ -0,0 +1,26 @@
+targets := vmlinux.bin vmlinux.bin.gz uImage
+
+# uImage build relies on mkimage being availble on your host for ARC target
+# You will need to build u-boot for ARC, rename mkimage to arc-elf32-mkimage
+# and make sure it's reacable from your PATH
+MKIMAGE := $(srctree)/scripts/mkuboot.sh
+
+OBJCOPYFLAGS= -O binary -R .note -R .note.gnu.build-id -R .comment -S
+
+LINUX_START_TEXT = $$(readelf -h vmlinux | \
+			grep "Entry point address" | grep -o 0x.*)
+
+UIMAGE_LOADADDR    = $(CONFIG_LINUX_LINK_BASE)
+UIMAGE_ENTRYADDR   = $(LINUX_START_TEXT)
+UIMAGE_COMPRESSION = gzip
+
+$(obj)/vmlinux.bin: vmlinux FORCE
+	$(call if_changed,objcopy)
+
+$(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin FORCE
+	$(call if_changed,gzip)
+
+$(obj)/uImage: $(obj)/vmlinux.bin.gz FORCE
+	$(call if_changed,uimage)
+
+PHONY += FORCE
diff --git a/arch/arc/boot/dts/Makefile b/arch/arc/boot/dts/Makefile
new file mode 100644
index 000000000000..5776835d583f
--- /dev/null
+++ b/arch/arc/boot/dts/Makefile
@@ -0,0 +1,13 @@
+# Built-in dtb
+builtindtb-y		:= angel4
+
+ifneq ($(CONFIG_ARC_BUILTIN_DTB_NAME),"")
+	builtindtb-y	:= $(patsubst "%",%,$(CONFIG_ARC_BUILTIN_DTB_NAME))
+endif
+
+obj-y   += $(builtindtb-y).dtb.o
+targets += $(builtindtb-y).dtb
+
+dtbs:  $(addprefix  $(obj)/, $(builtindtb-y).dtb)
+
+clean-files := *.dtb
diff --git a/arch/arc/boot/dts/angel4.dts b/arch/arc/boot/dts/angel4.dts
new file mode 100644
index 000000000000..bae4f936cb03
--- /dev/null
+++ b/arch/arc/boot/dts/angel4.dts
@@ -0,0 +1,55 @@
+/*
+ * Copyright (C) 2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+/dts-v1/;
+
+/include/ "skeleton.dtsi"
+
+/ {
+	compatible = "snps,arc-angel4";
+	clock-frequency = <80000000>;	/* 80 MHZ */
+	#address-cells = <1>;
+	#size-cells = <1>;
+	interrupt-parent = <&intc>;
+
+	chosen {
+		bootargs = "console=ttyARC0,115200n8";
+	};
+
+	aliases {
+		serial0 = &arcuart0;
+	};
+
+	memory {
+		device_type = "memory";
+		reg = <0x00000000 0x10000000>;	/* 256M */
+	};
+
+	fpga {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		/* child and parent address space 1:1 mapped */
+		ranges;
+
+		intc: interrupt-controller {
+			compatible = "snps,arc700-intc";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+		};
+
+		arcuart0: serial@c0fc1000 {
+			compatible = "snps,arc-uart";
+			reg = <0xc0fc1000 0x100>;
+			interrupts = <5>;
+			clock-frequency = <80000000>;
+			current-speed = <115200>;
+			status = "okay";
+		};
+	};
+};
diff --git a/arch/arc/boot/dts/skeleton.dts b/arch/arc/boot/dts/skeleton.dts
new file mode 100644
index 000000000000..25a84fb5b3dc
--- /dev/null
+++ b/arch/arc/boot/dts/skeleton.dts
@@ -0,0 +1,10 @@
+/*
+ * Copyright (C) 2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+/dts-v1/;
+
+/include/ "skeleton.dtsi"
diff --git a/arch/arc/boot/dts/skeleton.dtsi b/arch/arc/boot/dts/skeleton.dtsi
new file mode 100644
index 000000000000..a870bdd5e404
--- /dev/null
+++ b/arch/arc/boot/dts/skeleton.dtsi
@@ -0,0 +1,37 @@
+/*
+ * Copyright (C) 2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*
+ * Skeleton device tree; the bare minimum needed to boot; just include and
+ * add a compatible value.
+ */
+
+/ {
+	compatible = "snps,arc";
+	clock-frequency = <80000000>;	/* 80 MHZ */
+	#address-cells = <1>;
+	#size-cells = <1>;
+	chosen { };
+	aliases { };
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu@0 {
+			device_type = "cpu";
+			compatible = "snps,arc770d";
+			reg = <0>;
+		};
+	};
+
+	memory {
+		device_type = "memory";
+		reg = <0x00000000 0x10000000>;	/* 256M */
+	};
+};
diff --git a/arch/arc/configs/fpga_defconfig b/arch/arc/configs/fpga_defconfig
new file mode 100644
index 000000000000..b8698067ebbe
--- /dev/null
+++ b/arch/arc/configs/fpga_defconfig
@@ -0,0 +1,61 @@
+CONFIG_CROSS_COMPILE="arc-elf32-"
+# CONFIG_LOCALVERSION_AUTO is not set
+CONFIG_DEFAULT_HOSTNAME="ARCLinux"
+# CONFIG_SWAP is not set
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_NAMESPACES=y
+# CONFIG_UTS_NS is not set
+# CONFIG_PID_NS is not set
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_INITRAMFS_SOURCE="../arc_initramfs"
+CONFIG_KALLSYMS_ALL=y
+CONFIG_EMBEDDED=y
+# CONFIG_SLUB_DEBUG is not set
+# CONFIG_COMPAT_BRK is not set
+CONFIG_KPROBES=y
+CONFIG_MODULES=y
+# CONFIG_LBDAF is not set
+# CONFIG_BLK_DEV_BSG is not set
+# CONFIG_IOSCHED_DEADLINE is not set
+# CONFIG_IOSCHED_CFQ is not set
+CONFIG_ARC_PLAT_FPGA_LEGACY=y
+CONFIG_ARC_BOARD_ML509=y
+# CONFIG_ARC_HAS_RTSC is not set
+CONFIG_ARC_BUILTIN_DTB_NAME="angel4"
+# CONFIG_COMPACTION is not set
+# CONFIG_CROSS_MEMORY_ATTACH is not set
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_UNIX_DIAG=y
+CONFIG_NET_KEY=y
+CONFIG_INET=y
+# CONFIG_IPV6 is not set
+# CONFIG_STANDALONE is not set
+# CONFIG_PREVENT_FIRMWARE_BUILD is not set
+# CONFIG_FIRMWARE_IN_KERNEL is not set
+# CONFIG_BLK_DEV is not set
+# CONFIG_INPUT_MOUSEDEV_PSAUX is not set
+# CONFIG_INPUT_KEYBOARD is not set
+# CONFIG_INPUT_MOUSE is not set
+# CONFIG_SERIO is not set
+# CONFIG_LEGACY_PTYS is not set
+# CONFIG_DEVKMEM is not set
+CONFIG_SERIAL_ARC=y
+CONFIG_SERIAL_ARC_CONSOLE=y
+# CONFIG_HW_RANDOM is not set
+# CONFIG_HWMON is not set
+# CONFIG_VGA_CONSOLE is not set
+# CONFIG_HID is not set
+# CONFIG_USB_SUPPORT is not set
+# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_EXT2_FS=y
+CONFIG_EXT2_FS_XATTR=y
+CONFIG_TMPFS=y
+# CONFIG_MISC_FILESYSTEMS is not set
+CONFIG_NFS_FS=y
+# CONFIG_ENABLE_WARN_DEPRECATED is not set
+# CONFIG_ENABLE_MUST_CHECK is not set
+CONFIG_XZ_DEC=y
diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild
new file mode 100644
index 000000000000..48af742f8b5a
--- /dev/null
+++ b/arch/arc/include/asm/Kbuild
@@ -0,0 +1,49 @@
+generic-y += auxvec.h
+generic-y += bugs.h
+generic-y += bitsperlong.h
+generic-y += clkdev.h
+generic-y += cputime.h
+generic-y += device.h
+generic-y += div64.h
+generic-y += emergency-restart.h
+generic-y += errno.h
+generic-y += fcntl.h
+generic-y += fb.h
+generic-y += ftrace.h
+generic-y += hardirq.h
+generic-y += hw_irq.h
+generic-y += ioctl.h
+generic-y += ioctls.h
+generic-y += ipcbuf.h
+generic-y += irq_regs.h
+generic-y += kmap_types.h
+generic-y += kvm_para.h
+generic-y += local.h
+generic-y += local64.h
+generic-y += mman.h
+generic-y += msgbuf.h
+generic-y += param.h
+generic-y += parport.h
+generic-y += pci.h
+generic-y += percpu.h
+generic-y += poll.h
+generic-y += posix_types.h
+generic-y += resource.h
+generic-y += scatterlist.h
+generic-y += sembuf.h
+generic-y += shmbuf.h
+generic-y += shmparam.h
+generic-y += siginfo.h
+generic-y += socket.h
+generic-y += sockios.h
+generic-y += stat.h
+generic-y += statfs.h
+generic-y += termbits.h
+generic-y += termios.h
+generic-y += topology.h
+generic-y += trace_clock.h
+generic-y += types.h
+generic-y += ucontext.h
+generic-y += user.h
+generic-y += vga.h
+generic-y += xor.h
diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h
new file mode 100644
index 000000000000..1b907c465666
--- /dev/null
+++ b/arch/arc/include/asm/arcregs.h
@@ -0,0 +1,433 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_ARC_ARCREGS_H
+#define _ASM_ARC_ARCREGS_H
+
+#ifdef __KERNEL__
+
+/* Build Configuration Registers */
+#define ARC_REG_DCCMBASE_BCR	0x61	/* DCCM Base Addr */
+#define ARC_REG_CRC_BCR		0x62
+#define ARC_REG_DVFB_BCR	0x64
+#define ARC_REG_EXTARITH_BCR	0x65
+#define ARC_REG_VECBASE_BCR	0x68
+#define ARC_REG_PERIBASE_BCR	0x69
+#define ARC_REG_FP_BCR		0x6B	/* Single-Precision FPU */
+#define ARC_REG_DPFP_BCR	0x6C	/* Dbl Precision FPU */
+#define ARC_REG_MMU_BCR		0x6f
+#define ARC_REG_DCCM_BCR	0x74	/* DCCM Present + SZ */
+#define ARC_REG_TIMERS_BCR	0x75
+#define ARC_REG_ICCM_BCR	0x78
+#define ARC_REG_XY_MEM_BCR	0x79
+#define ARC_REG_MAC_BCR		0x7a
+#define ARC_REG_MUL_BCR		0x7b
+#define ARC_REG_SWAP_BCR	0x7c
+#define ARC_REG_NORM_BCR	0x7d
+#define ARC_REG_MIXMAX_BCR	0x7e
+#define ARC_REG_BARREL_BCR	0x7f
+#define ARC_REG_D_UNCACH_BCR	0x6A
+
+/* status32 Bits Positions */
+#define STATUS_H_BIT		0	/* CPU Halted */
+#define STATUS_E1_BIT		1	/* Int 1 enable */
+#define STATUS_E2_BIT		2	/* Int 2 enable */
+#define STATUS_A1_BIT		3	/* Int 1 active */
+#define STATUS_A2_BIT		4	/* Int 2 active */
+#define STATUS_AE_BIT		5	/* Exception active */
+#define STATUS_DE_BIT		6	/* PC is in delay slot */
+#define STATUS_U_BIT		7	/* User/Kernel mode */
+#define STATUS_L_BIT		12	/* Loop inhibit */
+
+/* These masks correspond to the status word(STATUS_32) bits */
+#define STATUS_H_MASK		(1<<STATUS_H_BIT)
+#define STATUS_E1_MASK		(1<<STATUS_E1_BIT)
+#define STATUS_E2_MASK		(1<<STATUS_E2_BIT)
+#define STATUS_A1_MASK		(1<<STATUS_A1_BIT)
+#define STATUS_A2_MASK		(1<<STATUS_A2_BIT)
+#define STATUS_AE_MASK		(1<<STATUS_AE_BIT)
+#define STATUS_DE_MASK		(1<<STATUS_DE_BIT)
+#define STATUS_U_MASK		(1<<STATUS_U_BIT)
+#define STATUS_L_MASK		(1<<STATUS_L_BIT)
+
+/*
+ * ECR: Exception Cause Reg bits-n-pieces
+ * [23:16] = Exception Vector
+ * [15: 8] = Exception Cause Code
+ * [ 7: 0] = Exception Parameters (for certain types only)
+ */
+#define ECR_VEC_MASK			0xff0000
+#define ECR_CODE_MASK			0x00ff00
+#define ECR_PARAM_MASK			0x0000ff
+
+/* Exception Cause Vector Values */
+#define ECR_V_INSN_ERR			0x02
+#define ECR_V_MACH_CHK			0x20
+#define ECR_V_ITLB_MISS			0x21
+#define ECR_V_DTLB_MISS			0x22
+#define ECR_V_PROTV			0x23
+
+/* Protection Violation Exception Cause Code Values */
+#define ECR_C_PROTV_INST_FETCH		0x00
+#define ECR_C_PROTV_LOAD		0x01
+#define ECR_C_PROTV_STORE		0x02
+#define ECR_C_PROTV_XCHG		0x03
+#define ECR_C_PROTV_MISALIG_DATA	0x04
+
+/* DTLB Miss Exception Cause Code Values */
+#define ECR_C_BIT_DTLB_LD_MISS		8
+#define ECR_C_BIT_DTLB_ST_MISS		9
+
+
+/* Auxiliary registers */
+#define AUX_IDENTITY		4
+#define AUX_INTR_VEC_BASE	0x25
+#define AUX_IRQ_LEV		0x200	/* IRQ Priority: L1 or L2 */
+#define AUX_IRQ_HINT		0x201	/* For generating Soft Interrupts */
+#define AUX_IRQ_LV12		0x43	/* interrupt level register */
+
+#define AUX_IENABLE		0x40c
+#define AUX_ITRIGGER		0x40d
+#define AUX_IPULSE		0x415
+
+/* Timer related Aux registers */
+#define ARC_REG_TIMER0_LIMIT	0x23	/* timer 0 limit */
+#define ARC_REG_TIMER0_CTRL	0x22	/* timer 0 control */
+#define ARC_REG_TIMER0_CNT	0x21	/* timer 0 count */
+#define ARC_REG_TIMER1_LIMIT	0x102	/* timer 1 limit */
+#define ARC_REG_TIMER1_CTRL	0x101	/* timer 1 control */
+#define ARC_REG_TIMER1_CNT	0x100	/* timer 1 count */
+
+#define TIMER_CTRL_IE		(1 << 0) /* Interupt when Count reachs limit */
+#define TIMER_CTRL_NH		(1 << 1) /* Count only when CPU NOT halted */
+
+/* MMU Management regs */
+#define ARC_REG_TLBPD0		0x405
+#define ARC_REG_TLBPD1		0x406
+#define ARC_REG_TLBINDEX	0x407
+#define ARC_REG_TLBCOMMAND	0x408
+#define ARC_REG_PID		0x409
+#define ARC_REG_SCRATCH_DATA0	0x418
+
+/* Bits in MMU PID register */
+#define MMU_ENABLE		(1 << 31)	/* Enable MMU for process */
+
+/* Error code if probe fails */
+#define TLB_LKUP_ERR		0x80000000
+
+/* TLB Commands */
+#define TLBWrite    0x1
+#define TLBRead     0x2
+#define TLBGetIndex 0x3
+#define TLBProbe    0x4
+
+#if (CONFIG_ARC_MMU_VER >= 2)
+#define TLBWriteNI  0x5		/* write JTLB without inv uTLBs */
+#define TLBIVUTLB   0x6		/* explicitly inv uTLBs */
+#else
+#undef TLBWriteNI		/* These cmds don't exist on older MMU */
+#undef TLBIVUTLB
+#endif
+
+/* Instruction cache related Auxiliary registers */
+#define ARC_REG_IC_BCR		0x77	/* Build Config reg */
+#define ARC_REG_IC_IVIC		0x10
+#define ARC_REG_IC_CTRL		0x11
+#define ARC_REG_IC_IVIL		0x19
+#if (CONFIG_ARC_MMU_VER > 2)
+#define ARC_REG_IC_PTAG		0x1E
+#endif
+
+/* Bit val in IC_CTRL */
+#define IC_CTRL_CACHE_DISABLE   0x1
+
+/* Data cache related Auxiliary registers */
+#define ARC_REG_DC_BCR		0x72
+#define ARC_REG_DC_IVDC		0x47
+#define ARC_REG_DC_CTRL		0x48
+#define ARC_REG_DC_IVDL		0x4A
+#define ARC_REG_DC_FLSH		0x4B
+#define ARC_REG_DC_FLDL		0x4C
+#if (CONFIG_ARC_MMU_VER > 2)
+#define ARC_REG_DC_PTAG		0x5C
+#endif
+
+/* Bit val in DC_CTRL */
+#define DC_CTRL_INV_MODE_FLUSH  0x40
+#define DC_CTRL_FLUSH_STATUS    0x100
+
+/* MMU Management regs */
+#define ARC_REG_PID		0x409
+#define ARC_REG_SCRATCH_DATA0	0x418
+
+/* Bits in MMU PID register */
+#define MMU_ENABLE		(1 << 31)	/* Enable MMU for process */
+
+/*
+ * Floating Pt Registers
+ * Status regs are read-only (build-time) so need not be saved/restored
+ */
+#define ARC_AUX_FP_STAT         0x300
+#define ARC_AUX_DPFP_1L         0x301
+#define ARC_AUX_DPFP_1H         0x302
+#define ARC_AUX_DPFP_2L         0x303
+#define ARC_AUX_DPFP_2H         0x304
+#define ARC_AUX_DPFP_STAT       0x305
+
+#ifndef __ASSEMBLY__
+
+/*
+ ******************************************************************
+ *      Inline ASM macros to read/write AUX Regs
+ *      Essentially invocation of lr/sr insns from "C"
+ */
+
+#if 1
+
+#define read_aux_reg(reg)	__builtin_arc_lr(reg)
+
+/* gcc builtin sr needs reg param to be long immediate */
+#define write_aux_reg(reg_immed, val)		\
+		__builtin_arc_sr((unsigned int)val, reg_immed)
+
+#else
+
+#define read_aux_reg(reg)		\
+({					\
+	unsigned int __ret;		\
+	__asm__ __volatile__(		\
+	"	lr    %0, [%1]"		\
+	: "=r"(__ret)			\
+	: "i"(reg));			\
+	__ret;				\
+})
+
+/*
+ * Aux Reg address is specified as long immediate by caller
+ * e.g.
+ *    write_aux_reg(0x69, some_val);
+ * This generates tightest code.
+ */
+#define write_aux_reg(reg_imm, val)	\
+({					\
+	__asm__ __volatile__(		\
+	"	sr   %0, [%1]	\n"	\
+	:				\
+	: "ir"(val), "i"(reg_imm));	\
+})
+
+/*
+ * Aux Reg address is specified in a variable
+ *  * e.g.
+ *      reg_num = 0x69
+ *      write_aux_reg2(reg_num, some_val);
+ * This has to generate glue code to load the reg num from
+ *  memory to a reg hence not recommended.
+ */
+#define write_aux_reg2(reg_in_var, val)		\
+({						\
+	unsigned int tmp;			\
+						\
+	__asm__ __volatile__(			\
+	"	ld   %0, [%2]	\n\t"		\
+	"	sr   %1, [%0]	\n\t"		\
+	: "=&r"(tmp)				\
+	: "r"(val), "memory"(&reg_in_var));	\
+})
+
+#endif
+
+#define READ_BCR(reg, into)				\
+{							\
+	unsigned int tmp;				\
+	tmp = read_aux_reg(reg);			\
+	if (sizeof(tmp) == sizeof(into)) {		\
+		into = *((typeof(into) *)&tmp);		\
+	} else {					\
+		extern void bogus_undefined(void);	\
+		bogus_undefined();			\
+	}						\
+}
+
+#define WRITE_BCR(reg, into)				\
+{							\
+	unsigned int tmp;				\
+	if (sizeof(tmp) == sizeof(into)) {		\
+		tmp = (*(unsigned int *)(into));	\
+		write_aux_reg(reg, tmp);		\
+	} else  {					\
+		extern void bogus_undefined(void);	\
+		bogus_undefined();			\
+	}						\
+}
+
+/* Helpers */
+#define TO_KB(bytes)		((bytes) >> 10)
+#define TO_MB(bytes)		(TO_KB(bytes) >> 10)
+#define PAGES_TO_KB(n_pages)	((n_pages) << (PAGE_SHIFT - 10))
+#define PAGES_TO_MB(n_pages)	(PAGES_TO_KB(n_pages) >> 10)
+
+#ifdef CONFIG_ARC_FPU_SAVE_RESTORE
+/* These DPFP regs need to be saved/restored across ctx-sw */
+struct arc_fpu {
+	struct {
+		unsigned int l, h;
+	} aux_dpfp[2];
+};
+#endif
+
+/*
+ ***************************************************************
+ * Build Configuration Registers, with encoded hardware config
+ */
+struct bcr_identity {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int chip_id:16, cpu_id:8, family:8;
+#else
+	unsigned int family:8, cpu_id:8, chip_id:16;
+#endif
+};
+
+struct bcr_mmu_1_2 {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int ver:8, ways:4, sets:4, u_itlb:8, u_dtlb:8;
+#else
+	unsigned int u_dtlb:8, u_itlb:8, sets:4, ways:4, ver:8;
+#endif
+};
+
+struct bcr_mmu_3 {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int ver:8, ways:4, sets:4, osm:1, reserv:3, pg_sz:4,
+		     u_itlb:4, u_dtlb:4;
+#else
+	unsigned int u_dtlb:4, u_itlb:4, pg_sz:4, reserv:3, osm:1, sets:4,
+		     ways:4, ver:8;
+#endif
+};
+
+#define EXTN_SWAP_VALID     0x1
+#define EXTN_NORM_VALID     0x2
+#define EXTN_MINMAX_VALID   0x2
+#define EXTN_BARREL_VALID   0x2
+
+struct bcr_extn {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int pad:20, crc:1, ext_arith:2, mul:2, barrel:2, minmax:2,
+		     norm:2, swap:1;
+#else
+	unsigned int swap:1, norm:2, minmax:2, barrel:2, mul:2, ext_arith:2,
+		     crc:1, pad:20;
+#endif
+};
+
+/* DSP Options Ref Manual */
+struct bcr_extn_mac_mul {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int pad:16, type:8, ver:8;
+#else
+	unsigned int ver:8, type:8, pad:16;
+#endif
+};
+
+struct bcr_extn_xymem {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int ram_org:2, num_banks:4, bank_sz:4, ver:8;
+#else
+	unsigned int ver:8, bank_sz:4, num_banks:4, ram_org:2;
+#endif
+};
+
+struct bcr_cache {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int pad:12, line_len:4, sz:4, config:4, ver:8;
+#else
+	unsigned int ver:8, config:4, sz:4, line_len:4, pad:12;
+#endif
+};
+
+struct bcr_perip {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int start:8, pad2:8, sz:8, pad:8;
+#else
+	unsigned int pad:8, sz:8, pad2:8, start:8;
+#endif
+};
+struct bcr_iccm {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int base:16, pad:5, sz:3, ver:8;
+#else
+	unsigned int ver:8, sz:3, pad:5, base:16;
+#endif
+};
+
+/* DCCM Base Address Register: ARC_REG_DCCMBASE_BCR */
+struct bcr_dccm_base {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int addr:24, ver:8;
+#else
+	unsigned int ver:8, addr:24;
+#endif
+};
+
+/* DCCM RAM Configuration Register: ARC_REG_DCCM_BCR */
+struct bcr_dccm {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int res:21, sz:3, ver:8;
+#else
+	unsigned int ver:8, sz:3, res:21;
+#endif
+};
+
+/* Both SP and DP FPU BCRs have same format */
+struct bcr_fp {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int fast:1, ver:8;
+#else
+	unsigned int ver:8, fast:1;
+#endif
+};
+
+/*
+ *******************************************************************
+ * Generic structures to hold build configuration used at runtime
+ */
+
+struct cpuinfo_arc_mmu {
+	unsigned int ver, pg_sz, sets, ways, u_dtlb, u_itlb, num_tlb;
+};
+
+struct cpuinfo_arc_cache {
+	unsigned int has_aliasing, sz, line_len, assoc, ver;
+};
+
+struct cpuinfo_arc_ccm {
+	unsigned int base_addr, sz;
+};
+
+struct cpuinfo_arc {
+	struct cpuinfo_arc_cache icache, dcache;
+	struct cpuinfo_arc_mmu mmu;
+	struct bcr_identity core;
+	unsigned int timers;
+	unsigned int vec_base;
+	unsigned int uncached_base;
+	struct cpuinfo_arc_ccm iccm, dccm;
+	struct bcr_extn extn;
+	struct bcr_extn_xymem extn_xymem;
+	struct bcr_extn_mac_mul extn_mac_mul;
+	struct bcr_fp fp, dpfp;
+};
+
+extern struct cpuinfo_arc cpuinfo_arc700[];
+
+#endif /* __ASEMBLY__ */
+
+#endif /* __KERNEL__ */
+
+#endif /* _ASM_ARC_ARCREGS_H */
diff --git a/arch/arc/include/asm/asm-offsets.h b/arch/arc/include/asm/asm-offsets.h
new file mode 100644
index 000000000000..dad18768fe43
--- /dev/null
+++ b/arch/arc/include/asm/asm-offsets.h
@@ -0,0 +1,9 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <generated/asm-offsets.h>
diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
new file mode 100644
index 000000000000..83f03ca6caf6
--- /dev/null
+++ b/arch/arc/include/asm/atomic.h
@@ -0,0 +1,232 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_ARC_ATOMIC_H
+#define _ASM_ARC_ATOMIC_H
+
+#ifdef __KERNEL__
+
+#ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+#include <linux/compiler.h>
+#include <asm/cmpxchg.h>
+#include <asm/barrier.h>
+#include <asm/smp.h>
+
+#define atomic_read(v)  ((v)->counter)
+
+#ifdef CONFIG_ARC_HAS_LLSC
+
+#define atomic_set(v, i) (((v)->counter) = (i))
+
+static inline void atomic_add(int i, atomic_t *v)
+{
+	unsigned int temp;
+
+	__asm__ __volatile__(
+	"1:	llock   %0, [%1]	\n"
+	"	add     %0, %0, %2	\n"
+	"	scond   %0, [%1]	\n"
+	"	bnz     1b		\n"
+	: "=&r"(temp)	/* Early clobber, to prevent reg reuse */
+	: "r"(&v->counter), "ir"(i)
+	: "cc");
+}
+
+static inline void atomic_sub(int i, atomic_t *v)
+{
+	unsigned int temp;
+
+	__asm__ __volatile__(
+	"1:	llock   %0, [%1]	\n"
+	"	sub     %0, %0, %2	\n"
+	"	scond   %0, [%1]	\n"
+	"	bnz     1b		\n"
+	: "=&r"(temp)
+	: "r"(&v->counter), "ir"(i)
+	: "cc");
+}
+
+/* add and also return the new value */
+static inline int atomic_add_return(int i, atomic_t *v)
+{
+	unsigned int temp;
+
+	__asm__ __volatile__(
+	"1:	llock   %0, [%1]	\n"
+	"	add     %0, %0, %2	\n"
+	"	scond   %0, [%1]	\n"
+	"	bnz     1b		\n"
+	: "=&r"(temp)
+	: "r"(&v->counter), "ir"(i)
+	: "cc");
+
+	return temp;
+}
+
+static inline int atomic_sub_return(int i, atomic_t *v)
+{
+	unsigned int temp;
+
+	__asm__ __volatile__(
+	"1:	llock   %0, [%1]	\n"
+	"	sub     %0, %0, %2	\n"
+	"	scond   %0, [%1]	\n"
+	"	bnz     1b		\n"
+	: "=&r"(temp)
+	: "r"(&v->counter), "ir"(i)
+	: "cc");
+
+	return temp;
+}
+
+static inline void atomic_clear_mask(unsigned long mask, unsigned long *addr)
+{
+	unsigned int temp;
+
+	__asm__ __volatile__(
+	"1:	llock   %0, [%1]	\n"
+	"	bic     %0, %0, %2	\n"
+	"	scond   %0, [%1]	\n"
+	"	bnz     1b		\n"
+	: "=&r"(temp)
+	: "r"(addr), "ir"(mask)
+	: "cc");
+}
+
+#else	/* !CONFIG_ARC_HAS_LLSC */
+
+#ifndef CONFIG_SMP
+
+ /* violating atomic_xxx API locking protocol in UP for optimization sake */
+#define atomic_set(v, i) (((v)->counter) = (i))
+
+#else
+
+static inline void atomic_set(atomic_t *v, int i)
+{
+	/*
+	 * Independent of hardware support, all of the atomic_xxx() APIs need
+	 * to follow the same locking rules to make sure that a "hardware"
+	 * atomic insn (e.g. LD) doesn't clobber an "emulated" atomic insn
+	 * sequence
+	 *
+	 * Thus atomic_set() despite being 1 insn (and seemingly atomic)
+	 * requires the locking.
+	 */
+	unsigned long flags;
+
+	atomic_ops_lock(flags);
+	v->counter = i;
+	atomic_ops_unlock(flags);
+}
+#endif
+
+/*
+ * Non hardware assisted Atomic-R-M-W
+ * Locking would change to irq-disabling only (UP) and spinlocks (SMP)
+ */
+
+static inline void atomic_add(int i, atomic_t *v)
+{
+	unsigned long flags;
+
+	atomic_ops_lock(flags);
+	v->counter += i;
+	atomic_ops_unlock(flags);
+}
+
+static inline void atomic_sub(int i, atomic_t *v)
+{
+	unsigned long flags;
+
+	atomic_ops_lock(flags);
+	v->counter -= i;
+	atomic_ops_unlock(flags);
+}
+
+static inline int atomic_add_return(int i, atomic_t *v)
+{
+	unsigned long flags;
+	unsigned long temp;
+
+	atomic_ops_lock(flags);
+	temp = v->counter;
+	temp += i;
+	v->counter = temp;
+	atomic_ops_unlock(flags);
+
+	return temp;
+}
+
+static inline int atomic_sub_return(int i, atomic_t *v)
+{
+	unsigned long flags;
+	unsigned long temp;
+
+	atomic_ops_lock(flags);
+	temp = v->counter;
+	temp -= i;
+	v->counter = temp;
+	atomic_ops_unlock(flags);
+
+	return temp;
+}
+
+static inline void atomic_clear_mask(unsigned long mask, unsigned long *addr)
+{
+	unsigned long flags;
+
+	atomic_ops_lock(flags);
+	*addr &= ~mask;
+	atomic_ops_unlock(flags);
+}
+
+#endif /* !CONFIG_ARC_HAS_LLSC */
+
+/**
+ * __atomic_add_unless - add unless the number is a given value
+ * @v: pointer of type atomic_t
+ * @a: the amount to add to v...
+ * @u: ...unless v is equal to u.
+ *
+ * Atomically adds @a to @v, so long as it was not @u.
+ * Returns the old value of @v
+ */
+#define __atomic_add_unless(v, a, u)					\
+({									\
+	int c, old;							\
+	c = atomic_read(v);						\
+	while (c != (u) && (old = atomic_cmpxchg((v), c, c + (a))) != c)\
+		c = old;						\
+	c;								\
+})
+
+#define atomic_inc_not_zero(v)		atomic_add_unless((v), 1, 0)
+
+#define atomic_inc(v)			atomic_add(1, v)
+#define atomic_dec(v)			atomic_sub(1, v)
+
+#define atomic_inc_and_test(v)		(atomic_add_return(1, v) == 0)
+#define atomic_dec_and_test(v)		(atomic_sub_return(1, v) == 0)
+#define atomic_inc_return(v)		atomic_add_return(1, (v))
+#define atomic_dec_return(v)		atomic_sub_return(1, (v))
+#define atomic_sub_and_test(i, v)	(atomic_sub_return(i, v) == 0)
+
+#define atomic_add_negative(i, v)	(atomic_add_return(i, v) < 0)
+
+#define ATOMIC_INIT(i)			{ (i) }
+
+#include <asm-generic/atomic64.h>
+
+#endif
+
+#endif
+
+#endif
diff --git a/arch/arc/include/asm/barrier.h b/arch/arc/include/asm/barrier.h
new file mode 100644
index 000000000000..f6cb7c4ffb35
--- /dev/null
+++ b/arch/arc/include/asm/barrier.h
@@ -0,0 +1,42 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ASM_BARRIER_H
+#define __ASM_BARRIER_H
+
+#ifndef __ASSEMBLY__
+
+/* TODO-vineetg: Need to see what this does, don't we need sync anywhere */
+#define mb() __asm__ __volatile__ ("" : : : "memory")
+#define rmb() mb()
+#define wmb() mb()
+#define set_mb(var, value)  do { var = value; mb(); } while (0)
+#define set_wmb(var, value) do { var = value; wmb(); } while (0)
+#define read_barrier_depends()  mb()
+
+/* TODO-vineetg verify the correctness of macros here */
+#ifdef CONFIG_SMP
+#define smp_mb()        mb()
+#define smp_rmb()       rmb()
+#define smp_wmb()       wmb()
+#else
+#define smp_mb()        barrier()
+#define smp_rmb()       barrier()
+#define smp_wmb()       barrier()
+#endif
+
+#define smp_mb__before_atomic_dec()	barrier()
+#define smp_mb__after_atomic_dec()	barrier()
+#define smp_mb__before_atomic_inc()	barrier()
+#define smp_mb__after_atomic_inc()	barrier()
+
+#define smp_read_barrier_depends()      do { } while (0)
+
+#endif
+
+#endif
diff --git a/arch/arc/include/asm/bitops.h b/arch/arc/include/asm/bitops.h
new file mode 100644
index 000000000000..647a83a8e756
--- /dev/null
+++ b/arch/arc/include/asm/bitops.h
@@ -0,0 +1,516 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_BITOPS_H
+#define _ASM_BITOPS_H
+
+#ifndef _LINUX_BITOPS_H
+#error only <linux/bitops.h> can be included directly
+#endif
+
+#ifdef __KERNEL__
+
+#ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+#include <linux/compiler.h>
+
+/*
+ * Hardware assisted read-modify-write using ARC700 LLOCK/SCOND insns.
+ * The Kconfig glue ensures that in SMP, this is only set if the container
+ * SoC/platform has cross-core coherent LLOCK/SCOND
+ */
+#if defined(CONFIG_ARC_HAS_LLSC)
+
+static inline void set_bit(unsigned long nr, volatile unsigned long *m)
+{
+	unsigned int temp;
+
+	m += nr >> 5;
+
+	if (__builtin_constant_p(nr))
+		nr &= 0x1f;
+
+	__asm__ __volatile__(
+	"1:	llock   %0, [%1]	\n"
+	"	bset    %0, %0, %2	\n"
+	"	scond   %0, [%1]	\n"
+	"	bnz     1b	\n"
+	: "=&r"(temp)
+	: "r"(m), "ir"(nr)
+	: "cc");
+}
+
+static inline void clear_bit(unsigned long nr, volatile unsigned long *m)
+{
+	unsigned int temp;
+
+	m += nr >> 5;
+
+	if (__builtin_constant_p(nr))
+		nr &= 0x1f;
+
+	__asm__ __volatile__(
+	"1:	llock   %0, [%1]	\n"
+	"	bclr    %0, %0, %2	\n"
+	"	scond   %0, [%1]	\n"
+	"	bnz     1b	\n"
+	: "=&r"(temp)
+	: "r"(m), "ir"(nr)
+	: "cc");
+}
+
+static inline void change_bit(unsigned long nr, volatile unsigned long *m)
+{
+	unsigned int temp;
+
+	m += nr >> 5;
+
+	if (__builtin_constant_p(nr))
+		nr &= 0x1f;
+
+	__asm__ __volatile__(
+	"1:	llock   %0, [%1]	\n"
+	"	bxor    %0, %0, %2	\n"
+	"	scond   %0, [%1]	\n"
+	"	bnz     1b		\n"
+	: "=&r"(temp)
+	: "r"(m), "ir"(nr)
+	: "cc");
+}
+
+/*
+ * Semantically:
+ *    Test the bit
+ *    if clear
+ *        set it and return 0 (old value)
+ *    else
+ *        return 1 (old value).
+ *
+ * Since ARC lacks a equivalent h/w primitive, the bit is set unconditionally
+ * and the old value of bit is returned
+ */
+static inline int test_and_set_bit(unsigned long nr, volatile unsigned long *m)
+{
+	unsigned long old, temp;
+
+	m += nr >> 5;
+
+	if (__builtin_constant_p(nr))
+		nr &= 0x1f;
+
+	__asm__ __volatile__(
+	"1:	llock   %0, [%2]	\n"
+	"	bset    %1, %0, %3	\n"
+	"	scond   %1, [%2]	\n"
+	"	bnz     1b		\n"
+	: "=&r"(old), "=&r"(temp)
+	: "r"(m), "ir"(nr)
+	: "cc");
+
+	return (old & (1 << nr)) != 0;
+}
+
+static inline int
+test_and_clear_bit(unsigned long nr, volatile unsigned long *m)
+{
+	unsigned int old, temp;
+
+	m += nr >> 5;
+
+	if (__builtin_constant_p(nr))
+		nr &= 0x1f;
+
+	__asm__ __volatile__(
+	"1:	llock   %0, [%2]	\n"
+	"	bclr    %1, %0, %3	\n"
+	"	scond   %1, [%2]	\n"
+	"	bnz     1b		\n"
+	: "=&r"(old), "=&r"(temp)
+	: "r"(m), "ir"(nr)
+	: "cc");
+
+	return (old & (1 << nr)) != 0;
+}
+
+static inline int
+test_and_change_bit(unsigned long nr, volatile unsigned long *m)
+{
+	unsigned int old, temp;
+
+	m += nr >> 5;
+
+	if (__builtin_constant_p(nr))
+		nr &= 0x1f;
+
+	__asm__ __volatile__(
+	"1:	llock   %0, [%2]	\n"
+	"	bxor    %1, %0, %3	\n"
+	"	scond   %1, [%2]	\n"
+	"	bnz     1b		\n"
+	: "=&r"(old), "=&r"(temp)
+	: "r"(m), "ir"(nr)
+	: "cc");
+
+	return (old & (1 << nr)) != 0;
+}
+
+#else	/* !CONFIG_ARC_HAS_LLSC */
+
+#include <asm/smp.h>
+
+/*
+ * Non hardware assisted Atomic-R-M-W
+ * Locking would change to irq-disabling only (UP) and spinlocks (SMP)
+ *
+ * There's "significant" micro-optimization in writing our own variants of
+ * bitops (over generic variants)
+ *
+ * (1) The generic APIs have "signed" @nr while we have it "unsigned"
+ *     This avoids extra code to be generated for pointer arithmatic, since
+ *     is "not sure" that index is NOT -ve
+ * (2) Utilize the fact that ARCompact bit fidding insn (BSET/BCLR/ASL) etc
+ *     only consider bottom 5 bits of @nr, so NO need to mask them off.
+ *     (GCC Quirk: however for constant @nr we still need to do the masking
+ *             at compile time)
+ */
+
+static inline void set_bit(unsigned long nr, volatile unsigned long *m)
+{
+	unsigned long temp, flags;
+	m += nr >> 5;
+
+	if (__builtin_constant_p(nr))
+		nr &= 0x1f;
+
+	bitops_lock(flags);
+
+	temp = *m;
+	*m = temp | (1UL << nr);
+
+	bitops_unlock(flags);
+}
+
+static inline void clear_bit(unsigned long nr, volatile unsigned long *m)
+{
+	unsigned long temp, flags;
+	m += nr >> 5;
+
+	if (__builtin_constant_p(nr))
+		nr &= 0x1f;
+
+	bitops_lock(flags);
+
+	temp = *m;
+	*m = temp & ~(1UL << nr);
+
+	bitops_unlock(flags);
+}
+
+static inline void change_bit(unsigned long nr, volatile unsigned long *m)
+{
+	unsigned long temp, flags;
+	m += nr >> 5;
+
+	if (__builtin_constant_p(nr))
+		nr &= 0x1f;
+
+	bitops_lock(flags);
+
+	temp = *m;
+	*m = temp ^ (1UL << nr);
+
+	bitops_unlock(flags);
+}
+
+static inline int test_and_set_bit(unsigned long nr, volatile unsigned long *m)
+{
+	unsigned long old, flags;
+	m += nr >> 5;
+
+	if (__builtin_constant_p(nr))
+		nr &= 0x1f;
+
+	bitops_lock(flags);
+
+	old = *m;
+	*m = old | (1 << nr);
+
+	bitops_unlock(flags);
+
+	return (old & (1 << nr)) != 0;
+}
+
+static inline int
+test_and_clear_bit(unsigned long nr, volatile unsigned long *m)
+{
+	unsigned long old, flags;
+	m += nr >> 5;
+
+	if (__builtin_constant_p(nr))
+		nr &= 0x1f;
+
+	bitops_lock(flags);
+
+	old = *m;
+	*m = old & ~(1 << nr);
+
+	bitops_unlock(flags);
+
+	return (old & (1 << nr)) != 0;
+}
+
+static inline int
+test_and_change_bit(unsigned long nr, volatile unsigned long *m)
+{
+	unsigned long old, flags;
+	m += nr >> 5;
+
+	if (__builtin_constant_p(nr))
+		nr &= 0x1f;
+
+	bitops_lock(flags);
+
+	old = *m;
+	*m = old ^ (1 << nr);
+
+	bitops_unlock(flags);
+
+	return (old & (1 << nr)) != 0;
+}
+
+#endif /* CONFIG_ARC_HAS_LLSC */
+
+/***************************************
+ * Non atomic variants
+ **************************************/
+
+static inline void __set_bit(unsigned long nr, volatile unsigned long *m)
+{
+	unsigned long temp;
+	m += nr >> 5;
+
+	if (__builtin_constant_p(nr))
+		nr &= 0x1f;
+
+	temp = *m;
+	*m = temp | (1UL << nr);
+}
+
+static inline void __clear_bit(unsigned long nr, volatile unsigned long *m)
+{
+	unsigned long temp;
+	m += nr >> 5;
+
+	if (__builtin_constant_p(nr))
+		nr &= 0x1f;
+
+	temp = *m;
+	*m = temp & ~(1UL << nr);
+}
+
+static inline void __change_bit(unsigned long nr, volatile unsigned long *m)
+{
+	unsigned long temp;
+	m += nr >> 5;
+
+	if (__builtin_constant_p(nr))
+		nr &= 0x1f;
+
+	temp = *m;
+	*m = temp ^ (1UL << nr);
+}
+
+static inline int
+__test_and_set_bit(unsigned long nr, volatile unsigned long *m)
+{
+	unsigned long old;
+	m += nr >> 5;
+
+	if (__builtin_constant_p(nr))
+		nr &= 0x1f;
+
+	old = *m;
+	*m = old | (1 << nr);
+
+	return (old & (1 << nr)) != 0;
+}
+
+static inline int
+__test_and_clear_bit(unsigned long nr, volatile unsigned long *m)
+{
+	unsigned long old;
+	m += nr >> 5;
+
+	if (__builtin_constant_p(nr))
+		nr &= 0x1f;
+
+	old = *m;
+	*m = old & ~(1 << nr);
+
+	return (old & (1 << nr)) != 0;
+}
+
+static inline int
+__test_and_change_bit(unsigned long nr, volatile unsigned long *m)
+{
+	unsigned long old;
+	m += nr >> 5;
+
+	if (__builtin_constant_p(nr))
+		nr &= 0x1f;
+
+	old = *m;
+	*m = old ^ (1 << nr);
+
+	return (old & (1 << nr)) != 0;
+}
+
+/*
+ * This routine doesn't need to be atomic.
+ */
+static inline int
+__constant_test_bit(unsigned int nr, const volatile unsigned long *addr)
+{
+	return ((1UL << (nr & 31)) &
+		(((const volatile unsigned int *)addr)[nr >> 5])) != 0;
+}
+
+static inline int
+__test_bit(unsigned int nr, const volatile unsigned long *addr)
+{
+	unsigned long mask;
+
+	addr += nr >> 5;
+
+	/* ARC700 only considers 5 bits in bit-fiddling insn */
+	mask = 1 << nr;
+
+	return ((mask & *addr) != 0);
+}
+
+#define test_bit(nr, addr)	(__builtin_constant_p(nr) ? \
+					__constant_test_bit((nr), (addr)) : \
+					__test_bit((nr), (addr)))
+
+/*
+ * Count the number of zeros, starting from MSB
+ * Helper for fls( ) friends
+ * This is a pure count, so (1-32) or (0-31) doesn't apply
+ * It could be 0 to 32, based on num of 0's in there
+ * clz(0x8000_0000) = 0, clz(0xFFFF_FFFF)=0, clz(0) = 32, clz(1) = 31
+ */
+static inline __attribute__ ((const)) int clz(unsigned int x)
+{
+	unsigned int res;
+
+	__asm__ __volatile__(
+	"	norm.f  %0, %1		\n"
+	"	mov.n   %0, 0		\n"
+	"	add.p   %0, %0, 1	\n"
+	: "=r"(res)
+	: "r"(x)
+	: "cc");
+
+	return res;
+}
+
+static inline int constant_fls(int x)
+{
+	int r = 32;
+
+	if (!x)
+		return 0;
+	if (!(x & 0xffff0000u)) {
+		x <<= 16;
+		r -= 16;
+	}
+	if (!(x & 0xff000000u)) {
+		x <<= 8;
+		r -= 8;
+	}
+	if (!(x & 0xf0000000u)) {
+		x <<= 4;
+		r -= 4;
+	}
+	if (!(x & 0xc0000000u)) {
+		x <<= 2;
+		r -= 2;
+	}
+	if (!(x & 0x80000000u)) {
+		x <<= 1;
+		r -= 1;
+	}
+	return r;
+}
+
+/*
+ * fls = Find Last Set in word
+ * @result: [1-32]
+ * fls(1) = 1, fls(0x80000000) = 32, fls(0) = 0
+ */
+static inline __attribute__ ((const)) int fls(unsigned long x)
+{
+	if (__builtin_constant_p(x))
+	       return constant_fls(x);
+
+	return 32 - clz(x);
+}
+
+/*
+ * __fls: Similar to fls, but zero based (0-31)
+ */
+static inline __attribute__ ((const)) int __fls(unsigned long x)
+{
+	if (!x)
+		return 0;
+	else
+		return fls(x) - 1;
+}
+
+/*
+ * ffs = Find First Set in word (LSB to MSB)
+ * @result: [1-32], 0 if all 0's
+ */
+#define ffs(x)	({ unsigned long __t = (x); fls(__t & -__t); })
+
+/*
+ * __ffs: Similar to ffs, but zero based (0-31)
+ */
+static inline __attribute__ ((const)) int __ffs(unsigned long word)
+{
+	if (!word)
+		return word;
+
+	return ffs(word) - 1;
+}
+
+/*
+ * ffz = Find First Zero in word.
+ * @return:[0-31], 32 if all 1's
+ */
+#define ffz(x)	__ffs(~(x))
+
+/* TODO does this affect uni-processor code */
+#define smp_mb__before_clear_bit()  barrier()
+#define smp_mb__after_clear_bit()   barrier()
+
+#include <asm-generic/bitops/hweight.h>
+#include <asm-generic/bitops/fls64.h>
+#include <asm-generic/bitops/sched.h>
+#include <asm-generic/bitops/lock.h>
+
+#include <asm-generic/bitops/find.h>
+#include <asm-generic/bitops/le.h>
+#include <asm-generic/bitops/ext2-atomic-setbit.h>
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* __KERNEL__ */
+
+#endif
diff --git a/arch/arc/include/asm/bug.h b/arch/arc/include/asm/bug.h
new file mode 100644
index 000000000000..2ad8f9b1c54b
--- /dev/null
+++ b/arch/arc/include/asm/bug.h
@@ -0,0 +1,37 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_ARC_BUG_H
+#define _ASM_ARC_BUG_H
+
+#ifndef __ASSEMBLY__
+
+#include <asm/ptrace.h>
+
+struct task_struct;
+
+void show_regs(struct pt_regs *regs);
+void show_stacktrace(struct task_struct *tsk, struct pt_regs *regs);
+void show_kernel_fault_diag(const char *str, struct pt_regs *regs,
+			    unsigned long address, unsigned long cause_reg);
+void die(const char *str, struct pt_regs *regs, unsigned long address,
+	 unsigned long cause_reg);
+
+#define BUG()	do {				\
+	dump_stack();					\
+	pr_warn("Kernel BUG in %s: %s: %d!\n",	\
+		__FILE__, __func__,  __LINE__);	\
+} while (0)
+
+#define HAVE_ARCH_BUG
+
+#include <asm-generic/bug.h>
+
+#endif	/* !__ASSEMBLY__ */
+
+#endif
diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h
new file mode 100644
index 000000000000..6632273861fd
--- /dev/null
+++ b/arch/arc/include/asm/cache.h
@@ -0,0 +1,75 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ARC_ASM_CACHE_H
+#define __ARC_ASM_CACHE_H
+
+/* In case $$ not config, setup a dummy number for rest of kernel */
+#ifndef CONFIG_ARC_CACHE_LINE_SHIFT
+#define L1_CACHE_SHIFT		6
+#else
+#define L1_CACHE_SHIFT		CONFIG_ARC_CACHE_LINE_SHIFT
+#endif
+
+#define L1_CACHE_BYTES		(1 << L1_CACHE_SHIFT)
+
+#define ARC_ICACHE_WAYS	2
+#define ARC_DCACHE_WAYS	4
+
+/* Helpers */
+#define ARC_ICACHE_LINE_LEN	L1_CACHE_BYTES
+#define ARC_DCACHE_LINE_LEN	L1_CACHE_BYTES
+
+#define ICACHE_LINE_MASK	(~(ARC_ICACHE_LINE_LEN - 1))
+#define DCACHE_LINE_MASK	(~(ARC_DCACHE_LINE_LEN - 1))
+
+#if ARC_ICACHE_LINE_LEN != ARC_DCACHE_LINE_LEN
+#error "Need to fix some code as I/D cache lines not same"
+#else
+#define is_not_cache_aligned(p)	((unsigned long)p & (~DCACHE_LINE_MASK))
+#endif
+
+#ifndef __ASSEMBLY__
+
+/* Uncached access macros */
+#define arc_read_uncached_32(ptr)	\
+({					\
+	unsigned int __ret;		\
+	__asm__ __volatile__(		\
+	"	ld.di %0, [%1]	\n"	\
+	: "=r"(__ret)			\
+	: "r"(ptr));			\
+	__ret;				\
+})
+
+#define arc_write_uncached_32(ptr, data)\
+({					\
+	__asm__ __volatile__(		\
+	"	st.di %0, [%1]	\n"	\
+	:				\
+	: "r"(data), "r"(ptr));		\
+})
+
+/* used to give SHMLBA a value to avoid Cache Aliasing */
+extern unsigned int ARC_shmlba;
+
+#define ARCH_DMA_MINALIGN      L1_CACHE_BYTES
+
+/*
+ * ARC700 doesn't cache any access in top 256M.
+ * Ideal for wiring memory mapped peripherals as we don't need to do
+ * explicit uncached accesses (LD.di/ST.di) hence more portable drivers
+ */
+#define ARC_UNCACHED_ADDR_SPACE	0xc0000000
+
+extern void arc_cache_init(void);
+extern char *arc_cache_mumbojumbo(int cpu_id, char *buf, int len);
+extern void __init read_decode_cache_bcr(void);
+#endif
+
+#endif /* _ASM_CACHE_H */
diff --git a/arch/arc/include/asm/cacheflush.h b/arch/arc/include/asm/cacheflush.h
new file mode 100644
index 000000000000..97ee96f26505
--- /dev/null
+++ b/arch/arc/include/asm/cacheflush.h
@@ -0,0 +1,67 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ *  vineetg: May 2011: for Non-aliasing VIPT D-cache following can be NOPs
+ *   -flush_cache_dup_mm (fork)
+ *   -likewise for flush_cache_mm (exit/execve)
+ *   -likewise for flush_cache_{range,page} (munmap, exit, COW-break)
+ *
+ *  vineetg: April 2008
+ *   -Added a critical CacheLine flush to copy_to_user_page( ) which
+ *     was causing gdbserver to not setup breakpoints consistently
+ */
+
+#ifndef _ASM_CACHEFLUSH_H
+#define _ASM_CACHEFLUSH_H
+
+#include <linux/mm.h>
+
+void flush_cache_all(void);
+
+void flush_icache_range(unsigned long start, unsigned long end);
+void flush_icache_page(struct vm_area_struct *vma, struct page *page);
+void flush_icache_range_vaddr(unsigned long paddr, unsigned long u_vaddr,
+				     int len);
+
+#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
+
+void flush_dcache_page(struct page *page);
+
+void dma_cache_wback_inv(unsigned long start, unsigned long sz);
+void dma_cache_inv(unsigned long start, unsigned long sz);
+void dma_cache_wback(unsigned long start, unsigned long sz);
+
+#define flush_dcache_mmap_lock(mapping)		do { } while (0)
+#define flush_dcache_mmap_unlock(mapping)	do { } while (0)
+
+/* TBD: optimize this */
+#define flush_cache_vmap(start, end)		flush_cache_all()
+#define flush_cache_vunmap(start, end)		flush_cache_all()
+
+/*
+ * VM callbacks when entire/range of user-space V-P mappings are
+ * torn-down/get-invalidated
+ *
+ * Currently we don't support D$ aliasing configs for our VIPT caches
+ * NOPS for VIPT Cache with non-aliasing D$ configurations only
+ */
+#define flush_cache_dup_mm(mm)			/* called on fork */
+#define flush_cache_mm(mm)			/* called on munmap/exit */
+#define flush_cache_range(mm, u_vstart, u_vend)
+#define flush_cache_page(vma, u_vaddr, pfn)	/* PF handling/COW-break */
+
+#define copy_to_user_page(vma, page, vaddr, dst, src, len)		\
+do {									\
+	memcpy(dst, src, len);						\
+	if (vma->vm_flags & VM_EXEC)					\
+		flush_icache_range_vaddr((unsigned long)(dst), vaddr, len);\
+} while (0)
+
+#define copy_from_user_page(vma, page, vaddr, dst, src, len)		\
+	memcpy(dst, src, len);						\
+
+#endif
diff --git a/arch/arc/include/asm/checksum.h b/arch/arc/include/asm/checksum.h
new file mode 100644
index 000000000000..10957298b7a3
--- /dev/null
+++ b/arch/arc/include/asm/checksum.h
@@ -0,0 +1,101 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Joern Rennecke  <joern.rennecke@embecosm.com>: Jan 2012
+ *  -Insn Scheduling improvements to csum core routines.
+ *      = csum_fold( ) largely derived from ARM version.
+ *      = ip_fast_cum( ) to have module scheduling
+ *  -gcc 4.4.x broke networking. Alias analysis needed to be primed.
+ *   worked around by adding memory clobber to ip_fast_csum( )
+ *
+ * vineetg: May 2010
+ *  -Rewrote ip_fast_cscum( ) and csum_fold( ) with fast inline asm
+ */
+
+#ifndef _ASM_ARC_CHECKSUM_H
+#define _ASM_ARC_CHECKSUM_H
+
+/*
+ *	Fold a partial checksum
+ *
+ *  The 2 swords comprising the 32bit sum are added, any carry to 16th bit
+ *  added back and final sword result inverted.
+ */
+static inline __sum16 csum_fold(__wsum s)
+{
+	unsigned r = s << 16 | s >> 16;	/* ror */
+	s = ~s;
+	s -= r;
+	return s >> 16;
+}
+
+/*
+ *	This is a version of ip_compute_csum() optimized for IP headers,
+ *	which always checksum on 4 octet boundaries.
+ */
+static inline __sum16
+ip_fast_csum(const void *iph, unsigned int ihl)
+{
+	const void *ptr = iph;
+	unsigned int tmp, tmp2, sum;
+
+	__asm__(
+	"	ld.ab  %0, [%3, 4]		\n"
+	"	ld.ab  %2, [%3, 4]		\n"
+	"	sub    %1, %4, 2		\n"
+	"	lsr.f  lp_count, %1, 1		\n"
+	"	bcc    0f			\n"
+	"	add.f  %0, %0, %2		\n"
+	"	ld.ab  %2, [%3, 4]		\n"
+	"0:	lp     1f			\n"
+	"	ld.ab  %1, [%3, 4]		\n"
+	"	adc.f  %0, %0, %2		\n"
+	"	ld.ab  %2, [%3, 4]		\n"
+	"	adc.f  %0, %0, %1		\n"
+	"1:	adc.f  %0, %0, %2		\n"
+	"	add.cs %0,%0,1			\n"
+	: "=&r"(sum), "=r"(tmp), "=&r"(tmp2), "+&r" (ptr)
+	: "r"(ihl)
+	: "cc", "lp_count", "memory");
+
+	return csum_fold(sum);
+}
+
+/*
+ * TCP pseudo Header is 12 bytes:
+ * SA [4], DA [4], zeroes [1], Proto[1], TCP Seg(hdr+data) Len [2]
+ */
+static inline __wsum
+csum_tcpudp_nofold(__be32 saddr, __be32 daddr, unsigned short len,
+		   unsigned short proto, __wsum sum)
+{
+	__asm__ __volatile__(
+	"	add.f %0, %0, %1	\n"
+	"	adc.f %0, %0, %2	\n"
+	"	adc.f %0, %0, %3	\n"
+	"	adc.f %0, %0, %4	\n"
+	"	adc   %0, %0, 0		\n"
+	: "+&r"(sum)
+	: "r"(saddr), "r"(daddr),
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	  "r"(len),
+#else
+	  "r"(len << 8),
+#endif
+	  "r"(htons(proto))
+	: "cc");
+
+	return sum;
+}
+
+#define csum_fold csum_fold
+#define ip_fast_csum ip_fast_csum
+#define csum_tcpudp_nofold csum_tcpudp_nofold
+
+#include <asm-generic/checksum.h>
+
+#endif /* _ASM_ARC_CHECKSUM_H */
diff --git a/arch/arc/include/asm/clk.h b/arch/arc/include/asm/clk.h
new file mode 100644
index 000000000000..bf9d29f5bd53
--- /dev/null
+++ b/arch/arc/include/asm/clk.h
@@ -0,0 +1,22 @@
+/*
+ * Copyright (C) 2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_ARC_CLK_H
+#define _ASM_ARC_CLK_H
+
+/* Although we can't really hide core_freq, the accessor is still better way */
+extern unsigned long core_freq;
+
+static inline unsigned long arc_get_core_freq(void)
+{
+	return core_freq;
+}
+
+extern int arc_set_core_freq(unsigned long);
+
+#endif
diff --git a/arch/arc/include/asm/cmpxchg.h b/arch/arc/include/asm/cmpxchg.h
new file mode 100644
index 000000000000..03cd6894855d
--- /dev/null
+++ b/arch/arc/include/asm/cmpxchg.h
@@ -0,0 +1,143 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ASM_ARC_CMPXCHG_H
+#define __ASM_ARC_CMPXCHG_H
+
+#include <linux/types.h>
+#include <asm/smp.h>
+
+#ifdef CONFIG_ARC_HAS_LLSC
+
+static inline unsigned long
+__cmpxchg(volatile void *ptr, unsigned long expected, unsigned long new)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__(
+	"1:	llock   %0, [%1]	\n"
+	"	brne    %0, %2, 2f	\n"
+	"	scond   %3, [%1]	\n"
+	"	bnz     1b		\n"
+	"2:				\n"
+	: "=&r"(prev)
+	: "r"(ptr), "ir"(expected),
+	  "r"(new) /* can't be "ir". scond can't take limm for "b" */
+	: "cc");
+
+	return prev;
+}
+
+#else
+
+static inline unsigned long
+__cmpxchg(volatile void *ptr, unsigned long expected, unsigned long new)
+{
+	unsigned long flags;
+	int prev;
+	volatile unsigned long *p = ptr;
+
+	atomic_ops_lock(flags);
+	prev = *p;
+	if (prev == expected)
+		*p = new;
+	atomic_ops_unlock(flags);
+	return prev;
+}
+
+#endif /* CONFIG_ARC_HAS_LLSC */
+
+#define cmpxchg(ptr, o, n) ((typeof(*(ptr)))__cmpxchg((ptr), \
+				(unsigned long)(o), (unsigned long)(n)))
+
+/*
+ * Since not supported natively, ARC cmpxchg() uses atomic_ops_lock (UP/SMP)
+ * just to gaurantee semantics.
+ * atomic_cmpxchg() needs to use the same locks as it's other atomic siblings
+ * which also happens to be atomic_ops_lock.
+ *
+ * Thus despite semantically being different, implementation of atomic_cmpxchg()
+ * is same as cmpxchg().
+ */
+#define atomic_cmpxchg(v, o, n) ((int)cmpxchg(&((v)->counter), (o), (n)))
+
+
+/*
+ * xchg (reg with memory) based on "Native atomic" EX insn
+ */
+static inline unsigned long __xchg(unsigned long val, volatile void *ptr,
+				   int size)
+{
+	extern unsigned long __xchg_bad_pointer(void);
+
+	switch (size) {
+	case 4:
+		__asm__ __volatile__(
+		"	ex  %0, [%1]	\n"
+		: "+r"(val)
+		: "r"(ptr)
+		: "memory");
+
+		return val;
+	}
+	return __xchg_bad_pointer();
+}
+
+#define _xchg(ptr, with) ((typeof(*(ptr)))__xchg((unsigned long)(with), (ptr), \
+						 sizeof(*(ptr))))
+
+/*
+ * On ARC700, EX insn is inherently atomic, so by default "vanilla" xchg() need
+ * not require any locking. However there's a quirk.
+ * ARC lacks native CMPXCHG, thus emulated (see above), using external locking -
+ * incidently it "reuses" the same atomic_ops_lock used by atomic APIs.
+ * Now, llist code uses cmpxchg() and xchg() on same data, so xchg() needs to
+ * abide by same serializing rules, thus ends up using atomic_ops_lock as well.
+ *
+ * This however is only relevant if SMP and/or ARC lacks LLSC
+ *   if (UP or LLSC)
+ *      xchg doesn't need serialization
+ *   else <==> !(UP or LLSC) <==> (!UP and !LLSC) <==> (SMP and !LLSC)
+ *      xchg needs serialization
+ */
+
+#if !defined(CONFIG_ARC_HAS_LLSC) && defined(CONFIG_SMP)
+
+#define xchg(ptr, with)			\
+({					\
+	unsigned long flags;		\
+	typeof(*(ptr)) old_val;		\
+					\
+	atomic_ops_lock(flags);		\
+	old_val = _xchg(ptr, with);	\
+	atomic_ops_unlock(flags);	\
+	old_val;			\
+})
+
+#else
+
+#define xchg(ptr, with)  _xchg(ptr, with)
+
+#endif
+
+/*
+ * "atomic" variant of xchg()
+ * REQ: It needs to follow the same serialization rules as other atomic_xxx()
+ * Since xchg() doesn't always do that, it would seem that following defintion
+ * is incorrect. But here's the rationale:
+ *   SMP : Even xchg() takes the atomic_ops_lock, so OK.
+ *   LLSC: atomic_ops_lock are not relevent at all (even if SMP, since LLSC
+ *         is natively "SMP safe", no serialization required).
+ *   UP  : other atomics disable IRQ, so no way a difft ctxt atomic_xchg()
+ *         could clobber them. atomic_xchg() itself would be 1 insn, so it
+ *         can't be clobbered by others. Thus no serialization required when
+ *         atomic_xchg is involved.
+ */
+#define atomic_xchg(v, new) (xchg(&((v)->counter), new))
+
+#endif
diff --git a/arch/arc/include/asm/current.h b/arch/arc/include/asm/current.h
new file mode 100644
index 000000000000..87b918585c4a
--- /dev/null
+++ b/arch/arc/include/asm/current.h
@@ -0,0 +1,32 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Vineetg: May 16th, 2008
+ *  - Current macro is now implemented as "global register" r25
+ */
+
+#ifndef _ASM_ARC_CURRENT_H
+#define _ASM_ARC_CURRENT_H
+
+#ifdef __KERNEL__
+
+#ifndef __ASSEMBLY__
+
+#ifdef CONFIG_ARC_CURR_IN_REG
+
+register struct task_struct *curr_arc asm("r25");
+#define current (curr_arc)
+
+#else
+#include <asm-generic/current.h>
+#endif /* ! CONFIG_ARC_CURR_IN_REG */
+
+#endif /* ! __ASSEMBLY__ */
+
+#endif	/* __KERNEL__ */
+
+#endif /* _ASM_ARC_CURRENT_H */
diff --git a/arch/arc/include/asm/defines.h b/arch/arc/include/asm/defines.h
new file mode 100644
index 000000000000..6097bb439cc5
--- /dev/null
+++ b/arch/arc/include/asm/defines.h
@@ -0,0 +1,56 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ARC_ASM_DEFINES_H__
+#define __ARC_ASM_DEFINES_H__
+
+#if defined(CONFIG_ARC_MMU_V1)
+#define CONFIG_ARC_MMU_VER 1
+#elif defined(CONFIG_ARC_MMU_V2)
+#define CONFIG_ARC_MMU_VER 2
+#elif defined(CONFIG_ARC_MMU_V3)
+#define CONFIG_ARC_MMU_VER 3
+#endif
+
+#ifdef CONFIG_ARC_HAS_LLSC
+#define __CONFIG_ARC_HAS_LLSC_VAL 1
+#else
+#define __CONFIG_ARC_HAS_LLSC_VAL 0
+#endif
+
+#ifdef CONFIG_ARC_HAS_SWAPE
+#define __CONFIG_ARC_HAS_SWAPE_VAL 1
+#else
+#define __CONFIG_ARC_HAS_SWAPE_VAL 0
+#endif
+
+#ifdef CONFIG_ARC_HAS_RTSC
+#define __CONFIG_ARC_HAS_RTSC_VAL 1
+#else
+#define __CONFIG_ARC_HAS_RTSC_VAL 0
+#endif
+
+#ifdef CONFIG_ARC_MMU_SASID
+#define __CONFIG_ARC_MMU_SASID_VAL 1
+#else
+#define __CONFIG_ARC_MMU_SASID_VAL 0
+#endif
+
+#ifdef CONFIG_ARC_HAS_ICACHE
+#define __CONFIG_ARC_HAS_ICACHE	1
+#else
+#define __CONFIG_ARC_HAS_ICACHE	0
+#endif
+
+#ifdef CONFIG_ARC_HAS_DCACHE
+#define __CONFIG_ARC_HAS_DCACHE	1
+#else
+#define __CONFIG_ARC_HAS_DCACHE	0
+#endif
+
+#endif /* __ARC_ASM_DEFINES_H__ */
diff --git a/arch/arc/include/asm/delay.h b/arch/arc/include/asm/delay.h
new file mode 100644
index 000000000000..442ce5d0f709
--- /dev/null
+++ b/arch/arc/include/asm/delay.h
@@ -0,0 +1,68 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Delay routines using pre computed loops_per_jiffy value.
+ *
+ * vineetg: Feb 2012
+ *  -Rewrote in "C" to avoid dealing with availability of H/w MPY
+ *  -Also reduced the num of MPY operations from 3 to 2
+ *
+ * Amit Bhor: Codito Technologies 2004
+ */
+
+#ifndef __ASM_ARC_UDELAY_H
+#define __ASM_ARC_UDELAY_H
+
+#include <asm/param.h>		/* HZ */
+
+static inline void __delay(unsigned long loops)
+{
+	__asm__ __volatile__(
+	"1:	sub.f %0, %0, 1	\n"
+	"	jpnz 1b		\n"
+	: "+r"(loops)
+	:
+	: "cc");
+}
+
+extern void __bad_udelay(void);
+
+/*
+ * Normal Math for computing loops in "N" usecs
+ *  -we have precomputed @loops_per_jiffy
+ *  -1 sec has HZ jiffies
+ * loops per "N" usecs = ((loops_per_jiffy * HZ / 1000000) * N)
+ *
+ * Approximate Division by multiplication:
+ *  -Mathematically if we multiply and divide a number by same value the
+ *   result remains unchanged:  In this case, we use 2^32
+ *  -> (loops_per_N_usec * 2^32 ) / 2^32
+ *  -> (((loops_per_jiffy * HZ / 1000000) * N) * 2^32) / 2^32
+ *  -> (loops_per_jiffy * HZ * N * 4295) / 2^32
+ *
+ *  -Divide by 2^32 is very simply right shift by 32
+ *  -We simply need to ensure that the multiply per above eqn happens in
+ *   64-bit precision (if CPU doesn't support it - gcc can emaulate it)
+ */
+
+static inline void __udelay(unsigned long usecs)
+{
+	unsigned long loops;
+
+	/* (long long) cast ensures 64 bit MPY - real or emulated
+	 * HZ * 4295 is pre-evaluated by gcc - hence only 2 mpy ops
+	 */
+	loops = ((long long)(usecs * 4295 * HZ) *
+		 (long long)(loops_per_jiffy)) >> 32;
+
+	__delay(loops);
+}
+
+#define udelay(n) (__builtin_constant_p(n) ? ((n) > 20000 ? __bad_udelay() \
+				: __udelay(n)) : __udelay(n))
+
+#endif /* __ASM_ARC_UDELAY_H */
diff --git a/arch/arc/include/asm/disasm.h b/arch/arc/include/asm/disasm.h
new file mode 100644
index 000000000000..f1cce3d059a1
--- /dev/null
+++ b/arch/arc/include/asm/disasm.h
@@ -0,0 +1,116 @@
+/*
+ * several functions that help interpret ARC instructions
+ * used for unaligned accesses, kprobes and kgdb
+ *
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ARC_DISASM_H__
+#define __ARC_DISASM_H__
+
+enum {
+	op_Bcc = 0, op_BLcc = 1, op_LD = 2, op_ST = 3, op_MAJOR_4 = 4,
+	op_MAJOR_5 = 5, op_LD_ADD = 12, op_ADD_SUB_SHIFT = 13,
+	op_ADD_MOV_CMP = 14, op_S = 15, op_LD_S = 16, op_LDB_S = 17,
+	op_LDW_S = 18, op_LDWX_S = 19, op_ST_S = 20, op_STB_S = 21,
+	op_STW_S = 22, op_Su5 = 23, op_SP = 24, op_GP = 25,
+	op_Pcl = 26, op_MOV_S = 27, op_ADD_CMP = 28, op_BR_S = 29,
+	op_B_S = 30, op_BL_S = 31
+};
+
+enum flow {
+	noflow,
+	direct_jump,
+	direct_call,
+	indirect_jump,
+	indirect_call,
+	invalid_instr
+};
+
+#define IS_BIT(word, n)		((word) & (1<<n))
+#define BITS(word, s, e)	(((word) >> (s)) & (~((-2) << ((e) - (s)))))
+
+#define MAJOR_OPCODE(word)	(BITS((word), 27, 31))
+#define MINOR_OPCODE(word)	(BITS((word), 16, 21))
+#define FIELD_A(word)		(BITS((word), 0, 5))
+#define FIELD_B(word)		((BITS((word), 12, 14)<<3) | \
+				(BITS((word), 24, 26)))
+#define FIELD_C(word)		(BITS((word), 6, 11))
+#define FIELD_u6(word)		FIELDC(word)
+#define FIELD_s12(word)		sign_extend(((BITS((word), 0, 5) << 6) | \
+					BITS((word), 6, 11)), 12)
+
+/* note that for BL/BRcc these two macro's need another AND statement to mask
+ * out bit 1 (make the result a multiple of 4) */
+#define FIELD_s9(word)		sign_extend(((BITS(word, 15, 15) << 8) | \
+					BITS(word, 16, 23)), 9)
+#define FIELD_s21(word)		sign_extend(((BITS(word, 6, 15) << 11) | \
+					(BITS(word, 17, 26) << 1)), 12)
+#define FIELD_s25(word)		sign_extend(((BITS(word, 0, 3) << 21) | \
+					(BITS(word, 6, 15) << 11) | \
+					(BITS(word, 17, 26) << 1)), 12)
+
+/* note: these operate on 16 bits! */
+#define FIELD_S_A(word)		((BITS((word), 2, 2)<<3) | BITS((word), 0, 2))
+#define FIELD_S_B(word)		((BITS((word), 10, 10)<<3) | \
+				BITS((word), 8, 10))
+#define FIELD_S_C(word)		((BITS((word), 7, 7)<<3) | BITS((word), 5, 7))
+#define FIELD_S_H(word)		((BITS((word), 0, 2)<<3) | BITS((word), 5, 8))
+#define FIELD_S_u5(word)	(BITS((word), 0, 4))
+#define FIELD_S_u6(word)	(BITS((word), 0, 4) << 1)
+#define FIELD_S_u7(word)	(BITS((word), 0, 4) << 2)
+#define FIELD_S_u10(word)	(BITS((word), 0, 7) << 2)
+#define FIELD_S_s7(word)	sign_extend(BITS((word), 0, 5) << 1, 9)
+#define FIELD_S_s8(word)	sign_extend(BITS((word), 0, 7) << 1, 9)
+#define FIELD_S_s9(word)	sign_extend(BITS((word), 0, 8), 9)
+#define FIELD_S_s10(word)	sign_extend(BITS((word), 0, 8) << 1, 10)
+#define FIELD_S_s11(word)	sign_extend(BITS((word), 0, 8) << 2, 11)
+#define FIELD_S_s13(word)	sign_extend(BITS((word), 0, 10) << 2, 13)
+
+#define STATUS32_L		0x00000100
+#define REG_LIMM		62
+
+struct disasm_state {
+	/* generic info */
+	unsigned long words[2];
+	int instr_len;
+	int major_opcode;
+	/* info for branch/jump */
+	int is_branch;
+	int target;
+	int delay_slot;
+	enum flow flow;
+	/* info for load/store */
+	int src1, src2, src3, dest, wb_reg;
+	int zz, aa, x, pref, di;
+	int fault, write;
+};
+
+static inline int sign_extend(int value, int bits)
+{
+	if (IS_BIT(value, (bits - 1)))
+		value |= (0xffffffff << bits);
+
+	return value;
+}
+
+static inline int is_short_instr(unsigned long addr)
+{
+	uint16_t word = *((uint16_t *)addr);
+	int opcode = (word >> 11) & 0x1F;
+	return (opcode >= 0x0B);
+}
+
+void disasm_instr(unsigned long addr, struct disasm_state *state,
+	int userspace, struct pt_regs *regs, struct callee_regs *cregs);
+int disasm_next_pc(unsigned long pc, struct pt_regs *regs, struct callee_regs
+	*cregs, unsigned long *fall_thru, unsigned long *target);
+long get_reg(int reg, struct pt_regs *regs, struct callee_regs *cregs);
+void set_reg(int reg, long val, struct pt_regs *regs,
+		struct callee_regs *cregs);
+
+#endif	/* __ARC_DISASM_H__ */
diff --git a/arch/arc/include/asm/dma-mapping.h b/arch/arc/include/asm/dma-mapping.h
new file mode 100644
index 000000000000..31f77aec0823
--- /dev/null
+++ b/arch/arc/include/asm/dma-mapping.h
@@ -0,0 +1,221 @@
+/*
+ * DMA Mapping glue for ARC
+ *
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef ASM_ARC_DMA_MAPPING_H
+#define ASM_ARC_DMA_MAPPING_H
+
+#include <asm-generic/dma-coherent.h>
+#include <asm/cacheflush.h>
+
+#ifndef CONFIG_ARC_PLAT_NEEDS_CPU_TO_DMA
+/*
+ * dma_map_* API take cpu addresses, which is kernel logical address in the
+ * untranslated address space (0x8000_0000) based. The dma address (bus addr)
+ * ideally needs to be 0x0000_0000 based hence these glue routines.
+ * However given that intermediate bus bridges can ignore the high bit, we can
+ * do with these routines being no-ops.
+ * If a platform/device comes up which sriclty requires 0 based bus addr
+ * (e.g. AHB-PCI bridge on Angel4 board), then it can provide it's own versions
+ */
+#define plat_dma_addr_to_kernel(dev, addr) ((unsigned long)(addr))
+#define plat_kernel_addr_to_dma(dev, ptr) ((dma_addr_t)(ptr))
+
+#else
+#include <plat/dma_addr.h>
+#endif
+
+void *dma_alloc_noncoherent(struct device *dev, size_t size,
+			    dma_addr_t *dma_handle, gfp_t gfp);
+
+void dma_free_noncoherent(struct device *dev, size_t size, void *vaddr,
+			  dma_addr_t dma_handle);
+
+void *dma_alloc_coherent(struct device *dev, size_t size,
+			 dma_addr_t *dma_handle, gfp_t gfp);
+
+void dma_free_coherent(struct device *dev, size_t size, void *kvaddr,
+		       dma_addr_t dma_handle);
+
+/* drivers/base/dma-mapping.c */
+extern int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
+			   void *cpu_addr, dma_addr_t dma_addr, size_t size);
+extern int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt,
+				  void *cpu_addr, dma_addr_t dma_addr,
+				  size_t size);
+
+#define dma_mmap_coherent(d, v, c, h, s) dma_common_mmap(d, v, c, h, s)
+#define dma_get_sgtable(d, t, v, h, s) dma_common_get_sgtable(d, t, v, h, s)
+
+/*
+ * streaming DMA Mapping API...
+ * CPU accesses page via normal paddr, thus needs to explicitly made
+ * consistent before each use
+ */
+
+static inline void __inline_dma_cache_sync(unsigned long paddr, size_t size,
+					   enum dma_data_direction dir)
+{
+	switch (dir) {
+	case DMA_FROM_DEVICE:
+		dma_cache_inv(paddr, size);
+		break;
+	case DMA_TO_DEVICE:
+		dma_cache_wback(paddr, size);
+		break;
+	case DMA_BIDIRECTIONAL:
+		dma_cache_wback_inv(paddr, size);
+		break;
+	default:
+		pr_err("Invalid DMA dir [%d] for OP @ %lx\n", dir, paddr);
+	}
+}
+
+void __arc_dma_cache_sync(unsigned long paddr, size_t size,
+			  enum dma_data_direction dir);
+
+#define _dma_cache_sync(addr, sz, dir)			\
+do {							\
+	if (__builtin_constant_p(dir))			\
+		__inline_dma_cache_sync(addr, sz, dir);	\
+	else						\
+		__arc_dma_cache_sync(addr, sz, dir);	\
+}							\
+while (0);
+
+static inline dma_addr_t
+dma_map_single(struct device *dev, void *cpu_addr, size_t size,
+	       enum dma_data_direction dir)
+{
+	_dma_cache_sync((unsigned long)cpu_addr, size, dir);
+	return plat_kernel_addr_to_dma(dev, cpu_addr);
+}
+
+static inline void
+dma_unmap_single(struct device *dev, dma_addr_t dma_addr,
+		 size_t size, enum dma_data_direction dir)
+{
+}
+
+static inline dma_addr_t
+dma_map_page(struct device *dev, struct page *page,
+	     unsigned long offset, size_t size,
+	     enum dma_data_direction dir)
+{
+	unsigned long paddr = page_to_phys(page) + offset;
+	return dma_map_single(dev, (void *)paddr, size, dir);
+}
+
+static inline void
+dma_unmap_page(struct device *dev, dma_addr_t dma_handle,
+	       size_t size, enum dma_data_direction dir)
+{
+}
+
+static inline int
+dma_map_sg(struct device *dev, struct scatterlist *sg,
+	   int nents, enum dma_data_direction dir)
+{
+	struct scatterlist *s;
+	int i;
+
+	for_each_sg(sg, s, nents, i)
+		sg->dma_address = dma_map_page(dev, sg_page(s), s->offset,
+					       s->length, dir);
+
+	return nents;
+}
+
+static inline void
+dma_unmap_sg(struct device *dev, struct scatterlist *sg,
+	     int nents, enum dma_data_direction dir)
+{
+	struct scatterlist *s;
+	int i;
+
+	for_each_sg(sg, s, nents, i)
+		dma_unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir);
+}
+
+static inline void
+dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle,
+			size_t size, enum dma_data_direction dir)
+{
+	_dma_cache_sync(plat_dma_addr_to_kernel(dev, dma_handle), size,
+			DMA_FROM_DEVICE);
+}
+
+static inline void
+dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle,
+			   size_t size, enum dma_data_direction dir)
+{
+	_dma_cache_sync(plat_dma_addr_to_kernel(dev, dma_handle), size,
+			DMA_TO_DEVICE);
+}
+
+static inline void
+dma_sync_single_range_for_cpu(struct device *dev, dma_addr_t dma_handle,
+			      unsigned long offset, size_t size,
+			      enum dma_data_direction direction)
+{
+	_dma_cache_sync(plat_dma_addr_to_kernel(dev, dma_handle) + offset,
+			size, DMA_FROM_DEVICE);
+}
+
+static inline void
+dma_sync_single_range_for_device(struct device *dev, dma_addr_t dma_handle,
+				 unsigned long offset, size_t size,
+				 enum dma_data_direction direction)
+{
+	_dma_cache_sync(plat_dma_addr_to_kernel(dev, dma_handle) + offset,
+			size, DMA_TO_DEVICE);
+}
+
+static inline void
+dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems,
+		    enum dma_data_direction dir)
+{
+	int i;
+
+	for (i = 0; i < nelems; i++, sg++)
+		_dma_cache_sync((unsigned int)sg_virt(sg), sg->length, dir);
+}
+
+static inline void
+dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nelems,
+		       enum dma_data_direction dir)
+{
+	int i;
+
+	for (i = 0; i < nelems; i++, sg++)
+		_dma_cache_sync((unsigned int)sg_virt(sg), sg->length, dir);
+}
+
+static inline int dma_supported(struct device *dev, u64 dma_mask)
+{
+	/* Support 32 bit DMA mask exclusively */
+	return dma_mask == DMA_BIT_MASK(32);
+}
+
+static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+	return 0;
+}
+
+static inline int dma_set_mask(struct device *dev, u64 dma_mask)
+{
+	if (!dev->dma_mask || !dma_supported(dev, dma_mask))
+		return -EIO;
+
+	*dev->dma_mask = dma_mask;
+
+	return 0;
+}
+
+#endif
diff --git a/arch/arc/include/asm/dma.h b/arch/arc/include/asm/dma.h
new file mode 100644
index 000000000000..ca7c45181de9
--- /dev/null
+++ b/arch/arc/include/asm/dma.h
@@ -0,0 +1,14 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef ASM_ARC_DMA_H
+#define ASM_ARC_DMA_H
+
+#define MAX_DMA_ADDRESS 0xC0000000
+
+#endif
diff --git a/arch/arc/include/asm/elf.h b/arch/arc/include/asm/elf.h
new file mode 100644
index 000000000000..f4c8d36ebecb
--- /dev/null
+++ b/arch/arc/include/asm/elf.h
@@ -0,0 +1,78 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ASM_ARC_ELF_H
+#define __ASM_ARC_ELF_H
+
+#include <linux/types.h>
+#include <uapi/asm/elf.h>
+
+/* These ELF defines belong to uapi but libc elf.h already defines them */
+#define EM_ARCOMPACT		93
+
+/* ARC Relocations (kernel Modules only) */
+#define  R_ARC_32		0x4
+#define  R_ARC_32_ME		0x1B
+#define  R_ARC_S25H_PCREL	0x10
+#define  R_ARC_S25W_PCREL	0x11
+
+/*to set parameters in the core dumps */
+#define ELF_ARCH		EM_ARCOMPACT
+#define ELF_CLASS		ELFCLASS32
+
+#ifdef CONFIG_CPU_BIG_ENDIAN
+#define ELF_DATA		ELFDATA2MSB
+#else
+#define ELF_DATA		ELFDATA2LSB
+#endif
+
+/*
+ * To ensure that
+ *  -we don't load something for the wrong architecture.
+ *  -The userspace is using the correct syscall ABI
+ */
+struct elf32_hdr;
+extern int elf_check_arch(const struct elf32_hdr *);
+#define elf_check_arch	elf_check_arch
+
+#define CORE_DUMP_USE_REGSET
+
+#define ELF_EXEC_PAGESIZE	PAGE_SIZE
+
+/*
+ * This is the location that an ET_DYN program is loaded if exec'ed.  Typical
+ * use of this is to invoke "./ld.so someprog" to test out a new version of
+ * the loader.  We need to make sure that it is out of the way of the program
+ * that it will "exec", and that there is sufficient room for the brk.
+ */
+#define ELF_ET_DYN_BASE		(2 * TASK_SIZE / 3)
+
+/*
+ * When the program starts, a1 contains a pointer to a function to be
+ * registered with atexit, as per the SVR4 ABI.  A value of 0 means we
+ * have no such handler.
+ */
+#define ELF_PLAT_INIT(_r, load_addr)	((_r)->r0 = 0)
+
+/*
+ * This yields a mask that user programs can use to figure out what
+ * instruction set this cpu supports.
+ */
+#define ELF_HWCAP	(0)
+
+/*
+ * This yields a string that ld.so will use to load implementation
+ * specific libraries for optimization.  This is more specific in
+ * intent than poking at uname or /proc/cpuinfo.
+ */
+#define ELF_PLATFORM	(NULL)
+
+#define SET_PERSONALITY(ex) \
+	set_personality(PER_LINUX | (current->personality & (~PER_MASK)))
+
+#endif
diff --git a/arch/arc/include/asm/entry.h b/arch/arc/include/asm/entry.h
new file mode 100644
index 000000000000..23daa326fc9b
--- /dev/null
+++ b/arch/arc/include/asm/entry.h
@@ -0,0 +1,724 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Vineetg: March 2009 (Supporting 2 levels of Interrupts)
+ *  Stack switching code can no longer reliably rely on the fact that
+ *  if we are NOT in user mode, stack is switched to kernel mode.
+ *  e.g. L2 IRQ interrupted a L1 ISR which had not yet completed
+ *  it's prologue including stack switching from user mode
+ *
+ * Vineetg: Aug 28th 2008: Bug #94984
+ *  -Zero Overhead Loop Context shd be cleared when entering IRQ/EXcp/Trap
+ *   Normally CPU does this automatically, however when doing FAKE rtie,
+ *   we also need to explicitly do this. The problem in macros
+ *   FAKE_RET_FROM_EXCPN and FAKE_RET_FROM_EXCPN_LOCK_IRQ was that this bit
+ *   was being "CLEARED" rather then "SET". Actually "SET" clears ZOL context
+ *
+ * Vineetg: May 5th 2008
+ *  -Modified CALLEE_REG save/restore macros to handle the fact that
+ *      r25 contains the kernel current task ptr
+ *  - Defined Stack Switching Macro to be reused in all intr/excp hdlrs
+ *  - Shaved off 11 instructions from RESTORE_ALL_INT1 by using the
+ *      address Write back load ld.ab instead of seperate ld/add instn
+ *
+ * Amit Bhor, Sameer Dhavale: Codito Technologies 2004
+ */
+
+#ifndef __ASM_ARC_ENTRY_H
+#define __ASM_ARC_ENTRY_H
+
+#ifdef __ASSEMBLY__
+#include <asm/unistd.h>		/* For NR_syscalls defination */
+#include <asm/asm-offsets.h>
+#include <asm/arcregs.h>
+#include <asm/ptrace.h>
+#include <asm/processor.h>	/* For VMALLOC_START */
+#include <asm/thread_info.h>	/* For THREAD_SIZE */
+
+/* Note on the LD/ST addr modes with addr reg wback
+ *
+ * LD.a same as LD.aw
+ *
+ * LD.a    reg1, [reg2, x]  => Pre Incr
+ *      Eff Addr for load = [reg2 + x]
+ *
+ * LD.ab   reg1, [reg2, x]  => Post Incr
+ *      Eff Addr for load = [reg2]
+ */
+
+/*--------------------------------------------------------------
+ * Save caller saved registers (scratch registers) ( r0 - r12 )
+ * Registers are pushed / popped in the order defined in struct ptregs
+ * in asm/ptrace.h
+ *-------------------------------------------------------------*/
+.macro  SAVE_CALLER_SAVED
+	st.a    r0, [sp, -4]
+	st.a    r1, [sp, -4]
+	st.a    r2, [sp, -4]
+	st.a    r3, [sp, -4]
+	st.a    r4, [sp, -4]
+	st.a    r5, [sp, -4]
+	st.a    r6, [sp, -4]
+	st.a    r7, [sp, -4]
+	st.a    r8, [sp, -4]
+	st.a    r9, [sp, -4]
+	st.a    r10, [sp, -4]
+	st.a    r11, [sp, -4]
+	st.a    r12, [sp, -4]
+.endm
+
+/*--------------------------------------------------------------
+ * Restore caller saved registers (scratch registers)
+ *-------------------------------------------------------------*/
+.macro RESTORE_CALLER_SAVED
+	ld.ab   r12, [sp, 4]
+	ld.ab   r11, [sp, 4]
+	ld.ab   r10, [sp, 4]
+	ld.ab   r9, [sp, 4]
+	ld.ab   r8, [sp, 4]
+	ld.ab   r7, [sp, 4]
+	ld.ab   r6, [sp, 4]
+	ld.ab   r5, [sp, 4]
+	ld.ab   r4, [sp, 4]
+	ld.ab   r3, [sp, 4]
+	ld.ab   r2, [sp, 4]
+	ld.ab   r1, [sp, 4]
+	ld.ab   r0, [sp, 4]
+.endm
+
+
+/*--------------------------------------------------------------
+ * Save callee saved registers (non scratch registers) ( r13 - r25 )
+ *  on kernel stack.
+ * User mode callee regs need to be saved in case of
+ *    -fork and friends for replicating from parent to child
+ *    -before going into do_signal( ) for ptrace/core-dump
+ * Special case handling is required for r25 in case it is used by kernel
+ *  for caching task ptr. Low level exception/ISR save user mode r25
+ *  into task->thread.user_r25. So it needs to be retrieved from there and
+ *  saved into kernel stack with rest of callee reg-file
+ *-------------------------------------------------------------*/
+.macro SAVE_CALLEE_SAVED_USER
+	st.a    r13, [sp, -4]
+	st.a    r14, [sp, -4]
+	st.a    r15, [sp, -4]
+	st.a    r16, [sp, -4]
+	st.a    r17, [sp, -4]
+	st.a    r18, [sp, -4]
+	st.a    r19, [sp, -4]
+	st.a    r20, [sp, -4]
+	st.a    r21, [sp, -4]
+	st.a    r22, [sp, -4]
+	st.a    r23, [sp, -4]
+	st.a    r24, [sp, -4]
+
+#ifdef CONFIG_ARC_CURR_IN_REG
+	; Retrieve orig r25 and save it on stack
+	ld      r12, [r25, TASK_THREAD + THREAD_USER_R25]
+	st.a    r12, [sp, -4]
+#else
+	st.a    r25, [sp, -4]
+#endif
+
+	/* move up by 1 word to "create" callee_regs->"stack_place_holder" */
+	sub sp, sp, 4
+.endm
+
+/*--------------------------------------------------------------
+ * Save callee saved registers (non scratch registers) ( r13 - r25 )
+ * kernel mode callee regs needed to be saved in case of context switch
+ * If r25 is used for caching task pointer then that need not be saved
+ * as it can be re-created from current task global
+ *-------------------------------------------------------------*/
+.macro SAVE_CALLEE_SAVED_KERNEL
+	st.a    r13, [sp, -4]
+	st.a    r14, [sp, -4]
+	st.a    r15, [sp, -4]
+	st.a    r16, [sp, -4]
+	st.a    r17, [sp, -4]
+	st.a    r18, [sp, -4]
+	st.a    r19, [sp, -4]
+	st.a    r20, [sp, -4]
+	st.a    r21, [sp, -4]
+	st.a    r22, [sp, -4]
+	st.a    r23, [sp, -4]
+	st.a    r24, [sp, -4]
+#ifdef CONFIG_ARC_CURR_IN_REG
+	sub     sp, sp, 8
+#else
+	st.a    r25, [sp, -4]
+	sub     sp, sp, 4
+#endif
+.endm
+
+/*--------------------------------------------------------------
+ * RESTORE_CALLEE_SAVED_KERNEL:
+ * Loads callee (non scratch) Reg File by popping from Kernel mode stack.
+ *  This is reverse of SAVE_CALLEE_SAVED,
+ *
+ * NOTE:
+ * Ideally this shd only be called in switch_to for loading
+ *  switched-IN task's CALLEE Reg File.
+ *  For all other cases RESTORE_CALLEE_SAVED_FAST must be used
+ *  which simply pops the stack w/o touching regs.
+ *-------------------------------------------------------------*/
+.macro RESTORE_CALLEE_SAVED_KERNEL
+
+
+#ifdef CONFIG_ARC_CURR_IN_REG
+	add     sp, sp, 8  /* skip callee_reg gutter and user r25 placeholder */
+#else
+	add     sp, sp, 4   /* skip "callee_regs->stack_place_holder" */
+	ld.ab   r25, [sp, 4]
+#endif
+
+	ld.ab   r24, [sp, 4]
+	ld.ab   r23, [sp, 4]
+	ld.ab   r22, [sp, 4]
+	ld.ab   r21, [sp, 4]
+	ld.ab   r20, [sp, 4]
+	ld.ab   r19, [sp, 4]
+	ld.ab   r18, [sp, 4]
+	ld.ab   r17, [sp, 4]
+	ld.ab   r16, [sp, 4]
+	ld.ab   r15, [sp, 4]
+	ld.ab   r14, [sp, 4]
+	ld.ab   r13, [sp, 4]
+
+.endm
+
+/*--------------------------------------------------------------
+ * RESTORE_CALLEE_SAVED_USER:
+ * This is called after do_signal where tracer might have changed callee regs
+ * thus we need to restore the reg file.
+ * Special case handling is required for r25 in case it is used by kernel
+ *  for caching task ptr. Ptrace would have modified on-kernel-stack value of
+ *  r25, which needs to be shoved back into task->thread.user_r25 where from
+ *  Low level exception/ISR return code will retrieve to populate with rest of
+ *  callee reg-file.
+ *-------------------------------------------------------------*/
+.macro RESTORE_CALLEE_SAVED_USER
+
+	add     sp, sp, 4   /* skip "callee_regs->stack_place_holder" */
+
+#ifdef CONFIG_ARC_CURR_IN_REG
+	ld.ab   r12, [sp, 4]
+	st      r12, [r25, TASK_THREAD + THREAD_USER_R25]
+#else
+	ld.ab   r25, [sp, 4]
+#endif
+
+	ld.ab   r24, [sp, 4]
+	ld.ab   r23, [sp, 4]
+	ld.ab   r22, [sp, 4]
+	ld.ab   r21, [sp, 4]
+	ld.ab   r20, [sp, 4]
+	ld.ab   r19, [sp, 4]
+	ld.ab   r18, [sp, 4]
+	ld.ab   r17, [sp, 4]
+	ld.ab   r16, [sp, 4]
+	ld.ab   r15, [sp, 4]
+	ld.ab   r14, [sp, 4]
+	ld.ab   r13, [sp, 4]
+.endm
+
+/*--------------------------------------------------------------
+ * Super FAST Restore callee saved regs by simply re-adjusting SP
+ *-------------------------------------------------------------*/
+.macro DISCARD_CALLEE_SAVED_USER
+	add     sp, sp, 14 * 4
+.endm
+
+/*--------------------------------------------------------------
+ * Restore User mode r25 saved in task_struct->thread.user_r25
+ *-------------------------------------------------------------*/
+.macro RESTORE_USER_R25
+	ld  r25, [r25, TASK_THREAD + THREAD_USER_R25]
+.endm
+
+/*-------------------------------------------------------------
+ * given a tsk struct, get to the base of it's kernel mode stack
+ * tsk->thread_info is really a PAGE, whose bottom hoists stack
+ * which grows upwards towards thread_info
+ *------------------------------------------------------------*/
+
+.macro GET_TSK_STACK_BASE tsk, out
+
+	/* Get task->thread_info (this is essentially start of a PAGE) */
+	ld  \out, [\tsk, TASK_THREAD_INFO]
+
+	/* Go to end of page where stack begins (grows upwards) */
+	add2 \out, \out, (THREAD_SIZE - 4)/4   /* one word GUTTER */
+
+.endm
+
+/*--------------------------------------------------------------
+ * Switch to Kernel Mode stack if SP points to User Mode stack
+ *
+ * Entry   : r9 contains pre-IRQ/exception/trap status32
+ * Exit    : SP is set to kernel mode stack pointer
+ *           If CURR_IN_REG, r25 set to "current" task pointer
+ * Clobbers: r9
+ *-------------------------------------------------------------*/
+
+.macro SWITCH_TO_KERNEL_STK
+
+	/* User Mode when this happened ? Yes: Proceed to switch stack */
+	bbit1   r9, STATUS_U_BIT, 88f
+
+	/* OK we were already in kernel mode when this event happened, thus can
+	 * assume SP is kernel mode SP. _NO_ need to do any stack switching
+	 */
+
+#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS
+	/* However....
+	 * If Level 2 Interrupts enabled, we may end up with a corner case:
+	 * 1. User Task executing
+	 * 2. L1 IRQ taken, ISR starts (CPU auto-switched to KERNEL mode)
+	 * 3. But before it could switch SP from USER to KERNEL stack
+	 *      a L2 IRQ "Interrupts" L1
+	 * Thay way although L2 IRQ happened in Kernel mode, stack is still
+	 * not switched.
+	 * To handle this, we may need to switch stack even if in kernel mode
+	 * provided SP has values in range of USER mode stack ( < 0x7000_0000 )
+	 */
+	brlo sp, VMALLOC_START, 88f
+
+	/* TODO: vineetg:
+	 * We need to be a bit more cautious here. What if a kernel bug in
+	 * L1 ISR, caused SP to go whaco (some small value which looks like
+	 * USER stk) and then we take L2 ISR.
+	 * Above brlo alone would treat it as a valid L1-L2 sceanrio
+	 * instead of shouting alound
+	 * The only feasible way is to make sure this L2 happened in
+	 * L1 prelogue ONLY i.e. ilink2 is less than a pre-set marker in
+	 * L1 ISR before it switches stack
+	 */
+
+#endif
+
+	/* Save Pre Intr/Exception KERNEL MODE SP on kernel stack
+	 * safe-keeping not really needed, but it keeps the epilogue code
+	 * (SP restore) simpler/uniform.
+	 */
+	b.d	77f
+
+	st.a	sp, [sp, -12]	; Make room for orig_r0 and orig_r8
+
+88: /*------Intr/Ecxp happened in user mode, "switch" stack ------ */
+
+	GET_CURR_TASK_ON_CPU   r9
+
+#ifdef CONFIG_ARC_CURR_IN_REG
+
+	/* If current task pointer cached in r25, time to
+	 *  -safekeep USER r25 in task->thread_struct->user_r25
+	 *  -load r25 with current task ptr
+	 */
+	st.as	r25, [r9, (TASK_THREAD + THREAD_USER_R25)/4]
+	mov	r25, r9
+#endif
+
+	/* With current tsk in r9, get it's kernel mode stack base */
+	GET_TSK_STACK_BASE  r9, r9
+
+#ifdef PT_REGS_CANARY
+	st	0xabcdabcd, [r9, 0]
+#endif
+
+	/* Save Pre Intr/Exception User SP on kernel stack */
+	st.a    sp, [r9, -12]	; Make room for orig_r0 and orig_r8
+
+	/* CAUTION:
+	 * SP should be set at the very end when we are done with everything
+	 * In case of 2 levels of interrupt we depend on value of SP to assume
+	 * that everything else is done (loading r25 etc)
+	 */
+
+	/* set SP to point to kernel mode stack */
+	mov sp, r9
+
+77: /* ----- Stack Switched to kernel Mode, Now save REG FILE ----- */
+
+.endm
+
+/*------------------------------------------------------------
+ * "FAKE" a rtie to return from CPU Exception context
+ * This is to re-enable Exceptions within exception
+ * Look at EV_ProtV to see how this is actually used
+ *-------------------------------------------------------------*/
+
+.macro FAKE_RET_FROM_EXCPN  reg
+
+	ld  \reg, [sp, PT_status32]
+	bic  \reg, \reg, (STATUS_U_MASK|STATUS_DE_MASK)
+	bset \reg, \reg, STATUS_L_BIT
+	sr  \reg, [erstatus]
+	mov \reg, 55f
+	sr  \reg, [eret]
+
+	rtie
+55:
+.endm
+
+/*
+ * @reg [OUT] &thread_info of "current"
+ */
+.macro GET_CURR_THR_INFO_FROM_SP  reg
+	and \reg, sp, ~(THREAD_SIZE - 1)
+.endm
+
+/*
+ * @reg [OUT] thread_info->flags of "current"
+ */
+.macro GET_CURR_THR_INFO_FLAGS  reg
+	GET_CURR_THR_INFO_FROM_SP  \reg
+	ld  \reg, [\reg, THREAD_INFO_FLAGS]
+.endm
+
+/*--------------------------------------------------------------
+ * For early Exception Prologue, a core reg is temporarily needed to
+ * code the rest of prolog (stack switching). This is done by stashing
+ * it to memory (non-SMP case) or SCRATCH0 Aux Reg (SMP).
+ *
+ * Before saving the full regfile - this reg is restored back, only
+ * to be saved again on kernel mode stack, as part of ptregs.
+ *-------------------------------------------------------------*/
+.macro EXCPN_PROLOG_FREEUP_REG	reg
+#ifdef CONFIG_SMP
+	sr  \reg, [ARC_REG_SCRATCH_DATA0]
+#else
+	st  \reg, [@ex_saved_reg1]
+#endif
+.endm
+
+.macro EXCPN_PROLOG_RESTORE_REG	reg
+#ifdef CONFIG_SMP
+	lr  \reg, [ARC_REG_SCRATCH_DATA0]
+#else
+	ld  \reg, [@ex_saved_reg1]
+#endif
+.endm
+
+/*--------------------------------------------------------------
+ * Save all registers used by Exceptions (TLB Miss, Prot-V, Mem err etc)
+ * Requires SP to be already switched to kernel mode Stack
+ * sp points to the next free element on the stack at exit of this macro.
+ * Registers are pushed / popped in the order defined in struct ptregs
+ * in asm/ptrace.h
+ * Note that syscalls are implemented via TRAP which is also a exception
+ * from CPU's point of view
+ *-------------------------------------------------------------*/
+.macro SAVE_ALL_EXCEPTION   marker
+
+	st      \marker, [sp, 8]
+	st      r0, [sp, 4]    /* orig_r0, needed only for sys calls */
+
+	/* Restore r9 used to code the early prologue */
+	EXCPN_PROLOG_RESTORE_REG  r9
+
+	SAVE_CALLER_SAVED
+	st.a    r26, [sp, -4]   /* gp */
+	st.a    fp, [sp, -4]
+	st.a    blink, [sp, -4]
+	lr	r9, [eret]
+	st.a    r9, [sp, -4]
+	lr	r9, [erstatus]
+	st.a    r9, [sp, -4]
+	st.a    lp_count, [sp, -4]
+	lr	r9, [lp_end]
+	st.a    r9, [sp, -4]
+	lr	r9, [lp_start]
+	st.a    r9, [sp, -4]
+	lr	r9, [erbta]
+	st.a    r9, [sp, -4]
+
+#ifdef PT_REGS_CANARY
+	mov   r9, 0xdeadbeef
+	st    r9, [sp, -4]
+#endif
+
+	/* move up by 1 word to "create" pt_regs->"stack_place_holder" */
+	sub sp, sp, 4
+.endm
+
+/*--------------------------------------------------------------
+ * Save scratch regs for exceptions
+ *-------------------------------------------------------------*/
+.macro SAVE_ALL_SYS
+	SAVE_ALL_EXCEPTION  orig_r8_IS_EXCPN
+.endm
+
+/*--------------------------------------------------------------
+ * Save scratch regs for sys calls
+ *-------------------------------------------------------------*/
+.macro SAVE_ALL_TRAP
+	/*
+	 * Setup pt_regs->orig_r8.
+	 * Encode syscall number (r8) in upper short word of event type (r9)
+	 * N.B. #1: This is already endian safe (see ptrace.h)
+	 *      #2: Only r9 can be used as scratch as it is already clobbered
+	 *          and it's contents are no longer needed by the latter part
+	 *          of exception prologue
+	 */
+	lsl  r9, r8, 16
+	or   r9, r9, orig_r8_IS_SCALL
+
+	SAVE_ALL_EXCEPTION  r9
+.endm
+
+/*--------------------------------------------------------------
+ * Restore all registers used by system call or Exceptions
+ * SP should always be pointing to the next free stack element
+ * when entering this macro.
+ *
+ * NOTE:
+ *
+ * It is recommended that lp_count/ilink1/ilink2 not be used as a dest reg
+ * for memory load operations. If used in that way interrupts are deffered
+ * by hardware and that is not good.
+ *-------------------------------------------------------------*/
+.macro RESTORE_ALL_SYS
+
+	add sp, sp, 4       /* hop over unused "pt_regs->stack_place_holder" */
+
+	ld.ab   r9, [sp, 4]
+	sr	r9, [erbta]
+	ld.ab   r9, [sp, 4]
+	sr	r9, [lp_start]
+	ld.ab   r9, [sp, 4]
+	sr	r9, [lp_end]
+	ld.ab   r9, [sp, 4]
+	mov	lp_count, r9
+	ld.ab   r9, [sp, 4]
+	sr	r9, [erstatus]
+	ld.ab   r9, [sp, 4]
+	sr	r9, [eret]
+	ld.ab   blink, [sp, 4]
+	ld.ab   fp, [sp, 4]
+	ld.ab   r26, [sp, 4]    /* gp */
+	RESTORE_CALLER_SAVED
+
+	ld  sp, [sp] /* restore original sp */
+	/* orig_r0 and orig_r8 skipped automatically */
+.endm
+
+
+/*--------------------------------------------------------------
+ * Save all registers used by interrupt handlers.
+ *-------------------------------------------------------------*/
+.macro SAVE_ALL_INT1
+
+	/* restore original r9 , saved in int1_saved_reg
+	* It will be saved on stack in macro: SAVE_CALLER_SAVED
+	*/
+#ifdef CONFIG_SMP
+	lr  r9, [ARC_REG_SCRATCH_DATA0]
+#else
+	ld  r9, [@int1_saved_reg]
+#endif
+
+	/* now we are ready to save the remaining context :) */
+	st      orig_r8_IS_IRQ1, [sp, 8]    /* Event Type */
+	st      0, [sp, 4]    /* orig_r0 , N/A for IRQ */
+	SAVE_CALLER_SAVED
+	st.a    r26, [sp, -4]   /* gp */
+	st.a    fp, [sp, -4]
+	st.a    blink, [sp, -4]
+	st.a    ilink1, [sp, -4]
+	lr	r9, [status32_l1]
+	st.a    r9, [sp, -4]
+	st.a    lp_count, [sp, -4]
+	lr	r9, [lp_end]
+	st.a    r9, [sp, -4]
+	lr	r9, [lp_start]
+	st.a    r9, [sp, -4]
+	lr	r9, [bta_l1]
+	st.a    r9, [sp, -4]
+
+#ifdef PT_REGS_CANARY
+	mov   r9, 0xdeadbee1
+	st    r9, [sp, -4]
+#endif
+	/* move up by 1 word to "create" pt_regs->"stack_place_holder" */
+	sub sp, sp, 4
+.endm
+
+.macro SAVE_ALL_INT2
+
+	/* TODO-vineetg: SMP we can't use global nor can we use
+	*   SCRATCH0 as we do for int1 because while int1 is using
+	*   it, int2 can come
+	*/
+	/* retsore original r9 , saved in sys_saved_r9 */
+	ld  r9, [@int2_saved_reg]
+
+	/* now we are ready to save the remaining context :) */
+	st      orig_r8_IS_IRQ2, [sp, 8]    /* Event Type */
+	st      0, [sp, 4]    /* orig_r0 , N/A for IRQ */
+	SAVE_CALLER_SAVED
+	st.a    r26, [sp, -4]   /* gp */
+	st.a    fp, [sp, -4]
+	st.a    blink, [sp, -4]
+	st.a    ilink2, [sp, -4]
+	lr	r9, [status32_l2]
+	st.a    r9, [sp, -4]
+	st.a    lp_count, [sp, -4]
+	lr	r9, [lp_end]
+	st.a    r9, [sp, -4]
+	lr	r9, [lp_start]
+	st.a    r9, [sp, -4]
+	lr	r9, [bta_l2]
+	st.a    r9, [sp, -4]
+
+#ifdef PT_REGS_CANARY
+	mov   r9, 0xdeadbee2
+	st    r9, [sp, -4]
+#endif
+
+	/* move up by 1 word to "create" pt_regs->"stack_place_holder" */
+	sub sp, sp, 4
+.endm
+
+/*--------------------------------------------------------------
+ * Restore all registers used by interrupt handlers.
+ *
+ * NOTE:
+ *
+ * It is recommended that lp_count/ilink1/ilink2 not be used as a dest reg
+ * for memory load operations. If used in that way interrupts are deffered
+ * by hardware and that is not good.
+ *-------------------------------------------------------------*/
+
+.macro RESTORE_ALL_INT1
+	add sp, sp, 4       /* hop over unused "pt_regs->stack_place_holder" */
+
+	ld.ab   r9, [sp, 4] /* Actual reg file */
+	sr	r9, [bta_l1]
+	ld.ab   r9, [sp, 4]
+	sr	r9, [lp_start]
+	ld.ab   r9, [sp, 4]
+	sr	r9, [lp_end]
+	ld.ab   r9, [sp, 4]
+	mov	lp_count, r9
+	ld.ab   r9, [sp, 4]
+	sr	r9, [status32_l1]
+	ld.ab   r9, [sp, 4]
+	mov	ilink1, r9
+	ld.ab   blink, [sp, 4]
+	ld.ab   fp, [sp, 4]
+	ld.ab   r26, [sp, 4]    /* gp */
+	RESTORE_CALLER_SAVED
+
+	ld  sp, [sp] /* restore original sp */
+	/* orig_r0 and orig_r8 skipped automatically */
+.endm
+
+.macro RESTORE_ALL_INT2
+	add sp, sp, 4       /* hop over unused "pt_regs->stack_place_holder" */
+
+	ld.ab   r9, [sp, 4]
+	sr	r9, [bta_l2]
+	ld.ab   r9, [sp, 4]
+	sr	r9, [lp_start]
+	ld.ab   r9, [sp, 4]
+	sr	r9, [lp_end]
+	ld.ab   r9, [sp, 4]
+	mov	lp_count, r9
+	ld.ab   r9, [sp, 4]
+	sr	r9, [status32_l2]
+	ld.ab   r9, [sp, 4]
+	mov	ilink2, r9
+	ld.ab   blink, [sp, 4]
+	ld.ab   fp, [sp, 4]
+	ld.ab   r26, [sp, 4]    /* gp */
+	RESTORE_CALLER_SAVED
+
+	ld  sp, [sp] /* restore original sp */
+	/* orig_r0 and orig_r8 skipped automatically */
+
+.endm
+
+
+/* Get CPU-ID of this core */
+.macro  GET_CPU_ID  reg
+	lr  \reg, [identity]
+	lsr \reg, \reg, 8
+	bmsk \reg, \reg, 7
+.endm
+
+#ifdef CONFIG_SMP
+
+/*-------------------------------------------------
+ * Retrieve the current running task on this CPU
+ * 1. Determine curr CPU id.
+ * 2. Use it to index into _current_task[ ]
+ */
+.macro  GET_CURR_TASK_ON_CPU   reg
+	GET_CPU_ID  \reg
+	ld.as  \reg, [@_current_task, \reg]
+.endm
+
+/*-------------------------------------------------
+ * Save a new task as the "current" task on this CPU
+ * 1. Determine curr CPU id.
+ * 2. Use it to index into _current_task[ ]
+ *
+ * Coded differently than GET_CURR_TASK_ON_CPU (which uses LD.AS)
+ * because ST r0, [r1, offset] can ONLY have s9 @offset
+ * while   LD can take s9 (4 byte insn) or LIMM (8 byte insn)
+ */
+
+.macro  SET_CURR_TASK_ON_CPU    tsk, tmp
+	GET_CPU_ID  \tmp
+	add2 \tmp, @_current_task, \tmp
+	st   \tsk, [\tmp]
+#ifdef CONFIG_ARC_CURR_IN_REG
+	mov r25, \tsk
+#endif
+
+.endm
+
+
+#else   /* Uniprocessor implementation of macros */
+
+.macro  GET_CURR_TASK_ON_CPU    reg
+	ld  \reg, [@_current_task]
+.endm
+
+.macro  SET_CURR_TASK_ON_CPU    tsk, tmp
+	st  \tsk, [@_current_task]
+#ifdef CONFIG_ARC_CURR_IN_REG
+	mov r25, \tsk
+#endif
+.endm
+
+#endif /* SMP / UNI */
+
+/* ------------------------------------------------------------------
+ * Get the ptr to some field of Current Task at @off in task struct
+ *  -Uses r25 for Current task ptr if that is enabled
+ */
+
+#ifdef CONFIG_ARC_CURR_IN_REG
+
+.macro GET_CURR_TASK_FIELD_PTR  off,  reg
+	add \reg, r25, \off
+.endm
+
+#else
+
+.macro GET_CURR_TASK_FIELD_PTR  off,  reg
+	GET_CURR_TASK_ON_CPU  \reg
+	add \reg, \reg, \off
+.endm
+
+#endif	/* CONFIG_ARC_CURR_IN_REG */
+
+#endif  /* __ASSEMBLY__ */
+
+#endif  /* __ASM_ARC_ENTRY_H */
diff --git a/arch/arc/include/asm/exec.h b/arch/arc/include/asm/exec.h
new file mode 100644
index 000000000000..28abc6905e07
--- /dev/null
+++ b/arch/arc/include/asm/exec.h
@@ -0,0 +1,15 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ASM_ARC_EXEC_H
+#define __ASM_ARC_EXEC_H
+
+/* Align to 16b */
+#define arch_align_stack(p) ((unsigned long)(p) & ~0xf)
+
+#endif
diff --git a/arch/arc/include/asm/futex.h b/arch/arc/include/asm/futex.h
new file mode 100644
index 000000000000..4dc64ddebece
--- /dev/null
+++ b/arch/arc/include/asm/futex.h
@@ -0,0 +1,151 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Vineetg: August 2010: From Android kernel work
+ */
+
+#ifndef _ASM_FUTEX_H
+#define _ASM_FUTEX_H
+
+#include <linux/futex.h>
+#include <linux/preempt.h>
+#include <linux/uaccess.h>
+#include <asm/errno.h>
+
+#define __futex_atomic_op(insn, ret, oldval, uaddr, oparg)\
+							\
+	__asm__ __volatile__(				\
+	"1:	ld  %1, [%2]			\n"	\
+		insn				"\n"	\
+	"2:	st  %0, [%2]			\n"	\
+	"	mov %0, 0			\n"	\
+	"3:					\n"	\
+	"	.section .fixup,\"ax\"		\n"	\
+	"	.align  4			\n"	\
+	"4:	mov %0, %4			\n"	\
+	"	b   3b				\n"	\
+	"	.previous			\n"	\
+	"	.section __ex_table,\"a\"	\n"	\
+	"	.align  4			\n"	\
+	"	.word   1b, 4b			\n"	\
+	"	.word   2b, 4b			\n"	\
+	"	.previous			\n"	\
+							\
+	: "=&r" (ret), "=&r" (oldval)			\
+	: "r" (uaddr), "r" (oparg), "ir" (-EFAULT)	\
+	: "cc", "memory")
+
+static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
+{
+	int op = (encoded_op >> 28) & 7;
+	int cmp = (encoded_op >> 24) & 15;
+	int oparg = (encoded_op << 8) >> 20;
+	int cmparg = (encoded_op << 20) >> 20;
+	int oldval = 0, ret;
+
+	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
+		oparg = 1 << oparg;
+
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+		return -EFAULT;
+
+	pagefault_disable();	/* implies preempt_disable() */
+
+	switch (op) {
+	case FUTEX_OP_SET:
+		__futex_atomic_op("mov %0, %3", ret, oldval, uaddr, oparg);
+		break;
+	case FUTEX_OP_ADD:
+		__futex_atomic_op("add %0, %1, %3", ret, oldval, uaddr, oparg);
+		break;
+	case FUTEX_OP_OR:
+		__futex_atomic_op("or  %0, %1, %3", ret, oldval, uaddr, oparg);
+		break;
+	case FUTEX_OP_ANDN:
+		__futex_atomic_op("bic %0, %1, %3", ret, oldval, uaddr, oparg);
+		break;
+	case FUTEX_OP_XOR:
+		__futex_atomic_op("xor %0, %1, %3", ret, oldval, uaddr, oparg);
+		break;
+	default:
+		ret = -ENOSYS;
+	}
+
+	pagefault_enable();	/* subsumes preempt_enable() */
+
+	if (!ret) {
+		switch (cmp) {
+		case FUTEX_OP_CMP_EQ:
+			ret = (oldval == cmparg);
+			break;
+		case FUTEX_OP_CMP_NE:
+			ret = (oldval != cmparg);
+			break;
+		case FUTEX_OP_CMP_LT:
+			ret = (oldval < cmparg);
+			break;
+		case FUTEX_OP_CMP_GE:
+			ret = (oldval >= cmparg);
+			break;
+		case FUTEX_OP_CMP_LE:
+			ret = (oldval <= cmparg);
+			break;
+		case FUTEX_OP_CMP_GT:
+			ret = (oldval > cmparg);
+			break;
+		default:
+			ret = -ENOSYS;
+		}
+	}
+	return ret;
+}
+
+/* Compare-xchg with preemption disabled.
+ *  Notes:
+ *      -Best-Effort: Exchg happens only if compare succeeds.
+ *          If compare fails, returns; leaving retry/looping to upper layers
+ *      -successful cmp-xchg: return orig value in @addr (same as cmp val)
+ *      -Compare fails: return orig value in @addr
+ *      -user access r/w fails: return -EFAULT
+ */
+static inline int
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval,
+					u32 newval)
+{
+	u32 val;
+
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+		return -EFAULT;
+
+	pagefault_disable();	/* implies preempt_disable() */
+
+	/* TBD : can use llock/scond */
+	__asm__ __volatile__(
+	"1:	ld    %0, [%3]	\n"
+	"	brne  %0, %1, 3f	\n"
+	"2:	st    %2, [%3]	\n"
+	"3:	\n"
+	"	.section .fixup,\"ax\"	\n"
+	"4:	mov %0, %4	\n"
+	"	b   3b	\n"
+	"	.previous	\n"
+	"	.section __ex_table,\"a\"	\n"
+	"	.align  4	\n"
+	"	.word   1b, 4b	\n"
+	"	.word   2b, 4b	\n"
+	"	.previous\n"
+	: "=&r"(val)
+	: "r"(oldval), "r"(newval), "r"(uaddr), "ir"(-EFAULT)
+	: "cc", "memory");
+
+	pagefault_enable();	/* subsumes preempt_enable() */
+
+	*uval = val;
+	return val;
+}
+
+#endif
diff --git a/arch/arc/include/asm/io.h b/arch/arc/include/asm/io.h
new file mode 100644
index 000000000000..473424d7528b
--- /dev/null
+++ b/arch/arc/include/asm/io.h
@@ -0,0 +1,105 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_ARC_IO_H
+#define _ASM_ARC_IO_H
+
+#include <linux/types.h>
+#include <asm/byteorder.h>
+#include <asm/page.h>
+
+#define PCI_IOBASE ((void __iomem *)0)
+
+extern void __iomem *ioremap(unsigned long physaddr, unsigned long size);
+extern void __iomem *ioremap_prot(phys_addr_t offset, unsigned long size,
+				  unsigned long flags);
+extern void iounmap(const void __iomem *addr);
+
+#define ioremap_nocache(phy, sz)	ioremap(phy, sz)
+#define ioremap_wc(phy, sz)		ioremap(phy, sz)
+
+/* Change struct page to physical address */
+#define page_to_phys(page)		(page_to_pfn(page) << PAGE_SHIFT)
+
+#define __raw_readb __raw_readb
+static inline u8 __raw_readb(const volatile void __iomem *addr)
+{
+	u8 b;
+
+	__asm__ __volatile__(
+	"	ldb%U1 %0, %1	\n"
+	: "=r" (b)
+	: "m" (*(volatile u8 __force *)addr)
+	: "memory");
+
+	return b;
+}
+
+#define __raw_readw __raw_readw
+static inline u16 __raw_readw(const volatile void __iomem *addr)
+{
+	u16 s;
+
+	__asm__ __volatile__(
+	"	ldw%U1 %0, %1	\n"
+	: "=r" (s)
+	: "m" (*(volatile u16 __force *)addr)
+	: "memory");
+
+	return s;
+}
+
+#define __raw_readl __raw_readl
+static inline u32 __raw_readl(const volatile void __iomem *addr)
+{
+	u32 w;
+
+	__asm__ __volatile__(
+	"	ld%U1 %0, %1	\n"
+	: "=r" (w)
+	: "m" (*(volatile u32 __force *)addr)
+	: "memory");
+
+	return w;
+}
+
+#define __raw_writeb __raw_writeb
+static inline void __raw_writeb(u8 b, volatile void __iomem *addr)
+{
+	__asm__ __volatile__(
+	"	stb%U1 %0, %1	\n"
+	:
+	: "r" (b), "m" (*(volatile u8 __force *)addr)
+	: "memory");
+}
+
+#define __raw_writew __raw_writew
+static inline void __raw_writew(u16 s, volatile void __iomem *addr)
+{
+	__asm__ __volatile__(
+	"	stw%U1 %0, %1	\n"
+	:
+	: "r" (s), "m" (*(volatile u16 __force *)addr)
+	: "memory");
+
+}
+
+#define __raw_writel __raw_writel
+static inline void __raw_writel(u32 w, volatile void __iomem *addr)
+{
+	__asm__ __volatile__(
+	"	st%U1 %0, %1	\n"
+	:
+	: "r" (w), "m" (*(volatile u32 __force *)addr)
+	: "memory");
+
+}
+
+#include <asm-generic/io.h>
+
+#endif /* _ASM_ARC_IO_H */
diff --git a/arch/arc/include/asm/irq.h b/arch/arc/include/asm/irq.h
new file mode 100644
index 000000000000..4c588f9820cf
--- /dev/null
+++ b/arch/arc/include/asm/irq.h
@@ -0,0 +1,25 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ASM_ARC_IRQ_H
+#define __ASM_ARC_IRQ_H
+
+#define NR_IRQS		32
+
+/* Platform Independent IRQs */
+#define TIMER0_IRQ      3
+#define TIMER1_IRQ      4
+
+#include <asm-generic/irq.h>
+
+extern void __init arc_init_IRQ(void);
+extern int __init get_hw_config_num_irq(void);
+
+void __cpuinit arc_local_timer_setup(unsigned int cpu);
+
+#endif
diff --git a/arch/arc/include/asm/irqflags.h b/arch/arc/include/asm/irqflags.h
new file mode 100644
index 000000000000..ccd84806b62f
--- /dev/null
+++ b/arch/arc/include/asm/irqflags.h
@@ -0,0 +1,153 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ASM_ARC_IRQFLAGS_H
+#define __ASM_ARC_IRQFLAGS_H
+
+/* vineetg: March 2010 : local_irq_save( ) optimisation
+ *  -Remove explicit mov of current status32 into reg, that is not needed
+ *  -Use BIC  insn instead of INVERTED + AND
+ *  -Conditionally disable interrupts (if they are not enabled, don't disable)
+*/
+
+#ifdef __KERNEL__
+
+#include <asm/arcregs.h>
+
+#ifndef __ASSEMBLY__
+
+/******************************************************************
+ * IRQ Control Macros
+ ******************************************************************/
+
+/*
+ * Save IRQ state and disable IRQs
+ */
+static inline long arch_local_irq_save(void)
+{
+	unsigned long temp, flags;
+
+	__asm__ __volatile__(
+	"	lr  %1, [status32]	\n"
+	"	bic %0, %1, %2		\n"
+	"	and.f 0, %1, %2	\n"
+	"	flag.nz %0		\n"
+	: "=r"(temp), "=r"(flags)
+	: "n"((STATUS_E1_MASK | STATUS_E2_MASK))
+	: "cc");
+
+	return flags;
+}
+
+/*
+ * restore saved IRQ state
+ */
+static inline void arch_local_irq_restore(unsigned long flags)
+{
+
+	__asm__ __volatile__(
+	"	flag %0			\n"
+	:
+	: "r"(flags));
+}
+
+/*
+ * Unconditionally Enable IRQs
+ */
+extern void arch_local_irq_enable(void);
+
+/*
+ * Unconditionally Disable IRQs
+ */
+static inline void arch_local_irq_disable(void)
+{
+	unsigned long temp;
+
+	__asm__ __volatile__(
+	"	lr  %0, [status32]	\n"
+	"	and %0, %0, %1		\n"
+	"	flag %0			\n"
+	: "=&r"(temp)
+	: "n"(~(STATUS_E1_MASK | STATUS_E2_MASK)));
+}
+
+/*
+ * save IRQ state
+ */
+static inline long arch_local_save_flags(void)
+{
+	unsigned long temp;
+
+	__asm__ __volatile__(
+	"	lr  %0, [status32]	\n"
+	: "=&r"(temp));
+
+	return temp;
+}
+
+/*
+ * Query IRQ state
+ */
+static inline int arch_irqs_disabled_flags(unsigned long flags)
+{
+	return !(flags & (STATUS_E1_MASK
+#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS
+			| STATUS_E2_MASK
+#endif
+		));
+}
+
+static inline int arch_irqs_disabled(void)
+{
+	return arch_irqs_disabled_flags(arch_local_save_flags());
+}
+
+static inline void arch_mask_irq(unsigned int irq)
+{
+	unsigned int ienb;
+
+	ienb = read_aux_reg(AUX_IENABLE);
+	ienb &= ~(1 << irq);
+	write_aux_reg(AUX_IENABLE, ienb);
+}
+
+static inline void arch_unmask_irq(unsigned int irq)
+{
+	unsigned int ienb;
+
+	ienb = read_aux_reg(AUX_IENABLE);
+	ienb |= (1 << irq);
+	write_aux_reg(AUX_IENABLE, ienb);
+}
+
+#else
+
+.macro IRQ_DISABLE  scratch
+	lr	\scratch, [status32]
+	bic	\scratch, \scratch, (STATUS_E1_MASK | STATUS_E2_MASK)
+	flag	\scratch
+.endm
+
+.macro IRQ_DISABLE_SAVE  scratch, save
+	lr	\scratch, [status32]
+	mov	\save, \scratch		/* Make a copy */
+	bic	\scratch, \scratch, (STATUS_E1_MASK | STATUS_E2_MASK)
+	flag	\scratch
+.endm
+
+.macro IRQ_ENABLE  scratch
+	lr	\scratch, [status32]
+	or	\scratch, \scratch, (STATUS_E1_MASK | STATUS_E2_MASK)
+	flag	\scratch
+.endm
+
+#endif	/* __ASSEMBLY__ */
+
+#endif	/* KERNEL */
+
+#endif
diff --git a/arch/arc/include/asm/kdebug.h b/arch/arc/include/asm/kdebug.h
new file mode 100644
index 000000000000..3fbe6c472c0a
--- /dev/null
+++ b/arch/arc/include/asm/kdebug.h
@@ -0,0 +1,19 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_ARC_KDEBUG_H
+#define _ASM_ARC_KDEBUG_H
+
+enum die_val {
+	DIE_UNUSED,
+	DIE_TRAP,
+	DIE_IERR,
+	DIE_OOPS
+};
+
+#endif
diff --git a/arch/arc/include/asm/kgdb.h b/arch/arc/include/asm/kgdb.h
new file mode 100644
index 000000000000..f3c4934f0ca9
--- /dev/null
+++ b/arch/arc/include/asm/kgdb.h
@@ -0,0 +1,61 @@
+/*
+ * kgdb support for ARC
+ *
+ * Copyright (C) 2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ARC_KGDB_H__
+#define __ARC_KGDB_H__
+
+#ifdef CONFIG_KGDB
+
+#include <asm/user.h>
+
+/* to ensure compatibility with Linux 2.6.35, we don't implement the get/set
+ * register API yet */
+#undef DBG_MAX_REG_NUM
+
+#define GDB_MAX_REGS		39
+
+#define BREAK_INSTR_SIZE	2
+#define CACHE_FLUSH_IS_SAFE	1
+#define NUMREGBYTES		(GDB_MAX_REGS * 4)
+#define BUFMAX			2048
+
+static inline void arch_kgdb_breakpoint(void)
+{
+	__asm__ __volatile__ ("trap_s	0x4\n");
+}
+
+extern void kgdb_trap(struct pt_regs *regs, int param);
+
+enum arc700_linux_regnums {
+	_R0		= 0,
+	_R1, _R2, _R3, _R4, _R5, _R6, _R7, _R8, _R9, _R10, _R11, _R12, _R13,
+	_R14, _R15, _R16, _R17, _R18, _R19, _R20, _R21, _R22, _R23, _R24,
+	_R25, _R26,
+	_BTA		= 27,
+	_LP_START	= 28,
+	_LP_END		= 29,
+	_LP_COUNT	= 30,
+	_STATUS32	= 31,
+	_BLINK		= 32,
+	_FP		= 33,
+	__SP		= 34,
+	_EFA		= 35,
+	_RET		= 36,
+	_ORIG_R8	= 37,
+	_STOP_PC	= 38
+};
+
+#else
+static inline void kgdb_trap(struct pt_regs *regs, int param)
+{
+}
+#endif
+
+#endif	/* __ARC_KGDB_H__ */
diff --git a/arch/arc/include/asm/kprobes.h b/arch/arc/include/asm/kprobes.h
new file mode 100644
index 000000000000..4d9c211fce70
--- /dev/null
+++ b/arch/arc/include/asm/kprobes.h
@@ -0,0 +1,62 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ARC_KPROBES_H
+#define _ARC_KPROBES_H
+
+#ifdef CONFIG_KPROBES
+
+typedef u16 kprobe_opcode_t;
+
+#define UNIMP_S_INSTRUCTION 0x79e0
+#define TRAP_S_2_INSTRUCTION 0x785e
+
+#define MAX_INSN_SIZE   8
+#define MAX_STACK_SIZE  64
+
+struct arch_specific_insn {
+	int is_short;
+	kprobe_opcode_t *t1_addr, *t2_addr;
+	kprobe_opcode_t t1_opcode, t2_opcode;
+};
+
+#define flush_insn_slot(p)  do {  } while (0)
+
+#define kretprobe_blacklist_size    0
+
+struct kprobe;
+
+void arch_remove_kprobe(struct kprobe *p);
+
+int kprobe_exceptions_notify(struct notifier_block *self,
+			     unsigned long val, void *data);
+
+struct prev_kprobe {
+	struct kprobe *kp;
+	unsigned long status;
+};
+
+struct kprobe_ctlblk {
+	unsigned int kprobe_status;
+	struct pt_regs jprobe_saved_regs;
+	char jprobes_stack[MAX_STACK_SIZE];
+	struct prev_kprobe prev_kprobe;
+};
+
+int kprobe_fault_handler(struct pt_regs *regs, unsigned long cause);
+void kretprobe_trampoline(void);
+void trap_is_kprobe(unsigned long cause, unsigned long address,
+			   struct pt_regs *regs);
+#else
+static void trap_is_kprobe(unsigned long cause, unsigned long address,
+			   struct pt_regs *regs)
+{
+}
+#endif
+
+#endif
diff --git a/arch/arc/include/asm/linkage.h b/arch/arc/include/asm/linkage.h
new file mode 100644
index 000000000000..0283e9e44e0d
--- /dev/null
+++ b/arch/arc/include/asm/linkage.h
@@ -0,0 +1,63 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ASM_LINKAGE_H
+#define __ASM_LINKAGE_H
+
+#ifdef __ASSEMBLY__
+
+/* Can't use the ENTRY macro in linux/linkage.h
+ * gas considers ';' as comment vs. newline
+ */
+.macro ARC_ENTRY name
+	.global \name
+	.align 4
+	\name:
+.endm
+
+.macro ARC_EXIT name
+#define ASM_PREV_SYM_ADDR(name)  .-##name
+	.size \ name, ASM_PREV_SYM_ADDR(\name)
+.endm
+
+/* annotation for data we want in DCCM - if enabled in .config */
+.macro ARCFP_DATA nm
+#ifdef CONFIG_ARC_HAS_DCCM
+	.section .data.arcfp
+#else
+	.section .data
+#endif
+	.global \nm
+.endm
+
+/* annotation for data we want in DCCM - if enabled in .config */
+.macro ARCFP_CODE
+#ifdef CONFIG_ARC_HAS_ICCM
+	.section .text.arcfp, "ax",@progbits
+#else
+	.section .text, "ax",@progbits
+#endif
+.endm
+
+#else	/* !__ASSEMBLY__ */
+
+#ifdef CONFIG_ARC_HAS_ICCM
+#define __arcfp_code __attribute__((__section__(".text.arcfp")))
+#else
+#define __arcfp_code __attribute__((__section__(".text")))
+#endif
+
+#ifdef CONFIG_ARC_HAS_DCCM
+#define __arcfp_data __attribute__((__section__(".data.arcfp")))
+#else
+#define __arcfp_data __attribute__((__section__(".data")))
+#endif
+
+#endif /* __ASSEMBLY__ */
+
+#endif
diff --git a/arch/arc/include/asm/mach_desc.h b/arch/arc/include/asm/mach_desc.h
new file mode 100644
index 000000000000..9998dc846ebb
--- /dev/null
+++ b/arch/arc/include/asm/mach_desc.h
@@ -0,0 +1,87 @@
+/*
+ * Copyright (C) 2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * based on METAG mach/arch.h (which in turn was based on ARM)
+ *
+ * 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_ARC_MACH_DESC_H_
+#define _ASM_ARC_MACH_DESC_H_
+
+/**
+ * struct machine_desc - Board specific callbacks, called from ARC common code
+ *	Provided by each ARC board using MACHINE_START()/MACHINE_END(), so
+ *	a multi-platform kernel builds with array of such descriptors.
+ *	We extend the early DT scan to also match the DT's "compatible" string
+ *	against the @dt_compat of all such descriptors, and one with highest
+ *	"DT score" is selected as global @machine_desc.
+ *
+ * @name:		Board/SoC name
+ * @dt_compat:		Array of device tree 'compatible' strings
+ * 			(XXX: although only 1st entry is looked at)
+ * @init_early:		Very early callback [called from setup_arch()]
+ * @init_irq:		setup external IRQ controllers [called from init_IRQ()]
+ * @init_smp:		for each CPU (e.g. setup IPI)
+ * 			[(M):init_IRQ(), (o):start_kernel_secondary()]
+ * @init_time:		platform specific clocksource/clockevent registration
+ * 			[called from time_init()]
+ * @init_machine:	arch initcall level callback (e.g. populate static
+ * 			platform devices or parse Devicetree)
+ * @init_late:		Late initcall level callback
+ *
+ */
+struct machine_desc {
+	const char		*name;
+	const char		**dt_compat;
+
+	void			(*init_early)(void);
+	void			(*init_irq)(void);
+#ifdef CONFIG_SMP
+	void			(*init_smp)(unsigned int);
+#endif
+	void			(*init_time)(void);
+	void			(*init_machine)(void);
+	void			(*init_late)(void);
+
+};
+
+/*
+ * Current machine - only accessible during boot.
+ */
+extern struct machine_desc *machine_desc;
+
+/*
+ * Machine type table - also only accessible during boot
+ */
+extern struct machine_desc __arch_info_begin[], __arch_info_end[];
+#define for_each_machine_desc(p)			\
+	for (p = __arch_info_begin; p < __arch_info_end; p++)
+
+static inline struct machine_desc *default_machine_desc(void)
+{
+	/* the default machine is the last one linked in */
+	if (__arch_info_end - 1 < __arch_info_begin)
+		return NULL;
+	return __arch_info_end - 1;
+}
+
+/*
+ * Set of macros to define architecture features.
+ * This is built into a table by the linker.
+ */
+#define MACHINE_START(_type, _name)			\
+static const struct machine_desc __mach_desc_##_type	\
+__used							\
+__attribute__((__section__(".arch.info.init"))) = {	\
+	.name		= _name,
+
+#define MACHINE_END				\
+};
+
+extern struct machine_desc *setup_machine_fdt(void *dt);
+extern void __init copy_devtree(void);
+
+#endif
diff --git a/arch/arc/include/asm/mmu.h b/arch/arc/include/asm/mmu.h
new file mode 100644
index 000000000000..56b02320f1a9
--- /dev/null
+++ b/arch/arc/include/asm/mmu.h
@@ -0,0 +1,23 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_ARC_MMU_H
+#define _ASM_ARC_MMU_H
+
+#ifndef __ASSEMBLY__
+
+typedef struct {
+	unsigned long asid;	/* Pvt Addr-Space ID for mm */
+#ifdef CONFIG_ARC_TLB_DBG
+	struct task_struct *tsk;
+#endif
+} mm_context_t;
+
+#endif
+
+#endif
diff --git a/arch/arc/include/asm/mmu_context.h b/arch/arc/include/asm/mmu_context.h
new file mode 100644
index 000000000000..0d71fb11b57c
--- /dev/null
+++ b/arch/arc/include/asm/mmu_context.h
@@ -0,0 +1,213 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * vineetg: May 2011
+ *  -Refactored get_new_mmu_context( ) to only handle live-mm.
+ *   retiring-mm handled in other hooks
+ *
+ * Vineetg: March 25th, 2008: Bug #92690
+ *  -Major rewrite of Core ASID allocation routine get_new_mmu_context
+ *
+ * Amit Bhor, Sameer Dhavale: Codito Technologies 2004
+ */
+
+#ifndef _ASM_ARC_MMU_CONTEXT_H
+#define _ASM_ARC_MMU_CONTEXT_H
+
+#include <asm/arcregs.h>
+#include <asm/tlb.h>
+
+#include <asm-generic/mm_hooks.h>
+
+/*		ARC700 ASID Management
+ *
+ * ARC MMU provides 8-bit ASID (0..255) to TAG TLB entries, allowing entries
+ * with same vaddr (different tasks) to co-exit. This provides for
+ * "Fast Context Switch" i.e. no TLB flush on ctxt-switch
+ *
+ * Linux assigns each task a unique ASID. A simple round-robin allocation
+ * of H/w ASID is done using software tracker @asid_cache.
+ * When it reaches max 255, the allocation cycle starts afresh by flushing
+ * the entire TLB and wrapping ASID back to zero.
+ *
+ * For book-keeping, Linux uses a couple of data-structures:
+ *  -mm_struct has an @asid field to keep a note of task's ASID (needed at the
+ *   time of say switch_mm( )
+ *  -An array of mm structs @asid_mm_map[] for asid->mm the reverse mapping,
+ *  given an ASID, finding the mm struct associated.
+ *
+ * The round-robin allocation algorithm allows for ASID stealing.
+ * If asid tracker is at "x-1", a new req will allocate "x", even if "x" was
+ * already assigned to another (switched-out) task. Obviously the prev owner
+ * is marked with an invalid ASID to make it request for a new ASID when it
+ * gets scheduled next time. However its TLB entries (with ASID "x") could
+ * exist, which must be cleared before the same ASID is used by the new owner.
+ * Flushing them would be plausible but costly solution. Instead we force a
+ * allocation policy quirk, which ensures that a stolen ASID won't have any
+ * TLB entries associates, alleviating the need to flush.
+ * The quirk essentially is not allowing ASID allocated in prev cycle
+ * to be used past a roll-over in the next cycle.
+ * When this happens (i.e. task ASID > asid tracker), task needs to refresh
+ * its ASID, aligning it to current value of tracker. If the task doesn't get
+ * scheduled past a roll-over, hence its ASID is not yet realigned with
+ * tracker, such ASID is anyways safely reusable because it is
+ * gauranteed that TLB entries with that ASID wont exist.
+ */
+
+#define FIRST_ASID  0
+#define MAX_ASID    255			/* 8 bit PID field in PID Aux reg */
+#define NO_ASID     (MAX_ASID + 1)	/* ASID Not alloc to mmu ctxt */
+#define NUM_ASID    ((MAX_ASID - FIRST_ASID) + 1)
+
+/* ASID to mm struct mapping */
+extern struct mm_struct *asid_mm_map[NUM_ASID + 1];
+
+extern int asid_cache;
+
+/*
+ * Assign a new ASID to task. If the task already has an ASID, it is
+ * relinquished.
+ */
+static inline void get_new_mmu_context(struct mm_struct *mm)
+{
+	struct mm_struct *prev_owner;
+	unsigned long flags;
+
+	local_irq_save(flags);
+
+	/*
+	 * Relinquish the currently owned ASID (if any).
+	 * Doing unconditionally saves a cmp-n-branch; for already unused
+	 * ASID slot, the value was/remains NULL
+	 */
+	asid_mm_map[mm->context.asid] = (struct mm_struct *)NULL;
+
+	/* move to new ASID */
+	if (++asid_cache > MAX_ASID) {	/* ASID roll-over */
+		asid_cache = FIRST_ASID;
+		flush_tlb_all();
+	}
+
+	/*
+	 * Is next ASID already owned by some-one else (we are stealing it).
+	 * If so, let the orig owner be aware of this, so when it runs, it
+	 * asks for a brand new ASID. This would only happen for a long-lived
+	 * task with ASID from prev allocation cycle (before ASID roll-over).
+	 *
+	 * This might look wrong - if we are re-using some other task's ASID,
+	 * won't we use it's stale TLB entries too. Actually switch_mm( ) takes
+	 * care of such a case: it ensures that task with ASID from prev alloc
+	 * cycle, when scheduled will refresh it's ASID: see switch_mm( ) below
+	 * The stealing scenario described here will only happen if that task
+	 * didn't get a chance to refresh it's ASID - implying stale entries
+	 * won't exist.
+	 */
+	prev_owner = asid_mm_map[asid_cache];
+	if (prev_owner)
+		prev_owner->context.asid = NO_ASID;
+
+	/* Assign new ASID to tsk */
+	asid_mm_map[asid_cache] = mm;
+	mm->context.asid = asid_cache;
+
+#ifdef CONFIG_ARC_TLB_DBG
+	pr_info("ARC_TLB_DBG: NewMM=0x%x OldMM=0x%x task_struct=0x%x Task: %s,"
+	       " pid:%u, assigned asid:%lu\n",
+	       (unsigned int)mm, (unsigned int)prev_owner,
+	       (unsigned int)(mm->context.tsk), (mm->context.tsk)->comm,
+	       (mm->context.tsk)->pid, mm->context.asid);
+#endif
+
+	write_aux_reg(ARC_REG_PID, asid_cache | MMU_ENABLE);
+
+	local_irq_restore(flags);
+}
+
+/*
+ * Initialize the context related info for a new mm_struct
+ * instance.
+ */
+static inline int
+init_new_context(struct task_struct *tsk, struct mm_struct *mm)
+{
+	mm->context.asid = NO_ASID;
+#ifdef CONFIG_ARC_TLB_DBG
+	mm->context.tsk = tsk;
+#endif
+	return 0;
+}
+
+/* Prepare the MMU for task: setup PID reg with allocated ASID
+    If task doesn't have an ASID (never alloc or stolen, get a new ASID)
+*/
+static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
+			     struct task_struct *tsk)
+{
+#ifndef CONFIG_SMP
+	/* PGD cached in MMU reg to avoid 3 mem lookups: task->mm->pgd */
+	write_aux_reg(ARC_REG_SCRATCH_DATA0, next->pgd);
+#endif
+
+	/*
+	 * Get a new ASID if task doesn't have a valid one. Possible when
+	 *  -task never had an ASID (fresh after fork)
+	 *  -it's ASID was stolen - past an ASID roll-over.
+	 *  -There's a third obscure scenario (if this task is running for the
+	 *   first time afer an ASID rollover), where despite having a valid
+	 *   ASID, we force a get for new ASID - see comments at top.
+	 *
+	 * Both the non-alloc scenario and first-use-after-rollover can be
+	 * detected using the single condition below:  NO_ASID = 256
+	 * while asid_cache is always a valid ASID value (0-255).
+	 */
+	if (next->context.asid > asid_cache) {
+		get_new_mmu_context(next);
+	} else {
+		/*
+		 * XXX: This will never happen given the chks above
+		 * BUG_ON(next->context.asid > MAX_ASID);
+		 */
+		write_aux_reg(ARC_REG_PID, next->context.asid | MMU_ENABLE);
+	}
+
+}
+
+static inline void destroy_context(struct mm_struct *mm)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+
+	asid_mm_map[mm->context.asid] = NULL;
+	mm->context.asid = NO_ASID;
+
+	local_irq_restore(flags);
+}
+
+/* it seemed that deactivate_mm( ) is a reasonable place to do book-keeping
+ * for retiring-mm. However destroy_context( ) still needs to do that because
+ * between mm_release( ) = >deactive_mm( ) and
+ * mmput => .. => __mmdrop( ) => destroy_context( )
+ * there is a good chance that task gets sched-out/in, making it's ASID valid
+ * again (this teased me for a whole day).
+ */
+#define deactivate_mm(tsk, mm)   do { } while (0)
+
+static inline void activate_mm(struct mm_struct *prev, struct mm_struct *next)
+{
+#ifndef CONFIG_SMP
+	write_aux_reg(ARC_REG_SCRATCH_DATA0, next->pgd);
+#endif
+
+	/* Unconditionally get a new ASID */
+	get_new_mmu_context(next);
+
+}
+
+#define enter_lazy_tlb(mm, tsk)
+
+#endif /* __ASM_ARC_MMU_CONTEXT_H */
diff --git a/arch/arc/include/asm/module.h b/arch/arc/include/asm/module.h
new file mode 100644
index 000000000000..518222bb3f8e
--- /dev/null
+++ b/arch/arc/include/asm/module.h
@@ -0,0 +1,28 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Amit Bhor, Sameer Dhavale: Codito Technologies 2004
+
+ */
+
+#ifndef _ASM_ARC_MODULE_H
+#define _ASM_ARC_MODULE_H
+
+#include <asm-generic/module.h>
+
+#ifdef CONFIG_ARC_DW2_UNWIND
+struct mod_arch_specific {
+	void *unw_info;
+	int unw_sec_idx;
+};
+#endif
+
+#define MODULE_PROC_FAMILY "ARC700"
+
+#define MODULE_ARCH_VERMAGIC MODULE_PROC_FAMILY
+
+#endif /* _ASM_ARC_MODULE_H */
diff --git a/arch/arc/include/asm/mutex.h b/arch/arc/include/asm/mutex.h
new file mode 100644
index 000000000000..a2f88ff9f506
--- /dev/null
+++ b/arch/arc/include/asm/mutex.h
@@ -0,0 +1,18 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*
+ * xchg() based mutex fast path maintains a state of 0 or 1, as opposed to
+ * atomic dec based which can "count" any number of lock contenders.
+ * This ideally needs to be fixed in core, but for now switching to dec ver.
+ */
+#if defined(CONFIG_SMP) && (CONFIG_NR_CPUS > 2)
+#include <asm-generic/mutex-dec.h>
+#else
+#include <asm-generic/mutex-xchg.h>
+#endif
diff --git a/arch/arc/include/asm/page.h b/arch/arc/include/asm/page.h
new file mode 100644
index 000000000000..bdf546104551
--- /dev/null
+++ b/arch/arc/include/asm/page.h
@@ -0,0 +1,109 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __ASM_ARC_PAGE_H
+#define __ASM_ARC_PAGE_H
+
+#include <uapi/asm/page.h>
+
+
+#ifndef __ASSEMBLY__
+
+#define get_user_page(vaddr)		__get_free_page(GFP_KERNEL)
+#define free_user_page(page, addr)	free_page(addr)
+
+/* TBD: for now don't worry about VIPT D$ aliasing */
+#define clear_page(paddr)		memset((paddr), 0, PAGE_SIZE)
+#define copy_page(to, from)		memcpy((to), (from), PAGE_SIZE)
+
+#define clear_user_page(addr, vaddr, pg)	clear_page(addr)
+#define copy_user_page(vto, vfrom, vaddr, pg)	copy_page(vto, vfrom)
+
+#undef STRICT_MM_TYPECHECKS
+
+#ifdef STRICT_MM_TYPECHECKS
+/*
+ * These are used to make use of C type-checking..
+ */
+typedef struct {
+	unsigned long pte;
+} pte_t;
+typedef struct {
+	unsigned long pgd;
+} pgd_t;
+typedef struct {
+	unsigned long pgprot;
+} pgprot_t;
+typedef unsigned long pgtable_t;
+
+#define pte_val(x)      ((x).pte)
+#define pgd_val(x)      ((x).pgd)
+#define pgprot_val(x)   ((x).pgprot)
+
+#define __pte(x)        ((pte_t) { (x) })
+#define __pgd(x)        ((pgd_t) { (x) })
+#define __pgprot(x)     ((pgprot_t) { (x) })
+
+#define pte_pgprot(x) __pgprot(pte_val(x))
+
+#else /* !STRICT_MM_TYPECHECKS */
+
+typedef unsigned long pte_t;
+typedef unsigned long pgd_t;
+typedef unsigned long pgprot_t;
+typedef unsigned long pgtable_t;
+
+#define pte_val(x)	(x)
+#define pgd_val(x)	(x)
+#define pgprot_val(x)	(x)
+#define __pte(x)	(x)
+#define __pgprot(x)	(x)
+#define pte_pgprot(x)	(x)
+
+#endif
+
+#define ARCH_PFN_OFFSET     (CONFIG_LINUX_LINK_BASE >> PAGE_SHIFT)
+
+#define pfn_valid(pfn)      (((pfn) - ARCH_PFN_OFFSET) < max_mapnr)
+
+/*
+ * __pa, __va, virt_to_page (ALERT: deprecated, don't use them)
+ *
+ * These macros have historically been misnamed
+ * virt here means link-address/program-address as embedded in object code.
+ * So if kernel img is linked at 0x8000_0000 onwards, 0x8010_0000 will be
+ * 128th page, and virt_to_page( ) will return the struct page corresp to it.
+ * mem_map[ ] is an array of struct page for each page frame in the system
+ *
+ * Independent of where linux is linked at, link-addr = physical address
+ * So the old macro  __pa = vaddr + PAGE_OFFSET - CONFIG_LINUX_LINK_BASE
+ * would have been wrong in case kernel is not at 0x8zs
+ */
+#define __pa(vaddr)  ((unsigned long)vaddr)
+#define __va(paddr)  ((void *)((unsigned long)(paddr)))
+
+#define virt_to_page(kaddr)	\
+	(mem_map + ((__pa(kaddr) - CONFIG_LINUX_LINK_BASE) >> PAGE_SHIFT))
+
+#define virt_addr_valid(kaddr)  pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
+
+/* Default Permissions for page, used in mmap.c */
+#ifdef CONFIG_ARC_STACK_NONEXEC
+#define VM_DATA_DEFAULT_FLAGS   (VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE)
+#else
+#define VM_DATA_DEFAULT_FLAGS   (VM_READ | VM_WRITE | VM_EXEC | \
+				 VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
+#endif
+
+#define WANT_PAGE_VIRTUAL   1
+
+#include <asm-generic/memory_model.h>   /* page_to_pfn, pfn_to_page */
+#include <asm-generic/getorder.h>
+
+#endif /* !__ASSEMBLY__ */
+
+#endif
diff --git a/arch/arc/include/asm/perf_event.h b/arch/arc/include/asm/perf_event.h
new file mode 100644
index 000000000000..115ad96480e6
--- /dev/null
+++ b/arch/arc/include/asm/perf_event.h
@@ -0,0 +1,13 @@
+/*
+ * Copyright (C) 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#ifndef __ASM_PERF_EVENT_H
+#define __ASM_PERF_EVENT_H
+
+#endif /* __ASM_PERF_EVENT_H */
diff --git a/arch/arc/include/asm/pgalloc.h b/arch/arc/include/asm/pgalloc.h
new file mode 100644
index 000000000000..36a9f20c21a3
--- /dev/null
+++ b/arch/arc/include/asm/pgalloc.h
@@ -0,0 +1,134 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * vineetg: June 2011
+ *  -"/proc/meminfo | grep PageTables" kept on increasing
+ *   Recently added pgtable dtor was not getting called.
+ *
+ * vineetg: May 2011
+ *  -Variable pg-sz means that Page Tables could be variable sized themselves
+ *    So calculate it based on addr traversal split [pgd-bits:pte-bits:xxx]
+ *  -Page Table size capped to max 1 to save memory - hence verified.
+ *  -Since these deal with constants, gcc compile-time optimizes them.
+ *
+ * vineetg: Nov 2010
+ *  -Added pgtable ctor/dtor used for pgtable mem accounting
+ *
+ * vineetg: April 2010
+ *  -Switched pgtable_t from being struct page * to unsigned long
+ *      =Needed so that Page Table allocator (pte_alloc_one) is not forced to
+ *       to deal with struct page. Thay way in future we can make it allocate
+ *       multiple PG Tbls in one Page Frame
+ *      =sweet side effect is avoiding calls to ugly page_address( ) from the
+ *       pg-tlb allocator sub-sys (pte_alloc_one, ptr_free, pmd_populate
+ *
+ *  Amit Bhor, Sameer Dhavale: Codito Technologies 2004
+ */
+
+#ifndef _ASM_ARC_PGALLOC_H
+#define _ASM_ARC_PGALLOC_H
+
+#include <linux/mm.h>
+#include <linux/log2.h>
+
+static inline void
+pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte)
+{
+	pmd_set(pmd, pte);
+}
+
+static inline void
+pmd_populate(struct mm_struct *mm, pmd_t *pmd, pgtable_t ptep)
+{
+	pmd_set(pmd, (pte_t *) ptep);
+}
+
+static inline int __get_order_pgd(void)
+{
+	return get_order(PTRS_PER_PGD * 4);
+}
+
+static inline pgd_t *pgd_alloc(struct mm_struct *mm)
+{
+	int num, num2;
+	pgd_t *ret = (pgd_t *) __get_free_pages(GFP_KERNEL, __get_order_pgd());
+
+	if (ret) {
+		num = USER_PTRS_PER_PGD + USER_KERNEL_GUTTER / PGDIR_SIZE;
+		memzero(ret, num * sizeof(pgd_t));
+
+		num2 = VMALLOC_SIZE / PGDIR_SIZE;
+		memcpy(ret + num, swapper_pg_dir + num, num2 * sizeof(pgd_t));
+
+		memzero(ret + num + num2,
+			       (PTRS_PER_PGD - num - num2) * sizeof(pgd_t));
+
+	}
+	return ret;
+}
+
+static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
+{
+	free_pages((unsigned long)pgd, __get_order_pgd());
+}
+
+
+/*
+ * With software-only page-tables, addr-split for traversal is tweakable and
+ * that directly governs how big tables would be at each level.
+ * Further, the MMU page size is configurable.
+ * Thus we need to programatically assert the size constraint
+ * All of this is const math, allowing gcc to do constant folding/propagation.
+ */
+
+static inline int __get_order_pte(void)
+{
+	return get_order(PTRS_PER_PTE * 4);
+}
+
+static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
+					unsigned long address)
+{
+	pte_t *pte;
+
+	pte = (pte_t *) __get_free_pages(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO,
+					 __get_order_pte());
+
+	return pte;
+}
+
+static inline pgtable_t
+pte_alloc_one(struct mm_struct *mm, unsigned long address)
+{
+	pgtable_t pte_pg;
+
+	pte_pg = __get_free_pages(GFP_KERNEL | __GFP_REPEAT, __get_order_pte());
+	if (pte_pg) {
+		memzero((void *)pte_pg, PTRS_PER_PTE * 4);
+		pgtable_page_ctor(virt_to_page(pte_pg));
+	}
+
+	return pte_pg;
+}
+
+static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
+{
+	free_pages((unsigned long)pte, __get_order_pte()); /* takes phy addr */
+}
+
+static inline void pte_free(struct mm_struct *mm, pgtable_t ptep)
+{
+	pgtable_page_dtor(virt_to_page(ptep));
+	free_pages(ptep, __get_order_pte());
+}
+
+#define __pte_free_tlb(tlb, pte, addr)  pte_free((tlb)->mm, pte)
+
+#define check_pgt_cache()   do { } while (0)
+#define pmd_pgtable(pmd) pmd_page_vaddr(pmd)
+
+#endif /* _ASM_ARC_PGALLOC_H */
diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h
new file mode 100644
index 000000000000..b7e36684c091
--- /dev/null
+++ b/arch/arc/include/asm/pgtable.h
@@ -0,0 +1,405 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * vineetg: May 2011
+ *  -Folded PAGE_PRESENT (used by VM) and PAGE_VALID (used by MMU) into 1.
+ *     They are semantically the same although in different contexts
+ *     VALID marks a TLB entry exists and it will only happen if PRESENT
+ *  - Utilise some unused free bits to confine PTE flags to 12 bits
+ *     This is a must for 4k pg-sz
+ *
+ * vineetg: Mar 2011 - changes to accomodate MMU TLB Page Descriptor mods
+ *  -TLB Locking never really existed, except for initial specs
+ *  -SILENT_xxx not needed for our port
+ *  -Per my request, MMU V3 changes the layout of some of the bits
+ *     to avoid a few shifts in TLB Miss handlers.
+ *
+ * vineetg: April 2010
+ *  -PGD entry no longer contains any flags. If empty it is 0, otherwise has
+ *   Pg-Tbl ptr. Thus pmd_present(), pmd_valid(), pmd_set( ) become simpler
+ *
+ * vineetg: April 2010
+ *  -Switched form 8:11:13 split for page table lookup to 11:8:13
+ *  -this speeds up page table allocation itself as we now have to memset 1K
+ *    instead of 8k per page table.
+ * -TODO: Right now page table alloc is 8K and rest 7K is unused
+ *    need to optimise it
+ *
+ * Amit Bhor, Sameer Dhavale: Codito Technologies 2004
+ */
+
+#ifndef _ASM_ARC_PGTABLE_H
+#define _ASM_ARC_PGTABLE_H
+
+#include <asm/page.h>
+#include <asm/mmu.h>
+#include <asm-generic/pgtable-nopmd.h>
+
+/**************************************************************************
+ * Page Table Flags
+ *
+ * ARC700 MMU only deals with softare managed TLB entries.
+ * Page Tables are purely for Linux VM's consumption and the bits below are
+ * suited to that (uniqueness). Hence some are not implemented in the TLB and
+ * some have different value in TLB.
+ * e.g. MMU v2: K_READ bit is 8 and so is GLOBAL (possible becoz they live in
+ *      seperate PD0 and PD1, which combined forms a translation entry)
+ *      while for PTE perspective, they are 8 and 9 respectively
+ * with MMU v3: Most bits (except SHARED) represent the exact hardware pos
+ *      (saves some bit shift ops in TLB Miss hdlrs)
+ */
+
+#if (CONFIG_ARC_MMU_VER <= 2)
+
+#define _PAGE_ACCESSED      (1<<1)	/* Page is accessed (S) */
+#define _PAGE_CACHEABLE     (1<<2)	/* Page is cached (H) */
+#define _PAGE_EXECUTE       (1<<3)	/* Page has user execute perm (H) */
+#define _PAGE_WRITE         (1<<4)	/* Page has user write perm (H) */
+#define _PAGE_READ          (1<<5)	/* Page has user read perm (H) */
+#define _PAGE_K_EXECUTE     (1<<6)	/* Page has kernel execute perm (H) */
+#define _PAGE_K_WRITE       (1<<7)	/* Page has kernel write perm (H) */
+#define _PAGE_K_READ        (1<<8)	/* Page has kernel perm (H) */
+#define _PAGE_GLOBAL        (1<<9)	/* Page is global (H) */
+#define _PAGE_MODIFIED      (1<<10)	/* Page modified (dirty) (S) */
+#define _PAGE_FILE          (1<<10)	/* page cache/ swap (S) */
+#define _PAGE_PRESENT       (1<<11)	/* TLB entry is valid (H) */
+
+#else
+
+/* PD1 */
+#define _PAGE_CACHEABLE     (1<<0)	/* Page is cached (H) */
+#define _PAGE_EXECUTE       (1<<1)	/* Page has user execute perm (H) */
+#define _PAGE_WRITE         (1<<2)	/* Page has user write perm (H) */
+#define _PAGE_READ          (1<<3)	/* Page has user read perm (H) */
+#define _PAGE_K_EXECUTE     (1<<4)	/* Page has kernel execute perm (H) */
+#define _PAGE_K_WRITE       (1<<5)	/* Page has kernel write perm (H) */
+#define _PAGE_K_READ        (1<<6)	/* Page has kernel perm (H) */
+#define _PAGE_ACCESSED      (1<<7)	/* Page is accessed (S) */
+
+/* PD0 */
+#define _PAGE_GLOBAL        (1<<8)	/* Page is global (H) */
+#define _PAGE_PRESENT       (1<<9)	/* TLB entry is valid (H) */
+#define _PAGE_SHARED_CODE   (1<<10)	/* Shared Code page with cmn vaddr
+					   usable for shared TLB entries (H) */
+
+#define _PAGE_MODIFIED      (1<<11)	/* Page modified (dirty) (S) */
+#define _PAGE_FILE          (1<<12)	/* page cache/ swap (S) */
+
+#define _PAGE_SHARED_CODE_H (1<<31)	/* Hardware counterpart of above */
+#endif
+
+/* Kernel allowed all permissions for all pages */
+#define _K_PAGE_PERMS  (_PAGE_K_EXECUTE | _PAGE_K_WRITE | _PAGE_K_READ)
+
+#ifdef CONFIG_ARC_CACHE_PAGES
+#define _PAGE_DEF_CACHEABLE _PAGE_CACHEABLE
+#else
+#define _PAGE_DEF_CACHEABLE (0)
+#endif
+
+/* Helper for every "user" page
+ * -kernel can R/W/X
+ * -by default cached, unless config otherwise
+ * -present in memory
+ */
+#define ___DEF (_PAGE_PRESENT | _K_PAGE_PERMS | _PAGE_DEF_CACHEABLE)
+
+/* Set of bits not changed in pte_modify */
+#define _PAGE_CHG_MASK	(PAGE_MASK | _PAGE_ACCESSED | _PAGE_MODIFIED)
+
+/* More Abbrevaited helpers */
+#define PAGE_U_NONE     __pgprot(___DEF)
+#define PAGE_U_R        __pgprot(___DEF | _PAGE_READ)
+#define PAGE_U_W_R      __pgprot(___DEF | _PAGE_READ | _PAGE_WRITE)
+#define PAGE_U_X_R      __pgprot(___DEF | _PAGE_READ | _PAGE_EXECUTE)
+#define PAGE_U_X_W_R    __pgprot(___DEF | _PAGE_READ | _PAGE_WRITE | \
+						       _PAGE_EXECUTE)
+
+#define PAGE_SHARED	PAGE_U_W_R
+
+/* While kernel runs out of unstrslated space, vmalloc/modules use a chunk of
+ * kernel vaddr space - visible in all addr spaces, but kernel mode only
+ * Thus Global, all-kernel-access, no-user-access, cached
+ */
+#define PAGE_KERNEL          __pgprot(___DEF | _PAGE_GLOBAL)
+
+/* ioremap */
+#define PAGE_KERNEL_NO_CACHE __pgprot(_PAGE_PRESENT | _K_PAGE_PERMS | \
+						     _PAGE_GLOBAL)
+
+/**************************************************************************
+ * Mapping of vm_flags (Generic VM) to PTE flags (arch specific)
+ *
+ * Certain cases have 1:1 mapping
+ *  e.g. __P101 means VM_READ, VM_EXEC and !VM_SHARED
+ *       which directly corresponds to  PAGE_U_X_R
+ *
+ * Other rules which cause the divergence from 1:1 mapping
+ *
+ *  1. Although ARC700 can do exclusive execute/write protection (meaning R
+ *     can be tracked independet of X/W unlike some other CPUs), still to
+ *     keep things consistent with other archs:
+ *      -Write implies Read:   W => R
+ *      -Execute implies Read: X => R
+ *
+ *  2. Pvt Writable doesn't have Write Enabled initially: Pvt-W => !W
+ *     This is to enable COW mechanism
+ */
+	/* xwr */
+#define __P000  PAGE_U_NONE
+#define __P001  PAGE_U_R
+#define __P010  PAGE_U_R	/* Pvt-W => !W */
+#define __P011  PAGE_U_R	/* Pvt-W => !W */
+#define __P100  PAGE_U_X_R	/* X => R */
+#define __P101  PAGE_U_X_R
+#define __P110  PAGE_U_X_R	/* Pvt-W => !W and X => R */
+#define __P111  PAGE_U_X_R	/* Pvt-W => !W */
+
+#define __S000  PAGE_U_NONE
+#define __S001  PAGE_U_R
+#define __S010  PAGE_U_W_R	/* W => R */
+#define __S011  PAGE_U_W_R
+#define __S100  PAGE_U_X_R	/* X => R */
+#define __S101  PAGE_U_X_R
+#define __S110  PAGE_U_X_W_R	/* X => R */
+#define __S111  PAGE_U_X_W_R
+
+/****************************************************************
+ * Page Table Lookup split
+ *
+ * We implement 2 tier paging and since this is all software, we are free
+ * to customize the span of a PGD / PTE entry to suit us
+ *
+ *			32 bit virtual address
+ * -------------------------------------------------------
+ * | BITS_FOR_PGD    |  BITS_FOR_PTE    |  BITS_IN_PAGE  |
+ * -------------------------------------------------------
+ *       |                  |                |
+ *       |                  |                --> off in page frame
+ *       |		    |
+ *       |                  ---> index into Page Table
+ *       |
+ *       ----> index into Page Directory
+ */
+
+#define BITS_IN_PAGE	PAGE_SHIFT
+
+/* Optimal Sizing of Pg Tbl - based on MMU page size */
+#if defined(CONFIG_ARC_PAGE_SIZE_8K)
+#define BITS_FOR_PTE	8
+#elif defined(CONFIG_ARC_PAGE_SIZE_16K)
+#define BITS_FOR_PTE	8
+#elif defined(CONFIG_ARC_PAGE_SIZE_4K)
+#define BITS_FOR_PTE	9
+#endif
+
+#define BITS_FOR_PGD	(32 - BITS_FOR_PTE - BITS_IN_PAGE)
+
+#define PGDIR_SHIFT	(BITS_FOR_PTE + BITS_IN_PAGE)
+#define PGDIR_SIZE	(1UL << PGDIR_SHIFT)	/* vaddr span, not PDG sz */
+#define PGDIR_MASK	(~(PGDIR_SIZE-1))
+
+#ifdef __ASSEMBLY__
+#define	PTRS_PER_PTE	(1 << BITS_FOR_PTE)
+#define	PTRS_PER_PGD	(1 << BITS_FOR_PGD)
+#else
+#define	PTRS_PER_PTE	(1UL << BITS_FOR_PTE)
+#define	PTRS_PER_PGD	(1UL << BITS_FOR_PGD)
+#endif
+/*
+ * Number of entries a user land program use.
+ * TASK_SIZE is the maximum vaddr that can be used by a userland program.
+ */
+#define	USER_PTRS_PER_PGD	(TASK_SIZE / PGDIR_SIZE)
+
+/*
+ * No special requirements for lowest virtual address we permit any user space
+ * mapping to be mapped at.
+ */
+#define FIRST_USER_ADDRESS      0
+
+
+/****************************************************************
+ * Bucket load of VM Helpers
+ */
+
+#ifndef __ASSEMBLY__
+
+#define pte_ERROR(e) \
+	pr_crit("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, pte_val(e))
+#define pgd_ERROR(e) \
+	pr_crit("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
+
+/* the zero page used for uninitialized and anonymous pages */
+extern char empty_zero_page[PAGE_SIZE];
+#define ZERO_PAGE(vaddr)	(virt_to_page(empty_zero_page))
+
+#define pte_unmap(pte)		do { } while (0)
+#define pte_unmap_nested(pte)		do { } while (0)
+
+#define set_pte(pteptr, pteval)	((*(pteptr)) = (pteval))
+#define set_pmd(pmdptr, pmdval)	(*(pmdptr) = pmdval)
+
+/* find the page descriptor of the Page Tbl ref by PMD entry */
+#define pmd_page(pmd)		virt_to_page(pmd_val(pmd) & PAGE_MASK)
+
+/* find the logical addr (phy for ARC) of the Page Tbl ref by PMD entry */
+#define pmd_page_vaddr(pmd)	(pmd_val(pmd) & PAGE_MASK)
+
+/* In a 2 level sys, setup the PGD entry with PTE value */
+static inline void pmd_set(pmd_t *pmdp, pte_t *ptep)
+{
+	pmd_val(*pmdp) = (unsigned long)ptep;
+}
+
+#define pte_none(x)			(!pte_val(x))
+#define pte_present(x)			(pte_val(x) & _PAGE_PRESENT)
+#define pte_clear(mm, addr, ptep)	set_pte_at(mm, addr, ptep, __pte(0))
+
+#define pmd_none(x)			(!pmd_val(x))
+#define	pmd_bad(x)			((pmd_val(x) & ~PAGE_MASK))
+#define pmd_present(x)			(pmd_val(x))
+#define pmd_clear(xp)			do { pmd_val(*(xp)) = 0; } while (0)
+
+#define pte_page(x) (mem_map + \
+		(unsigned long)(((pte_val(x) - PAGE_OFFSET) >> PAGE_SHIFT)))
+
+#define mk_pte(page, pgprot)						\
+({									\
+	pte_t pte;							\
+	pte_val(pte) = __pa(page_address(page)) + pgprot_val(pgprot);	\
+	pte;								\
+})
+
+/* TBD: Non linear mapping stuff */
+static inline int pte_file(pte_t pte)
+{
+	return pte_val(pte) & _PAGE_FILE;
+}
+
+#define PTE_FILE_MAX_BITS	30
+#define pgoff_to_pte(x)         __pte(x)
+#define pte_to_pgoff(x)		(pte_val(x) >> 2)
+#define pte_pfn(pte)		(pte_val(pte) >> PAGE_SHIFT)
+#define pfn_pte(pfn, prot)	(__pte(((pfn) << PAGE_SHIFT) | pgprot_val(prot)))
+#define __pte_index(addr)	(((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
+
+/*
+ * pte_offset gets a @ptr to PMD entry (PGD in our 2-tier paging system)
+ * and returns ptr to PTE entry corresponding to @addr
+ */
+#define pte_offset(dir, addr) ((pte_t *)(pmd_page_vaddr(*dir)) +\
+					 __pte_index(addr))
+
+/* No mapping of Page Tables in high mem etc, so following same as above */
+#define pte_offset_kernel(dir, addr)		pte_offset(dir, addr)
+#define pte_offset_map(dir, addr)		pte_offset(dir, addr)
+
+/* Zoo of pte_xxx function */
+#define pte_read(pte)		(pte_val(pte) & _PAGE_READ)
+#define pte_write(pte)		(pte_val(pte) & _PAGE_WRITE)
+#define pte_dirty(pte)		(pte_val(pte) & _PAGE_MODIFIED)
+#define pte_young(pte)		(pte_val(pte) & _PAGE_ACCESSED)
+#define pte_special(pte)	(0)
+
+#define PTE_BIT_FUNC(fn, op) \
+	static inline pte_t pte_##fn(pte_t pte) { pte_val(pte) op; return pte; }
+
+PTE_BIT_FUNC(wrprotect,	&= ~(_PAGE_WRITE));
+PTE_BIT_FUNC(mkwrite,	|= (_PAGE_WRITE));
+PTE_BIT_FUNC(mkclean,	&= ~(_PAGE_MODIFIED));
+PTE_BIT_FUNC(mkdirty,	|= (_PAGE_MODIFIED));
+PTE_BIT_FUNC(mkold,	&= ~(_PAGE_ACCESSED));
+PTE_BIT_FUNC(mkyoung,	|= (_PAGE_ACCESSED));
+PTE_BIT_FUNC(exprotect,	&= ~(_PAGE_EXECUTE));
+PTE_BIT_FUNC(mkexec,	|= (_PAGE_EXECUTE));
+
+static inline pte_t pte_mkspecial(pte_t pte) { return pte; }
+
+static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
+{
+	return __pte((pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot));
+}
+
+/* Macro to mark a page protection as uncacheable */
+#define pgprot_noncached(prot)	(__pgprot(pgprot_val(prot) & ~_PAGE_CACHEABLE))
+
+static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
+			      pte_t *ptep, pte_t pteval)
+{
+	set_pte(ptep, pteval);
+}
+
+/*
+ * All kernel related VM pages are in init's mm.
+ */
+#define pgd_offset_k(address)	pgd_offset(&init_mm, address)
+#define pgd_index(addr)		((addr) >> PGDIR_SHIFT)
+#define pgd_offset(mm, addr)	(((mm)->pgd)+pgd_index(addr))
+
+/*
+ * Macro to quickly access the PGD entry, utlising the fact that some
+ * arch may cache the pointer to Page Directory of "current" task
+ * in a MMU register
+ *
+ * Thus task->mm->pgd (3 pointer dereferences, cache misses etc simply
+ * becomes read a register
+ *
+ * ********CAUTION*******:
+ * Kernel code might be dealing with some mm_struct of NON "current"
+ * Thus use this macro only when you are certain that "current" is current
+ * e.g. when dealing with signal frame setup code etc
+ */
+#ifndef CONFIG_SMP
+#define pgd_offset_fast(mm, addr)	\
+({					\
+	pgd_t *pgd_base = (pgd_t *) read_aux_reg(ARC_REG_SCRATCH_DATA0);  \
+	pgd_base + pgd_index(addr);	\
+})
+#else
+#define pgd_offset_fast(mm, addr)	pgd_offset(mm, addr)
+#endif
+
+extern void paging_init(void);
+extern pgd_t swapper_pg_dir[] __aligned(PAGE_SIZE);
+void update_mmu_cache(struct vm_area_struct *vma, unsigned long address,
+		      pte_t *ptep);
+
+/* Encode swap {type,off} tuple into PTE
+ * We reserve 13 bits for 5-bit @type, keeping bits 12-5 zero, ensuring that
+ * both PAGE_FILE and PAGE_PRESENT are zero in a PTE holding swap "identifier"
+ */
+#define __swp_entry(type, off)	((swp_entry_t) { \
+					((type) & 0x1f) | ((off) << 13) })
+
+/* Decode a PTE containing swap "identifier "into constituents */
+#define __swp_type(pte_lookalike)	(((pte_lookalike).val) & 0x1f)
+#define __swp_offset(pte_lookalike)	((pte_lookalike).val << 13)
+
+/* NOPs, to keep generic kernel happy */
+#define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val(pte) })
+#define __swp_entry_to_pte(x)	((pte_t) { (x).val })
+
+#define kern_addr_valid(addr)	(1)
+
+/*
+ * remap a physical page `pfn' of size `size' with page protection `prot'
+ * into virtual address `from'
+ */
+#define io_remap_pfn_range(vma, from, pfn, size, prot) \
+			remap_pfn_range(vma, from, pfn, size, prot)
+
+#include <asm-generic/pgtable.h>
+
+/*
+ * No page table caches to initialise
+ */
+#define pgtable_cache_init()   do { } while (0)
+
+#endif /* __ASSEMBLY__ */
+
+#endif
diff --git a/arch/arc/include/asm/processor.h b/arch/arc/include/asm/processor.h
new file mode 100644
index 000000000000..5f26b2c1cba0
--- /dev/null
+++ b/arch/arc/include/asm/processor.h
@@ -0,0 +1,151 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * vineetg: March 2009
+ *  -Implemented task_pt_regs( )
+ *
+ * Amit Bhor, Sameer Dhavale, Ashwin Chaugule: Codito Technologies 2004
+ */
+
+#ifndef __ASM_ARC_PROCESSOR_H
+#define __ASM_ARC_PROCESSOR_H
+
+#ifdef __KERNEL__
+
+#ifndef __ASSEMBLY__
+
+#include <asm/arcregs.h>	/* for STATUS_E1_MASK et all */
+
+/* Arch specific stuff which needs to be saved per task.
+ * However these items are not so important so as to earn a place in
+ * struct thread_info
+ */
+struct thread_struct {
+	unsigned long ksp;	/* kernel mode stack pointer */
+	unsigned long callee_reg;	/* pointer to callee regs */
+	unsigned long fault_address;	/* dbls as brkpt holder as well */
+	unsigned long cause_code;	/* Exception Cause Code (ECR) */
+#ifdef CONFIG_ARC_CURR_IN_REG
+	unsigned long user_r25;
+#endif
+#ifdef CONFIG_ARC_FPU_SAVE_RESTORE
+	struct arc_fpu fpu;
+#endif
+};
+
+#define INIT_THREAD  {                          \
+	.ksp = sizeof(init_stack) + (unsigned long) init_stack, \
+}
+
+/* Forward declaration, a strange C thing */
+struct task_struct;
+
+/*
+ * Return saved PC of a blocked thread.
+ */
+unsigned long thread_saved_pc(struct task_struct *t);
+
+#define task_pt_regs(p) \
+	((struct pt_regs *)(THREAD_SIZE - 4 + (void *)task_stack_page(p)) - 1)
+
+/* Free all resources held by a thread. */
+#define release_thread(thread) do { } while (0)
+
+/* Prepare to copy thread state - unlazy all lazy status */
+#define prepare_to_copy(tsk)    do { } while (0)
+
+/*
+ * A lot of busy-wait loops in SMP are based off of non-volatile data otherwise
+ * get optimised away by gcc
+ */
+#ifdef CONFIG_SMP
+#define cpu_relax()	__asm__ __volatile__ ("" : : : "memory")
+#else
+#define cpu_relax()	do { } while (0)
+#endif
+
+#define copy_segments(tsk, mm)      do { } while (0)
+#define release_segments(mm)        do { } while (0)
+
+#define KSTK_EIP(tsk)   (task_pt_regs(tsk)->ret)
+
+/*
+ * Where abouts of Task's sp, fp, blink when it was last seen in kernel mode.
+ * These can't be derived from pt_regs as that would give correp user-mode val
+ */
+#define KSTK_ESP(tsk)   (tsk->thread.ksp)
+#define KSTK_BLINK(tsk) (*((unsigned int *)((KSTK_ESP(tsk)) + (13+1+1)*4)))
+#define KSTK_FP(tsk)    (*((unsigned int *)((KSTK_ESP(tsk)) + (13+1)*4)))
+
+/*
+ * Do necessary setup to start up a newly executed thread.
+ *
+ * E1,E2 so that Interrupts are enabled in user mode
+ * L set, so Loop inhibited to begin with
+ * lp_start and lp_end seeded with bogus non-zero values so to easily catch
+ * the ARC700 sr to lp_start hardware bug
+ */
+#define start_thread(_regs, _pc, _usp)				\
+do {								\
+	set_fs(USER_DS); /* reads from user space */		\
+	(_regs)->ret = (_pc);					\
+	/* Interrupts enabled in User Mode */			\
+	(_regs)->status32 = STATUS_U_MASK | STATUS_L_MASK	\
+		| STATUS_E1_MASK | STATUS_E2_MASK;		\
+	(_regs)->sp = (_usp);					\
+	/* bogus seed values for debugging */			\
+	(_regs)->lp_start = 0x10;				\
+	(_regs)->lp_end = 0x80;					\
+} while (0)
+
+extern unsigned int get_wchan(struct task_struct *p);
+
+/*
+ * Default implementation of macro that returns current
+ * instruction pointer ("program counter").
+ * Should the PC register be read instead ? This macro does not seem to
+ * be used in many places so this wont be all that bad.
+ */
+#define current_text_addr() ({ __label__ _l; _l: &&_l; })
+
+#endif /* !__ASSEMBLY__ */
+
+/* Kernels Virtual memory area.
+ * Unlike other architectures(MIPS, sh, cris ) ARC 700 does not have a
+ * "kernel translated" region (like KSEG2 in MIPS). So we use a upper part
+ * of the translated bottom 2GB for kernel virtual memory and protect
+ * these pages from user accesses by disabling Ru, Eu and Wu.
+ */
+#define VMALLOC_SIZE	(0x10000000)	/* 256M */
+#define VMALLOC_START	(PAGE_OFFSET - VMALLOC_SIZE)
+#define VMALLOC_END	(PAGE_OFFSET)
+
+/* Most of the architectures seem to be keeping some kind of padding between
+ * userspace TASK_SIZE and PAGE_OFFSET. i.e TASK_SIZE != PAGE_OFFSET.
+ */
+#define USER_KERNEL_GUTTER    0x10000000
+
+/* User address space:
+ * On ARC700, CPU allows the entire lower half of 32 bit address space to be
+ * translated. Thus potentially 2G (0:0x7FFF_FFFF) could be User vaddr space.
+ * However we steal 256M for kernel addr (0x7000_0000:0x7FFF_FFFF) and another
+ * 256M (0x6000_0000:0x6FFF_FFFF) is gutter between user/kernel spaces
+ * Thus total User vaddr space is (0:0x5FFF_FFFF)
+ */
+#define TASK_SIZE	(PAGE_OFFSET - VMALLOC_SIZE - USER_KERNEL_GUTTER)
+
+#define STACK_TOP       TASK_SIZE
+#define STACK_TOP_MAX   STACK_TOP
+
+/* This decides where the kernel will search for a free chunk of vm
+ * space during mmap's.
+ */
+#define TASK_UNMAPPED_BASE      (TASK_SIZE / 3)
+
+#endif /* __KERNEL__ */
+
+#endif /* __ASM_ARC_PROCESSOR_H */
diff --git a/arch/arc/include/asm/prom.h b/arch/arc/include/asm/prom.h
new file mode 100644
index 000000000000..692d0d0789a7
--- /dev/null
+++ b/arch/arc/include/asm/prom.h
@@ -0,0 +1,14 @@
+/*
+ * Copyright (C) 2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_ARC_PROM_H_
+#define _ASM_ARC_PROM_H_
+
+#define HAVE_ARCH_DEVTREE_FIXUPS
+
+#endif
diff --git a/arch/arc/include/asm/ptrace.h b/arch/arc/include/asm/ptrace.h
new file mode 100644
index 000000000000..8ae783d20a81
--- /dev/null
+++ b/arch/arc/include/asm/ptrace.h
@@ -0,0 +1,130 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Amit Bhor, Sameer Dhavale: Codito Technologies 2004
+ */
+#ifndef __ASM_ARC_PTRACE_H
+#define __ASM_ARC_PTRACE_H
+
+#include <uapi/asm/ptrace.h>
+
+#ifndef __ASSEMBLY__
+
+/* THE pt_regs: Defines how regs are saved during entry into kernel */
+
+struct pt_regs {
+	/*
+	 * 1 word gutter after reg-file has been saved
+	 * Technically not needed, Since SP always points to a "full" location
+	 * (vs. "empty"). But pt_regs is shared with tools....
+	 */
+	long res;
+
+	/* Real registers */
+	long bta;	/* bta_l1, bta_l2, erbta */
+	long lp_start;
+	long lp_end;
+	long lp_count;
+	long status32;	/* status32_l1, status32_l2, erstatus */
+	long ret;	/* ilink1, ilink2 or eret */
+	long blink;
+	long fp;
+	long r26;	/* gp */
+	long r12;
+	long r11;
+	long r10;
+	long r9;
+	long r8;
+	long r7;
+	long r6;
+	long r5;
+	long r4;
+	long r3;
+	long r2;
+	long r1;
+	long r0;
+	long sp;	/* user/kernel sp depending on where we came from  */
+	long orig_r0;
+
+	/*to distinguish bet excp, syscall, irq */
+	union {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+		/* so that assembly code is same for LE/BE */
+		unsigned long orig_r8:16, event:16;
+#else
+		unsigned long event:16, orig_r8:16;
+#endif
+		long orig_r8_word;
+	};
+};
+
+/* Callee saved registers - need to be saved only when you are scheduled out */
+
+struct callee_regs {
+	long res;	/* Again this is not needed */
+	long r25;
+	long r24;
+	long r23;
+	long r22;
+	long r21;
+	long r20;
+	long r19;
+	long r18;
+	long r17;
+	long r16;
+	long r15;
+	long r14;
+	long r13;
+};
+
+#define instruction_pointer(regs)	((regs)->ret)
+#define profile_pc(regs)		instruction_pointer(regs)
+
+/* return 1 if user mode or 0 if kernel mode */
+#define user_mode(regs) (regs->status32 & STATUS_U_MASK)
+
+#define user_stack_pointer(regs)\
+({  unsigned int sp;		\
+	if (user_mode(regs))	\
+		sp = (regs)->sp;\
+	else			\
+		sp = -1;	\
+	sp;			\
+})
+
+/* return 1 if PC in delay slot */
+#define delay_mode(regs) ((regs->status32 & STATUS_DE_MASK) == STATUS_DE_MASK)
+
+#define in_syscall(regs)    (regs->event & orig_r8_IS_SCALL)
+#define in_brkpt_trap(regs) (regs->event & orig_r8_IS_BRKPT)
+
+#define syscall_wont_restart(regs) (regs->event |= orig_r8_IS_SCALL_RESTARTED)
+#define syscall_restartable(regs) !(regs->event &  orig_r8_IS_SCALL_RESTARTED)
+
+#define current_pt_regs()					\
+({								\
+	/* open-coded current_thread_info() */			\
+	register unsigned long sp asm ("sp");			\
+	unsigned long pg_start = (sp & ~(THREAD_SIZE - 1));	\
+	(struct pt_regs *)(pg_start + THREAD_SIZE - 4) - 1;	\
+})
+
+static inline long regs_return_value(struct pt_regs *regs)
+{
+	return regs->r0;
+}
+
+#endif /* !__ASSEMBLY__ */
+
+#define orig_r8_IS_SCALL		0x0001
+#define orig_r8_IS_SCALL_RESTARTED	0x0002
+#define orig_r8_IS_BRKPT		0x0004
+#define orig_r8_IS_EXCPN		0x0004
+#define orig_r8_IS_IRQ1			0x0010
+#define orig_r8_IS_IRQ2			0x0020
+
+#endif /* __ASM_PTRACE_H */
diff --git a/arch/arc/include/asm/sections.h b/arch/arc/include/asm/sections.h
new file mode 100644
index 000000000000..6fc1159dfefe
--- /dev/null
+++ b/arch/arc/include/asm/sections.h
@@ -0,0 +1,18 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_ARC_SECTIONS_H
+#define _ASM_ARC_SECTIONS_H
+
+#include <asm-generic/sections.h>
+
+extern char _int_vec_base_lds[];
+extern char __arc_dccm_base[];
+extern char __dtb_start[];
+
+#endif
diff --git a/arch/arc/include/asm/segment.h b/arch/arc/include/asm/segment.h
new file mode 100644
index 000000000000..da2c45979817
--- /dev/null
+++ b/arch/arc/include/asm/segment.h
@@ -0,0 +1,24 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ASMARC_SEGMENT_H
+#define __ASMARC_SEGMENT_H
+
+#ifndef __ASSEMBLY__
+
+typedef unsigned long mm_segment_t;
+
+#define MAKE_MM_SEG(s)	((mm_segment_t) { (s) })
+
+#define KERNEL_DS		MAKE_MM_SEG(0)
+#define USER_DS			MAKE_MM_SEG(TASK_SIZE)
+
+#define segment_eq(a, b)	((a) == (b))
+
+#endif /* __ASSEMBLY__ */
+#endif /* __ASMARC_SEGMENT_H */
diff --git a/arch/arc/include/asm/serial.h b/arch/arc/include/asm/serial.h
new file mode 100644
index 000000000000..4dff5a1e4128
--- /dev/null
+++ b/arch/arc/include/asm/serial.h
@@ -0,0 +1,25 @@
+/*
+ * Copyright (C) 2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_ARC_SERIAL_H
+#define _ASM_ARC_SERIAL_H
+
+/*
+ * early-8250 requires BASE_BAUD to be defined and includes this header.
+ * We put in a typical value:
+ * 	(core clk / 16) - i.e. UART samples 16 times per sec.
+ * Athough in multi-platform-image this might not work, specially if the
+ * clk driving the UART is different.
+ * We can't use DeviceTree as this is typically for early serial.
+ */
+
+#include <asm/clk.h>
+
+#define BASE_BAUD	(arc_get_core_freq() / 16)
+
+#endif /* _ASM_ARC_SERIAL_H */
diff --git a/arch/arc/include/asm/setup.h b/arch/arc/include/asm/setup.h
new file mode 100644
index 000000000000..229e50681497
--- /dev/null
+++ b/arch/arc/include/asm/setup.h
@@ -0,0 +1,37 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __ASMARC_SETUP_H
+#define __ASMARC_SETUP_H
+
+
+#include <linux/types.h>
+#include <uapi/asm/setup.h>
+
+#define COMMAND_LINE_SIZE 256
+
+/*
+ * Data structure to map a ID to string
+ * Used a lot for bootup reporting of hardware diversity
+ */
+struct id_to_str {
+	int id;
+	const char *str;
+};
+
+struct cpuinfo_data {
+	struct id_to_str info;
+	int up_range;
+};
+
+extern int root_mountflags, end_mem;
+extern int running_on_hw;
+
+void __init setup_processor(void);
+void __init setup_arch_memory(void);
+
+#endif /* __ASMARC_SETUP_H */
diff --git a/arch/arc/include/asm/smp.h b/arch/arc/include/asm/smp.h
new file mode 100644
index 000000000000..c4fb211dcd25
--- /dev/null
+++ b/arch/arc/include/asm/smp.h
@@ -0,0 +1,130 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ASM_ARC_SMP_H
+#define __ASM_ARC_SMP_H
+
+#ifdef CONFIG_SMP
+
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/threads.h>
+
+#define raw_smp_processor_id() (current_thread_info()->cpu)
+
+/* including cpumask.h leads to cyclic deps hence this Forward declaration */
+struct cpumask;
+
+/*
+ * APIs provided by arch SMP code to generic code
+ */
+extern void arch_send_call_function_single_ipi(int cpu);
+extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
+
+/*
+ * APIs provided by arch SMP code to rest of arch code
+ */
+extern void __init smp_init_cpus(void);
+extern void __init first_lines_of_secondary(void);
+extern const char *arc_platform_smp_cpuinfo(void);
+
+/*
+ * API expected BY platform smp code (FROM arch smp code)
+ *
+ * smp_ipi_irq_setup:
+ *	Takes @cpu and @irq to which the arch-common ISR is hooked up
+ */
+extern int smp_ipi_irq_setup(int cpu, int irq);
+
+/*
+ * struct plat_smp_ops	- SMP callbacks provided by platform to ARC SMP
+ *
+ * @info:		SoC SMP specific info for /proc/cpuinfo etc
+ * @cpu_kick:		For Master to kickstart a cpu (optionally at a PC)
+ * @ipi_send:		To send IPI to a @cpumask
+ * @ips_clear:		To clear IPI received by @cpu at @irq
+ */
+struct plat_smp_ops {
+	const char 	*info;
+	void		(*cpu_kick)(int cpu, unsigned long pc);
+	void		(*ipi_send)(void *callmap);
+	void		(*ipi_clear)(int cpu, int irq);
+};
+
+/* TBD: stop exporting it for direct population by platform */
+extern struct plat_smp_ops  plat_smp_ops;
+
+#endif  /* CONFIG_SMP */
+
+/*
+ * ARC700 doesn't support atomic Read-Modify-Write ops.
+ * Originally Interrupts had to be disabled around code to gaurantee atomicity.
+ * The LLOCK/SCOND insns allow writing interrupt-hassle-free based atomic ops
+ * based on retry-if-irq-in-atomic (with hardware assist).
+ * However despite these, we provide the IRQ disabling variant
+ *
+ * (1) These insn were introduced only in 4.10 release. So for older released
+ *	support needed.
+ *
+ * (2) In a SMP setup, the LLOCK/SCOND atomiticity across CPUs needs to be
+ *	gaurantted by the platform (not something which core handles).
+ *	Assuming a platform won't, SMP Linux needs to use spinlocks + local IRQ
+ *	disabling for atomicity.
+ *
+ *	However exported spinlock API is not usable due to cyclic hdr deps
+ *	(even after system.h disintegration upstream)
+ *	asm/bitops.h -> linux/spinlock.h -> linux/preempt.h
+ *		-> linux/thread_info.h -> linux/bitops.h -> asm/bitops.h
+ *
+ *	So the workaround is to use the lowest level arch spinlock API.
+ *	The exported spinlock API is smart enough to be NOP for !CONFIG_SMP,
+ *	but same is not true for ARCH backend, hence the need for 2 variants
+ */
+#ifndef CONFIG_ARC_HAS_LLSC
+
+#include <linux/irqflags.h>
+#ifdef CONFIG_SMP
+
+#include <asm/spinlock.h>
+
+extern arch_spinlock_t smp_atomic_ops_lock;
+extern arch_spinlock_t smp_bitops_lock;
+
+#define atomic_ops_lock(flags)	do {		\
+	local_irq_save(flags);			\
+	arch_spin_lock(&smp_atomic_ops_lock);	\
+} while (0)
+
+#define atomic_ops_unlock(flags) do {		\
+	arch_spin_unlock(&smp_atomic_ops_lock);	\
+	local_irq_restore(flags);		\
+} while (0)
+
+#define bitops_lock(flags)	do {		\
+	local_irq_save(flags);			\
+	arch_spin_lock(&smp_bitops_lock);	\
+} while (0)
+
+#define bitops_unlock(flags) do {		\
+	arch_spin_unlock(&smp_bitops_lock);	\
+	local_irq_restore(flags);		\
+} while (0)
+
+#else /* !CONFIG_SMP */
+
+#define atomic_ops_lock(flags)		local_irq_save(flags)
+#define atomic_ops_unlock(flags)	local_irq_restore(flags)
+
+#define bitops_lock(flags)		local_irq_save(flags)
+#define bitops_unlock(flags)		local_irq_restore(flags)
+
+#endif /* !CONFIG_SMP */
+
+#endif	/* !CONFIG_ARC_HAS_LLSC */
+
+#endif
diff --git a/arch/arc/include/asm/spinlock.h b/arch/arc/include/asm/spinlock.h
new file mode 100644
index 000000000000..f158197ac5b0
--- /dev/null
+++ b/arch/arc/include/asm/spinlock.h
@@ -0,0 +1,144 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ASM_SPINLOCK_H
+#define __ASM_SPINLOCK_H
+
+#include <asm/spinlock_types.h>
+#include <asm/processor.h>
+#include <asm/barrier.h>
+
+#define arch_spin_is_locked(x)	((x)->slock != __ARCH_SPIN_LOCK_UNLOCKED__)
+#define arch_spin_lock_flags(lock, flags)	arch_spin_lock(lock)
+#define arch_spin_unlock_wait(x) \
+	do { while (arch_spin_is_locked(x)) cpu_relax(); } while (0)
+
+static inline void arch_spin_lock(arch_spinlock_t *lock)
+{
+	unsigned int tmp = __ARCH_SPIN_LOCK_LOCKED__;
+
+	__asm__ __volatile__(
+	"1:	ex  %0, [%1]		\n"
+	"	breq  %0, %2, 1b	\n"
+	: "+&r" (tmp)
+	: "r"(&(lock->slock)), "ir"(__ARCH_SPIN_LOCK_LOCKED__)
+	: "memory");
+}
+
+static inline int arch_spin_trylock(arch_spinlock_t *lock)
+{
+	unsigned int tmp = __ARCH_SPIN_LOCK_LOCKED__;
+
+	__asm__ __volatile__(
+	"1:	ex  %0, [%1]		\n"
+	: "+r" (tmp)
+	: "r"(&(lock->slock))
+	: "memory");
+
+	return (tmp == __ARCH_SPIN_LOCK_UNLOCKED__);
+}
+
+static inline void arch_spin_unlock(arch_spinlock_t *lock)
+{
+	lock->slock = __ARCH_SPIN_LOCK_UNLOCKED__;
+	smp_mb();
+}
+
+/*
+ * Read-write spinlocks, allowing multiple readers but only one writer.
+ *
+ * The spinlock itself is contained in @counter and access to it is
+ * serialized with @lock_mutex.
+ *
+ * Unfair locking as Writers could be starved indefinitely by Reader(s)
+ */
+
+/* Would read_trylock() succeed? */
+#define arch_read_can_lock(x)	((x)->counter > 0)
+
+/* Would write_trylock() succeed? */
+#define arch_write_can_lock(x)	((x)->counter == __ARCH_RW_LOCK_UNLOCKED__)
+
+/* 1 - lock taken successfully */
+static inline int arch_read_trylock(arch_rwlock_t *rw)
+{
+	int ret = 0;
+
+	arch_spin_lock(&(rw->lock_mutex));
+
+	/*
+	 * zero means writer holds the lock exclusively, deny Reader.
+	 * Otherwise grant lock to first/subseq reader
+	 */
+	if (rw->counter > 0) {
+		rw->counter--;
+		ret = 1;
+	}
+
+	arch_spin_unlock(&(rw->lock_mutex));
+
+	smp_mb();
+	return ret;
+}
+
+/* 1 - lock taken successfully */
+static inline int arch_write_trylock(arch_rwlock_t *rw)
+{
+	int ret = 0;
+
+	arch_spin_lock(&(rw->lock_mutex));
+
+	/*
+	 * If reader(s) hold lock (lock < __ARCH_RW_LOCK_UNLOCKED__),
+	 * deny writer. Otherwise if unlocked grant to writer
+	 * Hence the claim that Linux rwlocks are unfair to writers.
+	 * (can be starved for an indefinite time by readers).
+	 */
+	if (rw->counter == __ARCH_RW_LOCK_UNLOCKED__) {
+		rw->counter = 0;
+		ret = 1;
+	}
+	arch_spin_unlock(&(rw->lock_mutex));
+
+	return ret;
+}
+
+static inline void arch_read_lock(arch_rwlock_t *rw)
+{
+	while (!arch_read_trylock(rw))
+		cpu_relax();
+}
+
+static inline void arch_write_lock(arch_rwlock_t *rw)
+{
+	while (!arch_write_trylock(rw))
+		cpu_relax();
+}
+
+static inline void arch_read_unlock(arch_rwlock_t *rw)
+{
+	arch_spin_lock(&(rw->lock_mutex));
+	rw->counter++;
+	arch_spin_unlock(&(rw->lock_mutex));
+}
+
+static inline void arch_write_unlock(arch_rwlock_t *rw)
+{
+	arch_spin_lock(&(rw->lock_mutex));
+	rw->counter = __ARCH_RW_LOCK_UNLOCKED__;
+	arch_spin_unlock(&(rw->lock_mutex));
+}
+
+#define arch_read_lock_flags(lock, flags)	arch_read_lock(lock)
+#define arch_write_lock_flags(lock, flags)	arch_write_lock(lock)
+
+#define arch_spin_relax(lock)	cpu_relax()
+#define arch_read_relax(lock)	cpu_relax()
+#define arch_write_relax(lock)	cpu_relax()
+
+#endif /* __ASM_SPINLOCK_H */
diff --git a/arch/arc/include/asm/spinlock_types.h b/arch/arc/include/asm/spinlock_types.h
new file mode 100644
index 000000000000..8276bfd61704
--- /dev/null
+++ b/arch/arc/include/asm/spinlock_types.h
@@ -0,0 +1,35 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ASM_SPINLOCK_TYPES_H
+#define __ASM_SPINLOCK_TYPES_H
+
+typedef struct {
+	volatile unsigned int slock;
+} arch_spinlock_t;
+
+#define __ARCH_SPIN_LOCK_UNLOCKED__	0
+#define __ARCH_SPIN_LOCK_LOCKED__	1
+
+#define __ARCH_SPIN_LOCK_UNLOCKED	{ __ARCH_SPIN_LOCK_UNLOCKED__ }
+#define __ARCH_SPIN_LOCK_LOCKED		{ __ARCH_SPIN_LOCK_LOCKED__ }
+
+/*
+ * Unlocked:     0x01_00_00_00
+ * Read lock(s): 0x00_FF_00_00 to say 0x01
+ * Write lock:   0x0, but only possible if prior value "unlocked" 0x0100_0000
+ */
+typedef struct {
+	volatile unsigned int	counter;
+	arch_spinlock_t		lock_mutex;
+} arch_rwlock_t;
+
+#define __ARCH_RW_LOCK_UNLOCKED__	0x01000000
+#define __ARCH_RW_LOCK_UNLOCKED		{ .counter = __ARCH_RW_LOCK_UNLOCKED__ }
+
+#endif
diff --git a/arch/arc/include/asm/string.h b/arch/arc/include/asm/string.h
new file mode 100644
index 000000000000..87676c8f1412
--- /dev/null
+++ b/arch/arc/include/asm/string.h
@@ -0,0 +1,40 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * vineetg: May 2011
+ *  -We had half-optimised memset/memcpy, got better versions of those
+ *  -Added memcmp, strchr, strcpy, strcmp, strlen
+ *
+ * Amit Bhor: Codito Technologies 2004
+ */
+
+#ifndef _ASM_ARC_STRING_H
+#define _ASM_ARC_STRING_H
+
+#include <linux/types.h>
+
+#ifdef __KERNEL__
+
+#define __HAVE_ARCH_MEMSET
+#define __HAVE_ARCH_MEMCPY
+#define __HAVE_ARCH_MEMCMP
+#define __HAVE_ARCH_STRCHR
+#define __HAVE_ARCH_STRCPY
+#define __HAVE_ARCH_STRCMP
+#define __HAVE_ARCH_STRLEN
+
+extern void *memset(void *ptr, int, __kernel_size_t);
+extern void *memcpy(void *, const void *, __kernel_size_t);
+extern void memzero(void *ptr, __kernel_size_t n);
+extern int memcmp(const void *, const void *, __kernel_size_t);
+extern char *strchr(const char *s, int c);
+extern char *strcpy(char *dest, const char *src);
+extern int strcmp(const char *cs, const char *ct);
+extern __kernel_size_t strlen(const char *);
+
+#endif /* __KERNEL__ */
+#endif /* _ASM_ARC_STRING_H */
diff --git a/arch/arc/include/asm/switch_to.h b/arch/arc/include/asm/switch_to.h
new file mode 100644
index 000000000000..1b171ab5fec0
--- /dev/null
+++ b/arch/arc/include/asm/switch_to.h
@@ -0,0 +1,41 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_ARC_SWITCH_TO_H
+#define _ASM_ARC_SWITCH_TO_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/sched.h>
+
+#ifdef CONFIG_ARC_FPU_SAVE_RESTORE
+
+extern void fpu_save_restore(struct task_struct *p, struct task_struct *n);
+#define ARC_FPU_PREV(p, n)	fpu_save_restore(p, n)
+#define ARC_FPU_NEXT(t)
+
+#else
+
+#define ARC_FPU_PREV(p, n)
+#define ARC_FPU_NEXT(n)
+
+#endif /* !CONFIG_ARC_FPU_SAVE_RESTORE */
+
+struct task_struct *__switch_to(struct task_struct *p, struct task_struct *n);
+
+#define switch_to(prev, next, last)	\
+do {					\
+	ARC_FPU_PREV(prev, next);	\
+	last = __switch_to(prev, next);\
+	ARC_FPU_NEXT(next);		\
+	mb();				\
+} while (0)
+
+#endif
+
+#endif
diff --git a/arch/arc/include/asm/syscall.h b/arch/arc/include/asm/syscall.h
new file mode 100644
index 000000000000..33ab3048e9b2
--- /dev/null
+++ b/arch/arc/include/asm/syscall.h
@@ -0,0 +1,72 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_ARC_SYSCALL_H
+#define _ASM_ARC_SYSCALL_H  1
+
+#include <linux/err.h>
+#include <linux/sched.h>
+#include <asm/unistd.h>
+#include <asm/ptrace.h>		/* in_syscall() */
+
+static inline long
+syscall_get_nr(struct task_struct *task, struct pt_regs *regs)
+{
+	if (user_mode(regs) && in_syscall(regs))
+		return regs->orig_r8;
+	else
+		return -1;
+}
+
+static inline void
+syscall_rollback(struct task_struct *task, struct pt_regs *regs)
+{
+	/* XXX: I can't fathom how pt_regs->r8 will be clobbered ? */
+	regs->r8 = regs->orig_r8;
+}
+
+static inline long
+syscall_get_error(struct task_struct *task, struct pt_regs *regs)
+{
+	/* 0 if syscall succeeded, otherwise -Errorcode */
+	return IS_ERR_VALUE(regs->r0) ? regs->r0 : 0;
+}
+
+static inline long
+syscall_get_return_value(struct task_struct *task, struct pt_regs *regs)
+{
+	return regs->r0;
+}
+
+static inline void
+syscall_set_return_value(struct task_struct *task, struct pt_regs *regs,
+			 int error, long val)
+{
+	regs->r0 = (long) error ?: val;
+}
+
+/*
+ * @i:      argument index [0,5]
+ * @n:      number of arguments; n+i must be [1,6].
+ */
+static inline void
+syscall_get_arguments(struct task_struct *task, struct pt_regs *regs,
+		      unsigned int i, unsigned int n, unsigned long *args)
+{
+	unsigned long *inside_ptregs = &(regs->r0);
+	inside_ptregs -= i;
+
+	BUG_ON((i + n) > 6);
+
+	while (n--) {
+		args[i++] = (*inside_ptregs);
+		inside_ptregs--;
+	}
+}
+
+#endif
diff --git a/arch/arc/include/asm/syscalls.h b/arch/arc/include/asm/syscalls.h
new file mode 100644
index 000000000000..e53a5340ba4f
--- /dev/null
+++ b/arch/arc/include/asm/syscalls.h
@@ -0,0 +1,29 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_ARC_SYSCALLS_H
+#define _ASM_ARC_SYSCALLS_H  1
+
+#ifdef __KERNEL__
+
+#include <linux/compiler.h>
+#include <linux/linkage.h>
+#include <linux/types.h>
+
+int sys_clone_wrapper(int, int, int, int, int);
+int sys_fork_wrapper(void);
+int sys_vfork_wrapper(void);
+int sys_cacheflush(uint32_t, uint32_t uint32_t);
+int sys_arc_settls(void *);
+int sys_arc_gettls(void);
+
+#include <asm-generic/syscalls.h>
+
+#endif	/* __KERNEL__ */
+
+#endif
diff --git a/arch/arc/include/asm/thread_info.h b/arch/arc/include/asm/thread_info.h
new file mode 100644
index 000000000000..2d50a4cdd7f3
--- /dev/null
+++ b/arch/arc/include/asm/thread_info.h
@@ -0,0 +1,121 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Vineetg: Oct 2009
+ *  No need for ARC specific thread_info allocator (kmalloc/free). This is
+ *  anyways one page allocation, thus slab alloc can be short-circuited and
+ *  the generic version (get_free_page) would be loads better.
+ *
+ * Sameer Dhavale: Codito Technologies 2004
+ */
+
+#ifndef _ASM_THREAD_INFO_H
+#define _ASM_THREAD_INFO_H
+
+#ifdef __KERNEL__
+
+#include <asm/page.h>
+
+#ifdef CONFIG_16KSTACKS
+#define THREAD_SIZE_ORDER 1
+#else
+#define THREAD_SIZE_ORDER 0
+#endif
+
+#define THREAD_SIZE     (PAGE_SIZE << THREAD_SIZE_ORDER)
+
+#ifndef __ASSEMBLY__
+
+#include <linux/thread_info.h>
+#include <asm/segment.h>
+
+/*
+ * low level task data that entry.S needs immediate access to
+ * - this struct should fit entirely inside of one cache line
+ * - this struct shares the supervisor stack pages
+ * - if the contents of this structure are changed, the assembly constants
+ *   must also be changed
+ */
+struct thread_info {
+	unsigned long flags;		/* low level flags */
+	int preempt_count;		/* 0 => preemptable, <0 => BUG */
+	struct task_struct *task;	/* main task structure */
+	mm_segment_t addr_limit;	/* thread address space */
+	struct exec_domain *exec_domain;/* execution domain */
+	__u32 cpu;			/* current CPU */
+	unsigned long thr_ptr;		/* TLS ptr */
+	struct restart_block restart_block;
+};
+
+/*
+ * macros/functions for gaining access to the thread information structure
+ *
+ * preempt_count needs to be 1 initially, until the scheduler is functional.
+ */
+#define INIT_THREAD_INFO(tsk)			\
+{						\
+	.task       = &tsk,			\
+	.exec_domain    = &default_exec_domain,	\
+	.flags      = 0,			\
+	.cpu        = 0,			\
+	.preempt_count  = INIT_PREEMPT_COUNT,	\
+	.addr_limit = KERNEL_DS,		\
+	.restart_block  = {			\
+		.fn = do_no_restart_syscall,	\
+	},					\
+}
+
+#define init_thread_info    (init_thread_union.thread_info)
+#define init_stack          (init_thread_union.stack)
+
+static inline __attribute_const__ struct thread_info *current_thread_info(void)
+{
+	register unsigned long sp asm("sp");
+	return (struct thread_info *)(sp & ~(THREAD_SIZE - 1));
+}
+
+#endif /* !__ASSEMBLY__ */
+
+#define PREEMPT_ACTIVE      0x10000000
+
+/*
+ * thread information flags
+ * - these are process state flags that various assembly files may need to
+ *   access
+ * - pending work-to-be-done flags are in LSW
+ * - other flags in MSW
+ */
+#define TIF_RESTORE_SIGMASK	0	/* restore sig mask in do_signal() */
+#define TIF_NOTIFY_RESUME	1	/* resumption notification requested */
+#define TIF_SIGPENDING		2	/* signal pending */
+#define TIF_NEED_RESCHED	3	/* rescheduling necessary */
+#define TIF_SYSCALL_AUDIT	4	/* syscall auditing active */
+#define TIF_SYSCALL_TRACE	15	/* syscall trace active */
+
+/* true if poll_idle() is polling TIF_NEED_RESCHED */
+#define TIF_MEMDIE		16
+
+#define _TIF_SYSCALL_TRACE	(1<<TIF_SYSCALL_TRACE)
+#define _TIF_NOTIFY_RESUME	(1<<TIF_NOTIFY_RESUME)
+#define _TIF_SIGPENDING		(1<<TIF_SIGPENDING)
+#define _TIF_NEED_RESCHED	(1<<TIF_NEED_RESCHED)
+#define _TIF_SYSCALL_AUDIT	(1<<TIF_SYSCALL_AUDIT)
+#define _TIF_MEMDIE		(1<<TIF_MEMDIE)
+
+/* work to do on interrupt/exception return */
+#define _TIF_WORK_MASK		(_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
+				 _TIF_NOTIFY_RESUME)
+
+/*
+ * _TIF_ALLWORK_MASK includes SYSCALL_TRACE, but we don't need it.
+ * SYSCALL_TRACE is anways seperately/unconditionally tested right after a
+ * syscall, so all that reamins to be tested is _TIF_WORK_MASK
+ */
+
+#endif /* __KERNEL__ */
+
+#endif /* _ASM_THREAD_INFO_H */
diff --git a/arch/arc/include/asm/timex.h b/arch/arc/include/asm/timex.h
new file mode 100644
index 000000000000..0a82960a75e9
--- /dev/null
+++ b/arch/arc/include/asm/timex.h
@@ -0,0 +1,18 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_ARC_TIMEX_H
+#define _ASM_ARC_TIMEX_H
+
+#define CLOCK_TICK_RATE	80000000 /* slated to be removed */
+
+#include <asm-generic/timex.h>
+
+/* XXX: get_cycles() to be implemented with RTSC insn */
+
+#endif /* _ASM_ARC_TIMEX_H */
diff --git a/arch/arc/include/asm/tlb-mmu1.h b/arch/arc/include/asm/tlb-mmu1.h
new file mode 100644
index 000000000000..a5ff961b1efc
--- /dev/null
+++ b/arch/arc/include/asm/tlb-mmu1.h
@@ -0,0 +1,104 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ASM_TLB_MMU_V1_H__
+#define __ASM_TLB_MMU_V1_H__
+
+#if defined(__ASSEMBLY__) && defined(CONFIG_ARC_MMU_VER == 1)
+
+#include <asm/tlb.h>
+
+.macro TLB_WRITE_HEURISTICS
+
+#define JH_HACK1
+#undef JH_HACK2
+#undef JH_HACK3
+
+#ifdef JH_HACK3
+; Calculate set index for 2-way MMU
+; -avoiding use of GetIndex from MMU
+;   and its unpleasant LFSR pseudo-random sequence
+;
+; r1 = TLBPD0 from TLB_RELOAD above
+;
+; -- jh_ex_way_set not cleared on startup
+;    didn't want to change setup.c
+;    hence extra instruction to clean
+;
+; -- should be in cache since in same line
+;    as r0/r1 saves above
+;
+ld  r0,[jh_ex_way_sel]  ; victim pointer
+and r0,r0,1         ; clean
+xor.f   r0,r0,1         ; flip
+st  r0,[jh_ex_way_sel]  ; store back
+asr r0,r1,12        ; get set # <<1, note bit 12=R=0
+or.nz   r0,r0,1         ; set way bit
+and r0,r0,0xff      ; clean
+sr  r0,[ARC_REG_TLBINDEX]
+#endif
+
+#ifdef JH_HACK2
+; JH hack #2
+;  Faster than hack #1 in non-thrash case, but hard-coded for 2-way MMU
+;  Slower in thrash case (where it matters) because more code is executed
+;  Inefficient due to two-register paradigm of this miss handler
+;
+/* r1 = data TLBPD0 at this point */
+lr      r0,[eret]               /* instruction address */
+xor     r0,r0,r1                /* compare set #       */
+and.f   r0,r0,0x000fe000        /* 2-way MMU mask      */
+bne     88f                     /* not in same set - no need to probe */
+
+lr      r0,[eret]               /* instruction address */
+and     r0,r0,PAGE_MASK         /* VPN of instruction address */
+; lr  r1,[ARC_REG_TLBPD0]     /* Data VPN+ASID - already in r1 from TLB_RELOAD*/
+and     r1,r1,0xff              /* Data ASID */
+or      r0,r0,r1                /* Instruction address + Data ASID */
+
+lr      r1,[ARC_REG_TLBPD0]     /* save TLBPD0 containing data TLB*/
+sr      r0,[ARC_REG_TLBPD0]     /* write instruction address to TLBPD0 */
+sr      TLBProbe, [ARC_REG_TLBCOMMAND] /* Look for instruction */
+lr      r0,[ARC_REG_TLBINDEX]   /* r0 = index where instruction is, if at all */
+sr      r1,[ARC_REG_TLBPD0]     /* restore TLBPD0 */
+
+xor     r0,r0,1                 /* flip bottom bit of data index */
+b.d     89f
+sr      r0,[ARC_REG_TLBINDEX]   /* and put it back */
+88:
+sr  TLBGetIndex, [ARC_REG_TLBCOMMAND]
+89:
+#endif
+
+#ifdef JH_HACK1
+;
+; Always checks whether instruction will be kicked out by dtlb miss
+;
+mov_s   r3, r1                  ; save PD0 prepared by TLB_RELOAD in r3
+lr      r0,[eret]               /* instruction address */
+and     r0,r0,PAGE_MASK         /* VPN of instruction address */
+bmsk    r1,r3,7                 /* Data ASID, bits 7-0 */
+or_s    r0,r0,r1                /* Instruction address + Data ASID */
+
+sr      r0,[ARC_REG_TLBPD0]     /* write instruction address to TLBPD0 */
+sr      TLBProbe, [ARC_REG_TLBCOMMAND] /* Look for instruction */
+lr      r0,[ARC_REG_TLBINDEX]   /* r0 = index where instruction is, if at all */
+sr      r3,[ARC_REG_TLBPD0]     /* restore TLBPD0 */
+
+sr      TLBGetIndex, [ARC_REG_TLBCOMMAND]
+lr      r1,[ARC_REG_TLBINDEX]   /* r1 = index where MMU wants to put data */
+cmp     r0,r1                   /* if no match on indices, go around */
+xor.eq  r1,r1,1                 /* flip bottom bit of data index */
+sr      r1,[ARC_REG_TLBINDEX]   /* and put it back */
+#endif
+
+.endm
+
+#endif
+
+#endif
diff --git a/arch/arc/include/asm/tlb.h b/arch/arc/include/asm/tlb.h
new file mode 100644
index 000000000000..3eb2ce0bdfa3
--- /dev/null
+++ b/arch/arc/include/asm/tlb.h
@@ -0,0 +1,58 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_ARC_TLB_H
+#define _ASM_ARC_TLB_H
+
+#ifdef __KERNEL__
+
+#include <asm/pgtable.h>
+
+/* Masks for actual TLB "PD"s */
+#define PTE_BITS_IN_PD0	(_PAGE_GLOBAL | _PAGE_PRESENT)
+#define PTE_BITS_IN_PD1	(PAGE_MASK | _PAGE_CACHEABLE | \
+			 _PAGE_EXECUTE | _PAGE_WRITE | _PAGE_READ | \
+			 _PAGE_K_EXECUTE | _PAGE_K_WRITE | _PAGE_K_READ)
+
+#ifndef __ASSEMBLY__
+
+#define tlb_flush(tlb) local_flush_tlb_mm((tlb)->mm)
+
+/*
+ * This pair is called at time of munmap/exit to flush cache and TLB entries
+ * for mappings being torn down.
+ * 1) cache-flush part -implemented via tlb_start_vma( ) can be NOP (for now)
+ *    as we don't support aliasing configs in our VIPT D$.
+ * 2) tlb-flush part - implemted via tlb_end_vma( ) can be NOP as well-
+ *    albiet for difft reasons - its better handled by moving to new ASID
+ *
+ * Note, read http://lkml.org/lkml/2004/1/15/6
+ */
+#define tlb_start_vma(tlb, vma)
+#define tlb_end_vma(tlb, vma)
+
+#define __tlb_remove_tlb_entry(tlb, ptep, address)
+
+#include <linux/pagemap.h>
+#include <asm-generic/tlb.h>
+
+#ifdef CONFIG_ARC_DBG_TLB_PARANOIA
+void tlb_paranoid_check(unsigned int pid_sw, unsigned long address);
+#else
+#define tlb_paranoid_check(a, b)
+#endif
+
+void arc_mmu_init(void);
+extern char *arc_mmu_mumbojumbo(int cpu_id, char *buf, int len);
+void __init read_decode_mmu_bcr(void);
+
+#endif	/* __ASSEMBLY__ */
+
+#endif	/* __KERNEL__ */
+
+#endif /* _ASM_ARC_TLB_H */
diff --git a/arch/arc/include/asm/tlbflush.h b/arch/arc/include/asm/tlbflush.h
new file mode 100644
index 000000000000..b2f9bc7f68c8
--- /dev/null
+++ b/arch/arc/include/asm/tlbflush.h
@@ -0,0 +1,28 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ASM_ARC_TLBFLUSH__
+#define __ASM_ARC_TLBFLUSH__
+
+#include <linux/mm.h>
+
+void local_flush_tlb_all(void);
+void local_flush_tlb_mm(struct mm_struct *mm);
+void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long page);
+void local_flush_tlb_kernel_range(unsigned long start, unsigned long end);
+void local_flush_tlb_range(struct vm_area_struct *vma,
+			   unsigned long start, unsigned long end);
+
+/* XXX: Revisit for SMP */
+#define flush_tlb_range(vma, s, e)	local_flush_tlb_range(vma, s, e)
+#define flush_tlb_page(vma, page)	local_flush_tlb_page(vma, page)
+#define flush_tlb_kernel_range(s, e)	local_flush_tlb_kernel_range(s, e)
+#define flush_tlb_all()			local_flush_tlb_all()
+#define flush_tlb_mm(mm)		local_flush_tlb_mm(mm)
+
+#endif
diff --git a/arch/arc/include/asm/uaccess.h b/arch/arc/include/asm/uaccess.h
new file mode 100644
index 000000000000..32420824375b
--- /dev/null
+++ b/arch/arc/include/asm/uaccess.h
@@ -0,0 +1,751 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * vineetg: June 2010
+ *    -__clear_user( ) called multiple times during elf load was byte loop
+ *    converted to do as much word clear as possible.
+ *
+ * vineetg: Dec 2009
+ *    -Hand crafted constant propagation for "constant" copy sizes
+ *    -stock kernel shrunk by 33K at -O3
+ *
+ * vineetg: Sept 2009
+ *    -Added option to (UN)inline copy_(to|from)_user to reduce code sz
+ *    -kernel shrunk by 200K even at -O3 (gcc 4.2.1)
+ *    -Enabled when doing -Os
+ *
+ * Amit Bhor, Sameer Dhavale: Codito Technologies 2004
+ */
+
+#ifndef _ASM_ARC_UACCESS_H
+#define _ASM_ARC_UACCESS_H
+
+#include <linux/sched.h>
+#include <asm/errno.h>
+#include <linux/string.h>	/* for generic string functions */
+
+
+#define __kernel_ok		(segment_eq(get_fs(), KERNEL_DS))
+
+/*
+ * Algorthmically, for __user_ok() we want do:
+ * 	(start < TASK_SIZE) && (start+len < TASK_SIZE)
+ * where TASK_SIZE could either be retrieved from thread_info->addr_limit or
+ * emitted directly in code.
+ *
+ * This can however be rewritten as follows:
+ *	(len <= TASK_SIZE) && (start+len < TASK_SIZE)
+ *
+ * Because it essentially checks if buffer end is within limit and @len is
+ * non-ngeative, which implies that buffer start will be within limit too.
+ *
+ * The reason for rewriting being, for majorit yof cases, @len is generally
+ * compile time constant, causing first sub-expression to be compile time
+ * subsumed.
+ *
+ * The second part would generate weird large LIMMs e.g. (0x6000_0000 - 0x10),
+ * so we check for TASK_SIZE using get_fs() since the addr_limit load from mem
+ * would already have been done at this call site for __kernel_ok()
+ *
+ */
+#define __user_ok(addr, sz)	(((sz) <= TASK_SIZE) && \
+				 (((addr)+(sz)) <= get_fs()))
+#define __access_ok(addr, sz)	(unlikely(__kernel_ok) || \
+				 likely(__user_ok((addr), (sz))))
+
+/*********** Single byte/hword/word copies ******************/
+
+#define __get_user_fn(sz, u, k)					\
+({								\
+	long __ret = 0;	/* success by default */	\
+	switch (sz) {						\
+	case 1: __arc_get_user_one(*(k), u, "ldb", __ret); break;	\
+	case 2: __arc_get_user_one(*(k), u, "ldw", __ret); break;	\
+	case 4: __arc_get_user_one(*(k), u, "ld", __ret);  break;	\
+	case 8: __arc_get_user_one_64(*(k), u, __ret);     break;	\
+	}							\
+	__ret;							\
+})
+
+/*
+ * Returns 0 on success, -EFAULT if not.
+ * @ret already contains 0 - given that errors will be less likely
+ * (hence +r asm constraint below).
+ * In case of error, fixup code will make it -EFAULT
+ */
+#define __arc_get_user_one(dst, src, op, ret)	\
+	__asm__ __volatile__(                   \
+	"1:	"op"    %1,[%2]\n"		\
+	"2:	;nop\n"				\
+	"	.section .fixup, \"ax\"\n"	\
+	"	.align 4\n"			\
+	"3:	mov %0, %3\n"			\
+	"	j   2b\n"			\
+	"	.previous\n"			\
+	"	.section __ex_table, \"a\"\n"	\
+	"	.align 4\n"			\
+	"	.word 1b,3b\n"			\
+	"	.previous\n"			\
+						\
+	: "+r" (ret), "=r" (dst)		\
+	: "r" (src), "ir" (-EFAULT))
+
+#define __arc_get_user_one_64(dst, src, ret)	\
+	__asm__ __volatile__(                   \
+	"1:	ld   %1,[%2]\n"			\
+	"4:	ld  %R1,[%2, 4]\n"		\
+	"2:	;nop\n"				\
+	"	.section .fixup, \"ax\"\n"	\
+	"	.align 4\n"			\
+	"3:	mov %0, %3\n"			\
+	"	j   2b\n"			\
+	"	.previous\n"			\
+	"	.section __ex_table, \"a\"\n"	\
+	"	.align 4\n"			\
+	"	.word 1b,3b\n"			\
+	"	.word 4b,3b\n"			\
+	"	.previous\n"			\
+						\
+	: "+r" (ret), "=r" (dst)		\
+	: "r" (src), "ir" (-EFAULT))
+
+#define __put_user_fn(sz, u, k)					\
+({								\
+	long __ret = 0;	/* success by default */	\
+	switch (sz) {						\
+	case 1: __arc_put_user_one(*(k), u, "stb", __ret); break;	\
+	case 2: __arc_put_user_one(*(k), u, "stw", __ret); break;	\
+	case 4: __arc_put_user_one(*(k), u, "st", __ret);  break;	\
+	case 8: __arc_put_user_one_64(*(k), u, __ret);     break;	\
+	}							\
+	__ret;							\
+})
+
+#define __arc_put_user_one(src, dst, op, ret)	\
+	__asm__ __volatile__(                   \
+	"1:	"op"    %1,[%2]\n"		\
+	"2:	;nop\n"				\
+	"	.section .fixup, \"ax\"\n"	\
+	"	.align 4\n"			\
+	"3:	mov %0, %3\n"			\
+	"	j   2b\n"			\
+	"	.previous\n"			\
+	"	.section __ex_table, \"a\"\n"	\
+	"	.align 4\n"			\
+	"	.word 1b,3b\n"			\
+	"	.previous\n"			\
+						\
+	: "+r" (ret)				\
+	: "r" (src), "r" (dst), "ir" (-EFAULT))
+
+#define __arc_put_user_one_64(src, dst, ret)	\
+	__asm__ __volatile__(                   \
+	"1:	st   %1,[%2]\n"			\
+	"4:	st  %R1,[%2, 4]\n"		\
+	"2:	;nop\n"				\
+	"	.section .fixup, \"ax\"\n"	\
+	"	.align 4\n"			\
+	"3:	mov %0, %3\n"			\
+	"	j   2b\n"			\
+	"	.previous\n"			\
+	"	.section __ex_table, \"a\"\n"	\
+	"	.align 4\n"			\
+	"	.word 1b,3b\n"			\
+	"	.word 4b,3b\n"			\
+	"	.previous\n"			\
+						\
+	: "+r" (ret)				\
+	: "r" (src), "r" (dst), "ir" (-EFAULT))
+
+
+static inline unsigned long
+__arc_copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+	long res = 0;
+	char val;
+	unsigned long tmp1, tmp2, tmp3, tmp4;
+	unsigned long orig_n = n;
+
+	if (n == 0)
+		return 0;
+
+	/* unaligned */
+	if (((unsigned long)to & 0x3) || ((unsigned long)from & 0x3)) {
+
+		unsigned char tmp;
+
+		__asm__ __volatile__ (
+		"	mov.f   lp_count, %0		\n"
+		"	lpnz 2f				\n"
+		"1:	ldb.ab  %1, [%3, 1]		\n"
+		"	stb.ab  %1, [%2, 1]		\n"
+		"	sub     %0,%0,1			\n"
+		"2:	;nop				\n"
+		"	.section .fixup, \"ax\"		\n"
+		"	.align 4			\n"
+		"3:	j   2b				\n"
+		"	.previous			\n"
+		"	.section __ex_table, \"a\"	\n"
+		"	.align 4			\n"
+		"	.word   1b, 3b			\n"
+		"	.previous			\n"
+
+		: "+r" (n),
+		/*
+		 * Note as an '&' earlyclobber operand to make sure the
+		 * temporary register inside the loop is not the same as
+		 *  FROM or TO.
+		*/
+		  "=&r" (tmp), "+r" (to), "+r" (from)
+		:
+		: "lp_count", "lp_start", "lp_end", "memory");
+
+		return n;
+	}
+
+	/*
+	 * Hand-crafted constant propagation to reduce code sz of the
+	 * laddered copy 16x,8,4,2,1
+	 */
+	if (__builtin_constant_p(orig_n)) {
+		res = orig_n;
+
+		if (orig_n / 16) {
+			orig_n = orig_n % 16;
+
+			__asm__ __volatile__(
+			"	lsr   lp_count, %7,4		\n"
+			"	lp    3f			\n"
+			"1:	ld.ab   %3, [%2, 4]		\n"
+			"11:	ld.ab   %4, [%2, 4]		\n"
+			"12:	ld.ab   %5, [%2, 4]		\n"
+			"13:	ld.ab   %6, [%2, 4]		\n"
+			"	st.ab   %3, [%1, 4]		\n"
+			"	st.ab   %4, [%1, 4]		\n"
+			"	st.ab   %5, [%1, 4]		\n"
+			"	st.ab   %6, [%1, 4]		\n"
+			"	sub     %0,%0,16		\n"
+			"3:	;nop				\n"
+			"	.section .fixup, \"ax\"		\n"
+			"	.align 4			\n"
+			"4:	j   3b				\n"
+			"	.previous			\n"
+			"	.section __ex_table, \"a\"	\n"
+			"	.align 4			\n"
+			"	.word   1b, 4b			\n"
+			"	.word   11b,4b			\n"
+			"	.word   12b,4b			\n"
+			"	.word   13b,4b			\n"
+			"	.previous			\n"
+			: "+r" (res), "+r"(to), "+r"(from),
+			  "=r"(tmp1), "=r"(tmp2), "=r"(tmp3), "=r"(tmp4)
+			: "ir"(n)
+			: "lp_count", "memory");
+		}
+		if (orig_n / 8) {
+			orig_n = orig_n % 8;
+
+			__asm__ __volatile__(
+			"14:	ld.ab   %3, [%2,4]		\n"
+			"15:	ld.ab   %4, [%2,4]		\n"
+			"	st.ab   %3, [%1,4]		\n"
+			"	st.ab   %4, [%1,4]		\n"
+			"	sub     %0,%0,8			\n"
+			"31:	;nop				\n"
+			"	.section .fixup, \"ax\"		\n"
+			"	.align 4			\n"
+			"4:	j   31b				\n"
+			"	.previous			\n"
+			"	.section __ex_table, \"a\"	\n"
+			"	.align 4			\n"
+			"	.word   14b,4b			\n"
+			"	.word   15b,4b			\n"
+			"	.previous			\n"
+			: "+r" (res), "+r"(to), "+r"(from),
+			  "=r"(tmp1), "=r"(tmp2)
+			:
+			: "memory");
+		}
+		if (orig_n / 4) {
+			orig_n = orig_n % 4;
+
+			__asm__ __volatile__(
+			"16:	ld.ab   %3, [%2,4]		\n"
+			"	st.ab   %3, [%1,4]		\n"
+			"	sub     %0,%0,4			\n"
+			"32:	;nop				\n"
+			"	.section .fixup, \"ax\"		\n"
+			"	.align 4			\n"
+			"4:	j   32b				\n"
+			"	.previous			\n"
+			"	.section __ex_table, \"a\"	\n"
+			"	.align 4			\n"
+			"	.word   16b,4b			\n"
+			"	.previous			\n"
+			: "+r" (res), "+r"(to), "+r"(from), "=r"(tmp1)
+			:
+			: "memory");
+		}
+		if (orig_n / 2) {
+			orig_n = orig_n % 2;
+
+			__asm__ __volatile__(
+			"17:	ldw.ab   %3, [%2,2]		\n"
+			"	stw.ab   %3, [%1,2]		\n"
+			"	sub      %0,%0,2		\n"
+			"33:	;nop				\n"
+			"	.section .fixup, \"ax\"		\n"
+			"	.align 4			\n"
+			"4:	j   33b				\n"
+			"	.previous			\n"
+			"	.section __ex_table, \"a\"	\n"
+			"	.align 4			\n"
+			"	.word   17b,4b			\n"
+			"	.previous			\n"
+			: "+r" (res), "+r"(to), "+r"(from), "=r"(tmp1)
+			:
+			: "memory");
+		}
+		if (orig_n & 1) {
+			__asm__ __volatile__(
+			"18:	ldb.ab   %3, [%2,2]		\n"
+			"	stb.ab   %3, [%1,2]		\n"
+			"	sub      %0,%0,1		\n"
+			"34:	; nop				\n"
+			"	.section .fixup, \"ax\"		\n"
+			"	.align 4			\n"
+			"4:	j   34b				\n"
+			"	.previous			\n"
+			"	.section __ex_table, \"a\"	\n"
+			"	.align 4			\n"
+			"	.word   18b,4b			\n"
+			"	.previous			\n"
+			: "+r" (res), "+r"(to), "+r"(from), "=r"(tmp1)
+			:
+			: "memory");
+		}
+	} else {  /* n is NOT constant, so laddered copy of 16x,8,4,2,1  */
+
+		__asm__ __volatile__(
+		"	mov %0,%3			\n"
+		"	lsr.f   lp_count, %3,4		\n"  /* 16x bytes */
+		"	lpnz    3f			\n"
+		"1:	ld.ab   %5, [%2, 4]		\n"
+		"11:	ld.ab   %6, [%2, 4]		\n"
+		"12:	ld.ab   %7, [%2, 4]		\n"
+		"13:	ld.ab   %8, [%2, 4]		\n"
+		"	st.ab   %5, [%1, 4]		\n"
+		"	st.ab   %6, [%1, 4]		\n"
+		"	st.ab   %7, [%1, 4]		\n"
+		"	st.ab   %8, [%1, 4]		\n"
+		"	sub     %0,%0,16		\n"
+		"3:	and.f   %3,%3,0xf		\n"  /* stragglers */
+		"	bz      34f			\n"
+		"	bbit0   %3,3,31f		\n"  /* 8 bytes left */
+		"14:	ld.ab   %5, [%2,4]		\n"
+		"15:	ld.ab   %6, [%2,4]		\n"
+		"	st.ab   %5, [%1,4]		\n"
+		"	st.ab   %6, [%1,4]		\n"
+		"	sub.f   %0,%0,8			\n"
+		"31:	bbit0   %3,2,32f		\n"  /* 4 bytes left */
+		"16:	ld.ab   %5, [%2,4]		\n"
+		"	st.ab   %5, [%1,4]		\n"
+		"	sub.f   %0,%0,4			\n"
+		"32:	bbit0   %3,1,33f		\n"  /* 2 bytes left */
+		"17:	ldw.ab  %5, [%2,2]		\n"
+		"	stw.ab  %5, [%1,2]		\n"
+		"	sub.f   %0,%0,2			\n"
+		"33:	bbit0   %3,0,34f		\n"
+		"18:	ldb.ab  %5, [%2,1]		\n"  /* 1 byte left */
+		"	stb.ab  %5, [%1,1]		\n"
+		"	sub.f   %0,%0,1			\n"
+		"34:	;nop				\n"
+		"	.section .fixup, \"ax\"		\n"
+		"	.align 4			\n"
+		"4:	j   34b				\n"
+		"	.previous			\n"
+		"	.section __ex_table, \"a\"	\n"
+		"	.align 4			\n"
+		"	.word   1b, 4b			\n"
+		"	.word   11b,4b			\n"
+		"	.word   12b,4b			\n"
+		"	.word   13b,4b			\n"
+		"	.word   14b,4b			\n"
+		"	.word   15b,4b			\n"
+		"	.word   16b,4b			\n"
+		"	.word   17b,4b			\n"
+		"	.word   18b,4b			\n"
+		"	.previous			\n"
+		: "=r" (res), "+r"(to), "+r"(from), "+r"(n), "=r"(val),
+		  "=r"(tmp1), "=r"(tmp2), "=r"(tmp3), "=r"(tmp4)
+		:
+		: "lp_count", "memory");
+	}
+
+	return res;
+}
+
+extern unsigned long slowpath_copy_to_user(void __user *to, const void *from,
+					   unsigned long n);
+
+static inline unsigned long
+__arc_copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+	long res = 0;
+	char val;
+	unsigned long tmp1, tmp2, tmp3, tmp4;
+	unsigned long orig_n = n;
+
+	if (n == 0)
+		return 0;
+
+	/* unaligned */
+	if (((unsigned long)to & 0x3) || ((unsigned long)from & 0x3)) {
+
+		unsigned char tmp;
+
+		__asm__ __volatile__(
+		"	mov.f   lp_count, %0		\n"
+		"	lpnz 3f				\n"
+		"	ldb.ab  %1, [%3, 1]		\n"
+		"1:	stb.ab  %1, [%2, 1]		\n"
+		"	sub     %0, %0, 1		\n"
+		"3:	;nop				\n"
+		"	.section .fixup, \"ax\"		\n"
+		"	.align 4			\n"
+		"4:	j   3b				\n"
+		"	.previous			\n"
+		"	.section __ex_table, \"a\"	\n"
+		"	.align 4			\n"
+		"	.word   1b, 4b			\n"
+		"	.previous			\n"
+
+		: "+r" (n),
+		/* Note as an '&' earlyclobber operand to make sure the
+		 * temporary register inside the loop is not the same as
+		 * FROM or TO.
+		 */
+		  "=&r" (tmp), "+r" (to), "+r" (from)
+		:
+		: "lp_count", "lp_start", "lp_end", "memory");
+
+		return n;
+	}
+
+	if (__builtin_constant_p(orig_n)) {
+		res = orig_n;
+
+		if (orig_n / 16) {
+			orig_n = orig_n % 16;
+
+			__asm__ __volatile__(
+			"	lsr lp_count, %7,4		\n"
+			"	lp  3f				\n"
+			"	ld.ab %3, [%2, 4]		\n"
+			"	ld.ab %4, [%2, 4]		\n"
+			"	ld.ab %5, [%2, 4]		\n"
+			"	ld.ab %6, [%2, 4]		\n"
+			"1:	st.ab %3, [%1, 4]		\n"
+			"11:	st.ab %4, [%1, 4]		\n"
+			"12:	st.ab %5, [%1, 4]		\n"
+			"13:	st.ab %6, [%1, 4]		\n"
+			"	sub   %0, %0, 16		\n"
+			"3:;nop					\n"
+			"	.section .fixup, \"ax\"		\n"
+			"	.align 4			\n"
+			"4:	j   3b				\n"
+			"	.previous			\n"
+			"	.section __ex_table, \"a\"	\n"
+			"	.align 4			\n"
+			"	.word   1b, 4b			\n"
+			"	.word   11b,4b			\n"
+			"	.word   12b,4b			\n"
+			"	.word   13b,4b			\n"
+			"	.previous			\n"
+			: "+r" (res), "+r"(to), "+r"(from),
+			  "=r"(tmp1), "=r"(tmp2), "=r"(tmp3), "=r"(tmp4)
+			: "ir"(n)
+			: "lp_count", "memory");
+		}
+		if (orig_n / 8) {
+			orig_n = orig_n % 8;
+
+			__asm__ __volatile__(
+			"	ld.ab   %3, [%2,4]		\n"
+			"	ld.ab   %4, [%2,4]		\n"
+			"14:	st.ab   %3, [%1,4]		\n"
+			"15:	st.ab   %4, [%1,4]		\n"
+			"	sub     %0, %0, 8		\n"
+			"31:;nop				\n"
+			"	.section .fixup, \"ax\"		\n"
+			"	.align 4			\n"
+			"4:	j   31b				\n"
+			"	.previous			\n"
+			"	.section __ex_table, \"a\"	\n"
+			"	.align 4			\n"
+			"	.word   14b,4b			\n"
+			"	.word   15b,4b			\n"
+			"	.previous			\n"
+			: "+r" (res), "+r"(to), "+r"(from),
+			  "=r"(tmp1), "=r"(tmp2)
+			:
+			: "memory");
+		}
+		if (orig_n / 4) {
+			orig_n = orig_n % 4;
+
+			__asm__ __volatile__(
+			"	ld.ab   %3, [%2,4]		\n"
+			"16:	st.ab   %3, [%1,4]		\n"
+			"	sub     %0, %0, 4		\n"
+			"32:;nop				\n"
+			"	.section .fixup, \"ax\"		\n"
+			"	.align 4			\n"
+			"4:	j   32b				\n"
+			"	.previous			\n"
+			"	.section __ex_table, \"a\"	\n"
+			"	.align 4			\n"
+			"	.word   16b,4b			\n"
+			"	.previous			\n"
+			: "+r" (res), "+r"(to), "+r"(from), "=r"(tmp1)
+			:
+			: "memory");
+		}
+		if (orig_n / 2) {
+			orig_n = orig_n % 2;
+
+			__asm__ __volatile__(
+			"	ldw.ab    %3, [%2,2]		\n"
+			"17:	stw.ab    %3, [%1,2]		\n"
+			"	sub       %0, %0, 2		\n"
+			"33:;nop				\n"
+			"	.section .fixup, \"ax\"		\n"
+			"	.align 4			\n"
+			"4:	j   33b				\n"
+			"	.previous			\n"
+			"	.section __ex_table, \"a\"	\n"
+			"	.align 4			\n"
+			"	.word   17b,4b			\n"
+			"	.previous			\n"
+			: "+r" (res), "+r"(to), "+r"(from), "=r"(tmp1)
+			:
+			: "memory");
+		}
+		if (orig_n & 1) {
+			__asm__ __volatile__(
+			"	ldb.ab  %3, [%2,1]		\n"
+			"18:	stb.ab  %3, [%1,1]		\n"
+			"	sub     %0, %0, 1		\n"
+			"34:	;nop				\n"
+			"	.section .fixup, \"ax\"		\n"
+			"	.align 4			\n"
+			"4:	j   34b				\n"
+			"	.previous			\n"
+			"	.section __ex_table, \"a\"	\n"
+			"	.align 4			\n"
+			"	.word   18b,4b			\n"
+			"	.previous			\n"
+			: "+r" (res), "+r"(to), "+r"(from), "=r"(tmp1)
+			:
+			: "memory");
+		}
+	} else {  /* n is NOT constant, so laddered copy of 16x,8,4,2,1  */
+
+		__asm__ __volatile__(
+		"	mov   %0,%3			\n"
+		"	lsr.f lp_count, %3,4		\n"  /* 16x bytes */
+		"	lpnz  3f			\n"
+		"	ld.ab %5, [%2, 4]		\n"
+		"	ld.ab %6, [%2, 4]		\n"
+		"	ld.ab %7, [%2, 4]		\n"
+		"	ld.ab %8, [%2, 4]		\n"
+		"1:	st.ab %5, [%1, 4]		\n"
+		"11:	st.ab %6, [%1, 4]		\n"
+		"12:	st.ab %7, [%1, 4]		\n"
+		"13:	st.ab %8, [%1, 4]		\n"
+		"	sub   %0, %0, 16		\n"
+		"3:	and.f %3,%3,0xf			\n" /* stragglers */
+		"	bz 34f				\n"
+		"	bbit0   %3,3,31f		\n" /* 8 bytes left */
+		"	ld.ab   %5, [%2,4]		\n"
+		"	ld.ab   %6, [%2,4]		\n"
+		"14:	st.ab   %5, [%1,4]		\n"
+		"15:	st.ab   %6, [%1,4]		\n"
+		"	sub.f   %0, %0, 8		\n"
+		"31:	bbit0   %3,2,32f		\n"  /* 4 bytes left */
+		"	ld.ab   %5, [%2,4]		\n"
+		"16:	st.ab   %5, [%1,4]		\n"
+		"	sub.f   %0, %0, 4		\n"
+		"32:	bbit0 %3,1,33f			\n"  /* 2 bytes left */
+		"	ldw.ab    %5, [%2,2]		\n"
+		"17:	stw.ab    %5, [%1,2]		\n"
+		"	sub.f %0, %0, 2			\n"
+		"33:	bbit0 %3,0,34f			\n"
+		"	ldb.ab    %5, [%2,1]		\n"  /* 1 byte left */
+		"18:	stb.ab  %5, [%1,1]		\n"
+		"	sub.f %0, %0, 1			\n"
+		"34:	;nop				\n"
+		"	.section .fixup, \"ax\"		\n"
+		"	.align 4			\n"
+		"4:	j   34b				\n"
+		"	.previous			\n"
+		"	.section __ex_table, \"a\"	\n"
+		"	.align 4			\n"
+		"	.word   1b, 4b			\n"
+		"	.word   11b,4b			\n"
+		"	.word   12b,4b			\n"
+		"	.word   13b,4b			\n"
+		"	.word   14b,4b			\n"
+		"	.word   15b,4b			\n"
+		"	.word   16b,4b			\n"
+		"	.word   17b,4b			\n"
+		"	.word   18b,4b			\n"
+		"	.previous			\n"
+		: "=r" (res), "+r"(to), "+r"(from), "+r"(n), "=r"(val),
+		  "=r"(tmp1), "=r"(tmp2), "=r"(tmp3), "=r"(tmp4)
+		:
+		: "lp_count", "memory");
+	}
+
+	return res;
+}
+
+static inline unsigned long __arc_clear_user(void __user *to, unsigned long n)
+{
+	long res = n;
+	unsigned char *d_char = to;
+
+	__asm__ __volatile__(
+	"	bbit0   %0, 0, 1f		\n"
+	"75:	stb.ab  %2, [%0,1]		\n"
+	"	sub %1, %1, 1			\n"
+	"1:	bbit0   %0, 1, 2f		\n"
+	"76:	stw.ab  %2, [%0,2]		\n"
+	"	sub %1, %1, 2			\n"
+	"2:	asr.f   lp_count, %1, 2		\n"
+	"	lpnz    3f			\n"
+	"77:	st.ab   %2, [%0,4]		\n"
+	"	sub %1, %1, 4			\n"
+	"3:	bbit0   %1, 1, 4f		\n"
+	"78:	stw.ab  %2, [%0,2]		\n"
+	"	sub %1, %1, 2			\n"
+	"4:	bbit0   %1, 0, 5f		\n"
+	"79:	stb.ab  %2, [%0,1]		\n"
+	"	sub %1, %1, 1			\n"
+	"5:					\n"
+	"	.section .fixup, \"ax\"		\n"
+	"	.align 4			\n"
+	"3:	j   5b				\n"
+	"	.previous			\n"
+	"	.section __ex_table, \"a\"	\n"
+	"	.align 4			\n"
+	"	.word   75b, 3b			\n"
+	"	.word   76b, 3b			\n"
+	"	.word   77b, 3b			\n"
+	"	.word   78b, 3b			\n"
+	"	.word   79b, 3b			\n"
+	"	.previous			\n"
+	: "+r"(d_char), "+r"(res)
+	: "i"(0)
+	: "lp_count", "lp_start", "lp_end", "memory");
+
+	return res;
+}
+
+static inline long
+__arc_strncpy_from_user(char *dst, const char __user *src, long count)
+{
+	long res = count;
+	char val;
+	unsigned int hw_count;
+
+	if (count == 0)
+		return 0;
+
+	__asm__ __volatile__(
+	"	lp 2f		\n"
+	"1:	ldb.ab  %3, [%2, 1]		\n"
+	"	breq.d  %3, 0, 2f		\n"
+	"	stb.ab  %3, [%1, 1]		\n"
+	"2:	sub %0, %6, %4			\n"
+	"3:	;nop				\n"
+	"	.section .fixup, \"ax\"		\n"
+	"	.align 4			\n"
+	"4:	mov %0, %5			\n"
+	"	j   3b				\n"
+	"	.previous			\n"
+	"	.section __ex_table, \"a\"	\n"
+	"	.align 4			\n"
+	"	.word   1b, 4b			\n"
+	"	.previous			\n"
+	: "=r"(res), "+r"(dst), "+r"(src), "=&r"(val), "=l"(hw_count)
+	: "g"(-EFAULT), "ir"(count), "4"(count)	/* this "4" seeds lp_count */
+	: "memory");
+
+	return res;
+}
+
+static inline long __arc_strnlen_user(const char __user *s, long n)
+{
+	long res, tmp1, cnt;
+	char val;
+
+	__asm__ __volatile__(
+	"	mov %2, %1			\n"
+	"1:	ldb.ab  %3, [%0, 1]		\n"
+	"	breq.d  %3, 0, 2f		\n"
+	"	sub.f   %2, %2, 1		\n"
+	"	bnz 1b				\n"
+	"	sub %2, %2, 1			\n"
+	"2:	sub %0, %1, %2			\n"
+	"3:	;nop				\n"
+	"	.section .fixup, \"ax\"		\n"
+	"	.align 4			\n"
+	"4:	mov %0, 0			\n"
+	"	j   3b				\n"
+	"	.previous			\n"
+	"	.section __ex_table, \"a\"	\n"
+	"	.align 4			\n"
+	"	.word 1b, 4b			\n"
+	"	.previous			\n"
+	: "=r"(res), "=r"(tmp1), "=r"(cnt), "=r"(val)
+	: "0"(s), "1"(n)
+	: "memory");
+
+	return res;
+}
+
+#ifndef CONFIG_CC_OPTIMIZE_FOR_SIZE
+#define __copy_from_user(t, f, n)	__arc_copy_from_user(t, f, n)
+#define __copy_to_user(t, f, n)		__arc_copy_to_user(t, f, n)
+#define __clear_user(d, n)		__arc_clear_user(d, n)
+#define __strncpy_from_user(d, s, n)	__arc_strncpy_from_user(d, s, n)
+#define __strnlen_user(s, n)		__arc_strnlen_user(s, n)
+#else
+extern long arc_copy_from_user_noinline(void *to, const void __user * from,
+		unsigned long n);
+extern long arc_copy_to_user_noinline(void __user *to, const void *from,
+		unsigned long n);
+extern unsigned long arc_clear_user_noinline(void __user *to,
+		unsigned long n);
+extern long arc_strncpy_from_user_noinline (char *dst, const char __user *src,
+		long count);
+extern long arc_strnlen_user_noinline(const char __user *src, long n);
+
+#define __copy_from_user(t, f, n)	arc_copy_from_user_noinline(t, f, n)
+#define __copy_to_user(t, f, n)		arc_copy_to_user_noinline(t, f, n)
+#define __clear_user(d, n)		arc_clear_user_noinline(d, n)
+#define __strncpy_from_user(d, s, n)	arc_strncpy_from_user_noinline(d, s, n)
+#define __strnlen_user(s, n)		arc_strnlen_user_noinline(s, n)
+
+#endif
+
+#include <asm-generic/uaccess.h>
+
+extern int fixup_exception(struct pt_regs *regs);
+
+#endif
diff --git a/arch/arc/include/asm/unaligned.h b/arch/arc/include/asm/unaligned.h
new file mode 100644
index 000000000000..5dbe63f17b66
--- /dev/null
+++ b/arch/arc/include/asm/unaligned.h
@@ -0,0 +1,29 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_ARC_UNALIGNED_H
+#define _ASM_ARC_UNALIGNED_H
+
+/* ARC700 can't handle unaligned Data accesses. */
+
+#include <asm-generic/unaligned.h>
+#include <asm/ptrace.h>
+
+#ifdef CONFIG_ARC_MISALIGN_ACCESS
+int misaligned_fixup(unsigned long address, struct pt_regs *regs,
+		     unsigned long cause, struct callee_regs *cregs);
+#else
+static inline int
+misaligned_fixup(unsigned long address, struct pt_regs *regs,
+		 unsigned long cause, struct callee_regs *cregs)
+{
+	return 0;
+}
+#endif
+
+#endif /* _ASM_ARC_UNALIGNED_H */
diff --git a/arch/arc/include/asm/unwind.h b/arch/arc/include/asm/unwind.h
new file mode 100644
index 000000000000..7ca628b6ee2a
--- /dev/null
+++ b/arch/arc/include/asm/unwind.h
@@ -0,0 +1,163 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_ARC_UNWIND_H
+#define _ASM_ARC_UNWIND_H
+
+#ifdef CONFIG_ARC_DW2_UNWIND
+
+#include <linux/sched.h>
+
+struct arc700_regs {
+	unsigned long r0;
+	unsigned long r1;
+	unsigned long r2;
+	unsigned long r3;
+	unsigned long r4;
+	unsigned long r5;
+	unsigned long r6;
+	unsigned long r7;
+	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 r16;
+	unsigned long r17;
+	unsigned long r18;
+	unsigned long r19;
+	unsigned long r20;
+	unsigned long r21;
+	unsigned long r22;
+	unsigned long r23;
+	unsigned long r24;
+	unsigned long r25;
+	unsigned long r26;
+	unsigned long r27;	/* fp */
+	unsigned long r28;	/* sp */
+	unsigned long r29;
+	unsigned long r30;
+	unsigned long r31;	/* blink */
+	unsigned long r63;	/* pc */
+};
+
+struct unwind_frame_info {
+	struct arc700_regs regs;
+	struct task_struct *task;
+	unsigned call_frame:1;
+};
+
+#define UNW_PC(frame)		((frame)->regs.r63)
+#define UNW_SP(frame)		((frame)->regs.r28)
+#define UNW_BLINK(frame)	((frame)->regs.r31)
+
+/* Rajesh FIXME */
+#ifdef CONFIG_FRAME_POINTER
+#define UNW_FP(frame)		((frame)->regs.r27)
+#define FRAME_RETADDR_OFFSET	4
+#define FRAME_LINK_OFFSET	0
+#define STACK_BOTTOM_UNW(tsk)	STACK_LIMIT((tsk)->thread.ksp)
+#define STACK_TOP_UNW(tsk)	((tsk)->thread.ksp)
+#else
+#define UNW_FP(frame)		((void)(frame), 0)
+#endif
+
+#define STACK_LIMIT(ptr)	(((ptr) - 1) & ~(THREAD_SIZE - 1))
+
+#define UNW_REGISTER_INFO \
+	PTREGS_INFO(r0), \
+	PTREGS_INFO(r1), \
+	PTREGS_INFO(r2), \
+	PTREGS_INFO(r3), \
+	PTREGS_INFO(r4), \
+	PTREGS_INFO(r5), \
+	PTREGS_INFO(r6), \
+	PTREGS_INFO(r7), \
+	PTREGS_INFO(r8), \
+	PTREGS_INFO(r9), \
+	PTREGS_INFO(r10), \
+	PTREGS_INFO(r11), \
+	PTREGS_INFO(r12), \
+	PTREGS_INFO(r13), \
+	PTREGS_INFO(r14), \
+	PTREGS_INFO(r15), \
+	PTREGS_INFO(r16), \
+	PTREGS_INFO(r17), \
+	PTREGS_INFO(r18), \
+	PTREGS_INFO(r19), \
+	PTREGS_INFO(r20), \
+	PTREGS_INFO(r21), \
+	PTREGS_INFO(r22), \
+	PTREGS_INFO(r23), \
+	PTREGS_INFO(r24), \
+	PTREGS_INFO(r25), \
+	PTREGS_INFO(r26), \
+	PTREGS_INFO(r27), \
+	PTREGS_INFO(r28), \
+	PTREGS_INFO(r29), \
+	PTREGS_INFO(r30), \
+	PTREGS_INFO(r31), \
+	PTREGS_INFO(r63)
+
+#define UNW_DEFAULT_RA(raItem, dataAlign) \
+	((raItem).where == Memory && !((raItem).value * (dataAlign) + 4))
+
+extern int arc_unwind(struct unwind_frame_info *frame);
+extern void arc_unwind_init(void);
+extern void arc_unwind_setup(void);
+extern void *unwind_add_table(struct module *module, const void *table_start,
+			      unsigned long table_size);
+extern void unwind_remove_table(void *handle, int init_only);
+
+static inline int
+arch_unwind_init_running(struct unwind_frame_info *info,
+			 int (*callback) (struct unwind_frame_info *info,
+					  void *arg),
+			 void *arg)
+{
+	return 0;
+}
+
+static inline int arch_unw_user_mode(const struct unwind_frame_info *info)
+{
+	return 0;
+}
+
+static inline void arch_unw_init_blocked(struct unwind_frame_info *info)
+{
+	return;
+}
+
+static inline void arch_unw_init_frame_info(struct unwind_frame_info *info,
+					    struct pt_regs *regs)
+{
+	return;
+}
+
+#else
+
+#define UNW_PC(frame) ((void)(frame), 0)
+#define UNW_SP(frame) ((void)(frame), 0)
+#define UNW_FP(frame) ((void)(frame), 0)
+
+static inline void arc_unwind_init(void)
+{
+}
+
+static inline void arc_unwind_setup(void)
+{
+}
+#define unwind_add_table(a, b, c)
+#define unwind_remove_table(a, b)
+
+#endif /* CONFIG_ARC_DW2_UNWIND */
+
+#endif /* _ASM_ARC_UNWIND_H */
diff --git a/arch/arc/include/uapi/asm/Kbuild b/arch/arc/include/uapi/asm/Kbuild
new file mode 100644
index 000000000000..18fefaea73fd
--- /dev/null
+++ b/arch/arc/include/uapi/asm/Kbuild
@@ -0,0 +1,12 @@
+# UAPI Header export list
+include include/uapi/asm-generic/Kbuild.asm
+header-y += elf.h
+header-y += page.h
+header-y += setup.h
+header-y += byteorder.h
+header-y += cachectl.h
+header-y += ptrace.h
+header-y += sigcontext.h
+header-y += signal.h
+header-y += swab.h
+header-y += unistd.h
diff --git a/arch/arc/include/uapi/asm/byteorder.h b/arch/arc/include/uapi/asm/byteorder.h
new file mode 100644
index 000000000000..9da71d415c38
--- /dev/null
+++ b/arch/arc/include/uapi/asm/byteorder.h
@@ -0,0 +1,18 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ASM_ARC_BYTEORDER_H
+#define __ASM_ARC_BYTEORDER_H
+
+#ifdef CONFIG_CPU_BIG_ENDIAN
+#include <linux/byteorder/big_endian.h>
+#else
+#include <linux/byteorder/little_endian.h>
+#endif
+
+#endif /* ASM_ARC_BYTEORDER_H */
diff --git a/arch/arc/include/uapi/asm/cachectl.h b/arch/arc/include/uapi/asm/cachectl.h
new file mode 100644
index 000000000000..51c73f0255b3
--- /dev/null
+++ b/arch/arc/include/uapi/asm/cachectl.h
@@ -0,0 +1,28 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ARC_ASM_CACHECTL_H
+#define __ARC_ASM_CACHECTL_H
+
+/*
+ * ARC ABI flags defined for Android's finegrained cacheflush requirements
+ */
+#define CF_I_INV	0x0002
+#define CF_D_FLUSH	0x0010
+#define CF_D_FLUSH_INV	0x0020
+
+#define CF_DEFAULT	(CF_I_INV | CF_D_FLUSH)
+
+/*
+ * Standard flags expected by cacheflush system call users
+ */
+#define ICACHE	CF_I_INV
+#define DCACHE	CF_D_FLUSH
+#define BCACHE	(CF_I_INV | CF_D_FLUSH)
+
+#endif
diff --git a/arch/arc/include/uapi/asm/elf.h b/arch/arc/include/uapi/asm/elf.h
new file mode 100644
index 000000000000..0f99ac8fcbb2
--- /dev/null
+++ b/arch/arc/include/uapi/asm/elf.h
@@ -0,0 +1,26 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _UAPI__ASM_ARC_ELF_H
+#define _UAPI__ASM_ARC_ELF_H
+
+#include <asm/ptrace.h>		/* for user_regs_struct */
+
+/* Machine specific ELF Hdr flags */
+#define EF_ARC_OSABI_MSK	0x00000f00
+#define EF_ARC_OSABI_ORIG	0x00000000   /* MUST be zero for back-compat */
+#define EF_ARC_OSABI_CURRENT	0x00000300   /* v3 (no legacy syscalls) */
+
+typedef unsigned long elf_greg_t;
+typedef unsigned long elf_fpregset_t;
+
+#define ELF_NGREG	(sizeof(struct user_regs_struct) / sizeof(elf_greg_t))
+
+typedef elf_greg_t elf_gregset_t[ELF_NGREG];
+
+#endif
diff --git a/arch/arc/include/uapi/asm/page.h b/arch/arc/include/uapi/asm/page.h
new file mode 100644
index 000000000000..e5d41e08240c
--- /dev/null
+++ b/arch/arc/include/uapi/asm/page.h
@@ -0,0 +1,39 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _UAPI__ASM_ARC_PAGE_H
+#define _UAPI__ASM_ARC_PAGE_H
+
+/* PAGE_SHIFT determines the page size */
+#if defined(CONFIG_ARC_PAGE_SIZE_16K)
+#define PAGE_SHIFT 14
+#elif defined(CONFIG_ARC_PAGE_SIZE_4K)
+#define PAGE_SHIFT 12
+#else
+/*
+ * Default 8k
+ * done this way (instead of under CONFIG_ARC_PAGE_SIZE_8K) because adhoc
+ * user code (busybox appletlib.h) expects PAGE_SHIFT to be defined w/o
+ * using the correct uClibc header and in their build our autoconf.h is
+ * not available
+ */
+#define PAGE_SHIFT 13
+#endif
+
+#ifdef __ASSEMBLY__
+#define PAGE_SIZE	(1 << PAGE_SHIFT)
+#define PAGE_OFFSET	(0x80000000)
+#else
+#define PAGE_SIZE	(1UL << PAGE_SHIFT)	/* Default 8K */
+#define PAGE_OFFSET	(0x80000000UL)	/* Kernel starts at 2G onwards */
+#endif
+
+#define PAGE_MASK	(~(PAGE_SIZE-1))
+
+
+#endif /* _UAPI__ASM_ARC_PAGE_H */
diff --git a/arch/arc/include/uapi/asm/ptrace.h b/arch/arc/include/uapi/asm/ptrace.h
new file mode 100644
index 000000000000..6afa4f702075
--- /dev/null
+++ b/arch/arc/include/uapi/asm/ptrace.h
@@ -0,0 +1,48 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Amit Bhor, Sameer Dhavale: Codito Technologies 2004
+ */
+
+#ifndef _UAPI__ASM_ARC_PTRACE_H
+#define _UAPI__ASM_ARC_PTRACE_H
+
+
+#ifndef __ASSEMBLY__
+/*
+ * Userspace ABI: Register state needed by
+ *  -ptrace (gdbserver)
+ *  -sigcontext (SA_SIGNINFO signal frame)
+ *
+ * This is to decouple pt_regs from user-space ABI, to be able to change it
+ * w/o affecting the ABI.
+ * Although the layout (initial padding) is similar to pt_regs to have some
+ * optimizations when copying pt_regs to/from user_regs_struct.
+ *
+ * Also, sigcontext only care about the scratch regs as that is what we really
+ * save/restore for signal handling.
+*/
+struct user_regs_struct {
+
+	struct scratch {
+		long pad;
+		long bta, lp_start, lp_end, lp_count;
+		long status32, ret, blink, fp, gp;
+		long r12, r11, r10, r9, r8, r7, r6, r5, r4, r3, r2, r1, r0;
+		long sp;
+	} scratch;
+	struct callee {
+		long pad;
+		long r25, r24, r23, r22, r21, r20;
+		long r19, r18, r17, r16, r15, r14, r13;
+	} callee;
+	long efa;	/* break pt addr, for break points in delay slots */
+	long stop_pc;	/* give dbg stop_pc directly after checking orig_r8 */
+};
+#endif /* !__ASSEMBLY__ */
+
+#endif /* _UAPI__ASM_ARC_PTRACE_H */
diff --git a/arch/arc/include/uapi/asm/setup.h b/arch/arc/include/uapi/asm/setup.h
new file mode 100644
index 000000000000..a6d4e44938be
--- /dev/null
+++ b/arch/arc/include/uapi/asm/setup.h
@@ -0,0 +1,6 @@
+/*
+ * setup.h is part of userspace header ABI so UAPI scripts have to generate it
+ * even if there's nothing to export - causing empty <uapi/asm/setup.h>
+ * However to prevent "patch" from discarding it we add this placeholder
+ * comment
+ */
diff --git a/arch/arc/include/uapi/asm/sigcontext.h b/arch/arc/include/uapi/asm/sigcontext.h
new file mode 100644
index 000000000000..9678a11fc158
--- /dev/null
+++ b/arch/arc/include/uapi/asm/sigcontext.h
@@ -0,0 +1,22 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_ARC_SIGCONTEXT_H
+#define _ASM_ARC_SIGCONTEXT_H
+
+#include <asm/ptrace.h>
+
+/*
+ * Signal context structure - contains all info to do with the state
+ * before the signal handler was invoked.
+ */
+struct sigcontext {
+	struct user_regs_struct regs;
+};
+
+#endif /* _ASM_ARC_SIGCONTEXT_H */
diff --git a/arch/arc/include/uapi/asm/signal.h b/arch/arc/include/uapi/asm/signal.h
new file mode 100644
index 000000000000..fad62f7f42d6
--- /dev/null
+++ b/arch/arc/include/uapi/asm/signal.h
@@ -0,0 +1,27 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Amit Bhor, Sameer Dhavale: Codito Technologies 2004
+ */
+
+#ifndef _ASM_ARC_SIGNAL_H
+#define _ASM_ARC_SIGNAL_H
+
+/*
+ * This is much needed for ARC sigreturn optimization.
+ * This allows uClibc to piggback the addr of a sigreturn stub in sigaction,
+ * which allows sigreturn based re-entry into kernel after handling signal.
+ * W/o this kernel needs to "synthesize" the sigreturn trampoline on user
+ * mode stack which in turn forces the following:
+ * -TLB Flush (after making the stack page executable)
+ * -Cache line Flush (to make I/D Cache lines coherent)
+ */
+#define SA_RESTORER	0x04000000
+
+#include <asm-generic/signal.h>
+
+#endif /* _ASM_ARC_SIGNAL_H */
diff --git a/arch/arc/include/uapi/asm/swab.h b/arch/arc/include/uapi/asm/swab.h
new file mode 100644
index 000000000000..095599a73195
--- /dev/null
+++ b/arch/arc/include/uapi/asm/swab.h
@@ -0,0 +1,98 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * vineetg: May 2011
+ *  -Support single cycle endian-swap insn in ARC700 4.10
+ *
+ * vineetg: June 2009
+ *  -Better htonl implementation (5 instead of 9 ALU instructions)
+ *  -Hardware assisted single cycle bswap (Use Case of ARC custom instrn)
+ */
+
+#ifndef __ASM_ARC_SWAB_H
+#define __ASM_ARC_SWAB_H
+
+#include <linux/types.h>
+
+/* Native single cycle endian swap insn */
+#ifdef CONFIG_ARC_HAS_SWAPE
+
+#define __arch_swab32(x)		\
+({					\
+	unsigned int tmp = x;		\
+	__asm__(			\
+	"	swape	%0, %1	\n"	\
+	: "=r" (tmp)			\
+	: "r" (tmp));			\
+	tmp;				\
+})
+
+#else
+
+/* Several ways of Endian-Swap Emulation for ARC
+ * 0: kernel generic
+ * 1: ARC optimised "C"
+ * 2: ARC Custom instruction
+ */
+#define ARC_BSWAP_TYPE	1
+
+#if (ARC_BSWAP_TYPE == 1)		/******* Software only ********/
+
+/* The kernel default implementation of htonl is
+ *		return  x<<24 | x>>24 |
+ *		 (x & (__u32)0x0000ff00UL)<<8 | (x & (__u32)0x00ff0000UL)>>8;
+ *
+ * This generates 9 instructions on ARC (excluding the ld/st)
+ *
+ * 8051fd8c:	ld     r3,[r7,20]	; Mem op : Get the value to be swapped
+ * 8051fd98:	asl    r5,r3,24		; get  3rd Byte
+ * 8051fd9c:	lsr    r2,r3,24		; get  0th Byte
+ * 8051fda0:	and    r4,r3,0xff00
+ * 8051fda8:	asl    r4,r4,8		; get 1st Byte
+ * 8051fdac:	and    r3,r3,0x00ff0000
+ * 8051fdb4:	or     r2,r2,r5		; combine 0th and 3rd Bytes
+ * 8051fdb8:	lsr    r3,r3,8		; 2nd Byte at correct place in Dst Reg
+ * 8051fdbc:	or     r2,r2,r4		; combine 0,3 Bytes with 1st Byte
+ * 8051fdc0:	or     r2,r2,r3		; combine 0,3,1 Bytes with 2nd Byte
+ * 8051fdc4:	st     r2,[r1,20]	; Mem op : save result back to mem
+ *
+ * Joern suggested a better "C" algorithm which is great since
+ * (1) It is portable to any architecure
+ * (2) At the same time it takes advantage of ARC ISA (rotate intrns)
+ */
+
+#define __arch_swab32(x)					\
+({	unsigned long __in = (x), __tmp;			\
+	__tmp = __in << 8 | __in >> 24; /* ror tmp,in,24 */	\
+	__in = __in << 24 | __in >> 8; /* ror in,in,8 */	\
+	__tmp ^= __in;						\
+	__tmp &= 0xff00ff;					\
+	__tmp ^ __in;						\
+})
+
+#elif (ARC_BSWAP_TYPE == 2)	/* Custom single cycle bwap instruction */
+
+#define __arch_swab32(x)						\
+({									\
+	unsigned int tmp = x;						\
+	__asm__(							\
+	"	.extInstruction	bswap, 7, 0x00, SUFFIX_NONE, SYNTAX_2OP	\n"\
+	"	bswap  %0, %1						\n"\
+	: "=r" (tmp)							\
+	: "r" (tmp));							\
+	tmp;								\
+})
+
+#endif /* ARC_BSWAP_TYPE=zzz */
+
+#endif /* CONFIG_ARC_HAS_SWAPE */
+
+#if !defined(__STRICT_ANSI__) || defined(__KERNEL__)
+#define __SWAB_64_THRU_32__
+#endif
+
+#endif
diff --git a/arch/arc/include/uapi/asm/unistd.h b/arch/arc/include/uapi/asm/unistd.h
new file mode 100644
index 000000000000..6f30484f34b7
--- /dev/null
+++ b/arch/arc/include/uapi/asm/unistd.h
@@ -0,0 +1,34 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/******** no-legacy-syscalls-ABI *******/
+
+#define __ARCH_WANT_SYS_EXECVE
+#define __ARCH_WANT_SYS_CLONE
+#define __ARCH_WANT_SYS_VFORK
+#define __ARCH_WANT_SYS_FORK
+
+#define sys_mmap2 sys_mmap_pgoff
+
+#include <asm-generic/unistd.h>
+
+#define NR_syscalls	__NR_syscalls
+
+/* ARC specific syscall */
+#define __NR_cacheflush		(__NR_arch_specific_syscall + 0)
+#define __NR_arc_settls		(__NR_arch_specific_syscall + 1)
+#define __NR_arc_gettls		(__NR_arch_specific_syscall + 2)
+
+__SYSCALL(__NR_cacheflush, sys_cacheflush)
+__SYSCALL(__NR_arc_settls, sys_arc_settls)
+__SYSCALL(__NR_arc_gettls, sys_arc_gettls)
+
+
+/* Generic syscall (fs/filesystems.c - lost in asm-generic/unistd.h */
+#define __NR_sysfs		(__NR_arch_specific_syscall + 3)
+__SYSCALL(__NR_sysfs, sys_sysfs)
diff --git a/arch/arc/kernel/Makefile b/arch/arc/kernel/Makefile
new file mode 100644
index 000000000000..c242ef07ba70
--- /dev/null
+++ b/arch/arc/kernel/Makefile
@@ -0,0 +1,33 @@
+#
+# Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License version 2 as
+# published by the Free Software Foundation.
+
+# Pass UTS_MACHINE for user_regset definition
+CFLAGS_ptrace.o		+= -DUTS_MACHINE='"$(UTS_MACHINE)"'
+
+obj-y	:= arcksyms.o setup.o irq.o time.o reset.o ptrace.o entry.o process.o
+obj-y	+= signal.o traps.o sys.o troubleshoot.o stacktrace.o disasm.o clk.o
+obj-y	+= devtree.o
+
+obj-$(CONFIG_MODULES)			+= arcksyms.o module.o
+obj-$(CONFIG_SMP) 			+= smp.o
+obj-$(CONFIG_ARC_DW2_UNWIND)		+= unwind.o
+obj-$(CONFIG_KPROBES)      		+= kprobes.o
+obj-$(CONFIG_ARC_MISALIGN_ACCESS) 	+= unaligned.o
+obj-$(CONFIG_KGDB)			+= kgdb.o
+obj-$(CONFIG_ARC_METAWARE_HLINK)	+= arc_hostlink.o
+
+obj-$(CONFIG_ARC_FPU_SAVE_RESTORE)	+= fpu.o
+CFLAGS_fpu.o   += -mdpfp
+
+ifdef CONFIG_ARC_DW2_UNWIND
+CFLAGS_ctx_sw.o += -fno-omit-frame-pointer
+obj-y += ctx_sw.o
+else
+obj-y += ctx_sw_asm.o
+endif
+
+extra-y := vmlinux.lds head.o
diff --git a/arch/arc/kernel/arc_hostlink.c b/arch/arc/kernel/arc_hostlink.c
new file mode 100644
index 000000000000..47b2a17cc52a
--- /dev/null
+++ b/arch/arc/kernel/arc_hostlink.c
@@ -0,0 +1,58 @@
+/*
+ * arc_hostlink.c: Pseudo-driver for Metaware provided "hostlink" facility
+ *
+ * Allows Linux userland access to host in absence of any peripherals.
+ *
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/fs.h>		/* file_operations */
+#include <linux/miscdevice.h>
+#include <linux/mm.h>		/* VM_IO */
+#include <linux/module.h>
+#include <linux/uaccess.h>
+
+static unsigned char __HOSTLINK__[4 * PAGE_SIZE] __aligned(PAGE_SIZE);
+
+static int arc_hl_mmap(struct file *fp, struct vm_area_struct *vma)
+{
+	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+
+	if (io_remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
+			       vma->vm_end - vma->vm_start,
+			       vma->vm_page_prot)) {
+		pr_warn("Hostlink buffer mmap ERROR\n");
+		return -EAGAIN;
+	}
+	return 0;
+}
+
+static long arc_hl_ioctl(struct file *file, unsigned int cmd,
+			unsigned long arg)
+{
+	/* we only support, returning the physical addr to mmap in user space */
+	put_user((unsigned int)__HOSTLINK__, (int __user *)arg);
+	return 0;
+}
+
+static const struct file_operations arc_hl_fops = {
+	.unlocked_ioctl	= arc_hl_ioctl,
+	.mmap		= arc_hl_mmap,
+};
+
+static struct miscdevice arc_hl_dev = {
+	.minor	= MISC_DYNAMIC_MINOR,
+	.name	= "hostlink",
+	.fops	= &arc_hl_fops
+};
+
+static int __init arc_hl_init(void)
+{
+	pr_info("ARC Hostlink driver mmap at 0x%p\n", __HOSTLINK__);
+	return misc_register(&arc_hl_dev);
+}
+module_init(arc_hl_init);
diff --git a/arch/arc/kernel/arcksyms.c b/arch/arc/kernel/arcksyms.c
new file mode 100644
index 000000000000..4d9e77724bed
--- /dev/null
+++ b/arch/arc/kernel/arcksyms.c
@@ -0,0 +1,56 @@
+/*
+ * arcksyms.c - Exporting symbols not exportable from their own sources
+ *
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/module.h>
+
+/* libgcc functions, not part of kernel sources */
+extern void __ashldi3(void);
+extern void __ashrdi3(void);
+extern void __divsi3(void);
+extern void __divsf3(void);
+extern void __lshrdi3(void);
+extern void __modsi3(void);
+extern void __muldi3(void);
+extern void __ucmpdi2(void);
+extern void __udivsi3(void);
+extern void __umodsi3(void);
+extern void __cmpdi2(void);
+extern void __fixunsdfsi(void);
+extern void __muldf3(void);
+extern void __divdf3(void);
+extern void __floatunsidf(void);
+extern void __floatunsisf(void);
+
+EXPORT_SYMBOL(__ashldi3);
+EXPORT_SYMBOL(__ashrdi3);
+EXPORT_SYMBOL(__divsi3);
+EXPORT_SYMBOL(__divsf3);
+EXPORT_SYMBOL(__lshrdi3);
+EXPORT_SYMBOL(__modsi3);
+EXPORT_SYMBOL(__muldi3);
+EXPORT_SYMBOL(__ucmpdi2);
+EXPORT_SYMBOL(__udivsi3);
+EXPORT_SYMBOL(__umodsi3);
+EXPORT_SYMBOL(__cmpdi2);
+EXPORT_SYMBOL(__fixunsdfsi);
+EXPORT_SYMBOL(__muldf3);
+EXPORT_SYMBOL(__divdf3);
+EXPORT_SYMBOL(__floatunsidf);
+EXPORT_SYMBOL(__floatunsisf);
+
+/* ARC optimised assembler routines */
+EXPORT_SYMBOL(memset);
+EXPORT_SYMBOL(memcpy);
+EXPORT_SYMBOL(memcmp);
+EXPORT_SYMBOL(strchr);
+EXPORT_SYMBOL(strcpy);
+EXPORT_SYMBOL(strcmp);
+EXPORT_SYMBOL(strlen);
diff --git a/arch/arc/kernel/asm-offsets.c b/arch/arc/kernel/asm-offsets.c
new file mode 100644
index 000000000000..0dc148ebce74
--- /dev/null
+++ b/arch/arc/kernel/asm-offsets.c
@@ -0,0 +1,64 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/interrupt.h>
+#include <linux/thread_info.h>
+#include <linux/kbuild.h>
+#include <asm/hardirq.h>
+#include <asm/page.h>
+#include <asm/ptrace.h>
+
+int main(void)
+{
+	DEFINE(TASK_THREAD, offsetof(struct task_struct, thread));
+	DEFINE(TASK_THREAD_INFO, offsetof(struct task_struct, stack));
+
+	BLANK();
+
+	DEFINE(THREAD_KSP, offsetof(struct thread_struct, ksp));
+	DEFINE(THREAD_CALLEE_REG, offsetof(struct thread_struct, callee_reg));
+#ifdef CONFIG_ARC_CURR_IN_REG
+	DEFINE(THREAD_USER_R25, offsetof(struct thread_struct, user_r25));
+#endif
+	DEFINE(THREAD_FAULT_ADDR,
+	       offsetof(struct thread_struct, fault_address));
+
+	BLANK();
+
+	DEFINE(THREAD_INFO_FLAGS, offsetof(struct thread_info, flags));
+	DEFINE(THREAD_INFO_PREEMPT_COUNT,
+	       offsetof(struct thread_info, preempt_count));
+
+	BLANK();
+
+	DEFINE(TASK_ACT_MM, offsetof(struct task_struct, active_mm));
+	DEFINE(TASK_TGID, offsetof(struct task_struct, tgid));
+
+	DEFINE(MM_CTXT, offsetof(struct mm_struct, context));
+	DEFINE(MM_PGD, offsetof(struct mm_struct, pgd));
+
+	DEFINE(MM_CTXT_ASID, offsetof(mm_context_t, asid));
+
+	BLANK();
+
+	DEFINE(PT_status32, offsetof(struct pt_regs, status32));
+	DEFINE(PT_orig_r8, offsetof(struct pt_regs, orig_r8_word));
+	DEFINE(PT_sp, offsetof(struct pt_regs, sp));
+	DEFINE(PT_r0, offsetof(struct pt_regs, r0));
+	DEFINE(PT_r1, offsetof(struct pt_regs, r1));
+	DEFINE(PT_r2, offsetof(struct pt_regs, r2));
+	DEFINE(PT_r3, offsetof(struct pt_regs, r3));
+	DEFINE(PT_r4, offsetof(struct pt_regs, r4));
+	DEFINE(PT_r5, offsetof(struct pt_regs, r5));
+	DEFINE(PT_r6, offsetof(struct pt_regs, r6));
+	DEFINE(PT_r7, offsetof(struct pt_regs, r7));
+
+	return 0;
+}
diff --git a/arch/arc/kernel/clk.c b/arch/arc/kernel/clk.c
new file mode 100644
index 000000000000..66ce0dc917fb
--- /dev/null
+++ b/arch/arc/kernel/clk.c
@@ -0,0 +1,21 @@
+/*
+ * Copyright (C) 2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <asm/clk.h>
+
+unsigned long core_freq = 800000000;
+
+/*
+ * As of now we default to device-tree provided clock
+ * In future we can determine this in early boot
+ */
+int arc_set_core_freq(unsigned long freq)
+{
+	core_freq = freq;
+	return 0;
+}
diff --git a/arch/arc/kernel/ctx_sw.c b/arch/arc/kernel/ctx_sw.c
new file mode 100644
index 000000000000..60844dac6132
--- /dev/null
+++ b/arch/arc/kernel/ctx_sw.c
@@ -0,0 +1,109 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Vineetg: Aug 2009
+ *  -"C" version of lowest level context switch asm macro called by schedular
+ *   gcc doesn't generate the dward CFI info for hand written asm, hence can't
+ *   backtrace out of it (e.g. tasks sleeping in kernel).
+ *   So we cheat a bit by writing almost similar code in inline-asm.
+ *  -This is a hacky way of doing things, but there is no other simple way.
+ *   I don't want/intend to extend unwinding code to understand raw asm
+ */
+
+#include <asm/asm-offsets.h>
+#include <linux/sched.h>
+
+struct task_struct *__sched
+__switch_to(struct task_struct *prev_task, struct task_struct *next_task)
+{
+	unsigned int tmp;
+	unsigned int prev = (unsigned int)prev_task;
+	unsigned int next = (unsigned int)next_task;
+	int num_words_to_skip = 1;
+#ifdef CONFIG_ARC_CURR_IN_REG
+	num_words_to_skip++;
+#endif
+
+	__asm__ __volatile__(
+		/* FP/BLINK save generated by gcc (standard function prologue */
+		"st.a    r13, [sp, -4]   \n\t"
+		"st.a    r14, [sp, -4]   \n\t"
+		"st.a    r15, [sp, -4]   \n\t"
+		"st.a    r16, [sp, -4]   \n\t"
+		"st.a    r17, [sp, -4]   \n\t"
+		"st.a    r18, [sp, -4]   \n\t"
+		"st.a    r19, [sp, -4]   \n\t"
+		"st.a    r20, [sp, -4]   \n\t"
+		"st.a    r21, [sp, -4]   \n\t"
+		"st.a    r22, [sp, -4]   \n\t"
+		"st.a    r23, [sp, -4]   \n\t"
+		"st.a    r24, [sp, -4]   \n\t"
+#ifndef CONFIG_ARC_CURR_IN_REG
+		"st.a    r25, [sp, -4]   \n\t"
+#endif
+		"sub     sp, sp, %4      \n\t"	/* create gutter at top */
+
+		/* set ksp of outgoing task in tsk->thread.ksp */
+		"st.as   sp, [%3, %1]    \n\t"
+
+		"sync   \n\t"
+
+		/*
+		 * setup _current_task with incoming tsk.
+		 * optionally, set r25 to that as well
+		 * For SMP extra work to get to &_current_task[cpu]
+		 * (open coded SET_CURR_TASK_ON_CPU)
+		 */
+#ifndef CONFIG_SMP
+		"st  %2, [@_current_task]	\n\t"
+#else
+		"lr   r24, [identity]		\n\t"
+		"lsr  r24, r24, 8		\n\t"
+		"bmsk r24, r24, 7		\n\t"
+		"add2 r24, @_current_task, r24	\n\t"
+		"st   %2,  [r24]		\n\t"
+#endif
+#ifdef CONFIG_ARC_CURR_IN_REG
+		"mov r25, %2   \n\t"
+#endif
+
+		/* get ksp of incoming task from tsk->thread.ksp */
+		"ld.as  sp, [%2, %1]   \n\t"
+
+		/* start loading it's CALLEE reg file */
+
+		"add    sp, sp, %4     \n\t"	/* skip gutter at top */
+
+#ifndef CONFIG_ARC_CURR_IN_REG
+		"ld.ab   r25, [sp, 4]   \n\t"
+#endif
+		"ld.ab   r24, [sp, 4]   \n\t"
+		"ld.ab   r23, [sp, 4]   \n\t"
+		"ld.ab   r22, [sp, 4]   \n\t"
+		"ld.ab   r21, [sp, 4]   \n\t"
+		"ld.ab   r20, [sp, 4]   \n\t"
+		"ld.ab   r19, [sp, 4]   \n\t"
+		"ld.ab   r18, [sp, 4]   \n\t"
+		"ld.ab   r17, [sp, 4]   \n\t"
+		"ld.ab   r16, [sp, 4]   \n\t"
+		"ld.ab   r15, [sp, 4]   \n\t"
+		"ld.ab   r14, [sp, 4]   \n\t"
+		"ld.ab   r13, [sp, 4]   \n\t"
+
+		/* last (ret value) = prev : although for ARC it mov r0, r0 */
+		"mov     %0, %3        \n\t"
+
+		/* FP/BLINK restore generated by gcc (standard func epilogue */
+
+		: "=r"(tmp)
+		: "n"((TASK_THREAD + THREAD_KSP) / 4), "r"(next), "r"(prev),
+		  "n"(num_words_to_skip * 4)
+		: "blink"
+	);
+
+	return (struct task_struct *)tmp;
+}
diff --git a/arch/arc/kernel/ctx_sw_asm.S b/arch/arc/kernel/ctx_sw_asm.S
new file mode 100644
index 000000000000..d8972345e4c2
--- /dev/null
+++ b/arch/arc/kernel/ctx_sw_asm.S
@@ -0,0 +1,58 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Vineetg: Aug 2009
+ *  -Moved core context switch macro out of entry.S into this file.
+ *  -This is the more "natural" hand written assembler
+ */
+
+#include <asm/entry.h>       /* For the SAVE_* macros */
+#include <asm/asm-offsets.h>
+#include <asm/linkage.h>
+
+;################### Low Level Context Switch ##########################
+
+	.section .sched.text,"ax",@progbits
+	.align 4
+	.global __switch_to
+	.type   __switch_to, @function
+__switch_to:
+
+	/* Save regs on kernel mode stack of task */
+	st.a    blink, [sp, -4]
+	st.a    fp, [sp, -4]
+	SAVE_CALLEE_SAVED_KERNEL
+
+	/* Save the now KSP in task->thread.ksp */
+	st.as  sp, [r0, (TASK_THREAD + THREAD_KSP)/4]
+
+	/*
+	* Return last task in r0 (return reg)
+	* On ARC, Return reg = First Arg reg = r0.
+	* Since we already have last task in r0,
+	* don't need to do anything special to return it
+	*/
+
+	/* hardware memory barrier */
+	sync
+
+	/*
+	 * switch to new task, contained in r1
+	 * Temp reg r3 is required to get the ptr to store val
+	 */
+	SET_CURR_TASK_ON_CPU  r1, r3
+
+	/* reload SP with kernel mode stack pointer in task->thread.ksp */
+	ld.as  sp, [r1, (TASK_THREAD + THREAD_KSP)/4]
+
+	/* restore the registers */
+	RESTORE_CALLEE_SAVED_KERNEL
+	ld.ab   fp, [sp, 4]
+	ld.ab   blink, [sp, 4]
+	j       [blink]
+
+ARC_EXIT __switch_to
diff --git a/arch/arc/kernel/devtree.c b/arch/arc/kernel/devtree.c
new file mode 100644
index 000000000000..bdee3a812052
--- /dev/null
+++ b/arch/arc/kernel/devtree.c
@@ -0,0 +1,123 @@
+/*
+ * Copyright (C) 2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * Based on reduced version of METAG
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+
+#include <linux/init.h>
+#include <linux/reboot.h>
+#include <linux/memblock.h>
+#include <linux/of.h>
+#include <linux/of_fdt.h>
+#include <asm/prom.h>
+#include <asm/clk.h>
+#include <asm/mach_desc.h>
+
+/* called from unflatten_device_tree() to bootstrap devicetree itself */
+void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align)
+{
+	return __va(memblock_alloc(size, align));
+}
+
+/**
+ * setup_machine_fdt - Machine setup when an dtb was passed to the kernel
+ * @dt:		virtual address pointer to dt blob
+ *
+ * If a dtb was passed to the kernel, then use it to choose the correct
+ * machine_desc and to setup the system.
+ */
+struct machine_desc * __init setup_machine_fdt(void *dt)
+{
+	struct boot_param_header *devtree = dt;
+	struct machine_desc *mdesc = NULL, *mdesc_best = NULL;
+	unsigned int score, mdesc_score = ~1;
+	unsigned long dt_root;
+	const char *model, *compat;
+	void *clk;
+	char manufacturer[16];
+	unsigned long len;
+
+	/* check device tree validity */
+	if (be32_to_cpu(devtree->magic) != OF_DT_HEADER)
+		return NULL;
+
+	initial_boot_params = devtree;
+	dt_root = of_get_flat_dt_root();
+
+	/*
+	 * The kernel could be multi-platform enabled, thus could have many
+	 * "baked-in" machine descriptors. Search thru all for the best
+	 * "compatible" string match.
+	 */
+	for_each_machine_desc(mdesc) {
+		score = of_flat_dt_match(dt_root, mdesc->dt_compat);
+		if (score > 0 && score < mdesc_score) {
+			mdesc_best = mdesc;
+			mdesc_score = score;
+		}
+	}
+	if (!mdesc_best) {
+		const char *prop;
+		long size;
+
+		pr_err("\n unrecognized device tree list:\n[ ");
+
+		prop = of_get_flat_dt_prop(dt_root, "compatible", &size);
+		if (prop) {
+			while (size > 0) {
+				printk("'%s' ", prop);
+				size -= strlen(prop) + 1;
+				prop += strlen(prop) + 1;
+			}
+		}
+		printk("]\n\n");
+
+		machine_halt();
+	}
+
+	/* compat = "<manufacturer>,<model>" */
+	compat =  mdesc_best->dt_compat[0];
+
+	model = strchr(compat, ',');
+	if (model)
+		model++;
+
+	strlcpy(manufacturer, compat, model ? model - compat : strlen(compat));
+
+	pr_info("Board \"%s\" from %s (Manufacturer)\n", model, manufacturer);
+
+	/* Retrieve various information from the /chosen node */
+	of_scan_flat_dt(early_init_dt_scan_chosen, boot_command_line);
+
+	/* Initialize {size,address}-cells info */
+	of_scan_flat_dt(early_init_dt_scan_root, NULL);
+
+	/* Setup memory, calling early_init_dt_add_memory_arch */
+	of_scan_flat_dt(early_init_dt_scan_memory, NULL);
+
+	clk = of_get_flat_dt_prop(dt_root, "clock-frequency", &len);
+	if (clk)
+		arc_set_core_freq(of_read_ulong(clk, len/4));
+
+	return mdesc_best;
+}
+
+/*
+ * Copy the flattened DT out of .init since unflattening doesn't copy strings
+ * and the normal DT APIs refs them from orig flat DT
+ */
+void __init copy_devtree(void)
+{
+	void *alloc = early_init_dt_alloc_memory_arch(
+			be32_to_cpu(initial_boot_params->totalsize), 64);
+	if (alloc) {
+		memcpy(alloc, initial_boot_params,
+				be32_to_cpu(initial_boot_params->totalsize));
+		initial_boot_params = alloc;
+	}
+}
diff --git a/arch/arc/kernel/disasm.c b/arch/arc/kernel/disasm.c
new file mode 100644
index 000000000000..2f390289a792
--- /dev/null
+++ b/arch/arc/kernel/disasm.c
@@ -0,0 +1,538 @@
+/*
+ * several functions that help interpret ARC instructions
+ * used for unaligned accesses, kprobes and kgdb
+ *
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/types.h>
+#include <linux/kprobes.h>
+#include <linux/slab.h>
+#include <asm/disasm.h>
+#include <asm/uaccess.h>
+
+#if defined(CONFIG_KGDB) || defined(CONFIG_ARC_MISALIGN_ACCESS) || \
+	defined(CONFIG_KPROBES)
+
+/* disasm_instr: Analyses instruction at addr, stores
+ * findings in *state
+ */
+void __kprobes disasm_instr(unsigned long addr, struct disasm_state *state,
+	int userspace, struct pt_regs *regs, struct callee_regs *cregs)
+{
+	int fieldA = 0;
+	int fieldC = 0, fieldCisReg = 0;
+	uint16_t word1 = 0, word0 = 0;
+	int subopcode, is_linked, op_format;
+	uint16_t *ins_ptr;
+	uint16_t ins_buf[4];
+	int bytes_not_copied = 0;
+
+	memset(state, 0, sizeof(struct disasm_state));
+
+	/* This fetches the upper part of the 32 bit instruction
+	 * in both the cases of Little Endian or Big Endian configurations. */
+	if (userspace) {
+		bytes_not_copied = copy_from_user(ins_buf,
+						(const void __user *) addr, 8);
+		if (bytes_not_copied > 6)
+			goto fault;
+		ins_ptr = ins_buf;
+	} else {
+		ins_ptr = (uint16_t *) addr;
+	}
+
+	word1 = *((uint16_t *)addr);
+
+	state->major_opcode = (word1 >> 11) & 0x1F;
+
+	/* Check if the instruction is 32 bit or 16 bit instruction */
+	if (state->major_opcode < 0x0B) {
+		if (bytes_not_copied > 4)
+			goto fault;
+		state->instr_len = 4;
+		word0 = *((uint16_t *)(addr+2));
+		state->words[0] = (word1 << 16) | word0;
+	} else {
+		state->instr_len = 2;
+		state->words[0] = word1;
+	}
+
+	/* Read the second word in case of limm */
+	word1 = *((uint16_t *)(addr + state->instr_len));
+	word0 = *((uint16_t *)(addr + state->instr_len + 2));
+	state->words[1] = (word1 << 16) | word0;
+
+	switch (state->major_opcode) {
+	case op_Bcc:
+		state->is_branch = 1;
+
+		/* unconditional branch s25, conditional branch s21 */
+		fieldA = (IS_BIT(state->words[0], 16)) ?
+			FIELD_s25(state->words[0]) :
+			FIELD_s21(state->words[0]);
+
+		state->delay_slot = IS_BIT(state->words[0], 5);
+		state->target = fieldA + (addr & ~0x3);
+		state->flow = direct_jump;
+		break;
+
+	case op_BLcc:
+		if (IS_BIT(state->words[0], 16)) {
+			/* Branch and Link*/
+			/* unconditional branch s25, conditional branch s21 */
+			fieldA = (IS_BIT(state->words[0], 17)) ?
+				(FIELD_s25(state->words[0]) & ~0x3) :
+				FIELD_s21(state->words[0]);
+
+			state->flow = direct_call;
+		} else {
+			/*Branch On Compare */
+			fieldA = FIELD_s9(state->words[0]) & ~0x3;
+			state->flow = direct_jump;
+		}
+
+		state->delay_slot = IS_BIT(state->words[0], 5);
+		state->target = fieldA + (addr & ~0x3);
+		state->is_branch = 1;
+		break;
+
+	case op_LD:  /* LD<zz> a,[b,s9] */
+		state->write = 0;
+		state->di = BITS(state->words[0], 11, 11);
+		if (state->di)
+			break;
+		state->x = BITS(state->words[0], 6, 6);
+		state->zz = BITS(state->words[0], 7, 8);
+		state->aa = BITS(state->words[0], 9, 10);
+		state->wb_reg = FIELD_B(state->words[0]);
+		if (state->wb_reg == REG_LIMM) {
+			state->instr_len += 4;
+			state->aa = 0;
+			state->src1 = state->words[1];
+		} else {
+			state->src1 = get_reg(state->wb_reg, regs, cregs);
+		}
+		state->src2 = FIELD_s9(state->words[0]);
+		state->dest = FIELD_A(state->words[0]);
+		state->pref = (state->dest == REG_LIMM);
+		break;
+
+	case op_ST:
+		state->write = 1;
+		state->di = BITS(state->words[0], 5, 5);
+		if (state->di)
+			break;
+		state->aa = BITS(state->words[0], 3, 4);
+		state->zz = BITS(state->words[0], 1, 2);
+		state->src1 = FIELD_C(state->words[0]);
+		if (state->src1 == REG_LIMM) {
+			state->instr_len += 4;
+			state->src1 = state->words[1];
+		} else {
+			state->src1 = get_reg(state->src1, regs, cregs);
+		}
+		state->wb_reg = FIELD_B(state->words[0]);
+		if (state->wb_reg == REG_LIMM) {
+			state->aa = 0;
+			state->instr_len += 4;
+			state->src2 = state->words[1];
+		} else {
+			state->src2 = get_reg(state->wb_reg, regs, cregs);
+		}
+		state->src3 = FIELD_s9(state->words[0]);
+		break;
+
+	case op_MAJOR_4:
+		subopcode = MINOR_OPCODE(state->words[0]);
+		switch (subopcode) {
+		case 32:	/* Jcc */
+		case 33:	/* Jcc.D */
+		case 34:	/* JLcc */
+		case 35:	/* JLcc.D */
+			is_linked = 0;
+
+			if (subopcode == 33 || subopcode == 35)
+				state->delay_slot = 1;
+
+			if (subopcode == 34 || subopcode == 35)
+				is_linked = 1;
+
+			fieldCisReg = 0;
+			op_format = BITS(state->words[0], 22, 23);
+			if (op_format == 0 || ((op_format == 3) &&
+				(!IS_BIT(state->words[0], 5)))) {
+				fieldC = FIELD_C(state->words[0]);
+
+				if (fieldC == REG_LIMM) {
+					fieldC = state->words[1];
+					state->instr_len += 4;
+				} else {
+					fieldCisReg = 1;
+				}
+			} else if (op_format == 1 || ((op_format == 3)
+				&& (IS_BIT(state->words[0], 5)))) {
+				fieldC = FIELD_C(state->words[0]);
+			} else  {
+				/* op_format == 2 */
+				fieldC = FIELD_s12(state->words[0]);
+			}
+
+			if (!fieldCisReg) {
+				state->target = fieldC;
+				state->flow = is_linked ?
+					direct_call : direct_jump;
+			} else {
+				state->target = get_reg(fieldC, regs, cregs);
+				state->flow = is_linked ?
+					indirect_call : indirect_jump;
+			}
+			state->is_branch = 1;
+			break;
+
+		case 40:	/* LPcc */
+			if (BITS(state->words[0], 22, 23) == 3) {
+				/* Conditional LPcc u7 */
+				fieldC = FIELD_C(state->words[0]);
+
+				fieldC = fieldC << 1;
+				fieldC += (addr & ~0x03);
+				state->is_branch = 1;
+				state->flow = direct_jump;
+				state->target = fieldC;
+			}
+			/* For Unconditional lp, next pc is the fall through
+			 * which is updated */
+			break;
+
+		case 48 ... 55:	/* LD a,[b,c] */
+			state->di = BITS(state->words[0], 15, 15);
+			if (state->di)
+				break;
+			state->x = BITS(state->words[0], 16, 16);
+			state->zz = BITS(state->words[0], 17, 18);
+			state->aa = BITS(state->words[0], 22, 23);
+			state->wb_reg = FIELD_B(state->words[0]);
+			if (state->wb_reg == REG_LIMM) {
+				state->instr_len += 4;
+				state->src1 = state->words[1];
+			} else {
+				state->src1 = get_reg(state->wb_reg, regs,
+						cregs);
+			}
+			state->src2 = FIELD_C(state->words[0]);
+			if (state->src2 == REG_LIMM) {
+				state->instr_len += 4;
+				state->src2 = state->words[1];
+			} else {
+				state->src2 = get_reg(state->src2, regs,
+					cregs);
+			}
+			state->dest = FIELD_A(state->words[0]);
+			if (state->dest == REG_LIMM)
+				state->pref = 1;
+			break;
+
+		case 10:	/* MOV */
+			/* still need to check for limm to extract instr len */
+			/* MOV is special case because it only takes 2 args */
+			switch (BITS(state->words[0], 22, 23)) {
+			case 0: /* OP a,b,c */
+				if (FIELD_C(state->words[0]) == REG_LIMM)
+					state->instr_len += 4;
+				break;
+			case 1: /* OP a,b,u6 */
+				break;
+			case 2: /* OP b,b,s12 */
+				break;
+			case 3: /* OP.cc b,b,c/u6 */
+				if ((!IS_BIT(state->words[0], 5)) &&
+				    (FIELD_C(state->words[0]) == REG_LIMM))
+					state->instr_len += 4;
+				break;
+			}
+			break;
+
+
+		default:
+			/* Not a Load, Jump or Loop instruction */
+			/* still need to check for limm to extract instr len */
+			switch (BITS(state->words[0], 22, 23)) {
+			case 0: /* OP a,b,c */
+				if ((FIELD_B(state->words[0]) == REG_LIMM) ||
+				    (FIELD_C(state->words[0]) == REG_LIMM))
+					state->instr_len += 4;
+				break;
+			case 1: /* OP a,b,u6 */
+				break;
+			case 2: /* OP b,b,s12 */
+				break;
+			case 3: /* OP.cc b,b,c/u6 */
+				if ((!IS_BIT(state->words[0], 5)) &&
+				   ((FIELD_B(state->words[0]) == REG_LIMM) ||
+				    (FIELD_C(state->words[0]) == REG_LIMM)))
+					state->instr_len += 4;
+				break;
+			}
+			break;
+		}
+		break;
+
+	/* 16 Bit Instructions */
+	case op_LD_ADD: /* LD_S|LDB_S|LDW_S a,[b,c] */
+		state->zz = BITS(state->words[0], 3, 4);
+		state->src1 = get_reg(FIELD_S_B(state->words[0]), regs, cregs);
+		state->src2 = get_reg(FIELD_S_C(state->words[0]), regs, cregs);
+		state->dest = FIELD_S_A(state->words[0]);
+		break;
+
+	case op_ADD_MOV_CMP:
+		/* check for limm, ignore mov_s h,b (== mov_s 0,b) */
+		if ((BITS(state->words[0], 3, 4) < 3) &&
+		    (FIELD_S_H(state->words[0]) == REG_LIMM))
+			state->instr_len += 4;
+		break;
+
+	case op_S:
+		subopcode = BITS(state->words[0], 5, 7);
+		switch (subopcode) {
+		case 0:	/* j_s */
+		case 1:	/* j_s.d */
+		case 2:	/* jl_s */
+		case 3:	/* jl_s.d */
+			state->target = get_reg(FIELD_S_B(state->words[0]),
+						regs, cregs);
+			state->delay_slot = subopcode & 1;
+			state->flow = (subopcode >= 2) ?
+				direct_call : indirect_jump;
+			break;
+		case 7:
+			switch (BITS(state->words[0], 8, 10)) {
+			case 4:	/* jeq_s [blink] */
+			case 5:	/* jne_s [blink] */
+			case 6:	/* j_s [blink] */
+			case 7:	/* j_s.d [blink] */
+				state->delay_slot = (subopcode == 7);
+				state->flow = indirect_jump;
+				state->target = get_reg(31, regs, cregs);
+			default:
+				break;
+			}
+		default:
+			break;
+		}
+		break;
+
+	case op_LD_S:	/* LD_S c, [b, u7] */
+		state->src1 = get_reg(FIELD_S_B(state->words[0]), regs, cregs);
+		state->src2 = FIELD_S_u7(state->words[0]);
+		state->dest = FIELD_S_C(state->words[0]);
+		break;
+
+	case op_LDB_S:
+	case op_STB_S:
+		/* no further handling required as byte accesses should not
+		 * cause an unaligned access exception */
+		state->zz = 1;
+		break;
+
+	case op_LDWX_S:	/* LDWX_S c, [b, u6] */
+		state->x = 1;
+		/* intentional fall-through */
+
+	case op_LDW_S:	/* LDW_S c, [b, u6] */
+		state->zz = 2;
+		state->src1 = get_reg(FIELD_S_B(state->words[0]), regs, cregs);
+		state->src2 = FIELD_S_u6(state->words[0]);
+		state->dest = FIELD_S_C(state->words[0]);
+		break;
+
+	case op_ST_S:	/* ST_S c, [b, u7] */
+		state->write = 1;
+		state->src1 = get_reg(FIELD_S_C(state->words[0]), regs, cregs);
+		state->src2 = get_reg(FIELD_S_B(state->words[0]), regs, cregs);
+		state->src3 = FIELD_S_u7(state->words[0]);
+		break;
+
+	case op_STW_S:	/* STW_S c,[b,u6] */
+		state->write = 1;
+		state->zz = 2;
+		state->src1 = get_reg(FIELD_S_C(state->words[0]), regs, cregs);
+		state->src2 = get_reg(FIELD_S_B(state->words[0]), regs, cregs);
+		state->src3 = FIELD_S_u6(state->words[0]);
+		break;
+
+	case op_SP:	/* LD_S|LDB_S b,[sp,u7], ST_S|STB_S b,[sp,u7] */
+		/* note: we are ignoring possibility of:
+		 * ADD_S, SUB_S, PUSH_S, POP_S as these should not
+		 * cause unaliged exception anyway */
+		state->write = BITS(state->words[0], 6, 6);
+		state->zz = BITS(state->words[0], 5, 5);
+		if (state->zz)
+			break;	/* byte accesses should not come here */
+		if (!state->write) {
+			state->src1 = get_reg(28, regs, cregs);
+			state->src2 = FIELD_S_u7(state->words[0]);
+			state->dest = FIELD_S_B(state->words[0]);
+		} else {
+			state->src1 = get_reg(FIELD_S_B(state->words[0]), regs,
+					cregs);
+			state->src2 = get_reg(28, regs, cregs);
+			state->src3 = FIELD_S_u7(state->words[0]);
+		}
+		break;
+
+	case op_GP:	/* LD_S|LDB_S|LDW_S r0,[gp,s11/s9/s10] */
+		/* note: ADD_S r0, gp, s11 is ignored */
+		state->zz = BITS(state->words[0], 9, 10);
+		state->src1 = get_reg(26, regs, cregs);
+		state->src2 = state->zz ? FIELD_S_s10(state->words[0]) :
+			FIELD_S_s11(state->words[0]);
+		state->dest = 0;
+		break;
+
+	case op_Pcl:	/* LD_S b,[pcl,u10] */
+		state->src1 = regs->ret & ~3;
+		state->src2 = FIELD_S_u10(state->words[0]);
+		state->dest = FIELD_S_B(state->words[0]);
+		break;
+
+	case op_BR_S:
+		state->target = FIELD_S_s8(state->words[0]) + (addr & ~0x03);
+		state->flow = direct_jump;
+		state->is_branch = 1;
+		break;
+
+	case op_B_S:
+		fieldA = (BITS(state->words[0], 9, 10) == 3) ?
+			FIELD_S_s7(state->words[0]) :
+			FIELD_S_s10(state->words[0]);
+		state->target = fieldA + (addr & ~0x03);
+		state->flow = direct_jump;
+		state->is_branch = 1;
+		break;
+
+	case op_BL_S:
+		state->target = FIELD_S_s13(state->words[0]) + (addr & ~0x03);
+		state->flow = direct_call;
+		state->is_branch = 1;
+		break;
+
+	default:
+		break;
+	}
+
+	if (bytes_not_copied <= (8 - state->instr_len))
+		return;
+
+fault:	state->fault = 1;
+}
+
+long __kprobes get_reg(int reg, struct pt_regs *regs,
+		       struct callee_regs *cregs)
+{
+	long *p;
+
+	if (reg <= 12) {
+		p = &regs->r0;
+		return p[-reg];
+	}
+
+	if (cregs && (reg <= 25)) {
+		p = &cregs->r13;
+		return p[13-reg];
+	}
+
+	if (reg == 26)
+		return regs->r26;
+	if (reg == 27)
+		return regs->fp;
+	if (reg == 28)
+		return regs->sp;
+	if (reg == 31)
+		return regs->blink;
+
+	return 0;
+}
+
+void __kprobes set_reg(int reg, long val, struct pt_regs *regs,
+		struct callee_regs *cregs)
+{
+	long *p;
+
+	switch (reg) {
+	case 0 ... 12:
+		p = &regs->r0;
+		p[-reg] = val;
+		break;
+	case 13 ... 25:
+		if (cregs) {
+			p = &cregs->r13;
+			p[13-reg] = val;
+		}
+		break;
+	case 26:
+		regs->r26 = val;
+		break;
+	case 27:
+		regs->fp = val;
+		break;
+	case 28:
+		regs->sp = val;
+		break;
+	case 31:
+		regs->blink = val;
+		break;
+	default:
+		break;
+	}
+}
+
+/*
+ * Disassembles the insn at @pc and sets @next_pc to next PC (which could be
+ * @pc +2/4/6 (ARCompact ISA allows free intermixing of 16/32 bit insns).
+ *
+ * If @pc is a branch
+ *	-@tgt_if_br is set to branch target.
+ *	-If branch has delay slot, @next_pc updated with actual next PC.
+ */
+int __kprobes disasm_next_pc(unsigned long pc, struct pt_regs *regs,
+			     struct callee_regs *cregs,
+			     unsigned long *next_pc, unsigned long *tgt_if_br)
+{
+	struct disasm_state instr;
+
+	memset(&instr, 0, sizeof(struct disasm_state));
+	disasm_instr(pc, &instr, 0, regs, cregs);
+
+	*next_pc = pc + instr.instr_len;
+
+	/* Instruction with possible two targets branch, jump and loop */
+	if (instr.is_branch)
+		*tgt_if_br = instr.target;
+
+	/* For the instructions with delay slots, the fall through is the
+	 * instruction following the instruction in delay slot.
+	 */
+	 if (instr.delay_slot) {
+		struct disasm_state instr_d;
+
+		disasm_instr(*next_pc, &instr_d, 0, regs, cregs);
+
+		*next_pc += instr_d.instr_len;
+	 }
+
+	 /* Zero Overhead Loop - end of the loop */
+	if (!(regs->status32 & STATUS32_L) && (*next_pc == regs->lp_end)
+		&& (regs->lp_count > 1)) {
+		*next_pc = regs->lp_start;
+	}
+
+	return instr.is_branch;
+}
+
+#endif /* CONFIG_KGDB || CONFIG_MISALIGN_ACCESS || CONFIG_KPROBES */
diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S
new file mode 100644
index 000000000000..ef6800ba2f03
--- /dev/null
+++ b/arch/arc/kernel/entry.S
@@ -0,0 +1,839 @@
+/*
+ * Low Level Interrupts/Traps/Exceptions(non-TLB) Handling for ARC
+ *
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * vineetg: May 2011
+ *  -Userspace unaligned access emulation
+ *
+ * vineetg: Feb 2011 (ptrace low level code fixes)
+ *  -traced syscall return code (r0) was not saved into pt_regs for restoring
+ *   into user reg-file when traded task rets to user space.
+ *  -syscalls needing arch-wrappers (mainly for passing sp as pt_regs)
+ *   were not invoking post-syscall trace hook (jumping directly into
+ *   ret_from_system_call)
+ *
+ * vineetg: Nov 2010:
+ *  -Vector table jumps (@8 bytes) converted into branches (@4 bytes)
+ *  -To maintain the slot size of 8 bytes/vector, added nop, which is
+ *   not executed at runtime.
+ *
+ * vineetg: Nov 2009 (Everything needed for TIF_RESTORE_SIGMASK)
+ *  -do_signal()invoked upon TIF_RESTORE_SIGMASK as well
+ *  -Wrappers for sys_{,rt_}sigsuspend() nolonger needed as they don't
+ *   need ptregs anymore
+ *
+ * Vineetg: Oct 2009
+ *  -In a rare scenario, Process gets a Priv-V exception and gets scheduled
+ *   out. Since we don't do FAKE RTIE for Priv-V, CPU excpetion state remains
+ *   active (AE bit enabled).  This causes a double fault for a subseq valid
+ *   exception. Thus FAKE RTIE needed in low level Priv-Violation handler.
+ *   Instr Error could also cause similar scenario, so same there as well.
+ *
+ * Vineetg: March 2009 (Supporting 2 levels of Interrupts)
+ *
+ * Vineetg: Aug 28th 2008: Bug #94984
+ *  -Zero Overhead Loop Context shd be cleared when entering IRQ/EXcp/Trap
+ *   Normally CPU does this automatically, however when doing FAKE rtie,
+ *   we need to explicitly do this. The problem in macros
+ *   FAKE_RET_FROM_EXCPN and FAKE_RET_FROM_EXCPN_LOCK_IRQ was that this bit
+ *   was being "CLEARED" rather then "SET". Since it is Loop INHIBIT Bit,
+ *   setting it and not clearing it clears ZOL context
+ *
+ * Vineetg: May 16th, 2008
+ *  - r25 now contains the Current Task when in kernel
+ *
+ * Vineetg: Dec 22, 2007
+ *    Minor Surgery of Low Level ISR to make it SMP safe
+ *    - MMU_SCRATCH0 Reg used for freeing up r9 in Level 1 ISR
+ *    - _current_task is made an array of NR_CPUS
+ *    - Access of _current_task wrapped inside a macro so that if hardware
+ *       team agrees for a dedicated reg, no other code is touched
+ *
+ * Amit Bhor, Rahul Trivedi, Kanika Nema, Sameer Dhavale : Codito Tech 2004
+ */
+
+/*------------------------------------------------------------------
+ *    Function                            ABI
+ *------------------------------------------------------------------
+ *
+ *  Arguments                           r0 - r7
+ *  Caller Saved Registers              r0 - r12
+ *  Callee Saved Registers              r13- r25
+ *  Global Pointer (gp)                 r26
+ *  Frame Pointer (fp)                  r27
+ *  Stack Pointer (sp)                  r28
+ *  Interrupt link register (ilink1)    r29
+ *  Interrupt link register (ilink2)    r30
+ *  Branch link register (blink)        r31
+ *------------------------------------------------------------------
+ */
+
+	.cpu A7
+
+;############################ Vector Table #################################
+
+.macro VECTOR  lbl
+#if 1   /* Just in case, build breaks */
+	j   \lbl
+#else
+	b   \lbl
+	nop
+#endif
+.endm
+
+	.section .vector, "ax",@progbits
+	.align 4
+
+/* Each entry in the vector table must occupy 2 words. Since it is a jump
+ * across sections (.vector to .text) we are gauranteed that 'j somewhere'
+ * will use the 'j limm' form of the intrsuction as long as somewhere is in
+ * a section other than .vector.
+ */
+
+; ********* Critical System Events **********************
+VECTOR   res_service             ; 0x0, Restart Vector  (0x0)
+VECTOR   mem_service             ; 0x8, Mem exception   (0x1)
+VECTOR   instr_service           ; 0x10, Instrn Error   (0x2)
+
+; ******************** Device ISRs **********************
+#ifdef CONFIG_ARC_IRQ3_LV2
+VECTOR   handle_interrupt_level2
+#else
+VECTOR   handle_interrupt_level1
+#endif
+
+VECTOR   handle_interrupt_level1
+
+#ifdef CONFIG_ARC_IRQ5_LV2
+VECTOR   handle_interrupt_level2
+#else
+VECTOR   handle_interrupt_level1
+#endif
+
+#ifdef CONFIG_ARC_IRQ6_LV2
+VECTOR   handle_interrupt_level2
+#else
+VECTOR   handle_interrupt_level1
+#endif
+
+.rept   25
+VECTOR   handle_interrupt_level1 ; Other devices
+.endr
+
+/* FOR ARC600: timer = 0x3, uart = 0x8, emac = 0x10 */
+
+; ******************** Exceptions **********************
+VECTOR   EV_MachineCheck         ; 0x100, Fatal Machine check   (0x20)
+VECTOR   EV_TLBMissI             ; 0x108, Intruction TLB miss   (0x21)
+VECTOR   EV_TLBMissD             ; 0x110, Data TLB miss         (0x22)
+VECTOR   EV_TLBProtV             ; 0x118, Protection Violation  (0x23)
+				 ;         or Misaligned Access
+VECTOR   EV_PrivilegeV           ; 0x120, Privilege Violation   (0x24)
+VECTOR   EV_Trap                 ; 0x128, Trap exception        (0x25)
+VECTOR   EV_Extension            ; 0x130, Extn Intruction Excp  (0x26)
+
+.rept   24
+VECTOR   reserved                ; Reserved Exceptions
+.endr
+
+#include <linux/linkage.h>   /* ARC_{EXTRY,EXIT} */
+#include <asm/entry.h>       /* SAVE_ALL_{INT1,INT2,TRAP...} */
+#include <asm/errno.h>
+#include <asm/arcregs.h>
+#include <asm/irqflags.h>
+
+;##################### Scratch Mem for IRQ stack switching #############
+
+ARCFP_DATA int1_saved_reg
+	.align 32
+	.type   int1_saved_reg, @object
+	.size   int1_saved_reg, 4
+int1_saved_reg:
+	.zero 4
+
+/* Each Interrupt level needs it's own scratch */
+#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS
+
+ARCFP_DATA int2_saved_reg
+	.type   int2_saved_reg, @object
+	.size   int2_saved_reg, 4
+int2_saved_reg:
+	.zero 4
+
+#endif
+
+; ---------------------------------------------
+	.section .text, "ax",@progbits
+
+res_service:		; processor restart
+	flag    0x1     ; not implemented
+	nop
+	nop
+
+reserved:		; processor restart
+	rtie            ; jump to processor initializations
+
+;##################### Interrupt Handling ##############################
+
+#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS
+; ---------------------------------------------
+;  Level 2 ISR: Can interrupt a Level 1 ISR
+; ---------------------------------------------
+ARC_ENTRY handle_interrupt_level2
+
+	; TODO-vineetg for SMP this wont work
+	; free up r9 as scratchpad
+	st  r9, [@int2_saved_reg]
+
+	;Which mode (user/kernel) was the system in when intr occured
+	lr  r9, [status32_l2]
+
+	SWITCH_TO_KERNEL_STK
+	SAVE_ALL_INT2
+
+	;------------------------------------------------------
+	; if L2 IRQ interrupted a L1 ISR, disable preemption
+	;------------------------------------------------------
+
+	ld r9, [sp, PT_status32]        ; get statu32_l2 (saved in pt_regs)
+	bbit0 r9, STATUS_A1_BIT, 1f     ; L1 not active when L2 IRQ, so normal
+
+	; A1 is set in status32_l2
+	; bump thread_info->preempt_count (Disable preemption)
+	GET_CURR_THR_INFO_FROM_SP   r10
+	ld      r9, [r10, THREAD_INFO_PREEMPT_COUNT]
+	add     r9, r9, 1
+	st      r9, [r10, THREAD_INFO_PREEMPT_COUNT]
+
+1:
+	;------------------------------------------------------
+	; setup params for Linux common ISR and invoke it
+	;------------------------------------------------------
+	lr  r0, [icause2]
+	and r0, r0, 0x1f
+
+	bl.d  @arch_do_IRQ
+	mov r1, sp
+
+	mov r8,0x2
+	sr r8, [AUX_IRQ_LV12]       ; clear bit in Sticky Status Reg
+
+	b   ret_from_exception
+
+ARC_EXIT handle_interrupt_level2
+
+#endif
+
+; ---------------------------------------------
+;  Level 1 ISR
+; ---------------------------------------------
+ARC_ENTRY handle_interrupt_level1
+
+	/* free up r9 as scratchpad */
+#ifdef CONFIG_SMP
+	sr  r9, [ARC_REG_SCRATCH_DATA0]
+#else
+	st   r9, [@int1_saved_reg]
+#endif
+
+	;Which mode (user/kernel) was the system in when intr occured
+	lr  r9, [status32_l1]
+
+	SWITCH_TO_KERNEL_STK
+	SAVE_ALL_INT1
+
+	lr  r0, [icause1]
+	and r0, r0, 0x1f
+
+	bl.d  @arch_do_IRQ
+	mov r1, sp
+
+	mov r8,0x1
+	sr r8, [AUX_IRQ_LV12]       ; clear bit in Sticky Status Reg
+
+	b   ret_from_exception
+ARC_EXIT handle_interrupt_level1
+
+;################### Non TLB Exception Handling #############################
+
+; ---------------------------------------------
+; Instruction Error Exception Handler
+; ---------------------------------------------
+
+ARC_ENTRY instr_service
+
+	EXCPN_PROLOG_FREEUP_REG r9
+
+	lr  r9, [erstatus]
+
+	SWITCH_TO_KERNEL_STK
+	SAVE_ALL_SYS
+
+	lr  r0, [ecr]
+	lr  r1, [efa]
+
+	mov r2, sp
+
+	FAKE_RET_FROM_EXCPN r9
+
+	bl  do_insterror_or_kprobe
+	b   ret_from_exception
+ARC_EXIT instr_service
+
+; ---------------------------------------------
+; Memory Error Exception Handler
+; ---------------------------------------------
+
+ARC_ENTRY mem_service
+
+	EXCPN_PROLOG_FREEUP_REG r9
+
+	lr  r9, [erstatus]
+
+	SWITCH_TO_KERNEL_STK
+	SAVE_ALL_SYS
+
+	lr  r0, [ecr]
+	lr  r1, [efa]
+	mov r2, sp
+	bl  do_memory_error
+	b   ret_from_exception
+ARC_EXIT mem_service
+
+; ---------------------------------------------
+; Machine Check Exception Handler
+; ---------------------------------------------
+
+ARC_ENTRY EV_MachineCheck
+
+	EXCPN_PROLOG_FREEUP_REG r9
+	lr  r9, [erstatus]
+
+	SWITCH_TO_KERNEL_STK
+	SAVE_ALL_SYS
+
+	lr  r0, [ecr]
+	lr  r1, [efa]
+	mov r2, sp
+
+	brne    r0, 0x200100, 1f
+	bl      do_tlb_overlap_fault
+	b       ret_from_exception
+
+1:
+	; DEAD END: can't do much, display Regs and HALT
+	SAVE_CALLEE_SAVED_USER
+
+	GET_CURR_TASK_FIELD_PTR   TASK_THREAD, r10
+	st  sp, [r10, THREAD_CALLEE_REG]
+
+	j  do_machine_check_fault
+
+ARC_EXIT EV_MachineCheck
+
+; ---------------------------------------------
+; Protection Violation Exception Handler
+; ---------------------------------------------
+
+ARC_ENTRY EV_TLBProtV
+
+	EXCPN_PROLOG_FREEUP_REG r9
+
+	;Which mode (user/kernel) was the system in when Exception occured
+	lr  r9, [erstatus]
+
+	SWITCH_TO_KERNEL_STK
+	SAVE_ALL_SYS
+
+	;---------(3) Save some more regs-----------------
+	;  vineetg: Mar 6th: Random Seg Fault issue #1
+	;  ecr and efa were not saved in case an Intr sneaks in
+	;  after fake rtie
+	;
+	lr  r3, [ecr]
+	lr  r4, [efa]
+
+	; --------(4) Return from CPU Exception Mode ---------
+	;  Fake a rtie, but rtie to next label
+	;  That way, subsequently, do_page_fault ( ) executes in pure kernel
+	;  mode with further Exceptions enabled
+
+	FAKE_RET_FROM_EXCPN r9
+
+	;------ (5) Type of Protection Violation? ----------
+	;
+	; ProtV Hardware Exception is triggered for Access Faults of 2 types
+	;   -Access Violaton (WRITE to READ ONLY Page) - for linux COW
+	;   -Unaligned Access (READ/WRITE on odd boundary)
+	;
+	cmp r3, 0x230400    ; Misaligned data access ?
+	beq 4f
+
+	;========= (6a) Access Violation Processing ========
+	cmp r3, 0x230100
+	mov r1, 0x0              ; if LD exception ? write = 0
+	mov.ne r1, 0x1           ; else write = 1
+
+	mov r2, r4              ; faulting address
+	mov r0, sp              ; pt_regs
+	bl  do_page_fault
+	b   ret_from_exception
+
+	;========== (6b) Non aligned access ============
+4:
+	mov r0, r3              ; cause code
+	mov r1, r4              ; faulting address
+	mov r2, sp              ; pt_regs
+
+#ifdef  CONFIG_ARC_MISALIGN_ACCESS
+	SAVE_CALLEE_SAVED_USER
+	mov r3, sp              ; callee_regs
+#endif
+
+	bl  do_misaligned_access
+
+#ifdef  CONFIG_ARC_MISALIGN_ACCESS
+	DISCARD_CALLEE_SAVED_USER
+#endif
+
+	b   ret_from_exception
+
+ARC_EXIT EV_TLBProtV
+
+; ---------------------------------------------
+; Privilege Violation Exception Handler
+; ---------------------------------------------
+ARC_ENTRY EV_PrivilegeV
+
+	EXCPN_PROLOG_FREEUP_REG r9
+
+	lr  r9, [erstatus]
+
+	SWITCH_TO_KERNEL_STK
+	SAVE_ALL_SYS
+
+	lr  r0, [ecr]
+	lr  r1, [efa]
+	mov r2, sp
+
+	FAKE_RET_FROM_EXCPN r9
+
+	bl  do_privilege_fault
+	b   ret_from_exception
+ARC_EXIT EV_PrivilegeV
+
+; ---------------------------------------------
+; Extension Instruction Exception Handler
+; ---------------------------------------------
+ARC_ENTRY EV_Extension
+
+	EXCPN_PROLOG_FREEUP_REG r9
+	lr  r9, [erstatus]
+
+	SWITCH_TO_KERNEL_STK
+	SAVE_ALL_SYS
+
+	lr  r0, [ecr]
+	lr  r1, [efa]
+	mov r2, sp
+	bl  do_extension_fault
+	b   ret_from_exception
+ARC_EXIT EV_Extension
+
+;######################### System Call Tracing #########################
+
+tracesys:
+	; save EFA in case tracer wants the PC of traced task
+	; using ERET won't work since next-PC has already committed
+	lr  r12, [efa]
+	GET_CURR_TASK_FIELD_PTR   TASK_THREAD, r11
+	st  r12, [r11, THREAD_FAULT_ADDR]
+
+	; PRE Sys Call Ptrace hook
+	mov r0, sp			; pt_regs needed
+	bl  @syscall_trace_entry
+
+	; Tracing code now returns the syscall num (orig or modif)
+	mov r8, r0
+
+	; Do the Sys Call as we normally would.
+	; Validate the Sys Call number
+	cmp     r8,  NR_syscalls
+	mov.hi  r0, -ENOSYS
+	bhi     tracesys_exit
+
+	; Restore the sys-call args. Mere invocation of the hook abv could have
+	; clobbered them (since they are in scratch regs). The tracer could also
+	; have deliberately changed the syscall args: r0-r7
+	ld  r0, [sp, PT_r0]
+	ld  r1, [sp, PT_r1]
+	ld  r2, [sp, PT_r2]
+	ld  r3, [sp, PT_r3]
+	ld  r4, [sp, PT_r4]
+	ld  r5, [sp, PT_r5]
+	ld  r6, [sp, PT_r6]
+	ld  r7, [sp, PT_r7]
+	ld.as   r9, [sys_call_table, r8]
+	jl      [r9]        ; Entry into Sys Call Handler
+
+tracesys_exit:
+	st  r0, [sp, PT_r0]     ; sys call return value in pt_regs
+
+	;POST Sys Call Ptrace Hook
+	bl  @syscall_trace_exit
+	b   ret_from_exception ; NOT ret_from_system_call at is saves r0 which
+	; we'd done before calling post hook above
+
+;################### Break Point TRAP ##########################
+
+	; ======= (5b) Trap is due to Break-Point =========
+
+trap_with_param:
+
+	; stop_pc info by gdb needs this info
+	stw orig_r8_IS_BRKPT, [sp, PT_orig_r8]
+
+	mov r0, r12
+	lr  r1, [efa]
+	mov r2, sp
+
+	; Now that we have read EFA, its safe to do "fake" rtie
+	;   and get out of CPU exception mode
+	FAKE_RET_FROM_EXCPN r11
+
+	; Save callee regs in case gdb wants to have a look
+	; SP will grow up by size of CALLEE Reg-File
+	; NOTE: clobbers r12
+	SAVE_CALLEE_SAVED_USER
+
+	; save location of saved Callee Regs @ thread_struct->pc
+	GET_CURR_TASK_FIELD_PTR   TASK_THREAD, r10
+	st  sp, [r10, THREAD_CALLEE_REG]
+
+	; Call the trap handler
+	bl  do_non_swi_trap
+
+	; unwind stack to discard Callee saved Regs
+	DISCARD_CALLEE_SAVED_USER
+
+	b   ret_from_exception
+
+;##################### Trap Handling ##############################
+;
+; EV_Trap caused by TRAP_S and TRAP0 instructions.
+;------------------------------------------------------------------
+;   (1) System Calls
+;       :parameters in r0-r7.
+;       :r8 has the system call number
+;   (2) Break Points
+;------------------------------------------------------------------
+
+ARC_ENTRY EV_Trap
+
+	; Need at least 1 reg to code the early exception prolog
+	EXCPN_PROLOG_FREEUP_REG r9
+
+	;Which mode (user/kernel) was the system in when intr occured
+	lr  r9, [erstatus]
+
+	SWITCH_TO_KERNEL_STK
+	SAVE_ALL_TRAP
+
+	;------- (4) What caused the Trap --------------
+	lr     r12, [ecr]
+	and.f  0, r12, ECR_PARAM_MASK
+	bnz    trap_with_param
+
+	; ======= (5a) Trap is due to System Call ========
+
+	; Before doing anything, return from CPU Exception Mode
+	FAKE_RET_FROM_EXCPN r11
+
+	; If syscall tracing ongoing, invoke pre-pos-hooks
+	GET_CURR_THR_INFO_FLAGS   r10
+	btst r10, TIF_SYSCALL_TRACE
+	bnz tracesys  ; this never comes back
+
+	;============ This is normal System Call case ==========
+	; Sys-call num shd not exceed the total system calls avail
+	cmp     r8,  NR_syscalls
+	mov.hi  r0, -ENOSYS
+	bhi     ret_from_system_call
+
+	; Offset into the syscall_table and call handler
+	ld.as   r9,[sys_call_table, r8]
+	jl      [r9]        ; Entry into Sys Call Handler
+
+	; fall through to ret_from_system_call
+ARC_EXIT EV_Trap
+
+ARC_ENTRY ret_from_system_call
+
+	st  r0, [sp, PT_r0]     ; sys call return value in pt_regs
+
+	; fall through yet again to ret_from_exception
+
+;############# Return from Intr/Excp/Trap (Linux Specifics) ##############
+;
+; If ret to user mode do we need to handle signals, schedule() et al.
+
+ARC_ENTRY ret_from_exception
+
+	; Pre-{IRQ,Trap,Exception} K/U mode from pt_regs->status32
+	ld  r8, [sp, PT_status32]   ; returning to User/Kernel Mode
+
+#ifdef CONFIG_PREEMPT
+	bbit0  r8, STATUS_U_BIT, resume_kernel_mode
+#else
+	bbit0  r8, STATUS_U_BIT, restore_regs
+#endif
+
+	; Before returning to User mode check-for-and-complete any pending work
+	; such as rescheduling/signal-delivery etc.
+resume_user_mode_begin:
+
+	; Disable IRQs to ensures that chk for pending work itself is atomic
+	; (and we don't end up missing a NEED_RESCHED/SIGPENDING due to an
+	; interim IRQ).
+	IRQ_DISABLE	r10
+
+	; Fast Path return to user mode if no pending work
+	GET_CURR_THR_INFO_FLAGS   r9
+	and.f  0,  r9, _TIF_WORK_MASK
+	bz     restore_regs
+
+	; --- (Slow Path #1) task preemption ---
+	bbit0  r9, TIF_NEED_RESCHED, .Lchk_pend_signals
+	mov    blink, resume_user_mode_begin  ; tail-call to U mode ret chks
+	b      @schedule 	; BTST+Bnz causes relo error in link
+
+.Lchk_pend_signals:
+	IRQ_ENABLE	r10
+
+	; --- (Slow Path #2) pending signal  ---
+	mov r0, sp	; pt_regs for arg to do_signal()/do_notify_resume()
+
+	bbit0  r9, TIF_SIGPENDING, .Lchk_notify_resume
+
+	; Normal Trap/IRQ entry only saves Scratch (caller-saved) regs
+	; in pt_reg since the "C" ABI (kernel code) will automatically
+	; save/restore callee-saved regs.
+	;
+	; However, here we need to explicitly save callee regs because
+	; (i)  If this signal causes coredump - full regfile needed
+	; (ii) If signal is SIGTRAP/SIGSTOP, task is being traced thus
+	;      tracer might call PEEKUSR(CALLEE reg)
+	;
+	; NOTE: SP will grow up by size of CALLEE Reg-File
+	SAVE_CALLEE_SAVED_USER		; clobbers r12
+
+	; save location of saved Callee Regs @ thread_struct->callee
+	GET_CURR_TASK_FIELD_PTR   TASK_THREAD, r10
+	st  sp, [r10, THREAD_CALLEE_REG]
+
+	bl  @do_signal
+
+	; Ideally we want to discard the Callee reg above, however if this was
+	; a tracing signal, tracer could have done a POKEUSR(CALLEE reg)
+	RESTORE_CALLEE_SAVED_USER
+
+	b      resume_user_mode_begin	; loop back to start of U mode ret
+
+	; --- (Slow Path #3) notify_resume ---
+.Lchk_notify_resume:
+	btst   r9, TIF_NOTIFY_RESUME
+	blnz   @do_notify_resume
+	b      resume_user_mode_begin	; unconditionally back to U mode ret chks
+					; for single exit point from this block
+
+#ifdef CONFIG_PREEMPT
+
+resume_kernel_mode:
+
+	; Can't preempt if preemption disabled
+	GET_CURR_THR_INFO_FROM_SP   r10
+	ld  r8, [r10, THREAD_INFO_PREEMPT_COUNT]
+	brne  r8, 0, restore_regs
+
+	; check if this task's NEED_RESCHED flag set
+	ld  r9, [r10, THREAD_INFO_FLAGS]
+	bbit0  r9, TIF_NEED_RESCHED, restore_regs
+
+	IRQ_DISABLE	r9
+
+	; Invoke PREEMPTION
+	bl      preempt_schedule_irq
+
+	; preempt_schedule_irq() always returns with IRQ disabled
+#endif
+
+	; fall through
+
+;############# Return from Intr/Excp/Trap (ARC Specifics) ##############
+;
+; Restore the saved sys context (common exit-path for EXCPN/IRQ/Trap)
+; IRQ shd definitely not happen between now and rtie
+
+restore_regs :
+
+	; Disable Interrupts while restoring reg-file back
+	; XXX can this be optimised out
+	IRQ_DISABLE_SAVE    r9, r10	;@r10 has prisitine (pre-disable) copy
+
+#ifdef CONFIG_ARC_CURR_IN_REG
+	; Restore User R25
+	; Earlier this used to be only for returning to user mode
+	; However with 2 levels of IRQ this can also happen even if
+	; in kernel mode
+	ld r9, [sp, PT_sp]
+	brhs r9, VMALLOC_START, 8f
+	RESTORE_USER_R25
+8:
+#endif
+
+	; Restore REG File. In case multiple Events outstanding,
+	; use the same priorty as rtie: EXCPN, L2 IRQ, L1 IRQ, None
+	; Note that we use realtime STATUS32 (not pt_regs->status32) to
+	; decide that.
+
+	; if Returning from Exception
+	bbit0  r10, STATUS_AE_BIT, not_exception
+	RESTORE_ALL_SYS
+	rtie
+
+	; Not Exception so maybe Interrupts (Level 1 or 2)
+
+not_exception:
+
+#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS
+
+	bbit0  r10, STATUS_A2_BIT, not_level2_interrupt
+
+	;------------------------------------------------------------------
+	; if L2 IRQ interrupted a L1 ISR,  we'd disbaled preemption earlier
+	; so that sched doesnt move to new task, causing L1 to be delayed
+	; undeterministically. Now that we've achieved that, lets reset
+	; things to what they were, before returning from L2 context
+	;----------------------------------------------------------------
+
+	ldw  r9, [sp, PT_orig_r8]      ; get orig_r8 to make sure it is
+	brne r9, orig_r8_IS_IRQ2, 149f ; infact a L2 ISR ret path
+
+	ld r9, [sp, PT_status32]       ; get statu32_l2 (saved in pt_regs)
+	bbit0 r9, STATUS_A1_BIT, 149f  ; L1 not active when L2 IRQ, so normal
+
+	; A1 is set in status32_l2
+	; decrement thread_info->preempt_count (re-enable preemption)
+	GET_CURR_THR_INFO_FROM_SP   r10
+	ld      r9, [r10, THREAD_INFO_PREEMPT_COUNT]
+
+	; paranoid check, given A1 was active when A2 happened, preempt count
+	; must not be 0 beccause we would have incremented it.
+	; If this does happen we simply HALT as it means a BUG !!!
+	cmp     r9, 0
+	bnz     2f
+	flag 1
+
+2:
+	sub     r9, r9, 1
+	st      r9, [r10, THREAD_INFO_PREEMPT_COUNT]
+
+149:
+	;return from level 2
+	RESTORE_ALL_INT2
+debug_marker_l2:
+	rtie
+
+not_level2_interrupt:
+
+#endif
+
+	bbit0  r10, STATUS_A1_BIT, not_level1_interrupt
+
+	;return from level 1
+
+	RESTORE_ALL_INT1
+debug_marker_l1:
+	rtie
+
+not_level1_interrupt:
+
+	;this case is for syscalls or Exceptions (with fake rtie)
+
+	RESTORE_ALL_SYS
+debug_marker_syscall:
+	rtie
+
+ARC_EXIT ret_from_exception
+
+ARC_ENTRY ret_from_fork
+	; when the forked child comes here from the __switch_to function
+	; r0 has the last task pointer.
+	; put last task in scheduler queue
+	bl   @schedule_tail
+
+	; If kernel thread, jump to it's entry-point
+	ld   r9, [sp, PT_status32]
+	brne r9, 0, 1f
+
+	jl.d [r14]
+	mov  r0, r13		; arg to payload
+
+1:
+	; special case of kernel_thread entry point returning back due to
+	; kernel_execve() - pretend return from syscall to ret to userland
+	b    ret_from_exception
+ARC_EXIT ret_from_fork
+
+;################### Special Sys Call Wrappers ##########################
+
+; TBD: call do_fork directly from here
+ARC_ENTRY sys_fork_wrapper
+	SAVE_CALLEE_SAVED_USER
+	bl  @sys_fork
+	DISCARD_CALLEE_SAVED_USER
+
+	GET_CURR_THR_INFO_FLAGS   r10
+	btst r10, TIF_SYSCALL_TRACE
+	bnz  tracesys_exit
+
+	b ret_from_system_call
+ARC_EXIT sys_fork_wrapper
+
+ARC_ENTRY sys_vfork_wrapper
+	SAVE_CALLEE_SAVED_USER
+	bl  @sys_vfork
+	DISCARD_CALLEE_SAVED_USER
+
+	GET_CURR_THR_INFO_FLAGS   r10
+	btst r10, TIF_SYSCALL_TRACE
+	bnz  tracesys_exit
+
+	b ret_from_system_call
+ARC_EXIT sys_vfork_wrapper
+
+ARC_ENTRY sys_clone_wrapper
+	SAVE_CALLEE_SAVED_USER
+	bl  @sys_clone
+	DISCARD_CALLEE_SAVED_USER
+
+	GET_CURR_THR_INFO_FLAGS   r10
+	btst r10, TIF_SYSCALL_TRACE
+	bnz  tracesys_exit
+
+	b ret_from_system_call
+ARC_EXIT sys_clone_wrapper
+
+#ifdef CONFIG_ARC_DW2_UNWIND
+; Workaround for bug 94179 (STAR ):
+; Despite -fasynchronous-unwind-tables, linker is not making dwarf2 unwinder
+; section (.debug_frame) as loadable. So we force it here.
+; This also fixes STAR 9000487933 where the prev-workaround (objcopy --setflag)
+; would not work after a clean build due to kernel build system dependencies.
+.section .debug_frame, "wa",@progbits
+#endif
diff --git a/arch/arc/kernel/fpu.c b/arch/arc/kernel/fpu.c
new file mode 100644
index 000000000000..f352e512cbd1
--- /dev/null
+++ b/arch/arc/kernel/fpu.c
@@ -0,0 +1,55 @@
+/*
+ * fpu.c - save/restore of Floating Point Unit Registers on task switch
+ *
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/sched.h>
+#include <asm/switch_to.h>
+
+/*
+ * To save/restore FPU regs, simplest scheme would use LR/SR insns.
+ * However since SR serializes the pipeline, an alternate "hack" can be used
+ * which uses the FPU Exchange insn (DEXCL) to r/w FPU regs.
+ *
+ * Store to 64bit dpfp1 reg from a pair of core regs:
+ *   dexcl1 0, r1, r0  ; where r1:r0 is the 64 bit val
+ *
+ * Read from dpfp1 into pair of core regs (w/o clobbering dpfp1)
+ *   mov_s    r3, 0
+ *   daddh11  r1, r3, r3   ; get "hi" into r1 (dpfp1 unchanged)
+ *   dexcl1   r0, r1, r3   ; get "low" into r0 (dpfp1 low clobbered)
+ *   dexcl1    0, r1, r0   ; restore dpfp1 to orig value
+ *
+ * However we can tweak the read, so that read-out of outgoing task's FPU regs
+ * and write of incoming task's regs happen in one shot. So all the work is
+ * done before context switch
+ */
+
+void fpu_save_restore(struct task_struct *prev, struct task_struct *next)
+{
+	unsigned int *saveto = &prev->thread.fpu.aux_dpfp[0].l;
+	unsigned int *readfrom = &next->thread.fpu.aux_dpfp[0].l;
+
+	const unsigned int zero = 0;
+
+	__asm__ __volatile__(
+		"daddh11  %0, %2, %2\n"
+		"dexcl1   %1, %3, %4\n"
+		: "=&r" (*(saveto + 1)), /* early clobber must here */
+		  "=&r" (*(saveto))
+		: "r" (zero), "r" (*(readfrom + 1)), "r" (*(readfrom))
+	);
+
+	__asm__ __volatile__(
+		"daddh22  %0, %2, %2\n"
+		"dexcl2   %1, %3, %4\n"
+		: "=&r"(*(saveto + 3)),	/* early clobber must here */
+		  "=&r"(*(saveto + 2))
+		: "r" (zero), "r" (*(readfrom + 3)), "r" (*(readfrom + 2))
+	);
+}
diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S
new file mode 100644
index 000000000000..006dec3fc353
--- /dev/null
+++ b/arch/arc/kernel/head.S
@@ -0,0 +1,111 @@
+/*
+ * ARC CPU startup Code
+ *
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Vineetg: Dec 2007
+ *  -Check if we are running on Simulator or on real hardware
+ *      to skip certain things during boot on simulator
+ */
+
+#include <asm/asm-offsets.h>
+#include <asm/entry.h>
+#include <linux/linkage.h>
+#include <asm/arcregs.h>
+
+	.cpu A7
+
+	.section .init.text, "ax",@progbits
+	.type stext, @function
+	.globl stext
+stext:
+	;-------------------------------------------------------------------
+	; Don't clobber r0-r4 yet. It might have bootloader provided info
+	;-------------------------------------------------------------------
+
+#ifdef CONFIG_SMP
+	; Only Boot (Master) proceeds. Others wait in platform dependent way
+	;	IDENTITY Reg [ 3  2  1  0 ]
+	;	(cpu-id)             ^^^	=> Zero for UP ARC700
+	;					=> #Core-ID if SMP (Master 0)
+	GET_CPU_ID  r5
+	cmp	r5, 0
+	jnz	arc_platform_smp_wait_to_boot
+#endif
+	; Clear BSS before updating any globals
+	; XXX: use ZOL here
+	mov	r5, __bss_start
+	mov	r6, __bss_stop
+1:
+	st.ab   0, [r5,4]
+	brlt    r5, r6, 1b
+
+#ifdef CONFIG_CMDLINE_UBOOT
+	; support for bootloader provided cmdline
+	;    If cmdline passed by u-boot, then
+	;    r0 = 1  (because ATAGS parsing, now retired, used to use 0)
+	;    r1 = magic number (board identity)
+	;    r2 = addr of cmdline string (somewhere in memory/flash)
+
+	brne	r0, 1, .Lother_bootup_chores	; u-boot didn't pass cmdline
+	breq	r2, 0, .Lother_bootup_chores	; or cmdline is NULL
+
+	mov	r5, @command_line
+1:
+	ldb.ab  r6, [r2, 1]
+	breq    r6, 0, .Lother_bootup_chores
+	b.d     1b
+	stb.ab  r6, [r5, 1]
+#endif
+
+.Lother_bootup_chores:
+
+	; Identify if running on ISS vs Silicon
+	; 	IDENTITY Reg [ 3  2  1  0 ]
+	;	(chip-id)      ^^^^^		==> 0xffff for ISS
+	lr	r0, [identity]
+	lsr	r3, r0, 16
+	cmp	r3, 0xffff
+	mov.z	r4, 0
+	mov.nz	r4, 1
+	st	r4, [@running_on_hw]
+
+	; setup "current" tsk and optionally cache it in dedicated r25
+	mov	r9, @init_task
+	SET_CURR_TASK_ON_CPU  r9, r0	; r9 = tsk, r0 = scratch
+
+	; setup stack (fp, sp)
+	mov	fp, 0
+
+	; tsk->thread_info is really a PAGE, whose bottom hoists stack
+	GET_TSK_STACK_BASE r9, sp	; r9 = tsk, sp = stack base(output)
+
+	j	start_kernel	; "C" entry point
+
+#ifdef CONFIG_SMP
+;----------------------------------------------------------------
+;     First lines of code run by secondary before jumping to 'C'
+;----------------------------------------------------------------
+	.section .init.text, "ax",@progbits
+	.type first_lines_of_secondary, @function
+	.globl first_lines_of_secondary
+
+first_lines_of_secondary:
+
+	; setup per-cpu idle task as "current" on this CPU
+	ld	r0, [@secondary_idle_tsk]
+	SET_CURR_TASK_ON_CPU  r0, r1
+
+	; setup stack (fp, sp)
+	mov	fp, 0
+
+	; set it's stack base to tsk->thread_info bottom
+	GET_TSK_STACK_BASE r0, sp
+
+	j	start_kernel_secondary
+
+#endif
diff --git a/arch/arc/kernel/irq.c b/arch/arc/kernel/irq.c
new file mode 100644
index 000000000000..551c10dff481
--- /dev/null
+++ b/arch/arc/kernel/irq.c
@@ -0,0 +1,273 @@
+/*
+ * Copyright (C) 2011-12 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/irqdomain.h>
+#include <asm/sections.h>
+#include <asm/irq.h>
+#include <asm/mach_desc.h>
+
+/*
+ * Early Hardware specific Interrupt setup
+ * -Called very early (start_kernel -> setup_arch -> setup_processor)
+ * -Platform Independent (must for any ARC700)
+ * -Needed for each CPU (hence not foldable into init_IRQ)
+ *
+ * what it does ?
+ * -setup Vector Table Base Reg - in case Linux not linked at 0x8000_0000
+ * -Disable all IRQs (on CPU side)
+ * -Optionally, setup the High priority Interrupts as Level 2 IRQs
+ */
+void __init arc_init_IRQ(void)
+{
+	int level_mask = 0;
+
+	write_aux_reg(AUX_INTR_VEC_BASE, _int_vec_base_lds);
+
+	/* Disable all IRQs: enable them as devices request */
+	write_aux_reg(AUX_IENABLE, 0);
+
+       /* setup any high priority Interrupts (Level2 in ARCompact jargon) */
+#ifdef CONFIG_ARC_IRQ3_LV2
+	level_mask |= (1 << 3);
+#endif
+#ifdef CONFIG_ARC_IRQ5_LV2
+	level_mask |= (1 << 5);
+#endif
+#ifdef CONFIG_ARC_IRQ6_LV2
+	level_mask |= (1 << 6);
+#endif
+
+	if (level_mask) {
+		pr_info("Level-2 interrupts bitset %x\n", level_mask);
+		write_aux_reg(AUX_IRQ_LEV, level_mask);
+	}
+}
+
+/*
+ * ARC700 core includes a simple on-chip intc supporting
+ * -per IRQ enable/disable
+ * -2 levels of interrupts (high/low)
+ * -all interrupts being level triggered
+ *
+ * To reduce platform code, we assume all IRQs directly hooked-up into intc.
+ * Platforms with external intc, hence cascaded IRQs, are free to over-ride
+ * below, per IRQ.
+ */
+
+static void arc_mask_irq(struct irq_data *data)
+{
+	arch_mask_irq(data->irq);
+}
+
+static void arc_unmask_irq(struct irq_data *data)
+{
+	arch_unmask_irq(data->irq);
+}
+
+static struct irq_chip onchip_intc = {
+	.name           = "ARC In-core Intc",
+	.irq_mask	= arc_mask_irq,
+	.irq_unmask	= arc_unmask_irq,
+};
+
+static int arc_intc_domain_map(struct irq_domain *d, unsigned int irq,
+				irq_hw_number_t hw)
+{
+	if (irq == TIMER0_IRQ)
+		irq_set_chip_and_handler(irq, &onchip_intc, handle_percpu_irq);
+	else
+		irq_set_chip_and_handler(irq, &onchip_intc, handle_level_irq);
+
+	return 0;
+}
+
+static const struct irq_domain_ops arc_intc_domain_ops = {
+	.xlate = irq_domain_xlate_onecell,
+	.map = arc_intc_domain_map,
+};
+
+static struct irq_domain *root_domain;
+
+void __init init_onchip_IRQ(void)
+{
+	struct device_node *intc = NULL;
+
+	intc = of_find_compatible_node(NULL, NULL, "snps,arc700-intc");
+	if(!intc)
+		panic("DeviceTree Missing incore intc\n");
+
+	root_domain = irq_domain_add_legacy(intc, NR_IRQS, 0, 0,
+					    &arc_intc_domain_ops, NULL);
+
+	if (!root_domain)
+		panic("root irq domain not avail\n");
+
+	/* with this we don't need to export root_domain */
+	irq_set_default_host(root_domain);
+}
+
+/*
+ * Late Interrupt system init called from start_kernel for Boot CPU only
+ *
+ * Since slab must already be initialized, platforms can start doing any
+ * needed request_irq( )s
+ */
+void __init init_IRQ(void)
+{
+	init_onchip_IRQ();
+
+	/* Any external intc can be setup here */
+	if (machine_desc->init_irq)
+		machine_desc->init_irq();
+
+#ifdef CONFIG_SMP
+	/* Master CPU can initialize it's side of IPI */
+	if (machine_desc->init_smp)
+		machine_desc->init_smp(smp_processor_id());
+#endif
+}
+
+/*
+ * "C" Entry point for any ARC ISR, called from low level vector handler
+ * @irq is the vector number read from ICAUSE reg of on-chip intc
+ */
+void arch_do_IRQ(unsigned int irq, struct pt_regs *regs)
+{
+	struct pt_regs *old_regs = set_irq_regs(regs);
+
+	irq_enter();
+	generic_handle_irq(irq);
+	irq_exit();
+	set_irq_regs(old_regs);
+}
+
+int __init get_hw_config_num_irq(void)
+{
+	uint32_t val = read_aux_reg(ARC_REG_VECBASE_BCR);
+
+	switch (val & 0x03) {
+	case 0:
+		return 16;
+	case 1:
+		return 32;
+	case 2:
+		return 8;
+	default:
+		return 0;
+	}
+
+	return 0;
+}
+
+/*
+ * arch_local_irq_enable - Enable interrupts.
+ *
+ * 1. Explicitly called to re-enable interrupts
+ * 2. Implicitly called from spin_unlock_irq, write_unlock_irq etc
+ *    which maybe in hard ISR itself
+ *
+ * Semantics of this function change depending on where it is called from:
+ *
+ * -If called from hard-ISR, it must not invert interrupt priorities
+ *  e.g. suppose TIMER is high priority (Level 2) IRQ
+ *    Time hard-ISR, timer_interrupt( ) calls spin_unlock_irq several times.
+ *    Here local_irq_enable( ) shd not re-enable lower priority interrupts
+ * -If called from soft-ISR, it must re-enable all interrupts
+ *    soft ISR are low prioity jobs which can be very slow, thus all IRQs
+ *    must be enabled while they run.
+ *    Now hardware context wise we may still be in L2 ISR (not done rtie)
+ *    still we must re-enable both L1 and L2 IRQs
+ *  Another twist is prev scenario with flow being
+ *     L1 ISR ==> interrupted by L2 ISR  ==> L2 soft ISR
+ *     here we must not re-enable Ll as prev Ll Interrupt's h/w context will get
+ *     over-written (this is deficiency in ARC700 Interrupt mechanism)
+ */
+
+#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS	/* Complex version for 2 IRQ levels */
+
+void arch_local_irq_enable(void)
+{
+
+	unsigned long flags;
+	flags = arch_local_save_flags();
+
+	/* Allow both L1 and L2 at the onset */
+	flags |= (STATUS_E1_MASK | STATUS_E2_MASK);
+
+	/* Called from hard ISR (between irq_enter and irq_exit) */
+	if (in_irq()) {
+
+		/* If in L2 ISR, don't re-enable any further IRQs as this can
+		 * cause IRQ priorities to get upside down. e.g. it could allow
+		 * L1 be taken while in L2 hard ISR which is wrong not only in
+		 * theory, it can also cause the dreaded L1-L2-L1 scenario
+		 */
+		if (flags & STATUS_A2_MASK)
+			flags &= ~(STATUS_E1_MASK | STATUS_E2_MASK);
+
+		/* Even if in L1 ISR, allowe Higher prio L2 IRQs */
+		else if (flags & STATUS_A1_MASK)
+			flags &= ~(STATUS_E1_MASK);
+	}
+
+	/* called from soft IRQ, ideally we want to re-enable all levels */
+
+	else if (in_softirq()) {
+
+		/* However if this is case of L1 interrupted by L2,
+		 * re-enabling both may cause whaco L1-L2-L1 scenario
+		 * because ARC700 allows level 1 to interrupt an active L2 ISR
+		 * Thus we disable both
+		 * However some code, executing in soft ISR wants some IRQs
+		 * to be enabled so we re-enable L2 only
+		 *
+		 * How do we determine L1 intr by L2
+		 *  -A2 is set (means in L2 ISR)
+		 *  -E1 is set in this ISR's pt_regs->status32 which is
+		 *      saved copy of status32_l2 when l2 ISR happened
+		 */
+		struct pt_regs *pt = get_irq_regs();
+		if ((flags & STATUS_A2_MASK) && pt &&
+		    (pt->status32 & STATUS_A1_MASK)) {
+			/*flags &= ~(STATUS_E1_MASK | STATUS_E2_MASK); */
+			flags &= ~(STATUS_E1_MASK);
+		}
+	}
+
+	arch_local_irq_restore(flags);
+}
+
+#else /* ! CONFIG_ARC_COMPACT_IRQ_LEVELS */
+
+/*
+ * Simpler version for only 1 level of interrupt
+ * Here we only Worry about Level 1 Bits
+ */
+void arch_local_irq_enable(void)
+{
+	unsigned long flags;
+
+	/*
+	 * ARC IDE Drivers tries to re-enable interrupts from hard-isr
+	 * context which is simply wrong
+	 */
+	if (in_irq()) {
+		WARN_ONCE(1, "IRQ enabled from hard-isr");
+		return;
+	}
+
+	flags = arch_local_save_flags();
+	flags |= (STATUS_E1_MASK | STATUS_E2_MASK);
+	arch_local_irq_restore(flags);
+}
+#endif
+EXPORT_SYMBOL(arch_local_irq_enable);
diff --git a/arch/arc/kernel/kgdb.c b/arch/arc/kernel/kgdb.c
new file mode 100644
index 000000000000..2888ba5be47e
--- /dev/null
+++ b/arch/arc/kernel/kgdb.c
@@ -0,0 +1,205 @@
+/*
+ * kgdb support for ARC
+ *
+ * Copyright (C) 2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kgdb.h>
+#include <asm/disasm.h>
+#include <asm/cacheflush.h>
+
+static void to_gdb_regs(unsigned long *gdb_regs, struct pt_regs *kernel_regs,
+			struct callee_regs *cregs)
+{
+	int regno;
+
+	for (regno = 0; regno <= 26; regno++)
+		gdb_regs[_R0 + regno] = get_reg(regno, kernel_regs, cregs);
+
+	for (regno = 27; regno < GDB_MAX_REGS; regno++)
+		gdb_regs[regno] = 0;
+
+	gdb_regs[_FP]		= kernel_regs->fp;
+	gdb_regs[__SP]		= kernel_regs->sp;
+	gdb_regs[_BLINK]	= kernel_regs->blink;
+	gdb_regs[_RET]		= kernel_regs->ret;
+	gdb_regs[_STATUS32]	= kernel_regs->status32;
+	gdb_regs[_LP_COUNT]	= kernel_regs->lp_count;
+	gdb_regs[_LP_END]	= kernel_regs->lp_end;
+	gdb_regs[_LP_START]	= kernel_regs->lp_start;
+	gdb_regs[_BTA]		= kernel_regs->bta;
+	gdb_regs[_STOP_PC]	= kernel_regs->ret;
+}
+
+static void from_gdb_regs(unsigned long *gdb_regs, struct pt_regs *kernel_regs,
+			struct callee_regs *cregs)
+{
+	int regno;
+
+	for (regno = 0; regno <= 26; regno++)
+		set_reg(regno, gdb_regs[regno + _R0], kernel_regs, cregs);
+
+	kernel_regs->fp		= gdb_regs[_FP];
+	kernel_regs->sp		= gdb_regs[__SP];
+	kernel_regs->blink	= gdb_regs[_BLINK];
+	kernel_regs->ret	= gdb_regs[_RET];
+	kernel_regs->status32	= gdb_regs[_STATUS32];
+	kernel_regs->lp_count	= gdb_regs[_LP_COUNT];
+	kernel_regs->lp_end	= gdb_regs[_LP_END];
+	kernel_regs->lp_start	= gdb_regs[_LP_START];
+	kernel_regs->bta	= gdb_regs[_BTA];
+}
+
+
+void pt_regs_to_gdb_regs(unsigned long *gdb_regs, struct pt_regs *kernel_regs)
+{
+	to_gdb_regs(gdb_regs, kernel_regs, (struct callee_regs *)
+		current->thread.callee_reg);
+}
+
+void gdb_regs_to_pt_regs(unsigned long *gdb_regs, struct pt_regs *kernel_regs)
+{
+	from_gdb_regs(gdb_regs, kernel_regs, (struct callee_regs *)
+		current->thread.callee_reg);
+}
+
+void sleeping_thread_to_gdb_regs(unsigned long *gdb_regs,
+				 struct task_struct *task)
+{
+	if (task)
+		to_gdb_regs(gdb_regs, task_pt_regs(task),
+			(struct callee_regs *) task->thread.callee_reg);
+}
+
+struct single_step_data_t {
+	uint16_t opcode[2];
+	unsigned long address[2];
+	int is_branch;
+	int armed;
+} single_step_data;
+
+static void undo_single_step(struct pt_regs *regs)
+{
+	if (single_step_data.armed) {
+		int i;
+
+		for (i = 0; i < (single_step_data.is_branch ? 2 : 1); i++) {
+			memcpy((void *) single_step_data.address[i],
+				&single_step_data.opcode[i],
+				BREAK_INSTR_SIZE);
+
+			flush_icache_range(single_step_data.address[i],
+				single_step_data.address[i] +
+				BREAK_INSTR_SIZE);
+		}
+		single_step_data.armed = 0;
+	}
+}
+
+static void place_trap(unsigned long address, void *save)
+{
+	memcpy(save, (void *) address, BREAK_INSTR_SIZE);
+	memcpy((void *) address, &arch_kgdb_ops.gdb_bpt_instr,
+		BREAK_INSTR_SIZE);
+	flush_icache_range(address, address + BREAK_INSTR_SIZE);
+}
+
+static void do_single_step(struct pt_regs *regs)
+{
+	single_step_data.is_branch = disasm_next_pc((unsigned long)
+		regs->ret, regs, (struct callee_regs *)
+		current->thread.callee_reg,
+		&single_step_data.address[0],
+		&single_step_data.address[1]);
+
+	place_trap(single_step_data.address[0], &single_step_data.opcode[0]);
+
+	if (single_step_data.is_branch) {
+		place_trap(single_step_data.address[1],
+			&single_step_data.opcode[1]);
+	}
+
+	single_step_data.armed++;
+}
+
+int kgdb_arch_handle_exception(int e_vector, int signo, int err_code,
+			       char *remcomInBuffer, char *remcomOutBuffer,
+			       struct pt_regs *regs)
+{
+	unsigned long addr;
+	char *ptr;
+
+	undo_single_step(regs);
+
+	switch (remcomInBuffer[0]) {
+	case 's':
+	case 'c':
+		ptr = &remcomInBuffer[1];
+		if (kgdb_hex2long(&ptr, &addr))
+			regs->ret = addr;
+
+	case 'D':
+	case 'k':
+		atomic_set(&kgdb_cpu_doing_single_step, -1);
+
+		if (remcomInBuffer[0] == 's') {
+			do_single_step(regs);
+			atomic_set(&kgdb_cpu_doing_single_step,
+				   smp_processor_id());
+		}
+
+		return 0;
+	}
+	return -1;
+}
+
+unsigned long kgdb_arch_pc(int exception, struct pt_regs *regs)
+{
+	return instruction_pointer(regs);
+}
+
+int kgdb_arch_init(void)
+{
+	single_step_data.armed = 0;
+	return 0;
+}
+
+void kgdb_trap(struct pt_regs *regs, int param)
+{
+	/* trap_s 3 is used for breakpoints that overwrite existing
+	 * instructions, while trap_s 4 is used for compiled breakpoints.
+	 *
+	 * with trap_s 3 breakpoints the original instruction needs to be
+	 * restored and continuation needs to start at the location of the
+	 * breakpoint.
+	 *
+	 * with trap_s 4 (compiled) breakpoints, continuation needs to
+	 * start after the breakpoint.
+	 */
+	if (param == 3)
+		instruction_pointer(regs) -= BREAK_INSTR_SIZE;
+
+	kgdb_handle_exception(1, SIGTRAP, 0, regs);
+}
+
+void kgdb_arch_exit(void)
+{
+}
+
+void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long ip)
+{
+	instruction_pointer(regs) = ip;
+}
+
+struct kgdb_arch arch_kgdb_ops = {
+	/* breakpoint instruction: TRAP_S 0x3 */
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	.gdb_bpt_instr		= {0x78, 0x7e},
+#else
+	.gdb_bpt_instr		= {0x7e, 0x78},
+#endif
+};
diff --git a/arch/arc/kernel/kprobes.c b/arch/arc/kernel/kprobes.c
new file mode 100644
index 000000000000..3bfeacb674de
--- /dev/null
+++ b/arch/arc/kernel/kprobes.c
@@ -0,0 +1,525 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/types.h>
+#include <linux/kprobes.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/kprobes.h>
+#include <linux/kdebug.h>
+#include <linux/sched.h>
+#include <linux/uaccess.h>
+#include <asm/cacheflush.h>
+#include <asm/current.h>
+#include <asm/disasm.h>
+
+#define MIN_STACK_SIZE(addr)	min((unsigned long)MAX_STACK_SIZE, \
+		(unsigned long)current_thread_info() + THREAD_SIZE - (addr))
+
+DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
+DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
+
+int __kprobes arch_prepare_kprobe(struct kprobe *p)
+{
+	/* Attempt to probe at unaligned address */
+	if ((unsigned long)p->addr & 0x01)
+		return -EINVAL;
+
+	/* Address should not be in exception handling code */
+
+	p->ainsn.is_short = is_short_instr((unsigned long)p->addr);
+	p->opcode = *p->addr;
+
+	return 0;
+}
+
+void __kprobes arch_arm_kprobe(struct kprobe *p)
+{
+	*p->addr = UNIMP_S_INSTRUCTION;
+
+	flush_icache_range((unsigned long)p->addr,
+			   (unsigned long)p->addr + sizeof(kprobe_opcode_t));
+}
+
+void __kprobes arch_disarm_kprobe(struct kprobe *p)
+{
+	*p->addr = p->opcode;
+
+	flush_icache_range((unsigned long)p->addr,
+			   (unsigned long)p->addr + sizeof(kprobe_opcode_t));
+}
+
+void __kprobes arch_remove_kprobe(struct kprobe *p)
+{
+	arch_disarm_kprobe(p);
+
+	/* Can we remove the kprobe in the middle of kprobe handling? */
+	if (p->ainsn.t1_addr) {
+		*(p->ainsn.t1_addr) = p->ainsn.t1_opcode;
+
+		flush_icache_range((unsigned long)p->ainsn.t1_addr,
+				   (unsigned long)p->ainsn.t1_addr +
+				   sizeof(kprobe_opcode_t));
+
+		p->ainsn.t1_addr = NULL;
+	}
+
+	if (p->ainsn.t2_addr) {
+		*(p->ainsn.t2_addr) = p->ainsn.t2_opcode;
+
+		flush_icache_range((unsigned long)p->ainsn.t2_addr,
+				   (unsigned long)p->ainsn.t2_addr +
+				   sizeof(kprobe_opcode_t));
+
+		p->ainsn.t2_addr = NULL;
+	}
+}
+
+static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb)
+{
+	kcb->prev_kprobe.kp = kprobe_running();
+	kcb->prev_kprobe.status = kcb->kprobe_status;
+}
+
+static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb)
+{
+	__get_cpu_var(current_kprobe) = kcb->prev_kprobe.kp;
+	kcb->kprobe_status = kcb->prev_kprobe.status;
+}
+
+static inline void __kprobes set_current_kprobe(struct kprobe *p)
+{
+	__get_cpu_var(current_kprobe) = p;
+}
+
+static void __kprobes resume_execution(struct kprobe *p, unsigned long addr,
+				       struct pt_regs *regs)
+{
+	/* Remove the trap instructions inserted for single step and
+	 * restore the original instructions
+	 */
+	if (p->ainsn.t1_addr) {
+		*(p->ainsn.t1_addr) = p->ainsn.t1_opcode;
+
+		flush_icache_range((unsigned long)p->ainsn.t1_addr,
+				   (unsigned long)p->ainsn.t1_addr +
+				   sizeof(kprobe_opcode_t));
+
+		p->ainsn.t1_addr = NULL;
+	}
+
+	if (p->ainsn.t2_addr) {
+		*(p->ainsn.t2_addr) = p->ainsn.t2_opcode;
+
+		flush_icache_range((unsigned long)p->ainsn.t2_addr,
+				   (unsigned long)p->ainsn.t2_addr +
+				   sizeof(kprobe_opcode_t));
+
+		p->ainsn.t2_addr = NULL;
+	}
+
+	return;
+}
+
+static void __kprobes setup_singlestep(struct kprobe *p, struct pt_regs *regs)
+{
+	unsigned long next_pc;
+	unsigned long tgt_if_br = 0;
+	int is_branch;
+	unsigned long bta;
+
+	/* Copy the opcode back to the kprobe location and execute the
+	 * instruction. Because of this we will not be able to get into the
+	 * same kprobe until this kprobe is done
+	 */
+	*(p->addr) = p->opcode;
+
+	flush_icache_range((unsigned long)p->addr,
+			   (unsigned long)p->addr + sizeof(kprobe_opcode_t));
+
+	/* Now we insert the trap at the next location after this instruction to
+	 * single step. If it is a branch we insert the trap at possible branch
+	 * targets
+	 */
+
+	bta = regs->bta;
+
+	if (regs->status32 & 0x40) {
+		/* We are in a delay slot with the branch taken */
+
+		next_pc = bta & ~0x01;
+
+		if (!p->ainsn.is_short) {
+			if (bta & 0x01)
+				regs->blink += 2;
+			else {
+				/* Branch not taken */
+				next_pc += 2;
+
+				/* next pc is taken from bta after executing the
+				 * delay slot instruction
+				 */
+				regs->bta += 2;
+			}
+		}
+
+		is_branch = 0;
+	} else
+		is_branch =
+		    disasm_next_pc((unsigned long)p->addr, regs,
+			(struct callee_regs *) current->thread.callee_reg,
+			&next_pc, &tgt_if_br);
+
+	p->ainsn.t1_addr = (kprobe_opcode_t *) next_pc;
+	p->ainsn.t1_opcode = *(p->ainsn.t1_addr);
+	*(p->ainsn.t1_addr) = TRAP_S_2_INSTRUCTION;
+
+	flush_icache_range((unsigned long)p->ainsn.t1_addr,
+			   (unsigned long)p->ainsn.t1_addr +
+			   sizeof(kprobe_opcode_t));
+
+	if (is_branch) {
+		p->ainsn.t2_addr = (kprobe_opcode_t *) tgt_if_br;
+		p->ainsn.t2_opcode = *(p->ainsn.t2_addr);
+		*(p->ainsn.t2_addr) = TRAP_S_2_INSTRUCTION;
+
+		flush_icache_range((unsigned long)p->ainsn.t2_addr,
+				   (unsigned long)p->ainsn.t2_addr +
+				   sizeof(kprobe_opcode_t));
+	}
+}
+
+int __kprobes arc_kprobe_handler(unsigned long addr, struct pt_regs *regs)
+{
+	struct kprobe *p;
+	struct kprobe_ctlblk *kcb;
+
+	preempt_disable();
+
+	kcb = get_kprobe_ctlblk();
+	p = get_kprobe((unsigned long *)addr);
+
+	if (p) {
+		/*
+		 * We have reentered the kprobe_handler, since another kprobe
+		 * was hit while within the handler, we save the original
+		 * kprobes and single step on the instruction of the new probe
+		 * without calling any user handlers to avoid recursive
+		 * kprobes.
+		 */
+		if (kprobe_running()) {
+			save_previous_kprobe(kcb);
+			set_current_kprobe(p);
+			kprobes_inc_nmissed_count(p);
+			setup_singlestep(p, regs);
+			kcb->kprobe_status = KPROBE_REENTER;
+			return 1;
+		}
+
+		set_current_kprobe(p);
+		kcb->kprobe_status = KPROBE_HIT_ACTIVE;
+
+		/* If we have no pre-handler or it returned 0, we continue with
+		 * normal processing. If we have a pre-handler and it returned
+		 * non-zero - which is expected from setjmp_pre_handler for
+		 * jprobe, we return without single stepping and leave that to
+		 * the break-handler which is invoked by a kprobe from
+		 * jprobe_return
+		 */
+		if (!p->pre_handler || !p->pre_handler(p, regs)) {
+			setup_singlestep(p, regs);
+			kcb->kprobe_status = KPROBE_HIT_SS;
+		}
+
+		return 1;
+	} else if (kprobe_running()) {
+		p = __get_cpu_var(current_kprobe);
+		if (p->break_handler && p->break_handler(p, regs)) {
+			setup_singlestep(p, regs);
+			kcb->kprobe_status = KPROBE_HIT_SS;
+			return 1;
+		}
+	}
+
+	/* no_kprobe: */
+	preempt_enable_no_resched();
+	return 0;
+}
+
+static int __kprobes arc_post_kprobe_handler(unsigned long addr,
+					 struct pt_regs *regs)
+{
+	struct kprobe *cur = kprobe_running();
+	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+
+	if (!cur)
+		return 0;
+
+	resume_execution(cur, addr, regs);
+
+	/* Rearm the kprobe */
+	arch_arm_kprobe(cur);
+
+	/*
+	 * When we return from trap instruction we go to the next instruction
+	 * We restored the actual instruction in resume_exectuiont and we to
+	 * return to the same address and execute it
+	 */
+	regs->ret = addr;
+
+	if ((kcb->kprobe_status != KPROBE_REENTER) && cur->post_handler) {
+		kcb->kprobe_status = KPROBE_HIT_SSDONE;
+		cur->post_handler(cur, regs, 0);
+	}
+
+	if (kcb->kprobe_status == KPROBE_REENTER) {
+		restore_previous_kprobe(kcb);
+		goto out;
+	}
+
+	reset_current_kprobe();
+
+out:
+	preempt_enable_no_resched();
+	return 1;
+}
+
+/*
+ * Fault can be for the instruction being single stepped or for the
+ * pre/post handlers in the module.
+ * This is applicable for applications like user probes, where we have the
+ * probe in user space and the handlers in the kernel
+ */
+
+int __kprobes kprobe_fault_handler(struct pt_regs *regs, unsigned long trapnr)
+{
+	struct kprobe *cur = kprobe_running();
+	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+
+	switch (kcb->kprobe_status) {
+	case KPROBE_HIT_SS:
+	case KPROBE_REENTER:
+		/*
+		 * We are here because the instruction being single stepped
+		 * caused the fault. We reset the current kprobe and allow the
+		 * exception handler as if it is regular exception. In our
+		 * case it doesn't matter because the system will be halted
+		 */
+		resume_execution(cur, (unsigned long)cur->addr, regs);
+
+		if (kcb->kprobe_status == KPROBE_REENTER)
+			restore_previous_kprobe(kcb);
+		else
+			reset_current_kprobe();
+
+		preempt_enable_no_resched();
+		break;
+
+	case KPROBE_HIT_ACTIVE:
+	case KPROBE_HIT_SSDONE:
+		/*
+		 * We are here because the instructions in the pre/post handler
+		 * caused the fault.
+		 */
+
+		/* We increment the nmissed count for accounting,
+		 * we can also use npre/npostfault count for accouting
+		 * these specific fault cases.
+		 */
+		kprobes_inc_nmissed_count(cur);
+
+		/*
+		 * We come here because instructions in the pre/post
+		 * handler caused the page_fault, this could happen
+		 * if handler tries to access user space by
+		 * copy_from_user(), get_user() etc. Let the
+		 * user-specified handler try to fix it first.
+		 */
+		if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr))
+			return 1;
+
+		/*
+		 * In case the user-specified fault handler returned zero,
+		 * try to fix up.
+		 */
+		if (fixup_exception(regs))
+			return 1;
+
+		/*
+		 * fixup_exception() could not handle it,
+		 * Let do_page_fault() fix it.
+		 */
+		break;
+
+	default:
+		break;
+	}
+	return 0;
+}
+
+int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
+				       unsigned long val, void *data)
+{
+	struct die_args *args = data;
+	unsigned long addr = args->err;
+	int ret = NOTIFY_DONE;
+
+	switch (val) {
+	case DIE_IERR:
+		if (arc_kprobe_handler(addr, args->regs))
+			return NOTIFY_STOP;
+		break;
+
+	case DIE_TRAP:
+		if (arc_post_kprobe_handler(addr, args->regs))
+			return NOTIFY_STOP;
+		break;
+
+	default:
+		break;
+	}
+
+	return ret;
+}
+
+int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
+{
+	struct jprobe *jp = container_of(p, struct jprobe, kp);
+	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+	unsigned long sp_addr = regs->sp;
+
+	kcb->jprobe_saved_regs = *regs;
+	memcpy(kcb->jprobes_stack, (void *)sp_addr, MIN_STACK_SIZE(sp_addr));
+	regs->ret = (unsigned long)(jp->entry);
+
+	return 1;
+}
+
+void __kprobes jprobe_return(void)
+{
+	__asm__ __volatile__("unimp_s");
+	return;
+}
+
+int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
+{
+	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+	unsigned long sp_addr;
+
+	*regs = kcb->jprobe_saved_regs;
+	sp_addr = regs->sp;
+	memcpy((void *)sp_addr, kcb->jprobes_stack, MIN_STACK_SIZE(sp_addr));
+	preempt_enable_no_resched();
+
+	return 1;
+}
+
+static void __used kretprobe_trampoline_holder(void)
+{
+	__asm__ __volatile__(".global kretprobe_trampoline\n"
+			     "kretprobe_trampoline:\n" "nop\n");
+}
+
+void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
+				      struct pt_regs *regs)
+{
+
+	ri->ret_addr = (kprobe_opcode_t *) regs->blink;
+
+	/* Replace the return addr with trampoline addr */
+	regs->blink = (unsigned long)&kretprobe_trampoline;
+}
+
+static int __kprobes trampoline_probe_handler(struct kprobe *p,
+					      struct pt_regs *regs)
+{
+	struct kretprobe_instance *ri = NULL;
+	struct hlist_head *head, empty_rp;
+	struct hlist_node *tmp;
+	unsigned long flags, orig_ret_address = 0;
+	unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline;
+
+	INIT_HLIST_HEAD(&empty_rp);
+	kretprobe_hash_lock(current, &head, &flags);
+
+	/*
+	 * It is possible to have multiple instances associated with a given
+	 * task either because an multiple functions in the call path
+	 * have a return probe installed on them, and/or more than one return
+	 * return probe was registered for a target function.
+	 *
+	 * We can handle this because:
+	 *     - instances are always inserted at the head of the list
+	 *     - when multiple return probes are registered for the same
+	 *       function, the first instance's ret_addr will point to the
+	 *       real return address, and all the rest will point to
+	 *       kretprobe_trampoline
+	 */
+	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
+		if (ri->task != current)
+			/* another task is sharing our hash bucket */
+			continue;
+
+		if (ri->rp && ri->rp->handler)
+			ri->rp->handler(ri, regs);
+
+		orig_ret_address = (unsigned long)ri->ret_addr;
+		recycle_rp_inst(ri, &empty_rp);
+
+		if (orig_ret_address != trampoline_address) {
+			/*
+			 * This is the real return address. Any other
+			 * instances associated with this task are for
+			 * other calls deeper on the call stack
+			 */
+			break;
+		}
+	}
+
+	kretprobe_assert(ri, orig_ret_address, trampoline_address);
+	regs->ret = orig_ret_address;
+
+	reset_current_kprobe();
+	kretprobe_hash_unlock(current, &flags);
+	preempt_enable_no_resched();
+
+	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
+		hlist_del(&ri->hlist);
+		kfree(ri);
+	}
+
+	/* By returning a non zero value, we are telling the kprobe handler
+	 * that we don't want the post_handler to run
+	 */
+	return 1;
+}
+
+static struct kprobe trampoline_p = {
+	.addr = (kprobe_opcode_t *) &kretprobe_trampoline,
+	.pre_handler = trampoline_probe_handler
+};
+
+int __init arch_init_kprobes(void)
+{
+	/* Registering the trampoline code for the kret probe */
+	return register_kprobe(&trampoline_p);
+}
+
+int __kprobes arch_trampoline_kprobe(struct kprobe *p)
+{
+	if (p->addr == (kprobe_opcode_t *) &kretprobe_trampoline)
+		return 1;
+
+	return 0;
+}
+
+void trap_is_kprobe(unsigned long cause, unsigned long address,
+		    struct pt_regs *regs)
+{
+	notify_die(DIE_TRAP, "kprobe_trap", regs, address, cause, SIGTRAP);
+}
diff --git a/arch/arc/kernel/module.c b/arch/arc/kernel/module.c
new file mode 100644
index 000000000000..cdd359352c0a
--- /dev/null
+++ b/arch/arc/kernel/module.c
@@ -0,0 +1,145 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/moduleloader.h>
+#include <linux/kernel.h>
+#include <linux/elf.h>
+#include <linux/vmalloc.h>
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include <linux/string.h>
+#include <asm/unwind.h>
+
+static inline void arc_write_me(unsigned short *addr, unsigned long value)
+{
+	*addr = (value & 0xffff0000) >> 16;
+	*(addr + 1) = (value & 0xffff);
+}
+
+/* ARC specific section quirks - before relocation loop in generic loader
+ *
+ * For dwarf unwinding out of modules, this needs to
+ * 1. Ensure the .debug_frame is allocatable (ARC Linker bug: despite
+ *    -fasynchronous-unwind-tables it doesn't).
+ * 2. Since we are iterating thru sec hdr tbl anyways, make a note of
+ *    the exact section index, for later use.
+ */
+int module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs,
+			      char *secstr, struct module *mod)
+{
+#ifdef CONFIG_ARC_DW2_UNWIND
+	int i;
+
+	mod->arch.unw_sec_idx = 0;
+	mod->arch.unw_info = NULL;
+
+	for (i = 1; i < hdr->e_shnum; i++) {
+		if (strcmp(secstr+sechdrs[i].sh_name, ".debug_frame") == 0) {
+			sechdrs[i].sh_flags |= SHF_ALLOC;
+			mod->arch.unw_sec_idx = i;
+			break;
+		}
+	}
+#endif
+    return 0;
+}
+
+void module_arch_cleanup(struct module *mod)
+{
+#ifdef CONFIG_ARC_DW2_UNWIND
+	if (mod->arch.unw_info)
+		unwind_remove_table(mod->arch.unw_info, 0);
+#endif
+}
+
+int apply_relocate_add(Elf32_Shdr *sechdrs,
+		       const char *strtab,
+		       unsigned int symindex,	/* sec index for sym tbl */
+		       unsigned int relsec,	/* sec index for relo sec */
+		       struct module *module)
+{
+	int i, n;
+	Elf32_Rela *rel_entry = (void *)sechdrs[relsec].sh_addr;
+	Elf32_Sym *sym_entry, *sym_sec;
+	Elf32_Addr relocation;
+	Elf32_Addr location;
+	Elf32_Addr sec_to_patch;
+	int relo_type;
+
+	sec_to_patch = sechdrs[sechdrs[relsec].sh_info].sh_addr;
+	sym_sec = (Elf32_Sym *) sechdrs[symindex].sh_addr;
+	n = sechdrs[relsec].sh_size / sizeof(*rel_entry);
+
+	pr_debug("\n========== Module Sym reloc ===========================\n");
+	pr_debug("Section to fixup %x\n", sec_to_patch);
+	pr_debug("=========================================================\n");
+	pr_debug("rela->r_off | rela->addend | sym->st_value | ADDR | VALUE\n");
+	pr_debug("=========================================================\n");
+
+	/* Loop thru entries in relocation section */
+	for (i = 0; i < n; i++) {
+
+		/* This is where to make the change */
+		location = sec_to_patch + rel_entry[i].r_offset;
+
+		/* This is the symbol it is referring to.  Note that all
+		   undefined symbols have been resolved.  */
+		sym_entry = sym_sec + ELF32_R_SYM(rel_entry[i].r_info);
+
+		relocation = sym_entry->st_value + rel_entry[i].r_addend;
+
+		pr_debug("\t%x\t\t%x\t\t%x  %x %x [%s]\n",
+			rel_entry[i].r_offset, rel_entry[i].r_addend,
+			sym_entry->st_value, location, relocation,
+			strtab + sym_entry->st_name);
+
+		/* This assumes modules are built with -mlong-calls
+		 * so any branches/jumps are absolute 32 bit jmps
+		 * global data access again is abs 32 bit.
+		 * Both of these are handled by same relocation type
+		 */
+		relo_type = ELF32_R_TYPE(rel_entry[i].r_info);
+
+		if (likely(R_ARC_32_ME == relo_type))
+			arc_write_me((unsigned short *)location, relocation);
+		else if (R_ARC_32 == relo_type)
+			*((Elf32_Addr *) location) = relocation;
+		else
+			goto relo_err;
+
+	}
+	return 0;
+
+relo_err:
+	pr_err("%s: unknown relocation: %u\n",
+		module->name, ELF32_R_TYPE(rel_entry[i].r_info));
+	return -ENOEXEC;
+
+}
+
+/* Just before lift off: After sections have been relocated, we add the
+ * dwarf section to unwinder table pool
+ * This couldn't be done in module_frob_arch_sections() because
+ * relocations had not been applied by then
+ */
+int module_finalize(const Elf32_Ehdr *hdr, const Elf_Shdr *sechdrs,
+		    struct module *mod)
+{
+#ifdef CONFIG_ARC_DW2_UNWIND
+	void *unw;
+	int unwsec = mod->arch.unw_sec_idx;
+
+	if (unwsec) {
+		unw = unwind_add_table(mod, (void *)sechdrs[unwsec].sh_addr,
+				       sechdrs[unwsec].sh_size);
+		mod->arch.unw_info = unw;
+	}
+#endif
+    return 0;
+}
diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c
new file mode 100644
index 000000000000..0a7531d99294
--- /dev/null
+++ b/arch/arc/kernel/process.c
@@ -0,0 +1,235 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Amit Bhor, Kanika Nema: Codito Technologies 2004
+ */
+
+#include <linux/errno.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/fs.h>
+#include <linux/unistd.h>
+#include <linux/ptrace.h>
+#include <linux/slab.h>
+#include <linux/syscalls.h>
+#include <linux/elf.h>
+#include <linux/tick.h>
+
+SYSCALL_DEFINE1(arc_settls, void *, user_tls_data_ptr)
+{
+	task_thread_info(current)->thr_ptr = (unsigned int)user_tls_data_ptr;
+	return 0;
+}
+
+/*
+ * We return the user space TLS data ptr as sys-call return code
+ * Ideally it should be copy to user.
+ * However we can cheat by the fact that some sys-calls do return
+ * absurdly high values
+ * Since the tls dat aptr is not going to be in range of 0xFFFF_xxxx
+ * it won't be considered a sys-call error
+ * and it will be loads better than copy-to-user, which is a definite
+ * D-TLB Miss
+ */
+SYSCALL_DEFINE0(arc_gettls)
+{
+	return task_thread_info(current)->thr_ptr;
+}
+
+static inline void arch_idle(void)
+{
+	/* sleep, but enable all interrupts before committing */
+	__asm__("sleep 0x3");
+}
+
+void cpu_idle(void)
+{
+	/* Since we SLEEP in idle loop, TIF_POLLING_NRFLAG can't be set */
+
+	/* endless idle loop with no priority at all */
+	while (1) {
+		tick_nohz_idle_enter();
+		rcu_idle_enter();
+
+doze:
+		local_irq_disable();
+		if (!need_resched()) {
+			arch_idle();
+			goto doze;
+		} else {
+			local_irq_enable();
+		}
+
+		rcu_idle_exit();
+		tick_nohz_idle_exit();
+
+		schedule_preempt_disabled();
+	}
+}
+
+asmlinkage void ret_from_fork(void);
+
+/* Layout of Child kernel mode stack as setup at the end of this function is
+ *
+ * |     ...        |
+ * |     ...        |
+ * |    unused      |
+ * |                |
+ * ------------------  <==== top of Stack (thread.ksp)
+ * |   UNUSED 1 word|
+ * ------------------
+ * |     r25        |
+ * ~                ~
+ * |    --to--      |   (CALLEE Regs of user mode)
+ * |     r13        |
+ * ------------------
+ * |     fp         |
+ * |    blink       |   @ret_from_fork
+ * ------------------
+ * |                |
+ * ~                ~
+ * ~                ~
+ * |                |
+ * ------------------
+ * |     r12        |
+ * ~                ~
+ * |    --to--      |   (scratch Regs of user mode)
+ * |     r0         |
+ * ------------------
+ * |   UNUSED 1 word|
+ * ------------------  <===== END of PAGE
+ */
+int copy_thread(unsigned long clone_flags,
+		unsigned long usp, unsigned long arg,
+		struct task_struct *p)
+{
+	struct pt_regs *c_regs;        /* child's pt_regs */
+	unsigned long *childksp;       /* to unwind out of __switch_to() */
+	struct callee_regs *c_callee;  /* child's callee regs */
+	struct callee_regs *parent_callee;  /* paren't callee */
+	struct pt_regs *regs = current_pt_regs();
+
+	/* Mark the specific anchors to begin with (see pic above) */
+	c_regs = task_pt_regs(p);
+	childksp = (unsigned long *)c_regs - 2;  /* 2 words for FP/BLINK */
+	c_callee = ((struct callee_regs *)childksp) - 1;
+
+	/*
+	 * __switch_to() uses thread.ksp to start unwinding stack
+	 * For kernel threads we don't need to create callee regs, the
+	 * stack layout nevertheless needs to remain the same.
+	 * Also, since __switch_to anyways unwinds callee regs, we use
+	 * this to populate kernel thread entry-pt/args into callee regs,
+	 * so that ret_from_kernel_thread() becomes simpler.
+	 */
+	p->thread.ksp = (unsigned long)c_callee;	/* THREAD_KSP */
+
+	/* __switch_to expects FP(0), BLINK(return addr) at top */
+	childksp[0] = 0;			/* fp */
+	childksp[1] = (unsigned long)ret_from_fork; /* blink */
+
+	if (unlikely(p->flags & PF_KTHREAD)) {
+		memset(c_regs, 0, sizeof(struct pt_regs));
+
+		c_callee->r13 = arg; /* argument to kernel thread */
+		c_callee->r14 = usp;  /* function */
+
+		return 0;
+	}
+
+	/*--------- User Task Only --------------*/
+
+	/* __switch_to expects FP(0), BLINK(return addr) at top of stack */
+	childksp[0] = 0;				/* for POP fp */
+	childksp[1] = (unsigned long)ret_from_fork;	/* for POP blink */
+
+	/* Copy parents pt regs on child's kernel mode stack */
+	*c_regs = *regs;
+
+	if (usp)
+		c_regs->sp = usp;
+
+	c_regs->r0 = 0;		/* fork returns 0 in child */
+
+	parent_callee = ((struct callee_regs *)regs) - 1;
+	*c_callee = *parent_callee;
+
+	if (unlikely(clone_flags & CLONE_SETTLS)) {
+		/*
+		 * set task's userland tls data ptr from 4th arg
+		 * clone C-lib call is difft from clone sys-call
+		 */
+		task_thread_info(p)->thr_ptr = regs->r3;
+	} else {
+		/* Normal fork case: set parent's TLS ptr in child */
+		task_thread_info(p)->thr_ptr =
+		task_thread_info(current)->thr_ptr;
+	}
+
+	return 0;
+}
+
+/*
+ * Some archs flush debug and FPU info here
+ */
+void flush_thread(void)
+{
+}
+
+/*
+ * Free any architecture-specific thread data structures, etc.
+ */
+void exit_thread(void)
+{
+}
+
+int dump_fpu(struct pt_regs *regs, elf_fpregset_t *fpu)
+{
+	return 0;
+}
+
+/*
+ * API: expected by schedular Code: If thread is sleeping where is that.
+ * What is this good for? it will be always the scheduler or ret_from_fork.
+ * So we hard code that anyways.
+ */
+unsigned long thread_saved_pc(struct task_struct *t)
+{
+	struct pt_regs *regs = task_pt_regs(t);
+	unsigned long blink = 0;
+
+	/*
+	 * If the thread being queried for in not itself calling this, then it
+	 * implies it is not executing, which in turn implies it is sleeping,
+	 * which in turn implies it got switched OUT by the schedular.
+	 * In that case, it's kernel mode blink can reliably retrieved as per
+	 * the picture above (right above pt_regs).
+	 */
+	if (t != current && t->state != TASK_RUNNING)
+		blink = *((unsigned int *)regs - 1);
+
+	return blink;
+}
+
+int elf_check_arch(const struct elf32_hdr *x)
+{
+	unsigned int eflags;
+
+	if (x->e_machine != EM_ARCOMPACT)
+		return 0;
+
+	eflags = x->e_flags;
+	if ((eflags & EF_ARC_OSABI_MSK) < EF_ARC_OSABI_CURRENT) {
+		pr_err("ABI mismatch - you need newer toolchain\n");
+		force_sigsegv(SIGSEGV, current);
+		return 0;
+	}
+
+	return 1;
+}
+EXPORT_SYMBOL(elf_check_arch);
diff --git a/arch/arc/kernel/ptrace.c b/arch/arc/kernel/ptrace.c
new file mode 100644
index 000000000000..c6a81c58d0f3
--- /dev/null
+++ b/arch/arc/kernel/ptrace.c
@@ -0,0 +1,158 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/ptrace.h>
+#include <linux/tracehook.h>
+#include <linux/regset.h>
+#include <linux/unistd.h>
+#include <linux/elf.h>
+
+static struct callee_regs *task_callee_regs(struct task_struct *tsk)
+{
+	struct callee_regs *tmp = (struct callee_regs *)tsk->thread.callee_reg;
+	return tmp;
+}
+
+static int genregs_get(struct task_struct *target,
+		       const struct user_regset *regset,
+		       unsigned int pos, unsigned int count,
+		       void *kbuf, void __user *ubuf)
+{
+	const struct pt_regs *ptregs = task_pt_regs(target);
+	const struct callee_regs *cregs = task_callee_regs(target);
+	int ret = 0;
+	unsigned int stop_pc_val;
+
+#define REG_O_CHUNK(START, END, PTR)	\
+	if (!ret)	\
+		ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, PTR, \
+			offsetof(struct user_regs_struct, START), \
+			offsetof(struct user_regs_struct, END));
+
+#define REG_O_ONE(LOC, PTR)	\
+	if (!ret)		\
+		ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, PTR, \
+			offsetof(struct user_regs_struct, LOC), \
+			offsetof(struct user_regs_struct, LOC) + 4);
+
+	REG_O_CHUNK(scratch, callee, ptregs);
+	REG_O_CHUNK(callee, efa, cregs);
+	REG_O_CHUNK(efa, stop_pc, &target->thread.fault_address);
+
+	if (!ret) {
+		if (in_brkpt_trap(ptregs)) {
+			stop_pc_val = target->thread.fault_address;
+			pr_debug("\t\tstop_pc (brk-pt)\n");
+		} else {
+			stop_pc_val = ptregs->ret;
+			pr_debug("\t\tstop_pc (others)\n");
+		}
+
+		REG_O_ONE(stop_pc, &stop_pc_val);
+	}
+
+	return ret;
+}
+
+static int genregs_set(struct task_struct *target,
+		       const struct user_regset *regset,
+		       unsigned int pos, unsigned int count,
+		       const void *kbuf, const void __user *ubuf)
+{
+	const struct pt_regs *ptregs = task_pt_regs(target);
+	const struct callee_regs *cregs = task_callee_regs(target);
+	int ret = 0;
+
+#define REG_IN_CHUNK(FIRST, NEXT, PTR)	\
+	if (!ret)			\
+		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, \
+			(void *)(PTR), \
+			offsetof(struct user_regs_struct, FIRST), \
+			offsetof(struct user_regs_struct, NEXT));
+
+#define REG_IN_ONE(LOC, PTR)		\
+	if (!ret)			\
+		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, \
+			(void *)(PTR), \
+			offsetof(struct user_regs_struct, LOC), \
+			offsetof(struct user_regs_struct, LOC) + 4);
+
+#define REG_IGNORE_ONE(LOC)		\
+	if (!ret)			\
+		ret = user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf, \
+			offsetof(struct user_regs_struct, LOC), \
+			offsetof(struct user_regs_struct, LOC) + 4);
+
+	/* TBD: disallow updates to STATUS32, orig_r8 etc*/
+	REG_IN_CHUNK(scratch, callee, ptregs);	/* pt_regs[bta..orig_r8] */
+	REG_IN_CHUNK(callee, efa, cregs);	/* callee_regs[r25..r13] */
+	REG_IGNORE_ONE(efa);			/* efa update invalid */
+	REG_IN_ONE(stop_pc, &ptregs->ret);	/* stop_pc: PC update */
+
+	return ret;
+}
+
+enum arc_getset {
+	REGSET_GENERAL,
+};
+
+static const struct user_regset arc_regsets[] = {
+	[REGSET_GENERAL] = {
+	       .core_note_type = NT_PRSTATUS,
+	       .n = ELF_NGREG,
+	       .size = sizeof(unsigned long),
+	       .align = sizeof(unsigned long),
+	       .get = genregs_get,
+	       .set = genregs_set,
+	}
+};
+
+static const struct user_regset_view user_arc_view = {
+	.name		= UTS_MACHINE,
+	.e_machine	= EM_ARCOMPACT,
+	.regsets	= arc_regsets,
+	.n		= ARRAY_SIZE(arc_regsets)
+};
+
+const struct user_regset_view *task_user_regset_view(struct task_struct *task)
+{
+	return &user_arc_view;
+}
+
+void ptrace_disable(struct task_struct *child)
+{
+}
+
+long arch_ptrace(struct task_struct *child, long request,
+		 unsigned long addr, unsigned long data)
+{
+	int ret = -EIO;
+
+	pr_debug("REQ=%ld: ADDR =0x%lx, DATA=0x%lx)\n", request, addr, data);
+
+	switch (request) {
+	default:
+		ret = ptrace_request(child, request, addr, data);
+		break;
+	}
+
+	return ret;
+}
+
+asmlinkage int syscall_trace_entry(struct pt_regs *regs)
+{
+	if (tracehook_report_syscall_entry(regs))
+		return ULONG_MAX;
+
+	return regs->r8;
+}
+
+asmlinkage void syscall_trace_exit(struct pt_regs *regs)
+{
+	tracehook_report_syscall_exit(regs, 0);
+}
diff --git a/arch/arc/kernel/reset.c b/arch/arc/kernel/reset.c
new file mode 100644
index 000000000000..e227a2b1c943
--- /dev/null
+++ b/arch/arc/kernel/reset.c
@@ -0,0 +1,33 @@
+/*
+ * Copyright (C) 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/printk.h>
+#include <linux/reboot.h>
+#include <linux/pm.h>
+
+void machine_halt(void)
+{
+	/* Halt the processor */
+	__asm__ __volatile__("flag  1\n");
+}
+
+void machine_restart(char *__unused)
+{
+	/* Soft reset : jump to reset vector */
+	pr_info("Put your restart handler here\n");
+	machine_halt();
+}
+
+void machine_power_off(void)
+{
+	/* FIXME ::  power off ??? */
+	machine_halt();
+}
+
+void (*pm_power_off) (void) = NULL;
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
new file mode 100644
index 000000000000..dc0f968dae0a
--- /dev/null
+++ b/arch/arc/kernel/setup.c
@@ -0,0 +1,473 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/seq_file.h>
+#include <linux/fs.h>
+#include <linux/delay.h>
+#include <linux/root_dev.h>
+#include <linux/console.h>
+#include <linux/module.h>
+#include <linux/cpu.h>
+#include <linux/of_fdt.h>
+#include <asm/sections.h>
+#include <asm/arcregs.h>
+#include <asm/tlb.h>
+#include <asm/cache.h>
+#include <asm/setup.h>
+#include <asm/page.h>
+#include <asm/irq.h>
+#include <asm/arcregs.h>
+#include <asm/prom.h>
+#include <asm/unwind.h>
+#include <asm/clk.h>
+#include <asm/mach_desc.h>
+
+#define FIX_PTR(x)  __asm__ __volatile__(";" : "+r"(x))
+
+int running_on_hw = 1;	/* vs. on ISS */
+
+char __initdata command_line[COMMAND_LINE_SIZE];
+struct machine_desc *machine_desc __initdata;
+
+struct task_struct *_current_task[NR_CPUS];	/* For stack switching */
+
+struct cpuinfo_arc cpuinfo_arc700[NR_CPUS];
+
+
+void __init read_arc_build_cfg_regs(void)
+{
+	struct bcr_perip uncached_space;
+	struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()];
+	FIX_PTR(cpu);
+
+	READ_BCR(AUX_IDENTITY, cpu->core);
+
+	cpu->timers = read_aux_reg(ARC_REG_TIMERS_BCR);
+
+	cpu->vec_base = read_aux_reg(AUX_INTR_VEC_BASE);
+	if (cpu->vec_base == 0)
+		cpu->vec_base = (unsigned int)_int_vec_base_lds;
+
+	READ_BCR(ARC_REG_D_UNCACH_BCR, uncached_space);
+	cpu->uncached_base = uncached_space.start << 24;
+
+	cpu->extn.mul = read_aux_reg(ARC_REG_MUL_BCR);
+	cpu->extn.swap = read_aux_reg(ARC_REG_SWAP_BCR);
+	cpu->extn.norm = read_aux_reg(ARC_REG_NORM_BCR);
+	cpu->extn.minmax = read_aux_reg(ARC_REG_MIXMAX_BCR);
+	cpu->extn.barrel = read_aux_reg(ARC_REG_BARREL_BCR);
+	READ_BCR(ARC_REG_MAC_BCR, cpu->extn_mac_mul);
+
+	cpu->extn.ext_arith = read_aux_reg(ARC_REG_EXTARITH_BCR);
+	cpu->extn.crc = read_aux_reg(ARC_REG_CRC_BCR);
+
+	/* Note that we read the CCM BCRs independent of kernel config
+	 * This is to catch the cases where user doesn't know that
+	 * CCMs are present in hardware build
+	 */
+	{
+		struct bcr_iccm iccm;
+		struct bcr_dccm dccm;
+		struct bcr_dccm_base dccm_base;
+		unsigned int bcr_32bit_val;
+
+		bcr_32bit_val = read_aux_reg(ARC_REG_ICCM_BCR);
+		if (bcr_32bit_val) {
+			iccm = *((struct bcr_iccm *)&bcr_32bit_val);
+			cpu->iccm.base_addr = iccm.base << 16;
+			cpu->iccm.sz = 0x2000 << (iccm.sz - 1);
+		}
+
+		bcr_32bit_val = read_aux_reg(ARC_REG_DCCM_BCR);
+		if (bcr_32bit_val) {
+			dccm = *((struct bcr_dccm *)&bcr_32bit_val);
+			cpu->dccm.sz = 0x800 << (dccm.sz);
+
+			READ_BCR(ARC_REG_DCCMBASE_BCR, dccm_base);
+			cpu->dccm.base_addr = dccm_base.addr << 8;
+		}
+	}
+
+	READ_BCR(ARC_REG_XY_MEM_BCR, cpu->extn_xymem);
+
+	read_decode_mmu_bcr();
+	read_decode_cache_bcr();
+
+	READ_BCR(ARC_REG_FP_BCR, cpu->fp);
+	READ_BCR(ARC_REG_DPFP_BCR, cpu->dpfp);
+}
+
+static const struct cpuinfo_data arc_cpu_tbl[] = {
+	{ {0x10, "ARCTangent A5"}, 0x1F},
+	{ {0x20, "ARC 600"      }, 0x2F},
+	{ {0x30, "ARC 700"      }, 0x33},
+	{ {0x34, "ARC 700 R4.10"}, 0x34},
+	{ {0x00, NULL		} }
+};
+
+char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len)
+{
+	int n = 0;
+	struct cpuinfo_arc *cpu = &cpuinfo_arc700[cpu_id];
+	struct bcr_identity *core = &cpu->core;
+	const struct cpuinfo_data *tbl;
+	int be = 0;
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	be = 1;
+#endif
+	FIX_PTR(cpu);
+
+	n += scnprintf(buf + n, len - n,
+		       "\nARC IDENTITY\t: Family [%#02x]"
+		       " Cpu-id [%#02x] Chip-id [%#4x]\n",
+		       core->family, core->cpu_id,
+		       core->chip_id);
+
+	for (tbl = &arc_cpu_tbl[0]; tbl->info.id != 0; tbl++) {
+		if ((core->family >= tbl->info.id) &&
+		    (core->family <= tbl->up_range)) {
+			n += scnprintf(buf + n, len - n,
+				       "processor\t: %s %s\n",
+				       tbl->info.str,
+				       be ? "[Big Endian]" : "");
+			break;
+		}
+	}
+
+	if (tbl->info.id == 0)
+		n += scnprintf(buf + n, len - n, "UNKNOWN ARC Processor\n");
+
+	n += scnprintf(buf + n, len - n, "CPU speed\t: %u.%02u Mhz\n",
+		       (unsigned int)(arc_get_core_freq() / 1000000),
+		       (unsigned int)(arc_get_core_freq() / 10000) % 100);
+
+	n += scnprintf(buf + n, len - n, "Timers\t\t: %s %s\n",
+		       (cpu->timers & 0x200) ? "TIMER1" : "",
+		       (cpu->timers & 0x100) ? "TIMER0" : "");
+
+	n += scnprintf(buf + n, len - n, "Vect Tbl Base\t: %#x\n",
+		       cpu->vec_base);
+
+	n += scnprintf(buf + n, len - n, "UNCACHED Base\t: %#x\n",
+		       cpu->uncached_base);
+
+	return buf;
+}
+
+static const struct id_to_str mul_type_nm[] = {
+	{ 0x0, "N/A"},
+	{ 0x1, "32x32 (spl Result Reg)" },
+	{ 0x2, "32x32 (ANY Result Reg)" }
+};
+
+static const struct id_to_str mac_mul_nm[] = {
+	{0x0, "N/A"},
+	{0x1, "N/A"},
+	{0x2, "Dual 16 x 16"},
+	{0x3, "N/A"},
+	{0x4, "32x16"},
+	{0x5, "N/A"},
+	{0x6, "Dual 16x16 and 32x16"}
+};
+
+char *arc_extn_mumbojumbo(int cpu_id, char *buf, int len)
+{
+	int n = 0;
+	struct cpuinfo_arc *cpu = &cpuinfo_arc700[cpu_id];
+
+	FIX_PTR(cpu);
+#define IS_AVAIL1(var, str)	((var) ? str : "")
+#define IS_AVAIL2(var, str)	((var == 0x2) ? str : "")
+#define IS_USED(var)		((var) ? "(in-use)" : "(not used)")
+
+	n += scnprintf(buf + n, len - n,
+		       "Extn [700-Base]\t: %s %s %s %s %s %s\n",
+		       IS_AVAIL2(cpu->extn.norm, "norm,"),
+		       IS_AVAIL2(cpu->extn.barrel, "barrel-shift,"),
+		       IS_AVAIL1(cpu->extn.swap, "swap,"),
+		       IS_AVAIL2(cpu->extn.minmax, "minmax,"),
+		       IS_AVAIL1(cpu->extn.crc, "crc,"),
+		       IS_AVAIL2(cpu->extn.ext_arith, "ext-arith"));
+
+	n += scnprintf(buf + n, len - n, "Extn [700-MPY]\t: %s",
+		       mul_type_nm[cpu->extn.mul].str);
+
+	n += scnprintf(buf + n, len - n, "   MAC MPY: %s\n",
+		       mac_mul_nm[cpu->extn_mac_mul.type].str);
+
+	if (cpu->core.family == 0x34) {
+		n += scnprintf(buf + n, len - n,
+		"Extn [700-4.10]\t: LLOCK/SCOND %s, SWAPE %s, RTSC %s\n",
+			       IS_USED(__CONFIG_ARC_HAS_LLSC_VAL),
+			       IS_USED(__CONFIG_ARC_HAS_SWAPE_VAL),
+			       IS_USED(__CONFIG_ARC_HAS_RTSC_VAL));
+	}
+
+	n += scnprintf(buf + n, len - n, "Extn [CCM]\t: %s",
+		       !(cpu->dccm.sz || cpu->iccm.sz) ? "N/A" : "");
+
+	if (cpu->dccm.sz)
+		n += scnprintf(buf + n, len - n, "DCCM: @ %x, %d KB ",
+			       cpu->dccm.base_addr, TO_KB(cpu->dccm.sz));
+
+	if (cpu->iccm.sz)
+		n += scnprintf(buf + n, len - n, "ICCM: @ %x, %d KB",
+			       cpu->iccm.base_addr, TO_KB(cpu->iccm.sz));
+
+	n += scnprintf(buf + n, len - n, "\nExtn [FPU]\t: %s",
+		       !(cpu->fp.ver || cpu->dpfp.ver) ? "N/A" : "");
+
+	if (cpu->fp.ver)
+		n += scnprintf(buf + n, len - n, "SP [v%d] %s",
+			       cpu->fp.ver, cpu->fp.fast ? "(fast)" : "");
+
+	if (cpu->dpfp.ver)
+		n += scnprintf(buf + n, len - n, "DP [v%d] %s",
+			       cpu->dpfp.ver, cpu->dpfp.fast ? "(fast)" : "");
+
+	n += scnprintf(buf + n, len - n, "\n");
+
+#ifdef _ASM_GENERIC_UNISTD_H
+	n += scnprintf(buf + n, len - n,
+		       "OS ABI [v2]\t: asm-generic/{unistd,stat,fcntl}\n");
+#endif
+
+	return buf;
+}
+
+void __init arc_chk_ccms(void)
+{
+#if defined(CONFIG_ARC_HAS_DCCM) || defined(CONFIG_ARC_HAS_ICCM)
+	struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()];
+
+#ifdef CONFIG_ARC_HAS_DCCM
+	/*
+	 * DCCM can be arbit placed in hardware.
+	 * Make sure it's placement/sz matches what Linux is built with
+	 */
+	if ((unsigned int)__arc_dccm_base != cpu->dccm.base_addr)
+		panic("Linux built with incorrect DCCM Base address\n");
+
+	if (CONFIG_ARC_DCCM_SZ != cpu->dccm.sz)
+		panic("Linux built with incorrect DCCM Size\n");
+#endif
+
+#ifdef CONFIG_ARC_HAS_ICCM
+	if (CONFIG_ARC_ICCM_SZ != cpu->iccm.sz)
+		panic("Linux built with incorrect ICCM Size\n");
+#endif
+#endif
+}
+
+/*
+ * Ensure that FP hardware and kernel config match
+ * -If hardware contains DPFP, kernel needs to save/restore FPU state
+ *  across context switches
+ * -If hardware lacks DPFP, but kernel configured to save FPU state then
+ *  kernel trying to access non-existant DPFP regs will crash
+ *
+ * We only check for Dbl precision Floating Point, because only DPFP
+ * hardware has dedicated regs which need to be saved/restored on ctx-sw
+ * (Single Precision uses core regs), thus kernel is kind of oblivious to it
+ */
+void __init arc_chk_fpu(void)
+{
+	struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()];
+
+	if (cpu->dpfp.ver) {
+#ifndef CONFIG_ARC_FPU_SAVE_RESTORE
+		pr_warn("DPFP support broken in this kernel...\n");
+#endif
+	} else {
+#ifdef CONFIG_ARC_FPU_SAVE_RESTORE
+		panic("H/w lacks DPFP support, apps won't work\n");
+#endif
+	}
+}
+
+/*
+ * Initialize and setup the processor core
+ * This is called by all the CPUs thus should not do special case stuff
+ *    such as only for boot CPU etc
+ */
+
+void __init setup_processor(void)
+{
+	char str[512];
+	int cpu_id = smp_processor_id();
+
+	read_arc_build_cfg_regs();
+	arc_init_IRQ();
+
+	printk(arc_cpu_mumbojumbo(cpu_id, str, sizeof(str)));
+
+	arc_mmu_init();
+	arc_cache_init();
+	arc_chk_ccms();
+
+	printk(arc_extn_mumbojumbo(cpu_id, str, sizeof(str)));
+
+#ifdef CONFIG_SMP
+	printk(arc_platform_smp_cpuinfo());
+#endif
+
+	arc_chk_fpu();
+}
+
+void __init setup_arch(char **cmdline_p)
+{
+#ifdef CONFIG_CMDLINE_UBOOT
+	/* Make sure that a whitespace is inserted before */
+	strlcat(command_line, " ", sizeof(command_line));
+#endif
+	/*
+	 * Append .config cmdline to base command line, which might already
+	 * contain u-boot "bootargs" (handled by head.S, if so configured)
+	 */
+	strlcat(command_line, CONFIG_CMDLINE, sizeof(command_line));
+
+	/* Save unparsed command line copy for /proc/cmdline */
+	strlcpy(boot_command_line, command_line, COMMAND_LINE_SIZE);
+	*cmdline_p = command_line;
+
+	machine_desc = setup_machine_fdt(__dtb_start);
+	if (!machine_desc)
+		panic("Embedded DT invalid\n");
+
+	/* To force early parsing of things like mem=xxx */
+	parse_early_param();
+
+	/* Platform/board specific: e.g. early console registration */
+	if (machine_desc->init_early)
+		machine_desc->init_early();
+
+	setup_processor();
+
+#ifdef CONFIG_SMP
+	smp_init_cpus();
+#endif
+
+	setup_arch_memory();
+
+	/* copy flat DT out of .init and then unflatten it */
+	copy_devtree();
+	unflatten_device_tree();
+
+	/* Can be issue if someone passes cmd line arg "ro"
+	 * But that is unlikely so keeping it as it is
+	 */
+	root_mountflags &= ~MS_RDONLY;
+
+	console_verbose();
+
+#if defined(CONFIG_VT) && defined(CONFIG_DUMMY_CONSOLE)
+	conswitchp = &dummy_con;
+#endif
+
+	arc_unwind_init();
+	arc_unwind_setup();
+}
+
+static int __init customize_machine(void)
+{
+	/* Add platform devices */
+	if (machine_desc->init_machine)
+		machine_desc->init_machine();
+
+	return 0;
+}
+arch_initcall(customize_machine);
+
+static int __init init_late_machine(void)
+{
+	if (machine_desc->init_late)
+		machine_desc->init_late();
+
+	return 0;
+}
+late_initcall(init_late_machine);
+/*
+ *  Get CPU information for use by the procfs.
+ */
+
+#define cpu_to_ptr(c)	((void *)(0xFFFF0000 | (unsigned int)(c)))
+#define ptr_to_cpu(p)	(~0xFFFF0000UL & (unsigned int)(p))
+
+static int show_cpuinfo(struct seq_file *m, void *v)
+{
+	char *str;
+	int cpu_id = ptr_to_cpu(v);
+
+	str = (char *)__get_free_page(GFP_TEMPORARY);
+	if (!str)
+		goto done;
+
+	seq_printf(m, arc_cpu_mumbojumbo(cpu_id, str, PAGE_SIZE));
+
+	seq_printf(m, "Bogo MIPS : \t%lu.%02lu\n",
+		   loops_per_jiffy / (500000 / HZ),
+		   (loops_per_jiffy / (5000 / HZ)) % 100);
+
+	seq_printf(m, arc_mmu_mumbojumbo(cpu_id, str, PAGE_SIZE));
+
+	seq_printf(m, arc_cache_mumbojumbo(cpu_id, str, PAGE_SIZE));
+
+	seq_printf(m, arc_extn_mumbojumbo(cpu_id, str, PAGE_SIZE));
+
+#ifdef CONFIG_SMP
+	seq_printf(m, arc_platform_smp_cpuinfo());
+#endif
+
+	free_page((unsigned long)str);
+done:
+	seq_printf(m, "\n\n");
+
+	return 0;
+}
+
+static void *c_start(struct seq_file *m, loff_t *pos)
+{
+	/*
+	 * Callback returns cpu-id to iterator for show routine, NULL to stop.
+	 * However since NULL is also a valid cpu-id (0), we use a round-about
+	 * way to pass it w/o having to kmalloc/free a 2 byte string.
+	 * Encode cpu-id as 0xFFcccc, which is decoded by show routine.
+	 */
+	return *pos < num_possible_cpus() ? cpu_to_ptr(*pos) : NULL;
+}
+
+static void *c_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	++*pos;
+	return c_start(m, pos);
+}
+
+static void c_stop(struct seq_file *m, void *v)
+{
+}
+
+const struct seq_operations cpuinfo_op = {
+	.start	= c_start,
+	.next	= c_next,
+	.stop	= c_stop,
+	.show	= show_cpuinfo
+};
+
+static DEFINE_PER_CPU(struct cpu, cpu_topology);
+
+static int __init topology_init(void)
+{
+	int cpu;
+
+	for_each_present_cpu(cpu)
+	    register_cpu(&per_cpu(cpu_topology, cpu), cpu);
+
+	return 0;
+}
+
+subsys_initcall(topology_init);
diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c
new file mode 100644
index 000000000000..ee6ef2f60a28
--- /dev/null
+++ b/arch/arc/kernel/signal.c
@@ -0,0 +1,360 @@
+/*
+ * Signal Handling for ARC
+ *
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * vineetg: Jan 2010 (Restarting of timer related syscalls)
+ *
+ * vineetg: Nov 2009 (Everything needed for TIF_RESTORE_SIGMASK)
+ *  -do_signal() supports TIF_RESTORE_SIGMASK
+ *  -do_signal() no loner needs oldset, required by OLD sys_sigsuspend
+ *  -sys_rt_sigsuspend() now comes from generic code, so discard arch implemen
+ *  -sys_sigsuspend() no longer needs to fudge ptregs, hence that arg removed
+ *  -sys_sigsuspend() no longer loops for do_signal(), sets TIF_xxx and leaves
+ *   the job to do_signal()
+ *
+ * vineetg: July 2009
+ *  -Modified Code to support the uClibc provided userland sigreturn stub
+ *   to avoid kernel synthesing it on user stack at runtime, costing TLB
+ *   probes and Cache line flushes.
+ *
+ * vineetg: July 2009
+ *  -In stash_usr_regs( ) and restore_usr_regs( ), save/restore of user regs
+ *   in done in block copy rather than one word at a time.
+ *   This saves around 2K of code and improves LMBench lat_sig <catch>
+ *
+ * rajeshwarr: Feb 2009
+ *  - Support for Realtime Signals
+ *
+ * vineetg: Aug 11th 2008: Bug #94183
+ *  -ViXS were still seeing crashes when using insmod to load drivers.
+ *   It turned out that the code to change Execute permssions for TLB entries
+ *   of user was not guarded for interrupts (mod_tlb_permission)
+ *   This was cauing TLB entries to be overwritten on unrelated indexes
+ *
+ * Vineetg: July 15th 2008: Bug #94183
+ *  -Exception happens in Delay slot of a JMP, and before user space resumes,
+ *   Signal is delivered (Ctrl + C) = >SIGINT.
+ *   setup_frame( ) sets up PC,SP,BLINK to enable user space signal handler
+ *   to run, but doesn't clear the Delay slot bit from status32. As a result,
+ *   on resuming user mode, signal handler branches off to BTA of orig JMP
+ *  -FIX: clear the DE bit from status32 in setup_frame( )
+ *
+ * Rahul Trivedi, Kanika Nema: Codito Technologies 2004
+ */
+
+#include <linux/signal.h>
+#include <linux/ptrace.h>
+#include <linux/personality.h>
+#include <linux/uaccess.h>
+#include <linux/syscalls.h>
+#include <linux/tracehook.h>
+#include <asm/ucontext.h>
+
+struct rt_sigframe {
+	struct siginfo info;
+	struct ucontext uc;
+#define MAGIC_SIGALTSTK		0x07302004
+	unsigned int sigret_magic;
+};
+
+static int
+stash_usr_regs(struct rt_sigframe __user *sf, struct pt_regs *regs,
+	       sigset_t *set)
+{
+	int err;
+	err = __copy_to_user(&(sf->uc.uc_mcontext.regs), regs,
+			     sizeof(sf->uc.uc_mcontext.regs.scratch));
+	err |= __copy_to_user(&sf->uc.uc_sigmask, set, sizeof(sigset_t));
+
+	return err;
+}
+
+static int restore_usr_regs(struct pt_regs *regs, struct rt_sigframe __user *sf)
+{
+	sigset_t set;
+	int err;
+
+	err = __copy_from_user(&set, &sf->uc.uc_sigmask, sizeof(set));
+	if (!err)
+		set_current_blocked(&set);
+
+	err |= __copy_from_user(regs, &(sf->uc.uc_mcontext.regs),
+				sizeof(sf->uc.uc_mcontext.regs.scratch));
+
+	return err;
+}
+
+static inline int is_do_ss_needed(unsigned int magic)
+{
+	if (MAGIC_SIGALTSTK == magic)
+		return 1;
+	else
+		return 0;
+}
+
+SYSCALL_DEFINE0(rt_sigreturn)
+{
+	struct rt_sigframe __user *sf;
+	unsigned int magic;
+	int err;
+	struct pt_regs *regs = current_pt_regs();
+
+	/* Always make any pending restarted system calls return -EINTR */
+	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+
+	/* Since we stacked the signal on a word boundary,
+	 * then 'sp' should be word aligned here.  If it's
+	 * not, then the user is trying to mess with us.
+	 */
+	if (regs->sp & 3)
+		goto badframe;
+
+	sf = (struct rt_sigframe __force __user *)(regs->sp);
+
+	if (!access_ok(VERIFY_READ, sf, sizeof(*sf)))
+		goto badframe;
+
+	err = restore_usr_regs(regs, sf);
+	err |= __get_user(magic, &sf->sigret_magic);
+	if (err)
+		goto badframe;
+
+	if (unlikely(is_do_ss_needed(magic)))
+		if (restore_altstack(&sf->uc.uc_stack))
+			goto badframe;
+
+	/* Don't restart from sigreturn */
+	syscall_wont_restart(regs);
+
+	return regs->r0;
+
+badframe:
+	force_sig(SIGSEGV, current);
+	return 0;
+}
+
+/*
+ * Determine which stack to use..
+ */
+static inline void __user *get_sigframe(struct k_sigaction *ka,
+					struct pt_regs *regs,
+					unsigned long framesize)
+{
+	unsigned long sp = regs->sp;
+	void __user *frame;
+
+	/* This is the X/Open sanctioned signal stack switching */
+	if ((ka->sa.sa_flags & SA_ONSTACK) && !sas_ss_flags(sp))
+		sp = current->sas_ss_sp + current->sas_ss_size;
+
+	/* No matter what happens, 'sp' must be word
+	 * aligned otherwise nasty things could happen
+	 */
+
+	/* ATPCS B01 mandates 8-byte alignment */
+	frame = (void __user *)((sp - framesize) & ~7);
+
+	/* Check that we can actually write to the signal frame */
+	if (!access_ok(VERIFY_WRITE, frame, framesize))
+		frame = NULL;
+
+	return frame;
+}
+
+/*
+ * translate the signal
+ */
+static inline int map_sig(int sig)
+{
+	struct thread_info *thread = current_thread_info();
+	if (thread->exec_domain && thread->exec_domain->signal_invmap
+	    && sig < 32)
+		sig = thread->exec_domain->signal_invmap[sig];
+	return sig;
+}
+
+static int
+setup_rt_frame(int signo, struct k_sigaction *ka, siginfo_t *info,
+	       sigset_t *set, struct pt_regs *regs)
+{
+	struct rt_sigframe __user *sf;
+	unsigned int magic = 0;
+	int err = 0;
+
+	sf = get_sigframe(ka, regs, sizeof(struct rt_sigframe));
+	if (!sf)
+		return 1;
+
+	/*
+	 * SA_SIGINFO requires 3 args to signal handler:
+	 *  #1: sig-no (common to any handler)
+	 *  #2: struct siginfo
+	 *  #3: struct ucontext (completely populated)
+	 */
+	if (unlikely(ka->sa.sa_flags & SA_SIGINFO)) {
+		err |= copy_siginfo_to_user(&sf->info, info);
+		err |= __put_user(0, &sf->uc.uc_flags);
+		err |= __put_user(NULL, &sf->uc.uc_link);
+		err |= __save_altstack(&sf->uc.uc_stack, regs->sp);
+
+		/* setup args 2 and 3 for user mode handler */
+		regs->r1 = (unsigned long)&sf->info;
+		regs->r2 = (unsigned long)&sf->uc;
+
+		/*
+		 * small optim to avoid unconditonally calling do_sigaltstack
+		 * in sigreturn path, now that we only have rt_sigreturn
+		 */
+		magic = MAGIC_SIGALTSTK;
+	}
+
+	/*
+	 * w/o SA_SIGINFO, struct ucontext is partially populated (only
+	 * uc_mcontext/uc_sigmask) for kernel's normal user state preservation
+	 * during signal handler execution. This works for SA_SIGINFO as well
+	 * although the semantics are now overloaded (the same reg state can be
+	 * inspected by userland: but are they allowed to fiddle with it ?
+	 */
+	err |= stash_usr_regs(sf, regs, set);
+	err |= __put_user(magic, &sf->sigret_magic);
+	if (err)
+		return err;
+
+	/* #1 arg to the user Signal handler */
+	regs->r0 = map_sig(signo);
+
+	/* setup PC of user space signal handler */
+	regs->ret = (unsigned long)ka->sa.sa_handler;
+
+	/*
+	 * handler returns using sigreturn stub provided already by userpsace
+	 */
+	BUG_ON(!(ka->sa.sa_flags & SA_RESTORER));
+	regs->blink = (unsigned long)ka->sa.sa_restorer;
+
+	/* User Stack for signal handler will be above the frame just carved */
+	regs->sp = (unsigned long)sf;
+
+	/*
+	 * Bug 94183, Clear the DE bit, so that when signal handler
+	 * starts to run, it doesn't use BTA
+	 */
+	regs->status32 &= ~STATUS_DE_MASK;
+	regs->status32 |= STATUS_L_MASK;
+
+	return err;
+}
+
+static void arc_restart_syscall(struct k_sigaction *ka, struct pt_regs *regs)
+{
+	switch (regs->r0) {
+	case -ERESTART_RESTARTBLOCK:
+	case -ERESTARTNOHAND:
+		/*
+		 * ERESTARTNOHAND means that the syscall should
+		 * only be restarted if there was no handler for
+		 * the signal, and since we only get here if there
+		 * is a handler, we don't restart
+		 */
+		regs->r0 = -EINTR;   /* ERESTART_xxx is internal */
+		break;
+
+	case -ERESTARTSYS:
+		/*
+		 * ERESTARTSYS means to restart the syscall if
+		 * there is no handler or the handler was
+		 * registered with SA_RESTART
+		 */
+		if (!(ka->sa.sa_flags & SA_RESTART)) {
+			regs->r0 = -EINTR;
+			break;
+		}
+		/* fallthrough */
+
+	case -ERESTARTNOINTR:
+		/*
+		 * ERESTARTNOINTR means that the syscall should
+		 * be called again after the signal handler returns.
+		 * Setup reg state just as it was before doing the trap
+		 * r0 has been clobbered with sys call ret code thus it
+		 * needs to be reloaded with orig first arg to syscall
+		 * in orig_r0. Rest of relevant reg-file:
+		 * r8 (syscall num) and (r1 - r7) will be reset to
+		 * their orig user space value when we ret from kernel
+		 */
+		regs->r0 = regs->orig_r0;
+		regs->ret -= 4;
+		break;
+	}
+}
+
+/*
+ * OK, we're invoking a handler
+ */
+static void
+handle_signal(unsigned long sig, struct k_sigaction *ka, siginfo_t *info,
+	      struct pt_regs *regs)
+{
+	sigset_t *oldset = sigmask_to_save();
+	int ret;
+
+	/* Set up the stack frame */
+	ret = setup_rt_frame(sig, ka, info, oldset, regs);
+
+	if (ret)
+		force_sigsegv(sig, current);
+	else
+		signal_delivered(sig, info, ka, regs, 0);
+}
+
+void do_signal(struct pt_regs *regs)
+{
+	struct k_sigaction ka;
+	siginfo_t info;
+	int signr;
+	int restart_scall;
+
+	signr = get_signal_to_deliver(&info, &ka, regs, NULL);
+
+	restart_scall = in_syscall(regs) && syscall_restartable(regs);
+
+	if (signr > 0) {
+		if (restart_scall) {
+			arc_restart_syscall(&ka, regs);
+			syscall_wont_restart(regs);	/* No more restarts */
+		}
+		handle_signal(signr, &ka, &info, regs);
+		return;
+	}
+
+	if (restart_scall) {
+		/* No handler for syscall: restart it */
+		if (regs->r0 == -ERESTARTNOHAND ||
+		    regs->r0 == -ERESTARTSYS || regs->r0 == -ERESTARTNOINTR) {
+			regs->r0 = regs->orig_r0;
+			regs->ret -= 4;
+		} else if (regs->r0 == -ERESTART_RESTARTBLOCK) {
+			regs->r8 = __NR_restart_syscall;
+			regs->ret -= 4;
+		}
+		syscall_wont_restart(regs);	/* No more restarts */
+	}
+
+	/* If there's no signal to deliver, restore the saved sigmask back */
+	restore_saved_sigmask();
+}
+
+void do_notify_resume(struct pt_regs *regs)
+{
+	/*
+	 * ASM glue gaurantees that this is only called when returning to
+	 * user mode
+	 */
+	if (test_and_clear_thread_flag(TIF_NOTIFY_RESUME))
+		tracehook_notify_resume(regs);
+}
diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c
new file mode 100644
index 000000000000..3af3e06dcf02
--- /dev/null
+++ b/arch/arc/kernel/smp.c
@@ -0,0 +1,332 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * RajeshwarR: Dec 11, 2007
+ *   -- Added support for Inter Processor Interrupts
+ *
+ * Vineetg: Nov 1st, 2007
+ *    -- Initial Write (Borrowed heavily from ARM)
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/spinlock.h>
+#include <linux/sched.h>
+#include <linux/interrupt.h>
+#include <linux/profile.h>
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/mm.h>
+#include <linux/cpu.h>
+#include <linux/smp.h>
+#include <linux/irq.h>
+#include <linux/delay.h>
+#include <linux/atomic.h>
+#include <linux/percpu.h>
+#include <linux/cpumask.h>
+#include <linux/spinlock_types.h>
+#include <linux/reboot.h>
+#include <asm/processor.h>
+#include <asm/setup.h>
+#include <asm/mach_desc.h>
+
+arch_spinlock_t smp_atomic_ops_lock = __ARCH_SPIN_LOCK_UNLOCKED;
+arch_spinlock_t smp_bitops_lock = __ARCH_SPIN_LOCK_UNLOCKED;
+
+struct plat_smp_ops  plat_smp_ops;
+
+/* XXX: per cpu ? Only needed once in early seconday boot */
+struct task_struct *secondary_idle_tsk;
+
+/* Called from start_kernel */
+void __init smp_prepare_boot_cpu(void)
+{
+}
+
+/*
+ * Initialise the CPU possible map early - this describes the CPUs
+ * which may be present or become present in the system.
+ */
+void __init smp_init_cpus(void)
+{
+	unsigned int i;
+
+	for (i = 0; i < NR_CPUS; i++)
+		set_cpu_possible(i, true);
+}
+
+/* called from init ( ) =>  process 1 */
+void __init smp_prepare_cpus(unsigned int max_cpus)
+{
+	int i;
+
+	/*
+	 * Initialise the present map, which describes the set of CPUs
+	 * actually populated at the present time.
+	 */
+	for (i = 0; i < max_cpus; i++)
+		set_cpu_present(i, true);
+}
+
+void __init smp_cpus_done(unsigned int max_cpus)
+{
+
+}
+
+/*
+ * After power-up, a non Master CPU needs to wait for Master to kick start it
+ *
+ * The default implementation halts
+ *
+ * This relies on platform specific support allowing Master to directly set
+ * this CPU's PC (to be @first_lines_of_secondary() and kick start it.
+ *
+ * In lack of such h/w assist, platforms can override this function
+ *   - make this function busy-spin on a token, eventually set by Master
+ *     (from arc_platform_smp_wakeup_cpu())
+ *   - Once token is available, jump to @first_lines_of_secondary
+ *     (using inline asm).
+ *
+ * Alert: can NOT use stack here as it has not been determined/setup for CPU.
+ *        If it turns out to be elaborate, it's better to code it in assembly
+ *
+ */
+void __attribute__((weak)) arc_platform_smp_wait_to_boot(int cpu)
+{
+	/*
+	 * As a hack for debugging - since debugger will single-step over the
+	 * FLAG insn - wrap the halt itself it in a self loop
+	 */
+	__asm__ __volatile__(
+	"1:		\n"
+	"	flag 1	\n"
+	"	b 1b	\n");
+}
+
+const char *arc_platform_smp_cpuinfo(void)
+{
+	return plat_smp_ops.info;
+}
+
+/*
+ * The very first "C" code executed by secondary
+ * Called from asm stub in head.S
+ * "current"/R25 already setup by low level boot code
+ */
+void __cpuinit start_kernel_secondary(void)
+{
+	struct mm_struct *mm = &init_mm;
+	unsigned int cpu = smp_processor_id();
+
+	/* MMU, Caches, Vector Table, Interrupts etc */
+	setup_processor();
+
+	atomic_inc(&mm->mm_users);
+	atomic_inc(&mm->mm_count);
+	current->active_mm = mm;
+
+	notify_cpu_starting(cpu);
+	set_cpu_online(cpu, true);
+
+	pr_info("## CPU%u LIVE ##: Executing Code...\n", cpu);
+
+	if (machine_desc->init_smp)
+		machine_desc->init_smp(smp_processor_id());
+
+	arc_local_timer_setup(cpu);
+
+	local_irq_enable();
+	preempt_disable();
+	cpu_idle();
+}
+
+/*
+ * Called from kernel_init( ) -> smp_init( ) - for each CPU
+ *
+ * At this point, Secondary Processor  is "HALT"ed:
+ *  -It booted, but was halted in head.S
+ *  -It was configured to halt-on-reset
+ *  So need to wake it up.
+ *
+ * Essential requirements being where to run from (PC) and stack (SP)
+*/
+int __cpuinit __cpu_up(unsigned int cpu, struct task_struct *idle)
+{
+	unsigned long wait_till;
+
+	secondary_idle_tsk = idle;
+
+	pr_info("Idle Task [%d] %p", cpu, idle);
+	pr_info("Trying to bring up CPU%u ...\n", cpu);
+
+	if (plat_smp_ops.cpu_kick)
+		plat_smp_ops.cpu_kick(cpu,
+				(unsigned long)first_lines_of_secondary);
+
+	/* wait for 1 sec after kicking the secondary */
+	wait_till = jiffies + HZ;
+	while (time_before(jiffies, wait_till)) {
+		if (cpu_online(cpu))
+			break;
+	}
+
+	if (!cpu_online(cpu)) {
+		pr_info("Timeout: CPU%u FAILED to comeup !!!\n", cpu);
+		return -1;
+	}
+
+	secondary_idle_tsk = NULL;
+
+	return 0;
+}
+
+/*
+ * not supported here
+ */
+int __init setup_profiling_timer(unsigned int multiplier)
+{
+	return -EINVAL;
+}
+
+/*****************************************************************************/
+/*              Inter Processor Interrupt Handling                           */
+/*****************************************************************************/
+
+/*
+ * structures for inter-processor calls
+ * A Collection of single bit ipi messages
+ *
+ */
+
+/*
+ * TODO_rajesh investigate tlb message types.
+ * IPI Timer not needed because each ARC has an individual Interrupting Timer
+ */
+enum ipi_msg_type {
+	IPI_NOP = 0,
+	IPI_RESCHEDULE = 1,
+	IPI_CALL_FUNC,
+	IPI_CALL_FUNC_SINGLE,
+	IPI_CPU_STOP
+};
+
+struct ipi_data {
+	unsigned long bits;
+};
+
+static DEFINE_PER_CPU(struct ipi_data, ipi_data);
+
+static void ipi_send_msg(const struct cpumask *callmap, enum ipi_msg_type msg)
+{
+	unsigned long flags;
+	unsigned int cpu;
+
+	local_irq_save(flags);
+
+	for_each_cpu(cpu, callmap) {
+		struct ipi_data *ipi = &per_cpu(ipi_data, cpu);
+		set_bit(msg, &ipi->bits);
+	}
+
+	/* Call the platform specific cross-CPU call function  */
+	if (plat_smp_ops.ipi_send)
+		plat_smp_ops.ipi_send((void *)callmap);
+
+	local_irq_restore(flags);
+}
+
+void smp_send_reschedule(int cpu)
+{
+	ipi_send_msg(cpumask_of(cpu), IPI_RESCHEDULE);
+}
+
+void smp_send_stop(void)
+{
+	struct cpumask targets;
+	cpumask_copy(&targets, cpu_online_mask);
+	cpumask_clear_cpu(smp_processor_id(), &targets);
+	ipi_send_msg(&targets, IPI_CPU_STOP);
+}
+
+void arch_send_call_function_single_ipi(int cpu)
+{
+	ipi_send_msg(cpumask_of(cpu), IPI_CALL_FUNC_SINGLE);
+}
+
+void arch_send_call_function_ipi_mask(const struct cpumask *mask)
+{
+	ipi_send_msg(mask, IPI_CALL_FUNC);
+}
+
+/*
+ * ipi_cpu_stop - handle IPI from smp_send_stop()
+ */
+static void ipi_cpu_stop(unsigned int cpu)
+{
+	machine_halt();
+}
+
+static inline void __do_IPI(unsigned long *ops, struct ipi_data *ipi, int cpu)
+{
+	unsigned long msg = 0;
+
+	do {
+		msg = find_next_bit(ops, BITS_PER_LONG, msg+1);
+
+		switch (msg) {
+		case IPI_RESCHEDULE:
+			scheduler_ipi();
+			break;
+
+		case IPI_CALL_FUNC:
+			generic_smp_call_function_interrupt();
+			break;
+
+		case IPI_CALL_FUNC_SINGLE:
+			generic_smp_call_function_single_interrupt();
+			break;
+
+		case IPI_CPU_STOP:
+			ipi_cpu_stop(cpu);
+			break;
+		}
+	} while (msg < BITS_PER_LONG);
+
+}
+
+/*
+ * arch-common ISR to handle for inter-processor interrupts
+ * Has hooks for platform specific IPI
+ */
+irqreturn_t do_IPI(int irq, void *dev_id)
+{
+	int cpu = smp_processor_id();
+	struct ipi_data *ipi = &per_cpu(ipi_data, cpu);
+	unsigned long ops;
+
+	if (plat_smp_ops.ipi_clear)
+		plat_smp_ops.ipi_clear(cpu, irq);
+
+	/*
+	 * XXX: is this loop really needed
+	 * And do we need to move ipi_clean inside
+	 */
+	while ((ops = xchg(&ipi->bits, 0)) != 0)
+		__do_IPI(&ops, ipi, cpu);
+
+	return IRQ_HANDLED;
+}
+
+/*
+ * API called by platform code to hookup arch-common ISR to their IPI IRQ
+ */
+static DEFINE_PER_CPU(int, ipi_dev);
+int smp_ipi_irq_setup(int cpu, int irq)
+{
+	int *dev_id = &per_cpu(ipi_dev, smp_processor_id());
+	return request_percpu_irq(irq, do_IPI, "IPI Interrupt", dev_id);
+}
diff --git a/arch/arc/kernel/stacktrace.c b/arch/arc/kernel/stacktrace.c
new file mode 100644
index 000000000000..a63ff842564b
--- /dev/null
+++ b/arch/arc/kernel/stacktrace.c
@@ -0,0 +1,254 @@
+/*
+ *	stacktrace.c : stacktracing APIs needed by rest of kernel
+ *			(wrappers over ARC dwarf based unwinder)
+ *
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ *  vineetg: aug 2009
+ *  -Implemented CONFIG_STACKTRACE APIs, primarily save_stack_trace_tsk( )
+ *   for displaying task's kernel mode call stack in /proc/<pid>/stack
+ *  -Iterator based approach to have single copy of unwinding core and APIs
+ *   needing unwinding, implement the logic in iterator regarding:
+ *      = which frame onwards to start capture
+ *      = which frame to stop capturing (wchan)
+ *      = specifics of data structs where trace is saved(CONFIG_STACKTRACE etc)
+ *
+ *  vineetg: March 2009
+ *  -Implemented correct versions of thread_saved_pc() and get_wchan()
+ *
+ *  rajeshwarr: 2008
+ *  -Initial implementation
+ */
+
+#include <linux/ptrace.h>
+#include <linux/export.h>
+#include <linux/stacktrace.h>
+#include <linux/kallsyms.h>
+#include <asm/arcregs.h>
+#include <asm/unwind.h>
+#include <asm/switch_to.h>
+
+/*-------------------------------------------------------------------------
+ *              Unwinder Iterator
+ *-------------------------------------------------------------------------
+ */
+
+#ifdef CONFIG_ARC_DW2_UNWIND
+
+static void seed_unwind_frame_info(struct task_struct *tsk,
+				   struct pt_regs *regs,
+				   struct unwind_frame_info *frame_info)
+{
+	if (tsk == NULL && regs == NULL) {
+		unsigned long fp, sp, blink, ret;
+		frame_info->task = current;
+
+		__asm__ __volatile__(
+			"mov %0,r27\n\t"
+			"mov %1,r28\n\t"
+			"mov %2,r31\n\t"
+			"mov %3,r63\n\t"
+			: "=r"(fp), "=r"(sp), "=r"(blink), "=r"(ret)
+		);
+
+		frame_info->regs.r27 = fp;
+		frame_info->regs.r28 = sp;
+		frame_info->regs.r31 = blink;
+		frame_info->regs.r63 = ret;
+		frame_info->call_frame = 0;
+	} else if (regs == NULL) {
+
+		frame_info->task = tsk;
+
+		frame_info->regs.r27 = KSTK_FP(tsk);
+		frame_info->regs.r28 = KSTK_ESP(tsk);
+		frame_info->regs.r31 = KSTK_BLINK(tsk);
+		frame_info->regs.r63 = (unsigned int)__switch_to;
+
+		/* In the prologue of __switch_to, first FP is saved on stack
+		 * and then SP is copied to FP. Dwarf assumes cfa as FP based
+		 * but we didn't save FP. The value retrieved above is FP's
+		 * state in previous frame.
+		 * As a work around for this, we unwind from __switch_to start
+		 * and adjust SP accordingly. The other limitation is that
+		 * __switch_to macro is dwarf rules are not generated for inline
+		 * assembly code
+		 */
+		frame_info->regs.r27 = 0;
+		frame_info->regs.r28 += 64;
+		frame_info->call_frame = 0;
+
+	} else {
+		frame_info->task = tsk;
+
+		frame_info->regs.r27 = regs->fp;
+		frame_info->regs.r28 = regs->sp;
+		frame_info->regs.r31 = regs->blink;
+		frame_info->regs.r63 = regs->ret;
+		frame_info->call_frame = 0;
+	}
+}
+
+#endif
+
+static noinline unsigned int
+arc_unwind_core(struct task_struct *tsk, struct pt_regs *regs,
+		int (*consumer_fn) (unsigned int, void *), void *arg)
+{
+#ifdef CONFIG_ARC_DW2_UNWIND
+	int ret = 0;
+	unsigned int address;
+	struct unwind_frame_info frame_info;
+
+	seed_unwind_frame_info(tsk, regs, &frame_info);
+
+	while (1) {
+		address = UNW_PC(&frame_info);
+
+		if (address && __kernel_text_address(address)) {
+			if (consumer_fn(address, arg) == -1)
+				break;
+		}
+
+		ret = arc_unwind(&frame_info);
+
+		if (ret == 0) {
+			frame_info.regs.r63 = frame_info.regs.r31;
+			continue;
+		} else {
+			break;
+		}
+	}
+
+	return address;		/* return the last address it saw */
+#else
+	/* On ARC, only Dward based unwinder works. fp based backtracing is
+	 * not possible (-fno-omit-frame-pointer) because of the way function
+	 * prelogue is setup (callee regs saved and then fp set and not other
+	 * way around
+	 */
+	pr_warn("CONFIG_ARC_DW2_UNWIND needs to be enabled\n");
+	return 0;
+
+#endif
+}
+
+/*-------------------------------------------------------------------------
+ * callbacks called by unwinder iterator to implement kernel APIs
+ *
+ * The callback can return -1 to force the iterator to stop, which by default
+ * keeps going till the bottom-most frame.
+ *-------------------------------------------------------------------------
+ */
+
+/* Call-back which plugs into unwinding core to dump the stack in
+ * case of panic/OOPs/BUG etc
+ */
+static int __print_sym(unsigned int address, void *unused)
+{
+	__print_symbol("  %s\n", address);
+	return 0;
+}
+
+#ifdef CONFIG_STACKTRACE
+
+/* Call-back which plugs into unwinding core to capture the
+ * traces needed by kernel on /proc/<pid>/stack
+ */
+static int __collect_all(unsigned int address, void *arg)
+{
+	struct stack_trace *trace = arg;
+
+	if (trace->skip > 0)
+		trace->skip--;
+	else
+		trace->entries[trace->nr_entries++] = address;
+
+	if (trace->nr_entries >= trace->max_entries)
+		return -1;
+
+	return 0;
+}
+
+static int __collect_all_but_sched(unsigned int address, void *arg)
+{
+	struct stack_trace *trace = arg;
+
+	if (in_sched_functions(address))
+		return 0;
+
+	if (trace->skip > 0)
+		trace->skip--;
+	else
+		trace->entries[trace->nr_entries++] = address;
+
+	if (trace->nr_entries >= trace->max_entries)
+		return -1;
+
+	return 0;
+}
+
+#endif
+
+static int __get_first_nonsched(unsigned int address, void *unused)
+{
+	if (in_sched_functions(address))
+		return 0;
+
+	return -1;
+}
+
+/*-------------------------------------------------------------------------
+ *              APIs expected by various kernel sub-systems
+ *-------------------------------------------------------------------------
+ */
+
+noinline void show_stacktrace(struct task_struct *tsk, struct pt_regs *regs)
+{
+	pr_info("\nStack Trace:\n");
+	arc_unwind_core(tsk, regs, __print_sym, NULL);
+}
+EXPORT_SYMBOL(show_stacktrace);
+
+/* Expected by sched Code */
+void show_stack(struct task_struct *tsk, unsigned long *sp)
+{
+	show_stacktrace(tsk, NULL);
+}
+
+/* Expected by Rest of kernel code */
+void dump_stack(void)
+{
+	show_stacktrace(NULL, NULL);
+}
+EXPORT_SYMBOL(dump_stack);
+
+/* Another API expected by schedular, shows up in "ps" as Wait Channel
+ * Ofcourse just returning schedule( ) would be pointless so unwind until
+ * the function is not in schedular code
+ */
+unsigned int get_wchan(struct task_struct *tsk)
+{
+	return arc_unwind_core(tsk, NULL, __get_first_nonsched, NULL);
+}
+
+#ifdef CONFIG_STACKTRACE
+
+/*
+ * API required by CONFIG_STACKTRACE, CONFIG_LATENCYTOP.
+ * A typical use is when /proc/<pid>/stack is queried by userland
+ */
+void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
+{
+	arc_unwind_core(tsk, NULL, __collect_all_but_sched, trace);
+}
+
+void save_stack_trace(struct stack_trace *trace)
+{
+	arc_unwind_core(current, NULL, __collect_all, trace);
+}
+#endif
diff --git a/arch/arc/kernel/sys.c b/arch/arc/kernel/sys.c
new file mode 100644
index 000000000000..f6bdd07583f3
--- /dev/null
+++ b/arch/arc/kernel/sys.c
@@ -0,0 +1,18 @@
+
+#include <linux/syscalls.h>
+#include <linux/signal.h>
+#include <linux/unistd.h>
+
+#include <asm/syscalls.h>
+
+#define sys_clone	sys_clone_wrapper
+#define sys_fork	sys_fork_wrapper
+#define sys_vfork	sys_vfork_wrapper
+
+#undef __SYSCALL
+#define __SYSCALL(nr, call) [nr] = (call),
+
+void *sys_call_table[NR_syscalls] = {
+	[0 ... NR_syscalls-1] = sys_ni_syscall,
+#include <asm/unistd.h>
+};
diff --git a/arch/arc/kernel/time.c b/arch/arc/kernel/time.c
new file mode 100644
index 000000000000..f13f72807aa5
--- /dev/null
+++ b/arch/arc/kernel/time.c
@@ -0,0 +1,265 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * vineetg: Jan 1011
+ *  -sched_clock( ) no longer jiffies based. Uses the same clocksource
+ *   as gtod
+ *
+ * Rajeshwarr/Vineetg: Mar 2008
+ *  -Implemented CONFIG_GENERIC_TIME (rather deleted arch specific code)
+ *   for arch independent gettimeofday()
+ *  -Implemented CONFIG_GENERIC_CLOCKEVENTS as base for hrtimers
+ *
+ * Vineetg: Mar 2008: Forked off from time.c which now is time-jiff.c
+ */
+
+/* ARC700 has two 32bit independent prog Timers: TIMER0 and TIMER1
+ * Each can programmed to go from @count to @limit and optionally
+ * interrupt when that happens.
+ * A write to Control Register clears the Interrupt
+ *
+ * We've designated TIMER0 for events (clockevents)
+ * while TIMER1 for free running (clocksource)
+ *
+ * Newer ARC700 cores have 64bit clk fetching RTSC insn, preferred over TIMER1
+ */
+
+#include <linux/spinlock.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/interrupt.h>
+#include <linux/time.h>
+#include <linux/init.h>
+#include <linux/timex.h>
+#include <linux/profile.h>
+#include <linux/clocksource.h>
+#include <linux/clockchips.h>
+#include <asm/irq.h>
+#include <asm/arcregs.h>
+#include <asm/clk.h>
+#include <asm/mach_desc.h>
+
+#define ARC_TIMER_MAX	0xFFFFFFFF
+
+/********** Clock Source Device *********/
+
+#ifdef CONFIG_ARC_HAS_RTSC
+
+int __cpuinit arc_counter_setup(void)
+{
+	/* RTSC insn taps into cpu clk, needs no setup */
+
+	/* For SMP, only allowed if cross-core-sync, hence usable as cs */
+	return 1;
+}
+
+static cycle_t arc_counter_read(struct clocksource *cs)
+{
+	unsigned long flags;
+	union {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+		struct { u32 high, low; };
+#else
+		struct { u32 low, high; };
+#endif
+		cycle_t  full;
+	} stamp;
+
+	flags = arch_local_irq_save();
+
+	__asm__ __volatile(
+	"	.extCoreRegister tsch, 58,  r, cannot_shortcut	\n"
+	"	rtsc %0, 0	\n"
+	"	mov  %1, 0	\n"
+	: "=r" (stamp.low), "=r" (stamp.high));
+
+	arch_local_irq_restore(flags);
+
+	return stamp.full;
+}
+
+static struct clocksource arc_counter = {
+	.name   = "ARC RTSC",
+	.rating = 300,
+	.read   = arc_counter_read,
+	.mask   = CLOCKSOURCE_MASK(32),
+	.flags  = CLOCK_SOURCE_IS_CONTINUOUS,
+};
+
+#else /* !CONFIG_ARC_HAS_RTSC */
+
+static bool is_usable_as_clocksource(void)
+{
+#ifdef CONFIG_SMP
+	return 0;
+#else
+	return 1;
+#endif
+}
+
+/*
+ * set 32bit TIMER1 to keep counting monotonically and wraparound
+ */
+int __cpuinit arc_counter_setup(void)
+{
+	write_aux_reg(ARC_REG_TIMER1_LIMIT, ARC_TIMER_MAX);
+	write_aux_reg(ARC_REG_TIMER1_CNT, 0);
+	write_aux_reg(ARC_REG_TIMER1_CTRL, TIMER_CTRL_NH);
+
+	return is_usable_as_clocksource();
+}
+
+static cycle_t arc_counter_read(struct clocksource *cs)
+{
+	return (cycle_t) read_aux_reg(ARC_REG_TIMER1_CNT);
+}
+
+static struct clocksource arc_counter = {
+	.name   = "ARC Timer1",
+	.rating = 300,
+	.read   = arc_counter_read,
+	.mask   = CLOCKSOURCE_MASK(32),
+	.flags  = CLOCK_SOURCE_IS_CONTINUOUS,
+};
+
+#endif
+
+/********** Clock Event Device *********/
+
+/*
+ * Arm the timer to interrupt after @limit cycles
+ * The distinction for oneshot/periodic is done in arc_event_timer_ack() below
+ */
+static void arc_timer_event_setup(unsigned int limit)
+{
+	write_aux_reg(ARC_REG_TIMER0_LIMIT, limit);
+	write_aux_reg(ARC_REG_TIMER0_CNT, 0);	/* start from 0 */
+
+	write_aux_reg(ARC_REG_TIMER0_CTRL, TIMER_CTRL_IE | TIMER_CTRL_NH);
+}
+
+/*
+ * Acknowledge the interrupt (oneshot) and optionally re-arm it (periodic)
+ * -Any write to CTRL Reg will ack the intr (NH bit: Count when not halted)
+ * -Rearming is done by setting the IE bit
+ *
+ * Small optimisation: Normal code would have been
+ *   if (irq_reenable)
+ *     CTRL_REG = (IE | NH);
+ *   else
+ *     CTRL_REG = NH;
+ * However since IE is BIT0 we can fold the branch
+ */
+static void arc_timer_event_ack(unsigned int irq_reenable)
+{
+	write_aux_reg(ARC_REG_TIMER0_CTRL, irq_reenable | TIMER_CTRL_NH);
+}
+
+static int arc_clkevent_set_next_event(unsigned long delta,
+				       struct clock_event_device *dev)
+{
+	arc_timer_event_setup(delta);
+	return 0;
+}
+
+static void arc_clkevent_set_mode(enum clock_event_mode mode,
+				  struct clock_event_device *dev)
+{
+	switch (mode) {
+	case CLOCK_EVT_MODE_PERIODIC:
+		arc_timer_event_setup(arc_get_core_freq() / HZ);
+		break;
+	case CLOCK_EVT_MODE_ONESHOT:
+		break;
+	default:
+		break;
+	}
+
+	return;
+}
+
+static DEFINE_PER_CPU(struct clock_event_device, arc_clockevent_device) = {
+	.name		= "ARC Timer0",
+	.features	= CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_PERIODIC,
+	.mode		= CLOCK_EVT_MODE_UNUSED,
+	.rating		= 300,
+	.irq		= TIMER0_IRQ,	/* hardwired, no need for resources */
+	.set_next_event = arc_clkevent_set_next_event,
+	.set_mode	= arc_clkevent_set_mode,
+};
+
+static irqreturn_t timer_irq_handler(int irq, void *dev_id)
+{
+	struct clock_event_device *clk = &__get_cpu_var(arc_clockevent_device);
+
+	arc_timer_event_ack(clk->mode == CLOCK_EVT_MODE_PERIODIC);
+	clk->event_handler(clk);
+	return IRQ_HANDLED;
+}
+
+static struct irqaction arc_timer_irq = {
+	.name    = "Timer0 (clock-evt-dev)",
+	.flags   = IRQF_TIMER | IRQF_PERCPU,
+	.handler = timer_irq_handler,
+};
+
+/*
+ * Setup the local event timer for @cpu
+ * N.B. weak so that some exotic ARC SoCs can completely override it
+ */
+void __attribute__((weak)) __cpuinit arc_local_timer_setup(unsigned int cpu)
+{
+	struct clock_event_device *clk = &per_cpu(arc_clockevent_device, cpu);
+
+	clockevents_calc_mult_shift(clk, arc_get_core_freq(), 5);
+
+	clk->max_delta_ns = clockevent_delta2ns(ARC_TIMER_MAX, clk);
+	clk->cpumask = cpumask_of(cpu);
+
+	clockevents_register_device(clk);
+
+	/*
+	 * setup the per-cpu timer IRQ handler - for all cpus
+	 * For non boot CPU explicitly unmask at intc
+	 * setup_irq() -> .. -> irq_startup() already does this on boot-cpu
+	 */
+	if (!cpu)
+		setup_irq(TIMER0_IRQ, &arc_timer_irq);
+	else
+		arch_unmask_irq(TIMER0_IRQ);
+}
+
+/*
+ * Called from start_kernel() - boot CPU only
+ *
+ * -Sets up h/w timers as applicable on boot cpu
+ * -Also sets up any global state needed for timer subsystem:
+ *    - for "counting" timer, registers a clocksource, usable across CPUs
+ *      (provided that underlying counter h/w is synchronized across cores)
+ *    - for "event" timer, sets up TIMER0 IRQ (as that is platform agnostic)
+ */
+void __init time_init(void)
+{
+	/*
+	 * sets up the timekeeping free-flowing counter which also returns
+	 * whether the counter is usable as clocksource
+	 */
+	if (arc_counter_setup())
+		/*
+		 * CLK upto 4.29 GHz can be safely represented in 32 bits
+		 * because Max 32 bit number is 4,294,967,295
+		 */
+		clocksource_register_hz(&arc_counter, arc_get_core_freq());
+
+	/* sets up the periodic event timer */
+	arc_local_timer_setup(smp_processor_id());
+
+	if (machine_desc->init_time)
+		machine_desc->init_time();
+}
diff --git a/arch/arc/kernel/traps.c b/arch/arc/kernel/traps.c
new file mode 100644
index 000000000000..7496995371e8
--- /dev/null
+++ b/arch/arc/kernel/traps.c
@@ -0,0 +1,170 @@
+/*
+ * Traps/Non-MMU Exception handling for ARC
+ *
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * vineetg: May 2011
+ *  -user-space unaligned access emulation
+ *
+ * Rahul Trivedi: Codito Technologies 2004
+ */
+
+#include <linux/sched.h>
+#include <linux/kdebug.h>
+#include <linux/uaccess.h>
+#include <asm/ptrace.h>
+#include <asm/setup.h>
+#include <asm/kprobes.h>
+#include <asm/unaligned.h>
+#include <asm/kgdb.h>
+
+void __init trap_init(void)
+{
+	return;
+}
+
+void die(const char *str, struct pt_regs *regs, unsigned long address,
+	 unsigned long cause_reg)
+{
+	show_kernel_fault_diag(str, regs, address, cause_reg);
+
+	/* DEAD END */
+	__asm__("flag 1");
+}
+
+/*
+ * Helper called for bulk of exceptions NOT needing specific handling
+ *  -for user faults enqueues requested signal
+ *  -for kernel, chk if due to copy_(to|from)_user, otherwise die()
+ */
+static noinline int handle_exception(unsigned long cause, char *str,
+				     struct pt_regs *regs, siginfo_t *info)
+{
+	if (user_mode(regs)) {
+		struct task_struct *tsk = current;
+
+		tsk->thread.fault_address = (__force unsigned int)info->si_addr;
+		tsk->thread.cause_code = cause;
+
+		force_sig_info(info->si_signo, info, tsk);
+
+	} else {
+		/* If not due to copy_(to|from)_user, we are doomed */
+		if (fixup_exception(regs))
+			return 0;
+
+		die(str, regs, (unsigned long)info->si_addr, cause);
+	}
+
+	return 1;
+}
+
+#define DO_ERROR_INFO(signr, str, name, sicode) \
+int name(unsigned long cause, unsigned long address, struct pt_regs *regs) \
+{						\
+	siginfo_t info = {			\
+		.si_signo = signr,		\
+		.si_errno = 0,			\
+		.si_code  = sicode,		\
+		.si_addr = (void __user *)address,	\
+	};					\
+	return handle_exception(cause, str, regs, &info);\
+}
+
+/*
+ * Entry points for exceptions NOT needing specific handling
+ */
+DO_ERROR_INFO(SIGILL, "Priv Op/Disabled Extn", do_privilege_fault, ILL_PRVOPC)
+DO_ERROR_INFO(SIGILL, "Invalid Extn Insn", do_extension_fault, ILL_ILLOPC)
+DO_ERROR_INFO(SIGILL, "Illegal Insn (or Seq)", insterror_is_error, ILL_ILLOPC)
+DO_ERROR_INFO(SIGBUS, "Invalid Mem Access", do_memory_error, BUS_ADRERR)
+DO_ERROR_INFO(SIGTRAP, "Breakpoint Set", trap_is_brkpt, TRAP_BRKPT)
+
+#ifdef CONFIG_ARC_MISALIGN_ACCESS
+/*
+ * Entry Point for Misaligned Data access Exception, for emulating in software
+ */
+int do_misaligned_access(unsigned long cause, unsigned long address,
+			 struct pt_regs *regs, struct callee_regs *cregs)
+{
+	if (misaligned_fixup(address, regs, cause, cregs) != 0) {
+		siginfo_t info;
+
+		info.si_signo = SIGBUS;
+		info.si_errno = 0;
+		info.si_code = BUS_ADRALN;
+		info.si_addr = (void __user *)address;
+		return handle_exception(cause, "Misaligned Access", regs,
+					  &info);
+	}
+	return 0;
+}
+
+#else
+DO_ERROR_INFO(SIGSEGV, "Misaligned Access", do_misaligned_access, SEGV_ACCERR)
+#endif
+
+/*
+ * Entry point for miscll errors such as Nested Exceptions
+ *  -Duplicate TLB entry is handled seperately though
+ */
+void do_machine_check_fault(unsigned long cause, unsigned long address,
+			    struct pt_regs *regs)
+{
+	die("Machine Check Exception", regs, address, cause);
+}
+
+
+/*
+ * Entry point for traps induced by ARCompact TRAP_S <n> insn
+ * This is same family as TRAP0/SWI insn (use the same vector).
+ * The only difference being SWI insn take no operand, while TRAP_S does
+ * which reflects in ECR Reg as 8 bit param.
+ * Thus TRAP_S <n> can be used for specific purpose
+ *  -1 used for software breakpointing (gdb)
+ *  -2 used by kprobes
+ */
+void do_non_swi_trap(unsigned long cause, unsigned long address,
+			struct pt_regs *regs)
+{
+	unsigned int param = cause & 0xff;
+
+	switch (param) {
+	case 1:
+		trap_is_brkpt(cause, address, regs);
+		break;
+
+	case 2:
+		trap_is_kprobe(param, address, regs);
+		break;
+
+	case 3:
+	case 4:
+		kgdb_trap(regs, param);
+		break;
+
+	default:
+		break;
+	}
+}
+
+/*
+ * Entry point for Instruction Error Exception
+ *  -For a corner case, ARC kprobes implementation resorts to using
+ *   this exception, hence the check
+ */
+void do_insterror_or_kprobe(unsigned long cause,
+				       unsigned long address,
+				       struct pt_regs *regs)
+{
+	/* Check if this exception is caused by kprobes */
+	if (notify_die(DIE_IERR, "kprobe_ierr", regs, address,
+		       cause, SIGILL) == NOTIFY_STOP)
+		return;
+
+	insterror_is_error(cause, address, regs);
+}
diff --git a/arch/arc/kernel/troubleshoot.c b/arch/arc/kernel/troubleshoot.c
new file mode 100644
index 000000000000..7c10873c311f
--- /dev/null
+++ b/arch/arc/kernel/troubleshoot.c
@@ -0,0 +1,322 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ */
+
+#include <linux/ptrace.h>
+#include <linux/module.h>
+#include <linux/mm.h>
+#include <linux/fs.h>
+#include <linux/kdev_t.h>
+#include <linux/fs_struct.h>
+#include <linux/proc_fs.h>
+#include <linux/file.h>
+#include <asm/arcregs.h>
+
+/*
+ * Common routine to print scratch regs (r0-r12) or callee regs (r13-r25)
+ *   -Prints 3 regs per line and a CR.
+ *   -To continue, callee regs right after scratch, special handling of CR
+ */
+static noinline void print_reg_file(long *reg_rev, int start_num)
+{
+	unsigned int i;
+	char buf[512];
+	int n = 0, len = sizeof(buf);
+
+	/* weird loop because pt_regs regs rev r12..r0, r25..r13 */
+	for (i = start_num; i < start_num + 13; i++) {
+		n += scnprintf(buf + n, len - n, "r%02u: 0x%08lx\t",
+			       i, (unsigned long)*reg_rev);
+
+		if (((i + 1) % 3) == 0)
+			n += scnprintf(buf + n, len - n, "\n");
+
+		reg_rev--;
+	}
+
+	if (start_num != 0)
+		n += scnprintf(buf + n, len - n, "\n\n");
+
+	pr_info("%s", buf);
+}
+
+static void show_callee_regs(struct callee_regs *cregs)
+{
+	print_reg_file(&(cregs->r13), 13);
+}
+
+void print_task_path_n_nm(struct task_struct *tsk, char *buf)
+{
+	struct path path;
+	char *path_nm = NULL;
+	struct mm_struct *mm;
+	struct file *exe_file;
+
+	mm = get_task_mm(tsk);
+	if (!mm)
+		goto done;
+
+	exe_file = get_mm_exe_file(mm);
+	mmput(mm);
+
+	if (exe_file) {
+		path = exe_file->f_path;
+		path_get(&exe_file->f_path);
+		fput(exe_file);
+		path_nm = d_path(&path, buf, 255);
+		path_put(&path);
+	}
+
+done:
+	pr_info("%s, TGID %u\n", path_nm, tsk->tgid);
+}
+EXPORT_SYMBOL(print_task_path_n_nm);
+
+static void show_faulting_vma(unsigned long address, char *buf)
+{
+	struct vm_area_struct *vma;
+	struct inode *inode;
+	unsigned long ino = 0;
+	dev_t dev = 0;
+	char *nm = buf;
+
+	vma = find_vma(current->active_mm, address);
+
+	/* check against the find_vma( ) behaviour which returns the next VMA
+	 * if the container VMA is not found
+	 */
+	if (vma && (vma->vm_start <= address)) {
+		struct file *file = vma->vm_file;
+		if (file) {
+			struct path *path = &file->f_path;
+			nm = d_path(path, buf, PAGE_SIZE - 1);
+			inode = vma->vm_file->f_path.dentry->d_inode;
+			dev = inode->i_sb->s_dev;
+			ino = inode->i_ino;
+		}
+		pr_info("    @off 0x%lx in [%s]\n"
+			"    VMA: 0x%08lx to 0x%08lx\n\n",
+		       address - vma->vm_start, nm, vma->vm_start, vma->vm_end);
+	} else
+		pr_info("    @No matching VMA found\n");
+}
+
+static void show_ecr_verbose(struct pt_regs *regs)
+{
+	unsigned int vec, cause_code, cause_reg;
+	unsigned long address;
+
+	cause_reg = current->thread.cause_code;
+	pr_info("\n[ECR]: 0x%08x => ", cause_reg);
+
+	/* For Data fault, this is data address not instruction addr */
+	address = current->thread.fault_address;
+
+	vec = cause_reg >> 16;
+	cause_code = (cause_reg >> 8) & 0xFF;
+
+	/* For DTLB Miss or ProtV, display the memory involved too */
+	if (vec == ECR_V_DTLB_MISS) {
+		pr_cont("Invalid (%s) @ 0x%08lx by insn @ 0x%08lx\n",
+		       (cause_code == 0x01) ? "Read From" :
+		       ((cause_code == 0x02) ? "Write to" : "EX"),
+		       address, regs->ret);
+	} else if (vec == ECR_V_ITLB_MISS) {
+		pr_cont("Insn could not be fetched\n");
+	} else if (vec == ECR_V_MACH_CHK) {
+		pr_cont("%s\n", (cause_code == 0x0) ?
+					"Double Fault" : "Other Fatal Err");
+
+	} else if (vec == ECR_V_PROTV) {
+		if (cause_code == ECR_C_PROTV_INST_FETCH)
+			pr_cont("Execute from Non-exec Page\n");
+		else if (cause_code == ECR_C_PROTV_LOAD)
+			pr_cont("Read from Non-readable Page\n");
+		else if (cause_code == ECR_C_PROTV_STORE)
+			pr_cont("Write to Non-writable Page\n");
+		else if (cause_code == ECR_C_PROTV_XCHG)
+			pr_cont("Data exchange protection violation\n");
+		else if (cause_code == ECR_C_PROTV_MISALIG_DATA)
+			pr_cont("Misaligned r/w from 0x%08lx\n", address);
+	} else if (vec == ECR_V_INSN_ERR) {
+		pr_cont("Illegal Insn\n");
+	} else {
+		pr_cont("Check Programmer's Manual\n");
+	}
+}
+
+/************************************************************************
+ *  API called by rest of kernel
+ ***********************************************************************/
+
+void show_regs(struct pt_regs *regs)
+{
+	struct task_struct *tsk = current;
+	struct callee_regs *cregs;
+	char *buf;
+
+	buf = (char *)__get_free_page(GFP_TEMPORARY);
+	if (!buf)
+		return;
+
+	print_task_path_n_nm(tsk, buf);
+
+	if (current->thread.cause_code)
+		show_ecr_verbose(regs);
+
+	pr_info("[EFA]: 0x%08lx\n", current->thread.fault_address);
+	pr_info("[ERET]: 0x%08lx (PC of Faulting Instr)\n", regs->ret);
+
+	show_faulting_vma(regs->ret, buf);	/* faulting code, not data */
+
+	/* can't use print_vma_addr() yet as it doesn't check for
+	 * non-inclusive vma
+	 */
+
+	/* print special regs */
+	pr_info("status32: 0x%08lx\n", regs->status32);
+	pr_info(" SP: 0x%08lx\tFP: 0x%08lx\n", regs->sp, regs->fp);
+	pr_info("BTA: 0x%08lx\tBLINK: 0x%08lx\n",
+		regs->bta, regs->blink);
+	pr_info("LPS: 0x%08lx\tLPE: 0x%08lx\tLPC: 0x%08lx\n",
+	       regs->lp_start, regs->lp_end, regs->lp_count);
+
+	/* print regs->r0 thru regs->r12
+	 * Sequential printing was generating horrible code
+	 */
+	print_reg_file(&(regs->r0), 0);
+
+	/* If Callee regs were saved, display them too */
+	cregs = (struct callee_regs *)current->thread.callee_reg;
+	if (cregs)
+		show_callee_regs(cregs);
+
+	free_page((unsigned long)buf);
+}
+
+void show_kernel_fault_diag(const char *str, struct pt_regs *regs,
+			    unsigned long address, unsigned long cause_reg)
+{
+	current->thread.fault_address = address;
+	current->thread.cause_code = cause_reg;
+
+	/* Caller and Callee regs */
+	show_regs(regs);
+
+	/* Show stack trace if this Fatality happened in kernel mode */
+	if (!user_mode(regs))
+		show_stacktrace(current, regs);
+}
+
+#ifdef CONFIG_DEBUG_FS
+
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/mount.h>
+#include <linux/pagemap.h>
+#include <linux/init.h>
+#include <linux/namei.h>
+#include <linux/debugfs.h>
+
+static struct dentry *test_dentry;
+static struct dentry *test_dir;
+static struct dentry *test_u32_dentry;
+
+static u32 clr_on_read = 1;
+
+#ifdef CONFIG_ARC_DBG_TLB_MISS_COUNT
+u32 numitlb, numdtlb, num_pte_not_present;
+
+static int fill_display_data(char *kbuf)
+{
+	size_t num = 0;
+	num += sprintf(kbuf + num, "I-TLB Miss %x\n", numitlb);
+	num += sprintf(kbuf + num, "D-TLB Miss %x\n", numdtlb);
+	num += sprintf(kbuf + num, "PTE not present %x\n", num_pte_not_present);
+
+	if (clr_on_read)
+		numitlb = numdtlb = num_pte_not_present = 0;
+
+	return num;
+}
+
+static int tlb_stats_open(struct inode *inode, struct file *file)
+{
+	file->private_data = (void *)__get_free_page(GFP_KERNEL);
+	return 0;
+}
+
+/* called on user read(): display the couters */
+static ssize_t tlb_stats_output(struct file *file,	/* file descriptor */
+				char __user *user_buf,	/* user buffer */
+				size_t len,		/* length of buffer */
+				loff_t *offset)		/* offset in the file */
+{
+	size_t num;
+	char *kbuf = (char *)file->private_data;
+
+	/* All of the data can he shoved in one iteration */
+	if (*offset != 0)
+		return 0;
+
+	num = fill_display_data(kbuf);
+
+	/* simple_read_from_buffer() is helper for copy to user space
+	   It copies up to @2 (num) bytes from kernel buffer @4 (kbuf) at offset
+	   @3 (offset) into the user space address starting at @1 (user_buf).
+	   @5 (len) is max size of user buffer
+	 */
+	return simple_read_from_buffer(user_buf, num, offset, kbuf, len);
+}
+
+/* called on user write : clears the counters */
+static ssize_t tlb_stats_clear(struct file *file, const char __user *user_buf,
+			       size_t length, loff_t *offset)
+{
+	numitlb = numdtlb = num_pte_not_present = 0;
+	return length;
+}
+
+static int tlb_stats_close(struct inode *inode, struct file *file)
+{
+	free_page((unsigned long)(file->private_data));
+	return 0;
+}
+
+static const struct file_operations tlb_stats_file_ops = {
+	.read = tlb_stats_output,
+	.write = tlb_stats_clear,
+	.open = tlb_stats_open,
+	.release = tlb_stats_close
+};
+#endif
+
+static int __init arc_debugfs_init(void)
+{
+	test_dir = debugfs_create_dir("arc", NULL);
+
+#ifdef CONFIG_ARC_DBG_TLB_MISS_COUNT
+	test_dentry = debugfs_create_file("tlb_stats", 0444, test_dir, NULL,
+					  &tlb_stats_file_ops);
+#endif
+
+	test_u32_dentry =
+	    debugfs_create_u32("clr_on_read", 0444, test_dir, &clr_on_read);
+
+	return 0;
+}
+
+module_init(arc_debugfs_init);
+
+static void __exit arc_debugfs_exit(void)
+{
+	debugfs_remove(test_u32_dentry);
+	debugfs_remove(test_dentry);
+	debugfs_remove(test_dir);
+}
+module_exit(arc_debugfs_exit);
+
+#endif
diff --git a/arch/arc/kernel/unaligned.c b/arch/arc/kernel/unaligned.c
new file mode 100644
index 000000000000..4cd81633febd
--- /dev/null
+++ b/arch/arc/kernel/unaligned.c
@@ -0,0 +1,245 @@
+/*
+ * Copyright (C) 2011-2012 Synopsys (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * vineetg : May 2011
+ *  -Adapted (from .26 to .35)
+ *  -original contribution by Tim.yao@amlogic.com
+ *
+ */
+
+#include <linux/types.h>
+#include <linux/ptrace.h>
+#include <linux/uaccess.h>
+#include <asm/disasm.h>
+
+#define __get8_unaligned_check(val, addr, err)		\
+	__asm__(					\
+	"1:	ldb.ab	%1, [%2, 1]\n"			\
+	"2:\n"						\
+	"	.section .fixup,\"ax\"\n"		\
+	"	.align	4\n"				\
+	"3:	mov	%0, 1\n"			\
+	"	b	2b\n"				\
+	"	.previous\n"				\
+	"	.section __ex_table,\"a\"\n"		\
+	"	.align	4\n"				\
+	"	.long	1b, 3b\n"			\
+	"	.previous\n"				\
+	: "=r" (err), "=&r" (val), "=r" (addr)		\
+	: "0" (err), "2" (addr))
+
+#define get16_unaligned_check(val, addr)		\
+	do {						\
+		unsigned int err = 0, v, a = addr;	\
+		__get8_unaligned_check(v, a, err);	\
+		val =  v ;				\
+		__get8_unaligned_check(v, a, err);	\
+		val |= v << 8;				\
+		if (err)				\
+			goto fault;			\
+	} while (0)
+
+#define get32_unaligned_check(val, addr)		\
+	do {						\
+		unsigned int err = 0, v, a = addr;	\
+		__get8_unaligned_check(v, a, err);	\
+		val =  v << 0;				\
+		__get8_unaligned_check(v, a, err);	\
+		val |= v << 8;				\
+		__get8_unaligned_check(v, a, err);	\
+		val |= v << 16;				\
+		__get8_unaligned_check(v, a, err);	\
+		val |= v << 24;				\
+		if (err)				\
+			goto fault;			\
+	} while (0)
+
+#define put16_unaligned_check(val, addr)		\
+	do {						\
+		unsigned int err = 0, v = val, a = addr;\
+							\
+		__asm__(				\
+		"1:	stb.ab	%1, [%2, 1]\n"		\
+		"	lsr %1, %1, 8\n"		\
+		"2:	stb	%1, [%2]\n"		\
+		"3:\n"					\
+		"	.section .fixup,\"ax\"\n"	\
+		"	.align	4\n"			\
+		"4:	mov	%0, 1\n"		\
+		"	b	3b\n"			\
+		"	.previous\n"			\
+		"	.section __ex_table,\"a\"\n"	\
+		"	.align	4\n"			\
+		"	.long	1b, 4b\n"		\
+		"	.long	2b, 4b\n"		\
+		"	.previous\n"			\
+		: "=r" (err), "=&r" (v), "=&r" (a)	\
+		: "0" (err), "1" (v), "2" (a));		\
+							\
+		if (err)				\
+			goto fault;			\
+	} while (0)
+
+#define put32_unaligned_check(val, addr)		\
+	do {						\
+		unsigned int err = 0, v = val, a = addr;\
+		__asm__(				\
+							\
+		"1:	stb.ab	%1, [%2, 1]\n"		\
+		"	lsr %1, %1, 8\n"		\
+		"2:	stb.ab	%1, [%2, 1]\n"		\
+		"	lsr %1, %1, 8\n"		\
+		"3:	stb.ab	%1, [%2, 1]\n"		\
+		"	lsr %1, %1, 8\n"		\
+		"4:	stb	%1, [%2]\n"		\
+		"5:\n"					\
+		"	.section .fixup,\"ax\"\n"	\
+		"	.align	4\n"			\
+		"6:	mov	%0, 1\n"		\
+		"	b	5b\n"			\
+		"	.previous\n"			\
+		"	.section __ex_table,\"a\"\n"	\
+		"	.align	4\n"			\
+		"	.long	1b, 6b\n"		\
+		"	.long	2b, 6b\n"		\
+		"	.long	3b, 6b\n"		\
+		"	.long	4b, 6b\n"		\
+		"	.previous\n"			\
+		: "=r" (err), "=&r" (v), "=&r" (a)	\
+		: "0" (err), "1" (v), "2" (a));		\
+							\
+		if (err)				\
+			goto fault;			\
+	} while (0)
+
+/* sysctl hooks */
+int unaligned_enabled __read_mostly = 1;	/* Enabled by default */
+int no_unaligned_warning __read_mostly = 1;	/* Only 1 warning by default */
+
+static void fixup_load(struct disasm_state *state, struct pt_regs *regs,
+			struct callee_regs *cregs)
+{
+	int val;
+
+	/* register write back */
+	if ((state->aa == 1) || (state->aa == 2)) {
+		set_reg(state->wb_reg, state->src1 + state->src2, regs, cregs);
+
+		if (state->aa == 2)
+			state->src2 = 0;
+	}
+
+	if (state->zz == 0) {
+		get32_unaligned_check(val, state->src1 + state->src2);
+	} else {
+		get16_unaligned_check(val, state->src1 + state->src2);
+
+		if (state->x)
+			val = (val << 16) >> 16;
+	}
+
+	if (state->pref == 0)
+		set_reg(state->dest, val, regs, cregs);
+
+	return;
+
+fault:	state->fault = 1;
+}
+
+static void fixup_store(struct disasm_state *state, struct pt_regs *regs,
+			struct callee_regs *cregs)
+{
+	/* register write back */
+	if ((state->aa == 1) || (state->aa == 2)) {
+		set_reg(state->wb_reg, state->src2 + state->src3, regs, cregs);
+
+		if (state->aa == 3)
+			state->src3 = 0;
+	} else if (state->aa == 3) {
+		if (state->zz == 2) {
+			set_reg(state->wb_reg, state->src2 + (state->src3 << 1),
+				regs, cregs);
+		} else if (!state->zz) {
+			set_reg(state->wb_reg, state->src2 + (state->src3 << 2),
+				regs, cregs);
+		} else {
+			goto fault;
+		}
+	}
+
+	/* write fix-up */
+	if (!state->zz)
+		put32_unaligned_check(state->src1, state->src2 + state->src3);
+	else
+		put16_unaligned_check(state->src1, state->src2 + state->src3);
+
+	return;
+
+fault:	state->fault = 1;
+}
+
+/*
+ * Handle an unaligned access
+ * Returns 0 if successfully handled, 1 if some error happened
+ */
+int misaligned_fixup(unsigned long address, struct pt_regs *regs,
+		     unsigned long cause, struct callee_regs *cregs)
+{
+	struct disasm_state state;
+	char buf[TASK_COMM_LEN];
+
+	/* handle user mode only and only if enabled by sysadmin */
+	if (!user_mode(regs) || !unaligned_enabled)
+		return 1;
+
+	if (no_unaligned_warning) {
+		pr_warn_once("%s(%d) made unaligned access which was emulated"
+			     " by kernel assist\n. This can degrade application"
+			     " performance significantly\n. To enable further"
+			     " logging of such instances, please \n"
+			     " echo 0 > /proc/sys/kernel/ignore-unaligned-usertrap\n",
+			     get_task_comm(buf, current), task_pid_nr(current));
+	} else {
+		/* Add rate limiting if it gets down to it */
+		pr_warn("%s(%d): unaligned access to/from 0x%lx by PC: 0x%lx\n",
+			get_task_comm(buf, current), task_pid_nr(current),
+			address, regs->ret);
+
+	}
+
+	disasm_instr(regs->ret, &state, 1, regs, cregs);
+
+	if (state.fault)
+		goto fault;
+
+	/* ldb/stb should not have unaligned exception */
+	if ((state.zz == 1) || (state.di))
+		goto fault;
+
+	if (!state.write)
+		fixup_load(&state, regs, cregs);
+	else
+		fixup_store(&state, regs, cregs);
+
+	if (state.fault)
+		goto fault;
+
+	if (delay_mode(regs)) {
+		regs->ret = regs->bta;
+		regs->status32 &= ~STATUS_DE_MASK;
+	} else {
+		regs->ret += state.instr_len;
+	}
+
+	return 0;
+
+fault:
+	pr_err("Alignment trap: fault in fix-up %08lx at [<%08lx>]\n",
+		state.words[0], address);
+
+	return 1;
+}
diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c
new file mode 100644
index 000000000000..a8d02223da44
--- /dev/null
+++ b/arch/arc/kernel/unwind.c
@@ -0,0 +1,1329 @@
+/*
+ * Copyright (C) 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ * Copyright (C) 2002-2006 Novell, Inc.
+ *	Jan Beulich <jbeulich@novell.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * A simple API for unwinding kernel stacks.  This is used for
+ * debugging and error reporting purposes.  The kernel doesn't need
+ * full-blown stack unwinding with all the bells and whistles, so there
+ * is not much point in implementing the full Dwarf2 unwind API.
+ */
+
+#include <linux/sched.h>
+#include <linux/module.h>
+#include <linux/bootmem.h>
+#include <linux/sort.h>
+#include <linux/slab.h>
+#include <linux/stop_machine.h>
+#include <linux/uaccess.h>
+#include <linux/ptrace.h>
+#include <asm/sections.h>
+#include <asm/unaligned.h>
+#include <asm/unwind.h>
+
+extern char __start_unwind[], __end_unwind[];
+/* extern const u8 __start_unwind_hdr[], __end_unwind_hdr[];*/
+
+/* #define UNWIND_DEBUG */
+
+#ifdef UNWIND_DEBUG
+int dbg_unw;
+#define unw_debug(fmt, ...)			\
+do {						\
+	if (dbg_unw)				\
+		pr_info(fmt, ##__VA_ARGS__);	\
+} while (0);
+#else
+#define unw_debug(fmt, ...)
+#endif
+
+#define MAX_STACK_DEPTH 8
+
+#define EXTRA_INFO(f) { \
+		BUILD_BUG_ON_ZERO(offsetof(struct unwind_frame_info, f) \
+				% FIELD_SIZEOF(struct unwind_frame_info, f)) \
+				+ offsetof(struct unwind_frame_info, f) \
+				/ FIELD_SIZEOF(struct unwind_frame_info, f), \
+				FIELD_SIZEOF(struct unwind_frame_info, f) \
+	}
+#define PTREGS_INFO(f) EXTRA_INFO(regs.f)
+
+static const struct {
+	unsigned offs:BITS_PER_LONG / 2;
+	unsigned width:BITS_PER_LONG / 2;
+} reg_info[] = {
+UNW_REGISTER_INFO};
+
+#undef PTREGS_INFO
+#undef EXTRA_INFO
+
+#ifndef REG_INVALID
+#define REG_INVALID(r) (reg_info[r].width == 0)
+#endif
+
+#define DW_CFA_nop                          0x00
+#define DW_CFA_set_loc                      0x01
+#define DW_CFA_advance_loc1                 0x02
+#define DW_CFA_advance_loc2                 0x03
+#define DW_CFA_advance_loc4                 0x04
+#define DW_CFA_offset_extended              0x05
+#define DW_CFA_restore_extended             0x06
+#define DW_CFA_undefined                    0x07
+#define DW_CFA_same_value                   0x08
+#define DW_CFA_register                     0x09
+#define DW_CFA_remember_state               0x0a
+#define DW_CFA_restore_state                0x0b
+#define DW_CFA_def_cfa                      0x0c
+#define DW_CFA_def_cfa_register             0x0d
+#define DW_CFA_def_cfa_offset               0x0e
+#define DW_CFA_def_cfa_expression           0x0f
+#define DW_CFA_expression                   0x10
+#define DW_CFA_offset_extended_sf           0x11
+#define DW_CFA_def_cfa_sf                   0x12
+#define DW_CFA_def_cfa_offset_sf            0x13
+#define DW_CFA_val_offset                   0x14
+#define DW_CFA_val_offset_sf                0x15
+#define DW_CFA_val_expression               0x16
+#define DW_CFA_lo_user                      0x1c
+#define DW_CFA_GNU_window_save              0x2d
+#define DW_CFA_GNU_args_size                0x2e
+#define DW_CFA_GNU_negative_offset_extended 0x2f
+#define DW_CFA_hi_user                      0x3f
+
+#define DW_EH_PE_FORM     0x07
+#define DW_EH_PE_native   0x00
+#define DW_EH_PE_leb128   0x01
+#define DW_EH_PE_data2    0x02
+#define DW_EH_PE_data4    0x03
+#define DW_EH_PE_data8    0x04
+#define DW_EH_PE_signed   0x08
+#define DW_EH_PE_ADJUST   0x70
+#define DW_EH_PE_abs      0x00
+#define DW_EH_PE_pcrel    0x10
+#define DW_EH_PE_textrel  0x20
+#define DW_EH_PE_datarel  0x30
+#define DW_EH_PE_funcrel  0x40
+#define DW_EH_PE_aligned  0x50
+#define DW_EH_PE_indirect 0x80
+#define DW_EH_PE_omit     0xff
+
+typedef unsigned long uleb128_t;
+typedef signed long sleb128_t;
+
+static struct unwind_table {
+	struct {
+		unsigned long pc;
+		unsigned long range;
+	} core, init;
+	const void *address;
+	unsigned long size;
+	const unsigned char *header;
+	unsigned long hdrsz;
+	struct unwind_table *link;
+	const char *name;
+} root_table;
+
+struct unwind_item {
+	enum item_location {
+		Nowhere,
+		Memory,
+		Register,
+		Value
+	} where;
+	uleb128_t value;
+};
+
+struct unwind_state {
+	uleb128_t loc, org;
+	const u8 *cieStart, *cieEnd;
+	uleb128_t codeAlign;
+	sleb128_t dataAlign;
+	struct cfa {
+		uleb128_t reg, offs;
+	} cfa;
+	struct unwind_item regs[ARRAY_SIZE(reg_info)];
+	unsigned stackDepth:8;
+	unsigned version:8;
+	const u8 *label;
+	const u8 *stack[MAX_STACK_DEPTH];
+};
+
+static const struct cfa badCFA = { ARRAY_SIZE(reg_info), 1 };
+
+static struct unwind_table *find_table(unsigned long pc)
+{
+	struct unwind_table *table;
+
+	for (table = &root_table; table; table = table->link)
+		if ((pc >= table->core.pc
+		     && pc < table->core.pc + table->core.range)
+		    || (pc >= table->init.pc
+			&& pc < table->init.pc + table->init.range))
+			break;
+
+	return table;
+}
+
+static unsigned long read_pointer(const u8 **pLoc,
+				  const void *end, signed ptrType);
+
+static void init_unwind_table(struct unwind_table *table, const char *name,
+			      const void *core_start, unsigned long core_size,
+			      const void *init_start, unsigned long init_size,
+			      const void *table_start, unsigned long table_size,
+			      const u8 *header_start, unsigned long header_size)
+{
+	const u8 *ptr = header_start + 4;
+	const u8 *end = header_start + header_size;
+
+	table->core.pc = (unsigned long)core_start;
+	table->core.range = core_size;
+	table->init.pc = (unsigned long)init_start;
+	table->init.range = init_size;
+	table->address = table_start;
+	table->size = table_size;
+
+	/* See if the linker provided table looks valid. */
+	if (header_size <= 4
+	    || header_start[0] != 1
+	    || (void *)read_pointer(&ptr, end, header_start[1]) != table_start
+	    || header_start[2] == DW_EH_PE_omit
+	    || read_pointer(&ptr, end, header_start[2]) <= 0
+	    || header_start[3] == DW_EH_PE_omit)
+		header_start = NULL;
+
+	table->hdrsz = header_size;
+	smp_wmb();
+	table->header = header_start;
+	table->link = NULL;
+	table->name = name;
+}
+
+void __init arc_unwind_init(void)
+{
+	init_unwind_table(&root_table, "kernel", _text, _end - _text, NULL, 0,
+			  __start_unwind, __end_unwind - __start_unwind,
+			  NULL, 0);
+	  /*__start_unwind_hdr, __end_unwind_hdr - __start_unwind_hdr);*/
+}
+
+static const u32 bad_cie, not_fde;
+static const u32 *cie_for_fde(const u32 *fde, const struct unwind_table *);
+static signed fde_pointer_type(const u32 *cie);
+
+struct eh_frame_hdr_table_entry {
+	unsigned long start, fde;
+};
+
+static int cmp_eh_frame_hdr_table_entries(const void *p1, const void *p2)
+{
+	const struct eh_frame_hdr_table_entry *e1 = p1;
+	const struct eh_frame_hdr_table_entry *e2 = p2;
+
+	return (e1->start > e2->start) - (e1->start < e2->start);
+}
+
+static void swap_eh_frame_hdr_table_entries(void *p1, void *p2, int size)
+{
+	struct eh_frame_hdr_table_entry *e1 = p1;
+	struct eh_frame_hdr_table_entry *e2 = p2;
+	unsigned long v;
+
+	v = e1->start;
+	e1->start = e2->start;
+	e2->start = v;
+	v = e1->fde;
+	e1->fde = e2->fde;
+	e2->fde = v;
+}
+
+static void __init setup_unwind_table(struct unwind_table *table,
+				      void *(*alloc) (unsigned long))
+{
+	const u8 *ptr;
+	unsigned long tableSize = table->size, hdrSize;
+	unsigned n;
+	const u32 *fde;
+	struct {
+		u8 version;
+		u8 eh_frame_ptr_enc;
+		u8 fde_count_enc;
+		u8 table_enc;
+		unsigned long eh_frame_ptr;
+		unsigned int fde_count;
+		struct eh_frame_hdr_table_entry table[];
+	} __attribute__ ((__packed__)) *header;
+
+	if (table->header)
+		return;
+
+	if (table->hdrsz)
+		pr_warn(".eh_frame_hdr for '%s' present but unusable\n",
+			table->name);
+
+	if (tableSize & (sizeof(*fde) - 1))
+		return;
+
+	for (fde = table->address, n = 0;
+	     tableSize > sizeof(*fde) && tableSize - sizeof(*fde) >= *fde;
+	     tableSize -= sizeof(*fde) + *fde, fde += 1 + *fde / sizeof(*fde)) {
+		const u32 *cie = cie_for_fde(fde, table);
+		signed ptrType;
+
+		if (cie == &not_fde)
+			continue;
+		if (cie == NULL || cie == &bad_cie)
+			return;
+		ptrType = fde_pointer_type(cie);
+		if (ptrType < 0)
+			return;
+
+		ptr = (const u8 *)(fde + 2);
+		if (!read_pointer(&ptr, (const u8 *)(fde + 1) + *fde,
+								ptrType)) {
+			/* FIXME_Rajesh We have 4 instances of null addresses
+			 * instead of the initial loc addr
+			 * return;
+			 */
+		}
+		++n;
+	}
+
+	if (tableSize || !n)
+		return;
+
+	hdrSize = 4 + sizeof(unsigned long) + sizeof(unsigned int)
+	    + 2 * n * sizeof(unsigned long);
+	header = alloc(hdrSize);
+	if (!header)
+		return;
+	header->version = 1;
+	header->eh_frame_ptr_enc = DW_EH_PE_abs | DW_EH_PE_native;
+	header->fde_count_enc = DW_EH_PE_abs | DW_EH_PE_data4;
+	header->table_enc = DW_EH_PE_abs | DW_EH_PE_native;
+	put_unaligned((unsigned long)table->address, &header->eh_frame_ptr);
+	BUILD_BUG_ON(offsetof(typeof(*header), fde_count)
+		     % __alignof(typeof(header->fde_count)));
+	header->fde_count = n;
+
+	BUILD_BUG_ON(offsetof(typeof(*header), table)
+		     % __alignof(typeof(*header->table)));
+	for (fde = table->address, tableSize = table->size, n = 0;
+	     tableSize;
+	     tableSize -= sizeof(*fde) + *fde, fde += 1 + *fde / sizeof(*fde)) {
+		/* const u32 *cie = fde + 1 - fde[1] / sizeof(*fde); */
+		const u32 *cie = (const u32 *)(fde[1]);
+
+		if (fde[1] == 0xffffffff)
+			continue;	/* this is a CIE */
+		ptr = (const u8 *)(fde + 2);
+		header->table[n].start = read_pointer(&ptr,
+						      (const u8 *)(fde + 1) +
+						      *fde,
+						      fde_pointer_type(cie));
+		header->table[n].fde = (unsigned long)fde;
+		++n;
+	}
+	WARN_ON(n != header->fde_count);
+
+	sort(header->table,
+	     n,
+	     sizeof(*header->table),
+	     cmp_eh_frame_hdr_table_entries, swap_eh_frame_hdr_table_entries);
+
+	table->hdrsz = hdrSize;
+	smp_wmb();
+	table->header = (const void *)header;
+}
+
+static void *__init balloc(unsigned long sz)
+{
+	return __alloc_bootmem_nopanic(sz,
+				       sizeof(unsigned int),
+				       __pa(MAX_DMA_ADDRESS));
+}
+
+void __init arc_unwind_setup(void)
+{
+	setup_unwind_table(&root_table, balloc);
+}
+
+#ifdef CONFIG_MODULES
+
+static struct unwind_table *last_table;
+
+/* Must be called with module_mutex held. */
+void *unwind_add_table(struct module *module, const void *table_start,
+		       unsigned long table_size)
+{
+	struct unwind_table *table;
+
+	if (table_size <= 0)
+		return NULL;
+
+	table = kmalloc(sizeof(*table), GFP_KERNEL);
+	if (!table)
+		return NULL;
+
+	init_unwind_table(table, module->name,
+			  module->module_core, module->core_size,
+			  module->module_init, module->init_size,
+			  table_start, table_size,
+			  NULL, 0);
+
+#ifdef UNWIND_DEBUG
+	unw_debug("Table added for [%s] %lx %lx\n",
+		module->name, table->core.pc, table->core.range);
+#endif
+	if (last_table)
+		last_table->link = table;
+	else
+		root_table.link = table;
+	last_table = table;
+
+	return table;
+}
+
+struct unlink_table_info {
+	struct unwind_table *table;
+	int init_only;
+};
+
+static int unlink_table(void *arg)
+{
+	struct unlink_table_info *info = arg;
+	struct unwind_table *table = info->table, *prev;
+
+	for (prev = &root_table; prev->link && prev->link != table;
+	     prev = prev->link)
+		;
+
+	if (prev->link) {
+		if (info->init_only) {
+			table->init.pc = 0;
+			table->init.range = 0;
+			info->table = NULL;
+		} else {
+			prev->link = table->link;
+			if (!prev->link)
+				last_table = prev;
+		}
+	} else
+		info->table = NULL;
+
+	return 0;
+}
+
+/* Must be called with module_mutex held. */
+void unwind_remove_table(void *handle, int init_only)
+{
+	struct unwind_table *table = handle;
+	struct unlink_table_info info;
+
+	if (!table || table == &root_table)
+		return;
+
+	if (init_only && table == last_table) {
+		table->init.pc = 0;
+		table->init.range = 0;
+		return;
+	}
+
+	info.table = table;
+	info.init_only = init_only;
+
+	unlink_table(&info); /* XXX: SMP */
+	kfree(table);
+}
+
+#endif /* CONFIG_MODULES */
+
+static uleb128_t get_uleb128(const u8 **pcur, const u8 *end)
+{
+	const u8 *cur = *pcur;
+	uleb128_t value;
+	unsigned shift;
+
+	for (shift = 0, value = 0; cur < end; shift += 7) {
+		if (shift + 7 > 8 * sizeof(value)
+		    && (*cur & 0x7fU) >= (1U << (8 * sizeof(value) - shift))) {
+			cur = end + 1;
+			break;
+		}
+		value |= (uleb128_t) (*cur & 0x7f) << shift;
+		if (!(*cur++ & 0x80))
+			break;
+	}
+	*pcur = cur;
+
+	return value;
+}
+
+static sleb128_t get_sleb128(const u8 **pcur, const u8 *end)
+{
+	const u8 *cur = *pcur;
+	sleb128_t value;
+	unsigned shift;
+
+	for (shift = 0, value = 0; cur < end; shift += 7) {
+		if (shift + 7 > 8 * sizeof(value)
+		    && (*cur & 0x7fU) >= (1U << (8 * sizeof(value) - shift))) {
+			cur = end + 1;
+			break;
+		}
+		value |= (sleb128_t) (*cur & 0x7f) << shift;
+		if (!(*cur & 0x80)) {
+			value |= -(*cur++ & 0x40) << shift;
+			break;
+		}
+	}
+	*pcur = cur;
+
+	return value;
+}
+
+static const u32 *cie_for_fde(const u32 *fde, const struct unwind_table *table)
+{
+	const u32 *cie;
+
+	if (!*fde || (*fde & (sizeof(*fde) - 1)))
+		return &bad_cie;
+
+	if (fde[1] == 0xffffffff)
+		return &not_fde;	/* this is a CIE */
+
+	if ((fde[1] & (sizeof(*fde) - 1)))
+/* || fde[1] > (unsigned long)(fde + 1) - (unsigned long)table->address) */
+		return NULL;	/* this is not a valid FDE */
+
+	/* cie = fde + 1 - fde[1] / sizeof(*fde); */
+	cie = (u32 *) fde[1];
+
+	if (*cie <= sizeof(*cie) + 4 || *cie >= fde[1] - sizeof(*fde)
+	    || (*cie & (sizeof(*cie) - 1))
+	    || (cie[1] != 0xffffffff))
+		return NULL;	/* this is not a (valid) CIE */
+	return cie;
+}
+
+static unsigned long read_pointer(const u8 **pLoc, const void *end,
+				  signed ptrType)
+{
+	unsigned long value = 0;
+	union {
+		const u8 *p8;
+		const u16 *p16u;
+		const s16 *p16s;
+		const u32 *p32u;
+		const s32 *p32s;
+		const unsigned long *pul;
+	} ptr;
+
+	if (ptrType < 0 || ptrType == DW_EH_PE_omit)
+		return 0;
+	ptr.p8 = *pLoc;
+	switch (ptrType & DW_EH_PE_FORM) {
+	case DW_EH_PE_data2:
+		if (end < (const void *)(ptr.p16u + 1))
+			return 0;
+		if (ptrType & DW_EH_PE_signed)
+			value = get_unaligned((u16 *) ptr.p16s++);
+		else
+			value = get_unaligned((u16 *) ptr.p16u++);
+		break;
+	case DW_EH_PE_data4:
+#ifdef CONFIG_64BIT
+		if (end < (const void *)(ptr.p32u + 1))
+			return 0;
+		if (ptrType & DW_EH_PE_signed)
+			value = get_unaligned(ptr.p32s++);
+		else
+			value = get_unaligned(ptr.p32u++);
+		break;
+	case DW_EH_PE_data8:
+		BUILD_BUG_ON(sizeof(u64) != sizeof(value));
+#else
+		BUILD_BUG_ON(sizeof(u32) != sizeof(value));
+#endif
+	case DW_EH_PE_native:
+		if (end < (const void *)(ptr.pul + 1))
+			return 0;
+		value = get_unaligned((unsigned long *)ptr.pul++);
+		break;
+	case DW_EH_PE_leb128:
+		BUILD_BUG_ON(sizeof(uleb128_t) > sizeof(value));
+		value = ptrType & DW_EH_PE_signed ? get_sleb128(&ptr.p8, end)
+		    : get_uleb128(&ptr.p8, end);
+		if ((const void *)ptr.p8 > end)
+			return 0;
+		break;
+	default:
+		return 0;
+	}
+	switch (ptrType & DW_EH_PE_ADJUST) {
+	case DW_EH_PE_abs:
+		break;
+	case DW_EH_PE_pcrel:
+		value += (unsigned long)*pLoc;
+		break;
+	default:
+		return 0;
+	}
+	if ((ptrType & DW_EH_PE_indirect)
+	    && __get_user(value, (unsigned long __user *)value))
+		return 0;
+	*pLoc = ptr.p8;
+
+	return value;
+}
+
+static signed fde_pointer_type(const u32 *cie)
+{
+	const u8 *ptr = (const u8 *)(cie + 2);
+	unsigned version = *ptr;
+
+	if (version != 1)
+		return -1;	/* unsupported */
+
+	if (*++ptr) {
+		const char *aug;
+		const u8 *end = (const u8 *)(cie + 1) + *cie;
+		uleb128_t len;
+
+		/* check if augmentation size is first (and thus present) */
+		if (*ptr != 'z')
+			return -1;
+
+		/* check if augmentation string is nul-terminated */
+		aug = (const void *)ptr;
+		ptr = memchr(aug, 0, end - ptr);
+		if (ptr == NULL)
+			return -1;
+
+		++ptr;		/* skip terminator */
+		get_uleb128(&ptr, end);	/* skip code alignment */
+		get_sleb128(&ptr, end);	/* skip data alignment */
+		/* skip return address column */
+		version <= 1 ? (void) ++ptr : (void)get_uleb128(&ptr, end);
+		len = get_uleb128(&ptr, end);	/* augmentation length */
+
+		if (ptr + len < ptr || ptr + len > end)
+			return -1;
+
+		end = ptr + len;
+		while (*++aug) {
+			if (ptr >= end)
+				return -1;
+			switch (*aug) {
+			case 'L':
+				++ptr;
+				break;
+			case 'P':{
+					signed ptrType = *ptr++;
+
+					if (!read_pointer(&ptr, end, ptrType)
+					    || ptr > end)
+						return -1;
+				}
+				break;
+			case 'R':
+				return *ptr;
+			default:
+				return -1;
+			}
+		}
+	}
+	return DW_EH_PE_native | DW_EH_PE_abs;
+}
+
+static int advance_loc(unsigned long delta, struct unwind_state *state)
+{
+	state->loc += delta * state->codeAlign;
+
+	/* FIXME_Rajesh: Probably we are defining for the initial range as well;
+	   return delta > 0;
+	 */
+	unw_debug("delta %3lu => loc 0x%lx: ", delta, state->loc);
+	return 1;
+}
+
+static void set_rule(uleb128_t reg, enum item_location where, uleb128_t value,
+		     struct unwind_state *state)
+{
+	if (reg < ARRAY_SIZE(state->regs)) {
+		state->regs[reg].where = where;
+		state->regs[reg].value = value;
+
+#ifdef UNWIND_DEBUG
+		unw_debug("r%lu: ", reg);
+		switch (where) {
+		case Nowhere:
+			unw_debug("s ");
+			break;
+		case Memory:
+			unw_debug("c(%lu) ", value);
+			break;
+		case Register:
+			unw_debug("r(%lu) ", value);
+			break;
+		case Value:
+			unw_debug("v(%lu) ", value);
+			break;
+		default:
+			break;
+		}
+#endif
+	}
+}
+
+static int processCFI(const u8 *start, const u8 *end, unsigned long targetLoc,
+		      signed ptrType, struct unwind_state *state)
+{
+	union {
+		const u8 *p8;
+		const u16 *p16;
+		const u32 *p32;
+	} ptr;
+	int result = 1;
+	u8 opcode;
+
+	if (start != state->cieStart) {
+		state->loc = state->org;
+		result =
+		    processCFI(state->cieStart, state->cieEnd, 0, ptrType,
+			       state);
+		if (targetLoc == 0 && state->label == NULL)
+			return result;
+	}
+	for (ptr.p8 = start; result && ptr.p8 < end;) {
+		switch (*ptr.p8 >> 6) {
+			uleb128_t value;
+
+		case 0:
+			opcode = *ptr.p8++;
+
+			switch (opcode) {
+			case DW_CFA_nop:
+				unw_debug("cfa nop ");
+				break;
+			case DW_CFA_set_loc:
+				state->loc = read_pointer(&ptr.p8, end,
+							  ptrType);
+				if (state->loc == 0)
+					result = 0;
+				unw_debug("cfa_set_loc: 0x%lx ", state->loc);
+				break;
+			case DW_CFA_advance_loc1:
+				unw_debug("\ncfa advance loc1:");
+				result = ptr.p8 < end
+				    && advance_loc(*ptr.p8++, state);
+				break;
+			case DW_CFA_advance_loc2:
+				value = *ptr.p8++;
+				value += *ptr.p8++ << 8;
+				unw_debug("\ncfa advance loc2:");
+				result = ptr.p8 <= end + 2
+				    /* && advance_loc(*ptr.p16++, state); */
+				    && advance_loc(value, state);
+				break;
+			case DW_CFA_advance_loc4:
+				unw_debug("\ncfa advance loc4:");
+				result = ptr.p8 <= end + 4
+				    && advance_loc(*ptr.p32++, state);
+				break;
+			case DW_CFA_offset_extended:
+				value = get_uleb128(&ptr.p8, end);
+				unw_debug("cfa_offset_extended: ");
+				set_rule(value, Memory,
+					 get_uleb128(&ptr.p8, end), state);
+				break;
+			case DW_CFA_val_offset:
+				value = get_uleb128(&ptr.p8, end);
+				set_rule(value, Value,
+					 get_uleb128(&ptr.p8, end), state);
+				break;
+			case DW_CFA_offset_extended_sf:
+				value = get_uleb128(&ptr.p8, end);
+				set_rule(value, Memory,
+					 get_sleb128(&ptr.p8, end), state);
+				break;
+			case DW_CFA_val_offset_sf:
+				value = get_uleb128(&ptr.p8, end);
+				set_rule(value, Value,
+					 get_sleb128(&ptr.p8, end), state);
+				break;
+			case DW_CFA_restore_extended:
+				unw_debug("cfa_restore_extended: ");
+			case DW_CFA_undefined:
+				unw_debug("cfa_undefined: ");
+			case DW_CFA_same_value:
+				unw_debug("cfa_same_value: ");
+				set_rule(get_uleb128(&ptr.p8, end), Nowhere, 0,
+					 state);
+				break;
+			case DW_CFA_register:
+				unw_debug("cfa_register: ");
+				value = get_uleb128(&ptr.p8, end);
+				set_rule(value,
+					 Register,
+					 get_uleb128(&ptr.p8, end), state);
+				break;
+			case DW_CFA_remember_state:
+				unw_debug("cfa_remember_state: ");
+				if (ptr.p8 == state->label) {
+					state->label = NULL;
+					return 1;
+				}
+				if (state->stackDepth >= MAX_STACK_DEPTH)
+					return 0;
+				state->stack[state->stackDepth++] = ptr.p8;
+				break;
+			case DW_CFA_restore_state:
+				unw_debug("cfa_restore_state: ");
+				if (state->stackDepth) {
+					const uleb128_t loc = state->loc;
+					const u8 *label = state->label;
+
+					state->label =
+					    state->stack[state->stackDepth - 1];
+					memcpy(&state->cfa, &badCFA,
+					       sizeof(state->cfa));
+					memset(state->regs, 0,
+					       sizeof(state->regs));
+					state->stackDepth = 0;
+					result =
+					    processCFI(start, end, 0, ptrType,
+						       state);
+					state->loc = loc;
+					state->label = label;
+				} else
+					return 0;
+				break;
+			case DW_CFA_def_cfa:
+				state->cfa.reg = get_uleb128(&ptr.p8, end);
+				unw_debug("cfa_def_cfa: r%lu ", state->cfa.reg);
+				/*nobreak*/
+			case DW_CFA_def_cfa_offset:
+				state->cfa.offs = get_uleb128(&ptr.p8, end);
+				unw_debug("cfa_def_cfa_offset: 0x%lx ",
+					  state->cfa.offs);
+				break;
+			case DW_CFA_def_cfa_sf:
+				state->cfa.reg = get_uleb128(&ptr.p8, end);
+				/*nobreak */
+			case DW_CFA_def_cfa_offset_sf:
+				state->cfa.offs = get_sleb128(&ptr.p8, end)
+				    * state->dataAlign;
+				break;
+			case DW_CFA_def_cfa_register:
+				unw_debug("cfa_def_cfa_regsiter: ");
+				state->cfa.reg = get_uleb128(&ptr.p8, end);
+				break;
+				/*todo case DW_CFA_def_cfa_expression: */
+				/*todo case DW_CFA_expression: */
+				/*todo case DW_CFA_val_expression: */
+			case DW_CFA_GNU_args_size:
+				get_uleb128(&ptr.p8, end);
+				break;
+			case DW_CFA_GNU_negative_offset_extended:
+				value = get_uleb128(&ptr.p8, end);
+				set_rule(value,
+					 Memory,
+					 (uleb128_t) 0 - get_uleb128(&ptr.p8,
+								     end),
+					 state);
+				break;
+			case DW_CFA_GNU_window_save:
+			default:
+				unw_debug("UNKNOW OPCODE 0x%x\n", opcode);
+				result = 0;
+				break;
+			}
+			break;
+		case 1:
+			unw_debug("\ncfa_adv_loc: ");
+			result = advance_loc(*ptr.p8++ & 0x3f, state);
+			break;
+		case 2:
+			unw_debug("cfa_offset: ");
+			value = *ptr.p8++ & 0x3f;
+			set_rule(value, Memory, get_uleb128(&ptr.p8, end),
+				 state);
+			break;
+		case 3:
+			unw_debug("cfa_restore: ");
+			set_rule(*ptr.p8++ & 0x3f, Nowhere, 0, state);
+			break;
+		}
+
+		if (ptr.p8 > end)
+			result = 0;
+		if (result && targetLoc != 0 && targetLoc < state->loc)
+			return 1;
+	}
+
+	return result && ptr.p8 == end && (targetLoc == 0 || (
+		/*todo While in theory this should apply, gcc in practice omits
+		  everything past the function prolog, and hence the location
+		  never reaches the end of the function.
+		targetLoc < state->loc && */  state->label == NULL));
+}
+
+/* Unwind to previous to frame.  Returns 0 if successful, negative
+ * number in case of an error. */
+int arc_unwind(struct unwind_frame_info *frame)
+{
+#define FRAME_REG(r, t) (((t *)frame)[reg_info[r].offs])
+	const u32 *fde = NULL, *cie = NULL;
+	const u8 *ptr = NULL, *end = NULL;
+	unsigned long pc = UNW_PC(frame) - frame->call_frame;
+	unsigned long startLoc = 0, endLoc = 0, cfa;
+	unsigned i;
+	signed ptrType = -1;
+	uleb128_t retAddrReg = 0;
+	const struct unwind_table *table;
+	struct unwind_state state;
+	unsigned long *fptr;
+	unsigned long addr;
+
+	unw_debug("\n\nUNWIND FRAME:\n");
+	unw_debug("PC: 0x%lx BLINK: 0x%lx, SP: 0x%lx, FP: 0x%x\n",
+		  UNW_PC(frame), UNW_BLINK(frame), UNW_SP(frame),
+		  UNW_FP(frame));
+
+	if (UNW_PC(frame) == 0)
+		return -EINVAL;
+
+#ifdef UNWIND_DEBUG
+	{
+		unsigned long *sptr = (unsigned long *)UNW_SP(frame);
+		unw_debug("\nStack Dump:\n");
+		for (i = 0; i < 20; i++, sptr++)
+			unw_debug("0x%p:  0x%lx\n", sptr, *sptr);
+		unw_debug("\n");
+	}
+#endif
+
+	table = find_table(pc);
+	if (table != NULL
+	    && !(table->size & (sizeof(*fde) - 1))) {
+		const u8 *hdr = table->header;
+		unsigned long tableSize;
+
+		smp_rmb();
+		if (hdr && hdr[0] == 1) {
+			switch (hdr[3] & DW_EH_PE_FORM) {
+			case DW_EH_PE_native:
+				tableSize = sizeof(unsigned long);
+				break;
+			case DW_EH_PE_data2:
+				tableSize = 2;
+				break;
+			case DW_EH_PE_data4:
+				tableSize = 4;
+				break;
+			case DW_EH_PE_data8:
+				tableSize = 8;
+				break;
+			default:
+				tableSize = 0;
+				break;
+			}
+			ptr = hdr + 4;
+			end = hdr + table->hdrsz;
+			if (tableSize && read_pointer(&ptr, end, hdr[1])
+			    == (unsigned long)table->address
+			    && (i = read_pointer(&ptr, end, hdr[2])) > 0
+			    && i == (end - ptr) / (2 * tableSize)
+			    && !((end - ptr) % (2 * tableSize))) {
+				do {
+					const u8 *cur =
+					    ptr + (i / 2) * (2 * tableSize);
+
+					startLoc = read_pointer(&cur,
+								cur + tableSize,
+								hdr[3]);
+					if (pc < startLoc)
+						i /= 2;
+					else {
+						ptr = cur - tableSize;
+						i = (i + 1) / 2;
+					}
+				} while (startLoc && i > 1);
+				if (i == 1
+				    && (startLoc = read_pointer(&ptr,
+								ptr + tableSize,
+								hdr[3])) != 0
+				    && pc >= startLoc)
+					fde = (void *)read_pointer(&ptr,
+								   ptr +
+								   tableSize,
+								   hdr[3]);
+			}
+		}
+
+		if (fde != NULL) {
+			cie = cie_for_fde(fde, table);
+			ptr = (const u8 *)(fde + 2);
+			if (cie != NULL
+			    && cie != &bad_cie
+			    && cie != &not_fde
+			    && (ptrType = fde_pointer_type(cie)) >= 0
+			    && read_pointer(&ptr,
+					    (const u8 *)(fde + 1) + *fde,
+					    ptrType) == startLoc) {
+				if (!(ptrType & DW_EH_PE_indirect))
+					ptrType &=
+					    DW_EH_PE_FORM | DW_EH_PE_signed;
+				endLoc =
+				    startLoc + read_pointer(&ptr,
+							    (const u8 *)(fde +
+									 1) +
+							    *fde, ptrType);
+				if (pc >= endLoc)
+					fde = NULL;
+			} else
+				fde = NULL;
+		}
+		if (fde == NULL) {
+			for (fde = table->address, tableSize = table->size;
+			     cie = NULL, tableSize > sizeof(*fde)
+			     && tableSize - sizeof(*fde) >= *fde;
+			     tableSize -= sizeof(*fde) + *fde,
+			     fde += 1 + *fde / sizeof(*fde)) {
+				cie = cie_for_fde(fde, table);
+				if (cie == &bad_cie) {
+					cie = NULL;
+					break;
+				}
+				if (cie == NULL
+				    || cie == &not_fde
+				    || (ptrType = fde_pointer_type(cie)) < 0)
+					continue;
+				ptr = (const u8 *)(fde + 2);
+				startLoc = read_pointer(&ptr,
+							(const u8 *)(fde + 1) +
+							*fde, ptrType);
+				if (!startLoc)
+					continue;
+				if (!(ptrType & DW_EH_PE_indirect))
+					ptrType &=
+					    DW_EH_PE_FORM | DW_EH_PE_signed;
+				endLoc =
+				    startLoc + read_pointer(&ptr,
+							    (const u8 *)(fde +
+									 1) +
+							    *fde, ptrType);
+				if (pc >= startLoc && pc < endLoc)
+					break;
+			}
+		}
+	}
+	if (cie != NULL) {
+		memset(&state, 0, sizeof(state));
+		state.cieEnd = ptr;	/* keep here temporarily */
+		ptr = (const u8 *)(cie + 2);
+		end = (const u8 *)(cie + 1) + *cie;
+		frame->call_frame = 1;
+		if ((state.version = *ptr) != 1)
+			cie = NULL;	/* unsupported version */
+		else if (*++ptr) {
+			/* check if augmentation size is first (thus present) */
+			if (*ptr == 'z') {
+				while (++ptr < end && *ptr) {
+					switch (*ptr) {
+					/* chk for ignorable or already handled
+					 * nul-terminated augmentation string */
+					case 'L':
+					case 'P':
+					case 'R':
+						continue;
+					case 'S':
+						frame->call_frame = 0;
+						continue;
+					default:
+						break;
+					}
+					break;
+				}
+			}
+			if (ptr >= end || *ptr)
+				cie = NULL;
+		}
+		++ptr;
+	}
+	if (cie != NULL) {
+		/* get code aligment factor */
+		state.codeAlign = get_uleb128(&ptr, end);
+		/* get data aligment factor */
+		state.dataAlign = get_sleb128(&ptr, end);
+		if (state.codeAlign == 0 || state.dataAlign == 0 || ptr >= end)
+			cie = NULL;
+		else {
+			retAddrReg =
+			    state.version <= 1 ? *ptr++ : get_uleb128(&ptr,
+								      end);
+			unw_debug("CIE Frame Info:\n");
+			unw_debug("return Address register 0x%lx\n",
+				  retAddrReg);
+			unw_debug("data Align: %ld\n", state.dataAlign);
+			unw_debug("code Align: %lu\n", state.codeAlign);
+			/* skip augmentation */
+			if (((const char *)(cie + 2))[1] == 'z') {
+				uleb128_t augSize = get_uleb128(&ptr, end);
+
+				ptr += augSize;
+			}
+			if (ptr > end || retAddrReg >= ARRAY_SIZE(reg_info)
+			    || REG_INVALID(retAddrReg)
+			    || reg_info[retAddrReg].width !=
+			    sizeof(unsigned long))
+				cie = NULL;
+		}
+	}
+	if (cie != NULL) {
+		state.cieStart = ptr;
+		ptr = state.cieEnd;
+		state.cieEnd = end;
+		end = (const u8 *)(fde + 1) + *fde;
+		/* skip augmentation */
+		if (((const char *)(cie + 2))[1] == 'z') {
+			uleb128_t augSize = get_uleb128(&ptr, end);
+
+			if ((ptr += augSize) > end)
+				fde = NULL;
+		}
+	}
+	if (cie == NULL || fde == NULL) {
+#ifdef CONFIG_FRAME_POINTER
+		unsigned long top, bottom;
+
+		top = STACK_TOP_UNW(frame->task);
+		bottom = STACK_BOTTOM_UNW(frame->task);
+#if FRAME_RETADDR_OFFSET < 0
+		if (UNW_SP(frame) < top && UNW_FP(frame) <= UNW_SP(frame)
+		    && bottom < UNW_FP(frame)
+#else
+		if (UNW_SP(frame) > top && UNW_FP(frame) >= UNW_SP(frame)
+		    && bottom > UNW_FP(frame)
+#endif
+		    && !((UNW_SP(frame) | UNW_FP(frame))
+			 & (sizeof(unsigned long) - 1))) {
+			unsigned long link;
+
+			if (!__get_user(link, (unsigned long *)
+					(UNW_FP(frame) + FRAME_LINK_OFFSET))
+#if FRAME_RETADDR_OFFSET < 0
+			    && link > bottom && link < UNW_FP(frame)
+#else
+			    && link > UNW_FP(frame) && link < bottom
+#endif
+			    && !(link & (sizeof(link) - 1))
+			    && !__get_user(UNW_PC(frame),
+					   (unsigned long *)(UNW_FP(frame)
+						+ FRAME_RETADDR_OFFSET)))
+			{
+				UNW_SP(frame) =
+				    UNW_FP(frame) + FRAME_RETADDR_OFFSET
+#if FRAME_RETADDR_OFFSET < 0
+				    -
+#else
+				    +
+#endif
+				    sizeof(UNW_PC(frame));
+				UNW_FP(frame) = link;
+				return 0;
+			}
+		}
+#endif
+		return -ENXIO;
+	}
+	state.org = startLoc;
+	memcpy(&state.cfa, &badCFA, sizeof(state.cfa));
+
+	unw_debug("\nProcess instructions\n");
+
+	/* process instructions
+	 * For ARC, we optimize by having blink(retAddrReg) with
+	 * the sameValue in the leaf function, so we should not check
+	 * state.regs[retAddrReg].where == Nowhere
+	 */
+	if (!processCFI(ptr, end, pc, ptrType, &state)
+	    || state.loc > endLoc
+/*	   || state.regs[retAddrReg].where == Nowhere */
+	    || state.cfa.reg >= ARRAY_SIZE(reg_info)
+	    || reg_info[state.cfa.reg].width != sizeof(unsigned long)
+	    || state.cfa.offs % sizeof(unsigned long))
+		return -EIO;
+
+#ifdef UNWIND_DEBUG
+	unw_debug("\n");
+
+	unw_debug("\nRegister State Based on the rules parsed from FDE:\n");
+	for (i = 0; i < ARRAY_SIZE(state.regs); ++i) {
+
+		if (REG_INVALID(i))
+			continue;
+
+		switch (state.regs[i].where) {
+		case Nowhere:
+			break;
+		case Memory:
+			unw_debug(" r%d: c(%lu),", i, state.regs[i].value);
+			break;
+		case Register:
+			unw_debug(" r%d: r(%lu),", i, state.regs[i].value);
+			break;
+		case Value:
+			unw_debug(" r%d: v(%lu),", i, state.regs[i].value);
+			break;
+		}
+	}
+
+	unw_debug("\n");
+#endif
+
+	/* update frame */
+#ifndef CONFIG_AS_CFI_SIGNAL_FRAME
+	if (frame->call_frame
+	    && !UNW_DEFAULT_RA(state.regs[retAddrReg], state.dataAlign))
+		frame->call_frame = 0;
+#endif
+	cfa = FRAME_REG(state.cfa.reg, unsigned long) + state.cfa.offs;
+	startLoc = min_t(unsigned long, UNW_SP(frame), cfa);
+	endLoc = max_t(unsigned long, UNW_SP(frame), cfa);
+	if (STACK_LIMIT(startLoc) != STACK_LIMIT(endLoc)) {
+		startLoc = min(STACK_LIMIT(cfa), cfa);
+		endLoc = max(STACK_LIMIT(cfa), cfa);
+	}
+
+	unw_debug("\nCFA reg: 0x%lx, offset: 0x%lx =>  0x%lx\n",
+		  state.cfa.reg, state.cfa.offs, cfa);
+
+	for (i = 0; i < ARRAY_SIZE(state.regs); ++i) {
+		if (REG_INVALID(i)) {
+			if (state.regs[i].where == Nowhere)
+				continue;
+			return -EIO;
+		}
+		switch (state.regs[i].where) {
+		default:
+			break;
+		case Register:
+			if (state.regs[i].value >= ARRAY_SIZE(reg_info)
+			    || REG_INVALID(state.regs[i].value)
+			    || reg_info[i].width >
+			    reg_info[state.regs[i].value].width)
+				return -EIO;
+			switch (reg_info[state.regs[i].value].width) {
+			case sizeof(u8):
+				state.regs[i].value =
+				FRAME_REG(state.regs[i].value, const u8);
+				break;
+			case sizeof(u16):
+				state.regs[i].value =
+				FRAME_REG(state.regs[i].value, const u16);
+				break;
+			case sizeof(u32):
+				state.regs[i].value =
+				FRAME_REG(state.regs[i].value, const u32);
+				break;
+#ifdef CONFIG_64BIT
+			case sizeof(u64):
+				state.regs[i].value =
+				FRAME_REG(state.regs[i].value, const u64);
+				break;
+#endif
+			default:
+				return -EIO;
+			}
+			break;
+		}
+	}
+
+	unw_debug("\nRegister state after evaluation with realtime Stack:\n");
+	fptr = (unsigned long *)(&frame->regs);
+	for (i = 0; i < ARRAY_SIZE(state.regs); ++i, fptr++) {
+
+		if (REG_INVALID(i))
+			continue;
+		switch (state.regs[i].where) {
+		case Nowhere:
+			if (reg_info[i].width != sizeof(UNW_SP(frame))
+			    || &FRAME_REG(i, __typeof__(UNW_SP(frame)))
+			    != &UNW_SP(frame))
+				continue;
+			UNW_SP(frame) = cfa;
+			break;
+		case Register:
+			switch (reg_info[i].width) {
+			case sizeof(u8):
+				FRAME_REG(i, u8) = state.regs[i].value;
+				break;
+			case sizeof(u16):
+				FRAME_REG(i, u16) = state.regs[i].value;
+				break;
+			case sizeof(u32):
+				FRAME_REG(i, u32) = state.regs[i].value;
+				break;
+#ifdef CONFIG_64BIT
+			case sizeof(u64):
+				FRAME_REG(i, u64) = state.regs[i].value;
+				break;
+#endif
+			default:
+				return -EIO;
+			}
+			break;
+		case Value:
+			if (reg_info[i].width != sizeof(unsigned long))
+				return -EIO;
+			FRAME_REG(i, unsigned long) = cfa + state.regs[i].value
+			    * state.dataAlign;
+			break;
+		case Memory:
+			addr = cfa + state.regs[i].value * state.dataAlign;
+
+			if ((state.regs[i].value * state.dataAlign)
+			    % sizeof(unsigned long)
+			    || addr < startLoc
+			    || addr + sizeof(unsigned long) < addr
+			    || addr + sizeof(unsigned long) > endLoc)
+					return -EIO;
+
+			switch (reg_info[i].width) {
+			case sizeof(u8):
+				__get_user(FRAME_REG(i, u8),
+					   (u8 __user *)addr);
+				break;
+			case sizeof(u16):
+				__get_user(FRAME_REG(i, u16),
+					   (u16 __user *)addr);
+				break;
+			case sizeof(u32):
+				__get_user(FRAME_REG(i, u32),
+					   (u32 __user *)addr);
+				break;
+#ifdef CONFIG_64BIT
+			case sizeof(u64):
+				__get_user(FRAME_REG(i, u64),
+					   (u64 __user *)addr);
+				break;
+#endif
+			default:
+				return -EIO;
+			}
+
+			break;
+		}
+		unw_debug("r%d: 0x%lx ", i, *fptr);
+	}
+
+	return 0;
+#undef FRAME_REG
+}
+EXPORT_SYMBOL(arc_unwind);
diff --git a/arch/arc/kernel/vmlinux.lds.S b/arch/arc/kernel/vmlinux.lds.S
new file mode 100644
index 000000000000..d3c92f52d444
--- /dev/null
+++ b/arch/arc/kernel/vmlinux.lds.S
@@ -0,0 +1,163 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <asm-generic/vmlinux.lds.h>
+#include <asm/cache.h>
+#include <asm/page.h>
+#include <asm/thread_info.h>
+
+OUTPUT_ARCH(arc)
+ENTRY(_stext)
+
+#ifdef CONFIG_CPU_BIG_ENDIAN
+jiffies = jiffies_64 + 4;
+#else
+jiffies = jiffies_64;
+#endif
+
+SECTIONS
+{
+	/*
+	 * ICCM starts at 0x8000_0000. So if kernel is relocated to some other
+	 * address, make sure peripheral at 0x8z doesn't clash with ICCM
+	 * Essentially vector is also in ICCM.
+	 */
+
+	. = CONFIG_LINUX_LINK_BASE;
+
+	_int_vec_base_lds = .;
+	.vector : {
+		*(.vector)
+		. = ALIGN(PAGE_SIZE);
+	}
+
+#ifdef CONFIG_ARC_HAS_ICCM
+	.text.arcfp : {
+		*(.text.arcfp)
+		. = ALIGN(CONFIG_ARC_ICCM_SZ * 1024);
+	}
+#endif
+
+	/*
+	 * The reason for having a seperate subsection .init.ramfs is to
+	 * prevent objump from including it in kernel dumps
+	 *
+	 * Reason for having .init.ramfs above .init is to make sure that the
+	 * binary blob is tucked away to one side, reducing the displacement
+	 * between .init.text and .text, avoiding any possible relocation
+	 * errors because of calls from .init.text to .text
+	 * Yes such calls do exist. e.g.
+	 *	decompress_inflate.c:gunzip( ) -> zlib_inflate_workspace( )
+	 */
+
+	__init_begin = .;
+
+	.init.ramfs : { INIT_RAM_FS }
+
+	. = ALIGN(PAGE_SIZE);
+	_stext = .;
+
+	HEAD_TEXT_SECTION
+	INIT_TEXT_SECTION(L1_CACHE_BYTES)
+
+	/* INIT_DATA_SECTION open-coded: special INIT_RAM_FS handling */
+	.init.data : {
+		INIT_DATA
+		INIT_SETUP(L1_CACHE_BYTES)
+		INIT_CALLS
+		CON_INITCALL
+		SECURITY_INITCALL
+	}
+
+	.init.arch.info : {
+		__arch_info_begin = .;
+		*(.arch.info.init)
+		__arch_info_end = .;
+	}
+
+	PERCPU_SECTION(L1_CACHE_BYTES)
+
+	/*
+	 * .exit.text is discard at runtime, not link time, to deal with
+	 * references from .debug_frame
+	 * It will be init freed, being inside [__init_start : __init_end]
+	 */
+	.exit.text : { EXIT_TEXT }
+	.exit.data : { EXIT_DATA }
+
+	. = ALIGN(PAGE_SIZE);
+	__init_end = .;
+
+	.text : {
+		_text = .;
+		TEXT_TEXT
+		SCHED_TEXT
+		LOCK_TEXT
+		KPROBES_TEXT
+		*(.fixup)
+		*(.gnu.warning)
+	}
+	EXCEPTION_TABLE(L1_CACHE_BYTES)
+	_etext = .;
+
+	_sdata = .;
+	RO_DATA_SECTION(PAGE_SIZE)
+
+	/*
+	 * 1. this is .data essentially
+	 * 2. THREAD_SIZE for init.task, must be kernel-stk sz aligned
+	 */
+	RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
+
+	_edata = .;
+
+	BSS_SECTION(0, 0, 0)
+
+#ifdef CONFIG_ARC_DW2_UNWIND
+	. = ALIGN(PAGE_SIZE);
+	.debug_frame  : {
+		__start_unwind = .;
+		*(.debug_frame)
+		__end_unwind = .;
+	}
+#else
+	/DISCARD/ : {	*(.debug_frame) }
+#endif
+
+	NOTES
+
+	. = ALIGN(PAGE_SIZE);
+	_end = . ;
+
+	STABS_DEBUG
+	DISCARDS
+
+	.arcextmap 0 : {
+		*(.gnu.linkonce.arcextmap.*)
+		*(.arcextmap.*)
+	}
+
+	/* open-coded because we need .debug_frame seperately for unwinding */
+	.debug_aranges 0 : { *(.debug_aranges) }
+	.debug_pubnames 0 : { *(.debug_pubnames) }
+	.debug_info 0 : { *(.debug_info) }
+	.debug_abbrev 0 : { *(.debug_abbrev) }
+	.debug_line 0 : { *(.debug_line) }
+	.debug_str 0 : { *(.debug_str) }
+	.debug_loc 0 : { *(.debug_loc) }
+	.debug_macinfo 0 : { *(.debug_macinfo) }
+
+#ifdef CONFIG_ARC_HAS_DCCM
+	. = CONFIG_ARC_DCCM_BASE;
+	__arc_dccm_base = .;
+	.data.arcfp : {
+		*(.data.arcfp)
+	}
+	. = ALIGN(CONFIG_ARC_DCCM_SZ * 1024);
+#endif
+}
diff --git a/arch/arc/lib/Makefile b/arch/arc/lib/Makefile
new file mode 100644
index 000000000000..db46e200baba
--- /dev/null
+++ b/arch/arc/lib/Makefile
@@ -0,0 +1,9 @@
+#
+# Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License version 2 as
+# published by the Free Software Foundation.
+
+lib-y	:= strchr-700.o strcmp.o strcpy-700.o strlen.o
+lib-y	+= memcmp.o memcpy-700.o memset.o
diff --git a/arch/arc/lib/memcmp.S b/arch/arc/lib/memcmp.S
new file mode 100644
index 000000000000..bc813d55b6c3
--- /dev/null
+++ b/arch/arc/lib/memcmp.S
@@ -0,0 +1,124 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <asm/linkage.h>
+
+#ifdef __LITTLE_ENDIAN__
+#define WORD2 r2
+#define SHIFT r3
+#else /* BIG ENDIAN */
+#define WORD2 r3
+#define SHIFT r2
+#endif
+
+ARC_ENTRY memcmp
+	or	r12,r0,r1
+	asl_s	r12,r12,30
+	sub	r3,r2,1
+	brls	r2,r12,.Lbytewise
+	ld	r4,[r0,0]
+	ld	r5,[r1,0]
+	lsr.f	lp_count,r3,3
+	lpne	.Loop_end
+	ld_s	WORD2,[r0,4]
+	ld_s	r12,[r1,4]
+	brne	r4,r5,.Leven
+	ld.a	r4,[r0,8]
+	ld.a	r5,[r1,8]
+	brne	WORD2,r12,.Lodd
+.Loop_end:
+	asl_s	SHIFT,SHIFT,3
+	bhs_s	.Last_cmp
+	brne	r4,r5,.Leven
+	ld	r4,[r0,4]
+	ld	r5,[r1,4]
+#ifdef __LITTLE_ENDIAN__
+	nop_s
+	; one more load latency cycle
+.Last_cmp:
+	xor	r0,r4,r5
+	bset	r0,r0,SHIFT
+	sub_s	r1,r0,1
+	bic_s	r1,r1,r0
+	norm	r1,r1
+	b.d	.Leven_cmp
+	and	r1,r1,24
+.Leven:
+	xor	r0,r4,r5
+	sub_s	r1,r0,1
+	bic_s	r1,r1,r0
+	norm	r1,r1
+	; slow track insn
+	and	r1,r1,24
+.Leven_cmp:
+	asl	r2,r4,r1
+	asl	r12,r5,r1
+	lsr_s	r2,r2,1
+	lsr_s	r12,r12,1
+	j_s.d	[blink]
+	sub	r0,r2,r12
+	.balign	4
+.Lodd:
+	xor	r0,WORD2,r12
+	sub_s	r1,r0,1
+	bic_s	r1,r1,r0
+	norm	r1,r1
+	; slow track insn
+	and	r1,r1,24
+	asl_s	r2,r2,r1
+	asl_s	r12,r12,r1
+	lsr_s	r2,r2,1
+	lsr_s	r12,r12,1
+	j_s.d	[blink]
+	sub	r0,r2,r12
+#else /* BIG ENDIAN */
+.Last_cmp:
+	neg_s	SHIFT,SHIFT
+	lsr	r4,r4,SHIFT
+	lsr	r5,r5,SHIFT
+	; slow track insn
+.Leven:
+	sub.f	r0,r4,r5
+	mov.ne	r0,1
+	j_s.d	[blink]
+	bset.cs	r0,r0,31
+.Lodd:
+	cmp_s	WORD2,r12
+
+	mov_s	r0,1
+	j_s.d	[blink]
+	bset.cs	r0,r0,31
+#endif /* ENDIAN */
+	.balign	4
+.Lbytewise:
+	breq	r2,0,.Lnil
+	ldb	r4,[r0,0]
+	ldb	r5,[r1,0]
+	lsr.f	lp_count,r3
+	lpne	.Lbyte_end
+	ldb_s	r3,[r0,1]
+	ldb	r12,[r1,1]
+	brne	r4,r5,.Lbyte_even
+	ldb.a	r4,[r0,2]
+	ldb.a	r5,[r1,2]
+	brne	r3,r12,.Lbyte_odd
+.Lbyte_end:
+	bcc	.Lbyte_even
+	brne	r4,r5,.Lbyte_even
+	ldb_s	r3,[r0,1]
+	ldb_s	r12,[r1,1]
+.Lbyte_odd:
+	j_s.d	[blink]
+	sub	r0,r3,r12
+.Lbyte_even:
+	j_s.d	[blink]
+	sub	r0,r4,r5
+.Lnil:
+	j_s.d	[blink]
+	mov	r0,0
+ARC_EXIT memcmp
diff --git a/arch/arc/lib/memcpy-700.S b/arch/arc/lib/memcpy-700.S
new file mode 100644
index 000000000000..b64cc10ac918
--- /dev/null
+++ b/arch/arc/lib/memcpy-700.S
@@ -0,0 +1,66 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <asm/linkage.h>
+
+ARC_ENTRY memcpy
+	or	r3,r0,r1
+	asl_s	r3,r3,30
+	mov_s	r5,r0
+	brls.d	r2,r3,.Lcopy_bytewise
+	sub.f	r3,r2,1
+	ld_s	r12,[r1,0]
+	asr.f	lp_count,r3,3
+	bbit0.d	r3,2,.Lnox4
+	bmsk_s	r2,r2,1
+	st.ab	r12,[r5,4]
+	ld.a	r12,[r1,4]
+.Lnox4:
+	lppnz	.Lendloop
+	ld_s	r3,[r1,4]
+	st.ab	r12,[r5,4]
+	ld.a	r12,[r1,8]
+	st.ab	r3,[r5,4]
+.Lendloop:
+	breq	r2,0,.Last_store
+	ld	r3,[r5,0]
+#ifdef __LITTLE_ENDIAN__
+	add3	r2,-1,r2
+	; uses long immediate
+	xor_s	r12,r12,r3
+	bmsk	r12,r12,r2
+    xor_s	r12,r12,r3
+#else /* BIG ENDIAN */
+	sub3	r2,31,r2
+	; uses long immediate
+        xor_s	r3,r3,r12
+        bmsk	r3,r3,r2
+        xor_s	r12,r12,r3
+#endif /* ENDIAN */
+.Last_store:
+	j_s.d	[blink]
+	st	r12,[r5,0]
+
+	.balign	4
+.Lcopy_bytewise:
+	jcs	[blink]
+	ldb_s	r12,[r1,0]
+	lsr.f	lp_count,r3
+	bhs_s	.Lnox1
+	stb.ab	r12,[r5,1]
+	ldb.a	r12,[r1,1]
+.Lnox1:
+	lppnz	.Lendbloop
+	ldb_s	r3,[r1,1]
+	stb.ab	r12,[r5,1]
+	ldb.a	r12,[r1,2]
+	stb.ab	r3,[r5,1]
+.Lendbloop:
+	j_s.d	[blink]
+	stb	r12,[r5,0]
+ARC_EXIT memcpy
diff --git a/arch/arc/lib/memset.S b/arch/arc/lib/memset.S
new file mode 100644
index 000000000000..9b2d88d2e141
--- /dev/null
+++ b/arch/arc/lib/memset.S
@@ -0,0 +1,59 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <asm/linkage.h>
+
+#define SMALL	7 /* Must be at least 6 to deal with alignment/loop issues.  */
+
+ARC_ENTRY memset
+	mov_s	r4,r0
+	or	r12,r0,r2
+	bmsk.f	r12,r12,1
+	extb_s	r1,r1
+	asl	r3,r1,8
+	beq.d	.Laligned
+	or_s	r1,r1,r3
+	brls	r2,SMALL,.Ltiny
+	add	r3,r2,r0
+	stb	r1,[r3,-1]
+	bclr_s	r3,r3,0
+	stw	r1,[r3,-2]
+	bmsk.f	r12,r0,1
+	add_s	r2,r2,r12
+	sub.ne	r2,r2,4
+	stb.ab	r1,[r4,1]
+	and	r4,r4,-2
+	stw.ab	r1,[r4,2]
+	and	r4,r4,-4
+.Laligned:	; This code address should be aligned for speed.
+	asl	r3,r1,16
+	lsr.f	lp_count,r2,2
+	or_s	r1,r1,r3
+	lpne	.Loop_end
+	st.ab	r1,[r4,4]
+.Loop_end:
+	j_s	[blink]
+
+	.balign	4
+.Ltiny:
+	mov.f	lp_count,r2
+	lpne	.Ltiny_end
+	stb.ab	r1,[r4,1]
+.Ltiny_end:
+	j_s	[blink]
+ARC_EXIT memset
+
+; memzero: @r0 = mem, @r1 = size_t
+; memset:  @r0 = mem, @r1 = char, @r2 = size_t
+
+ARC_ENTRY memzero
+    ; adjust bzero args to memset args
+    mov r2, r1
+    mov r1, 0
+    b  memset    ;tail call so need to tinker with blink
+ARC_EXIT memzero
diff --git a/arch/arc/lib/strchr-700.S b/arch/arc/lib/strchr-700.S
new file mode 100644
index 000000000000..99c10475d477
--- /dev/null
+++ b/arch/arc/lib/strchr-700.S
@@ -0,0 +1,123 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/* ARC700 has a relatively long pipeline and branch prediction, so we want
+   to avoid branches that are hard to predict.  On the other hand, the
+   presence of the norm instruction makes it easier to operate on whole
+   words branch-free.  */
+
+#include <asm/linkage.h>
+
+ARC_ENTRY strchr
+	extb_s	r1,r1
+	asl	r5,r1,8
+	bmsk	r2,r0,1
+	or	r5,r5,r1
+	mov_s	r3,0x01010101
+	breq.d	r2,r0,.Laligned
+	asl	r4,r5,16
+	sub_s	r0,r0,r2
+	asl	r7,r2,3
+	ld_s	r2,[r0]
+#ifdef __LITTLE_ENDIAN__
+	asl	r7,r3,r7
+#else
+	lsr	r7,r3,r7
+#endif
+	or	r5,r5,r4
+	ror	r4,r3
+	sub	r12,r2,r7
+	bic_s	r12,r12,r2
+	and	r12,r12,r4
+	brne.d	r12,0,.Lfound0_ua
+	xor	r6,r2,r5
+	ld.a	r2,[r0,4]
+	sub	r12,r6,r7
+	bic	r12,r12,r6
+	and	r7,r12,r4
+	breq	r7,0,.Loop ; For speed, we want this branch to be unaligned.
+	b	.Lfound_char ; Likewise this one.
+; /* We require this code address to be unaligned for speed...  */
+.Laligned:
+	ld_s	r2,[r0]
+	or	r5,r5,r4
+	ror	r4,r3
+; /* ... so that this code address is aligned, for itself and ...  */
+.Loop:
+	sub	r12,r2,r3
+	bic_s	r12,r12,r2
+	and	r12,r12,r4
+	brne.d	r12,0,.Lfound0
+	xor	r6,r2,r5
+	ld.a	r2,[r0,4]
+	sub	r12,r6,r3
+	bic	r12,r12,r6
+	and	r7,r12,r4
+	breq	r7,0,.Loop /* ... so that this branch is unaligned.  */
+	; Found searched-for character.  r0 has already advanced to next word.
+#ifdef __LITTLE_ENDIAN__
+/* We only need the information about the first matching byte
+   (i.e. the least significant matching byte) to be exact,
+   hence there is no problem with carry effects.  */
+.Lfound_char:
+	sub	r3,r7,1
+	bic	r3,r3,r7
+	norm	r2,r3
+	sub_s	r0,r0,1
+	asr_s	r2,r2,3
+	j.d	[blink]
+	sub_s	r0,r0,r2
+
+	.balign	4
+.Lfound0_ua:
+	mov	r3,r7
+.Lfound0:
+	sub	r3,r6,r3
+	bic	r3,r3,r6
+	and	r2,r3,r4
+	or_s	r12,r12,r2
+	sub_s	r3,r12,1
+	bic_s	r3,r3,r12
+	norm	r3,r3
+	add_s	r0,r0,3
+	asr_s	r12,r3,3
+	asl.f	0,r2,r3
+	sub_s	r0,r0,r12
+	j_s.d	[blink]
+	mov.pl	r0,0
+#else /* BIG ENDIAN */
+.Lfound_char:
+	lsr	r7,r7,7
+
+	bic	r2,r7,r6
+	norm	r2,r2
+	sub_s	r0,r0,4
+	asr_s	r2,r2,3
+	j.d	[blink]
+	add_s	r0,r0,r2
+
+.Lfound0_ua:
+	mov_s	r3,r7
+.Lfound0:
+	asl_s	r2,r2,7
+	or	r7,r6,r4
+	bic_s	r12,r12,r2
+	sub	r2,r7,r3
+	or	r2,r2,r6
+	bic	r12,r2,r12
+	bic.f	r3,r4,r12
+	norm	r3,r3
+
+	add.pl	r3,r3,1
+	asr_s	r12,r3,3
+	asl.f	0,r2,r3
+	add_s	r0,r0,r12
+	j_s.d	[blink]
+	mov.mi	r0,0
+#endif /* ENDIAN */
+ARC_EXIT strchr
diff --git a/arch/arc/lib/strcmp.S b/arch/arc/lib/strcmp.S
new file mode 100644
index 000000000000..5dc802b45cf3
--- /dev/null
+++ b/arch/arc/lib/strcmp.S
@@ -0,0 +1,96 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/* This is optimized primarily for the ARC700.
+   It would be possible to speed up the loops by one cycle / word
+   respective one cycle / byte by forcing double source 1 alignment, unrolling
+   by a factor of two, and speculatively loading the second word / byte of
+   source 1; however, that would increase the overhead for loop setup / finish,
+   and strcmp might often terminate early.  */
+
+#include <asm/linkage.h>
+
+ARC_ENTRY strcmp
+	or	r2,r0,r1
+	bmsk_s	r2,r2,1
+	brne	r2,0,.Lcharloop
+	mov_s	r12,0x01010101
+	ror	r5,r12
+.Lwordloop:
+	ld.ab	r2,[r0,4]
+	ld.ab	r3,[r1,4]
+	nop_s
+	sub	r4,r2,r12
+	bic	r4,r4,r2
+	and	r4,r4,r5
+	brne	r4,0,.Lfound0
+	breq	r2,r3,.Lwordloop
+#ifdef	__LITTLE_ENDIAN__
+	xor	r0,r2,r3	; mask for difference
+	sub_s	r1,r0,1
+	bic_s	r0,r0,r1	; mask for least significant difference bit
+	sub	r1,r5,r0
+	xor	r0,r5,r1	; mask for least significant difference byte
+	and_s	r2,r2,r0
+	and_s	r3,r3,r0
+#endif /* LITTLE ENDIAN */
+	cmp_s	r2,r3
+	mov_s	r0,1
+	j_s.d	[blink]
+	bset.lo	r0,r0,31
+
+	.balign	4
+#ifdef __LITTLE_ENDIAN__
+.Lfound0:
+	xor	r0,r2,r3	; mask for difference
+	or	r0,r0,r4	; or in zero indicator
+	sub_s	r1,r0,1
+	bic_s	r0,r0,r1	; mask for least significant difference bit
+	sub	r1,r5,r0
+	xor	r0,r5,r1	; mask for least significant difference byte
+	and_s	r2,r2,r0
+	and_s	r3,r3,r0
+	sub.f	r0,r2,r3
+	mov.hi	r0,1
+	j_s.d	[blink]
+	bset.lo	r0,r0,31
+#else /* BIG ENDIAN */
+	/* The zero-detection above can mis-detect 0x01 bytes as zeroes
+	   because of carry-propagateion from a lower significant zero byte.
+	   We can compensate for this by checking that bit0 is zero.
+	   This compensation is not necessary in the step where we
+	   get a low estimate for r2, because in any affected bytes
+	   we already have 0x00 or 0x01, which will remain unchanged
+	   when bit 7 is cleared.  */
+	.balign	4
+.Lfound0:
+	lsr	r0,r4,8
+	lsr_s	r1,r2
+	bic_s	r2,r2,r0	; get low estimate for r2 and get ...
+	bic_s	r0,r0,r1	; <this is the adjusted mask for zeros>
+	or_s	r3,r3,r0	; ... high estimate r3 so that r2 > r3 will ...
+	cmp_s	r3,r2		; ... be independent of trailing garbage
+	or_s	r2,r2,r0	; likewise for r3 > r2
+	bic_s	r3,r3,r0
+	rlc	r0,0		; r0 := r2 > r3 ? 1 : 0
+	cmp_s	r2,r3
+	j_s.d	[blink]
+	bset.lo	r0,r0,31
+#endif /* ENDIAN */
+
+	.balign	4
+.Lcharloop:
+	ldb.ab	r2,[r0,1]
+	ldb.ab	r3,[r1,1]
+	nop_s
+	breq	r2,0,.Lcmpend
+	breq	r2,r3,.Lcharloop
+.Lcmpend:
+	j_s.d	[blink]
+	sub	r0,r2,r3
+ARC_EXIT strcmp
diff --git a/arch/arc/lib/strcpy-700.S b/arch/arc/lib/strcpy-700.S
new file mode 100644
index 000000000000..b7ca4ae81d88
--- /dev/null
+++ b/arch/arc/lib/strcpy-700.S
@@ -0,0 +1,70 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/* If dst and src are 4 byte aligned, copy 8 bytes at a time.
+   If the src is 4, but not 8 byte aligned, we first read 4 bytes to get
+   it 8 byte aligned.  Thus, we can do a little read-ahead, without
+   dereferencing a cache line that we should not touch.
+   Note that short and long instructions have been scheduled to avoid
+   branch stalls.
+   The beq_s to r3z could be made unaligned & long to avoid a stall
+   there, but the it is not likely to be taken often, and it
+   would also be likey to cost an unaligned mispredict at the next call.  */
+
+#include <asm/linkage.h>
+
+ARC_ENTRY strcpy
+	or	r2,r0,r1
+	bmsk_s	r2,r2,1
+	brne.d	r2,0,charloop
+	mov_s	r10,r0
+	ld_s	r3,[r1,0]
+	mov	r8,0x01010101
+	bbit0.d	r1,2,loop_start
+	ror	r12,r8
+	sub	r2,r3,r8
+	bic_s	r2,r2,r3
+	tst_s	r2,r12
+	bne	r3z
+	mov_s	r4,r3
+	.balign 4
+loop:
+	ld.a	r3,[r1,4]
+	st.ab	r4,[r10,4]
+loop_start:
+	ld.a	r4,[r1,4]
+	sub	r2,r3,r8
+	bic_s	r2,r2,r3
+	tst_s	r2,r12
+	bne_s	r3z
+	st.ab	r3,[r10,4]
+	sub	r2,r4,r8
+	bic	r2,r2,r4
+	tst	r2,r12
+	beq	loop
+	mov_s	r3,r4
+#ifdef __LITTLE_ENDIAN__
+r3z:	bmsk.f	r1,r3,7
+	lsr_s	r3,r3,8
+#else
+r3z:	lsr.f	r1,r3,24
+	asl_s	r3,r3,8
+#endif
+	bne.d	r3z
+	stb.ab	r1,[r10,1]
+	j_s	[blink]
+
+	.balign	4
+charloop:
+	ldb.ab	r3,[r1,1]
+
+
+	brne.d	r3,0,charloop
+	stb.ab	r3,[r10,1]
+	j	[blink]
+ARC_EXIT strcpy
diff --git a/arch/arc/lib/strlen.S b/arch/arc/lib/strlen.S
new file mode 100644
index 000000000000..39759e099696
--- /dev/null
+++ b/arch/arc/lib/strlen.S
@@ -0,0 +1,83 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <asm/linkage.h>
+
+ARC_ENTRY strlen
+	or	r3,r0,7
+	ld	r2,[r3,-7]
+	ld.a	r6,[r3,-3]
+	mov	r4,0x01010101
+	; uses long immediate
+#ifdef __LITTLE_ENDIAN__
+	asl_s	r1,r0,3
+	btst_s	r0,2
+	asl	r7,r4,r1
+	ror	r5,r4
+	sub	r1,r2,r7
+	bic_s	r1,r1,r2
+	mov.eq	r7,r4
+	sub	r12,r6,r7
+	bic	r12,r12,r6
+	or.eq	r12,r12,r1
+	and	r12,r12,r5
+	brne	r12,0,.Learly_end
+#else /* BIG ENDIAN */
+	ror	r5,r4
+	btst_s	r0,2
+	mov_s	r1,31
+	sub3	r7,r1,r0
+	sub	r1,r2,r4
+	bic_s	r1,r1,r2
+	bmsk	r1,r1,r7
+	sub	r12,r6,r4
+	bic	r12,r12,r6
+	bmsk.ne	r12,r12,r7
+	or.eq	r12,r12,r1
+	and	r12,r12,r5
+	brne	r12,0,.Learly_end
+#endif /* ENDIAN */
+
+.Loop:
+	ld_s	r2,[r3,4]
+	ld.a	r6,[r3,8]
+	; stall for load result
+	sub	r1,r2,r4
+	bic_s	r1,r1,r2
+	sub	r12,r6,r4
+	bic	r12,r12,r6
+	or	r12,r12,r1
+	and	r12,r12,r5
+	breq r12,0,.Loop
+.Lend:
+	and.f	r1,r1,r5
+	sub.ne	r3,r3,4
+	mov.eq	r1,r12
+#ifdef __LITTLE_ENDIAN__
+	sub_s	r2,r1,1
+	bic_s	r2,r2,r1
+	norm	r1,r2
+	sub_s	r0,r0,3
+	lsr_s	r1,r1,3
+	sub	    r0,r3,r0
+	j_s.d	[blink]
+	sub	    r0,r0,r1
+#else /* BIG ENDIAN */
+	lsr_s	r1,r1,7
+	mov.eq	r2,r6
+	bic_s	r1,r1,r2
+	norm	r1,r1
+	sub	    r0,r3,r0
+	lsr_s	r1,r1,3
+	j_s.d	[blink]
+	add	    r0,r0,r1
+#endif /* ENDIAN */
+.Learly_end:
+	b.d	.Lend
+	sub_s.ne r1,r1,r1
+ARC_EXIT strlen
diff --git a/arch/arc/mm/Makefile b/arch/arc/mm/Makefile
new file mode 100644
index 000000000000..168dc146a8f6
--- /dev/null
+++ b/arch/arc/mm/Makefile
@@ -0,0 +1,10 @@
+#
+# Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License version 2 as
+# published by the Free Software Foundation.
+#
+
+obj-y	:= extable.o ioremap.o dma.o fault.o init.o
+obj-y	+= tlb.o tlbex.o cache_arc700.o
diff --git a/arch/arc/mm/cache_arc700.c b/arch/arc/mm/cache_arc700.c
new file mode 100644
index 000000000000..88d617d84234
--- /dev/null
+++ b/arch/arc/mm/cache_arc700.c
@@ -0,0 +1,768 @@
+/*
+ * ARC700 VIPT Cache Management
+ *
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ *  vineetg: May 2011: for Non-aliasing VIPT D-cache following can be NOPs
+ *   -flush_cache_dup_mm (fork)
+ *   -likewise for flush_cache_mm (exit/execve)
+ *   -likewise for flush_cache_range,flush_cache_page (munmap, exit, COW-break)
+ *
+ * vineetg: Apr 2011
+ *  -Now that MMU can support larger pg sz (16K), the determiniation of
+ *   aliasing shd not be based on assumption of 8k pg
+ *
+ * vineetg: Mar 2011
+ *  -optimised version of flush_icache_range( ) for making I/D coherent
+ *   when vaddr is available (agnostic of num of aliases)
+ *
+ * vineetg: Mar 2011
+ *  -Added documentation about I-cache aliasing on ARC700 and the way it
+ *   was handled up until MMU V2.
+ *  -Spotted a three year old bug when killing the 4 aliases, which needs
+ *   bottom 2 bits, so we need to do paddr | {0x00, 0x01, 0x02, 0x03}
+ *                        instead of paddr | {0x00, 0x01, 0x10, 0x11}
+ *   (Rajesh you owe me one now)
+ *
+ * vineetg: Dec 2010
+ *  -Off-by-one error when computing num_of_lines to flush
+ *   This broke signal handling with bionic which uses synthetic sigret stub
+ *
+ * vineetg: Mar 2010
+ *  -GCC can't generate ZOL for core cache flush loops.
+ *   Conv them into iterations based as opposed to while (start < end) types
+ *
+ * Vineetg: July 2009
+ *  -In I-cache flush routine we used to chk for aliasing for every line INV.
+ *   Instead now we setup routines per cache geometry and invoke them
+ *   via function pointers.
+ *
+ * Vineetg: Jan 2009
+ *  -Cache Line flush routines used to flush an extra line beyond end addr
+ *   because check was while (end >= start) instead of (end > start)
+ *     =Some call sites had to work around by doing -1, -4 etc to end param
+ *     =Some callers didnt care. This was spec bad in case of INV routines
+ *      which would discard valid data (cause of the horrible ext2 bug
+ *      in ARC IDE driver)
+ *
+ * vineetg: June 11th 2008: Fixed flush_icache_range( )
+ *  -Since ARC700 caches are not coherent (I$ doesnt snoop D$) both need
+ *   to be flushed, which it was not doing.
+ *  -load_module( ) passes vmalloc addr (Kernel Virtual Addr) to the API,
+ *   however ARC cache maintenance OPs require PHY addr. Thus need to do
+ *   vmalloc_to_phy.
+ *  -Also added optimisation there, that for range > PAGE SIZE we flush the
+ *   entire cache in one shot rather than line by line. For e.g. a module
+ *   with Code sz 600k, old code flushed 600k worth of cache (line-by-line),
+ *   while cache is only 16 or 32k.
+ */
+
+#include <linux/module.h>
+#include <linux/mm.h>
+#include <linux/sched.h>
+#include <linux/cache.h>
+#include <linux/mmu_context.h>
+#include <linux/syscalls.h>
+#include <linux/uaccess.h>
+#include <asm/cacheflush.h>
+#include <asm/cachectl.h>
+#include <asm/setup.h>
+
+
+#ifdef CONFIG_ARC_HAS_ICACHE
+static void __ic_line_inv_no_alias(unsigned long, int);
+static void __ic_line_inv_2_alias(unsigned long, int);
+static void __ic_line_inv_4_alias(unsigned long, int);
+
+/* Holds the ptr to flush routine, dependign on size due to aliasing issues */
+static void (*___flush_icache_rtn) (unsigned long, int);
+#endif
+
+char *arc_cache_mumbojumbo(int cpu_id, char *buf, int len)
+{
+	int n = 0;
+	unsigned int c = smp_processor_id();
+
+#define PR_CACHE(p, enb, str)						\
+{									\
+	if (!(p)->ver)							\
+		n += scnprintf(buf + n, len - n, str"\t\t: N/A\n");	\
+	else								\
+		n += scnprintf(buf + n, len - n,			\
+			str"\t\t: (%uK) VIPT, %dway set-asc, %ub Line %s\n", \
+			TO_KB((p)->sz), (p)->assoc, (p)->line_len,	\
+			enb ?  "" : "DISABLED (kernel-build)");		\
+}
+
+	PR_CACHE(&cpuinfo_arc700[c].icache, __CONFIG_ARC_HAS_ICACHE, "I-Cache");
+	PR_CACHE(&cpuinfo_arc700[c].dcache, __CONFIG_ARC_HAS_DCACHE, "D-Cache");
+
+	return buf;
+}
+
+/*
+ * Read the Cache Build Confuration Registers, Decode them and save into
+ * the cpuinfo structure for later use.
+ * No Validation done here, simply read/convert the BCRs
+ */
+void __init read_decode_cache_bcr(void)
+{
+	struct bcr_cache ibcr, dbcr;
+	struct cpuinfo_arc_cache *p_ic, *p_dc;
+	unsigned int cpu = smp_processor_id();
+
+	p_ic = &cpuinfo_arc700[cpu].icache;
+	READ_BCR(ARC_REG_IC_BCR, ibcr);
+
+	if (ibcr.config == 0x3)
+		p_ic->assoc = 2;
+	p_ic->line_len = 8 << ibcr.line_len;
+	p_ic->sz = 0x200 << ibcr.sz;
+	p_ic->ver = ibcr.ver;
+
+	p_dc = &cpuinfo_arc700[cpu].dcache;
+	READ_BCR(ARC_REG_DC_BCR, dbcr);
+
+	if (dbcr.config == 0x2)
+		p_dc->assoc = 4;
+	p_dc->line_len = 16 << dbcr.line_len;
+	p_dc->sz = 0x200 << dbcr.sz;
+	p_dc->ver = dbcr.ver;
+}
+
+/*
+ * 1. Validate the Cache Geomtery (compile time config matches hardware)
+ * 2. If I-cache suffers from aliasing, setup work arounds (difft flush rtn)
+ *    (aliasing D-cache configurations are not supported YET)
+ * 3. Enable the Caches, setup default flush mode for D-Cache
+ * 3. Calculate the SHMLBA used by user space
+ */
+void __init arc_cache_init(void)
+{
+	unsigned int temp;
+	unsigned int cpu = smp_processor_id();
+	struct cpuinfo_arc_cache *ic = &cpuinfo_arc700[cpu].icache;
+	struct cpuinfo_arc_cache *dc = &cpuinfo_arc700[cpu].dcache;
+	int way_pg_ratio = way_pg_ratio;
+	char str[256];
+
+	printk(arc_cache_mumbojumbo(0, str, sizeof(str)));
+
+	if (!ic->ver)
+		goto chk_dc;
+
+#ifdef CONFIG_ARC_HAS_ICACHE
+	/* 1. Confirm some of I-cache params which Linux assumes */
+	if ((ic->assoc != ARC_ICACHE_WAYS) ||
+	    (ic->line_len != ARC_ICACHE_LINE_LEN)) {
+		panic("Cache H/W doesn't match kernel Config");
+	}
+#if (CONFIG_ARC_MMU_VER > 2)
+	if (ic->ver != 3) {
+		if (running_on_hw)
+			panic("Cache ver doesn't match MMU ver\n");
+
+		/* For ISS - suggest the toggles to use */
+		pr_err("Use -prop=icache_version=3,-prop=dcache_version=3\n");
+
+	}
+#endif
+
+	/*
+	 * if Cache way size is <= page size then no aliasing exhibited
+	 * otherwise ratio determines num of aliases.
+	 * e.g. 32K I$, 2 way set assoc, 8k pg size
+	 *       way-sz = 32k/2 = 16k
+	 *       way-pg-ratio = 16k/8k = 2, so 2 aliases possible
+	 *       (meaning 1 line could be in 2 possible locations).
+	 */
+	way_pg_ratio = ic->sz / ARC_ICACHE_WAYS / PAGE_SIZE;
+	switch (way_pg_ratio) {
+	case 0:
+	case 1:
+		___flush_icache_rtn = __ic_line_inv_no_alias;
+		break;
+	case 2:
+		___flush_icache_rtn = __ic_line_inv_2_alias;
+		break;
+	case 4:
+		___flush_icache_rtn = __ic_line_inv_4_alias;
+		break;
+	default:
+		panic("Unsupported I-Cache Sz\n");
+	}
+#endif
+
+	/* Enable/disable I-Cache */
+	temp = read_aux_reg(ARC_REG_IC_CTRL);
+
+#ifdef CONFIG_ARC_HAS_ICACHE
+	temp &= ~IC_CTRL_CACHE_DISABLE;
+#else
+	temp |= IC_CTRL_CACHE_DISABLE;
+#endif
+
+	write_aux_reg(ARC_REG_IC_CTRL, temp);
+
+chk_dc:
+	if (!dc->ver)
+		return;
+
+#ifdef CONFIG_ARC_HAS_DCACHE
+	if ((dc->assoc != ARC_DCACHE_WAYS) ||
+	    (dc->line_len != ARC_DCACHE_LINE_LEN)) {
+		panic("Cache H/W doesn't match kernel Config");
+	}
+
+	/* check for D-Cache aliasing */
+	if ((dc->sz / ARC_DCACHE_WAYS) > PAGE_SIZE)
+		panic("D$ aliasing not handled right now\n");
+#endif
+
+	/* Set the default Invalidate Mode to "simpy discard dirty lines"
+	 *  as this is more frequent then flush before invalidate
+	 * Ofcourse we toggle this default behviour when desired
+	 */
+	temp = read_aux_reg(ARC_REG_DC_CTRL);
+	temp &= ~DC_CTRL_INV_MODE_FLUSH;
+
+#ifdef CONFIG_ARC_HAS_DCACHE
+	/* Enable D-Cache: Clear Bit 0 */
+	write_aux_reg(ARC_REG_DC_CTRL, temp & ~IC_CTRL_CACHE_DISABLE);
+#else
+	/* Flush D cache */
+	write_aux_reg(ARC_REG_DC_FLSH, 0x1);
+	/* Disable D cache */
+	write_aux_reg(ARC_REG_DC_CTRL, temp | IC_CTRL_CACHE_DISABLE);
+#endif
+
+	return;
+}
+
+#define OP_INV		0x1
+#define OP_FLUSH	0x2
+#define OP_FLUSH_N_INV	0x3
+
+#ifdef CONFIG_ARC_HAS_DCACHE
+
+/***************************************************************
+ * Machine specific helpers for Entire D-Cache or Per Line ops
+ */
+
+static inline void wait_for_flush(void)
+{
+	while (read_aux_reg(ARC_REG_DC_CTRL) & DC_CTRL_FLUSH_STATUS)
+		;
+}
+
+/*
+ * Operation on Entire D-Cache
+ * @cacheop = {OP_INV, OP_FLUSH, OP_FLUSH_N_INV}
+ * Note that constant propagation ensures all the checks are gone
+ * in generated code
+ */
+static inline void __dc_entire_op(const int cacheop)
+{
+	unsigned long flags, tmp = tmp;
+	int aux;
+
+	local_irq_save(flags);
+
+	if (cacheop == OP_FLUSH_N_INV) {
+		/* Dcache provides 2 cmd: FLUSH or INV
+		 * INV inturn has sub-modes: DISCARD or FLUSH-BEFORE
+		 * flush-n-inv is achieved by INV cmd but with IM=1
+		 * Default INV sub-mode is DISCARD, which needs to be toggled
+		 */
+		tmp = read_aux_reg(ARC_REG_DC_CTRL);
+		write_aux_reg(ARC_REG_DC_CTRL, tmp | DC_CTRL_INV_MODE_FLUSH);
+	}
+
+	if (cacheop & OP_INV)	/* Inv or flush-n-inv use same cmd reg */
+		aux = ARC_REG_DC_IVDC;
+	else
+		aux = ARC_REG_DC_FLSH;
+
+	write_aux_reg(aux, 0x1);
+
+	if (cacheop & OP_FLUSH)	/* flush / flush-n-inv both wait */
+		wait_for_flush();
+
+	/* Switch back the DISCARD ONLY Invalidate mode */
+	if (cacheop == OP_FLUSH_N_INV)
+		write_aux_reg(ARC_REG_DC_CTRL, tmp & ~DC_CTRL_INV_MODE_FLUSH);
+
+	local_irq_restore(flags);
+}
+
+/*
+ * Per Line Operation on D-Cache
+ * Doesn't deal with type-of-op/IRQ-disabling/waiting-for-flush-to-complete
+ * It's sole purpose is to help gcc generate ZOL
+ */
+static inline void __dc_line_loop(unsigned long start, unsigned long sz,
+					  int aux_reg)
+{
+	int num_lines, slack;
+
+	/* Ensure we properly floor/ceil the non-line aligned/sized requests
+	 * and have @start - aligned to cache line and integral @num_lines.
+	 * This however can be avoided for page sized since:
+	 *  -@start will be cache-line aligned already (being page aligned)
+	 *  -@sz will be integral multiple of line size (being page sized).
+	 */
+	if (!(__builtin_constant_p(sz) && sz == PAGE_SIZE)) {
+		slack = start & ~DCACHE_LINE_MASK;
+		sz += slack;
+		start -= slack;
+	}
+
+	num_lines = DIV_ROUND_UP(sz, ARC_DCACHE_LINE_LEN);
+
+	while (num_lines-- > 0) {
+#if (CONFIG_ARC_MMU_VER > 2)
+		/*
+		 * Just as for I$, in MMU v3, D$ ops also require
+		 * "tag" bits in DC_PTAG, "index" bits in FLDL,IVDL ops
+		 * But we pass phy addr for both. This works since Linux
+		 * doesn't support aliasing configs for D$, yet.
+		 * Thus paddr is enough to provide both tag and index.
+		 */
+		write_aux_reg(ARC_REG_DC_PTAG, start);
+#endif
+		write_aux_reg(aux_reg, start);
+		start += ARC_DCACHE_LINE_LEN;
+	}
+}
+
+/*
+ * D-Cache : Per Line INV (discard or wback+discard) or FLUSH (wback)
+ */
+static inline void __dc_line_op(unsigned long start, unsigned long sz,
+					const int cacheop)
+{
+	unsigned long flags, tmp = tmp;
+	int aux;
+
+	local_irq_save(flags);
+
+	if (cacheop == OP_FLUSH_N_INV) {
+		/*
+		 * Dcache provides 2 cmd: FLUSH or INV
+		 * INV inturn has sub-modes: DISCARD or FLUSH-BEFORE
+		 * flush-n-inv is achieved by INV cmd but with IM=1
+		 * Default INV sub-mode is DISCARD, which needs to be toggled
+		 */
+		tmp = read_aux_reg(ARC_REG_DC_CTRL);
+		write_aux_reg(ARC_REG_DC_CTRL, tmp | DC_CTRL_INV_MODE_FLUSH);
+	}
+
+	if (cacheop & OP_INV)	/* Inv / flush-n-inv use same cmd reg */
+		aux = ARC_REG_DC_IVDL;
+	else
+		aux = ARC_REG_DC_FLDL;
+
+	__dc_line_loop(start, sz, aux);
+
+	if (cacheop & OP_FLUSH)	/* flush / flush-n-inv both wait */
+		wait_for_flush();
+
+	/* Switch back the DISCARD ONLY Invalidate mode */
+	if (cacheop == OP_FLUSH_N_INV)
+		write_aux_reg(ARC_REG_DC_CTRL, tmp & ~DC_CTRL_INV_MODE_FLUSH);
+
+	local_irq_restore(flags);
+}
+
+#else
+
+#define __dc_entire_op(cacheop)
+#define __dc_line_op(start, sz, cacheop)
+
+#endif /* CONFIG_ARC_HAS_DCACHE */
+
+
+#ifdef CONFIG_ARC_HAS_ICACHE
+
+/*
+ *		I-Cache Aliasing in ARC700 VIPT caches
+ *
+ * For fetching code from I$, ARC700 uses vaddr (embedded in program code)
+ * to "index" into SET of cache-line and paddr from MMU to match the TAG
+ * in the WAYS of SET.
+ *
+ * However the CDU iterface (to flush/inv) lines from software, only takes
+ * paddr (to have simpler hardware interface). For simpler cases, using paddr
+ * alone suffices.
+ * e.g. 2-way-set-assoc, 16K I$ (8k MMU pg sz, 32b cache line size):
+ *      way_sz = cache_sz / num_ways = 16k/2 = 8k
+ *      num_sets = way_sz / line_sz = 8k/32 = 256 => 8 bits
+ *   Ignoring the bottom 5 bits corresp to the off within a 32b cacheline,
+ *   bits req for calc set-index = bits 12:5 (0 based). Since this range fits
+ *   inside the bottom 13 bits of paddr, which are same for vaddr and paddr
+ *   (with 8k pg sz), paddr alone can be safely used by CDU to unambigously
+ *   locate a cache-line.
+ *
+ * However for a difft sized cache, say 32k I$, above math yields need
+ * for 14 bits of vaddr to locate a cache line, which can't be provided by
+ * paddr, since the bit 13 (0 based) might differ between the two.
+ *
+ * This lack of extra bits needed for correct line addressing, defines the
+ * classical problem of Cache aliasing with VIPT architectures
+ * num_aliases = 1 << extra_bits
+ * e.g. 2-way-set-assoc, 32K I$ with 8k MMU pg sz => 2 aliases
+ *      2-way-set-assoc, 64K I$ with 8k MMU pg sz => 4 aliases
+ *      2-way-set-assoc, 16K I$ with 8k MMU pg sz => NO aliases
+ *
+ * ------------------
+ * MMU v1/v2 (Fixed Page Size 8k)
+ * ------------------
+ * The solution was to provide CDU with these additonal vaddr bits. These
+ * would be bits [x:13], x would depend on cache-geom.
+ * H/w folks chose [17:13] to be a future safe range, and moreso these 5 bits
+ * of vaddr could easily be "stuffed" in the paddr as bits [4:0] since the
+ * orig 5 bits of paddr were anyways ignored by CDU line ops, as they
+ * represent the offset within cache-line. The adv of using this "clumsy"
+ * interface for additional info was no new reg was needed in CDU.
+ *
+ * 17:13 represented the max num of bits passable, actual bits needed were
+ * fewer, based on the num-of-aliases possible.
+ * -for 2 alias possibility, only bit 13 needed (32K cache)
+ * -for 4 alias possibility, bits 14:13 needed (64K cache)
+ *
+ * Since vaddr was not available for all instances of I$ flush req by core
+ * kernel, the only safe way (non-optimal though) was to kill all possible
+ * lines which could represent an alias (even if they didnt represent one
+ * in execution).
+ * e.g. for 64K I$, 4 aliases possible, so we did
+ *      flush start
+ *      flush start | 0x01
+ *      flush start | 0x2
+ *      flush start | 0x3
+ *
+ * The penalty was invoking the operation itself, since tag match is anyways
+ * paddr based, a line which didn't represent an alias would not match the
+ * paddr, hence wont be killed
+ *
+ * Note that aliasing concerns are independent of line-sz for a given cache
+ * geometry (size + set_assoc) because the extra bits required by line-sz are
+ * reduced from the set calc.
+ * e.g. 2-way-set-assoc, 32K I$ with 8k MMU pg sz and using math above
+ *  32b line-sz: 9 bits set-index-calc, 5 bits offset-in-line => 1 extra bit
+ *  64b line-sz: 8 bits set-index-calc, 6 bits offset-in-line => 1 extra bit
+ *
+ * ------------------
+ * MMU v3
+ * ------------------
+ * This ver of MMU supports var page sizes (1k-16k) - Linux will support
+ * 8k (default), 16k and 4k.
+ * However from hardware perspective, smaller page sizes aggrevate aliasing
+ * meaning more vaddr bits needed to disambiguate the cache-line-op ;
+ * the existing scheme of piggybacking won't work for certain configurations.
+ * Two new registers IC_PTAG and DC_PTAG inttoduced.
+ * "tag" bits are provided in PTAG, index bits in existing IVIL/IVDL/FLDL regs
+ */
+
+/***********************************************************
+ * Machine specific helpers for per line I-Cache invalidate.
+ * 3 routines to accpunt for 1, 2, 4 aliases possible
+ */
+
+static void __ic_line_inv_no_alias(unsigned long start, int num_lines)
+{
+	while (num_lines-- > 0) {
+#if (CONFIG_ARC_MMU_VER > 2)
+		write_aux_reg(ARC_REG_IC_PTAG, start);
+#endif
+		write_aux_reg(ARC_REG_IC_IVIL, start);
+		start += ARC_ICACHE_LINE_LEN;
+	}
+}
+
+static void __ic_line_inv_2_alias(unsigned long start, int num_lines)
+{
+	while (num_lines-- > 0) {
+
+#if (CONFIG_ARC_MMU_VER > 2)
+		/*
+		 *  MMU v3, CDU prog model (for line ops) now uses a new IC_PTAG
+		 * reg to pass the "tag" bits and existing IVIL reg only looks
+		 * at bits relevant for "index" (details above)
+		 * Programming Notes:
+		 * -when writing tag to PTAG reg, bit chopping can be avoided,
+		 *  CDU ignores non-tag bits.
+		 * -Ideally "index" must be computed from vaddr, but it is not
+		 *  avail in these rtns. So to be safe, we kill the lines in all
+		 *  possible indexes corresp to num of aliases possible for
+		 *  given cache config.
+		 */
+		write_aux_reg(ARC_REG_IC_PTAG, start);
+		write_aux_reg(ARC_REG_IC_IVIL,
+				  start & ~(0x1 << PAGE_SHIFT));
+		write_aux_reg(ARC_REG_IC_IVIL, start | (0x1 << PAGE_SHIFT));
+#else
+		write_aux_reg(ARC_REG_IC_IVIL, start);
+		write_aux_reg(ARC_REG_IC_IVIL, start | 0x01);
+#endif
+		start += ARC_ICACHE_LINE_LEN;
+	}
+}
+
+static void __ic_line_inv_4_alias(unsigned long start, int num_lines)
+{
+	while (num_lines-- > 0) {
+
+#if (CONFIG_ARC_MMU_VER > 2)
+		write_aux_reg(ARC_REG_IC_PTAG, start);
+
+		write_aux_reg(ARC_REG_IC_IVIL,
+				  start & ~(0x3 << PAGE_SHIFT));
+		write_aux_reg(ARC_REG_IC_IVIL,
+				  start & ~(0x2 << PAGE_SHIFT));
+		write_aux_reg(ARC_REG_IC_IVIL,
+				  start & ~(0x1 << PAGE_SHIFT));
+		write_aux_reg(ARC_REG_IC_IVIL, start | (0x3 << PAGE_SHIFT));
+#else
+		write_aux_reg(ARC_REG_IC_IVIL, start);
+		write_aux_reg(ARC_REG_IC_IVIL, start | 0x01);
+		write_aux_reg(ARC_REG_IC_IVIL, start | 0x02);
+		write_aux_reg(ARC_REG_IC_IVIL, start | 0x03);
+#endif
+		start += ARC_ICACHE_LINE_LEN;
+	}
+}
+
+static void __ic_line_inv(unsigned long start, unsigned long sz)
+{
+	unsigned long flags;
+	int num_lines, slack;
+
+	/*
+	 * Ensure we properly floor/ceil the non-line aligned/sized requests
+	 * and have @start - aligned to cache line, and integral @num_lines
+	 * However page sized flushes can be compile time optimised.
+	 *  -@start will be cache-line aligned already (being page aligned)
+	 *  -@sz will be integral multiple of line size (being page sized).
+	 */
+	if (!(__builtin_constant_p(sz) && sz == PAGE_SIZE)) {
+		slack = start & ~ICACHE_LINE_MASK;
+		sz += slack;
+		start -= slack;
+	}
+
+	num_lines = DIV_ROUND_UP(sz, ARC_ICACHE_LINE_LEN);
+
+	local_irq_save(flags);
+	(*___flush_icache_rtn) (start, num_lines);
+	local_irq_restore(flags);
+}
+
+/* Unlike routines above, having vaddr for flush op (along with paddr),
+ * prevents the need to speculatively kill the lines in multiple sets
+ * based on ratio of way_sz : pg_sz
+ */
+static void __ic_line_inv_vaddr(unsigned long phy_start,
+					 unsigned long vaddr, unsigned long sz)
+{
+	unsigned long flags;
+	int num_lines, slack;
+	unsigned int addr;
+
+	slack = phy_start & ~ICACHE_LINE_MASK;
+	sz += slack;
+	phy_start -= slack;
+	num_lines = DIV_ROUND_UP(sz, ARC_ICACHE_LINE_LEN);
+
+#if (CONFIG_ARC_MMU_VER > 2)
+	vaddr &= ~ICACHE_LINE_MASK;
+	addr = phy_start;
+#else
+	/* bits 17:13 of vaddr go as bits 4:0 of paddr */
+	addr = phy_start | ((vaddr >> 13) & 0x1F);
+#endif
+
+	local_irq_save(flags);
+	while (num_lines-- > 0) {
+#if (CONFIG_ARC_MMU_VER > 2)
+		/* tag comes from phy addr */
+		write_aux_reg(ARC_REG_IC_PTAG, addr);
+
+		/* index bits come from vaddr */
+		write_aux_reg(ARC_REG_IC_IVIL, vaddr);
+		vaddr += ARC_ICACHE_LINE_LEN;
+#else
+		/* this paddr contains vaddrs bits as needed */
+		write_aux_reg(ARC_REG_IC_IVIL, addr);
+#endif
+		addr += ARC_ICACHE_LINE_LEN;
+	}
+	local_irq_restore(flags);
+}
+
+#else
+
+#define __ic_line_inv(start, sz)
+#define __ic_line_inv_vaddr(pstart, vstart, sz)
+
+#endif /* CONFIG_ARC_HAS_ICACHE */
+
+
+/***********************************************************
+ * Exported APIs
+ */
+
+/* TBD: use pg_arch_1 to optimize this */
+void flush_dcache_page(struct page *page)
+{
+	__dc_line_op((unsigned long)page_address(page), PAGE_SIZE, OP_FLUSH);
+}
+EXPORT_SYMBOL(flush_dcache_page);
+
+
+void dma_cache_wback_inv(unsigned long start, unsigned long sz)
+{
+	__dc_line_op(start, sz, OP_FLUSH_N_INV);
+}
+EXPORT_SYMBOL(dma_cache_wback_inv);
+
+void dma_cache_inv(unsigned long start, unsigned long sz)
+{
+	__dc_line_op(start, sz, OP_INV);
+}
+EXPORT_SYMBOL(dma_cache_inv);
+
+void dma_cache_wback(unsigned long start, unsigned long sz)
+{
+	__dc_line_op(start, sz, OP_FLUSH);
+}
+EXPORT_SYMBOL(dma_cache_wback);
+
+/*
+ * This is API for making I/D Caches consistent when modifying code
+ * (loadable modules, kprobes,  etc)
+ * This is called on insmod, with kernel virtual address for CODE of
+ * the module. ARC cache maintenance ops require PHY address thus we
+ * need to convert vmalloc addr to PHY addr
+ */
+void flush_icache_range(unsigned long kstart, unsigned long kend)
+{
+	unsigned int tot_sz, off, sz;
+	unsigned long phy, pfn;
+	unsigned long flags;
+
+	/* printk("Kernel Cache Cohenercy: %lx to %lx\n",kstart, kend); */
+
+	/* This is not the right API for user virtual address */
+	if (kstart < TASK_SIZE) {
+		BUG_ON("Flush icache range for user virtual addr space");
+		return;
+	}
+
+	/* Shortcut for bigger flush ranges.
+	 * Here we don't care if this was kernel virtual or phy addr
+	 */
+	tot_sz = kend - kstart;
+	if (tot_sz > PAGE_SIZE) {
+		flush_cache_all();
+		return;
+	}
+
+	/* Case: Kernel Phy addr (0x8000_0000 onwards) */
+	if (likely(kstart > PAGE_OFFSET)) {
+		__ic_line_inv(kstart, kend - kstart);
+		__dc_line_op(kstart, kend - kstart, OP_FLUSH);
+		return;
+	}
+
+	/*
+	 * Case: Kernel Vaddr (0x7000_0000 to 0x7fff_ffff)
+	 * (1) ARC Cache Maintenance ops only take Phy addr, hence special
+	 *     handling of kernel vaddr.
+	 *
+	 * (2) Despite @tot_sz being < PAGE_SIZE (bigger cases handled already),
+	 *     it still needs to handle  a 2 page scenario, where the range
+	 *     straddles across 2 virtual pages and hence need for loop
+	 */
+	while (tot_sz > 0) {
+		off = kstart % PAGE_SIZE;
+		pfn = vmalloc_to_pfn((void *)kstart);
+		phy = (pfn << PAGE_SHIFT) + off;
+		sz = min_t(unsigned int, tot_sz, PAGE_SIZE - off);
+		local_irq_save(flags);
+		__dc_line_op(phy, sz, OP_FLUSH);
+		__ic_line_inv(phy, sz);
+		local_irq_restore(flags);
+		kstart += sz;
+		tot_sz -= sz;
+	}
+}
+
+/*
+ * Optimised ver of flush_icache_range() with spec callers: ptrace/signals
+ * where vaddr is also available. This allows passing both vaddr and paddr
+ * bits to CDU for cache flush, short-circuting the current pessimistic algo
+ * which kills all possible aliases.
+ * An added adv of knowing that vaddr is user-vaddr avoids various checks
+ * and handling for k-vaddr, k-paddr as done in orig ver above
+ */
+void flush_icache_range_vaddr(unsigned long paddr, unsigned long u_vaddr,
+			      int len)
+{
+	__ic_line_inv_vaddr(paddr, u_vaddr, len);
+	__dc_line_op(paddr, len, OP_FLUSH);
+}
+
+/*
+ * XXX: This also needs to be optim using pg_arch_1
+ * This is called when a page-cache page is about to be mapped into a
+ * user process' address space.  It offers an opportunity for a
+ * port to ensure d-cache/i-cache coherency if necessary.
+ */
+void flush_icache_page(struct vm_area_struct *vma, struct page *page)
+{
+	if (!(vma->vm_flags & VM_EXEC))
+		return;
+
+	__ic_line_inv((unsigned long)page_address(page), PAGE_SIZE);
+}
+
+void flush_icache_all(void)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+
+	write_aux_reg(ARC_REG_IC_IVIC, 1);
+
+	/* lr will not complete till the icache inv operation is not over */
+	read_aux_reg(ARC_REG_IC_CTRL);
+	local_irq_restore(flags);
+}
+
+noinline void flush_cache_all(void)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+
+	flush_icache_all();
+	__dc_entire_op(OP_FLUSH_N_INV);
+
+	local_irq_restore(flags);
+
+}
+
+/**********************************************************************
+ * Explicit Cache flush request from user space via syscall
+ * Needed for JITs which generate code on the fly
+ */
+SYSCALL_DEFINE3(cacheflush, uint32_t, start, uint32_t, sz, uint32_t, flags)
+{
+	/* TBD: optimize this */
+	flush_cache_all();
+	return 0;
+}
diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c
new file mode 100644
index 000000000000..12cc6485b218
--- /dev/null
+++ b/arch/arc/mm/dma.c
@@ -0,0 +1,94 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*
+ * DMA Coherent API Notes
+ *
+ * I/O is inherently non-coherent on ARC. So a coherent DMA buffer is
+ * implemented by accessintg it using a kernel virtual address, with
+ * Cache bit off in the TLB entry.
+ *
+ * The default DMA address == Phy address which is 0x8000_0000 based.
+ * A platform/device can make it zero based, by over-riding
+ * plat_{dma,kernel}_addr_to_{kernel,dma}
+ */
+
+#include <linux/dma-mapping.h>
+#include <linux/dma-debug.h>
+#include <linux/export.h>
+#include <asm/cacheflush.h>
+
+/*
+ * Helpers for Coherent DMA API.
+ */
+void *dma_alloc_noncoherent(struct device *dev, size_t size,
+			    dma_addr_t *dma_handle, gfp_t gfp)
+{
+	void *paddr;
+
+	/* This is linear addr (0x8000_0000 based) */
+	paddr = alloc_pages_exact(size, gfp);
+	if (!paddr)
+		return NULL;
+
+	/* This is bus address, platform dependent */
+	*dma_handle = plat_kernel_addr_to_dma(dev, paddr);
+
+	return paddr;
+}
+EXPORT_SYMBOL(dma_alloc_noncoherent);
+
+void dma_free_noncoherent(struct device *dev, size_t size, void *vaddr,
+			  dma_addr_t dma_handle)
+{
+	free_pages_exact((void *)plat_dma_addr_to_kernel(dev, dma_handle),
+			 size);
+}
+EXPORT_SYMBOL(dma_free_noncoherent);
+
+void *dma_alloc_coherent(struct device *dev, size_t size,
+			 dma_addr_t *dma_handle, gfp_t gfp)
+{
+	void *paddr, *kvaddr;
+
+	/* This is linear addr (0x8000_0000 based) */
+	paddr = alloc_pages_exact(size, gfp);
+	if (!paddr)
+		return NULL;
+
+	/* This is kernel Virtual address (0x7000_0000 based) */
+	kvaddr = ioremap_nocache((unsigned long)paddr, size);
+	if (kvaddr != NULL)
+		memset(kvaddr, 0, size);
+
+	/* This is bus address, platform dependent */
+	*dma_handle = plat_kernel_addr_to_dma(dev, paddr);
+
+	return kvaddr;
+}
+EXPORT_SYMBOL(dma_alloc_coherent);
+
+void dma_free_coherent(struct device *dev, size_t size, void *kvaddr,
+		       dma_addr_t dma_handle)
+{
+	iounmap((void __force __iomem *)kvaddr);
+
+	free_pages_exact((void *)plat_dma_addr_to_kernel(dev, dma_handle),
+			 size);
+}
+EXPORT_SYMBOL(dma_free_coherent);
+
+/*
+ * Helper for streaming DMA...
+ */
+void __arc_dma_cache_sync(unsigned long paddr, size_t size,
+			  enum dma_data_direction dir)
+{
+	__inline_dma_cache_sync(paddr, size, dir);
+}
+EXPORT_SYMBOL(__arc_dma_cache_sync);
diff --git a/arch/arc/mm/extable.c b/arch/arc/mm/extable.c
new file mode 100644
index 000000000000..014172ba8432
--- /dev/null
+++ b/arch/arc/mm/extable.c
@@ -0,0 +1,63 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Borrowed heavily from MIPS
+ */
+
+#include <linux/module.h>
+#include <linux/uaccess.h>
+
+int fixup_exception(struct pt_regs *regs)
+{
+	const struct exception_table_entry *fixup;
+
+	fixup = search_exception_tables(instruction_pointer(regs));
+	if (fixup) {
+		regs->ret = fixup->fixup;
+
+		return 1;
+	}
+
+	return 0;
+}
+
+#ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE
+
+long arc_copy_from_user_noinline(void *to, const void __user * from,
+		unsigned long n)
+{
+	return __arc_copy_from_user(to, from, n);
+}
+EXPORT_SYMBOL(arc_copy_from_user_noinline);
+
+long arc_copy_to_user_noinline(void __user *to, const void *from,
+		unsigned long n)
+{
+	return __arc_copy_to_user(to, from, n);
+}
+EXPORT_SYMBOL(arc_copy_to_user_noinline);
+
+unsigned long arc_clear_user_noinline(void __user *to,
+		unsigned long n)
+{
+	return __arc_clear_user(to, n);
+}
+EXPORT_SYMBOL(arc_clear_user_noinline);
+
+long arc_strncpy_from_user_noinline (char *dst, const char __user *src,
+		long count)
+{
+	return __arc_strncpy_from_user(dst, src, count);
+}
+EXPORT_SYMBOL(arc_strncpy_from_user_noinline);
+
+long arc_strnlen_user_noinline(const char __user *src, long n)
+{
+	return __arc_strnlen_user(src, n);
+}
+EXPORT_SYMBOL(arc_strnlen_user_noinline);
+#endif
diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c
new file mode 100644
index 000000000000..af55aab803d2
--- /dev/null
+++ b/arch/arc/mm/fault.c
@@ -0,0 +1,228 @@
+/* Page Fault Handling for ARC (TLB Miss / ProtV)
+ *
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/signal.h>
+#include <linux/interrupt.h>
+#include <linux/sched.h>
+#include <linux/errno.h>
+#include <linux/ptrace.h>
+#include <linux/version.h>
+#include <linux/uaccess.h>
+#include <linux/kdebug.h>
+#include <asm/pgalloc.h>
+
+static int handle_vmalloc_fault(struct mm_struct *mm, unsigned long address)
+{
+	/*
+	 * Synchronize this task's top level page-table
+	 * with the 'reference' page table.
+	 */
+	pgd_t *pgd, *pgd_k;
+	pud_t *pud, *pud_k;
+	pmd_t *pmd, *pmd_k;
+
+	pgd = pgd_offset_fast(mm, address);
+	pgd_k = pgd_offset_k(address);
+
+	if (!pgd_present(*pgd_k))
+		goto bad_area;
+
+	pud = pud_offset(pgd, address);
+	pud_k = pud_offset(pgd_k, address);
+	if (!pud_present(*pud_k))
+		goto bad_area;
+
+	pmd = pmd_offset(pud, address);
+	pmd_k = pmd_offset(pud_k, address);
+	if (!pmd_present(*pmd_k))
+		goto bad_area;
+
+	set_pmd(pmd, *pmd_k);
+
+	/* XXX: create the TLB entry here */
+	return 0;
+
+bad_area:
+	return 1;
+}
+
+void do_page_fault(struct pt_regs *regs, int write, unsigned long address,
+		   unsigned long cause_code)
+{
+	struct vm_area_struct *vma = NULL;
+	struct task_struct *tsk = current;
+	struct mm_struct *mm = tsk->mm;
+	siginfo_t info;
+	int fault, ret;
+	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
+				(write ? FAULT_FLAG_WRITE : 0);
+
+	/*
+	 * We fault-in kernel-space virtual memory on-demand. The
+	 * 'reference' page table is init_mm.pgd.
+	 *
+	 * NOTE! We MUST NOT take any locks for this case. We may
+	 * be in an interrupt or a critical region, and should
+	 * only copy the information from the master page table,
+	 * nothing more.
+	 */
+	if (address >= VMALLOC_START && address <= VMALLOC_END) {
+		ret = handle_vmalloc_fault(mm, address);
+		if (unlikely(ret))
+			goto bad_area_nosemaphore;
+		else
+			return;
+	}
+
+	info.si_code = SEGV_MAPERR;
+
+	/*
+	 * If we're in an interrupt or have no user
+	 * context, we must not take the fault..
+	 */
+	if (in_atomic() || !mm)
+		goto no_context;
+
+retry:
+	down_read(&mm->mmap_sem);
+	vma = find_vma(mm, address);
+	if (!vma)
+		goto bad_area;
+	if (vma->vm_start <= address)
+		goto good_area;
+	if (!(vma->vm_flags & VM_GROWSDOWN))
+		goto bad_area;
+	if (expand_stack(vma, address))
+		goto bad_area;
+
+	/*
+	 * Ok, we have a good vm_area for this memory access, so
+	 * we can handle it..
+	 */
+good_area:
+	info.si_code = SEGV_ACCERR;
+
+	/* Handle protection violation, execute on heap or stack */
+
+	if (cause_code == ((ECR_V_PROTV << 16) | ECR_C_PROTV_INST_FETCH))
+		goto bad_area;
+
+	if (write) {
+		if (!(vma->vm_flags & VM_WRITE))
+			goto bad_area;
+	} else {
+		if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
+			goto bad_area;
+	}
+
+survive:
+	/*
+	 * If for any reason at all we couldn't handle the fault,
+	 * make sure we exit gracefully rather than endlessly redo
+	 * the fault.
+	 */
+	fault = handle_mm_fault(mm, vma, address, flags);
+
+	/* If Pagefault was interrupted by SIGKILL, exit page fault "early" */
+	if (unlikely(fatal_signal_pending(current))) {
+		if ((fault & VM_FAULT_ERROR) && !(fault & VM_FAULT_RETRY))
+			up_read(&mm->mmap_sem);
+		if (user_mode(regs))
+			return;
+	}
+
+	if (likely(!(fault & VM_FAULT_ERROR))) {
+		if (flags & FAULT_FLAG_ALLOW_RETRY) {
+			/* To avoid updating stats twice for retry case */
+			if (fault & VM_FAULT_MAJOR)
+				tsk->maj_flt++;
+			else
+				tsk->min_flt++;
+
+			if (fault & VM_FAULT_RETRY) {
+				flags &= ~FAULT_FLAG_ALLOW_RETRY;
+				flags |= FAULT_FLAG_TRIED;
+				goto retry;
+			}
+		}
+
+		/* Fault Handled Gracefully */
+		up_read(&mm->mmap_sem);
+		return;
+	}
+
+	/* TBD: switch to pagefault_out_of_memory() */
+	if (fault & VM_FAULT_OOM)
+		goto out_of_memory;
+	else if (fault & VM_FAULT_SIGBUS)
+		goto do_sigbus;
+
+	/* no man's land */
+	BUG();
+
+	/*
+	 * Something tried to access memory that isn't in our memory map..
+	 * Fix it, but check if it's kernel or user first..
+	 */
+bad_area:
+	up_read(&mm->mmap_sem);
+
+bad_area_nosemaphore:
+	/* User mode accesses just cause a SIGSEGV */
+	if (user_mode(regs)) {
+		tsk->thread.fault_address = address;
+		tsk->thread.cause_code = cause_code;
+		info.si_signo = SIGSEGV;
+		info.si_errno = 0;
+		/* info.si_code has been set above */
+		info.si_addr = (void __user *)address;
+		force_sig_info(SIGSEGV, &info, tsk);
+		return;
+	}
+
+no_context:
+	/* Are we prepared to handle this kernel fault?
+	 *
+	 * (The kernel has valid exception-points in the source
+	 *  when it acesses user-memory. When it fails in one
+	 *  of those points, we find it in a table and do a jump
+	 *  to some fixup code that loads an appropriate error
+	 *  code)
+	 */
+	if (fixup_exception(regs))
+		return;
+
+	die("Oops", regs, address, cause_code);
+
+out_of_memory:
+	if (is_global_init(tsk)) {
+		yield();
+		goto survive;
+	}
+	up_read(&mm->mmap_sem);
+
+	if (user_mode(regs))
+		do_group_exit(SIGKILL);	/* This will never return */
+
+	goto no_context;
+
+do_sigbus:
+	up_read(&mm->mmap_sem);
+
+	if (!user_mode(regs))
+		goto no_context;
+
+	tsk->thread.fault_address = address;
+	tsk->thread.cause_code = cause_code;
+	info.si_signo = SIGBUS;
+	info.si_errno = 0;
+	info.si_code = BUS_ADRERR;
+	info.si_addr = (void __user *)address;
+	force_sig_info(SIGBUS, &info, tsk);
+}
diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c
new file mode 100644
index 000000000000..caf797de23fc
--- /dev/null
+++ b/arch/arc/mm/init.c
@@ -0,0 +1,187 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/bootmem.h>
+#include <linux/memblock.h>
+#ifdef CONFIG_BLOCK_DEV_RAM
+#include <linux/blk.h>
+#endif
+#include <linux/swap.h>
+#include <linux/module.h>
+#include <asm/page.h>
+#include <asm/pgalloc.h>
+#include <asm/sections.h>
+#include <asm/arcregs.h>
+
+pgd_t swapper_pg_dir[PTRS_PER_PGD] __aligned(PAGE_SIZE);
+char empty_zero_page[PAGE_SIZE] __aligned(PAGE_SIZE);
+EXPORT_SYMBOL(empty_zero_page);
+
+/* Default tot mem from .config */
+static unsigned long arc_mem_sz = 0x20000000;  /* some default */
+
+/* User can over-ride above with "mem=nnn[KkMm]" in cmdline */
+static int __init setup_mem_sz(char *str)
+{
+	arc_mem_sz = memparse(str, NULL) & PAGE_MASK;
+
+	/* early console might not be setup yet - it will show up later */
+	pr_info("\"mem=%s\": mem sz set to %ldM\n", str, TO_MB(arc_mem_sz));
+
+	return 0;
+}
+early_param("mem", setup_mem_sz);
+
+void __init early_init_dt_add_memory_arch(u64 base, u64 size)
+{
+	arc_mem_sz = size & PAGE_MASK;
+	pr_info("Memory size set via devicetree %ldM\n", TO_MB(arc_mem_sz));
+}
+
+/*
+ * First memory setup routine called from setup_arch()
+ * 1. setup swapper's mm @init_mm
+ * 2. Count the pages we have and setup bootmem allocator
+ * 3. zone setup
+ */
+void __init setup_arch_memory(void)
+{
+	unsigned long zones_size[MAX_NR_ZONES] = { 0, 0 };
+	unsigned long end_mem = CONFIG_LINUX_LINK_BASE + arc_mem_sz;
+
+	init_mm.start_code = (unsigned long)_text;
+	init_mm.end_code = (unsigned long)_etext;
+	init_mm.end_data = (unsigned long)_edata;
+	init_mm.brk = (unsigned long)_end;
+
+	/*
+	 * We do it here, so that memory is correctly instantiated
+	 * even if "mem=xxx" cmline over-ride is given and/or
+	 * DT has memory node. Each causes an update to @arc_mem_sz
+	 * and we finally add memory one here
+	 */
+	memblock_add(CONFIG_LINUX_LINK_BASE, arc_mem_sz);
+
+	/*------------- externs in mm need setting up ---------------*/
+
+	/* first page of system - kernel .vector starts here */
+	min_low_pfn = PFN_DOWN(CONFIG_LINUX_LINK_BASE);
+
+	/* Last usable page of low mem (no HIGHMEM yet for ARC port) */
+	max_low_pfn = max_pfn = PFN_DOWN(end_mem);
+
+	max_mapnr = num_physpages = max_low_pfn - min_low_pfn;
+
+	/*------------- reserve kernel image -----------------------*/
+	memblock_reserve(CONFIG_LINUX_LINK_BASE,
+			 __pa(_end) - CONFIG_LINUX_LINK_BASE);
+
+	memblock_dump_all();
+
+	/*-------------- node setup --------------------------------*/
+	memset(zones_size, 0, sizeof(zones_size));
+	zones_size[ZONE_NORMAL] = num_physpages;
+
+	/*
+	 * We can't use the helper free_area_init(zones[]) because it uses
+	 * PAGE_OFFSET to compute the @min_low_pfn which would be wrong
+	 * when our kernel doesn't start at PAGE_OFFSET, i.e.
+	 * PAGE_OFFSET != CONFIG_LINUX_LINK_BASE
+	 */
+	free_area_init_node(0,			/* node-id */
+			    zones_size,		/* num pages per zone */
+			    min_low_pfn,	/* first pfn of node */
+			    NULL);		/* NO holes */
+}
+
+/*
+ * mem_init - initializes memory
+ *
+ * Frees up bootmem
+ * Calculates and displays memory available/used
+ */
+void __init mem_init(void)
+{
+	int codesize, datasize, initsize, reserved_pages, free_pages;
+	int tmp;
+
+	high_memory = (void *)(CONFIG_LINUX_LINK_BASE + arc_mem_sz);
+
+	totalram_pages = free_all_bootmem();
+
+	/* count all reserved pages [kernel code/data/mem_map..] */
+	reserved_pages = 0;
+	for (tmp = 0; tmp < max_mapnr; tmp++)
+		if (PageReserved(mem_map + tmp))
+			reserved_pages++;
+
+	/* XXX: nr_free_pages() is equivalent */
+	free_pages = max_mapnr - reserved_pages;
+
+	/*
+	 * For the purpose of display below, split the "reserve mem"
+	 * kernel code/data is already shown explicitly,
+	 * Show any other reservations (mem_map[ ] et al)
+	 */
+	reserved_pages -= (((unsigned int)_end - CONFIG_LINUX_LINK_BASE) >>
+								PAGE_SHIFT);
+
+	codesize = _etext - _text;
+	datasize = _end - _etext;
+	initsize = __init_end - __init_begin;
+
+	pr_info("Memory Available: %dM / %ldM (%dK code, %dK data, %dK init, %dK reserv)\n",
+		PAGES_TO_MB(free_pages),
+		TO_MB(arc_mem_sz),
+		TO_KB(codesize), TO_KB(datasize), TO_KB(initsize),
+		PAGES_TO_KB(reserved_pages));
+}
+
+static void __init free_init_pages(const char *what, unsigned long begin,
+				   unsigned long end)
+{
+	unsigned long addr;
+
+	pr_info("Freeing %s: %ldk [%lx] to [%lx]\n",
+		what, TO_KB(end - begin), begin, end);
+
+	/* need to check that the page we free is not a partial page */
+	for (addr = begin; addr + PAGE_SIZE <= end; addr += PAGE_SIZE) {
+		ClearPageReserved(virt_to_page(addr));
+		init_page_count(virt_to_page(addr));
+		free_page(addr);
+		totalram_pages++;
+	}
+}
+
+/*
+ * free_initmem: Free all the __init memory.
+ */
+void __init_refok free_initmem(void)
+{
+	free_init_pages("unused kernel memory",
+			(unsigned long)__init_begin,
+			(unsigned long)__init_end);
+}
+
+#ifdef CONFIG_BLK_DEV_INITRD
+void __init free_initrd_mem(unsigned long start, unsigned long end)
+{
+	free_init_pages("initrd memory", start, end);
+}
+#endif
+
+#ifdef CONFIG_OF_FLATTREE
+void __init early_init_dt_setup_initrd_arch(unsigned long start,
+					    unsigned long end)
+{
+	pr_err("%s(%lx, %lx)\n", __func__, start, end);
+}
+#endif /* CONFIG_OF_FLATTREE */
diff --git a/arch/arc/mm/ioremap.c b/arch/arc/mm/ioremap.c
new file mode 100644
index 000000000000..3e5c92c79936
--- /dev/null
+++ b/arch/arc/mm/ioremap.c
@@ -0,0 +1,91 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/vmalloc.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/io.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <asm/cache.h>
+
+void __iomem *ioremap(unsigned long paddr, unsigned long size)
+{
+	unsigned long end;
+
+	/* Don't allow wraparound or zero size */
+	end = paddr + size - 1;
+	if (!size || (end < paddr))
+		return NULL;
+
+	/* If the region is h/w uncached, avoid MMU mappings */
+	if (paddr >= ARC_UNCACHED_ADDR_SPACE)
+		return (void __iomem *)paddr;
+
+	return ioremap_prot(paddr, size, PAGE_KERNEL_NO_CACHE);
+}
+EXPORT_SYMBOL(ioremap);
+
+/*
+ * ioremap with access flags
+ * Cache semantics wise it is same as ioremap - "forced" uncached.
+ * However unline vanilla ioremap which bypasses ARC MMU for addresses in
+ * ARC hardware uncached region, this one still goes thru the MMU as caller
+ * might need finer access control (R/W/X)
+ */
+void __iomem *ioremap_prot(phys_addr_t paddr, unsigned long size,
+			   unsigned long flags)
+{
+	void __iomem *vaddr;
+	struct vm_struct *area;
+	unsigned long off, end;
+	pgprot_t prot = __pgprot(flags);
+
+	/* Don't allow wraparound, zero size */
+	end = paddr + size - 1;
+	if ((!size) || (end < paddr))
+		return NULL;
+
+	/* An early platform driver might end up here */
+	if (!slab_is_available())
+		return NULL;
+
+	/* force uncached */
+	prot = pgprot_noncached(prot);
+
+	/* Mappings have to be page-aligned */
+	off = paddr & ~PAGE_MASK;
+	paddr &= PAGE_MASK;
+	size = PAGE_ALIGN(end + 1) - paddr;
+
+	/*
+	 * Ok, go for it..
+	 */
+	area = get_vm_area(size, VM_IOREMAP);
+	if (!area)
+		return NULL;
+	area->phys_addr = paddr;
+	vaddr = (void __iomem *)area->addr;
+	if (ioremap_page_range((unsigned long)vaddr,
+			       (unsigned long)vaddr + size, paddr, prot)) {
+		vunmap((void __force *)vaddr);
+		return NULL;
+	}
+	return (void __iomem *)(off + (char __iomem *)vaddr);
+}
+EXPORT_SYMBOL(ioremap_prot);
+
+
+void iounmap(const void __iomem *addr)
+{
+	if (addr >= (void __force __iomem *)ARC_UNCACHED_ADDR_SPACE)
+		return;
+
+	vfree((void *)(PAGE_MASK & (unsigned long __force)addr));
+}
+EXPORT_SYMBOL(iounmap);
diff --git a/arch/arc/mm/tlb.c b/arch/arc/mm/tlb.c
new file mode 100644
index 000000000000..9b9ce23f4ec3
--- /dev/null
+++ b/arch/arc/mm/tlb.c
@@ -0,0 +1,645 @@
+/*
+ * TLB Management (flush/create/diagnostics) for ARC700
+ *
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * vineetg: Aug 2011
+ *  -Reintroduce duplicate PD fixup - some customer chips still have the issue
+ *
+ * vineetg: May 2011
+ *  -No need to flush_cache_page( ) for each call to update_mmu_cache()
+ *   some of the LMBench tests improved amazingly
+ *      = page-fault thrice as fast (75 usec to 28 usec)
+ *      = mmap twice as fast (9.6 msec to 4.6 msec),
+ *      = fork (5.3 msec to 3.7 msec)
+ *
+ * vineetg: April 2011 :
+ *  -MMU v3: PD{0,1} bits layout changed: They don't overlap anymore,
+ *      helps avoid a shift when preparing PD0 from PTE
+ *
+ * vineetg: April 2011 : Preparing for MMU V3
+ *  -MMU v2/v3 BCRs decoded differently
+ *  -Remove TLB_SIZE hardcoding as it's variable now: 256 or 512
+ *  -tlb_entry_erase( ) can be void
+ *  -local_flush_tlb_range( ):
+ *      = need not "ceil" @end
+ *      = walks MMU only if range spans < 32 entries, as opposed to 256
+ *
+ * Vineetg: Sept 10th 2008
+ *  -Changes related to MMU v2 (Rel 4.8)
+ *
+ * Vineetg: Aug 29th 2008
+ *  -In TLB Flush operations (Metal Fix MMU) there is a explict command to
+ *    flush Micro-TLBS. If TLB Index Reg is invalid prior to TLBIVUTLB cmd,
+ *    it fails. Thus need to load it with ANY valid value before invoking
+ *    TLBIVUTLB cmd
+ *
+ * Vineetg: Aug 21th 2008:
+ *  -Reduced the duration of IRQ lockouts in TLB Flush routines
+ *  -Multiple copies of TLB erase code seperated into a "single" function
+ *  -In TLB Flush routines, interrupt disabling moved UP to retrieve ASID
+ *       in interrupt-safe region.
+ *
+ * Vineetg: April 23rd Bug #93131
+ *    Problem: tlb_flush_kernel_range() doesnt do anything if the range to
+ *              flush is more than the size of TLB itself.
+ *
+ * Rahul Trivedi : Codito Technologies 2004
+ */
+
+#include <linux/module.h>
+#include <asm/arcregs.h>
+#include <asm/setup.h>
+#include <asm/mmu_context.h>
+#include <asm/tlb.h>
+
+/*			Need for ARC MMU v2
+ *
+ * ARC700 MMU-v1 had a Joint-TLB for Code and Data and is 2 way set-assoc.
+ * For a memcpy operation with 3 players (src/dst/code) such that all 3 pages
+ * map into same set, there would be contention for the 2 ways causing severe
+ * Thrashing.
+ *
+ * Although J-TLB is 2 way set assoc, ARC700 caches J-TLB into uTLBS which has
+ * much higher associativity. u-D-TLB is 8 ways, u-I-TLB is 4 ways.
+ * Given this, the thrasing problem should never happen because once the 3
+ * J-TLB entries are created (even though 3rd will knock out one of the prev
+ * two), the u-D-TLB and u-I-TLB will have what is required to accomplish memcpy
+ *
+ * Yet we still see the Thrashing because a J-TLB Write cause flush of u-TLBs.
+ * This is a simple design for keeping them in sync. So what do we do?
+ * The solution which James came up was pretty neat. It utilised the assoc
+ * of uTLBs by not invalidating always but only when absolutely necessary.
+ *
+ * - Existing TLB commands work as before
+ * - New command (TLBWriteNI) for TLB write without clearing uTLBs
+ * - New command (TLBIVUTLB) to invalidate uTLBs.
+ *
+ * The uTLBs need only be invalidated when pages are being removed from the
+ * OS page table. If a 'victim' TLB entry is being overwritten in the main TLB
+ * as a result of a miss, the removed entry is still allowed to exist in the
+ * uTLBs as it is still valid and present in the OS page table. This allows the
+ * full associativity of the uTLBs to hide the limited associativity of the main
+ * TLB.
+ *
+ * During a miss handler, the new "TLBWriteNI" command is used to load
+ * entries without clearing the uTLBs.
+ *
+ * When the OS page table is updated, TLB entries that may be associated with a
+ * removed page are removed (flushed) from the TLB using TLBWrite. In this
+ * circumstance, the uTLBs must also be cleared. This is done by using the
+ * existing TLBWrite command. An explicit IVUTLB is also required for those
+ * corner cases when TLBWrite was not executed at all because the corresp
+ * J-TLB entry got evicted/replaced.
+ */
+
+/* A copy of the ASID from the PID reg is kept in asid_cache */
+int asid_cache = FIRST_ASID;
+
+/* ASID to mm struct mapping. We have one extra entry corresponding to
+ * NO_ASID to save us a compare when clearing the mm entry for old asid
+ * see get_new_mmu_context (asm-arc/mmu_context.h)
+ */
+struct mm_struct *asid_mm_map[NUM_ASID + 1];
+
+/*
+ * Utility Routine to erase a J-TLB entry
+ * The procedure is to look it up in the MMU. If found, ERASE it by
+ *  issuing a TlbWrite CMD with PD0 = PD1 = 0
+ */
+
+static void __tlb_entry_erase(void)
+{
+	write_aux_reg(ARC_REG_TLBPD1, 0);
+	write_aux_reg(ARC_REG_TLBPD0, 0);
+	write_aux_reg(ARC_REG_TLBCOMMAND, TLBWrite);
+}
+
+static void tlb_entry_erase(unsigned int vaddr_n_asid)
+{
+	unsigned int idx;
+
+	/* Locate the TLB entry for this vaddr + ASID */
+	write_aux_reg(ARC_REG_TLBPD0, vaddr_n_asid);
+	write_aux_reg(ARC_REG_TLBCOMMAND, TLBProbe);
+	idx = read_aux_reg(ARC_REG_TLBINDEX);
+
+	/* No error means entry found, zero it out */
+	if (likely(!(idx & TLB_LKUP_ERR))) {
+		__tlb_entry_erase();
+	} else {		/* Some sort of Error */
+
+		/* Duplicate entry error */
+		if (idx & 0x1) {
+			/* TODO we need to handle this case too */
+			pr_emerg("unhandled Duplicate flush for %x\n",
+			       vaddr_n_asid);
+		}
+		/* else entry not found so nothing to do */
+	}
+}
+
+/****************************************************************************
+ * ARC700 MMU caches recently used J-TLB entries (RAM) as uTLBs (FLOPs)
+ *
+ * New IVUTLB cmd in MMU v2 explictly invalidates the uTLB
+ *
+ * utlb_invalidate ( )
+ *  -For v2 MMU calls Flush uTLB Cmd
+ *  -For v1 MMU does nothing (except for Metal Fix v1 MMU)
+ *      This is because in v1 TLBWrite itself invalidate uTLBs
+ ***************************************************************************/
+
+static void utlb_invalidate(void)
+{
+#if (CONFIG_ARC_MMU_VER >= 2)
+
+#if (CONFIG_ARC_MMU_VER < 3)
+	/* MMU v2 introduced the uTLB Flush command.
+	 * There was however an obscure hardware bug, where uTLB flush would
+	 * fail when a prior probe for J-TLB (both totally unrelated) would
+	 * return lkup err - because the entry didnt exist in MMU.
+	 * The Workround was to set Index reg with some valid value, prior to
+	 * flush. This was fixed in MMU v3 hence not needed any more
+	 */
+	unsigned int idx;
+
+	/* make sure INDEX Reg is valid */
+	idx = read_aux_reg(ARC_REG_TLBINDEX);
+
+	/* If not write some dummy val */
+	if (unlikely(idx & TLB_LKUP_ERR))
+		write_aux_reg(ARC_REG_TLBINDEX, 0xa);
+#endif
+
+	write_aux_reg(ARC_REG_TLBCOMMAND, TLBIVUTLB);
+#endif
+
+}
+
+/*
+ * Un-conditionally (without lookup) erase the entire MMU contents
+ */
+
+noinline void local_flush_tlb_all(void)
+{
+	unsigned long flags;
+	unsigned int entry;
+	struct cpuinfo_arc_mmu *mmu = &cpuinfo_arc700[smp_processor_id()].mmu;
+
+	local_irq_save(flags);
+
+	/* Load PD0 and PD1 with template for a Blank Entry */
+	write_aux_reg(ARC_REG_TLBPD1, 0);
+	write_aux_reg(ARC_REG_TLBPD0, 0);
+
+	for (entry = 0; entry < mmu->num_tlb; entry++) {
+		/* write this entry to the TLB */
+		write_aux_reg(ARC_REG_TLBINDEX, entry);
+		write_aux_reg(ARC_REG_TLBCOMMAND, TLBWrite);
+	}
+
+	utlb_invalidate();
+
+	local_irq_restore(flags);
+}
+
+/*
+ * Flush the entrie MM for userland. The fastest way is to move to Next ASID
+ */
+noinline void local_flush_tlb_mm(struct mm_struct *mm)
+{
+	/*
+	 * Small optimisation courtesy IA64
+	 * flush_mm called during fork,exit,munmap etc, multiple times as well.
+	 * Only for fork( ) do we need to move parent to a new MMU ctxt,
+	 * all other cases are NOPs, hence this check.
+	 */
+	if (atomic_read(&mm->mm_users) == 0)
+		return;
+
+	/*
+	 * Workaround for Android weirdism:
+	 * A binder VMA could end up in a task such that vma->mm != tsk->mm
+	 * old code would cause h/w - s/w ASID to get out of sync
+	 */
+	if (current->mm != mm)
+		destroy_context(mm);
+	else
+		get_new_mmu_context(mm);
+}
+
+/*
+ * Flush a Range of TLB entries for userland.
+ * @start is inclusive, while @end is exclusive
+ * Difference between this and Kernel Range Flush is
+ *  -Here the fastest way (if range is too large) is to move to next ASID
+ *      without doing any explicit Shootdown
+ *  -In case of kernel Flush, entry has to be shot down explictly
+ */
+void local_flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
+			   unsigned long end)
+{
+	unsigned long flags;
+	unsigned int asid;
+
+	/* If range @start to @end is more than 32 TLB entries deep,
+	 * its better to move to a new ASID rather than searching for
+	 * individual entries and then shooting them down
+	 *
+	 * The calc above is rough, doesn't account for unaligned parts,
+	 * since this is heuristics based anyways
+	 */
+	if (unlikely((end - start) >= PAGE_SIZE * 32)) {
+		local_flush_tlb_mm(vma->vm_mm);
+		return;
+	}
+
+	/*
+	 * @start moved to page start: this alone suffices for checking
+	 * loop end condition below, w/o need for aligning @end to end
+	 * e.g. 2000 to 4001 will anyhow loop twice
+	 */
+	start &= PAGE_MASK;
+
+	local_irq_save(flags);
+	asid = vma->vm_mm->context.asid;
+
+	if (asid != NO_ASID) {
+		while (start < end) {
+			tlb_entry_erase(start | (asid & 0xff));
+			start += PAGE_SIZE;
+		}
+	}
+
+	utlb_invalidate();
+
+	local_irq_restore(flags);
+}
+
+/* Flush the kernel TLB entries - vmalloc/modules (Global from MMU perspective)
+ *  @start, @end interpreted as kvaddr
+ * Interestingly, shared TLB entries can also be flushed using just
+ * @start,@end alone (interpreted as user vaddr), although technically SASID
+ * is also needed. However our smart TLbProbe lookup takes care of that.
+ */
+void local_flush_tlb_kernel_range(unsigned long start, unsigned long end)
+{
+	unsigned long flags;
+
+	/* exactly same as above, except for TLB entry not taking ASID */
+
+	if (unlikely((end - start) >= PAGE_SIZE * 32)) {
+		local_flush_tlb_all();
+		return;
+	}
+
+	start &= PAGE_MASK;
+
+	local_irq_save(flags);
+	while (start < end) {
+		tlb_entry_erase(start);
+		start += PAGE_SIZE;
+	}
+
+	utlb_invalidate();
+
+	local_irq_restore(flags);
+}
+
+/*
+ * Delete TLB entry in MMU for a given page (??? address)
+ * NOTE One TLB entry contains translation for single PAGE
+ */
+
+void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long page)
+{
+	unsigned long flags;
+
+	/* Note that it is critical that interrupts are DISABLED between
+	 * checking the ASID and using it flush the TLB entry
+	 */
+	local_irq_save(flags);
+
+	if (vma->vm_mm->context.asid != NO_ASID) {
+		tlb_entry_erase((page & PAGE_MASK) |
+				(vma->vm_mm->context.asid & 0xff));
+		utlb_invalidate();
+	}
+
+	local_irq_restore(flags);
+}
+
+/*
+ * Routine to create a TLB entry
+ */
+void create_tlb(struct vm_area_struct *vma, unsigned long address, pte_t *ptep)
+{
+	unsigned long flags;
+	unsigned int idx, asid_or_sasid;
+	unsigned long pd0_flags;
+
+	/*
+	 * create_tlb() assumes that current->mm == vma->mm, since
+	 * -it ASID for TLB entry is fetched from MMU ASID reg (valid for curr)
+	 * -completes the lazy write to SASID reg (again valid for curr tsk)
+	 *
+	 * Removing the assumption involves
+	 * -Using vma->mm->context{ASID,SASID}, as opposed to MMU reg.
+	 * -Fix the TLB paranoid debug code to not trigger false negatives.
+	 * -More importantly it makes this handler inconsistent with fast-path
+	 *  TLB Refill handler which always deals with "current"
+	 *
+	 * Lets see the use cases when current->mm != vma->mm and we land here
+	 *  1. execve->copy_strings()->__get_user_pages->handle_mm_fault
+	 *     Here VM wants to pre-install a TLB entry for user stack while
+	 *     current->mm still points to pre-execve mm (hence the condition).
+	 *     However the stack vaddr is soon relocated (randomization) and
+	 *     move_page_tables() tries to undo that TLB entry.
+	 *     Thus not creating TLB entry is not any worse.
+	 *
+	 *  2. ptrace(POKETEXT) causes a CoW - debugger(current) inserting a
+	 *     breakpoint in debugged task. Not creating a TLB now is not
+	 *     performance critical.
+	 *
+	 * Both the cases above are not good enough for code churn.
+	 */
+	if (current->active_mm != vma->vm_mm)
+		return;
+
+	local_irq_save(flags);
+
+	tlb_paranoid_check(vma->vm_mm->context.asid, address);
+
+	address &= PAGE_MASK;
+
+	/* update this PTE credentials */
+	pte_val(*ptep) |= (_PAGE_PRESENT | _PAGE_ACCESSED);
+
+	/* Create HW TLB entry Flags (in PD0) from PTE Flags */
+#if (CONFIG_ARC_MMU_VER <= 2)
+	pd0_flags = ((pte_val(*ptep) & PTE_BITS_IN_PD0) >> 1);
+#else
+	pd0_flags = ((pte_val(*ptep) & PTE_BITS_IN_PD0));
+#endif
+
+	/* ASID for this task */
+	asid_or_sasid = read_aux_reg(ARC_REG_PID) & 0xff;
+
+	write_aux_reg(ARC_REG_TLBPD0, address | pd0_flags | asid_or_sasid);
+
+	/* Load remaining info in PD1 (Page Frame Addr and Kx/Kw/Kr Flags) */
+	write_aux_reg(ARC_REG_TLBPD1, (pte_val(*ptep) & PTE_BITS_IN_PD1));
+
+	/* First verify if entry for this vaddr+ASID already exists */
+	write_aux_reg(ARC_REG_TLBCOMMAND, TLBProbe);
+	idx = read_aux_reg(ARC_REG_TLBINDEX);
+
+	/*
+	 * If Not already present get a free slot from MMU.
+	 * Otherwise, Probe would have located the entry and set INDEX Reg
+	 * with existing location. This will cause Write CMD to over-write
+	 * existing entry with new PD0 and PD1
+	 */
+	if (likely(idx & TLB_LKUP_ERR))
+		write_aux_reg(ARC_REG_TLBCOMMAND, TLBGetIndex);
+
+	/*
+	 * Commit the Entry to MMU
+	 * It doesnt sound safe to use the TLBWriteNI cmd here
+	 * which doesn't flush uTLBs. I'd rather be safe than sorry.
+	 */
+	write_aux_reg(ARC_REG_TLBCOMMAND, TLBWrite);
+
+	local_irq_restore(flags);
+}
+
+/* arch hook called by core VM at the end of handle_mm_fault( ),
+ * when a new PTE is entered in Page Tables or an existing one
+ * is modified. We aggresively pre-install a TLB entry
+ */
+
+void update_mmu_cache(struct vm_area_struct *vma, unsigned long vaddress,
+		      pte_t *ptep)
+{
+
+	create_tlb(vma, vaddress, ptep);
+}
+
+/* Read the Cache Build Confuration Registers, Decode them and save into
+ * the cpuinfo structure for later use.
+ * No Validation is done here, simply read/convert the BCRs
+ */
+void __init read_decode_mmu_bcr(void)
+{
+	unsigned int tmp;
+	struct bcr_mmu_1_2 *mmu2;	/* encoded MMU2 attr */
+	struct bcr_mmu_3 *mmu3;		/* encoded MMU3 attr */
+	struct cpuinfo_arc_mmu *mmu = &cpuinfo_arc700[smp_processor_id()].mmu;
+
+	tmp = read_aux_reg(ARC_REG_MMU_BCR);
+	mmu->ver = (tmp >> 24);
+
+	if (mmu->ver <= 2) {
+		mmu2 = (struct bcr_mmu_1_2 *)&tmp;
+		mmu->pg_sz = PAGE_SIZE;
+		mmu->sets = 1 << mmu2->sets;
+		mmu->ways = 1 << mmu2->ways;
+		mmu->u_dtlb = mmu2->u_dtlb;
+		mmu->u_itlb = mmu2->u_itlb;
+	} else {
+		mmu3 = (struct bcr_mmu_3 *)&tmp;
+		mmu->pg_sz = 512 << mmu3->pg_sz;
+		mmu->sets = 1 << mmu3->sets;
+		mmu->ways = 1 << mmu3->ways;
+		mmu->u_dtlb = mmu3->u_dtlb;
+		mmu->u_itlb = mmu3->u_itlb;
+	}
+
+	mmu->num_tlb = mmu->sets * mmu->ways;
+}
+
+char *arc_mmu_mumbojumbo(int cpu_id, char *buf, int len)
+{
+	int n = 0;
+	struct cpuinfo_arc_mmu *p_mmu = &cpuinfo_arc700[smp_processor_id()].mmu;
+
+	n += scnprintf(buf + n, len - n, "ARC700 MMU [v%x]\t: %dk PAGE, ",
+		       p_mmu->ver, TO_KB(p_mmu->pg_sz));
+
+	n += scnprintf(buf + n, len - n,
+		       "J-TLB %d (%dx%d), uDTLB %d, uITLB %d, %s\n",
+		       p_mmu->num_tlb, p_mmu->sets, p_mmu->ways,
+		       p_mmu->u_dtlb, p_mmu->u_itlb,
+		       __CONFIG_ARC_MMU_SASID_VAL ? "SASID" : "");
+
+	return buf;
+}
+
+void __init arc_mmu_init(void)
+{
+	char str[256];
+	struct cpuinfo_arc_mmu *mmu = &cpuinfo_arc700[smp_processor_id()].mmu;
+
+	printk(arc_mmu_mumbojumbo(0, str, sizeof(str)));
+
+	/* For efficiency sake, kernel is compile time built for a MMU ver
+	 * This must match the hardware it is running on.
+	 * Linux built for MMU V2, if run on MMU V1 will break down because V1
+	 *  hardware doesn't understand cmds such as WriteNI, or IVUTLB
+	 * On the other hand, Linux built for V1 if run on MMU V2 will do
+	 *   un-needed workarounds to prevent memcpy thrashing.
+	 * Similarly MMU V3 has new features which won't work on older MMU
+	 */
+	if (mmu->ver != CONFIG_ARC_MMU_VER) {
+		panic("MMU ver %d doesn't match kernel built for %d...\n",
+		      mmu->ver, CONFIG_ARC_MMU_VER);
+	}
+
+	if (mmu->pg_sz != PAGE_SIZE)
+		panic("MMU pg size != PAGE_SIZE (%luk)\n", TO_KB(PAGE_SIZE));
+
+	/*
+	 * ASID mgmt data structures are compile time init
+	 *  asid_cache = FIRST_ASID and asid_mm_map[] all zeroes
+	 */
+
+	local_flush_tlb_all();
+
+	/* Enable the MMU */
+	write_aux_reg(ARC_REG_PID, MMU_ENABLE);
+
+	/* In smp we use this reg for interrupt 1 scratch */
+#ifndef CONFIG_SMP
+	/* swapper_pg_dir is the pgd for the kernel, used by vmalloc */
+	write_aux_reg(ARC_REG_SCRATCH_DATA0, swapper_pg_dir);
+#endif
+}
+
+/*
+ * TLB Programmer's Model uses Linear Indexes: 0 to {255, 511} for 128 x {2,4}
+ * The mapping is Column-first.
+ *		---------------------	-----------
+ *		|way0|way1|way2|way3|	|way0|way1|
+ *		---------------------	-----------
+ * [set0]	|  0 |  1 |  2 |  3 |	|  0 |  1 |
+ * [set1]	|  4 |  5 |  6 |  7 |	|  2 |  3 |
+ *		~		    ~	~	  ~
+ * [set127]	| 508| 509| 510| 511|	| 254| 255|
+ *		---------------------	-----------
+ * For normal operations we don't(must not) care how above works since
+ * MMU cmd getIndex(vaddr) abstracts that out.
+ * However for walking WAYS of a SET, we need to know this
+ */
+#define SET_WAY_TO_IDX(mmu, set, way)  ((set) * mmu->ways + (way))
+
+/* Handling of Duplicate PD (TLB entry) in MMU.
+ * -Could be due to buggy customer tapeouts or obscure kernel bugs
+ * -MMU complaints not at the time of duplicate PD installation, but at the
+ *      time of lookup matching multiple ways.
+ * -Ideally these should never happen - but if they do - workaround by deleting
+ *      the duplicate one.
+ * -Knob to be verbose abt it.(TODO: hook them up to debugfs)
+ */
+volatile int dup_pd_verbose = 1;/* Be slient abt it or complain (default) */
+
+void do_tlb_overlap_fault(unsigned long cause, unsigned long address,
+			  struct pt_regs *regs)
+{
+	int set, way, n;
+	unsigned int pd0[4], pd1[4];	/* assume max 4 ways */
+	unsigned long flags, is_valid;
+	struct cpuinfo_arc_mmu *mmu = &cpuinfo_arc700[smp_processor_id()].mmu;
+
+	local_irq_save(flags);
+
+	/* re-enable the MMU */
+	write_aux_reg(ARC_REG_PID, MMU_ENABLE | read_aux_reg(ARC_REG_PID));
+
+	/* loop thru all sets of TLB */
+	for (set = 0; set < mmu->sets; set++) {
+
+		/* read out all the ways of current set */
+		for (way = 0, is_valid = 0; way < mmu->ways; way++) {
+			write_aux_reg(ARC_REG_TLBINDEX,
+					  SET_WAY_TO_IDX(mmu, set, way));
+			write_aux_reg(ARC_REG_TLBCOMMAND, TLBRead);
+			pd0[way] = read_aux_reg(ARC_REG_TLBPD0);
+			pd1[way] = read_aux_reg(ARC_REG_TLBPD1);
+			is_valid |= pd0[way] & _PAGE_PRESENT;
+		}
+
+		/* If all the WAYS in SET are empty, skip to next SET */
+		if (!is_valid)
+			continue;
+
+		/* Scan the set for duplicate ways: needs a nested loop */
+		for (way = 0; way < mmu->ways; way++) {
+			if (!pd0[way])
+				continue;
+
+			for (n = way + 1; n < mmu->ways; n++) {
+				if ((pd0[way] & PAGE_MASK) ==
+				    (pd0[n] & PAGE_MASK)) {
+
+					if (dup_pd_verbose) {
+						pr_info("Duplicate PD's @"
+							"[%d:%d]/[%d:%d]\n",
+						     set, way, set, n);
+						pr_info("TLBPD0[%u]: %08x\n",
+						     way, pd0[way]);
+					}
+
+					/*
+					 * clear entry @way and not @n. This is
+					 * critical to our optimised loop
+					 */
+					pd0[way] = pd1[way] = 0;
+					write_aux_reg(ARC_REG_TLBINDEX,
+						SET_WAY_TO_IDX(mmu, set, way));
+					__tlb_entry_erase();
+				}
+			}
+		}
+	}
+
+	local_irq_restore(flags);
+}
+
+/***********************************************************************
+ * Diagnostic Routines
+ *  -Called from Low Level TLB Hanlders if things don;t look good
+ **********************************************************************/
+
+#ifdef CONFIG_ARC_DBG_TLB_PARANOIA
+
+/*
+ * Low Level ASM TLB handler calls this if it finds that HW and SW ASIDS
+ * don't match
+ */
+void print_asid_mismatch(int is_fast_path)
+{
+	int pid_sw, pid_hw;
+	pid_sw = current->active_mm->context.asid;
+	pid_hw = read_aux_reg(ARC_REG_PID) & 0xff;
+
+	pr_emerg("ASID Mismatch in %s Path Handler: sw-pid=0x%x hw-pid=0x%x\n",
+	       is_fast_path ? "Fast" : "Slow", pid_sw, pid_hw);
+
+	__asm__ __volatile__("flag 1");
+}
+
+void tlb_paranoid_check(unsigned int pid_sw, unsigned long addr)
+{
+	unsigned int pid_hw;
+
+	pid_hw = read_aux_reg(ARC_REG_PID) & 0xff;
+
+	if (addr < 0x70000000 && ((pid_hw != pid_sw) || (pid_sw == NO_ASID)))
+		print_asid_mismatch(0);
+}
+#endif
diff --git a/arch/arc/mm/tlbex.S b/arch/arc/mm/tlbex.S
new file mode 100644
index 000000000000..9df765dc7c3a
--- /dev/null
+++ b/arch/arc/mm/tlbex.S
@@ -0,0 +1,408 @@
+/*
+ * TLB Exception Handling for ARC
+ *
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Vineetg: April 2011 :
+ *  -MMU v1: moved out legacy code into a seperate file
+ *  -MMU v3: PD{0,1} bits layout changed: They don't overlap anymore,
+ *      helps avoid a shift when preparing PD0 from PTE
+ *
+ * Vineetg: July 2009
+ *  -For MMU V2, we need not do heuristics at the time of commiting a D-TLB
+ *   entry, so that it doesn't knock out it's I-TLB entry
+ *  -Some more fine tuning:
+ *   bmsk instead of add, asl.cc instead of branch, delay slot utilise etc
+ *
+ * Vineetg: July 2009
+ *  -Practically rewrote the I/D TLB Miss handlers
+ *   Now 40 and 135 instructions a peice as compared to 131 and 449 resp.
+ *   Hence Leaner by 1.5 K
+ *   Used Conditional arithmetic to replace excessive branching
+ *   Also used short instructions wherever possible
+ *
+ * Vineetg: Aug 13th 2008
+ *  -Passing ECR (Exception Cause REG) to do_page_fault( ) for printing
+ *   more information in case of a Fatality
+ *
+ * Vineetg: March 25th Bug #92690
+ *  -Added Debug Code to check if sw-ASID == hw-ASID
+
+ * Rahul Trivedi, Amit Bhor: Codito Technologies 2004
+ */
+
+	.cpu A7
+
+#include <linux/linkage.h>
+#include <asm/entry.h>
+#include <asm/tlb.h>
+#include <asm/pgtable.h>
+#include <asm/arcregs.h>
+#include <asm/cache.h>
+#include <asm/processor.h>
+#if (CONFIG_ARC_MMU_VER == 1)
+#include <asm/tlb-mmu1.h>
+#endif
+
+;--------------------------------------------------------------------------
+; scratch memory to save the registers (r0-r3) used to code TLB refill Handler
+; For details refer to comments before TLBMISS_FREEUP_REGS below
+;--------------------------------------------------------------------------
+
+ARCFP_DATA ex_saved_reg1
+	.align 1 << L1_CACHE_SHIFT	; IMP: Must be Cache Line aligned
+	.type   ex_saved_reg1, @object
+#ifdef CONFIG_SMP
+	.size   ex_saved_reg1, (CONFIG_NR_CPUS << L1_CACHE_SHIFT)
+ex_saved_reg1:
+	.zero (CONFIG_NR_CPUS << L1_CACHE_SHIFT)
+#else
+	.size   ex_saved_reg1, 16
+ex_saved_reg1:
+	.zero 16
+#endif
+
+;============================================================================
+;  Troubleshooting Stuff
+;============================================================================
+
+; Linux keeps ASID (Address Space ID) in task->active_mm->context.asid
+; When Creating TLB Entries, instead of doing 3 dependent loads from memory,
+; we use the MMU PID Reg to get current ASID.
+; In bizzare scenrios SW and HW ASID can get out-of-sync which is trouble.
+; So we try to detect this in TLB Mis shandler
+
+
+.macro DBG_ASID_MISMATCH
+
+#ifdef CONFIG_ARC_DBG_TLB_PARANOIA
+
+	; make sure h/w ASID is same as s/w ASID
+
+	GET_CURR_TASK_ON_CPU  r3
+	ld r0, [r3, TASK_ACT_MM]
+	ld r0, [r0, MM_CTXT+MM_CTXT_ASID]
+
+	lr r1, [ARC_REG_PID]
+	and r1, r1, 0xFF
+	breq r1, r0, 5f
+
+	; Error if H/w and S/w ASID don't match, but NOT if in kernel mode
+	lr  r0, [erstatus]
+	bbit0 r0, STATUS_U_BIT, 5f
+
+	; We sure are in troubled waters, Flag the error, but to do so
+	; need to switch to kernel mode stack to call error routine
+	GET_TSK_STACK_BASE   r3, sp
+
+	; Call printk to shoutout aloud
+	mov r0, 1
+	j print_asid_mismatch
+
+5:   ; ASIDs match so proceed normally
+	nop
+
+#endif
+
+.endm
+
+;============================================================================
+;TLB Miss handling Code
+;============================================================================
+
+;-----------------------------------------------------------------------------
+; This macro does the page-table lookup for the faulting address.
+; OUT: r0 = PTE faulted on, r1 = ptr to PTE, r2 = Faulting V-address
+.macro LOAD_FAULT_PTE
+
+	lr  r2, [efa]
+
+#ifndef CONFIG_SMP
+	lr  r1, [ARC_REG_SCRATCH_DATA0] ; current pgd
+#else
+	GET_CURR_TASK_ON_CPU  r1
+	ld  r1, [r1, TASK_ACT_MM]
+	ld  r1, [r1, MM_PGD]
+#endif
+
+	lsr     r0, r2, PGDIR_SHIFT     ; Bits for indexing into PGD
+	ld.as   r1, [r1, r0]            ; PGD entry corresp to faulting addr
+	and.f   r1, r1, PAGE_MASK       ; Ignoring protection and other flags
+	;   contains Ptr to Page Table
+	bz.d    do_slow_path_pf         ; if no Page Table, do page fault
+
+	; Get the PTE entry: The idea is
+	; (1) x = addr >> PAGE_SHIFT 	-> masks page-off bits from @fault-addr
+	; (2) y = x & (PTRS_PER_PTE - 1) -> to get index
+	; (3) z = pgtbl[y]
+	; To avoid the multiply by in end, we do the -2, <<2 below
+
+	lsr     r0, r2, (PAGE_SHIFT - 2)
+	and     r0, r0, ( (PTRS_PER_PTE - 1) << 2)
+	ld.aw   r0, [r1, r0]            ; get PTE and PTE ptr for fault addr
+#ifdef CONFIG_ARC_DBG_TLB_MISS_COUNT
+	and.f 0, r0, _PAGE_PRESENT
+	bz   1f
+	ld   r2, [num_pte_not_present]
+	add  r2, r2, 1
+	st   r2, [num_pte_not_present]
+1:
+#endif
+
+.endm
+
+;-----------------------------------------------------------------
+; Convert Linux PTE entry into TLB entry
+; A one-word PTE entry is programmed as two-word TLB Entry [PD0:PD1] in mmu
+; IN: r0 = PTE, r1 = ptr to PTE
+
+.macro CONV_PTE_TO_TLB
+	and r3, r0, PTE_BITS_IN_PD1 ; Extract permission flags+PFN from PTE
+	sr  r3, [ARC_REG_TLBPD1]    ; these go in PD1
+
+	and r2, r0, PTE_BITS_IN_PD0 ; Extract other PTE flags: (V)alid, (G)lb
+#if (CONFIG_ARC_MMU_VER <= 2)   /* Neednot be done with v3 onwards */
+	lsr r2, r2                  ; shift PTE flags to match layout in PD0
+#endif
+
+	lr  r3,[ARC_REG_TLBPD0]     ; MMU prepares PD0 with vaddr and asid
+
+	or  r3, r3, r2              ; S | vaddr | {sasid|asid}
+	sr  r3,[ARC_REG_TLBPD0]     ; rewrite PD0
+.endm
+
+;-----------------------------------------------------------------
+; Commit the TLB entry into MMU
+
+.macro COMMIT_ENTRY_TO_MMU
+
+	/* Get free TLB slot: Set = computed from vaddr, way = random */
+	sr  TLBGetIndex, [ARC_REG_TLBCOMMAND]
+
+	/* Commit the Write */
+#if (CONFIG_ARC_MMU_VER >= 2)   /* introduced in v2 */
+	sr TLBWriteNI, [ARC_REG_TLBCOMMAND]
+#else
+	sr TLBWrite, [ARC_REG_TLBCOMMAND]
+#endif
+.endm
+
+;-----------------------------------------------------------------
+; ARC700 Exception Handling doesn't auto-switch stack and it only provides
+; ONE scratch AUX reg "ARC_REG_SCRATCH_DATA0"
+;
+; For Non-SMP, the scratch AUX reg is repurposed to cache task PGD, so a
+; "global" is used to free-up FIRST core reg to be able to code the rest of
+; exception prologue (IRQ auto-disabled on Exceptions, so it's IRQ-safe).
+; Since the Fast Path TLB Miss handler is coded with 4 regs, the remaining 3
+; need to be saved as well by extending the "global" to be 4 words. Hence
+;	".size   ex_saved_reg1, 16"
+; [All of this dance is to avoid stack switching for each TLB Miss, since we
+; only need to save only a handful of regs, as opposed to complete reg file]
+;
+; For ARC700 SMP, the "global" obviously can't be used for free up the FIRST
+; core reg as it will not be SMP safe.
+; Thus scratch AUX reg is used (and no longer used to cache task PGD).
+; To save the rest of 3 regs - per cpu, the global is made "per-cpu".
+; Epilogue thus has to locate the "per-cpu" storage for regs.
+; To avoid cache line bouncing the per-cpu global is aligned/sized per
+; L1_CACHE_SHIFT, despite fundamentally needing to be 12 bytes only. Hence
+;	".size   ex_saved_reg1, (CONFIG_NR_CPUS << L1_CACHE_SHIFT)"
+
+; As simple as that....
+
+.macro TLBMISS_FREEUP_REGS
+#ifdef CONFIG_SMP
+	sr  r0, [ARC_REG_SCRATCH_DATA0]	; freeup r0 to code with
+	GET_CPU_ID  r0			; get to per cpu scratch mem,
+	lsl r0, r0, L1_CACHE_SHIFT	; cache line wide per cpu
+	add r0, @ex_saved_reg1, r0
+#else
+	st    r0, [@ex_saved_reg1]
+	mov_s r0, @ex_saved_reg1
+#endif
+	st_s  r1, [r0, 4]
+	st_s  r2, [r0, 8]
+	st_s  r3, [r0, 12]
+
+	; VERIFY if the ASID in MMU-PID Reg is same as
+	; one in Linux data structures
+
+	DBG_ASID_MISMATCH
+.endm
+
+;-----------------------------------------------------------------
+.macro TLBMISS_RESTORE_REGS
+#ifdef CONFIG_SMP
+	GET_CPU_ID  r0			; get to per cpu scratch mem
+	lsl r0, r0, L1_CACHE_SHIFT	; each is cache line wide
+	add r0, @ex_saved_reg1, r0
+	ld_s  r3, [r0,12]
+	ld_s  r2, [r0, 8]
+	ld_s  r1, [r0, 4]
+	lr    r0, [ARC_REG_SCRATCH_DATA0]
+#else
+	mov_s r0, @ex_saved_reg1
+	ld_s  r3, [r0,12]
+	ld_s  r2, [r0, 8]
+	ld_s  r1, [r0, 4]
+	ld_s  r0, [r0]
+#endif
+.endm
+
+ARCFP_CODE	;Fast Path Code, candidate for ICCM
+
+;-----------------------------------------------------------------------------
+; I-TLB Miss Exception Handler
+;-----------------------------------------------------------------------------
+
+ARC_ENTRY EV_TLBMissI
+
+	TLBMISS_FREEUP_REGS
+
+#ifdef CONFIG_ARC_DBG_TLB_MISS_COUNT
+	ld  r0, [@numitlb]
+	add r0, r0, 1
+	st  r0, [@numitlb]
+#endif
+
+	;----------------------------------------------------------------
+	; Get the PTE corresponding to V-addr accessed
+	LOAD_FAULT_PTE
+
+	;----------------------------------------------------------------
+	; VERIFY_PTE: Check if PTE permissions approp for executing code
+	cmp_s   r2, VMALLOC_START
+	mov.lo  r2, (_PAGE_PRESENT | _PAGE_READ | _PAGE_EXECUTE)
+	mov.hs  r2, (_PAGE_PRESENT | _PAGE_K_READ | _PAGE_K_EXECUTE)
+
+	and     r3, r0, r2  ; Mask out NON Flag bits from PTE
+	xor.f   r3, r3, r2  ; check ( ( pte & flags_test ) == flags_test )
+	bnz     do_slow_path_pf
+
+	; Let Linux VM know that the page was accessed
+	or      r0, r0, (_PAGE_PRESENT | _PAGE_ACCESSED)  ; set Accessed Bit
+	st_s    r0, [r1]                                  ; Write back PTE
+
+	CONV_PTE_TO_TLB
+	COMMIT_ENTRY_TO_MMU
+	TLBMISS_RESTORE_REGS
+	rtie
+
+ARC_EXIT EV_TLBMissI
+
+;-----------------------------------------------------------------------------
+; D-TLB Miss Exception Handler
+;-----------------------------------------------------------------------------
+
+ARC_ENTRY EV_TLBMissD
+
+	TLBMISS_FREEUP_REGS
+
+#ifdef CONFIG_ARC_DBG_TLB_MISS_COUNT
+	ld  r0, [@numdtlb]
+	add r0, r0, 1
+	st  r0, [@numdtlb]
+#endif
+
+	;----------------------------------------------------------------
+	; Get the PTE corresponding to V-addr accessed
+	; If PTE exists, it will setup, r0 = PTE, r1 = Ptr to PTE
+	LOAD_FAULT_PTE
+
+	;----------------------------------------------------------------
+	; VERIFY_PTE: Chk if PTE permissions approp for data access (R/W/R+W)
+
+	mov_s   r2, 0
+	lr      r3, [ecr]
+	btst_s  r3, ECR_C_BIT_DTLB_LD_MISS	; Read Access
+	or.nz   r2, r2, _PAGE_READ      	; chk for Read flag in PTE
+	btst_s  r3, ECR_C_BIT_DTLB_ST_MISS	; Write Access
+	or.nz   r2, r2, _PAGE_WRITE     	; chk for Write flag in PTE
+	; Above laddering takes care of XCHG access
+	;   which is both Read and Write
+
+	; If kernel mode access, ; make _PAGE_xx flags as _PAGE_K_xx
+	; For copy_(to|from)_user, despite exception taken in kernel mode,
+	; this code is not hit, because EFA would still be the user mode
+	; address (EFA < 0x6000_0000).
+	; This code is for legit kernel mode faults, vmalloc specifically
+	; (EFA: 0x7000_0000 to 0x7FFF_FFFF)
+
+	lr      r3, [efa]
+	cmp     r3, VMALLOC_START - 1   ; If kernel mode access
+	asl.hi  r2, r2, 3               ; make _PAGE_xx flags as _PAGE_K_xx
+	or      r2, r2, _PAGE_PRESENT   ; Common flag for K/U mode
+
+	; By now, r2 setup with all the Flags we need to check in PTE
+	and     r3, r0, r2              ; Mask out NON Flag bits from PTE
+	brne.d  r3, r2, do_slow_path_pf ; is ((pte & flags_test) == flags_test)
+
+	;----------------------------------------------------------------
+	; UPDATE_PTE: Let Linux VM know that page was accessed/dirty
+	lr      r3, [ecr]
+	or      r0, r0, (_PAGE_PRESENT | _PAGE_ACCESSED) ; Accessed bit always
+	btst_s  r3,  ECR_C_BIT_DTLB_ST_MISS   ; See if it was a Write Access ?
+	or.nz   r0, r0, _PAGE_MODIFIED        ; if Write, set Dirty bit as well
+	st_s    r0, [r1]                      ; Write back PTE
+
+	CONV_PTE_TO_TLB
+
+#if (CONFIG_ARC_MMU_VER == 1)
+	; MMU with 2 way set assoc J-TLB, needs some help in pathetic case of
+	; memcpy where 3 parties contend for 2 ways, ensuing a livelock.
+	; But only for old MMU or one with Metal Fix
+	TLB_WRITE_HEURISTICS
+#endif
+
+	COMMIT_ENTRY_TO_MMU
+	TLBMISS_RESTORE_REGS
+	rtie
+
+;-------- Common routine to call Linux Page Fault Handler -----------
+do_slow_path_pf:
+
+	; Restore the 4-scratch regs saved by fast path miss handler
+	TLBMISS_RESTORE_REGS
+
+	; Slow path TLB Miss handled as a regular ARC Exception
+	; (stack switching / save the complete reg-file).
+	; That requires freeing up r9
+	EXCPN_PROLOG_FREEUP_REG r9
+
+	lr  r9, [erstatus]
+
+	SWITCH_TO_KERNEL_STK
+	SAVE_ALL_SYS
+
+	; ------- setup args for Linux Page fault Hanlder ---------
+	mov_s r0, sp
+	lr  r2, [efa]
+	lr  r3, [ecr]
+
+	; Both st and ex imply WRITE access of some sort, hence do_page_fault( )
+	; invoked with write=1 for DTLB-st/ex Miss and write=0 for ITLB miss or
+	; DTLB-ld Miss
+	; DTLB Miss Cause code is ld = 0x01 , st = 0x02, ex = 0x03
+	; Following code uses that fact that st/ex have one bit in common
+
+	btst_s r3,  ECR_C_BIT_DTLB_ST_MISS
+	mov.z  r1, 0
+	mov.nz r1, 1
+
+	; We don't want exceptions to be disabled while the fault is handled.
+	; Now that we have saved the context we return from exception hence
+	; exceptions get re-enable
+
+	FAKE_RET_FROM_EXCPN  r9
+
+	bl  do_page_fault
+	b   ret_from_exception
+
+ARC_EXIT EV_TLBMissD
+
+ARC_ENTRY EV_TLBMissB   ; Bogus entry to measure sz of DTLBMiss hdlr
diff --git a/arch/arc/oprofile/Makefile b/arch/arc/oprofile/Makefile
new file mode 100644
index 000000000000..ce417a6e70b8
--- /dev/null
+++ b/arch/arc/oprofile/Makefile
@@ -0,0 +1,9 @@
+obj-$(CONFIG_OPROFILE) += oprofile.o
+
+DRIVER_OBJS = $(addprefix ../../../drivers/oprofile/, \
+		oprof.o cpu_buffer.o buffer_sync.o \
+		event_buffer.o oprofile_files.o \
+		oprofilefs.o oprofile_stats.o \
+		timer_int.o )
+
+oprofile-y	:= $(DRIVER_OBJS) common.o
diff --git a/arch/arc/oprofile/common.c b/arch/arc/oprofile/common.c
new file mode 100644
index 000000000000..c80fcad4a5a7
--- /dev/null
+++ b/arch/arc/oprofile/common.c
@@ -0,0 +1,26 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Based on orig code from @author John Levon <levon@movementarian.org>
+ */
+
+#include <linux/oprofile.h>
+#include <linux/perf_event.h>
+
+int __init oprofile_arch_init(struct oprofile_operations *ops)
+{
+	/*
+	 * A failure here, forces oprofile core to switch to Timer based PC
+	 * sampling, which will happen if say perf is not enabled/available
+	 */
+	return oprofile_perf_init(ops);
+}
+
+void oprofile_arch_exit(void)
+{
+	oprofile_perf_exit();
+}
diff --git a/arch/arc/plat-arcfpga/Kconfig b/arch/arc/plat-arcfpga/Kconfig
new file mode 100644
index 000000000000..b41e786cdbc0
--- /dev/null
+++ b/arch/arc/plat-arcfpga/Kconfig
@@ -0,0 +1,84 @@
+#
+# Copyright (C) 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License version 2 as
+# published by the Free Software Foundation.
+#
+
+menuconfig ARC_PLAT_FPGA_LEGACY
+	bool "\"Legacy\" ARC FPGA dev Boards"
+	select ISS_SMP_EXTN if SMP
+	help
+	  Support for ARC development boards, provided by Synopsys.
+	  These are based on FPGA or ISS. e.g.
+	  - ARCAngel4
+	  - ML509
+	  - MetaWare ISS
+
+if ARC_PLAT_FPGA_LEGACY
+
+config ARC_BOARD_ANGEL4
+	bool "ARC Angel4"
+	default y
+	help
+	  ARC Angel4 FPGA Ref Platform (Xilinx Virtex Based)
+
+config ARC_BOARD_ML509
+	bool "ML509"
+	help
+	  ARC ML509 FPGA Ref Platform (Xilinx Virtex-5 Based)
+
+config ISS_SMP_EXTN
+	bool "ARC SMP Extensions (ISS Models only)"
+	default n
+	depends on SMP
+	select ARC_HAS_COH_RTSC
+	help
+	  SMP Extensions to ARC700, in a "simulation only" Model, supported in
+	  ARC ISS (Instruction Set Simulator).
+	  The SMP extensions include:
+	  -IDU (Interrupt Distribution Unit)
+	  -XTL (To enable CPU start/stop/set-PC for another CPU)
+	  It doesn't provide coherent Caches and/or Atomic Ops (LLOCK/SCOND)
+
+config ARC_SERIAL_BAUD
+	int "UART Baud rate"
+	default "115200"
+	depends on SERIAL_ARC || SERIAL_ARC_CONSOLE
+	help
+	  Baud rate for the ARC UART
+
+menuconfig ARC_HAS_BVCI_LAT_UNIT
+	bool "BVCI Bus Latency Unit"
+	depends on ARC_BOARD_ML509 || ARC_BOARD_ANGEL4
+	help
+	  IP to add artifical latency to BVCI Bus Based FPGA builds.
+	  The default latency (even worst case) for FPGA is non-realistic
+	  (~10 SDRAM, ~5 SSRAM).
+
+config BVCI_LAT_UNITS
+	hex "Latency Unit(s) Bitmap"
+	default "0x0"
+	depends on ARC_HAS_BVCI_LAT_UNIT
+	help
+	  There are multiple Latency Units corresponding to the many
+	  interfaces of the system bus arbiter (both CPU side as well as
+	  the peripheral side).
+	  To add latency to ALL memory transaction, choose Unit 0, otherwise
+	  for finer grainer - interface wise latency, specify a bitmap (1 bit
+	  per unit) of all units. e.g. 1,2,12 will be 0x1003
+
+	  Unit  0 - System Arb and Mem Controller
+	  Unit  1 - I$ and System Bus
+	  Unit  2 - D$ and System Bus
+	  ..
+	  Unit 12 - IDE Disk controller and System Bus
+
+config BVCI_LAT_CYCLES
+	int "Latency Value in cycles"
+	range 0 63
+	default "30"
+	depends on ARC_HAS_BVCI_LAT_UNIT
+
+endif
diff --git a/arch/arc/plat-arcfpga/Makefile b/arch/arc/plat-arcfpga/Makefile
new file mode 100644
index 000000000000..a44e22ebc1b7
--- /dev/null
+++ b/arch/arc/plat-arcfpga/Makefile
@@ -0,0 +1,12 @@
+#
+# Copyright (C) 2011-2012 Synopsys, Inc. (www.synopsys.com)
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License version 2 as
+# published by the Free Software Foundation.
+#
+
+KBUILD_CFLAGS	+= -Iarch/arc/plat-arcfpga/include
+
+obj-y := platform.o irq.o
+obj-$(CONFIG_SMP)		+= smp.o
diff --git a/arch/arc/plat-arcfpga/include/plat/irq.h b/arch/arc/plat-arcfpga/include/plat/irq.h
new file mode 100644
index 000000000000..41e335670f60
--- /dev/null
+++ b/arch/arc/plat-arcfpga/include/plat/irq.h
@@ -0,0 +1,31 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * vineetg: Feb 2009
+ *  -For AA4 board, IRQ assignments to peripherals
+ */
+
+#ifndef __PLAT_IRQ_H
+#define __PLAT_IRQ_H
+
+#define UART0_IRQ	5
+#define UART1_IRQ	10
+#define UART2_IRQ	11
+
+#define VMAC_IRQ	6
+
+#define IDE_IRQ		13
+#define PCI_IRQ		14
+#define PS2_IRQ		15
+
+#ifdef CONFIG_SMP
+#define IDU_INTERRUPT_0 16
+#endif
+
+extern void __init plat_fpga_init_IRQ(void);
+
+#endif
diff --git a/arch/arc/plat-arcfpga/include/plat/memmap.h b/arch/arc/plat-arcfpga/include/plat/memmap.h
new file mode 100644
index 000000000000..1663f3388085
--- /dev/null
+++ b/arch/arc/plat-arcfpga/include/plat/memmap.h
@@ -0,0 +1,31 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * vineetg: Feb 2009
+ *  -For AA4 board, System Memory Map for Peripherals etc
+ */
+
+#ifndef __PLAT_MEMMAP_H
+#define __PLAT_MEMMAP_H
+
+#define UART0_BASE              0xC0FC1000
+#define UART1_BASE              0xC0FC1100
+
+#define VMAC_REG_BASEADDR       0xC0FC2000
+
+#define IDE_CONTROLLER_BASE     0xC0FC9000
+
+#define AHB_PCI_HOST_BRG_BASE   0xC0FD0000
+
+#define PGU_BASEADDR            0xC0FC8000
+#define VLCK_ADDR               0xC0FCF028
+
+#define BVCI_LAT_UNIT_BASE      0xC0FED000
+
+#define PS2_BASE_ADDR		0xC0FCC000
+
+#endif
diff --git a/arch/arc/plat-arcfpga/include/plat/smp.h b/arch/arc/plat-arcfpga/include/plat/smp.h
new file mode 100644
index 000000000000..c09eb4cfc77c
--- /dev/null
+++ b/arch/arc/plat-arcfpga/include/plat/smp.h
@@ -0,0 +1,118 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ *  Rajeshwar Ranga: Interrupt Distribution Unit API's
+ */
+
+#ifndef __PLAT_ARCFPGA_SMP_H
+#define __PLAT_ARCFPGA_SMP_H
+
+#ifdef CONFIG_SMP
+
+#include <linux/types.h>
+#include <asm/arcregs.h>
+
+#define ARC_AUX_IDU_REG_CMD		0x2000
+#define ARC_AUX_IDU_REG_PARAM		0x2001
+
+#define ARC_AUX_XTL_REG_CMD		0x2002
+#define ARC_AUX_XTL_REG_PARAM		0x2003
+
+#define ARC_REG_MP_BCR			0x2021
+
+#define ARC_XTL_CMD_WRITE_PC		0x04
+#define ARC_XTL_CMD_CLEAR_HALT		0x02
+
+/*
+ * Build Configuration Register which identifies the sub-components
+ */
+struct bcr_mp {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int mp_arch:16, pad:5, sdu:1, idu:1, scu:1, ver:8;
+#else
+	unsigned int ver:8, scu:1, idu:1, sdu:1, pad:5, mp_arch:16;
+#endif
+};
+
+/* IDU supports 256 common interrupts */
+#define NR_IDU_IRQS			256
+
+/*
+ * The Aux Regs layout is same bit-by-bit in both BE/LE modes.
+ * However when casted as a bitfield encoded "C" struct, gcc treats it as
+ * memory, generating different code for BE/LE, requiring strcture adj (see
+ * include/asm/arcregs.h)
+ *
+ * However when manually "carving" the value for a Aux, no special handling
+ * of BE is needed because of the property discribed above
+ */
+#define IDU_SET_COMMAND(irq, cmd)			\
+do {							\
+	uint32_t __val;					\
+	__val = (((irq & 0xFF) << 8) | (cmd & 0xFF));	\
+	write_aux_reg(ARC_AUX_IDU_REG_CMD, __val);	\
+} while (0)
+
+#define IDU_SET_PARAM(par)  write_aux_reg(ARC_AUX_IDU_REG_PARAM, par)
+#define IDU_GET_PARAM()     read_aux_reg(ARC_AUX_IDU_REG_PARAM)
+
+/* IDU Commands */
+#define IDU_DISABLE			0x00
+#define IDU_ENABLE			0x01
+#define IDU_IRQ_CLEAR			0x02
+#define IDU_IRQ_ASSERT			0x03
+#define IDU_IRQ_WMODE			0x04
+#define IDU_IRQ_STATUS			0x05
+#define IDU_IRQ_ACK			0x06
+#define IDU_IRQ_PEND			0x07
+#define IDU_IRQ_RMODE			0x08
+#define IDU_IRQ_WBITMASK		0x09
+#define IDU_IRQ_RBITMASK		0x0A
+
+#define idu_enable()		IDU_SET_COMMAND(0, IDU_ENABLE)
+#define idu_disable()		IDU_SET_COMMAND(0, IDU_DISABLE)
+
+#define idu_irq_assert(irq)	IDU_SET_COMMAND((irq), IDU_IRQ_ASSERT)
+#define idu_irq_clear(irq)	IDU_SET_COMMAND((irq), IDU_IRQ_CLEAR)
+
+/* IDU Interrupt Mode - Destination Encoding */
+#define IDU_IRQ_MOD_DISABLE		0x00
+#define IDU_IRQ_MOD_ROUND_RECP		0x01
+#define IDU_IRQ_MOD_TCPU_FIRSTRECP	0x02
+#define IDU_IRQ_MOD_TCPU_ALLRECP	0x03
+
+/* IDU Interrupt Mode  - Triggering Mode */
+#define IDU_IRQ_MODE_LEVEL_TRIG		0x00
+#define IDU_IRQ_MODE_PULSE_TRIG		0x01
+
+#define IDU_IRQ_MODE_PARAM(dest_mode, trig_mode)   \
+	(((trig_mode & 0x01) << 15) | (dest_mode & 0xFF))
+
+struct idu_irq_config {
+	uint8_t irq;
+	uint8_t dest_mode;
+	uint8_t trig_mode;
+};
+
+struct idu_irq_status {
+	uint8_t irq;
+	bool enabled;
+	bool status;
+	bool ack;
+	bool pend;
+	uint8_t next_rr;
+};
+
+extern void idu_irq_set_tgtcpu(uint8_t irq, uint32_t mask);
+extern void idu_irq_set_mode(uint8_t irq, uint8_t dest_mode, uint8_t trig_mode);
+
+extern void iss_model_init_smp(unsigned int cpu);
+extern void iss_model_init_early_smp(void);
+
+#endif	/* CONFIG_SMP */
+
+#endif
diff --git a/arch/arc/plat-arcfpga/irq.c b/arch/arc/plat-arcfpga/irq.c
new file mode 100644
index 000000000000..d2215fd889c2
--- /dev/null
+++ b/arch/arc/plat-arcfpga/irq.c
@@ -0,0 +1,25 @@
+/*
+ * ARC FPGA Platform IRQ hookups
+ *
+ * Copyright (C) 2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/interrupt.h>
+#include <plat/irq.h>
+
+void __init plat_fpga_init_IRQ(void)
+{
+	/*
+	 * SMP Hack because UART IRQ hardwired to cpu0 (boot-cpu) but if the
+	 * request_irq() comes from any other CPU, the low level IRQ unamsking
+	 * essential for getting Interrupts won't be enabled on cpu0, locking
+	 * up the UART state machine.
+	 */
+#ifdef CONFIG_SMP
+	arch_unmask_irq(UART0_IRQ);
+#endif
+}
diff --git a/arch/arc/plat-arcfpga/platform.c b/arch/arc/plat-arcfpga/platform.c
new file mode 100644
index 000000000000..4e20a1a5104d
--- /dev/null
+++ b/arch/arc/plat-arcfpga/platform.c
@@ -0,0 +1,226 @@
+/*
+ * ARC FPGA Platform support code
+ *
+ * Copyright (C) 2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/device.h>
+#include <linux/platform_device.h>
+#include <linux/io.h>
+#include <linux/console.h>
+#include <linux/of_platform.h>
+#include <asm/setup.h>
+#include <asm/clk.h>
+#include <asm/mach_desc.h>
+#include <plat/memmap.h>
+#include <plat/smp.h>
+#include <plat/irq.h>
+
+/*-----------------------BVCI Latency Unit -----------------------------*/
+
+#ifdef CONFIG_ARC_HAS_BVCI_LAT_UNIT
+
+int lat_cycles = CONFIG_BVCI_LAT_CYCLES;
+
+/* BVCI Bus Profiler: Latency Unit */
+static void __init setup_bvci_lat_unit(void)
+{
+#define MAX_BVCI_UNITS 12
+
+	unsigned int i;
+	unsigned int *base = (unsigned int *)BVCI_LAT_UNIT_BASE;
+	const unsigned long units_req = CONFIG_BVCI_LAT_UNITS;
+	const unsigned int REG_UNIT = 21;
+	const unsigned int REG_VAL = 22;
+
+	/*
+	 * There are multiple Latency Units corresponding to the many
+	 * interfaces of the system bus arbiter (both CPU side as well as
+	 * the peripheral side).
+	 *
+	 * Unit  0 - System Arb and Mem Controller - adds latency to all
+	 *	    memory trasactions
+	 * Unit  1 - I$ and System Bus
+	 * Unit  2 - D$ and System Bus
+	 * ..
+	 * Unit 12 - IDE Disk controller and System Bus
+	 *
+	 * The programmers model requires writing to lat_unit reg first
+	 * and then the latency value (cycles) to lat_value reg
+	 */
+
+	if (CONFIG_BVCI_LAT_UNITS == 0) {
+		writel(0, base + REG_UNIT);
+		writel(lat_cycles, base + REG_VAL);
+		pr_info("BVCI Latency for all Memory Transactions %d cycles\n",
+			lat_cycles);
+	} else {
+		for_each_set_bit(i, &units_req, MAX_BVCI_UNITS) {
+			writel(i + 1, base + REG_UNIT); /* loop is 0 based */
+			writel(lat_cycles, base + REG_VAL);
+			pr_info("BVCI Latency for Unit[%d] = %d cycles\n",
+				(i + 1), lat_cycles);
+		}
+	}
+}
+#else
+static void __init setup_bvci_lat_unit(void)
+{
+}
+#endif
+
+/*----------------------- Platform Devices -----------------------------*/
+
+static unsigned long arc_uart_info[] = {
+	0,	/* uart->is_emulated (runtime @running_on_hw) */
+	0,	/* uart->port.uartclk */
+	0,	/* uart->baud */
+	0
+};
+
+#if defined(CONFIG_SERIAL_ARC_CONSOLE)
+/*
+ * static platform data - but only for early serial
+ * TBD: derive this from a special DT node
+ */
+static struct resource arc_uart0_res[] = {
+	{
+		.start = UART0_BASE,
+		.end   = UART0_BASE + 0xFF,
+		.flags = IORESOURCE_MEM,
+	},
+	{
+		.start = UART0_IRQ,
+		.end   = UART0_IRQ,
+		.flags = IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device arc_uart0_dev = {
+	.name = "arc-uart",
+	.id = 0,
+	.num_resources = ARRAY_SIZE(arc_uart0_res),
+	.resource = arc_uart0_res,
+	.dev = {
+		.platform_data = &arc_uart_info,
+	},
+};
+
+static struct platform_device *fpga_early_devs[] __initdata = {
+	&arc_uart0_dev,
+};
+#endif
+
+static void arc_fpga_serial_init(void)
+{
+	/* To let driver workaround ISS bug: baudh Reg can't be set to 0 */
+	arc_uart_info[0] = !running_on_hw;
+
+	arc_uart_info[1] = arc_get_core_freq();
+
+	arc_uart_info[2] = CONFIG_ARC_SERIAL_BAUD;
+
+#if defined(CONFIG_SERIAL_ARC_CONSOLE)
+	early_platform_add_devices(fpga_early_devs,
+				   ARRAY_SIZE(fpga_early_devs));
+
+	/*
+	 * ARC console driver registers itself as an early platform driver
+	 * of class "earlyprintk".
+	 * Install it here, followed by probe of devices.
+	 * The installation here doesn't require earlyprintk in command line
+	 * To do so however, replace the lines below with
+	 *	parse_early_param();
+	 *	early_platform_driver_probe("earlyprintk", 1, 1);
+	 *						      ^^
+	 */
+	early_platform_driver_register_all("earlyprintk");
+	early_platform_driver_probe("earlyprintk", 1, 0);
+
+	/*
+	 * This is to make sure that arc uart would be preferred console
+	 * despite one/more of following:
+	 *   -command line lacked "console=ttyARC0" or
+	 *   -CONFIG_VT_CONSOLE was enabled (for no reason whatsoever)
+	 * Note that this needs to be done after above early console is reg,
+	 * otherwise the early console never gets a chance to run.
+	 */
+	add_preferred_console("ttyARC", 0, "115200");
+#endif
+}
+
+static void __init plat_fpga_early_init(void)
+{
+	pr_info("[plat-arcfpga]: registering early dev resources\n");
+
+	setup_bvci_lat_unit();
+
+	arc_fpga_serial_init();
+
+#ifdef CONFIG_SMP
+	iss_model_init_early_smp();
+#endif
+}
+
+static struct of_dev_auxdata plat_auxdata_lookup[] __initdata = {
+#if defined(CONFIG_SERIAL_ARC) || defined(CONFIG_SERIAL_ARC_MODULE)
+	OF_DEV_AUXDATA("snps,arc-uart", UART0_BASE, "arc-uart", arc_uart_info),
+#endif
+	{}
+};
+
+static void __init plat_fpga_populate_dev(void)
+{
+	pr_info("[plat-arcfpga]: registering device resources\n");
+
+	/*
+	 * Traverses flattened DeviceTree - registering platform devices
+	 * complete with their resources
+	 */
+	of_platform_populate(NULL, of_default_bus_match_table,
+			     plat_auxdata_lookup, NULL);
+}
+
+/*----------------------- Machine Descriptions ------------------------------
+ *
+ * Machine description is simply a set of platform/board specific callbacks
+ * This is not directly related to DeviceTree based dynamic device creation,
+ * however as part of early device tree scan, we also select the right
+ * callback set, by matching the DT compatible name.
+ */
+
+static const char *aa4_compat[] __initdata = {
+	"snps,arc-angel4",
+	NULL,
+};
+
+MACHINE_START(ANGEL4, "angel4")
+	.dt_compat	= aa4_compat,
+	.init_early	= plat_fpga_early_init,
+	.init_machine	= plat_fpga_populate_dev,
+	.init_irq	= plat_fpga_init_IRQ,
+#ifdef CONFIG_SMP
+	.init_smp	= iss_model_init_smp,
+#endif
+MACHINE_END
+
+static const char *ml509_compat[] __initdata = {
+	"snps,arc-ml509",
+	NULL,
+};
+
+MACHINE_START(ML509, "ml509")
+	.dt_compat	= ml509_compat,
+	.init_early	= plat_fpga_early_init,
+	.init_machine	= plat_fpga_populate_dev,
+	.init_irq	= plat_fpga_init_IRQ,
+#ifdef CONFIG_SMP
+	.init_smp	= iss_model_init_smp,
+#endif
+MACHINE_END
diff --git a/arch/arc/plat-arcfpga/smp.c b/arch/arc/plat-arcfpga/smp.c
new file mode 100644
index 000000000000..91b55349a5f8
--- /dev/null
+++ b/arch/arc/plat-arcfpga/smp.c
@@ -0,0 +1,171 @@
+/*
+ * ARC700 Simulation-only Extensions for SMP
+ *
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ *  Vineet Gupta    - 2012 : split off arch common and plat specific SMP
+ *  Rajeshwar Ranga - 2007 : Interrupt Distribution Unit API's
+ */
+
+#include <linux/smp.h>
+#include <linux/irq.h>
+#include <plat/irq.h>
+#include <plat/smp.h>
+
+static char smp_cpuinfo_buf[128];
+
+/*
+ *-------------------------------------------------------------------
+ * Platform specific callbacks expected by arch SMP code
+ *-------------------------------------------------------------------
+ */
+
+/*
+ * Master kick starting another CPU
+ */
+static void iss_model_smp_wakeup_cpu(int cpu, unsigned long pc)
+{
+	/* setup the start PC */
+	write_aux_reg(ARC_AUX_XTL_REG_PARAM, pc);
+
+	/* Trigger WRITE_PC cmd for this cpu */
+	write_aux_reg(ARC_AUX_XTL_REG_CMD,
+			(ARC_XTL_CMD_WRITE_PC | (cpu << 8)));
+
+	/* Take the cpu out of Halt */
+	write_aux_reg(ARC_AUX_XTL_REG_CMD,
+			(ARC_XTL_CMD_CLEAR_HALT | (cpu << 8)));
+
+}
+
+/*
+ * Any SMP specific init any CPU does when it comes up.
+ * Here we setup the CPU to enable Inter-Processor-Interrupts
+ * Called for each CPU
+ * -Master      : init_IRQ()
+ * -Other(s)    : start_kernel_secondary()
+ */
+void iss_model_init_smp(unsigned int cpu)
+{
+	/* Check if CPU is configured for more than 16 interrupts */
+	if (NR_IRQS <= 16 || get_hw_config_num_irq() <= 16)
+		panic("[arcfpga] IRQ system can't support IDU IPI\n");
+
+	idu_disable();
+
+	/****************************************************************
+	 * IDU provides a set of Common IRQs, each of which can be dynamically
+	 * attached to (1|many|all) CPUs.
+	 * The Common IRQs [0-15] are mapped as CPU pvt [16-31]
+	 *
+	 * Here we use a simple 1:1 mapping:
+	 * A CPU 'x' is wired to Common IRQ 'x'.
+	 * So an IDU ASSERT on IRQ 'x' will trigger Interupt on CPU 'x', which
+	 * makes up for our simple IPI plumbing.
+	 *
+	 * TBD: Have a dedicated multicast IRQ for sending IPIs to all CPUs
+	 *      w/o having to do one-at-a-time
+	 ******************************************************************/
+
+	/*
+	 * Claim an IRQ which would trigger IPI on this CPU.
+	 * In IDU parlance it involves setting up a cpu bitmask for the IRQ
+	 * The bitmap here contains only 1 CPU (self).
+	 */
+	idu_irq_set_tgtcpu(cpu, 0x1 << cpu);
+
+	/* Set the IRQ destination to use the bitmask above */
+	idu_irq_set_mode(cpu, 7, /* XXX: IDU_IRQ_MOD_TCPU_ALLRECP: ISS bug */
+			 IDU_IRQ_MODE_PULSE_TRIG);
+
+	idu_enable();
+
+	/* Attach the arch-common IPI ISR to our IDU IRQ */
+	smp_ipi_irq_setup(cpu, IDU_INTERRUPT_0 + cpu);
+}
+
+static void iss_model_ipi_send(void *arg)
+{
+	struct cpumask *callmap = arg;
+	unsigned int cpu;
+
+	for_each_cpu(cpu, callmap)
+		idu_irq_assert(cpu);
+}
+
+static void iss_model_ipi_clear(int cpu, int irq)
+{
+	idu_irq_clear(IDU_INTERRUPT_0 + cpu);
+}
+
+void iss_model_init_early_smp(void)
+{
+#define IS_AVAIL1(var, str)    ((var) ? str : "")
+
+	struct bcr_mp mp;
+
+	READ_BCR(ARC_REG_MP_BCR, mp);
+
+	sprintf(smp_cpuinfo_buf, "Extn [ISS-SMP]: v%d, arch(%d) %s %s %s\n",
+		mp.ver, mp.mp_arch, IS_AVAIL1(mp.scu, "SCU"),
+		IS_AVAIL1(mp.idu, "IDU"), IS_AVAIL1(mp.sdu, "SDU"));
+
+	plat_smp_ops.info = smp_cpuinfo_buf;
+
+	plat_smp_ops.cpu_kick = iss_model_smp_wakeup_cpu;
+	plat_smp_ops.ipi_send = iss_model_ipi_send;
+	plat_smp_ops.ipi_clear = iss_model_ipi_clear;
+}
+
+/*
+ *-------------------------------------------------------------------
+ * Low level Platform IPI Providers
+ *-------------------------------------------------------------------
+ */
+
+/* Set the Mode for the Common IRQ */
+void idu_irq_set_mode(uint8_t irq, uint8_t dest_mode, uint8_t trig_mode)
+{
+	uint32_t par = IDU_IRQ_MODE_PARAM(dest_mode, trig_mode);
+
+	IDU_SET_PARAM(par);
+	IDU_SET_COMMAND(irq, IDU_IRQ_WMODE);
+}
+
+/* Set the target cpu Bitmask for Common IRQ */
+void idu_irq_set_tgtcpu(uint8_t irq, uint32_t mask)
+{
+	IDU_SET_PARAM(mask);
+	IDU_SET_COMMAND(irq, IDU_IRQ_WBITMASK);
+}
+
+/* Get the Interrupt Acknowledged status for IRQ (as CPU Bitmask) */
+bool idu_irq_get_ack(uint8_t irq)
+{
+	uint32_t val;
+
+	IDU_SET_COMMAND(irq, IDU_IRQ_ACK);
+	val = IDU_GET_PARAM();
+
+	return val & (1 << irq);
+}
+
+/*
+ * Get the Interrupt Pending status for IRQ (as CPU Bitmask)
+ * -Pending means CPU has not yet noticed the IRQ (e.g. disabled)
+ * -After Interrupt has been taken, the IPI expcitily needs to be
+ *  cleared, to be acknowledged.
+ */
+bool idu_irq_get_pend(uint8_t irq)
+{
+	uint32_t val;
+
+	IDU_SET_COMMAND(irq, IDU_IRQ_PEND);
+	val = IDU_GET_PARAM();
+
+	return val & (1 << irq);
+}
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index 4d5ea7648574..a2a47d9d6a22 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -18,6 +18,7 @@ config PARISC
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_STRNCPY_FROM_USER
+	select SYSCTL_ARCH_UNALIGN_ALLOW
 	select HAVE_MOD_ARCH_SPECIFIC
 	select HAVE_VIRT_TO_BUS
 	select MODULES_USE_ELF_RELA
diff --git a/include/asm-generic/checksum.h b/include/asm-generic/checksum.h
index c084767c88bc..59811df58c5b 100644
--- a/include/asm-generic/checksum.h
+++ b/include/asm-generic/checksum.h
@@ -38,12 +38,15 @@ extern __wsum csum_partial_copy_from_user(const void __user *src, void *dst,
 	csum_partial_copy((src), (dst), (len), (sum))
 #endif
 
+#ifndef ip_fast_csum
 /*
  * This is a version of ip_compute_csum() optimized for IP headers,
  * which always checksum on 4 octet boundaries.
  */
 extern __sum16 ip_fast_csum(const void *iph, unsigned int ihl);
+#endif
 
+#ifndef csum_fold
 /*
  * Fold a partial checksum
  */
@@ -54,6 +57,7 @@ static inline __sum16 csum_fold(__wsum csum)
 	sum = (sum & 0xffff) + (sum >> 16);
 	return (__force __sum16)~sum;
 }
+#endif
 
 #ifndef csum_tcpudp_nofold
 /*
diff --git a/include/asm-generic/uaccess.h b/include/asm-generic/uaccess.h
index 9788568f7978..c184aa8ec8cd 100644
--- a/include/asm-generic/uaccess.h
+++ b/include/asm-generic/uaccess.h
@@ -7,7 +7,6 @@
  * address space, e.g. all NOMMU machines.
  */
 #include <linux/sched.h>
-#include <linux/mm.h>
 #include <linux/string.h>
 
 #include <asm/segment.h>
@@ -32,7 +31,9 @@ static inline void set_fs(mm_segment_t fs)
 }
 #endif
 
+#ifndef segment_eq
 #define segment_eq(a, b) ((a).seg == (b).seg)
+#endif
 
 #define VERIFY_READ	0
 #define VERIFY_WRITE	1
@@ -168,12 +169,18 @@ static inline __must_check long __copy_to_user(void __user *to,
 		-EFAULT;					\
 })
 
+#ifndef __put_user_fn
+
 static inline int __put_user_fn(size_t size, void __user *ptr, void *x)
 {
 	size = __copy_to_user(ptr, x, size);
 	return size ? -EFAULT : size;
 }
 
+#define __put_user_fn(sz, u, k)	__put_user_fn(sz, u, k)
+
+#endif
+
 extern int __put_user_bad(void) __attribute__((noreturn));
 
 #define __get_user(x, ptr)					\
@@ -224,12 +231,17 @@ extern int __put_user_bad(void) __attribute__((noreturn));
 		-EFAULT;					\
 })
 
+#ifndef __get_user_fn
 static inline int __get_user_fn(size_t size, const void __user *ptr, void *x)
 {
 	size = __copy_from_user(x, ptr, size);
 	return size ? -EFAULT : size;
 }
 
+#define __get_user_fn(sz, u, k)	__get_user_fn(sz, u, k)
+
+#endif
+
 extern int __get_user_bad(void) __attribute__((noreturn));
 
 #ifndef __copy_from_user_inatomic
diff --git a/init/Kconfig b/init/Kconfig
index 0a5e80fb9ba2..22616cd434bc 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1230,6 +1230,14 @@ config SYSCTL_ARCH_UNALIGN_NO_WARN
 	  Allows arch to define/use @no_unaligned_warning to possibly warn
 	  about unaligned access emulation going on under the hood.
 
+config SYSCTL_ARCH_UNALIGN_ALLOW
+	bool
+	help
+	  Enable support for /proc/sys/kernel/unaligned-trap
+	  Allows arches to define/use @unaligned_enabled to runtime toggle
+	  the unaligned access emulation.
+	  see arch/parisc/kernel/unaligned.c for reference
+
 config KALLSYMS
 	 bool "Load all symbols for debugging/ksymoops" if EXPERT
 	 default y
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index d1b4ee67d2df..afc1dc60f3f8 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -157,6 +157,9 @@ extern int sysctl_tsb_ratio;
 
 #ifdef __hppa__
 extern int pwrsw_enabled;
+#endif
+
+#ifdef CONFIG_SYSCTL_ARCH_UNALIGN_ALLOW
 extern int unaligned_enabled;
 #endif
 
@@ -555,6 +558,8 @@ static struct ctl_table kern_table[] = {
 	 	.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+#endif
+#ifdef CONFIG_SYSCTL_ARCH_UNALIGN_ALLOW
 	{
 		.procname	= "unaligned-trap",
 		.data		= &unaligned_enabled,
diff --git a/lib/checksum.c b/lib/checksum.c
index 12dceb27ff20..129775eb6de6 100644
--- a/lib/checksum.c
+++ b/lib/checksum.c
@@ -102,6 +102,7 @@ out:
 }
 #endif
 
+#ifndef ip_fast_csum
 /*
  *	This is a version of ip_compute_csum() optimized for IP headers,
  *	which always checksum on 4 octet boundaries.
@@ -111,6 +112,7 @@ __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
 	return (__force __sum16)~do_csum(iph, ihl*4);
 }
 EXPORT_SYMBOL(ip_fast_csum);
+#endif
 
 /*
  * computes the checksum of a memory block at buff, length len,
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index c2206c87fc9f..d5818c98d051 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -94,6 +94,12 @@
 #define CPUINFO_PROC	"cpu model"
 #endif
 
+#ifdef __arc__
+#define rmb()		asm volatile("" ::: "memory")
+#define cpu_relax()	rmb()
+#define CPUINFO_PROC	"Processor"
+#endif
+
 #include <time.h>
 #include <unistd.h>
 #include <sys/types.h>