Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Fix error output of boot instance creation failure

   Currently if a boot instance creation fails, instead of printing out
   the name of the instance that failed, it prints "(null)". That is
   because it prints "cur_str" that had already been processed by
   strsep(). Print the saved name instead.

   While at it, print the error code of the failure.

 - Fix use-after-free for same named historgrams

   Histograms can be named so that they can be used in multiple events.
   But if the named histogram has a variable attached, the second event
   that uses the named histogram which duplicates it and needs to free
   the original after duplication leaves the old variable in place and
   still visible. If another histogram uses than variable, it will use
   the stale one which will try to reference the freed duplicate
   histogram and crash the kernel.

   Free the duplicate variables along with the duplicated histogram
   data.

 - Check return value of kthread_run() in event self test

   The events self tests uses a kthread for testing but does not check
   if it succeeded in creating a kthread. If the kthread creation were
   to fail, the code will still try to call kthread_stop() on the error
   returned.

 - Fix race between reading trace_pipe and updating subbuffer size

   If a user is reading the trace_pipe file at the same time they update
   the ring buffer sub-buffer size, can cause the trace_pipe read to
   read stale data. Add trace_access_lock() around updating the ring
   buffer sub-buffer size.

 - Fix eventfs_inode on failure path in creation of the events directory

   In the creation of the "events" directory, if after allocating the
   eventfs_inode a failure is detected, it calls cleanup_ei() which
   calls free_ei(). The free_ei() will test if eventfs_inode being freed
   has no children. It is a bug if it does. But on the failure case of
   the creation of the "events" directory, the children lists have not
   yet been initialized and the free will trigger a warning because
   list_empty() on an uninitialized list returns false.

   Move the initialization into init_ei() where it makes more sense and
   makes sure that a created eventfs_inode has its lists initialized
   upon creation.

 - Check return value of kthread_run() in ftrace direct sample code

   The sample code that shows how to use the ftrace direct calls does
   not test the return of kthread_run() to see if it succeeds. Return a
   failure if the kthread_run() doesn't succeed.

 - Clear user events state on fork in case of alloc failure

   On fork, the child gets a pointer to the parent's user events state.
   It makes a copy of it then updates the child's pointer to it. But if
   the allocation fails, the duplication function leaves the child with
   a pointer to its parent's descriptor. When the child cleans up its
   data, it will free the parent's descriptor while the parent is still
   using it.

   In the duplication function, set the child's user_event_mm to NULL
   before testing if the allocation succeeded, and when it exits it will
   not free the parent's descriptor.

 - Fix retry exhaustion in simple ring buffer reader swap

   simple_ring_buffer_swap_reader_page() starts with retry set to 8 and
   post-decrements it only after a failed link replacement. On the final
   attempt, a successful replacement leaves retry at zero, while a
   failed replacement leaves it at -1.

   But the check for success expects the retry value to be non-zero and
   exits with an error on zero. This is the opposite result. Fix it.

 - Fail nicely when the remote swap_reader_page() returns an error

   Currently, if the swap_reader_page() of a remote buffer fails, it
   triggers a WARN_ON_ONCE() and continues normally. Instead, have it
   exit with an error and a pr_warn() print instead of a full WARNING.

* tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  ring-buffer: Stop remote reader update when page swap fails
  tracing: Fix retry exhaustion in simple ring buffer reader swap
  tracing/user_events: Clear copied tracing state before fork duplication
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify
  eventfs: Initialize ei->children and ei->list in init_ei()
  tracing: Fix use-after-free in trace_pipe read on sub-buffer order change
  tracing: Fix crash passing ERR_PTR to kthread_stop()
  tracing: Fix use-after-free with same-name named triggers
  tracing: Fix logged instance name on creation failure

210 files changed, 31949 insertions, 0 deletions

diff --git a/arch/arc/Kbuild b/arch/arc/Kbuild
new file mode 100644
index 000000000..20ea7dd48
--- /dev/null
+++ b/arch/arc/Kbuild
@@ -0,0 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-y += kernel/
+obj-y += mm/
+obj-y += net/
+
+# for cleaning
+subdir- += boot
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
new file mode 100644
index 000000000..2ed7186c8
--- /dev/null
+++ b/arch/arc/Kconfig
@@ -0,0 +1,562 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+#
+
+config ARC
+	def_bool y
+	select ARC_TIMERS
+	select ARCH_HAS_CPU_CACHE_ALIASING
+	select ARCH_HAS_CACHE_LINE_SIZE
+	select ARCH_HAS_DEBUG_VM_PGTABLE
+	select ARCH_HAS_DMA_PREP_COHERENT
+	select ARCH_HAS_PTE_SPECIAL
+	select ARCH_HAS_SETUP_DMA_OPS
+	select ARCH_HAS_SYNC_DMA_FOR_CPU
+	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
+	select ARCH_NEED_CMPXCHG_1_EMU
+	select ARCH_SUPPORTS_ATOMIC_RMW if ARC_HAS_LLSC
+	select ARCH_32BIT_OFF_T
+	select BUILDTIME_TABLE_SORT
+	select GENERIC_BUILTIN_DTB
+	select CLONE_BACKWARDS
+	select COMMON_CLK
+	select DMA_DIRECT_REMAP
+	select GENERIC_ATOMIC64 if !ISA_ARCV2 || !(ARC_HAS_LL64 && ARC_HAS_LLSC)
+	# for now, we don't need GENERIC_IRQ_PROBE, CONFIG_GENERIC_IRQ_CHIP
+	select GENERIC_IRQ_SHOW
+	select GENERIC_PCI_IOMAP
+	select GENERIC_SCHED_CLOCK
+	select GENERIC_SMP_IDLE_THREAD
+	select GENERIC_IOREMAP
+	select GENERIC_STRNCPY_FROM_USER if MMU
+	select GENERIC_STRNLEN_USER if MMU
+	select HAVE_ARCH_KGDB
+	select HAVE_ARCH_TRACEHOOK
+	select HAVE_ARCH_TRANSPARENT_HUGEPAGE if ARC_MMU_V4
+	select HAVE_DEBUG_STACKOVERFLOW
+	select HAVE_DEBUG_KMEMLEAK
+	select HAVE_IOREMAP_PROT
+	select HAVE_KERNEL_GZIP
+	select HAVE_KERNEL_LZMA
+	select HAVE_KPROBES
+	select HAVE_KRETPROBES
+	select HAVE_REGS_AND_STACK_ACCESS_API
+	select HAVE_MOD_ARCH_SPECIFIC
+	select HAVE_PERF_EVENTS
+	select HAVE_SYSCALL_TRACEPOINTS
+	select IRQ_DOMAIN
+	select LOCK_MM_AND_FIND_VMA
+	select MODULES_USE_ELF_RELA
+	select OF
+	select OF_EARLY_FLATTREE
+	select PCI_SYSCALL if PCI
+	select HAVE_ARCH_JUMP_LABEL if ISA_ARCV2 && !CPU_ENDIAN_BE32
+	select TRACE_IRQFLAGS_SUPPORT
+	select HAVE_EBPF_JIT if ISA_ARCV2
+
+config LOCKDEP_SUPPORT
+	def_bool y
+
+config SCHED_OMIT_FRAME_POINTER
+	def_bool y
+
+config GENERIC_CSUM
+	def_bool y
+
+config ARCH_FLATMEM_ENABLE
+	def_bool y
+
+config MMU
+	def_bool y
+
+config NO_IOPORT_MAP
+	def_bool y
+
+config GENERIC_CALIBRATE_DELAY
+	def_bool y
+
+config GENERIC_HWEIGHT
+	def_bool y
+
+config STACKTRACE_SUPPORT
+	def_bool y
+	select STACKTRACE
+
+menu "ARC Architecture Configuration"
+
+menu "ARC Platform/SoC/Board"
+
+source "arch/arc/plat-tb10x/Kconfig"
+source "arch/arc/plat-axs10x/Kconfig"
+source "arch/arc/plat-hsdk/Kconfig"
+
+endmenu
+
+choice
+	prompt "ARC Instruction Set"
+	default ISA_ARCV2
+
+config ISA_ARCOMPACT
+	bool "ARCompact ISA"
+	select CPU_NO_EFFICIENT_FFS
+	help
+	  The original ARC ISA of ARC600/700 cores
+
+config ISA_ARCV2
+	bool "ARC ISA v2"
+	select ARC_TIMERS_64BIT
+	help
+	  ISA for the Next Generation ARC-HS cores
+
+endchoice
+
+menu "ARC CPU Configuration"
+
+choice
+	prompt "ARC Core"
+	default ARC_CPU_770 if ISA_ARCOMPACT
+	default ARC_CPU_HS if ISA_ARCV2
+
+config ARC_CPU_770
+	bool "ARC770"
+	depends on ISA_ARCOMPACT
+	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 entries in MMU)
+	  -Caches: New Prog Model, Region Flush
+	  -Insns: endian swap, load-locked/store-conditional, time-stamp-ctr
+
+config ARC_CPU_HS
+	bool "ARC-HS"
+	depends on ISA_ARCV2
+	help
+	  Support for ARC HS38x Cores based on ARCv2 ISA
+	  The notable features are:
+	    - SMP configurations of up to 4 cores with coherency
+	    - Optional L2 Cache and IO-Coherency
+	    - Revised Interrupt Architecture (multiple priorites, reg banks,
+	        auto stack switch, auto regfile save/restore)
+	    - MMUv4 (PIPT dcache, Huge Pages)
+	    - Instructions for
+		* 64bit load/store: LDD, STD
+		* Hardware assisted divide/remainder: DIV, REM
+		* Function prologue/epilogue: ENTER_S, LEAVE_S
+		* IRQ enable/disable: CLRI, SETI
+		* pop count: FFS, FLS
+		* SETcc, BMSKN, XBFU...
+
+endchoice
+
+config ARC_TUNE_MCPU
+	string "Override default -mcpu compiler flag"
+	default ""
+	help
+	  Override default -mcpu=xxx compiler flag (which is set depending on
+	  the ISA version) with the specified value.
+	  NOTE: If specified flag isn't supported by current compiler the
+	  ISA default value will be used as a fallback.
+
+config CPU_BIG_ENDIAN
+	bool "Enable Big Endian Mode"
+	help
+	  Build kernel for Big Endian Mode of ARC CPU
+
+config SMP
+	bool "Symmetric Multi-Processing"
+	select ARC_MCIP if ISA_ARCV2
+	help
+	  This enables support for systems with more than one CPU.
+
+if SMP
+
+config NR_CPUS
+	int "Maximum number of CPUs (2-4096)"
+	range 2 4096
+	default "4"
+
+config ARC_SMP_HALT_ON_RESET
+	bool "Enable Halt-on-reset boot mode"
+	help
+	  In SMP configuration cores can be configured as Halt-on-reset
+	  or they could all start at same time. For Halt-on-reset, non
+	  masters are parked until Master kicks them so they can start off
+	  at designated entry point. For other case, all jump to common
+	  entry point and spin wait for Master's signal.
+
+endif #SMP
+
+config ARC_MCIP
+	bool "ARConnect Multicore IP (MCIP) Support "
+	depends on ISA_ARCV2
+	default y if SMP
+	help
+	  This IP block enables SMP in ARC-HS38 cores.
+	  It provides for cross-core interrupts, multi-core debug
+	  hardware semaphores, shared memory,....
+
+menuconfig ARC_CACHE
+	bool "Enable Cache Support"
+	default y
+
+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
+
+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
+
+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
+
+choice
+	prompt "MMU Version"
+	default ARC_MMU_V3 if ISA_ARCOMPACT
+	default ARC_MMU_V4 if ISA_ARCV2
+
+config ARC_MMU_V3
+	bool "MMU v3"
+	depends on ISA_ARCOMPACT
+	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)
+
+config ARC_MMU_V4
+	bool "MMU v4"
+	depends on ISA_ARCV2
+
+endchoice
+
+
+choice
+	prompt "MMU Page Size"
+	default ARC_PAGE_SIZE_8K
+
+config ARC_PAGE_SIZE_8K
+	bool "8KB"
+	select HAVE_PAGE_SIZE_8KB
+	help
+	  Choose between 8k vs 16k
+
+config ARC_PAGE_SIZE_16K
+	select HAVE_PAGE_SIZE_16KB
+	bool "16KB"
+
+config ARC_PAGE_SIZE_4K
+	bool "4KB"
+	select HAVE_PAGE_SIZE_4KB
+
+endchoice
+
+choice
+	prompt "MMU Super Page Size"
+	depends on ISA_ARCV2 && TRANSPARENT_HUGEPAGE
+	default ARC_HUGEPAGE_2M
+
+config ARC_HUGEPAGE_2M
+	bool "2MB"
+
+config ARC_HUGEPAGE_16M
+	bool "16MB"
+
+endchoice
+
+config PGTABLE_LEVELS
+	int "Number of Page table levels"
+	default 2
+
+config ARC_COMPACT_IRQ_LEVELS
+	depends on ISA_ARCOMPACT
+	bool "Setup Timer IRQ as high Priority"
+	# if SMP, LV2 enabled ONLY if ARC implementation has LV2 re-entrancy
+	depends on !SMP
+
+config ARC_FPU_SAVE_RESTORE
+	bool "Enable FPU state persistence across context switch"
+	help
+	  ARCompact FPU has internal registers to assist with Double precision
+	  Floating Point operations. There are control and stauts registers
+	  for floating point exceptions and rounding modes. These are
+	  preserved across task context switch when enabled.
+
+config ARC_CANT_LLSC
+	def_bool n
+
+config ARC_HAS_LLSC
+	bool "Insn: LLOCK/SCOND (efficient atomic ops)"
+	default y
+	depends on !ARC_CANT_LLSC
+
+if ISA_ARCV2
+
+config ARC_USE_UNALIGNED_MEM_ACCESS
+	bool "Enable unaligned access in HW"
+	default y
+	select HAVE_EFFICIENT_UNALIGNED_ACCESS
+	help
+	  The ARC HS architecture supports unaligned memory access
+	  which is disabled by default. Enable unaligned access in
+	  hardware and use software to use it
+
+config ARC_HAS_LL64
+	bool "Insn: 64bit LDD/STD"
+	help
+	  Enable gcc to generate 64-bit load/store instructions
+	  ISA mandates even/odd registers to allow encoding of two
+	  dest operands with 2 possible source operands.
+	default y
+
+config ARC_HAS_DIV_REM
+	bool "Insn: div, divu, rem, remu"
+	default y
+
+config ARC_HAS_ACCL_REGS
+	bool "Reg Pair ACCL:ACCH (FPU and/or MPY > 6 and/or DSP)"
+	default y
+	help
+	  Depending on the configuration, CPU can contain accumulator reg-pair
+	  (also referred to as r58:r59). These can also be used by gcc as GPR so
+	  kernel needs to save/restore per process
+
+config ARC_DSP_HANDLED
+	def_bool n
+
+config ARC_DSP_SAVE_RESTORE_REGS
+	def_bool n
+
+choice
+	prompt "DSP support"
+	default ARC_DSP_NONE
+	help
+	  Depending on the configuration, CPU can contain DSP registers
+	  (ACC0_GLO, ACC0_GHI, DSP_BFLY0, DSP_CTRL, DSP_FFT_CTRL).
+	  Below are options describing how to handle these registers in
+	  interrupt entry / exit and in context switch.
+
+config ARC_DSP_NONE
+	bool "No DSP extension presence in HW"
+	help
+	  No DSP extension presence in HW
+
+config ARC_DSP_KERNEL
+	bool "DSP extension in HW, no support for userspace"
+	select ARC_HAS_ACCL_REGS
+	select ARC_DSP_HANDLED
+	help
+	  DSP extension presence in HW, no support for DSP-enabled userspace
+	  applications. We don't save / restore DSP registers and only do
+	  some minimal preparations so userspace won't be able to break kernel
+
+config ARC_DSP_USERSPACE
+	bool "Support DSP for userspace apps"
+	select ARC_HAS_ACCL_REGS
+	select ARC_DSP_HANDLED
+	select ARC_DSP_SAVE_RESTORE_REGS
+	help
+	  DSP extension presence in HW, support save / restore DSP registers to
+	  run DSP-enabled userspace applications
+
+config ARC_DSP_AGU_USERSPACE
+	bool "Support DSP with AGU for userspace apps"
+	select ARC_HAS_ACCL_REGS
+	select ARC_DSP_HANDLED
+	select ARC_DSP_SAVE_RESTORE_REGS
+	help
+	  DSP and AGU extensions presence in HW, support save / restore DSP
+	  and AGU registers to run DSP-enabled userspace applications
+endchoice
+
+config ARC_IRQ_NO_AUTOSAVE
+	bool "Disable hardware autosave regfile on interrupts"
+	default n
+	help
+	  On HS cores, taken interrupt auto saves the regfile on stack.
+	  This is programmable and can be optionally disabled in which case
+	  software INTERRUPT_PROLOGUE/EPILGUE do the needed work
+
+config ARC_LPB_DISABLE
+	bool "Disable loop buffer (LPB)"
+	help
+	  On HS cores, loop buffer (LPB) is programmable in runtime and can
+	  be optionally disabled.
+
+endif # ISA_ARCV2
+
+endmenu   # "ARC CPU Configuration"
+
+config LINUX_LINK_BASE
+	hex "Kernel 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.
+	  This needs to match memory start address specified in Device Tree
+
+config LINUX_RAM_BASE
+	hex "RAM base address"
+	default LINUX_LINK_BASE
+	help
+	  By default Linux is linked at base of RAM. However in some special
+	  cases (such as HSDK), Linux can't be linked at start of DDR, hence
+	  this option.
+
+config HIGHMEM
+	bool "High Memory Support"
+	select HAVE_ARCH_PFN_VALID
+	select KMAP_LOCAL
+	help
+	  With ARC 2G:2G address split, only upper 2G is directly addressable by
+	  kernel. Enable this to potentially allow access to rest of 2G and PAE
+	  in future
+
+config ARC_HAS_PAE40
+	bool "Support for the 40-bit Physical Address Extension"
+	depends on ARC_MMU_V4
+	depends on !ARC_PAGE_SIZE_4K
+	select HIGHMEM
+	select PHYS_ADDR_T_64BIT
+	help
+	  Enable access to physical memory beyond 4G, only supported on
+	  ARC cores with 40 bit Physical Addressing support
+
+config ARC_KVADDR_SIZE
+	int "Kernel Virtual Address Space size (MB)"
+	range 0 512
+	default "256"
+	help
+	  The kernel address space is carved out of 256MB of translated address
+	  space for catering to vmalloc, modules, pkmap, fixmap. This however may
+	  not suffice vmalloc requirements of a 4K CPU EZChip system. So allow
+	  this to be stretched to 512 MB (by extending into the reserved
+	  kernel-user gutter)
+
+config ARC_CURR_IN_REG
+	bool "cache current task pointer in gp"
+	default y
+	help
+	  This reserves gp register to point to Current Task in
+	  kernel mode eliding memory access for each access
+
+
+config ARC_EMUL_UNALIGNED
+	bool "Emulate unaligned memory access (userspace only)"
+	select SYSCTL_ARCH_UNALIGN_NO_WARN
+	select SYSCTL_ARCH_UNALIGN_ALLOW
+	depends on ISA_ARCOMPACT
+	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 HZ
+	int "Timer Frequency"
+	default 100
+
+config ARC_METAWARE_HLINK
+	bool "Support for Metaware debugger assisted Host access"
+	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
+
+if ARC_DBG
+
+config ARC_DW2_UNWIND
+	bool "Enable DWARF specific kernel stack unwind"
+	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_JUMP_LABEL
+	bool "Paranoid checks in Static Keys (jump labels) code"
+	depends on JUMP_LABEL
+	default y if STATIC_KEYS_SELFTEST
+	help
+	  Enable paranoid checks and self-test of both ARC-specific and generic
+	  part of static keys (jump labels) related code.
+endif
+
+config BUILTIN_DTB_NAME
+	string "Built in DTB"
+	default "nsim_700"
+	help
+	  Set the name of the DTB to embed in the vmlinux binary.
+
+endmenu	 # "ARC Architecture Configuration"
+
+config ARCH_FORCE_MAX_ORDER
+	int "Maximum zone order"
+	default "11" if ARC_HUGEPAGE_16M
+	default "10"
+
+source "kernel/power/Kconfig"
diff --git a/arch/arc/Kconfig.debug b/arch/arc/Kconfig.debug
new file mode 100644
index 000000000..45add86de
--- /dev/null
+++ b/arch/arc/Kconfig.debug
@@ -0,0 +1,10 @@
+# SPDX-License-Identifier: GPL-2.0
+
+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.
diff --git a/arch/arc/Makefile b/arch/arc/Makefile
new file mode 100644
index 000000000..868805ffc
--- /dev/null
+++ b/arch/arc/Makefile
@@ -0,0 +1,108 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+#
+
+KBUILD_DEFCONFIG := haps_hs_smp_defconfig
+
+ifeq ($(CROSS_COMPILE),)
+CROSS_COMPILE := $(call cc-cross-prefix, arc-linux- arceb-linux- arc-linux-gnu-)
+endif
+
+cflags-y	+= -fno-common -pipe -fno-builtin -mmedium-calls -mswape -D__linux__
+
+tune-mcpu-def-$(CONFIG_ISA_ARCOMPACT)	:= -mcpu=arc700
+tune-mcpu-def-$(CONFIG_ISA_ARCV2)	:= -mcpu=hs38
+
+ifeq ($(CONFIG_ARC_TUNE_MCPU),)
+cflags-y				+= $(tune-mcpu-def-y)
+else
+tune-mcpu				:= $(CONFIG_ARC_TUNE_MCPU)
+ifneq ($(call cc-option,$(tune-mcpu)),)
+cflags-y				+= $(tune-mcpu)
+else
+# The flag provided by 'CONFIG_ARC_TUNE_MCPU' option isn't known by this compiler
+# (probably the compiler is too old). Use ISA default mcpu flag instead as a safe option.
+$(warning ** WARNING ** CONFIG_ARC_TUNE_MCPU flag '$(tune-mcpu)' is unknown, fallback to '$(tune-mcpu-def-y)')
+cflags-y				+= $(tune-mcpu-def-y)
+endif
+endif
+
+ifdef CONFIG_ARC_CURR_IN_REG
+# For a global register definition, 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 global register
+# Can't do unconditionally because of recursive include issues
+# due to <linux/thread_info.h>
+LINUXINCLUDE	+=  -include $(srctree)/arch/arc/include/asm/current.h
+cflags-y	+= -ffixed-gp
+endif
+
+cflags-y				+= -fsection-anchors
+
+cflags-$(CONFIG_ARC_HAS_LLSC)		+= -mlock
+
+ifdef CONFIG_ISA_ARCV2
+
+ifdef CONFIG_ARC_USE_UNALIGNED_MEM_ACCESS
+cflags-y				+= -munaligned-access
+else
+cflags-y				+= -mno-unaligned-access
+endif
+
+ifndef CONFIG_ARC_HAS_LL64
+cflags-y				+= -mno-ll64
+endif
+
+ifndef CONFIG_ARC_HAS_DIV_REM
+cflags-y				+= -mno-div-rem
+endif
+
+endif
+
+cfi := $(call as-instr,.cfi_startproc\n.cfi_endproc,-DARC_DW2_UNWIND_AS_CFI)
+cflags-$(CONFIG_ARC_DW2_UNWIND)		+= -fasynchronous-unwind-tables $(cfi)
+
+# small data is default for elf32 tool-chain. If not usable, disable it
+# This also allows repurposing GP as scratch reg to gcc reg allocator
+disable_small_data := y
+cflags-$(disable_small_data)		+= -mno-sdata
+
+cflags-$(CONFIG_CPU_BIG_ENDIAN)		+= -mbig-endian
+ldflags-$(CONFIG_CPU_BIG_ENDIAN)	+= -EB
+
+LIBGCC	= $(shell $(CC) $(cflags-y) --print-libgcc-file-name)
+
+# Modules with short calls might break for calls into builtin-kernel
+KBUILD_CFLAGS_MODULE	+= -mlong-calls -mno-millicode
+
+# Finally dump eveything into kernel build system
+KBUILD_CFLAGS	+= $(cflags-y)
+KBUILD_AFLAGS	+= $(KBUILD_CFLAGS)
+KBUILD_LDFLAGS	+= $(ldflags-y)
+
+core-y				+= arch/arc/plat-sim/
+core-$(CONFIG_ARC_PLAT_TB10X)	+= arch/arc/plat-tb10x/
+core-$(CONFIG_ARC_PLAT_AXS10X)	+= arch/arc/plat-axs10x/
+core-$(CONFIG_ARC_SOC_HSDK)	+= arch/arc/plat-hsdk/
+
+libs-y		+= arch/arc/lib/ $(LIBGCC)
+
+boot		:= arch/arc/boot
+
+boot_targets := uImage.bin uImage.gz uImage.lzma
+
+PHONY += $(boot_targets)
+$(boot_targets): vmlinux
+	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
+
+uimage-default-y			:= uImage.bin
+uimage-default-$(CONFIG_KERNEL_GZIP)	:= uImage.gz
+uimage-default-$(CONFIG_KERNEL_LZMA)	:= uImage.lzma
+
+PHONY += uImage
+uImage: $(uimage-default-y)
+	@ln -sf $< $(boot)/uImage
+	@$(kecho) '  Image $(boot)/uImage is ready'
+
+CLEAN_FILES += $(boot)/uImage
diff --git a/arch/arc/boot/.gitignore b/arch/arc/boot/.gitignore
new file mode 100644
index 000000000..675db1494
--- /dev/null
+++ b/arch/arc/boot/.gitignore
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+uImage
diff --git a/arch/arc/boot/Makefile b/arch/arc/boot/Makefile
new file mode 100644
index 000000000..5a8550124
--- /dev/null
+++ b/arch/arc/boot/Makefile
@@ -0,0 +1,38 @@
+# SPDX-License-Identifier: GPL-2.0
+
+# uImage build relies on mkimage being available 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 reachable from your PATH
+
+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)
+
+targets += vmlinux.bin
+targets += vmlinux.bin.gz
+targets += vmlinux.bin.lzma
+targets += uImage.bin
+targets += uImage.gz
+targets += uImage.lzma
+
+$(obj)/vmlinux.bin: vmlinux FORCE
+	$(call if_changed,objcopy)
+
+$(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin FORCE
+	$(call if_changed,gzip)
+
+$(obj)/vmlinux.bin.lzma: $(obj)/vmlinux.bin FORCE
+	$(call if_changed,lzma)
+
+$(obj)/uImage.bin: $(obj)/vmlinux.bin FORCE
+	$(call if_changed,uimage,none)
+
+$(obj)/uImage.gz: $(obj)/vmlinux.bin.gz FORCE
+	$(call if_changed,uimage,gzip)
+
+$(obj)/uImage.lzma: $(obj)/vmlinux.bin.lzma FORCE
+	$(call if_changed,uimage,lzma)
diff --git a/arch/arc/boot/dts/Makefile b/arch/arc/boot/dts/Makefile
new file mode 100644
index 000000000..ee5664f06
--- /dev/null
+++ b/arch/arc/boot/dts/Makefile
@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0
+
+dtb-y	:= $(addsuffix .dtb, $(CONFIG_BUILTIN_DTB_NAME))
+
+# for CONFIG_OF_ALL_DTBS test
+dtb-	:= $(patsubst $(src)/%.dts,%.dtb, $(wildcard $(src)/*.dts))
+
+# board-specific dtc flags
+DTC_FLAGS_hsdk += --pad 20
diff --git a/arch/arc/boot/dts/abilis_tb100.dtsi b/arch/arc/boot/dts/abilis_tb100.dtsi
new file mode 100644
index 000000000..41026a3bf
--- /dev/null
+++ b/arch/arc/boot/dts/abilis_tb100.dtsi
@@ -0,0 +1,336 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Abilis Systems TB100 SOC device tree
+ *
+ * Copyright (C) Abilis Systems 2013
+ *
+ * Author: Christian Ruppert <christian.ruppert@abilis.com>
+ */
+
+/include/ "abilis_tb10x.dtsi"
+
+
+/ {
+	soc100 {
+		bus-frequency	= <166666666>;
+
+		pll0: oscillator {
+			clock-frequency  = <1000000000>;
+		};
+		cpu_clk: clkdiv_cpu {
+			clock-mult = <1>;
+			clock-div = <2>;
+		};
+		ahb_clk: clkdiv_ahb {
+			clock-mult = <1>;
+			clock-div = <6>;
+		};
+
+		iomux: iomux@ff10601c {
+			/* Port 1 */
+			pctl_tsin_s0: pctl-tsin-s0 {   /* Serial TS-in 0 */
+				abilis,function = "mis0";
+			};
+			pctl_tsin_s1: pctl-tsin-s1 {   /* Serial TS-in 1 */
+				abilis,function = "mis1";
+			};
+			pctl_gpio_a: pctl-gpio-a {     /* GPIO bank A */
+				abilis,function = "gpioa";
+			};
+			pctl_tsin_p1: pctl-tsin-p1 {   /* Parallel TS-in 1 */
+				abilis,function = "mip1";
+			};
+			/* Port 2 */
+			pctl_tsin_s2: pctl-tsin-s2 {   /* Serial TS-in 2 */
+				abilis,function = "mis2";
+			};
+			pctl_tsin_s3: pctl-tsin-s3 {   /* Serial TS-in 3 */
+				abilis,function = "mis3";
+			};
+			pctl_gpio_c: pctl-gpio-c {     /* GPIO bank C */
+				abilis,function = "gpioc";
+			};
+			pctl_tsin_p3: pctl-tsin-p3 {   /* Parallel TS-in 3 */
+				abilis,function = "mip3";
+			};
+			/* Port 3 */
+			pctl_tsin_s4: pctl-tsin-s4 {   /* Serial TS-in 4 */
+				abilis,function = "mis4";
+			};
+			pctl_tsin_s5: pctl-tsin-s5 {   /* Serial TS-in 5 */
+				abilis,function = "mis5";
+			};
+			pctl_gpio_e: pctl-gpio-e {     /* GPIO bank E */
+				abilis,function = "gpioe";
+			};
+			pctl_tsin_p5: pctl-tsin-p5 {   /* Parallel TS-in 5 */
+				abilis,function = "mip5";
+			};
+			/* Port 4 */
+			pctl_tsin_s6: pctl-tsin-s6 {   /* Serial TS-in 6 */
+				abilis,function = "mis6";
+			};
+			pctl_tsin_s7: pctl-tsin-s7 {   /* Serial TS-in 7 */
+				abilis,function = "mis7";
+			};
+			pctl_gpio_g: pctl-gpio-g {     /* GPIO bank G */
+				abilis,function = "gpiog";
+			};
+			pctl_tsin_p7: pctl-tsin-p7 {   /* Parallel TS-in 7 */
+				abilis,function = "mip7";
+			};
+			/* Port 5 */
+			pctl_gpio_j: pctl-gpio-j {     /* GPIO bank J */
+				abilis,function = "gpioj";
+			};
+			pctl_gpio_k: pctl-gpio-k {     /* GPIO bank K */
+				abilis,function = "gpiok";
+			};
+			pctl_ciplus: pctl-ciplus {     /* CI+ interface */
+				abilis,function = "ciplus";
+			};
+			pctl_mcard: pctl-mcard {       /* M-Card interface */
+				abilis,function = "mcard";
+			};
+			/* Port 6 */
+			pctl_tsout_p: pctl-tsout-p {   /* Parallel TS-out */
+				abilis,function = "mop";
+			};
+			pctl_tsout_s0: pctl-tsout-s0 { /* Serial TS-out 0 */
+				abilis,function = "mos0";
+			};
+			pctl_tsout_s1: pctl-tsout-s1 { /* Serial TS-out 1 */
+				abilis,function = "mos1";
+			};
+			pctl_tsout_s2: pctl-tsout-s2 { /* Serial TS-out 2 */
+				abilis,function = "mos2";
+			};
+			pctl_tsout_s3: pctl-tsout-s3 { /* Serial TS-out 3 */
+				abilis,function = "mos3";
+			};
+			/* Port 7 */
+			pctl_uart0: pctl-uart0 {       /* UART 0 */
+				abilis,function = "uart0";
+			};
+			pctl_uart1: pctl-uart1 {       /* UART 1 */
+				abilis,function = "uart1";
+			};
+			pctl_gpio_l: pctl-gpio-l {     /* GPIO bank L */
+				abilis,function = "gpiol";
+			};
+			pctl_gpio_m: pctl-gpio-m {     /* GPIO bank M */
+				abilis,function = "gpiom";
+			};
+			/* Port 8 */
+			pctl_spi3: pctl-spi3 {
+				abilis,function = "spi3";
+			};
+			/* Port 9 */
+			pctl_spi1: pctl-spi1 {
+				abilis,function = "spi1";
+			};
+			pctl_gpio_n: pctl-gpio-n {
+				abilis,function = "gpion";
+			};
+			/* Unmuxed GPIOs */
+			pctl_gpio_b: pctl-gpio-b {
+				abilis,function = "gpiob";
+			};
+			pctl_gpio_d: pctl-gpio-d {
+				abilis,function = "gpiod";
+			};
+			pctl_gpio_f: pctl-gpio-f {
+				abilis,function = "gpiof";
+			};
+			pctl_gpio_h: pctl-gpio-h {
+				abilis,function = "gpioh";
+			};
+			pctl_gpio_i: pctl-gpio-i {
+				abilis,function = "gpioi";
+			};
+		};
+
+		gpioa: gpio@ff140000 {
+			compatible = "abilis,tb10x-gpio";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+			interrupt-parent = <&tb10x_ictl>;
+			interrupts = <27 2>;
+			reg = <0xff140000 0x1000>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			abilis,ngpio = <3>;
+			gpio-ranges = <&iomux 0 0 0>;
+			gpio-ranges-group-names = "gpioa";
+		};
+		gpiob: gpio@ff141000 {
+			compatible = "abilis,tb10x-gpio";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+			interrupt-parent = <&tb10x_ictl>;
+			interrupts = <27 2>;
+			reg = <0xff141000 0x1000>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			abilis,ngpio = <2>;
+			gpio-ranges = <&iomux 0 0 0>;
+			gpio-ranges-group-names = "gpiob";
+		};
+		gpioc: gpio@ff142000 {
+			compatible = "abilis,tb10x-gpio";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+			interrupt-parent = <&tb10x_ictl>;
+			interrupts = <27 2>;
+			reg = <0xff142000 0x1000>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			abilis,ngpio = <3>;
+			gpio-ranges = <&iomux 0 0 0>;
+			gpio-ranges-group-names = "gpioc";
+		};
+		gpiod: gpio@ff143000 {
+			compatible = "abilis,tb10x-gpio";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+			interrupt-parent = <&tb10x_ictl>;
+			interrupts = <27 2>;
+			reg = <0xff143000 0x1000>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			abilis,ngpio = <2>;
+			gpio-ranges = <&iomux 0 0 0>;
+			gpio-ranges-group-names = "gpiod";
+		};
+		gpioe: gpio@ff144000 {
+			compatible = "abilis,tb10x-gpio";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+			interrupt-parent = <&tb10x_ictl>;
+			interrupts = <27 2>;
+			reg = <0xff144000 0x1000>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			abilis,ngpio = <3>;
+			gpio-ranges = <&iomux 0 0 0>;
+			gpio-ranges-group-names = "gpioe";
+		};
+		gpiof: gpio@ff145000 {
+			compatible = "abilis,tb10x-gpio";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+			interrupt-parent = <&tb10x_ictl>;
+			interrupts = <27 2>;
+			reg = <0xff145000 0x1000>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			abilis,ngpio = <2>;
+			gpio-ranges = <&iomux 0 0 0>;
+			gpio-ranges-group-names = "gpiof";
+		};
+		gpiog: gpio@ff146000 {
+			compatible = "abilis,tb10x-gpio";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+			interrupt-parent = <&tb10x_ictl>;
+			interrupts = <27 2>;
+			reg = <0xff146000 0x1000>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			abilis,ngpio = <3>;
+			gpio-ranges = <&iomux 0 0 0>;
+			gpio-ranges-group-names = "gpiog";
+		};
+		gpioh: gpio@ff147000 {
+			compatible = "abilis,tb10x-gpio";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+			interrupt-parent = <&tb10x_ictl>;
+			interrupts = <27 2>;
+			reg = <0xff147000 0x1000>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			abilis,ngpio = <2>;
+			gpio-ranges = <&iomux 0 0 0>;
+			gpio-ranges-group-names = "gpioh";
+		};
+		gpioi: gpio@ff148000 {
+			compatible = "abilis,tb10x-gpio";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+			interrupt-parent = <&tb10x_ictl>;
+			interrupts = <27 2>;
+			reg = <0xff148000 0x1000>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			abilis,ngpio = <12>;
+			gpio-ranges = <&iomux 0 0 0>;
+			gpio-ranges-group-names = "gpioi";
+		};
+		gpioj: gpio@ff149000 {
+			compatible = "abilis,tb10x-gpio";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+			interrupt-parent = <&tb10x_ictl>;
+			interrupts = <27 2>;
+			reg = <0xff149000 0x1000>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			abilis,ngpio = <32>;
+			gpio-ranges = <&iomux 0 0 0>;
+			gpio-ranges-group-names = "gpioj";
+		};
+		gpiok: gpio@ff14a000 {
+			compatible = "abilis,tb10x-gpio";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+			interrupt-parent = <&tb10x_ictl>;
+			interrupts = <27 2>;
+			reg = <0xff14a000 0x1000>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			abilis,ngpio = <22>;
+			gpio-ranges = <&iomux 0 0 0>;
+			gpio-ranges-group-names = "gpiok";
+		};
+		gpiol: gpio@ff14b000 {
+			compatible = "abilis,tb10x-gpio";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+			interrupt-parent = <&tb10x_ictl>;
+			interrupts = <27 2>;
+			reg = <0xff14b000 0x1000>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			abilis,ngpio = <4>;
+			gpio-ranges = <&iomux 0 0 0>;
+			gpio-ranges-group-names = "gpiol";
+		};
+		gpiom: gpio@ff14c000 {
+			compatible = "abilis,tb10x-gpio";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+			interrupt-parent = <&tb10x_ictl>;
+			interrupts = <27 2>;
+			reg = <0xff14c000 0x1000>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			abilis,ngpio = <4>;
+			gpio-ranges = <&iomux 0 0 0>;
+			gpio-ranges-group-names = "gpiom";
+		};
+		gpion: gpio@ff14d000 {
+			compatible = "abilis,tb10x-gpio";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+			interrupt-parent = <&tb10x_ictl>;
+			interrupts = <27 2>;
+			reg = <0xff14d000 0x1000>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			abilis,ngpio = <5>;
+			gpio-ranges = <&iomux 0 0 0>;
+			gpio-ranges-group-names = "gpion";
+		};
+	};
+};
diff --git a/arch/arc/boot/dts/abilis_tb100_dvk.dts b/arch/arc/boot/dts/abilis_tb100_dvk.dts
new file mode 100644
index 000000000..6d346de5e
--- /dev/null
+++ b/arch/arc/boot/dts/abilis_tb100_dvk.dts
@@ -0,0 +1,116 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Abilis Systems TB100 Development Kit PCB device tree
+ *
+ * Copyright (C) Abilis Systems 2013
+ *
+ * Author: Christian Ruppert <christian.ruppert@abilis.com>
+ */
+
+/dts-v1/;
+
+/include/ "abilis_tb100.dtsi"
+
+/ {
+	model = "abilis,tb100";
+	chosen {
+		bootargs = "earlycon=uart8250,mmio32,0xff100000,9600n8 console=ttyS0,9600n8";
+	};
+
+	aliases { };
+
+	memory {
+		device_type = "memory";
+		reg = <0x80000000 0x08000000>;	/* 128M */
+	};
+
+	soc100 {
+		uart@ff100000 {
+			pinctrl-names = "default";
+			pinctrl-0 = <&pctl_uart0>;
+		};
+		ethernet@fe100000 {
+			phy-mode = "rgmii";
+		};
+
+		i2c0: i2c@ff120000 {
+			i2c-sda-hold-time-ns = <432>;
+		};
+		i2c1: i2c@ff121000 {
+			i2c-sda-hold-time-ns = <432>;
+		};
+		i2c2: i2c@ff122000 {
+			i2c-sda-hold-time-ns = <432>;
+		};
+		i2c3: i2c@ff123000 {
+			i2c-sda-hold-time-ns = <432>;
+		};
+		i2c4: i2c@ff124000 {
+			i2c-sda-hold-time-ns = <432>;
+		};
+
+		leds {
+			compatible = "gpio-leds";
+			power {
+				label = "Power";
+				gpios = <&gpioi 0 0>;
+				linux,default-trigger = "default-on";
+			};
+			heartbeat {
+				label = "Heartbeat";
+				gpios = <&gpioi 1 0>;
+				linux,default-trigger = "heartbeat";
+			};
+			led2 {
+				label = "LED2";
+				gpios = <&gpioi 2 0>;
+				default-state = "off";
+			};
+			led3 {
+				label = "LED3";
+				gpios = <&gpioi 3 0>;
+				default-state = "off";
+			};
+			led4 {
+				label = "LED4";
+				gpios = <&gpioi 4 0>;
+				default-state = "off";
+			};
+			led5 {
+				label = "LED5";
+				gpios = <&gpioi 5 0>;
+				default-state = "off";
+			};
+			led6 {
+				label = "LED6";
+				gpios = <&gpioi 6 0>;
+				default-state = "off";
+			};
+			led7 {
+				label = "LED7";
+				gpios = <&gpioi 7 0>;
+				default-state = "off";
+			};
+			led8 {
+				label = "LED8";
+				gpios = <&gpioi 8 0>;
+				default-state = "off";
+			};
+			led9 {
+				label = "LED9";
+				gpios = <&gpioi 9 0>;
+				default-state = "off";
+			};
+			led10 {
+				label = "LED10";
+				gpios = <&gpioi 10 0>;
+				default-state = "off";
+			};
+			led11 {
+				label = "LED11";
+				gpios = <&gpioi 11 0>;
+				default-state = "off";
+			};
+		};
+	};
+};
diff --git a/arch/arc/boot/dts/abilis_tb101.dtsi b/arch/arc/boot/dts/abilis_tb101.dtsi
new file mode 100644
index 000000000..041ab1ba0
--- /dev/null
+++ b/arch/arc/boot/dts/abilis_tb101.dtsi
@@ -0,0 +1,345 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Abilis Systems TB101 SOC device tree
+ *
+ * Copyright (C) Abilis Systems 2013
+ *
+ * Author: Christian Ruppert <christian.ruppert@abilis.com>
+ */
+
+/include/ "abilis_tb10x.dtsi"
+
+
+/ {
+	soc100 {
+		bus-frequency	= <166666666>;
+
+		pll0: oscillator {
+			clock-frequency  = <1000000000>;
+		};
+		cpu_clk: clkdiv_cpu {
+			clock-mult = <1>;
+			clock-div = <2>;
+		};
+		ahb_clk: clkdiv_ahb {
+			clock-mult = <1>;
+			clock-div = <6>;
+		};
+
+		iomux: iomux@ff10601c {
+			/* Port 1 */
+			pctl_tsin_s0: pctl-tsin-s0 {   /* Serial TS-in 0 */
+				abilis,function = "mis0";
+			};
+			pctl_tsin_s1: pctl-tsin-s1 {   /* Serial TS-in 1 */
+				abilis,function = "mis1";
+			};
+			pctl_gpio_a: pctl-gpio-a {     /* GPIO bank A */
+				abilis,function = "gpioa";
+			};
+			pctl_tsin_p1: pctl-tsin-p1 {   /* Parallel TS-in 1 */
+				abilis,function = "mip1";
+			};
+			/* Port 2 */
+			pctl_tsin_s2: pctl-tsin-s2 {   /* Serial TS-in 2 */
+				abilis,function = "mis2";
+			};
+			pctl_tsin_s3: pctl-tsin-s3 {   /* Serial TS-in 3 */
+				abilis,function = "mis3";
+			};
+			pctl_gpio_c: pctl-gpio-c {     /* GPIO bank C */
+				abilis,function = "gpioc";
+			};
+			pctl_tsin_p3: pctl-tsin-p3 {   /* Parallel TS-in 3 */
+				abilis,function = "mip3";
+			};
+			/* Port 3 */
+			pctl_tsin_s4: pctl-tsin-s4 {   /* Serial TS-in 4 */
+				abilis,function = "mis4";
+			};
+			pctl_tsin_s5: pctl-tsin-s5 {   /* Serial TS-in 5 */
+				abilis,function = "mis5";
+			};
+			pctl_gpio_e: pctl-gpio-e {     /* GPIO bank E */
+				abilis,function = "gpioe";
+			};
+			pctl_tsin_p5: pctl-tsin-p5 {   /* Parallel TS-in 5 */
+				abilis,function = "mip5";
+			};
+			/* Port 4 */
+			pctl_tsin_s6: pctl-tsin-s6 {   /* Serial TS-in 6 */
+				abilis,function = "mis6";
+			};
+			pctl_tsin_s7: pctl-tsin-s7 {   /* Serial TS-in 7 */
+				abilis,function = "mis7";
+			};
+			pctl_gpio_g: pctl-gpio-g {     /* GPIO bank G */
+				abilis,function = "gpiog";
+			};
+			pctl_tsin_p7: pctl-tsin-p7 {   /* Parallel TS-in 7 */
+				abilis,function = "mip7";
+			};
+			/* Port 5 */
+			pctl_gpio_j: pctl-gpio-j {     /* GPIO bank J */
+				abilis,function = "gpioj";
+			};
+			pctl_gpio_k: pctl-gpio-k {     /* GPIO bank K */
+				abilis,function = "gpiok";
+			};
+			pctl_ciplus: pctl-ciplus {     /* CI+ interface */
+				abilis,function = "ciplus";
+			};
+			pctl_mcard: pctl-mcard {       /* M-Card interface */
+				abilis,function = "mcard";
+			};
+			pctl_stc0: pctl-stc0 {         /* Smart card I/F 0 */
+				abilis,function = "stc0";
+			};
+			pctl_stc1: pctl-stc1 {         /* Smart card I/F 1 */
+				abilis,function = "stc1";
+			};
+			/* Port 6 */
+			pctl_tsout_p: pctl-tsout-p {   /* Parallel TS-out */
+				abilis,function = "mop";
+			};
+			pctl_tsout_s0: pctl-tsout-s0 { /* Serial TS-out 0 */
+				abilis,function = "mos0";
+			};
+			pctl_tsout_s1: pctl-tsout-s1 { /* Serial TS-out 1 */
+				abilis,function = "mos1";
+			};
+			pctl_tsout_s2: pctl-tsout-s2 { /* Serial TS-out 2 */
+				abilis,function = "mos2";
+			};
+			pctl_tsout_s3: pctl-tsout-s3 { /* Serial TS-out 3 */
+				abilis,function = "mos3";
+			};
+			/* Port 7 */
+			pctl_uart0: pctl-uart0 {       /* UART 0 */
+				abilis,function = "uart0";
+			};
+			pctl_uart1: pctl-uart1 {       /* UART 1 */
+				abilis,function = "uart1";
+			};
+			pctl_gpio_l: pctl-gpio-l {     /* GPIO bank L */
+				abilis,function = "gpiol";
+			};
+			pctl_gpio_m: pctl-gpio-m {     /* GPIO bank M */
+				abilis,function = "gpiom";
+			};
+			/* Port 8 */
+			pctl_spi3: pctl-spi3 {
+				abilis,function = "spi3";
+			};
+			pctl_jtag: pctl-jtag {
+				abilis,function = "jtag";
+			};
+			/* Port 9 */
+			pctl_spi1: pctl-spi1 {
+				abilis,function = "spi1";
+			};
+			pctl_gpio_n: pctl-gpio-n {
+				abilis,function = "gpion";
+			};
+			/* Unmuxed GPIOs */
+			pctl_gpio_b: pctl-gpio-b {
+				abilis,function = "gpiob";
+			};
+			pctl_gpio_d: pctl-gpio-d {
+				abilis,function = "gpiod";
+			};
+			pctl_gpio_f: pctl-gpio-f {
+				abilis,function = "gpiof";
+			};
+			pctl_gpio_h: pctl-gpio-h {
+				abilis,function = "gpioh";
+			};
+			pctl_gpio_i: pctl-gpio-i {
+				abilis,function = "gpioi";
+			};
+		};
+
+		gpioa: gpio@ff140000 {
+			compatible = "abilis,tb10x-gpio";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+			interrupt-parent = <&tb10x_ictl>;
+			interrupts = <27 2>;
+			reg = <0xff140000 0x1000>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			abilis,ngpio = <3>;
+			gpio-ranges = <&iomux 0 0 0>;
+			gpio-ranges-group-names = "gpioa";
+		};
+		gpiob: gpio@ff141000 {
+			compatible = "abilis,tb10x-gpio";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+			interrupt-parent = <&tb10x_ictl>;
+			interrupts = <27 2>;
+			reg = <0xff141000 0x1000>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			abilis,ngpio = <2>;
+			gpio-ranges = <&iomux 0 0 0>;
+			gpio-ranges-group-names = "gpiob";
+		};
+		gpioc: gpio@ff142000 {
+			compatible = "abilis,tb10x-gpio";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+			interrupt-parent = <&tb10x_ictl>;
+			interrupts = <27 2>;
+			reg = <0xff142000 0x1000>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			abilis,ngpio = <3>;
+			gpio-ranges = <&iomux 0 0 0>;
+			gpio-ranges-group-names = "gpioc";
+		};
+		gpiod: gpio@ff143000 {
+			compatible = "abilis,tb10x-gpio";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+			interrupt-parent = <&tb10x_ictl>;
+			interrupts = <27 2>;
+			reg = <0xff143000 0x1000>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			abilis,ngpio = <2>;
+			gpio-ranges = <&iomux 0 0 0>;
+			gpio-ranges-group-names = "gpiod";
+		};
+		gpioe: gpio@ff144000 {
+			compatible = "abilis,tb10x-gpio";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+			interrupt-parent = <&tb10x_ictl>;
+			interrupts = <27 2>;
+			reg = <0xff144000 0x1000>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			abilis,ngpio = <3>;
+			gpio-ranges = <&iomux 0 0 0>;
+			gpio-ranges-group-names = "gpioe";
+		};
+		gpiof: gpio@ff145000 {
+			compatible = "abilis,tb10x-gpio";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+			interrupt-parent = <&tb10x_ictl>;
+			interrupts = <27 2>;
+			reg = <0xff145000 0x1000>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			abilis,ngpio = <2>;
+			gpio-ranges = <&iomux 0 0 0>;
+			gpio-ranges-group-names = "gpiof";
+		};
+		gpiog: gpio@ff146000 {
+			compatible = "abilis,tb10x-gpio";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+			interrupt-parent = <&tb10x_ictl>;
+			interrupts = <27 2>;
+			reg = <0xff146000 0x1000>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			abilis,ngpio = <3>;
+			gpio-ranges = <&iomux 0 0 0>;
+			gpio-ranges-group-names = "gpiog";
+		};
+		gpioh: gpio@ff147000 {
+			compatible = "abilis,tb10x-gpio";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+			interrupt-parent = <&tb10x_ictl>;
+			interrupts = <27 2>;
+			reg = <0xff147000 0x1000>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			abilis,ngpio = <2>;
+			gpio-ranges = <&iomux 0 0 0>;
+			gpio-ranges-group-names = "gpioh";
+		};
+		gpioi: gpio@ff148000 {
+			compatible = "abilis,tb10x-gpio";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+			interrupt-parent = <&tb10x_ictl>;
+			interrupts = <27 2>;
+			reg = <0xff148000 0x1000>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			abilis,ngpio = <12>;
+			gpio-ranges = <&iomux 0 0 0>;
+			gpio-ranges-group-names = "gpioi";
+		};
+		gpioj: gpio@ff149000 {
+			compatible = "abilis,tb10x-gpio";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+			interrupt-parent = <&tb10x_ictl>;
+			interrupts = <27 2>;
+			reg = <0xff149000 0x1000>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			abilis,ngpio = <32>;
+			gpio-ranges = <&iomux 0 0 0>;
+			gpio-ranges-group-names = "gpioj";
+		};
+		gpiok: gpio@ff14a000 {
+			compatible = "abilis,tb10x-gpio";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+			interrupt-parent = <&tb10x_ictl>;
+			interrupts = <27 2>;
+			reg = <0xff14a000 0x1000>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			abilis,ngpio = <22>;
+			gpio-ranges = <&iomux 0 0 0>;
+			gpio-ranges-group-names = "gpiok";
+		};
+		gpiol: gpio@ff14b000 {
+			compatible = "abilis,tb10x-gpio";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+			interrupt-parent = <&tb10x_ictl>;
+			interrupts = <27 2>;
+			reg = <0xff14b000 0x1000>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			abilis,ngpio = <4>;
+			gpio-ranges = <&iomux 0 0 0>;
+			gpio-ranges-group-names = "gpiol";
+		};
+		gpiom: gpio@ff14c000 {
+			compatible = "abilis,tb10x-gpio";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+			interrupt-parent = <&tb10x_ictl>;
+			interrupts = <27 2>;
+			reg = <0xff14c000 0x1000>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			abilis,ngpio = <4>;
+			gpio-ranges = <&iomux 0 0 0>;
+			gpio-ranges-group-names = "gpiom";
+		};
+		gpion: gpio@ff14d000 {
+			compatible = "abilis,tb10x-gpio";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+			interrupt-parent = <&tb10x_ictl>;
+			interrupts = <27 2>;
+			reg = <0xff14d000 0x1000>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			abilis,ngpio = <5>;
+			gpio-ranges = <&iomux 0 0 0>;
+			gpio-ranges-group-names = "gpion";
+		};
+	};
+};
diff --git a/arch/arc/boot/dts/abilis_tb101_dvk.dts b/arch/arc/boot/dts/abilis_tb101_dvk.dts
new file mode 100644
index 000000000..d11b790f8
--- /dev/null
+++ b/arch/arc/boot/dts/abilis_tb101_dvk.dts
@@ -0,0 +1,116 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Abilis Systems TB101 Development Kit PCB device tree
+ *
+ * Copyright (C) Abilis Systems 2013
+ *
+ * Author: Christian Ruppert <christian.ruppert@abilis.com>
+ */
+
+/dts-v1/;
+
+/include/ "abilis_tb101.dtsi"
+
+/ {
+	model = "abilis,tb101";
+	chosen {
+		bootargs = "earlycon=uart8250,mmio32,0xff100000,9600n8 console=ttyS0,9600n8";
+	};
+
+	aliases { };
+
+	memory {
+		device_type = "memory";
+		reg = <0x80000000 0x08000000>;	/* 128M */
+	};
+
+	soc100 {
+		uart@ff100000 {
+			pinctrl-names = "default";
+			pinctrl-0 = <&pctl_uart0>;
+		};
+		ethernet@fe100000 {
+			phy-mode = "rgmii";
+		};
+
+		i2c0: i2c@ff120000 {
+			i2c-sda-hold-time-ns = <432>;
+		};
+		i2c1: i2c@ff121000 {
+			i2c-sda-hold-time-ns = <432>;
+		};
+		i2c2: i2c@ff122000 {
+			i2c-sda-hold-time-ns = <432>;
+		};
+		i2c3: i2c@ff123000 {
+			i2c-sda-hold-time-ns = <432>;
+		};
+		i2c4: i2c@ff124000 {
+			i2c-sda-hold-time-ns = <432>;
+		};
+
+		leds {
+			compatible = "gpio-leds";
+			power {
+				label = "Power";
+				gpios = <&gpioi 0 0>;
+				linux,default-trigger = "default-on";
+			};
+			heartbeat {
+				label = "Heartbeat";
+				gpios = <&gpioi 1 0>;
+				linux,default-trigger = "heartbeat";
+			};
+			led2 {
+				label = "LED2";
+				gpios = <&gpioi 2 0>;
+				default-state = "off";
+			};
+			led3 {
+				label = "LED3";
+				gpios = <&gpioi 3 0>;
+				default-state = "off";
+			};
+			led4 {
+				label = "LED4";
+				gpios = <&gpioi 4 0>;
+				default-state = "off";
+			};
+			led5 {
+				label = "LED5";
+				gpios = <&gpioi 5 0>;
+				default-state = "off";
+			};
+			led6 {
+				label = "LED6";
+				gpios = <&gpioi 6 0>;
+				default-state = "off";
+			};
+			led7 {
+				label = "LED7";
+				gpios = <&gpioi 7 0>;
+				default-state = "off";
+			};
+			led8 {
+				label = "LED8";
+				gpios = <&gpioi 8 0>;
+				default-state = "off";
+			};
+			led9 {
+				label = "LED9";
+				gpios = <&gpioi 9 0>;
+				default-state = "off";
+			};
+			led10 {
+				label = "LED10";
+				gpios = <&gpioi 10 0>;
+				default-state = "off";
+			};
+			led11 {
+				label = "LED11";
+				gpios = <&gpioi 11 0>;
+				default-state = "off";
+			};
+		};
+	};
+};
diff --git a/arch/arc/boot/dts/abilis_tb10x.dtsi b/arch/arc/boot/dts/abilis_tb10x.dtsi
new file mode 100644
index 000000000..aa62619f2
--- /dev/null
+++ b/arch/arc/boot/dts/abilis_tb10x.dtsi
@@ -0,0 +1,243 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Abilis Systems TB10X SOC device tree
+ *
+ * Copyright (C) Abilis Systems 2013
+ *
+ * Author: Christian Ruppert <christian.ruppert@abilis.com>
+ */
+
+
+/ {
+	compatible		= "abilis,arc-tb10x";
+	#address-cells		= <1>;
+	#size-cells		= <1>;
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		cpu@0 {
+			device_type = "cpu";
+			compatible = "snps,arc770d";
+			reg = <0>;
+		};
+	};
+
+	/* TIMER0 with interrupt for clockevent */
+	timer0 {
+		compatible = "snps,arc-timer";
+		interrupts = <3>;
+		interrupt-parent = <&intc>;
+		clocks = <&cpu_clk>;
+	};
+
+	/* TIMER1 for free running clocksource */
+	timer1 {
+		compatible = "snps,arc-timer";
+		clocks = <&cpu_clk>;
+	};
+
+	soc100 {
+		#address-cells	= <1>;
+		#size-cells	= <1>;
+		device_type	= "soc";
+		ranges		= <0xfe000000 0xfe000000 0x02000000
+				0x000f0000 0x000f0000 0x00010000>;
+		compatible	= "abilis,tb10x", "simple-bus";
+
+		pll0: oscillator {
+			compatible = "fixed-clock";
+			#clock-cells = <0>;
+			clock-output-names = "pll0";
+		};
+		cpu_clk: clkdiv_cpu {
+			compatible = "fixed-factor-clock";
+			#clock-cells = <0>;
+			clocks = <&pll0>;
+			clock-output-names = "cpu_clk";
+		};
+		ahb_clk: clkdiv_ahb {
+			compatible = "fixed-factor-clock";
+			#clock-cells = <0>;
+			clocks = <&pll0>;
+			clock-output-names = "ahb_clk";
+		};
+
+		iomux: iomux@ff10601c {
+			compatible = "abilis,tb10x-iomux";
+			#gpio-range-cells = <3>;
+			reg = <0xff10601c 0x4>;
+		};
+
+		intc: interrupt-controller {
+			compatible = "snps,arc700-intc";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+		};
+		tb10x_ictl: pic@fe002000 {
+			compatible = "abilis,tb10x-ictl";
+			reg = <0xfe002000 0x20>;
+			interrupt-controller;
+			#interrupt-cells = <2>;
+			interrupt-parent = <&intc>;
+			interrupts = <5 6 7 8 9 10 11 12 13 14 15 16 17 18 19
+					20 21 22 23 24 25 26 27 28 29 30 31>;
+		};
+
+		uart@ff100000 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0xff100000 0x100>;
+			clock-frequency = <166666666>;
+			interrupts = <25 8>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+			interrupt-parent = <&tb10x_ictl>;
+		};
+		ethernet@fe100000 {
+			compatible = "snps,dwmac-3.70a","snps,dwmac";
+			reg = <0xfe100000 0x1058>;
+			interrupt-parent = <&tb10x_ictl>;
+			interrupts = <6 8>;
+			interrupt-names = "macirq";
+			clocks = <&ahb_clk>;
+			clock-names = "stmmaceth";
+		};
+		dma@fe000000 {
+			compatible = "snps,dma-spear1340";
+			reg = <0xfe000000 0x400>;
+			interrupt-parent = <&tb10x_ictl>;
+			interrupts = <14 8>;
+			dma-channels = <6>;
+			dma-requests = <0>;
+			dma-masters = <1>;
+			#dma-cells = <3>;
+			chan_allocation_order = <0>;
+			chan_priority = <1>;
+			block_size = <0x7ff>;
+			data-width = <4>;
+			clocks = <&ahb_clk>;
+			clock-names = "hclk";
+			multi-block = <1 1 1 1 1 1>;
+		};
+
+		i2c0: i2c@ff120000 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "snps,designware-i2c";
+			reg = <0xff120000 0x1000>;
+			interrupt-parent = <&tb10x_ictl>;
+			interrupts = <12 8>;
+			clocks = <&ahb_clk>;
+		};
+		i2c1: i2c@ff121000 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "snps,designware-i2c";
+			reg = <0xff121000 0x1000>;
+			interrupt-parent = <&tb10x_ictl>;
+			interrupts = <12 8>;
+			clocks = <&ahb_clk>;
+		};
+		i2c2: i2c@ff122000 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "snps,designware-i2c";
+			reg = <0xff122000 0x1000>;
+			interrupt-parent = <&tb10x_ictl>;
+			interrupts = <12 8>;
+			clocks = <&ahb_clk>;
+		};
+		i2c3: i2c@ff123000 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "snps,designware-i2c";
+			reg = <0xff123000 0x1000>;
+			interrupt-parent = <&tb10x_ictl>;
+			interrupts = <12 8>;
+			clocks = <&ahb_clk>;
+		};
+		i2c4: i2c@ff124000 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "snps,designware-i2c";
+			reg = <0xff124000 0x1000>;
+			interrupt-parent = <&tb10x_ictl>;
+			interrupts = <12 8>;
+			clocks = <&ahb_clk>;
+		};
+
+		spi0: spi@fe010000 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			cell-index = <0>;
+			compatible = "abilis,tb100-spi";
+			num-cs = <1>;
+			reg = <0xfe010000 0x20>;
+			interrupt-parent = <&tb10x_ictl>;
+			interrupts = <26 8>;
+			clocks = <&ahb_clk>;
+		};
+		spi1: spi@fe011000 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			cell-index = <1>;
+			compatible = "abilis,tb100-spi";
+			num-cs = <2>;
+			reg = <0xfe011000 0x20>;
+			interrupt-parent = <&tb10x_ictl>;
+			interrupts = <10 8>;
+			clocks = <&ahb_clk>;
+		};
+
+		tb10x_tsm: tb10x-tsm@ff316000 {
+			compatible = "abilis,tb100-tsm";
+			reg = <0xff316000 0x400>;
+			interrupt-parent = <&tb10x_ictl>;
+			interrupts = <17 8>;
+			output-clkdiv = <4>;
+			global-packet-delay = <0x21>;
+			port-packet-delay = <0>;
+		};
+		tb10x_stream_proc: tb10x-stream-proc {
+			compatible = "abilis,tb100-streamproc";
+			reg =   <0xfff00000 0x200>,
+				<0x000f0000 0x10000>,
+				<0xfff00200 0x105>,
+				<0xff10600c 0x1>,
+				<0xfe001018 0x1>;
+			reg-names =     "mbox",
+					"sp_iccm",
+					"mbox_irq",
+					"cpuctrl",
+					"a6it_int_force";
+			interrupt-parent = <&tb10x_ictl>;
+			interrupts = <20 2>, <19 2>;
+			interrupt-names = "cmd_irq", "event_irq";
+		};
+		tb10x_mdsc0: tb10x-mdscr@ff300000 {
+			compatible = "abilis,tb100-mdscr";
+			reg = <0xff300000 0x7000>;
+			tb100-mdscr-manage-tsin;
+		};
+		tb10x_mscr0: tb10x-mdscr@ff307000 {
+			compatible = "abilis,tb100-mdscr";
+			reg = <0xff307000 0x7000>;
+		};
+		tb10x_scr0: tb10x-mdscr@ff30e000 {
+			compatible = "abilis,tb100-mdscr";
+			reg = <0xff30e000 0x4000>;
+			tb100-mdscr-manage-tsin;
+		};
+		tb10x_scr1: tb10x-mdscr@ff312000 {
+			compatible = "abilis,tb100-mdscr";
+			reg = <0xff312000 0x4000>;
+			tb100-mdscr-manage-tsin;
+		};
+		tb10x_wfb: tb10x-wfb@ff319000 {
+			compatible = "abilis,tb100-wfb";
+			reg = <0xff319000 0x1000>;
+			interrupt-parent = <&tb10x_ictl>;
+			interrupts = <16 8>;
+		};
+	};
+};
diff --git a/arch/arc/boot/dts/axc001.dtsi b/arch/arc/boot/dts/axc001.dtsi
new file mode 100644
index 000000000..88bcc7ab6
--- /dev/null
+++ b/arch/arc/boot/dts/axc001.dtsi
@@ -0,0 +1,126 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2013-15 Synopsys, Inc. (www.synopsys.com)
+ */
+
+/*
+ * Device tree for AXC001 770D/EM6/AS221 CPU card
+ * Note that this file only supports the 770D CPU
+ */
+
+/include/ "skeleton.dtsi"
+
+/ {
+	compatible = "snps,arc";
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	cpu_card {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		ranges = <0x00000000 0x0 0xf0000000 0x10000000>;
+
+		core_clk: core_clk {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <750000000>;
+		};
+
+		input_clk: input-clk {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <33333333>;
+		};
+
+		core_intc: arc700-intc@cpu {
+			compatible = "snps,arc700-intc";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+		};
+
+		/*
+		 * this GPIO block ORs all interrupts on CPU card (creg,..)
+		 * to uplink only 1 IRQ to ARC core intc
+		 */
+		dw-apb-gpio@2000 {
+			compatible = "snps,dw-apb-gpio";
+			reg = < 0x2000 0x80 >;
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			ictl_intc: gpio-controller@0 {
+				compatible = "snps,dw-apb-gpio-port";
+				gpio-controller;
+				#gpio-cells = <2>;
+				ngpios = <30>;
+				reg = <0>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+				interrupt-parent = <&core_intc>;
+				interrupts = <15>;
+			};
+		};
+
+		debug_uart: dw-apb-uart@5000 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x5000 0x100>;
+			clock-frequency = <33333000>;
+			interrupt-parent = <&ictl_intc>;
+			interrupts = <19 4>;
+			baud = <115200>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+		};
+
+		arcpct0: pct {
+			compatible = "snps,arc700-pct";
+		};
+	};
+
+	/*
+	 * This INTC is actually connected to DW APB GPIO
+	 * which acts as a wire between MB INTC and CPU INTC.
+	 * GPIO INTC is configured in platform init code
+	 * and here we mimic direct connection from MB INTC to
+	 * CPU INTC, thus we set "interrupts = <7>" instead of
+	 * "interrupts = <12>"
+	 *
+	 * This intc actually resides on MB, but we move it here to
+	 * avoid duplicating the MB dtsi file given that IRQ from
+	 * this intc to cpu intc are different for axs101 and axs103
+	 */
+	mb_intc: interrupt-controller@e0012000 {
+		#interrupt-cells = <1>;
+		compatible = "snps,dw-apb-ictl";
+		reg = < 0x0 0xe0012000 0x0 0x200 >;
+		interrupt-controller;
+		interrupt-parent = <&core_intc>;
+		interrupts = < 7 >;
+	};
+
+	memory {
+		device_type = "memory";
+		/* CONFIG_LINUX_RAM_BASE needs to match low mem start */
+		reg = <0x0 0x80000000 0x0 0x1b000000>;	/* (512 - 32) MiB */
+	};
+
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+		/*
+		 * We just move frame buffer area to the very end of
+		 * available DDR. And even though in case of ARC770 there's
+		 * no strict requirement for a frame-buffer to be in any
+		 * particular location it allows us to use the same
+		 * base board's DT node for ARC PGU as for ARc HS38.
+		 */
+		frame_buffer: frame_buffer@9e000000 {
+			compatible = "shared-dma-pool";
+			reg = <0x0 0x9e000000 0x0 0x2000000>;
+			no-map;
+		};
+	};
+};
diff --git a/arch/arc/boot/dts/axc003.dtsi b/arch/arc/boot/dts/axc003.dtsi
new file mode 100644
index 000000000..9a2dc39a5
--- /dev/null
+++ b/arch/arc/boot/dts/axc003.dtsi
@@ -0,0 +1,161 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
+ */
+
+/*
+ * Device tree for AXC003 CPU card: HS38x UP configuration
+ */
+
+/include/ "skeleton_hs.dtsi"
+
+/ {
+	compatible = "snps,arc";
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	cpu_card {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		ranges = <0x00000000 0x0 0xf0000000 0x10000000>;
+
+		input_clk: input-clk {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <33333333>;
+		};
+
+		core_clk: core-clk@80 {
+			compatible = "snps,axs10x-arc-pll-clock";
+			reg = <0x80 0x10>, <0x100 0x10>;
+			#clock-cells = <0>;
+			clocks = <&input_clk>;
+
+			/*
+			 * Set initial core pll output frequency to 90MHz.
+			 * It will be applied at the core pll driver probing
+			 * on early boot.
+			 */
+			assigned-clocks = <&core_clk>;
+			assigned-clock-rates = <90000000>;
+		};
+
+		core_intc: archs-intc@cpu {
+			compatible = "snps,archs-intc";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+		};
+
+		/*
+		 * this GPIO block ORs all interrupts on CPU card (creg,..)
+		 * to uplink only 1 IRQ to ARC core intc
+		 */
+		dw-apb-gpio@2000 {
+			compatible = "snps,dw-apb-gpio";
+			reg = < 0x2000 0x80 >;
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			ictl_intc: gpio-controller@0 {
+				compatible = "snps,dw-apb-gpio-port";
+				gpio-controller;
+				#gpio-cells = <2>;
+				ngpios = <30>;
+				reg = <0>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+				interrupt-parent = <&core_intc>;
+				interrupts = <25>;
+			};
+		};
+
+		debug_uart: dw-apb-uart@5000 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x5000 0x100>;
+			clock-frequency = <33333000>;
+			interrupt-parent = <&ictl_intc>;
+			interrupts = <2 4>;
+			baud = <115200>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+		};
+
+		arcpct0: pct {
+			compatible = "snps,archs-pct";
+			#interrupt-cells = <1>;
+			interrupt-parent = <&core_intc>;
+			interrupts = <20>;
+		};
+	};
+
+	/*
+	 * Mark DMA peripherals connected via IOC port as dma-coherent. We do
+	 * it via overlay because peripherals defined in axs10x_mb.dtsi are
+	 * used for both AXS101 and AXS103 boards and only AXS103 has IOC (so
+	 * only AXS103 board has HW-coherent DMA peripherals)
+	 * We don't need to mark pgu@17000 as dma-coherent because it uses
+	 * external DMA buffer located outside of IOC aperture.
+	 */
+	axs10x_mb {
+		ethernet@18000 {
+			dma-coherent;
+		};
+
+		usb@40000 {
+			dma-coherent;
+		};
+
+		usb@60000 {
+			dma-coherent;
+		};
+
+		mmc@15000 {
+			dma-coherent;
+		};
+	};
+
+	/*
+	 * The DW APB ICTL intc on MB is connected to CPU intc via a
+	 * DT "invisible" DW APB GPIO block, configured to simply pass thru
+	 * interrupts - setup accordingly in platform init (plat-axs10x/ax10x.c)
+	 *
+	 * So here we mimic a direct connection between them, ignoring the
+	 * ABPG GPIO. Thus set "interrupts = <24>" (DW APB GPIO to core)
+	 * instead of "interrupts = <12>" (DW APB ICTL to DW APB GPIO)
+	 *
+	 * This intc actually resides on MB, but we move it here to
+	 * avoid duplicating the MB dtsi file given that IRQ from
+	 * this intc to cpu intc are different for axs101 and axs103
+	 */
+	mb_intc: interrupt-controller@e0012000 {
+		#interrupt-cells = <1>;
+		compatible = "snps,dw-apb-ictl";
+		reg = < 0x0 0xe0012000 0x0 0x200 >;
+		interrupt-controller;
+		interrupt-parent = <&core_intc>;
+		interrupts = < 24 >;
+	};
+
+	memory {
+		device_type = "memory";
+		/* CONFIG_LINUX_RAM_BASE needs to match low mem start */
+		reg = <0x0 0x80000000 0x0 0x20000000	/* 512 MiB low mem */
+		       0x1 0xc0000000 0x0 0x40000000>;	/* 1 GiB highmem */
+	};
+
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+		/*
+		 * Move frame buffer out of IOC aperture (0x8z-0xaz).
+		 */
+		frame_buffer: frame_buffer@be000000 {
+			compatible = "shared-dma-pool";
+			reg = <0x0 0xbe000000 0x0 0x2000000>;
+			no-map;
+		};
+	};
+};
diff --git a/arch/arc/boot/dts/axc003_idu.dtsi b/arch/arc/boot/dts/axc003_idu.dtsi
new file mode 100644
index 000000000..f31382cb8
--- /dev/null
+++ b/arch/arc/boot/dts/axc003_idu.dtsi
@@ -0,0 +1,167 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2014, 2015 Synopsys, Inc. (www.synopsys.com)
+ */
+
+/*
+ * Device tree for AXC003 CPU card: HS38x2 (Dual Core) with IDU intc
+ */
+
+/include/ "skeleton_hs_idu.dtsi"
+
+/ {
+	compatible = "snps,arc";
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	cpu_card {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		ranges = <0x00000000 0x0 0xf0000000 0x10000000>;
+
+		input_clk: input-clk {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <33333333>;
+		};
+
+		core_clk: core-clk@80 {
+			compatible = "snps,axs10x-arc-pll-clock";
+			reg = <0x80 0x10>, <0x100 0x10>;
+			#clock-cells = <0>;
+			clocks = <&input_clk>;
+
+			/*
+			 * Set initial core pll output frequency to 100MHz.
+			 * It will be applied at the core pll driver probing
+			 * on early boot.
+			 */
+			assigned-clocks = <&core_clk>;
+			assigned-clock-rates = <100000000>;
+		};
+
+		core_intc: archs-intc@cpu {
+			compatible = "snps,archs-intc";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+		};
+
+		idu_intc: idu-interrupt-controller {
+			compatible = "snps,archs-idu-intc";
+			interrupt-controller;
+			interrupt-parent = <&core_intc>;
+			#interrupt-cells = <1>;
+		};
+
+		/*
+		 * this GPIO block ORs all interrupts on CPU card (creg,..)
+		 * to uplink only 1 IRQ to ARC core intc
+		 */
+		dw-apb-gpio@2000 {
+			compatible = "snps,dw-apb-gpio";
+			reg = < 0x2000 0x80 >;
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			ictl_intc: gpio-controller@0 {
+				compatible = "snps,dw-apb-gpio-port";
+				gpio-controller;
+				#gpio-cells = <2>;
+				ngpios = <30>;
+				reg = <0>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+				interrupt-parent = <&idu_intc>;
+				interrupts = <1>;
+			};
+		};
+
+		debug_uart: dw-apb-uart@5000 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x5000 0x100>;
+			clock-frequency = <33333000>;
+			interrupt-parent = <&ictl_intc>;
+			interrupts = <2 4>;
+			baud = <115200>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+		};
+
+		arcpct0: pct {
+			compatible = "snps,archs-pct";
+			#interrupt-cells = <1>;
+			interrupt-parent = <&core_intc>;
+			interrupts = <20>;
+		};
+	};
+
+	/*
+	 * Mark DMA peripherals connected via IOC port as dma-coherent. We do
+	 * it via overlay because peripherals defined in axs10x_mb.dtsi are
+	 * used for both AXS101 and AXS103 boards and only AXS103 has IOC (so
+	 * only AXS103 board has HW-coherent DMA peripherals)
+	 * We don't need to mark pgu@17000 as dma-coherent because it uses
+	 * external DMA buffer located outside of IOC aperture.
+	 */
+	axs10x_mb {
+		ethernet@18000 {
+			dma-coherent;
+		};
+
+		usb@40000 {
+			dma-coherent;
+		};
+
+		usb@60000 {
+			dma-coherent;
+		};
+
+		mmc@15000 {
+			dma-coherent;
+		};
+	};
+
+	/*
+	 * This INTC is actually connected to DW APB GPIO
+	 * which acts as a wire between MB INTC and CPU INTC.
+	 * GPIO INTC is configured in platform init code
+	 * and here we mimic direct connection from MB INTC to
+	 * CPU INTC, thus we set "interrupts = <0 1>" instead of
+	 * "interrupts = <12>"
+	 *
+	 * This intc actually resides on MB, but we move it here to
+	 * avoid duplicating the MB dtsi file given that IRQ from
+	 * this intc to cpu intc are different for axs101 and axs103
+	 */
+	mb_intc: interrupt-controller@e0012000 {
+		#interrupt-cells = <1>;
+		compatible = "snps,dw-apb-ictl";
+		reg = < 0x0 0xe0012000 0x0 0x200 >;
+		interrupt-controller;
+		interrupt-parent = <&idu_intc>;
+		interrupts = <0>;
+	};
+
+	memory {
+		device_type = "memory";
+		/* CONFIG_LINUX_RAM_BASE needs to match low mem start */
+		reg = <0x0 0x80000000 0x0 0x20000000	/* 512 MiB low mem */
+		       0x1 0xc0000000 0x0 0x40000000>;	/* 1 GiB highmem */
+	};
+
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+		/*
+		 * Move frame buffer out of IOC aperture (0x8z-0xaz).
+		 */
+		frame_buffer: frame_buffer@be000000 {
+			compatible = "shared-dma-pool";
+			reg = <0x0 0xbe000000 0x0 0x2000000>;
+			no-map;
+		};
+	};
+};
diff --git a/arch/arc/boot/dts/axs101.dts b/arch/arc/boot/dts/axs101.dts
new file mode 100644
index 000000000..c4cfc5f4f
--- /dev/null
+++ b/arch/arc/boot/dts/axs101.dts
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2013-15 Synopsys, Inc. (www.synopsys.com)
+ *
+ * ARC AXS101 S/W development platform
+ */
+/dts-v1/;
+
+/include/ "axc001.dtsi"
+/include/ "axs10x_mb.dtsi"
+
+/ {
+	model = "snps,axs101";
+	compatible = "snps,axs101", "snps,arc-sdp";
+
+	chosen {
+		bootargs = "earlycon=uart8250,mmio32,0xe0022000,115200n8 console=tty0 console=ttyS3,115200n8 consoleblank=0 print-fatal-signals=1";
+	};
+};
diff --git a/arch/arc/boot/dts/axs103.dts b/arch/arc/boot/dts/axs103.dts
new file mode 100644
index 000000000..16ccb7ba7
--- /dev/null
+++ b/arch/arc/boot/dts/axs103.dts
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
+ */
+
+/*
+ * Device Tree for AXS103 SDP with AXS10X Main Board and
+ * AXC003 FPGA Card (with UP bitfile)
+ */
+/dts-v1/;
+
+/include/ "axc003.dtsi"
+/include/ "axs10x_mb.dtsi"
+
+/ {
+	model = "snps,axs103";
+	compatible = "snps,axs103", "snps,arc-sdp";
+
+	chosen {
+		bootargs = "earlycon=uart8250,mmio32,0xe0022000,115200n8 console=ttyS3,115200n8 debug print-fatal-signals=1";
+	};
+};
diff --git a/arch/arc/boot/dts/axs103_idu.dts b/arch/arc/boot/dts/axs103_idu.dts
new file mode 100644
index 000000000..a934b92a8
--- /dev/null
+++ b/arch/arc/boot/dts/axs103_idu.dts
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
+ */
+
+/*
+ * Device Tree for AXS103 SDP with AXS10X Main Board and
+ * AXC003 FPGA Card (with SMP bitfile)
+ */
+/dts-v1/;
+
+/include/ "axc003_idu.dtsi"
+/include/ "axs10x_mb.dtsi"
+
+/ {
+	model = "snps,axs103-smp";
+	compatible = "snps,axs103", "snps,arc-sdp";
+
+	chosen {
+		bootargs = "earlycon=uart8250,mmio32,0xe0022000,115200n8 console=tty0 console=ttyS3,115200n8 print-fatal-signals=1 consoleblank=0";
+	};
+};
diff --git a/arch/arc/boot/dts/axs10x_mb.dtsi b/arch/arc/boot/dts/axs10x_mb.dtsi
new file mode 100644
index 000000000..3add2fe25
--- /dev/null
+++ b/arch/arc/boot/dts/axs10x_mb.dtsi
@@ -0,0 +1,330 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Support for peripherals on the AXS10x mainboard
+ *
+ * Copyright (C) 2013-15 Synopsys, Inc. (www.synopsys.com)
+ */
+
+/ {
+	aliases {
+		ethernet = &gmac;
+	};
+
+	axs10x_mb {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0x00000000 0x0 0xe0000000 0x10000000>;
+		interrupt-parent = <&mb_intc>;
+
+		creg_rst: reset-controller@11220 {
+			compatible = "snps,axs10x-reset";
+			#reset-cells = <1>;
+			reg = <0x11220 0x4>;
+		};
+
+		i2sclk: i2sclk@100a0 {
+			compatible = "snps,axs10x-i2s-pll-clock";
+			reg = <0x100a0 0x10>;
+			clocks = <&i2spll_clk>;
+			#clock-cells = <0>;
+		};
+
+		clocks {
+			i2spll_clk: i2spll_clk {
+				compatible = "fixed-clock";
+				clock-frequency = <27000000>;
+				#clock-cells = <0>;
+			};
+
+			i2cclk: i2cclk {
+				compatible = "fixed-clock";
+				clock-frequency = <50000000>;
+				#clock-cells = <0>;
+			};
+
+			apbclk: apbclk {
+				compatible = "fixed-clock";
+				clock-frequency = <50000000>;
+				#clock-cells = <0>;
+			};
+
+			mmcclk: mmcclk {
+				compatible = "fixed-clock";
+				/*
+				 * DW sdio controller has external ciu clock divider
+				 * controlled via register in SDIO IP. It divides
+				 * sdio_ref_clk (which comes from CGU) by 16 for
+				 * default. So default mmcclk clock (which comes
+				 * to sdk_in) is 25000000 Hz.
+				 */
+				clock-frequency = <25000000>;
+				#clock-cells = <0>;
+			};
+		};
+
+		pguclk: pguclk@10080 {
+			compatible = "snps,axs10x-pgu-pll-clock";
+			reg = <0x10080 0x10>, <0x110 0x10>;
+			#clock-cells = <0>;
+			clocks = <&input_clk>;
+		};
+
+		gmac: ethernet@18000 {
+			#interrupt-cells = <1>;
+			compatible = "snps,dwmac";
+			reg = < 0x18000 0x2000 >;
+			interrupts = < 4 >;
+			interrupt-names = "macirq";
+			phy-mode = "rgmii";
+			snps,pbl = < 32 >;
+			snps,multicast-filter-bins = <256>;
+			clocks = <&apbclk>;
+			clock-names = "stmmaceth";
+			max-speed = <100>;
+			resets = <&creg_rst 5>;
+			reset-names = "stmmaceth";
+			mac-address = [00 00 00 00 00 00]; /* Filled in by U-Boot */
+		};
+
+		usb@40000 {
+			compatible = "generic-ehci";
+			reg = < 0x40000 0x100 >;
+			interrupts = < 8 >;
+		};
+
+		usb@60000 {
+			compatible = "generic-ohci";
+			reg = < 0x60000 0x100 >;
+			interrupts = < 8 >;
+		};
+
+		/*
+		 * According to DW Mobile Storage databook it is required
+		 * to use  "Hold Register" if card is enumerated in SDR12 or
+		 * SDR25 modes.
+		 *
+		 * Utilization of "Hold Register" is already implemented via
+		 * dw_mci_pltfm_prepare_command() which in its turn gets
+		 * used through dw_mci_drv_data->prepare_command call-back.
+		 * This call-back is used in Altera Socfpga platform and so
+		 * we may reuse it saying that we're compatible with their
+		 * "altr,socfpga-dw-mshc".
+		 *
+		 * Most probably "Hold Register" utilization is platform-
+		 * independent requirement which means that single unified
+		 * "snps,dw-mshc" should be enough for all users of DW MMC once
+		 * dw_mci_pltfm_prepare_command() is used in generic platform
+		 * code.
+		 */
+		mmc@15000 {
+			compatible = "altr,socfpga-dw-mshc";
+			reg = < 0x15000 0x400 >;
+			fifo-depth = < 16 >;
+			card-detect-delay = < 200 >;
+			clocks = <&apbclk>, <&mmcclk>;
+			clock-names = "biu", "ciu";
+			interrupts = < 7 >;
+			bus-width = < 4 >;
+		};
+
+		uart@20000 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x20000 0x100>;
+			clock-frequency = <33333333>;
+			interrupts = <17>;
+			baud = <115200>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+		};
+
+		uart@21000 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x21000 0x100>;
+			clock-frequency = <33333333>;
+			interrupts = <18>;
+			baud = <115200>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+		};
+
+		/* UART muxed with USB data port (ttyS3) */
+		uart@22000 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x22000 0x100>;
+			clock-frequency = <33333333>;
+			interrupts = <19>;
+			baud = <115200>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+		};
+
+		i2c@1d000 {
+			compatible = "snps,designware-i2c";
+			reg = <0x1d000 0x100>;
+			clock-frequency = <400000>;
+			clocks = <&i2cclk>;
+			interrupts = <14>;
+		};
+
+		i2s: i2s@1e000 {
+			compatible = "snps,designware-i2s";
+			reg = <0x1e000 0x100>;
+			clocks = <&i2sclk 0>;
+			clock-names = "i2sclk";
+			interrupts = <15>;
+			#sound-dai-cells = <0>;
+		};
+
+		i2c@1f000 {
+			compatible = "snps,designware-i2c";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x1f000 0x100>;
+			clock-frequency = <400000>;
+			clocks = <&i2cclk>;
+			interrupts = <16>;
+
+			adv7511:adv7511@39{
+				compatible="adi,adv7511";
+				reg = <0x39>;
+				interrupts = <23>;
+				adi,input-depth = <8>;
+				adi,input-colorspace = "rgb";
+				adi,input-clock = "1x";
+				adi,clock-delay = <0x03>;
+				#sound-dai-cells = <0>;
+
+				ports {
+					#address-cells = <1>;
+					#size-cells = <0>;
+
+					/* RGB/YUV input */
+					port@0 {
+						reg = <0>;
+						adv7511_input:endpoint {
+						remote-endpoint = <&pgu_output>;
+						};
+					};
+
+					/* HDMI output */
+					port@1 {
+						reg = <1>;
+						adv7511_output: endpoint {
+							remote-endpoint = <&hdmi_connector_in>;
+						};
+					};
+				};
+			};
+
+			eeprom@54{
+				compatible = "atmel,24c01";
+				reg = <0x54>;
+				pagesize = <0x8>;
+			};
+
+			eeprom@57{
+				compatible = "atmel,24c04";
+				reg = <0x57>;
+				pagesize = <0x8>;
+			};
+		};
+
+		hdmi0: connector {
+			compatible = "hdmi-connector";
+			type = "a";
+			port {
+				hdmi_connector_in: endpoint {
+					remote-endpoint = <&adv7511_output>;
+				};
+			};
+		};
+
+		gpio0:gpio@13000 {
+			compatible = "snps,dw-apb-gpio";
+			reg = <0x13000 0x1000>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			gpio0_banka: gpio-controller@0 {
+				compatible = "snps,dw-apb-gpio-port";
+				gpio-controller;
+				#gpio-cells = <2>;
+				ngpios = <32>;
+				reg = <0>;
+			};
+
+			gpio0_bankb: gpio-controller@1 {
+				compatible = "snps,dw-apb-gpio-port";
+				gpio-controller;
+				#gpio-cells = <2>;
+				ngpios = <8>;
+				reg = <1>;
+			};
+
+			gpio0_bankc: gpio-controller@2 {
+				compatible = "snps,dw-apb-gpio-port";
+				gpio-controller;
+				#gpio-cells = <2>;
+				ngpios = <8>;
+				reg = <2>;
+			};
+		};
+
+		gpio1:gpio@14000 {
+			compatible = "snps,dw-apb-gpio";
+			reg = <0x14000 0x1000>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			gpio1_banka: gpio-controller@0 {
+				compatible = "snps,dw-apb-gpio-port";
+				gpio-controller;
+				#gpio-cells = <2>;
+				ngpios = <30>;
+				reg = <0>;
+			};
+
+			gpio1_bankb: gpio-controller@1 {
+				compatible = "snps,dw-apb-gpio-port";
+				gpio-controller;
+				#gpio-cells = <2>;
+				ngpios = <10>;
+				reg = <1>;
+			};
+
+			gpio1_bankc: gpio-controller@2 {
+				compatible = "snps,dw-apb-gpio-port";
+				gpio-controller;
+				#gpio-cells = <2>;
+				ngpios = <8>;
+				reg = <2>;
+			};
+		};
+
+		pgu@17000 {
+			compatible = "snps,arcpgu";
+			reg = <0x17000 0x400>;
+			clocks = <&pguclk>;
+			clock-names = "pxlclk";
+			memory-region = <&frame_buffer>;
+			port {
+				pgu_output: endpoint {
+					remote-endpoint = <&adv7511_input>;
+				};
+			};
+		};
+
+		sound_playback {
+			compatible = "simple-audio-card";
+			simple-audio-card,name = "AXS10x HDMI Audio";
+			simple-audio-card,format = "i2s";
+			simple-audio-card,cpu {
+				sound-dai = <&i2s>;
+			};
+			simple-audio-card,codec {
+				sound-dai = <&adv7511>;
+			};
+		};
+	};
+};
diff --git a/arch/arc/boot/dts/haps_hs.dts b/arch/arc/boot/dts/haps_hs.dts
new file mode 100644
index 000000000..76ad527a0
--- /dev/null
+++ b/arch/arc/boot/dts/haps_hs.dts
@@ -0,0 +1,99 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2016-2014 Synopsys, Inc. (www.synopsys.com)
+ */
+/dts-v1/;
+
+/include/ "skeleton_hs.dtsi"
+
+/ {
+	model = "snps,zebu_hs";
+	compatible = "snps,zebu_hs";
+	#address-cells = <2>;
+	#size-cells = <2>;
+	interrupt-parent = <&core_intc>;
+
+	memory {
+		device_type = "memory";
+		/* CONFIG_LINUX_RAM_BASE needs to match low mem start */
+		reg = <0x0 0x80000000 0x0 0x40000000	/* 1 GB low mem */
+		       0x1 0x00000000 0x0 0x40000000>;	/* 1 GB highmem */
+	};
+
+	chosen {
+		bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=ttyS0,115200n8 debug print-fatal-signals=1";
+	};
+
+	aliases {
+		serial0 = &uart0;
+	};
+
+	fpga {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		/* only perip space at end of low mem accessible
+			  bus addr,  parent bus addr, size    */
+		ranges = <0x80000000 0x0 0x80000000 0x80000000>;
+
+		core_clk: core_clk {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <50000000>;
+		};
+
+		core_intc: interrupt-controller {
+			compatible = "snps,archs-intc";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+		};
+
+		uart0: serial@f0000000 {
+			compatible = "ns16550a";
+			reg = <0xf0000000 0x2000>;
+			interrupts = <24>;
+			clock-frequency = <50000000>;
+			baud = <115200>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+			no-loopback-test = <1>;
+		};
+
+		arcpct0: pct {
+			compatible = "snps,archs-pct";
+			#interrupt-cells = <1>;
+			interrupts = <20>;
+		};
+
+		virtio0: virtio@f0100000 {
+			compatible = "virtio,mmio";
+			reg = <0xf0100000 0x2000>;
+			interrupts = <31>;
+		};
+
+		virtio1: virtio@f0102000 {
+			compatible = "virtio,mmio";
+			reg = <0xf0102000 0x2000>;
+			interrupts = <32>;
+		};
+
+		virtio2: virtio@f0104000 {
+			compatible = "virtio,mmio";
+			reg = <0xf0104000 0x2000>;
+			interrupts = <33>;
+		};
+
+		virtio3: virtio@f0106000 {
+			compatible = "virtio,mmio";
+			reg = <0xf0106000 0x2000>;
+			interrupts = <34>;
+		};
+
+		virtio4: virtio@f0108000 {
+			compatible = "virtio,mmio";
+			reg = <0xf0108000 0x2000>;
+			interrupts = <35>;
+		};
+	};
+};
diff --git a/arch/arc/boot/dts/haps_hs_idu.dts b/arch/arc/boot/dts/haps_hs_idu.dts
new file mode 100644
index 000000000..738c76cd0
--- /dev/null
+++ b/arch/arc/boot/dts/haps_hs_idu.dts
@@ -0,0 +1,74 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2016-2014 Synopsys, Inc. (www.synopsys.com)
+ */
+/dts-v1/;
+
+/include/ "skeleton_hs_idu.dtsi"
+
+/ {
+	model = "snps,zebu_hs-smp";
+	compatible = "snps,zebu_hs";
+	#address-cells = <1>;
+	#size-cells = <1>;
+	interrupt-parent = <&core_intc>;
+
+	memory {
+		device_type = "memory";
+		reg = <0x80000000 0x20000000>;	/* 512 */
+	};
+
+	chosen {
+		bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=ttyS0,115200n8 debug print-fatal-signals=1";
+	};
+
+	aliases {
+		serial0 = &uart0;
+	};
+
+	fpga {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		/* child and parent address space 1:1 mapped */
+		ranges;
+
+		core_clk: core_clk {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <50000000>;	/* 50 MHZ */
+		};
+
+		core_intc: interrupt-controller {
+			compatible = "snps,archs-intc";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+		};
+
+		idu_intc: idu-interrupt-controller {
+			compatible = "snps,archs-idu-intc";
+			interrupt-controller;
+			interrupt-parent = <&core_intc>;
+			#interrupt-cells = <1>;
+		};
+
+		uart0: serial@f0000000 {
+			compatible = "ns16550a";
+			reg = <0xf0000000 0x2000>;
+			interrupt-parent = <&idu_intc>;
+			interrupts = <0>;
+			clock-frequency = <50000000>;
+			baud = <115200>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+			no-loopback-test = <1>;
+		};
+
+		arcpct0: pct {
+			compatible = "snps,archs-pct";
+			#interrupt-cells = <1>;
+			interrupts = <20>;
+		};
+	};
+};
diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts
new file mode 100644
index 000000000..98bb85072
--- /dev/null
+++ b/arch/arc/boot/dts/hsdk.dts
@@ -0,0 +1,350 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2017 Synopsys, Inc. (www.synopsys.com)
+ */
+
+/*
+ * Device Tree for ARC HS Development Kit
+ */
+/dts-v1/;
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/reset/snps,hsdk-reset.h>
+
+/ {
+	model = "snps,hsdk";
+	compatible = "snps,hsdk";
+
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	chosen {
+		bootargs = "earlycon=uart8250,mmio32,0xf0005000,115200n8 console=ttyS0,115200n8 debug print-fatal-signals=1";
+	};
+
+	aliases {
+		ethernet = &gmac;
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu@0 {
+			device_type = "cpu";
+			compatible = "snps,archs38";
+			reg = <0>;
+			clocks = <&core_clk>;
+		};
+
+		cpu@1 {
+			device_type = "cpu";
+			compatible = "snps,archs38";
+			reg = <1>;
+			clocks = <&core_clk>;
+		};
+
+		cpu@2 {
+			device_type = "cpu";
+			compatible = "snps,archs38";
+			reg = <2>;
+			clocks = <&core_clk>;
+		};
+
+		cpu@3 {
+			device_type = "cpu";
+			compatible = "snps,archs38";
+			reg = <3>;
+			clocks = <&core_clk>;
+		};
+	};
+
+	input_clk: input-clk {
+		#clock-cells = <0>;
+		compatible = "fixed-clock";
+		clock-frequency = <33333333>;
+	};
+
+	reg_5v0: regulator-5v0 {
+		compatible = "regulator-fixed";
+
+		regulator-name = "5v0-supply";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+	};
+
+	cpu_intc: cpu-interrupt-controller {
+		compatible = "snps,archs-intc";
+		interrupt-controller;
+		#interrupt-cells = <1>;
+	};
+
+	idu_intc: idu-interrupt-controller {
+		compatible = "snps,archs-idu-intc";
+		interrupt-controller;
+		#interrupt-cells = <1>;
+		interrupt-parent = <&cpu_intc>;
+	};
+
+	arcpct: pct {
+		compatible = "snps,archs-pct";
+		interrupt-parent = <&cpu_intc>;
+		interrupts = <20>;
+	};
+
+	/* TIMER0 with interrupt for clockevent */
+	timer {
+		compatible = "snps,arc-timer";
+		interrupts = <16>;
+		interrupt-parent = <&cpu_intc>;
+		clocks = <&core_clk>;
+	};
+
+	/* 64-bit Global Free Running Counter */
+	gfrc {
+		compatible = "snps,archs-timer-gfrc";
+		clocks = <&core_clk>;
+	};
+
+	soc {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		interrupt-parent = <&idu_intc>;
+
+		ranges = <0x00000000 0x0 0xf0000000 0x10000000>;
+
+		cgu_rst: reset-controller@8a0 {
+			compatible = "snps,hsdk-reset";
+			#reset-cells = <1>;
+			reg = <0x8a0 0x4>, <0xff0 0x4>;
+		};
+
+		core_clk: core-clk@0 {
+			compatible = "snps,hsdk-core-pll-clock";
+			reg = <0x00 0x10>, <0x14b8 0x4>;
+			#clock-cells = <0>;
+			clocks = <&input_clk>;
+
+			/*
+			 * Set initial core pll output frequency to 1GHz.
+			 * It will be applied at the core pll driver probing
+			 * on early boot.
+			 */
+			assigned-clocks = <&core_clk>;
+			assigned-clock-rates = <1000000000>;
+		};
+
+		serial: serial@5000 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x5000 0x100>;
+			clock-frequency = <33330000>;
+			interrupts = <6>;
+			baud = <115200>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+		};
+
+		gmacclk: gmacclk {
+			compatible = "fixed-clock";
+			clock-frequency = <400000000>;
+			#clock-cells = <0>;
+		};
+
+		mmcclk_ciu: mmcclk-ciu {
+			compatible = "fixed-clock";
+			/*
+			 * DW sdio controller has external ciu clock divider
+			 * controlled via register in SDIO IP. Due to its
+			 * unexpected default value (it should divide by 1
+			 * but it divides by 8) SDIO IP uses wrong clock and
+			 * works unstable (see STAR 9001204800)
+			 * We switched to the minimum possible value of the
+			 * divisor (div-by-2) in HSDK platform code.
+			 * So add temporary fix and change clock frequency
+			 * to 50000000 Hz until we fix dw sdio driver itself.
+			 */
+			clock-frequency = <50000000>;
+			#clock-cells = <0>;
+		};
+
+		mmcclk_biu: mmcclk-biu {
+			compatible = "fixed-clock";
+			clock-frequency = <400000000>;
+			#clock-cells = <0>;
+		};
+
+		gpu_core_clk: gpu-core-clk {
+			compatible = "fixed-clock";
+			clock-frequency = <400000000>;
+			#clock-cells = <0>;
+		};
+
+		gpu_dma_clk: gpu-dma-clk {
+			compatible = "fixed-clock";
+			clock-frequency = <400000000>;
+			#clock-cells = <0>;
+		};
+
+		gpu_cfg_clk: gpu-cfg-clk {
+			compatible = "fixed-clock";
+			clock-frequency = <200000000>;
+			#clock-cells = <0>;
+		};
+
+		dmac_core_clk: dmac-core-clk {
+			compatible = "fixed-clock";
+			clock-frequency = <400000000>;
+			#clock-cells = <0>;
+		};
+
+		dmac_cfg_clk: dmac-gpu-cfg-clk {
+			compatible = "fixed-clock";
+			clock-frequency = <200000000>;
+			#clock-cells = <0>;
+		};
+
+		gmac: ethernet@8000 {
+			compatible = "snps,dwmac";
+			reg = <0x8000 0x2000>;
+			interrupts = <10>;
+			interrupt-names = "macirq";
+			phy-mode = "rgmii-id";
+			snps,pbl = <32>;
+			snps,multicast-filter-bins = <256>;
+			clocks = <&gmacclk>;
+			clock-names = "stmmaceth";
+			phy-handle = <&phy0>;
+			resets = <&cgu_rst HSDK_ETH_RESET>;
+			reset-names = "stmmaceth";
+			mac-address = [00 00 00 00 00 00]; /* Filled in by U-Boot */
+			dma-coherent;
+
+			tx-fifo-depth = <4096>;
+			rx-fifo-depth = <4096>;
+
+			mdio {
+				#address-cells = <1>;
+				#size-cells = <0>;
+				compatible = "snps,dwmac-mdio";
+				phy0: ethernet-phy@0 { /* Micrel KSZ9031 */
+					reg = <0>;
+				};
+			};
+		};
+
+		usb@60000 {
+			compatible = "snps,hsdk-v1.0-ohci", "generic-ohci";
+			reg = <0x60000 0x100>;
+			interrupts = <15>;
+			resets = <&cgu_rst HSDK_USB_RESET>;
+			dma-coherent;
+		};
+
+		usb@40000 {
+			compatible = "snps,hsdk-v1.0-ehci", "generic-ehci";
+			reg = <0x40000 0x100>;
+			interrupts = <15>;
+			resets = <&cgu_rst HSDK_USB_RESET>;
+			dma-coherent;
+		};
+
+		mmc@a000 {
+			compatible = "altr,socfpga-dw-mshc";
+			reg = <0xa000 0x400>;
+			num-slots = <1>;
+			fifo-depth = <16>;
+			card-detect-delay = <200>;
+			clocks = <&mmcclk_biu>, <&mmcclk_ciu>;
+			clock-names = "biu", "ciu";
+			interrupts = <12>;
+			bus-width = <4>;
+			dma-coherent;
+		};
+
+		spi0: spi@20000 {
+			compatible = "snps,dw-apb-ssi";
+			reg = <0x20000 0x100>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			interrupts = <16>;
+			num-cs = <2>;
+			reg-io-width = <4>;
+			clocks = <&input_clk>;
+			cs-gpios = <&creg_gpio 0 GPIO_ACTIVE_LOW>,
+				   <&creg_gpio 1 GPIO_ACTIVE_LOW>;
+
+			flash@0 {
+				compatible = "sst26wf016b", "jedec,spi-nor";
+				reg = <0>;
+				#address-cells = <1>;
+				#size-cells = <1>;
+				spi-max-frequency = <4000000>;
+			};
+
+			adc@1 {
+				compatible = "ti,adc108s102";
+				reg = <1>;
+				vref-supply = <&reg_5v0>;
+				spi-max-frequency = <1000000>;
+			};
+		};
+
+		creg_gpio: gpio@14b0 {
+			compatible = "snps,creg-gpio-hsdk";
+			reg = <0x14b0 0x4>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			ngpios = <2>;
+		};
+
+		gpio: gpio@3000 {
+			compatible = "snps,dw-apb-gpio";
+			reg = <0x3000 0x20>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			gpio_port_a: gpio-controller@0 {
+				compatible = "snps,dw-apb-gpio-port";
+				gpio-controller;
+				#gpio-cells = <2>;
+				ngpios = <24>;
+				reg = <0>;
+			};
+		};
+
+		gpu_3d: gpu@90000 {
+			compatible = "vivante,gc";
+			reg = <0x90000 0x4000>;
+			clocks = <&gpu_dma_clk>,
+				 <&gpu_cfg_clk>,
+				 <&gpu_core_clk>,
+				 <&gpu_core_clk>;
+			clock-names = "bus", "reg", "core", "shader";
+			interrupts = <28>;
+		};
+
+		dmac: dmac@80000 {
+			compatible = "snps,axi-dma-1.01a";
+			reg = <0x80000 0x400>;
+			interrupts = <27>;
+			clocks = <&dmac_core_clk>, <&dmac_cfg_clk>;
+			clock-names = "core-clk", "cfgr-clk";
+
+			dma-channels = <4>;
+			snps,dma-masters = <2>;
+			snps,data-width = <3>;
+			snps,block-size = <4096 4096 4096 4096>;
+			snps,priority = <0 1 2 3>;
+			snps,axi-max-burst-len = <16>;
+		};
+	};
+
+	memory@80000000 {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		device_type = "memory";
+		reg = <0x0 0x80000000 0x0 0x40000000>;  /* 1 GB lowmem */
+		/*     0x1 0x00000000 0x0 0x40000000>;     1 GB highmem */
+	};
+};
diff --git a/arch/arc/boot/dts/nsim_700.dts b/arch/arc/boot/dts/nsim_700.dts
new file mode 100644
index 000000000..f8832a15e
--- /dev/null
+++ b/arch/arc/boot/dts/nsim_700.dts
@@ -0,0 +1,59 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2012 Synopsys, Inc. (www.synopsys.com)
+ */
+/dts-v1/;
+
+/include/ "skeleton.dtsi"
+
+/ {
+	model = "snps,nsim";
+	compatible = "snps,nsim";
+	#address-cells = <1>;
+	#size-cells = <1>;
+	interrupt-parent = <&core_intc>;
+
+	chosen {
+		bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=ttyS0,115200n8 print-fatal-signals=1";
+	};
+
+	aliases {
+		serial0 = &uart0;
+	};
+
+	fpga {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		/* child and parent address space 1:1 mapped */
+		ranges;
+
+		core_clk: core_clk {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <80000000>;
+		};
+
+		core_intc: interrupt-controller {
+			compatible = "snps,arc700-intc";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+		};
+
+		uart0: serial@f0000000 {
+			compatible = "ns16550a";
+			reg = <0xf0000000 0x2000>;
+			interrupts = <24>;
+			clock-frequency = <50000000>;
+			baud = <115200>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+			no-loopback-test = <1>;
+		};
+
+		arcpct0: pct {
+			compatible = "snps,arc700-pct";
+		};
+	};
+};
diff --git a/arch/arc/boot/dts/nsimosci.dts b/arch/arc/boot/dts/nsimosci.dts
new file mode 100644
index 000000000..fc207c4a4
--- /dev/null
+++ b/arch/arc/boot/dts/nsimosci.dts
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2013 Synopsys, Inc. (www.synopsys.com)
+ */
+/dts-v1/;
+
+/include/ "skeleton.dtsi"
+
+/ {
+	model = "snps,nsimosci";
+	compatible = "snps,nsimosci";
+	#address-cells = <1>;
+	#size-cells = <1>;
+	interrupt-parent = <&core_intc>;
+
+	chosen {
+		/* this is for console on PGU */
+		/* bootargs = "console=tty0 consoleblank=0"; */
+		/* this is for console on serial */
+		bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblank=0 debug video=640x480-24 print-fatal-signals=1";
+	};
+
+	aliases {
+		serial0 = &uart0;
+	};
+
+	fpga {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		/* child and parent address space 1:1 mapped */
+		ranges;
+
+		core_clk: core_clk {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <20000000>;
+		};
+
+		core_intc: interrupt-controller {
+			compatible = "snps,arc700-intc";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+		};
+
+		uart0: serial@f0000000 {
+			compatible = "ns8250";
+			reg = <0xf0000000 0x2000>;
+			interrupts = <11>;
+			clock-frequency = <3686400>;
+			baud = <115200>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+			no-loopback-test = <1>;
+		};
+
+		pguclk: pguclk {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <25175000>;
+		};
+
+		pgu@f9000000 {
+			compatible = "snps,arcpgu";
+			reg = <0xf9000000 0x400>;
+			clocks = <&pguclk>;
+			clock-names = "pxlclk";
+		};
+
+		ps2: ps2@f9001000 {
+			compatible = "snps,arc_ps2";
+			reg = <0xf9000400 0x14>;
+			interrupts = <13>;
+			interrupt-names = "arc_ps2_irq";
+		};
+
+		eth0: ethernet@f0003000 {
+			compatible = "ezchip,nps-mgt-enet";
+			reg = <0xf0003000 0x44>;
+			interrupts = <7>;
+		};
+
+		arcpct0: pct {
+			compatible = "snps,arc700-pct";
+		};
+	};
+};
diff --git a/arch/arc/boot/dts/nsimosci_hs.dts b/arch/arc/boot/dts/nsimosci_hs.dts
new file mode 100644
index 000000000..71f1f8416
--- /dev/null
+++ b/arch/arc/boot/dts/nsimosci_hs.dts
@@ -0,0 +1,90 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
+ */
+/dts-v1/;
+
+/include/ "skeleton_hs.dtsi"
+
+/ {
+	model = "snps,nsimosci_hs";
+	compatible = "snps,nsimosci_hs";
+	#address-cells = <1>;
+	#size-cells = <1>;
+	interrupt-parent = <&core_intc>;
+
+	chosen {
+		/* this is for console on PGU */
+		/* bootargs = "console=tty0 consoleblank=0"; */
+		/* this is for console on serial */
+		bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblank=0 debug video=640x480-24 print-fatal-signals=1";
+	};
+
+	aliases {
+		serial0 = &uart0;
+	};
+
+	fpga {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		/* child and parent address space 1:1 mapped */
+		ranges;
+
+		core_clk: core_clk {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <20000000>;
+		};
+
+		core_intc: core-interrupt-controller {
+			compatible = "snps,archs-intc";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+		};
+
+		uart0: serial@f0000000 {
+			compatible = "ns8250";
+			reg = <0xf0000000 0x2000>;
+			interrupts = <24>;
+			clock-frequency = <3686400>;
+			baud = <115200>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+			no-loopback-test = <1>;
+		};
+
+		pguclk: pguclk {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <25175000>;
+		};
+
+		pgu@f9000000 {
+			compatible = "snps,arcpgu";
+			reg = <0xf9000000 0x400>;
+			clocks = <&pguclk>;
+			clock-names = "pxlclk";
+		};
+
+		ps2: ps2@f9001000 {
+			compatible = "snps,arc_ps2";
+			reg = <0xf9000400 0x14>;
+			interrupts = <27>;
+			interrupt-names = "arc_ps2_irq";
+		};
+
+		eth0: ethernet@f0003000 {
+			compatible = "ezchip,nps-mgt-enet";
+			reg = <0xf0003000 0x44>;
+			interrupts = <25>;
+		};
+
+		arcpct0: pct {
+			compatible = "snps,archs-pct";
+			#interrupt-cells = <1>;
+			interrupts = <20>;
+		};
+	};
+};
diff --git a/arch/arc/boot/dts/nsimosci_hs_idu.dts b/arch/arc/boot/dts/nsimosci_hs_idu.dts
new file mode 100644
index 000000000..69d794c59
--- /dev/null
+++ b/arch/arc/boot/dts/nsimosci_hs_idu.dts
@@ -0,0 +1,98 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
+ */
+/dts-v1/;
+
+/include/ "skeleton_hs_idu.dtsi"
+
+/ {
+	model = "snps,nsimosci_hs-smp";
+	compatible = "snps,nsimosci_hs";
+	#address-cells = <1>;
+	#size-cells = <1>;
+	interrupt-parent = <&core_intc>;
+
+	chosen {
+		/* this is for console on serial */
+		bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblan=0 debug video=640x480-24 print-fatal-signals=1";
+	};
+
+	aliases {
+		serial0 = &uart0;
+	};
+
+	fpga {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		/* child and parent address space 1:1 mapped */
+		ranges;
+
+		core_clk: core_clk {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <5000000>;
+		};
+
+		core_intc: core-interrupt-controller {
+			compatible = "snps,archs-intc";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+		};
+
+		idu_intc: idu-interrupt-controller {
+			compatible = "snps,archs-idu-intc";
+			interrupt-controller;
+			interrupt-parent = <&core_intc>;
+			#interrupt-cells = <1>;
+		};
+
+		uart0: serial@f0000000 {
+			compatible = "ns8250";
+			reg = <0xf0000000 0x2000>;
+			interrupt-parent = <&idu_intc>;
+			interrupts = <0>;
+			clock-frequency = <3686400>;
+			baud = <115200>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+			no-loopback-test = <1>;
+		};
+
+		pguclk: pguclk {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <25175000>;
+		};
+
+		pgu@f9000000 {
+			compatible = "snps,arcpgu";
+			reg = <0xf9000000 0x400>;
+			clocks = <&pguclk>;
+			clock-names = "pxlclk";
+		};
+
+		ps2: ps2@f9001000 {
+			compatible = "snps,arc_ps2";
+			reg = <0xf9000400 0x14>;
+			interrupts = <3>;
+			interrupt-parent = <&idu_intc>;
+			interrupt-names = "arc_ps2_irq";
+		};
+
+		eth0: ethernet@f0003000 {
+			compatible = "ezchip,nps-mgt-enet";
+			reg = <0xf0003000 0x44>;
+			interrupt-parent = <&idu_intc>;
+			interrupts = <1>;
+		};
+
+		arcpct0: pct {
+			compatible = "snps,archs-pct";
+			#interrupt-cells = <1>;
+			interrupts = <20>;
+		};
+	};
+};
diff --git a/arch/arc/boot/dts/skeleton.dtsi b/arch/arc/boot/dts/skeleton.dtsi
new file mode 100644
index 000000000..ba86b8036
--- /dev/null
+++ b/arch/arc/boot/dts/skeleton.dtsi
@@ -0,0 +1,48 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+/*
+ * Skeleton device tree; the bare minimum needed to boot; just include and
+ * add a compatible value.
+ */
+
+/ {
+	compatible = "snps,arc";
+	#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>;
+			clocks = <&core_clk>;
+		};
+	};
+
+	/* TIMER0 with interrupt for clockevent */
+	timer0 {
+		compatible = "snps,arc-timer";
+		interrupts = <3>;
+		interrupt-parent = <&core_intc>;
+		clocks = <&core_clk>;
+	};
+
+	/* TIMER1 for free running clocksource */
+	timer1 {
+		compatible = "snps,arc-timer";
+		clocks = <&core_clk>;
+	};
+
+	memory {
+		device_type = "memory";
+		reg = <0x80000000 0x10000000>;	/* 256M */
+	};
+};
diff --git a/arch/arc/boot/dts/skeleton_hs.dtsi b/arch/arc/boot/dts/skeleton_hs.dtsi
new file mode 100644
index 000000000..8fb49890e
--- /dev/null
+++ b/arch/arc/boot/dts/skeleton_hs.dtsi
@@ -0,0 +1,49 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2016 Synopsys, Inc. (www.synopsys.com)
+ */
+
+/ {
+	compatible = "snps,arc";
+	#address-cells = <1>;
+	#size-cells = <1>;
+	chosen { };
+	aliases { };
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu@0 {
+			device_type = "cpu";
+			compatible = "snps,archs38";
+			reg = <0>;
+			clocks = <&core_clk>;
+		};
+	};
+
+	/* TIMER0 with interrupt for clockevent */
+	timer0 {
+		compatible = "snps,arc-timer";
+		interrupts = <16>;
+		interrupt-parent = <&core_intc>;
+		clocks = <&core_clk>;
+	};
+
+	/* 64-bit Local RTC: preferred clocksource for UP */
+	rtc {
+		compatible = "snps,archs-timer-rtc";
+		clocks = <&core_clk>;
+	};
+
+	/* TIMER1 for free running clocksource: Fallback if rtc not found */
+	timer1 {
+		compatible = "snps,arc-timer";
+		clocks = <&core_clk>;
+	};
+
+	memory {
+		device_type = "memory";
+		reg = <0x80000000 0x10000000>;	/* 256M */
+	};
+};
diff --git a/arch/arc/boot/dts/skeleton_hs_idu.dtsi b/arch/arc/boot/dts/skeleton_hs_idu.dtsi
new file mode 100644
index 000000000..75f5c9ecb
--- /dev/null
+++ b/arch/arc/boot/dts/skeleton_hs_idu.dtsi
@@ -0,0 +1,61 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2016 Synopsys, Inc. (www.synopsys.com)
+ */
+
+/ {
+	compatible = "snps,arc";
+	#address-cells = <1>;
+	#size-cells = <1>;
+	chosen { };
+	aliases { };
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu@0 {
+			device_type = "cpu";
+			compatible = "snps,archs38";
+			reg = <0>;
+			clocks = <&core_clk>;
+		};
+		cpu@1 {
+			device_type = "cpu";
+			compatible = "snps,archs38";
+			reg = <1>;
+			clocks = <&core_clk>;
+		};
+		cpu@2 {
+			device_type = "cpu";
+			compatible = "snps,archs38";
+			reg = <2>;
+			clocks = <&core_clk>;
+		};
+		cpu@3 {
+			device_type = "cpu";
+			compatible = "snps,archs38";
+			reg = <3>;
+			clocks = <&core_clk>;
+		};
+	};
+
+	/* TIMER0 with interrupt for clockevent */
+	timer0 {
+		compatible = "snps,arc-timer";
+		interrupts = <16>;
+		interrupt-parent = <&core_intc>;
+		clocks = <&core_clk>;
+	};
+
+	/* 64-bit Global Free Running Counter */
+	gfrc {
+		compatible = "snps,archs-timer-gfrc";
+		clocks = <&core_clk>;
+	};
+
+	memory {
+		device_type = "memory";
+		reg = <0x80000000 0x10000000>;	/* 256M */
+	};
+};
diff --git a/arch/arc/boot/dts/vdk_axc003.dtsi b/arch/arc/boot/dts/vdk_axc003.dtsi
new file mode 100644
index 000000000..c21d0eb07
--- /dev/null
+++ b/arch/arc/boot/dts/vdk_axc003.dtsi
@@ -0,0 +1,65 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2013, 2014 Synopsys, Inc. (www.synopsys.com)
+ */
+
+/*
+ * Device tree for AXC003 CPU card: HS38x UP configuration (VDK version)
+ */
+
+/include/ "skeleton_hs.dtsi"
+
+/ {
+	compatible = "snps,arc";
+	#address-cells = <1>;
+	#size-cells = <1>;
+
+	cpu_card {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		ranges = <0x00000000 0xf0000000 0x10000000>;
+
+		core_clk: core_clk {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <50000000>;
+		};
+
+		core_intc: archs-intc@cpu {
+			compatible = "snps,archs-intc";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+		};
+
+		debug_uart: dw-apb-uart@5000 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x5000 0x100>;
+			clock-frequency = <2403200>;
+			interrupt-parent = <&core_intc>;
+			interrupts = <19>;
+			baud = <115200>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+		};
+
+	};
+
+	mb_intc: interrupt-controller@e0012000 {
+		#interrupt-cells = <1>;
+		compatible = "snps,dw-apb-ictl";
+		reg = < 0xe0012000 0x200 >;
+		interrupt-controller;
+		interrupt-parent = <&core_intc>;
+		interrupts = < 18 >;
+	};
+
+	memory {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0x00000000 0x80000000 0x40000000>;
+		device_type = "memory";
+		reg = <0x80000000 0x20000000>;	/* 512MiB */
+	};
+};
diff --git a/arch/arc/boot/dts/vdk_axc003_idu.dtsi b/arch/arc/boot/dts/vdk_axc003_idu.dtsi
new file mode 100644
index 000000000..4d348853a
--- /dev/null
+++ b/arch/arc/boot/dts/vdk_axc003_idu.dtsi
@@ -0,0 +1,73 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2014, 2015 Synopsys, Inc. (www.synopsys.com)
+ */
+
+/*
+ * Device tree for AXC003 CPU card:
+ * HS38x2 (Dual Core) with IDU intc (VDK version)
+ */
+
+/include/ "skeleton_hs_idu.dtsi"
+
+/ {
+	compatible = "snps,arc";
+	#address-cells = <1>;
+	#size-cells = <1>;
+
+	cpu_card {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		ranges = <0x00000000 0xf0000000 0x10000000>;
+
+		core_clk: core_clk {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <50000000>;
+		};
+
+		core_intc: archs-intc@cpu {
+			compatible = "snps,archs-intc";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+		};
+
+		idu_intc: idu-interrupt-controller {
+			compatible = "snps,archs-idu-intc";
+			interrupt-controller;
+			interrupt-parent = <&core_intc>;
+			#interrupt-cells = <1>;
+		};
+
+		debug_uart: dw-apb-uart@5000 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x5000 0x100>;
+			clock-frequency = <2403200>;
+			interrupt-parent = <&idu_intc>;
+			interrupts = <2>;
+			baud = <115200>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+		};
+
+	};
+
+	mb_intc: interrupt-controller@e0012000 {
+		#interrupt-cells = <1>;
+		compatible = "snps,dw-apb-ictl";
+		reg = < 0xe0012000 0x200 >;
+		interrupt-controller;
+		interrupt-parent = <&idu_intc>;
+		interrupts = <0>;
+	};
+
+	memory {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0x00000000 0x80000000 0x40000000>;
+		device_type = "memory";
+		reg = <0x80000000 0x20000000>;	/* 512MiB */
+	};
+};
diff --git a/arch/arc/boot/dts/vdk_axs10x_mb.dtsi b/arch/arc/boot/dts/vdk_axs10x_mb.dtsi
new file mode 100644
index 000000000..0e0e2d337
--- /dev/null
+++ b/arch/arc/boot/dts/vdk_axs10x_mb.dtsi
@@ -0,0 +1,126 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Support for peripherals on the AXS10x mainboard (VDK version)
+ *
+ * Copyright (C) 2013-15 Synopsys, Inc. (www.synopsys.com)
+ */
+
+/ {
+	axs10x_mb_vdk {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0x00000000 0xe0000000 0x10000000>;
+		interrupt-parent = <&mb_intc>;
+
+		clocks {
+			apbclk: apbclk {
+				compatible = "fixed-clock";
+				clock-frequency = <50000000>;
+				#clock-cells = <0>;
+			};
+
+			mmcclk: mmcclk {
+				compatible = "fixed-clock";
+				clock-frequency = <50000000>;
+				#clock-cells = <0>;
+			};
+
+			pguclk: pguclk {
+				#clock-cells = <0>;
+				compatible = "fixed-clock";
+				clock-frequency = <25175000>;
+			};
+		};
+
+		ethernet@18000 {
+			#interrupt-cells = <1>;
+			compatible = "snps,dwmac";
+			reg = < 0x18000 0x2000 >;
+			interrupts = < 4 >;
+			interrupt-names = "macirq";
+			phy-mode = "rgmii";
+			snps,phy-addr = < 0 >;  // VDK model phy address is 0
+			snps,pbl = < 32 >;
+			clocks = <&apbclk>;
+			clock-names = "stmmaceth";
+		};
+
+		usb@40000 {
+			compatible = "generic-ehci";
+			reg = < 0x40000 0x100 >;
+			interrupts = < 8 >;
+		};
+
+		uart@20000 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x20000 0x100>;
+			clock-frequency = <2403200>;
+			interrupts = <17>;
+			baud = <115200>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+		};
+
+		uart@21000 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x21000 0x100>;
+			clock-frequency = <2403200>;
+			interrupts = <18>;
+			baud = <115200>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+		};
+
+		uart@22000 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x22000 0x100>;
+			clock-frequency = <2403200>;
+			interrupts = <19>;
+			baud = <115200>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+		};
+
+/* PGU output directly sent to virtual LCD screen; hdmi controller not modelled */
+		pgu@17000 {
+			compatible = "snps,arcpgu";
+			reg = <0x17000 0x400>;
+			clocks = <&pguclk>;
+			clock-names = "pxlclk";
+		};
+
+/* VDK has additional ps2 keyboard/mouse interface integrated in LCD screen model */
+		ps2: ps2@e0017400 {
+			compatible = "snps,arc_ps2";
+			reg = <0x17400 0x14>;
+			interrupts = <5>;
+			interrupt-names = "arc_ps2_irq";
+		};
+
+		mmc@15000 {
+			compatible = "snps,dw-mshc";
+			reg = <0x15000 0x400>;
+			fifo-depth = <1024>;
+			card-detect-delay = <200>;
+			clocks = <&apbclk>, <&mmcclk>;
+			clock-names = "biu", "ciu";
+			interrupts = <7>;
+			bus-width = <4>;
+		};
+	};
+
+	/*
+	 * Embedded Vision subsystem UIO mappings; only relevant for EV VDK
+	 *
+	 * This node is intentionally put outside of MB above because
+	 * it maps areas outside of MB's 0xez-0xfz.
+	 */
+	uio_ev: uio@d0000000 {
+		compatible = "generic-uio";
+		reg = <0xd0000000 0x2000 0xd1000000 0x2000 0x90000000 0x10000000 0xc0000000 0x10000000>;
+		reg-names = "ev_gsa", "ev_ctrl", "ev_shared_mem", "ev_code_mem";
+		interrupt-parent = <&mb_intc>;
+		interrupts = <23>;
+	};
+};
diff --git a/arch/arc/boot/dts/vdk_hs38.dts b/arch/arc/boot/dts/vdk_hs38.dts
new file mode 100644
index 000000000..cddea7eac
--- /dev/null
+++ b/arch/arc/boot/dts/vdk_hs38.dts
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2013 Synopsys, Inc. (www.synopsys.com)
+ *
+ * ARC HS38 Virtual Development Kit (VDK)
+ */
+/dts-v1/;
+
+/include/ "vdk_axc003.dtsi"
+/include/ "vdk_axs10x_mb.dtsi"
+
+/ {
+	model = "snps,vdk_archs";
+	compatible = "snps,axs103";
+
+	chosen {
+		bootargs = "earlycon=uart8250,mmio32,0xe0022000,115200n8 console=tty0 console=ttyS3,115200n8 consoleblank=0";
+	};
+};
diff --git a/arch/arc/boot/dts/vdk_hs38_smp.dts b/arch/arc/boot/dts/vdk_hs38_smp.dts
new file mode 100644
index 000000000..f57d1922e
--- /dev/null
+++ b/arch/arc/boot/dts/vdk_hs38_smp.dts
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2013 Synopsys, Inc. (www.synopsys.com)
+ *
+ * ARC HS38 Virtual Development Kit, SMP version (VDK)
+ */
+/dts-v1/;
+
+/include/ "vdk_axc003_idu.dtsi"
+/include/ "vdk_axs10x_mb.dtsi"
+
+/ {
+	model = "snps,vdk_archs-smp";
+	compatible = "snps,axs103";
+
+	chosen {
+		bootargs = "earlycon=uart8250,mmio32,0xe0022000,115200n8 console=tty0 console=ttyS3,115200n8 consoleblank=0 video=640x480-24";
+	};
+};
diff --git a/arch/arc/configs/axs101_defconfig b/arch/arc/configs/axs101_defconfig
new file mode 100644
index 000000000..870e5291b
--- /dev/null
+++ b/arch/arc/configs/axs101_defconfig
@@ -0,0 +1,104 @@
+CONFIG_SYSVIPC=y
+CONFIG_POSIX_MQUEUE=y
+# CONFIG_CROSS_MEMORY_ATTACH is not set
+CONFIG_NO_HZ_IDLE=y
+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_EXPERT=y
+CONFIG_PERF_EVENTS=y
+# CONFIG_VM_EVENT_COUNTERS is not set
+# CONFIG_SLUB_DEBUG is not set
+# CONFIG_COMPAT_BRK is not set
+CONFIG_ISA_ARCOMPACT=y
+CONFIG_MODULES=y
+CONFIG_MODULE_FORCE_LOAD=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_MODULE_FORCE_UNLOAD=y
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_ARC_PLAT_AXS10X=y
+CONFIG_AXS101=y
+CONFIG_ARC_CACHE_LINE_SHIFT=5
+CONFIG_BUILTIN_DTB_NAME="axs101"
+CONFIG_PREEMPT=y
+# CONFIG_COMPACTION is not set
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_NET_KEY=y
+CONFIG_INET=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+CONFIG_IP_PNP_RARP=y
+# CONFIG_IPV6 is not set
+CONFIG_DEVTMPFS=y
+# CONFIG_STANDALONE is not set
+# CONFIG_PREVENT_FIRMWARE_BUILD is not set
+CONFIG_SCSI=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_NETDEVICES=y
+# CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_VENDOR_INTEL is not set
+# CONFIG_NET_VENDOR_MARVELL is not set
+# CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_NATSEMI is not set
+# CONFIG_NET_VENDOR_SEEQ is not set
+CONFIG_STMMAC_ETH=y
+# CONFIG_NET_VENDOR_VIA is not set
+# CONFIG_NET_VENDOR_WIZNET is not set
+CONFIG_NATIONAL_PHY=y
+# CONFIG_USB_NET_DRIVERS is not set
+CONFIG_INPUT_EVDEV=y
+CONFIG_MOUSE_PS2_TOUCHKIT=y
+CONFIG_MOUSE_SERIAL=y
+CONFIG_MOUSE_SYNAPTICS_USB=y
+# CONFIG_LEGACY_PTYS is not set
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_DW=y
+CONFIG_SERIAL_OF_PLATFORM=y
+# CONFIG_HW_RANDOM is not set
+CONFIG_I2C=y
+CONFIG_I2C_CHARDEV=y
+CONFIG_I2C_DESIGNWARE_CORE=y
+# CONFIG_HWMON is not set
+CONFIG_DRM=m
+CONFIG_DRM_I2C_ADV7511=m
+CONFIG_DRM_ARCPGU=m
+CONFIG_FB=y
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_LOGO=y
+# CONFIG_LOGO_LINUX_MONO is not set
+# CONFIG_LOGO_LINUX_VGA16 is not set
+# CONFIG_LOGO_LINUX_CLUT224 is not set
+CONFIG_USB_EHCI_HCD=y
+CONFIG_USB_EHCI_HCD_PLATFORM=y
+CONFIG_USB_OHCI_HCD=y
+CONFIG_USB_OHCI_HCD_PLATFORM=y
+CONFIG_USB_STORAGE=y
+CONFIG_MMC=y
+CONFIG_MMC_SDHCI=y
+CONFIG_MMC_SDHCI_PLTFM=y
+CONFIG_MMC_DW=y
+# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_EXT4_FS=y
+CONFIG_MSDOS_FS=y
+CONFIG_VFAT_FS=y
+CONFIG_NTFS_FS=y
+CONFIG_TMPFS=y
+CONFIG_NFS_FS=y
+CONFIG_NFS_V3_ACL=y
+CONFIG_NLS_CODEPAGE_437=y
+CONFIG_NLS_ISO8859_1=y
+CONFIG_STRIP_ASM_SYMS=y
+CONFIG_SOFTLOCKUP_DETECTOR=y
+CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10
+# CONFIG_SCHED_DEBUG is not set
+# CONFIG_DEBUG_PREEMPT is not set
+# CONFIG_FTRACE is not set
diff --git a/arch/arc/configs/axs103_defconfig b/arch/arc/configs/axs103_defconfig
new file mode 100644
index 000000000..d45e4d335
--- /dev/null
+++ b/arch/arc/configs/axs103_defconfig
@@ -0,0 +1,102 @@
+CONFIG_SYSVIPC=y
+CONFIG_POSIX_MQUEUE=y
+# CONFIG_CROSS_MEMORY_ATTACH is not set
+CONFIG_NO_HZ_IDLE=y
+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_EXPERT=y
+CONFIG_PERF_EVENTS=y
+# CONFIG_VM_EVENT_COUNTERS is not set
+# CONFIG_SLUB_DEBUG is not set
+# CONFIG_COMPAT_BRK is not set
+CONFIG_MODULES=y
+CONFIG_MODULE_FORCE_LOAD=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_MODULE_FORCE_UNLOAD=y
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_ARC_PLAT_AXS10X=y
+CONFIG_AXS103=y
+CONFIG_ISA_ARCV2=y
+CONFIG_BUILTIN_DTB_NAME="axs103"
+CONFIG_PREEMPT=y
+# CONFIG_COMPACTION is not set
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_NET_KEY=y
+CONFIG_INET=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+CONFIG_IP_PNP_RARP=y
+# CONFIG_IPV6 is not set
+CONFIG_DEVTMPFS=y
+# CONFIG_STANDALONE is not set
+# CONFIG_PREVENT_FIRMWARE_BUILD is not set
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_SCSI=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_NETDEVICES=y
+# CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_VENDOR_INTEL is not set
+# CONFIG_NET_VENDOR_MARVELL is not set
+# CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_NATSEMI is not set
+# CONFIG_NET_VENDOR_SEEQ is not set
+CONFIG_STMMAC_ETH=y
+# CONFIG_NET_VENDOR_VIA is not set
+# CONFIG_NET_VENDOR_WIZNET is not set
+CONFIG_NATIONAL_PHY=y
+# CONFIG_USB_NET_DRIVERS is not set
+CONFIG_INPUT_EVDEV=y
+CONFIG_MOUSE_PS2_TOUCHKIT=y
+CONFIG_MOUSE_SERIAL=y
+CONFIG_MOUSE_SYNAPTICS_USB=y
+# CONFIG_LEGACY_PTYS is not set
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_DW=y
+CONFIG_SERIAL_OF_PLATFORM=y
+# CONFIG_HW_RANDOM is not set
+CONFIG_I2C=y
+CONFIG_I2C_CHARDEV=y
+CONFIG_I2C_DESIGNWARE_CORE=y
+# CONFIG_HWMON is not set
+CONFIG_FB=y
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y
+CONFIG_LOGO=y
+# CONFIG_LOGO_LINUX_MONO is not set
+# CONFIG_LOGO_LINUX_VGA16 is not set
+# CONFIG_LOGO_LINUX_CLUT224 is not set
+CONFIG_USB_EHCI_HCD=y
+CONFIG_USB_EHCI_HCD_PLATFORM=y
+CONFIG_USB_OHCI_HCD=y
+CONFIG_USB_OHCI_HCD_PLATFORM=y
+CONFIG_USB_STORAGE=y
+CONFIG_MMC=y
+CONFIG_MMC_SDHCI=y
+CONFIG_MMC_SDHCI_PLTFM=y
+CONFIG_MMC_DW=y
+# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_EXT4_FS=y
+CONFIG_MSDOS_FS=y
+CONFIG_VFAT_FS=y
+CONFIG_NTFS_FS=y
+CONFIG_TMPFS=y
+CONFIG_NFS_FS=y
+CONFIG_NFS_V3_ACL=y
+CONFIG_NLS_CODEPAGE_437=y
+CONFIG_NLS_ISO8859_1=y
+CONFIG_STRIP_ASM_SYMS=y
+CONFIG_SOFTLOCKUP_DETECTOR=y
+CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10
+# CONFIG_SCHED_DEBUG is not set
+# CONFIG_DEBUG_PREEMPT is not set
+# CONFIG_FTRACE is not set
diff --git a/arch/arc/configs/axs103_smp_defconfig b/arch/arc/configs/axs103_smp_defconfig
new file mode 100644
index 000000000..f986c0205
--- /dev/null
+++ b/arch/arc/configs/axs103_smp_defconfig
@@ -0,0 +1,104 @@
+CONFIG_SYSVIPC=y
+CONFIG_POSIX_MQUEUE=y
+# CONFIG_CROSS_MEMORY_ATTACH is not set
+CONFIG_NO_HZ_IDLE=y
+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_EXPERT=y
+CONFIG_PERF_EVENTS=y
+# CONFIG_VM_EVENT_COUNTERS is not set
+# CONFIG_COMPAT_BRK is not set
+CONFIG_MODULES=y
+CONFIG_MODULE_FORCE_LOAD=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_MODULE_FORCE_UNLOAD=y
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_ARC_PLAT_AXS10X=y
+CONFIG_AXS103=y
+CONFIG_ISA_ARCV2=y
+CONFIG_SMP=y
+CONFIG_BUILTIN_DTB_NAME="axs103_idu"
+CONFIG_PREEMPT=y
+# CONFIG_COMPACTION is not set
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_NET_KEY=y
+CONFIG_INET=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+CONFIG_IP_PNP_RARP=y
+# CONFIG_IPV6 is not set
+CONFIG_DEVTMPFS=y
+# CONFIG_STANDALONE is not set
+# CONFIG_PREVENT_FIRMWARE_BUILD is not set
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_SCSI=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_NETDEVICES=y
+# CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_VENDOR_INTEL is not set
+# CONFIG_NET_VENDOR_MARVELL is not set
+# CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_NATSEMI is not set
+# CONFIG_NET_VENDOR_SEEQ is not set
+CONFIG_STMMAC_ETH=y
+# CONFIG_NET_VENDOR_VIA is not set
+# CONFIG_NET_VENDOR_WIZNET is not set
+CONFIG_NATIONAL_PHY=y
+# CONFIG_USB_NET_DRIVERS is not set
+CONFIG_INPUT_EVDEV=y
+CONFIG_MOUSE_PS2_TOUCHKIT=y
+CONFIG_MOUSE_SERIAL=y
+CONFIG_MOUSE_SYNAPTICS_USB=y
+# CONFIG_LEGACY_PTYS is not set
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_DW=y
+CONFIG_SERIAL_OF_PLATFORM=y
+# CONFIG_HW_RANDOM is not set
+CONFIG_I2C=y
+CONFIG_I2C_CHARDEV=y
+CONFIG_I2C_DESIGNWARE_CORE=y
+# CONFIG_HWMON is not set
+CONFIG_DRM=m
+CONFIG_DRM_I2C_ADV7511=m
+CONFIG_DRM_ARCPGU=m
+CONFIG_FB=y
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_LOGO=y
+# CONFIG_LOGO_LINUX_MONO is not set
+# CONFIG_LOGO_LINUX_VGA16 is not set
+# CONFIG_LOGO_LINUX_CLUT224 is not set
+CONFIG_USB_EHCI_HCD=y
+CONFIG_USB_EHCI_HCD_PLATFORM=y
+CONFIG_USB_OHCI_HCD=y
+CONFIG_USB_OHCI_HCD_PLATFORM=y
+CONFIG_USB_STORAGE=y
+CONFIG_MMC=y
+CONFIG_MMC_SDHCI=y
+CONFIG_MMC_SDHCI_PLTFM=y
+CONFIG_MMC_DW=y
+# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_EXT4_FS=y
+CONFIG_MSDOS_FS=y
+CONFIG_VFAT_FS=y
+CONFIG_NTFS_FS=y
+CONFIG_TMPFS=y
+CONFIG_NFS_FS=y
+CONFIG_NFS_V3_ACL=y
+CONFIG_NLS_CODEPAGE_437=y
+CONFIG_NLS_ISO8859_1=y
+CONFIG_STRIP_ASM_SYMS=y
+CONFIG_SOFTLOCKUP_DETECTOR=y
+CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10
+# CONFIG_SCHED_DEBUG is not set
+# CONFIG_DEBUG_PREEMPT is not set
+# CONFIG_FTRACE is not set
diff --git a/arch/arc/configs/haps_hs_defconfig b/arch/arc/configs/haps_hs_defconfig
new file mode 100644
index 000000000..3a1577112
--- /dev/null
+++ b/arch/arc/configs/haps_hs_defconfig
@@ -0,0 +1,62 @@
+# CONFIG_SWAP is not set
+CONFIG_SYSVIPC=y
+CONFIG_POSIX_MQUEUE=y
+# CONFIG_CROSS_MEMORY_ATTACH is not set
+CONFIG_NO_HZ_IDLE=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_PREEMPT=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_EXPERT=y
+CONFIG_PERF_EVENTS=y
+# CONFIG_COMPAT_BRK is not set
+CONFIG_BUILTIN_DTB_NAME="haps_hs"
+CONFIG_MODULES=y
+# CONFIG_BLK_DEV_BSG is not set
+# CONFIG_COMPACTION is not set
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_PACKET_DIAG=y
+CONFIG_UNIX=y
+CONFIG_UNIX_DIAG=y
+CONFIG_NET_KEY=y
+CONFIG_INET=y
+# CONFIG_IPV6 is not set
+# CONFIG_WIRELESS is not set
+CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
+# CONFIG_STANDALONE is not set
+# CONFIG_PREVENT_FIRMWARE_BUILD is not set
+CONFIG_VIRTIO_BLK=y
+CONFIG_NETDEVICES=y
+CONFIG_VIRTIO_NET=y
+# CONFIG_ETHERNET is not set
+# CONFIG_WLAN is not set
+CONFIG_INPUT_EVDEV=y
+# CONFIG_INPUT_KEYBOARD is not set
+# CONFIG_INPUT_MOUSE is not set
+# CONFIG_SERIO is not set
+# CONFIG_LEGACY_PTYS is not set
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_NR_UARTS=1
+CONFIG_SERIAL_8250_RUNTIME_UARTS=1
+CONFIG_SERIAL_8250_DW=y
+CONFIG_SERIAL_OF_PLATFORM=y
+# CONFIG_HW_RANDOM is not set
+# CONFIG_HWMON is not set
+# CONFIG_HID is not set
+# CONFIG_USB_SUPPORT is not set
+CONFIG_VIRTIO_MMIO=y
+# 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_DEBUG_MEMORY_INIT=y
+# CONFIG_DEBUG_PREEMPT is not set
diff --git a/arch/arc/configs/haps_hs_smp_defconfig b/arch/arc/configs/haps_hs_smp_defconfig
new file mode 100644
index 000000000..a3cf940b1
--- /dev/null
+++ b/arch/arc/configs/haps_hs_smp_defconfig
@@ -0,0 +1,62 @@
+# CONFIG_SWAP is not set
+CONFIG_SYSVIPC=y
+CONFIG_POSIX_MQUEUE=y
+# CONFIG_CROSS_MEMORY_ATTACH is not set
+CONFIG_NO_HZ_IDLE=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_PREEMPT=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_EXPERT=y
+CONFIG_PERF_EVENTS=y
+# CONFIG_VM_EVENT_COUNTERS is not set
+# CONFIG_COMPAT_BRK is not set
+CONFIG_SMP=y
+CONFIG_BUILTIN_DTB_NAME="haps_hs_idu"
+CONFIG_KPROBES=y
+CONFIG_MODULES=y
+# CONFIG_BLK_DEV_BSG is not set
+# CONFIG_COMPACTION is not set
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_PACKET_DIAG=y
+CONFIG_UNIX=y
+CONFIG_UNIX_DIAG=y
+CONFIG_NET_KEY=y
+CONFIG_INET=y
+# CONFIG_IPV6 is not set
+# CONFIG_WIRELESS is not set
+CONFIG_DEVTMPFS=y
+# CONFIG_STANDALONE is not set
+# CONFIG_PREVENT_FIRMWARE_BUILD is not set
+# CONFIG_BLK_DEV is not set
+CONFIG_NETDEVICES=y
+# CONFIG_ETHERNET is not set
+# CONFIG_WLAN is not set
+CONFIG_INPUT_EVDEV=y
+# CONFIG_INPUT_KEYBOARD is not set
+# CONFIG_INPUT_MOUSE is not set
+# CONFIG_SERIO is not set
+# CONFIG_LEGACY_PTYS is not set
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_NR_UARTS=1
+CONFIG_SERIAL_8250_RUNTIME_UARTS=1
+CONFIG_SERIAL_8250_DW=y
+CONFIG_SERIAL_OF_PLATFORM=y
+# CONFIG_HW_RANDOM is not set
+# CONFIG_HWMON 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_SOFTLOCKUP_DETECTOR=y
+# CONFIG_DEBUG_PREEMPT is not set
diff --git a/arch/arc/configs/hsdk_defconfig b/arch/arc/configs/hsdk_defconfig
new file mode 100644
index 000000000..1b8b2a098
--- /dev/null
+++ b/arch/arc/configs/hsdk_defconfig
@@ -0,0 +1,93 @@
+CONFIG_SYSVIPC=y
+# CONFIG_CROSS_MEMORY_ATTACH is not set
+CONFIG_NO_HZ_IDLE=y
+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_BLK_DEV_RAM=y
+CONFIG_EXPERT=y
+CONFIG_PERF_EVENTS=y
+# CONFIG_VM_EVENT_COUNTERS is not set
+# CONFIG_COMPAT_BRK is not set
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_ARC_SOC_HSDK=y
+CONFIG_ISA_ARCV2=y
+CONFIG_SMP=y
+CONFIG_LINUX_LINK_BASE=0x90000000
+CONFIG_LINUX_RAM_BASE=0x80000000
+CONFIG_BUILTIN_DTB_NAME="hsdk"
+CONFIG_PREEMPT=y
+# CONFIG_COMPACTION is not set
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_INET=y
+CONFIG_DEVTMPFS=y
+# CONFIG_STANDALONE is not set
+# CONFIG_PREVENT_FIRMWARE_BUILD is not set
+CONFIG_MTD=y
+CONFIG_MTD_SPI_NOR=y
+CONFIG_SCSI=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_NETDEVICES=y
+CONFIG_STMMAC_ETH=y
+CONFIG_MICREL_PHY=y
+CONFIG_INPUT_EVDEV=y
+# CONFIG_INPUT_KEYBOARD is not set
+# CONFIG_INPUT_MOUSE is not set
+# CONFIG_SERIO is not set
+# CONFIG_LEGACY_PTYS is not set
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_DW=y
+CONFIG_SERIAL_OF_PLATFORM=y
+# CONFIG_HW_RANDOM is not set
+CONFIG_SPI=y
+CONFIG_SPI_DESIGNWARE=y
+CONFIG_SPI_DW_MMIO=y
+CONFIG_GPIOLIB=y
+CONFIG_GPIO_SYSFS=y
+CONFIG_GPIO_DWAPB=y
+CONFIG_GPIO_SNPS_CREG=y
+# CONFIG_HWMON is not set
+CONFIG_REGULATOR=y
+CONFIG_REGULATOR_FIXED_VOLTAGE=y
+CONFIG_DRM=y
+# CONFIG_DRM_FBDEV_EMULATION is not set
+CONFIG_DRM_UDL=y
+CONFIG_DRM_ETNAVIV=y
+CONFIG_FB=y
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_USB=y
+CONFIG_USB_EHCI_HCD=y
+CONFIG_USB_EHCI_HCD_PLATFORM=y
+CONFIG_USB_OHCI_HCD=y
+CONFIG_USB_OHCI_HCD_PLATFORM=y
+CONFIG_USB_STORAGE=y
+CONFIG_MMC=y
+CONFIG_MMC_SDHCI=y
+CONFIG_MMC_SDHCI_PLTFM=y
+CONFIG_MMC_DW=y
+CONFIG_DMADEVICES=y
+CONFIG_DW_AXI_DMAC=y
+CONFIG_IIO=y
+CONFIG_TI_ADC108S102=y
+CONFIG_EXT4_FS=y
+CONFIG_VFAT_FS=y
+CONFIG_TMPFS=y
+CONFIG_NFS_FS=y
+CONFIG_NFS_V3_ACL=y
+CONFIG_NLS_CODEPAGE_437=y
+CONFIG_NLS_ISO8859_1=y
+CONFIG_STRIP_ASM_SYMS=y
+CONFIG_SOFTLOCKUP_DETECTOR=y
+CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10
+# CONFIG_SCHED_DEBUG is not set
+# CONFIG_DEBUG_PREEMPT is not set
+# CONFIG_FTRACE is not set
+CONFIG_CRYPTO_ECHAINIV=y
diff --git a/arch/arc/configs/nsim_700_defconfig b/arch/arc/configs/nsim_700_defconfig
new file mode 100644
index 000000000..f8b3235d9
--- /dev/null
+++ b/arch/arc/configs/nsim_700_defconfig
@@ -0,0 +1,59 @@
+# CONFIG_LOCALVERSION_AUTO is not set
+# CONFIG_SWAP is not set
+CONFIG_SYSVIPC=y
+CONFIG_POSIX_MQUEUE=y
+# CONFIG_CROSS_MEMORY_ATTACH is not set
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_PREEMPT=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_KALLSYMS_ALL=y
+CONFIG_EXPERT=y
+CONFIG_PERF_EVENTS=y
+# CONFIG_SLUB_DEBUG is not set
+# CONFIG_COMPAT_BRK is not set
+CONFIG_ISA_ARCOMPACT=y
+CONFIG_BUILTIN_DTB_NAME="nsim_700"
+CONFIG_KPROBES=y
+CONFIG_MODULES=y
+# CONFIG_BLK_DEV_BSG is not set
+# CONFIG_COMPACTION 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_DEVTMPFS=y
+# CONFIG_STANDALONE is not set
+# CONFIG_PREVENT_FIRMWARE_BUILD is not set
+# CONFIG_BLK_DEV is not set
+CONFIG_NETDEVICES=y
+# CONFIG_ETHERNET is not set
+# CONFIG_WLAN 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_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_NR_UARTS=1
+CONFIG_SERIAL_8250_RUNTIME_UARTS=1
+CONFIG_SERIAL_8250_DW=y
+CONFIG_SERIAL_OF_PLATFORM=y
+# CONFIG_HW_RANDOM is not set
+# CONFIG_HWMON 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_DEBUG_PREEMPT is not set
diff --git a/arch/arc/configs/nsimosci_defconfig b/arch/arc/configs/nsimosci_defconfig
new file mode 100644
index 000000000..ee45dc087
--- /dev/null
+++ b/arch/arc/configs/nsimosci_defconfig
@@ -0,0 +1,67 @@
+# CONFIG_LOCALVERSION_AUTO is not set
+# CONFIG_SWAP is not set
+CONFIG_SYSVIPC=y
+# CONFIG_CROSS_MEMORY_ATTACH is not set
+CONFIG_NO_HZ=y
+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_KALLSYMS_ALL=y
+CONFIG_EXPERT=y
+CONFIG_PERF_EVENTS=y
+# CONFIG_SLUB_DEBUG is not set
+# CONFIG_COMPAT_BRK is not set
+CONFIG_ISA_ARCOMPACT=y
+CONFIG_KPROBES=y
+CONFIG_MODULES=y
+# CONFIG_BLK_DEV_BSG is not set
+CONFIG_BUILTIN_DTB_NAME="nsimosci"
+# CONFIG_COMPACTION 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_DEVTMPFS=y
+# CONFIG_STANDALONE is not set
+# CONFIG_PREVENT_FIRMWARE_BUILD is not set
+# CONFIG_BLK_DEV is not set
+CONFIG_NETDEVICES=y
+CONFIG_EZCHIP_NPS_MANAGEMENT_ENET=y
+# CONFIG_INPUT_MOUSEDEV is not set
+CONFIG_INPUT_EVDEV=y
+# CONFIG_MOUSE_PS2_ALPS is not set
+# CONFIG_MOUSE_PS2_LOGIPS2PP is not set
+# CONFIG_MOUSE_PS2_SYNAPTICS is not set
+# CONFIG_MOUSE_PS2_CYPRESS is not set
+# CONFIG_MOUSE_PS2_TRACKPOINT is not set
+CONFIG_MOUSE_PS2_TOUCHKIT=y
+# CONFIG_SERIO_SERPORT is not set
+CONFIG_SERIO_ARC_PS2=y
+# CONFIG_LEGACY_PTYS is not set
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_NR_UARTS=1
+CONFIG_SERIAL_8250_RUNTIME_UARTS=1
+CONFIG_SERIAL_OF_PLATFORM=y
+# CONFIG_HW_RANDOM is not set
+# CONFIG_HWMON is not set
+CONFIG_DRM=y
+CONFIG_DRM_ARCPGU=y
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_LOGO=y
+# 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_NFS_V3_ACL=y
diff --git a/arch/arc/configs/nsimosci_hs_defconfig b/arch/arc/configs/nsimosci_hs_defconfig
new file mode 100644
index 000000000..e0a309970
--- /dev/null
+++ b/arch/arc/configs/nsimosci_hs_defconfig
@@ -0,0 +1,65 @@
+# CONFIG_LOCALVERSION_AUTO is not set
+# CONFIG_SWAP is not set
+CONFIG_SYSVIPC=y
+# CONFIG_CROSS_MEMORY_ATTACH is not set
+CONFIG_NO_HZ=y
+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_KALLSYMS_ALL=y
+CONFIG_EXPERT=y
+CONFIG_PERF_EVENTS=y
+# CONFIG_SLUB_DEBUG is not set
+# CONFIG_COMPAT_BRK is not set
+CONFIG_KPROBES=y
+CONFIG_MODULES=y
+# CONFIG_BLK_DEV_BSG is not set
+CONFIG_ISA_ARCV2=y
+CONFIG_BUILTIN_DTB_NAME="nsimosci_hs"
+# CONFIG_COMPACTION 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_DEVTMPFS=y
+# CONFIG_STANDALONE is not set
+# CONFIG_PREVENT_FIRMWARE_BUILD is not set
+# CONFIG_BLK_DEV is not set
+CONFIG_NETDEVICES=y
+CONFIG_EZCHIP_NPS_MANAGEMENT_ENET=y
+CONFIG_INPUT_EVDEV=y
+# CONFIG_MOUSE_PS2_ALPS is not set
+# CONFIG_MOUSE_PS2_LOGIPS2PP is not set
+# CONFIG_MOUSE_PS2_SYNAPTICS is not set
+# CONFIG_MOUSE_PS2_TRACKPOINT is not set
+CONFIG_MOUSE_PS2_TOUCHKIT=y
+# CONFIG_SERIO_SERPORT is not set
+CONFIG_SERIO_ARC_PS2=y
+# CONFIG_LEGACY_PTYS is not set
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_NR_UARTS=1
+CONFIG_SERIAL_8250_RUNTIME_UARTS=1
+CONFIG_SERIAL_OF_PLATFORM=y
+# CONFIG_HW_RANDOM is not set
+# CONFIG_HWMON is not set
+CONFIG_DRM=y
+CONFIG_DRM_ARCPGU=y
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_LOGO=y
+# 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_NFS_V3_ACL=y
diff --git a/arch/arc/configs/nsimosci_hs_smp_defconfig b/arch/arc/configs/nsimosci_hs_smp_defconfig
new file mode 100644
index 000000000..88325b8b4
--- /dev/null
+++ b/arch/arc/configs/nsimosci_hs_smp_defconfig
@@ -0,0 +1,74 @@
+# CONFIG_SWAP is not set
+CONFIG_SYSVIPC=y
+# CONFIG_CROSS_MEMORY_ATTACH is not set
+CONFIG_NO_HZ=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+# CONFIG_UTS_NS is not set
+# CONFIG_PID_NS is not set
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_PERF_EVENTS=y
+# CONFIG_COMPAT_BRK is not set
+CONFIG_KPROBES=y
+CONFIG_MODULES=y
+# CONFIG_BLK_DEV_BSG is not set
+CONFIG_ISA_ARCV2=y
+CONFIG_SMP=y
+# CONFIG_ARC_TIMERS_64BIT is not set
+CONFIG_BUILTIN_DTB_NAME="nsimosci_hs_idu"
+CONFIG_PREEMPT=y
+# CONFIG_COMPACTION is not set
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_PACKET_DIAG=y
+CONFIG_UNIX=y
+CONFIG_UNIX_DIAG=y
+CONFIG_NET_KEY=y
+CONFIG_INET=y
+# CONFIG_IPV6 is not set
+# CONFIG_WIRELESS is not set
+CONFIG_DEVTMPFS=y
+# CONFIG_STANDALONE is not set
+# CONFIG_PREVENT_FIRMWARE_BUILD is not set
+# CONFIG_BLK_DEV is not set
+CONFIG_NETDEVICES=y
+# CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_VENDOR_BROADCOM is not set
+CONFIG_EZCHIP_NPS_MANAGEMENT_ENET=y
+# CONFIG_NET_VENDOR_INTEL is not set
+# CONFIG_NET_VENDOR_MARVELL is not set
+# CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_NATSEMI is not set
+# CONFIG_NET_VENDOR_SEEQ is not set
+# CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_VIA is not set
+# CONFIG_NET_VENDOR_WIZNET is not set
+# CONFIG_WLAN is not set
+CONFIG_INPUT_EVDEV=y
+CONFIG_MOUSE_PS2_TOUCHKIT=y
+# CONFIG_SERIO_SERPORT is not set
+CONFIG_SERIO_ARC_PS2=y
+# CONFIG_LEGACY_PTYS is not set
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_NR_UARTS=1
+CONFIG_SERIAL_8250_RUNTIME_UARTS=1
+CONFIG_SERIAL_8250_DW=y
+CONFIG_SERIAL_OF_PLATFORM=y
+# CONFIG_HW_RANDOM is not set
+# CONFIG_HWMON is not set
+CONFIG_DRM=y
+CONFIG_DRM_ARCPGU=y
+CONFIG_LOGO=y
+# 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_NFS_V3_ACL=y
+CONFIG_FTRACE=y
+# CONFIG_NET_VENDOR_CADENCE is not set
diff --git a/arch/arc/configs/tb10x_defconfig b/arch/arc/configs/tb10x_defconfig
new file mode 100644
index 000000000..6e396a9dd
--- /dev/null
+++ b/arch/arc/configs/tb10x_defconfig
@@ -0,0 +1,99 @@
+# CONFIG_LOCALVERSION_AUTO is not set
+CONFIG_DEFAULT_HOSTNAME="tb10x"
+CONFIG_SYSVIPC=y
+CONFIG_POSIX_MQUEUE=y
+# CONFIG_CROSS_MEMORY_ATTACH is not set
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_BSD_PROCESS_ACCT=y
+CONFIG_BSD_PROCESS_ACCT_V3=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_LOG_BUF_SHIFT=16
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_INITRAMFS_SOURCE="../tb10x-rootfs.cpio"
+CONFIG_INITRAMFS_ROOT_UID=2100
+CONFIG_INITRAMFS_ROOT_GID=501
+# CONFIG_RD_GZIP is not set
+CONFIG_KALLSYMS_ALL=y
+# CONFIG_AIO is not set
+CONFIG_EXPERT=y
+# CONFIG_COMPAT_BRK is not set
+CONFIG_ISA_ARCOMPACT=y
+CONFIG_MODULES=y
+CONFIG_MODULE_FORCE_LOAD=y
+CONFIG_MODULE_UNLOAD=y
+# CONFIG_BLOCK is not set
+CONFIG_ARC_PLAT_TB10X=y
+CONFIG_ARC_CACHE_LINE_SHIFT=5
+CONFIG_HZ=250
+CONFIG_BUILTIN_DTB_NAME="abilis_tb100_dvk"
+CONFIG_PREEMPT_VOLUNTARY=y
+# CONFIG_COMPACTION is not set
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
+# CONFIG_INET_DIAG is not set
+# CONFIG_IPV6 is not set
+# CONFIG_WIRELESS is not set
+CONFIG_DEVTMPFS=y
+CONFIG_NETDEVICES=y
+# CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_VENDOR_INTEL is not set
+# CONFIG_NET_VENDOR_MARVELL is not set
+# CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_NATSEMI is not set
+# CONFIG_NET_VENDOR_SEEQ is not set
+CONFIG_STMMAC_ETH=y
+# CONFIG_NET_VENDOR_WIZNET is not set
+# CONFIG_WLAN is not set
+# CONFIG_INPUT is not set
+# CONFIG_SERIO is not set
+# CONFIG_VT is not set
+# CONFIG_LEGACY_PTYS is not set
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_NR_UARTS=1
+CONFIG_SERIAL_8250_RUNTIME_UARTS=1
+CONFIG_SERIAL_8250_DW=y
+# CONFIG_HW_RANDOM is not set
+CONFIG_I2C=y
+# CONFIG_I2C_COMPAT is not set
+CONFIG_I2C_DESIGNWARE_CORE=y
+CONFIG_GPIO_SYSFS=y
+# CONFIG_HWMON is not set
+# CONFIG_USB_SUPPORT is not set
+CONFIG_NEW_LEDS=y
+CONFIG_LEDS_CLASS=y
+CONFIG_LEDS_GPIO=y
+CONFIG_LEDS_TRIGGERS=y
+CONFIG_LEDS_TRIGGER_TIMER=y
+CONFIG_LEDS_TRIGGER_ONESHOT=y
+CONFIG_LEDS_TRIGGER_HEARTBEAT=y
+CONFIG_LEDS_TRIGGER_CPU=y
+CONFIG_LEDS_TRIGGER_GPIO=y
+CONFIG_LEDS_TRIGGER_DEFAULT_ON=y
+CONFIG_LEDS_TRIGGER_TRANSIENT=y
+CONFIG_DMADEVICES=y
+CONFIG_DW_DMAC=y
+CONFIG_ASYNC_TX_DMA=y
+# CONFIG_IOMMU_SUPPORT is not set
+# CONFIG_DNOTIFY is not set
+CONFIG_PROC_KCORE=y
+CONFIG_TMPFS=y
+CONFIG_CONFIGFS_FS=y
+# CONFIG_MISC_FILESYSTEMS is not set
+# CONFIG_NETWORK_FILESYSTEMS is not set
+CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
+CONFIG_STRIP_ASM_SYMS=y
+CONFIG_DEBUG_FS=y
+CONFIG_HEADERS_INSTALL=y
+CONFIG_DEBUG_SECTION_MISMATCH=y
+CONFIG_MAGIC_SYSRQ=y
+CONFIG_DEBUG_MEMORY_INIT=y
+CONFIG_DEBUG_STACKOVERFLOW=y
+CONFIG_DETECT_HUNG_TASK=y
+CONFIG_SCHEDSTATS=y
+# CONFIG_CRYPTO_HW is not set
+# CONFIG_NET_VENDOR_CADENCE is not set
diff --git a/arch/arc/configs/vdk_hs38_defconfig b/arch/arc/configs/vdk_hs38_defconfig
new file mode 100644
index 000000000..b7120523e
--- /dev/null
+++ b/arch/arc/configs/vdk_hs38_defconfig
@@ -0,0 +1,94 @@
+# CONFIG_LOCALVERSION_AUTO is not set
+# CONFIG_CROSS_MEMORY_ATTACH is not set
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_EXPERT=y
+CONFIG_PERF_EVENTS=y
+# CONFIG_VM_EVENT_COUNTERS is not set
+# CONFIG_SLUB_DEBUG is not set
+# CONFIG_COMPAT_BRK is not set
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_ARC_PLAT_AXS10X=y
+CONFIG_AXS103=y
+CONFIG_ISA_ARCV2=y
+CONFIG_BUILTIN_DTB_NAME="vdk_hs38"
+CONFIG_PREEMPT=y
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_NET_KEY=y
+CONFIG_INET=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+CONFIG_IP_PNP_RARP=y
+# CONFIG_IPV6 is not set
+CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
+# CONFIG_STANDALONE is not set
+# CONFIG_PREVENT_FIRMWARE_BUILD is not set
+CONFIG_MTD=y
+CONFIG_MTD_CMDLINE_PARTS=y
+CONFIG_MTD_BLOCK=y
+CONFIG_MTD_SLRAM=y
+CONFIG_BLK_DEV_RAM=y
+CONFIG_SCSI=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_NETDEVICES=y
+# CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_VENDOR_INTEL is not set
+# CONFIG_NET_VENDOR_MARVELL is not set
+# CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_NATSEMI is not set
+# CONFIG_NET_VENDOR_SEEQ is not set
+CONFIG_STMMAC_ETH=y
+# CONFIG_NET_VENDOR_VIA is not set
+# CONFIG_NET_VENDOR_WIZNET is not set
+CONFIG_NATIONAL_PHY=y
+CONFIG_MOUSE_PS2_TOUCHKIT=y
+CONFIG_SERIO_ARC_PS2=y
+# CONFIG_LEGACY_PTYS is not set
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_DW=y
+CONFIG_SERIAL_OF_PLATFORM=y
+# CONFIG_HW_RANDOM is not set
+# CONFIG_HWMON is not set
+CONFIG_FB=y
+# CONFIG_VGA_CONSOLE is not set
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y
+CONFIG_LOGO=y
+# CONFIG_LOGO_LINUX_MONO is not set
+# CONFIG_LOGO_LINUX_VGA16 is not set
+# CONFIG_LOGO_LINUX_CLUT224 is not set
+CONFIG_USB=y
+CONFIG_USB_EHCI_HCD=y
+# CONFIG_USB_EHCI_TT_NEWSCHED is not set
+CONFIG_USB_EHCI_HCD_PLATFORM=y
+CONFIG_USB_OHCI_HCD=y
+CONFIG_USB_OHCI_HCD_PLATFORM=y
+CONFIG_USB_STORAGE=y
+CONFIG_USB_SERIAL=y
+# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS=y
+CONFIG_MSDOS_FS=y
+CONFIG_VFAT_FS=y
+CONFIG_NTFS_FS=y
+CONFIG_TMPFS=y
+CONFIG_JFFS2_FS=y
+CONFIG_NFS_FS=y
+CONFIG_NFS_V3_ACL=y
+CONFIG_NLS_CODEPAGE_437=y
+CONFIG_NLS_ISO8859_1=y
+CONFIG_STRIP_ASM_SYMS=y
+CONFIG_DEBUG_SHIRQ=y
+CONFIG_SOFTLOCKUP_DETECTOR=y
+CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10
+# CONFIG_SCHED_DEBUG is not set
+# CONFIG_DEBUG_PREEMPT is not set
+# CONFIG_FTRACE is not set
diff --git a/arch/arc/configs/vdk_hs38_smp_defconfig b/arch/arc/configs/vdk_hs38_smp_defconfig
new file mode 100644
index 000000000..4077abd59
--- /dev/null
+++ b/arch/arc/configs/vdk_hs38_smp_defconfig
@@ -0,0 +1,100 @@
+# CONFIG_LOCALVERSION_AUTO is not set
+# CONFIG_CROSS_MEMORY_ATTACH is not set
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_EXPERT=y
+CONFIG_PERF_EVENTS=y
+# CONFIG_VM_EVENT_COUNTERS is not set
+# CONFIG_SLUB_DEBUG is not set
+# CONFIG_COMPAT_BRK is not set
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_ARC_PLAT_AXS10X=y
+CONFIG_AXS103=y
+CONFIG_ISA_ARCV2=y
+CONFIG_SMP=y
+# CONFIG_ARC_TIMERS_64BIT is not set
+CONFIG_BUILTIN_DTB_NAME="vdk_hs38_smp"
+CONFIG_PREEMPT=y
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_NET_KEY=y
+CONFIG_INET=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+CONFIG_IP_PNP_RARP=y
+# CONFIG_IPV6 is not set
+CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
+# CONFIG_STANDALONE is not set
+# CONFIG_PREVENT_FIRMWARE_BUILD is not set
+CONFIG_MTD=y
+CONFIG_MTD_CMDLINE_PARTS=y
+CONFIG_MTD_BLOCK=y
+CONFIG_MTD_SLRAM=y
+CONFIG_BLK_DEV_RAM=y
+CONFIG_SCSI=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_NETDEVICES=y
+# CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_VENDOR_INTEL is not set
+# CONFIG_NET_VENDOR_MARVELL is not set
+# CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_NATSEMI is not set
+# CONFIG_NET_VENDOR_SEEQ is not set
+CONFIG_STMMAC_ETH=y
+# CONFIG_NET_VENDOR_VIA is not set
+# CONFIG_NET_VENDOR_WIZNET is not set
+CONFIG_NATIONAL_PHY=y
+CONFIG_MOUSE_PS2_TOUCHKIT=y
+CONFIG_SERIO_ARC_PS2=y
+# CONFIG_LEGACY_PTYS is not set
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_DW=y
+CONFIG_SERIAL_OF_PLATFORM=y
+# CONFIG_HW_RANDOM is not set
+# CONFIG_HWMON is not set
+CONFIG_DRM=y
+CONFIG_DRM_ARCPGU=y
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_LOGO=y
+# CONFIG_LOGO_LINUX_MONO is not set
+# CONFIG_LOGO_LINUX_VGA16 is not set
+# CONFIG_LOGO_LINUX_CLUT224 is not set
+CONFIG_USB=y
+CONFIG_USB_EHCI_HCD=y
+# CONFIG_USB_EHCI_TT_NEWSCHED is not set
+CONFIG_USB_EHCI_HCD_PLATFORM=y
+CONFIG_USB_OHCI_HCD=y
+CONFIG_USB_OHCI_HCD_PLATFORM=y
+CONFIG_USB_STORAGE=y
+CONFIG_USB_SERIAL=y
+CONFIG_MMC=y
+CONFIG_MMC_SDHCI=y
+CONFIG_MMC_SDHCI_PLTFM=y
+CONFIG_MMC_DW=y
+CONFIG_UIO=y
+CONFIG_UIO_PDRV_GENIRQ=y
+# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_EXT4_FS=y
+CONFIG_MSDOS_FS=y
+CONFIG_VFAT_FS=y
+CONFIG_NTFS_FS=y
+CONFIG_TMPFS=y
+CONFIG_JFFS2_FS=y
+CONFIG_NFS_FS=y
+CONFIG_NFS_V3_ACL=y
+CONFIG_NLS_CODEPAGE_437=y
+CONFIG_NLS_ISO8859_1=y
+CONFIG_STRIP_ASM_SYMS=y
+CONFIG_DEBUG_SHIRQ=y
+CONFIG_SOFTLOCKUP_DETECTOR=y
+CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10
+# CONFIG_SCHED_DEBUG is not set
+# CONFIG_DEBUG_PREEMPT is not set
+# CONFIG_FTRACE is not set
diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild
new file mode 100644
index 000000000..483caacc6
--- /dev/null
+++ b/arch/arc/include/asm/Kbuild
@@ -0,0 +1,10 @@
+# SPDX-License-Identifier: GPL-2.0
+syscall-y += syscall_table_32.h
+
+generic-y += extable.h
+generic-y += kvm_para.h
+generic-y += mcs_spinlock.h
+generic-y += parport.h
+generic-y += ring_buffer.h
+generic-y += user.h
+generic-y += text-patching.h
diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h
new file mode 100644
index 000000000..d84908a17
--- /dev/null
+++ b/arch/arc/include/asm/arcregs.h
@@ -0,0 +1,367 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#ifndef _ASM_ARC_ARCREGS_H
+#define _ASM_ARC_ARCREGS_H
+
+/* Build Configuration Registers */
+#define ARC_REG_AUX_DCCM	0x18	/* DCCM Base Addr ARCv2 */
+#define ARC_REG_ERP_CTRL	0x3F	/* ARCv2 Error protection control */
+#define ARC_REG_DCCM_BASE_BUILD	0x61	/* DCCM Base Addr ARCompact */
+#define ARC_REG_CRC_BCR		0x62
+#define ARC_REG_VECBASE_BCR	0x68
+#define ARC_REG_PERIBASE_BCR	0x69
+#define ARC_REG_FP_BCR		0x6B	/* ARCompact: Single-Precision FPU */
+#define ARC_REG_DPFP_BCR	0x6C	/* ARCompact: Dbl Precision FPU */
+#define ARC_REG_ERP_BUILD	0xc7	/* ARCv2 Error protection Build: ECC/Parity */
+#define ARC_REG_FP_V2_BCR	0xc8	/* ARCv2 FPU */
+#define ARC_REG_SLC_BCR		0xce
+#define ARC_REG_DCCM_BUILD	0x74	/* DCCM size (common) */
+#define ARC_REG_AP_BCR		0x76
+#define ARC_REG_ICCM_BUILD	0x78	/* ICCM size (common) */
+#define ARC_REG_XY_MEM_BCR	0x79
+#define ARC_REG_MAC_BCR		0x7a
+#define ARC_REG_MPY_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
+#define ARC_REG_BPU_BCR		0xc0
+#define ARC_REG_ISA_CFG_BCR	0xc1
+#define ARC_REG_LPB_BUILD	0xE9	/* ARCv2 Loop Buffer Build */
+#define ARC_REG_RTT_BCR		0xF2
+#define ARC_REG_IRQ_BCR		0xF3
+#define ARC_REG_MICRO_ARCH_BCR	0xF9	/* ARCv2 Product revision */
+#define ARC_REG_SMART_BCR	0xFF
+#define ARC_REG_CLUSTER_BCR	0xcf
+#define ARC_REG_AUX_ICCM	0x208	/* ICCM Base Addr (ARCv2) */
+#define ARC_REG_LPB_CTRL	0x488	/* ARCv2 Loop Buffer control */
+#define ARC_REG_FPU_CTRL	0x300
+#define ARC_REG_FPU_STATUS	0x301
+
+/* Common for ARCompact and ARCv2 status register */
+#define ARC_REG_STATUS32	0x0A
+
+/* status32 Bits Positions */
+#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_Z_BIT            11
+#define STATUS_L_BIT		12	/* Loop inhibit */
+
+/* These masks correspond to the status word(STATUS_32) bits */
+#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_Z_MASK		(1<<STATUS_Z_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)
+ */
+#ifdef CONFIG_ISA_ARCOMPACT
+#define ECR_V_MEM_ERR			0x01
+#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
+#define ECR_V_TRAP			0x25
+#else
+#define ECR_V_MEM_ERR			0x01
+#define ECR_V_INSN_ERR			0x02
+#define ECR_V_MACH_CHK			0x03
+#define ECR_V_ITLB_MISS			0x04
+#define ECR_V_DTLB_MISS			0x05
+#define ECR_V_PROTV			0x06
+#define ECR_V_TRAP			0x09
+#define ECR_V_MISALIGN			0x0d
+#endif
+
+/* DTLB Miss and Protection Violation Cause Codes */
+
+#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
+
+#define ECR_C_BIT_PROTV_MISALIG_DATA	10
+
+/* Machine Check Cause Code Values */
+#define ECR_C_MCHK_DUP_TLB		0x01
+
+/* 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_EXEC_CTRL		8
+#define AUX_INTR_VEC_BASE	0x25
+#define AUX_VOL			0x5e
+
+/*
+ * 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
+
+/*
+ * DSP-related registers
+ * Registers names must correspond to dsp_callee_regs structure fields names
+ * for automatic offset calculation in DSP_AUX_SAVE_RESTORE macros.
+ */
+#define ARC_AUX_DSP_BUILD	0x7A
+#define ARC_AUX_ACC0_LO		0x580
+#define ARC_AUX_ACC0_GLO	0x581
+#define ARC_AUX_ACC0_HI		0x582
+#define ARC_AUX_ACC0_GHI	0x583
+#define ARC_AUX_DSP_BFLY0	0x598
+#define ARC_AUX_DSP_CTRL	0x59F
+#define ARC_AUX_DSP_FFT_CTRL	0x59E
+
+#define ARC_AUX_AGU_BUILD	0xCC
+#define ARC_AUX_AGU_AP0		0x5C0
+#define ARC_AUX_AGU_AP1		0x5C1
+#define ARC_AUX_AGU_AP2		0x5C2
+#define ARC_AUX_AGU_AP3		0x5C3
+#define ARC_AUX_AGU_OS0		0x5D0
+#define ARC_AUX_AGU_OS1		0x5D1
+#define ARC_AUX_AGU_MOD0	0x5E0
+#define ARC_AUX_AGU_MOD1	0x5E1
+#define ARC_AUX_AGU_MOD2	0x5E2
+#define ARC_AUX_AGU_MOD3	0x5E3
+
+#ifndef __ASSEMBLER__
+
+#include <soc/arc/arc_aux.h>
+
+/* Helpers */
+#define TO_KB(bytes)		((bytes) >> 10)
+#define TO_MB(bytes)		(TO_KB(bytes) >> 10)
+
+/*
+ ***************************************************************
+ * 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_isa_arcv2 {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int div_rem:4, pad2:4, ldd:1, unalign:1, atomic:1, be:1,
+		     pad1:12, ver:8;
+#else
+	unsigned int ver:8, pad1:12, be:1, atomic:1, unalign:1,
+		     ldd:1, pad2:4, div_rem:4;
+#endif
+};
+
+struct bcr_uarch_build {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int pad:8, prod:8, maj:8, min:8;
+#else
+	unsigned int min:8, maj:8, prod:8, pad:8;
+#endif
+};
+
+struct bcr_mmu_3 {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int ver:8, ways:4, sets:4, res:3, sasid:1, pg_sz:4,
+		     u_itlb:4, u_dtlb:4;
+#else
+	unsigned int u_dtlb:4, u_itlb:4, pg_sz:4, sasid:1, res:3, sets:4,
+		     ways:4, ver:8;
+#endif
+};
+
+struct bcr_mmu_4 {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int ver:8, sasid:1, sz1:4, sz0:4, res:2, pae:1,
+		     n_ways:2, n_entry:2, n_super:2, u_itlb:3, u_dtlb:3;
+#else
+	/*           DTLB      ITLB      JES        JE         JA      */
+	unsigned int u_dtlb:3, u_itlb:3, n_super:2, n_entry:2, n_ways:2,
+		     pae:1, res:2, sz0:4, sz1:4, sasid:1, ver:8;
+#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_slc_cfg {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int pad:24, way:2, lsz:2, sz:4;
+#else
+	unsigned int sz:4, lsz:2, way:2, pad:24;
+#endif
+};
+
+struct bcr_clust_cfg {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int pad:7, c:1, num_entries:8, num_cores:8, ver:8;
+#else
+	unsigned int ver:8, num_cores:8, num_entries:8, c:1, pad:7;
+#endif
+};
+
+struct bcr_volatile {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int start:4, limit:4, pad:22, order:1, disable:1;
+#else
+	unsigned int disable:1, order:1, pad:22, limit:4, start:4;
+#endif
+};
+
+struct bcr_mpy {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int pad:8, x1616:8, dsp:4, cycles:2, type:2, ver:8;
+#else
+	unsigned int ver:8, type:2, cycles:2, dsp:4, x1616:8, pad:8;
+#endif
+};
+
+struct bcr_iccm_arcompact {
+#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
+};
+
+struct bcr_iccm_arcv2 {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int pad:8, sz11:4, sz01:4, sz10:4, sz00:4, ver:8;
+#else
+	unsigned int ver:8, sz00:4, sz10:4, sz01:4, sz11:4, pad:8;
+#endif
+};
+
+struct bcr_dccm_arcompact {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int res:21, sz:3, ver:8;
+#else
+	unsigned int ver:8, sz:3, res:21;
+#endif
+};
+
+struct bcr_dccm_arcv2 {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int pad2:12, cyc:3, pad1:1, sz1:4, sz0:4, ver:8;
+#else
+	unsigned int ver:8, sz0:4, sz1:4, pad1:1, cyc:3, pad2:12;
+#endif
+};
+
+/* ARCompact: Both SP and DP FPU BCRs have same format */
+struct bcr_fp_arcompact {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int fast:1, ver:8;
+#else
+	unsigned int ver:8, fast:1;
+#endif
+};
+
+struct bcr_fp_arcv2 {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int pad2:15, dp:1, pad1:7, sp:1, ver:8;
+#else
+	unsigned int ver:8, sp:1, pad1:7, dp:1, pad2:15;
+#endif
+};
+
+struct bcr_actionpoint {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int pad:21, min:1, num:2, ver:8;
+#else
+	unsigned int ver:8, num:2, min:1, pad:21;
+#endif
+};
+
+#include <soc/arc/timers.h>
+
+struct bcr_bpu_arcompact {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int pad2:19, fam:1, pad:2, ent:2, ver:8;
+#else
+	unsigned int ver:8, ent:2, pad:2, fam:1, pad2:19;
+#endif
+};
+
+struct bcr_bpu_arcv2 {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int pad:6, fbe:2, tqe:2, ts:4, ft:1, rse:2, pte:3, bce:3, ver:8;
+#else
+	unsigned int ver:8, bce:3, pte:3, rse:2, ft:1, ts:4, tqe:2, fbe:2, pad:6;
+#endif
+};
+
+/* Error Protection Build: ECC/Parity */
+struct bcr_erp {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int pad3:5, mmu:3, pad2:4, ic:3, dc:3, pad1:6, ver:8;
+#else
+	unsigned int ver:8, pad1:6, dc:3, ic:3, pad2:4, mmu:3, pad3:5;
+#endif
+};
+
+/* Error Protection Control */
+struct ctl_erp {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int pad2:27, mpd:1, pad1:2, dpd:1, dpi:1;
+#else
+	unsigned int dpi:1, dpd:1, pad1:2, mpd:1, pad2:27;
+#endif
+};
+
+struct bcr_lpb {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int pad:16, entries:8, ver:8;
+#else
+	unsigned int ver:8, entries:8, pad:16;
+#endif
+};
+
+struct bcr_generic {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int info:24, ver:8;
+#else
+	unsigned int ver:8, info:24;
+#endif
+};
+
+static inline int is_isa_arcv2(void)
+{
+	return IS_ENABLED(CONFIG_ISA_ARCV2);
+}
+
+static inline int is_isa_arcompact(void)
+{
+	return IS_ENABLED(CONFIG_ISA_ARCOMPACT);
+}
+
+#endif /* __ASEMBLY__ */
+
+#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 000000000..32a1d3d51
--- /dev/null
+++ b/arch/arc/include/asm/asm-offsets.h
@@ -0,0 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#include <generated/asm-offsets.h>
diff --git a/arch/arc/include/asm/asserts.h b/arch/arc/include/asm/asserts.h
new file mode 100644
index 000000000..108f33be6
--- /dev/null
+++ b/arch/arc/include/asm/asserts.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2020 Synopsys, Inc. (www.synopsys.com)
+ *
+ * Author: Eugeniy Paltsev <Eugeniy.Paltsev@synopsys.com>
+ */
+#ifndef __ASM_ARC_ASSERTS_H
+#define __ASM_ARC_ASSERTS_H
+
+/* Helpers to sanitize config options. */
+
+void chk_opt_strict(char *opt_name, bool hw_exists, bool opt_ena);
+void chk_opt_weak(char *opt_name, bool hw_exists, bool opt_ena);
+
+/*
+ * Check required config option:
+ *  - panic in case of OPT enabled but corresponding HW absent.
+ *  - warn in case of OPT disabled but corresponding HW exists.
+*/
+#define CHK_OPT_STRICT(opt_name, hw_exists)				\
+({									\
+	chk_opt_strict(#opt_name, hw_exists, IS_ENABLED(opt_name));	\
+})
+
+/*
+ * Check optional config option:
+ *  - panic in case of OPT enabled but corresponding HW absent.
+*/
+#define CHK_OPT_WEAK(opt_name, hw_exists)				\
+({									\
+	chk_opt_weak(#opt_name, hw_exists, IS_ENABLED(opt_name));	\
+})
+
+#endif /* __ASM_ARC_ASSERTS_H */
diff --git a/arch/arc/include/asm/atomic-llsc.h b/arch/arc/include/asm/atomic-llsc.h
new file mode 100644
index 000000000..5258cb81a
--- /dev/null
+++ b/arch/arc/include/asm/atomic-llsc.h
@@ -0,0 +1,97 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef _ASM_ARC_ATOMIC_LLSC_H
+#define _ASM_ARC_ATOMIC_LLSC_H
+
+#define arch_atomic_set(v, i) WRITE_ONCE(((v)->counter), (i))
+
+#define ATOMIC_OP(op, asm_op)					\
+static inline void arch_atomic_##op(int i, atomic_t *v)			\
+{									\
+	unsigned int val;						\
+									\
+	__asm__ __volatile__(						\
+	"1:	llock   %[val], [%[ctr]]		\n"		\
+	"	" #asm_op " %[val], %[val], %[i]	\n"		\
+	"	scond   %[val], [%[ctr]]		\n"		\
+	"	bnz     1b				\n"		\
+	: [val]	"=&r"	(val) /* Early clobber to prevent reg reuse */	\
+	: [ctr]	"r"	(&v->counter), /* Not "m": llock only supports reg direct addr mode */	\
+	  [i]	"ir"	(i)						\
+	: "cc", "memory");						\
+}									\
+
+#define ATOMIC_OP_RETURN(op, asm_op)				\
+static inline int arch_atomic_##op##_return_relaxed(int i, atomic_t *v)	\
+{									\
+	unsigned int val;						\
+									\
+	__asm__ __volatile__(						\
+	"1:	llock   %[val], [%[ctr]]		\n"		\
+	"	" #asm_op " %[val], %[val], %[i]	\n"		\
+	"	scond   %[val], [%[ctr]]		\n"		\
+	"	bnz     1b				\n"		\
+	: [val]	"=&r"	(val)						\
+	: [ctr]	"r"	(&v->counter),					\
+	  [i]	"ir"	(i)						\
+	: "cc", "memory");						\
+									\
+	return val;							\
+}
+
+#define arch_atomic_add_return_relaxed		arch_atomic_add_return_relaxed
+#define arch_atomic_sub_return_relaxed		arch_atomic_sub_return_relaxed
+
+#define ATOMIC_FETCH_OP(op, asm_op)				\
+static inline int arch_atomic_fetch_##op##_relaxed(int i, atomic_t *v)	\
+{									\
+	unsigned int val, orig;						\
+									\
+	__asm__ __volatile__(						\
+	"1:	llock   %[orig], [%[ctr]]		\n"		\
+	"	" #asm_op " %[val], %[orig], %[i]	\n"		\
+	"	scond   %[val], [%[ctr]]		\n"		\
+	"	bnz     1b				\n"		\
+	: [val]	"=&r"	(val),						\
+	  [orig] "=&r" (orig)						\
+	: [ctr]	"r"	(&v->counter),					\
+	  [i]	"ir"	(i)						\
+	: "cc", "memory");						\
+									\
+	return orig;							\
+}
+
+#define arch_atomic_fetch_add_relaxed		arch_atomic_fetch_add_relaxed
+#define arch_atomic_fetch_sub_relaxed		arch_atomic_fetch_sub_relaxed
+
+#define arch_atomic_fetch_and_relaxed		arch_atomic_fetch_and_relaxed
+#define arch_atomic_fetch_andnot_relaxed	arch_atomic_fetch_andnot_relaxed
+#define arch_atomic_fetch_or_relaxed		arch_atomic_fetch_or_relaxed
+#define arch_atomic_fetch_xor_relaxed		arch_atomic_fetch_xor_relaxed
+
+#define ATOMIC_OPS(op, asm_op)					\
+	ATOMIC_OP(op, asm_op)					\
+	ATOMIC_OP_RETURN(op, asm_op)				\
+	ATOMIC_FETCH_OP(op, asm_op)
+
+ATOMIC_OPS(add, add)
+ATOMIC_OPS(sub, sub)
+
+#undef ATOMIC_OPS
+#define ATOMIC_OPS(op, asm_op)					\
+	ATOMIC_OP(op, asm_op)					\
+	ATOMIC_FETCH_OP(op, asm_op)
+
+ATOMIC_OPS(and, and)
+ATOMIC_OPS(andnot, bic)
+ATOMIC_OPS(or, or)
+ATOMIC_OPS(xor, xor)
+
+#define arch_atomic_andnot		arch_atomic_andnot
+
+#undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
+#undef ATOMIC_OP_RETURN
+#undef ATOMIC_OP
+
+#endif
diff --git a/arch/arc/include/asm/atomic-spinlock.h b/arch/arc/include/asm/atomic-spinlock.h
new file mode 100644
index 000000000..89d12a60f
--- /dev/null
+++ b/arch/arc/include/asm/atomic-spinlock.h
@@ -0,0 +1,111 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef _ASM_ARC_ATOMIC_SPLOCK_H
+#define _ASM_ARC_ATOMIC_SPLOCK_H
+
+/*
+ * Non hardware assisted Atomic-R-M-W
+ * Locking would change to irq-disabling only (UP) and spinlocks (SMP)
+ */
+
+static inline void arch_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);
+	WRITE_ONCE(v->counter, i);
+	atomic_ops_unlock(flags);
+}
+
+#define arch_atomic_set_release(v, i)	arch_atomic_set((v), (i))
+
+#define ATOMIC_OP(op, c_op, asm_op)					\
+static inline void arch_atomic_##op(int i, atomic_t *v)			\
+{									\
+	unsigned long flags;						\
+									\
+	atomic_ops_lock(flags);						\
+	v->counter c_op i;						\
+	atomic_ops_unlock(flags);					\
+}
+
+#define ATOMIC_OP_RETURN(op, c_op, asm_op)				\
+static inline int arch_atomic_##op##_return(int i, atomic_t *v)		\
+{									\
+	unsigned long flags;						\
+	unsigned int temp;						\
+									\
+	/*								\
+	 * spin lock/unlock provides the needed smp_mb() before/after	\
+	 */								\
+	atomic_ops_lock(flags);						\
+	temp = v->counter;						\
+	temp c_op i;							\
+	v->counter = temp;						\
+	atomic_ops_unlock(flags);					\
+									\
+	return temp;							\
+}
+
+#define ATOMIC_FETCH_OP(op, c_op, asm_op)				\
+static inline int arch_atomic_fetch_##op(int i, atomic_t *v)		\
+{									\
+	unsigned long flags;						\
+	unsigned int orig;						\
+									\
+	/*								\
+	 * spin lock/unlock provides the needed smp_mb() before/after	\
+	 */								\
+	atomic_ops_lock(flags);						\
+	orig = v->counter;						\
+	v->counter c_op i;						\
+	atomic_ops_unlock(flags);					\
+									\
+	return orig;							\
+}
+
+#define ATOMIC_OPS(op, c_op, asm_op)					\
+	ATOMIC_OP(op, c_op, asm_op)					\
+	ATOMIC_OP_RETURN(op, c_op, asm_op)				\
+	ATOMIC_FETCH_OP(op, c_op, asm_op)
+
+ATOMIC_OPS(add, +=, add)
+ATOMIC_OPS(sub, -=, sub)
+
+#define arch_atomic_fetch_add		arch_atomic_fetch_add
+#define arch_atomic_fetch_sub		arch_atomic_fetch_sub
+#define arch_atomic_add_return		arch_atomic_add_return
+#define arch_atomic_sub_return		arch_atomic_sub_return
+
+#undef ATOMIC_OPS
+#define ATOMIC_OPS(op, c_op, asm_op)					\
+	ATOMIC_OP(op, c_op, asm_op)					\
+	ATOMIC_FETCH_OP(op, c_op, asm_op)
+
+ATOMIC_OPS(and, &=, and)
+ATOMIC_OPS(andnot, &= ~, bic)
+ATOMIC_OPS(or, |=, or)
+ATOMIC_OPS(xor, ^=, xor)
+
+#define arch_atomic_andnot		arch_atomic_andnot
+
+#define arch_atomic_fetch_and		arch_atomic_fetch_and
+#define arch_atomic_fetch_andnot	arch_atomic_fetch_andnot
+#define arch_atomic_fetch_or		arch_atomic_fetch_or
+#define arch_atomic_fetch_xor		arch_atomic_fetch_xor
+
+#undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
+#undef ATOMIC_OP_RETURN
+#undef ATOMIC_OP
+
+#endif
diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
new file mode 100644
index 000000000..e615c42b9
--- /dev/null
+++ b/arch/arc/include/asm/atomic.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#ifndef _ASM_ARC_ATOMIC_H
+#define _ASM_ARC_ATOMIC_H
+
+#ifndef __ASSEMBLER__
+
+#include <linux/types.h>
+#include <linux/compiler.h>
+#include <asm/cmpxchg.h>
+#include <asm/barrier.h>
+#include <asm/smp.h>
+
+#define arch_atomic_read(v)  READ_ONCE((v)->counter)
+
+#ifdef CONFIG_ARC_HAS_LLSC
+#include <asm/atomic-llsc.h>
+#else
+#include <asm/atomic-spinlock.h>
+#endif
+
+/*
+ * 64-bit atomics
+ */
+#ifdef CONFIG_GENERIC_ATOMIC64
+#include <asm-generic/atomic64.h>
+#else
+#include <asm/atomic64-arcv2.h>
+#endif
+
+#endif	/* !__ASSEMBLER__ */
+
+#endif
diff --git a/arch/arc/include/asm/atomic64-arcv2.h b/arch/arc/include/asm/atomic64-arcv2.h
new file mode 100644
index 000000000..73080a664
--- /dev/null
+++ b/arch/arc/include/asm/atomic64-arcv2.h
@@ -0,0 +1,230 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+/*
+ * ARCv2 supports 64-bit exclusive load (LLOCKD) / store (SCONDD)
+ *  - The address HAS to be 64-bit aligned
+ */
+
+#ifndef _ASM_ARC_ATOMIC64_ARCV2_H
+#define _ASM_ARC_ATOMIC64_ARCV2_H
+
+typedef struct {
+	s64 __aligned(8) counter;
+} atomic64_t;
+
+#define ATOMIC64_INIT(a) { (a) }
+
+static inline s64 arch_atomic64_read(const atomic64_t *v)
+{
+	s64 val;
+
+	__asm__ __volatile__(
+	"	ldd   %0, [%1]	\n"
+	: "=r"(val)
+	: "r"(&v->counter));
+
+	return val;
+}
+
+static inline void arch_atomic64_set(atomic64_t *v, s64 a)
+{
+	/*
+	 * This could have been a simple assignment in "C" but would need
+	 * explicit volatile. Otherwise gcc optimizers could elide the store
+	 * which borked atomic64 self-test
+	 * In the inline asm version, memory clobber needed for exact same
+	 * reason, to tell gcc about the store.
+	 *
+	 * This however is not needed for sibling atomic64_add() etc since both
+	 * load/store are explicitly done in inline asm. As long as API is used
+	 * for each access, gcc has no way to optimize away any load/store
+	 */
+	__asm__ __volatile__(
+	"	std   %0, [%1]	\n"
+	:
+	: "r"(a), "r"(&v->counter)
+	: "memory");
+}
+
+#define ATOMIC64_OP(op, op1, op2)					\
+static inline void arch_atomic64_##op(s64 a, atomic64_t *v)		\
+{									\
+	s64 val;							\
+									\
+	__asm__ __volatile__(						\
+	"1:				\n"				\
+	"	llockd  %0, [%1]	\n"				\
+	"	" #op1 " %L0, %L0, %L2	\n"				\
+	"	" #op2 " %H0, %H0, %H2	\n"				\
+	"	scondd   %0, [%1]	\n"				\
+	"	bnz     1b		\n"				\
+	: "=&r"(val)							\
+	: "r"(&v->counter), "ir"(a)					\
+	: "cc", "memory");						\
+}									\
+
+#define ATOMIC64_OP_RETURN(op, op1, op2)		        	\
+static inline s64 arch_atomic64_##op##_return_relaxed(s64 a, atomic64_t *v)	\
+{									\
+	s64 val;							\
+									\
+	__asm__ __volatile__(						\
+	"1:				\n"				\
+	"	llockd   %0, [%1]	\n"				\
+	"	" #op1 " %L0, %L0, %L2	\n"				\
+	"	" #op2 " %H0, %H0, %H2	\n"				\
+	"	scondd   %0, [%1]	\n"				\
+	"	bnz     1b		\n"				\
+	: [val] "=&r"(val)						\
+	: "r"(&v->counter), "ir"(a)					\
+	: "cc", "memory");						\
+									\
+	return val;							\
+}
+
+#define arch_atomic64_add_return_relaxed	arch_atomic64_add_return_relaxed
+#define arch_atomic64_sub_return_relaxed	arch_atomic64_sub_return_relaxed
+
+#define ATOMIC64_FETCH_OP(op, op1, op2)		        		\
+static inline s64 arch_atomic64_fetch_##op##_relaxed(s64 a, atomic64_t *v)	\
+{									\
+	s64 val, orig;							\
+									\
+	__asm__ __volatile__(						\
+	"1:				\n"				\
+	"	llockd   %0, [%2]	\n"				\
+	"	" #op1 " %L1, %L0, %L3	\n"				\
+	"	" #op2 " %H1, %H0, %H3	\n"				\
+	"	scondd   %1, [%2]	\n"				\
+	"	bnz     1b		\n"				\
+	: "=&r"(orig), "=&r"(val)					\
+	: "r"(&v->counter), "ir"(a)					\
+	: "cc", "memory");						\
+									\
+	return orig;							\
+}
+
+#define arch_atomic64_fetch_add_relaxed		arch_atomic64_fetch_add_relaxed
+#define arch_atomic64_fetch_sub_relaxed		arch_atomic64_fetch_sub_relaxed
+
+#define arch_atomic64_fetch_and_relaxed		arch_atomic64_fetch_and_relaxed
+#define arch_atomic64_fetch_andnot_relaxed	arch_atomic64_fetch_andnot_relaxed
+#define arch_atomic64_fetch_or_relaxed		arch_atomic64_fetch_or_relaxed
+#define arch_atomic64_fetch_xor_relaxed		arch_atomic64_fetch_xor_relaxed
+
+#define ATOMIC64_OPS(op, op1, op2)					\
+	ATOMIC64_OP(op, op1, op2)					\
+	ATOMIC64_OP_RETURN(op, op1, op2)				\
+	ATOMIC64_FETCH_OP(op, op1, op2)
+
+ATOMIC64_OPS(add, add.f, adc)
+ATOMIC64_OPS(sub, sub.f, sbc)
+
+#undef ATOMIC64_OPS
+#define ATOMIC64_OPS(op, op1, op2)					\
+	ATOMIC64_OP(op, op1, op2)					\
+	ATOMIC64_FETCH_OP(op, op1, op2)
+
+ATOMIC64_OPS(and, and, and)
+ATOMIC64_OPS(andnot, bic, bic)
+ATOMIC64_OPS(or, or, or)
+ATOMIC64_OPS(xor, xor, xor)
+
+#define arch_atomic64_andnot		arch_atomic64_andnot
+
+#undef ATOMIC64_OPS
+#undef ATOMIC64_FETCH_OP
+#undef ATOMIC64_OP_RETURN
+#undef ATOMIC64_OP
+
+static inline u64 __arch_cmpxchg64_relaxed(volatile void *ptr, u64 old, u64 new)
+{
+	u64 prev;
+
+	__asm__ __volatile__(
+	"1:	llockd  %0, [%1]	\n"
+	"	brne    %L0, %L2, 2f	\n"
+	"	brne    %H0, %H2, 2f	\n"
+	"	scondd  %3, [%1]	\n"
+	"	bnz     1b		\n"
+	"2:				\n"
+	: "=&r"(prev)
+	: "r"(ptr), "ir"(old), "r"(new)
+	: "memory", "cc");
+
+	return prev;
+}
+#define arch_cmpxchg64_relaxed __arch_cmpxchg64_relaxed
+
+static inline s64 arch_atomic64_xchg(atomic64_t *ptr, s64 new)
+{
+	s64 prev;
+
+	smp_mb();
+
+	__asm__ __volatile__(
+	"1:	llockd  %0, [%1]	\n"
+	"	scondd  %2, [%1]	\n"
+	"	bnz     1b		\n"
+	"2:				\n"
+	: "=&r"(prev)
+	: "r"(ptr), "r"(new)
+	: "cc");	/* memory clobber comes from smp_mb() */
+
+	smp_mb();
+
+	return prev;
+}
+#define arch_atomic64_xchg arch_atomic64_xchg
+
+static inline s64 arch_atomic64_dec_if_positive(atomic64_t *v)
+{
+	s64 val;
+
+	smp_mb();
+
+	__asm__ __volatile__(
+	"1:	llockd  %0, [%1]	\n"
+	"	sub.f   %L0, %L0, 1	# w0 - 1, set C on borrow\n"
+	"	sub.c   %H0, %H0, 1	# if C set, w1 - 1\n"
+	"	brlt    %H0, 0, 2f	\n"
+	"	scondd  %0, [%1]	\n"
+	"	bnz     1b		\n"
+	"2:				\n"
+	: "=&r"(val)
+	: "r"(&v->counter)
+	: "cc");	/* memory clobber comes from smp_mb() */
+
+	smp_mb();
+
+	return val;
+}
+#define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive
+
+static inline s64 arch_atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u)
+{
+	s64 old, temp;
+
+	smp_mb();
+
+	__asm__ __volatile__(
+	"1:	llockd  %0, [%2]	\n"
+	"	brne	%L0, %L4, 2f	# continue to add since v != u \n"
+	"	breq.d	%H0, %H4, 3f	# return since v == u \n"
+	"2:				\n"
+	"	add.f   %L1, %L0, %L3	\n"
+	"	adc     %H1, %H0, %H3	\n"
+	"	scondd  %1, [%2]	\n"
+	"	bnz     1b		\n"
+	"3:				\n"
+	: "=&r"(old), "=&r" (temp)
+	: "r"(&v->counter), "r"(a), "r"(u)
+	: "cc");	/* memory clobber comes from smp_mb() */
+
+	smp_mb();
+
+	return old;
+}
+#define arch_atomic64_fetch_add_unless arch_atomic64_fetch_add_unless
+
+#endif
diff --git a/arch/arc/include/asm/barrier.h b/arch/arc/include/asm/barrier.h
new file mode 100644
index 000000000..4637de9e0
--- /dev/null
+++ b/arch/arc/include/asm/barrier.h
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#ifndef __ASM_BARRIER_H
+#define __ASM_BARRIER_H
+
+#ifdef CONFIG_ISA_ARCV2
+
+/*
+ * ARCv2 based HS38 cores are in-order issue, but still weakly ordered
+ * due to micro-arch buffering/queuing of load/store, cache hit vs. miss ...
+ *
+ * Explicit barrier provided by DMB instruction
+ *  - Operand supports fine grained load/store/load+store semantics
+ *  - Ensures that selected memory operation issued before it will complete
+ *    before any subsequent memory operation of same type
+ *  - DMB guarantees SMP as well as local barrier semantics
+ *    (asm-generic/barrier.h ensures sane smp_*mb if not defined here, i.e.
+ *    UP: barrier(), SMP: smp_*mb == *mb)
+ *  - DSYNC provides DMB+completion_of_cache_bpu_maintenance_ops hence not needed
+ *    in the general case. Plus it only provides full barrier.
+ */
+
+#define mb()	asm volatile("dmb 3\n" : : : "memory")
+#define rmb()	asm volatile("dmb 1\n" : : : "memory")
+#define wmb()	asm volatile("dmb 2\n" : : : "memory")
+
+#else
+
+/*
+ * ARCompact based cores (ARC700) only have SYNC instruction which is super
+ * heavy weight as it flushes the pipeline as well.
+ * There are no real SMP implementations of such cores.
+ */
+
+#define mb()	asm volatile("sync\n" : : : "memory")
+
+#endif
+
+#include <asm-generic/barrier.h>
+
+#endif
diff --git a/arch/arc/include/asm/bitops.h b/arch/arc/include/asm/bitops.h
new file mode 100644
index 000000000..df894235f
--- /dev/null
+++ b/arch/arc/include/asm/bitops.h
@@ -0,0 +1,199 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#ifndef _ASM_BITOPS_H
+#define _ASM_BITOPS_H
+
+#ifndef _LINUX_BITOPS_H
+#error only <linux/bitops.h> can be included directly
+#endif
+
+#ifndef __ASSEMBLER__
+
+#include <linux/types.h>
+#include <linux/compiler.h>
+
+#ifdef CONFIG_ISA_ARCOMPACT
+
+/*
+ * 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(unsigned 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))
+		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 int 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)) unsigned long __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)) unsigned long __ffs(unsigned long word)
+{
+	if (!word)
+		return word;
+
+	return ffs(word) - 1;
+}
+
+#else	/* CONFIG_ISA_ARCV2 */
+
+/*
+ * 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 int x)
+{
+	int n;
+
+	asm volatile(
+	"	fls.f	%0, %1		\n"  /* 0:31; 0(Z) if src 0 */
+	"	add.nz	%0, %0, 1	\n"  /* 0:31 -> 1:32 */
+	: "=r"(n)	/* Early clobber not needed */
+	: "r"(x)
+	: "cc");
+
+	return n;
+}
+
+/*
+ * __fls: Similar to fls, but zero based (0-31). Also 0 if no bit set
+ */
+static inline __attribute__ ((const)) unsigned long __fls(unsigned long x)
+{
+	if (__builtin_constant_p(x))
+		return x ? BITS_PER_LONG - 1 - __builtin_clzl(x) : 0;
+	/* FLS insn has exactly same semantics as the API */
+	return	__builtin_arc_fls(x);
+}
+
+/*
+ * ffs = Find First Set in word (LSB to MSB)
+ * @result: [1-32], 0 if all 0's
+ */
+static inline __attribute__ ((const)) int ffs(unsigned int x)
+{
+	int n;
+
+	asm volatile(
+	"	ffs.f	%0, %1		\n"  /* 0:31; 31(Z) if src 0 */
+	"	add.nz	%0, %0, 1	\n"  /* 0:31 -> 1:32 */
+	"	mov.z	%0, 0		\n"  /* 31(Z)-> 0 */
+	: "=r"(n)	/* Early clobber not needed */
+	: "r"(x)
+	: "cc");
+
+	return n;
+}
+
+/*
+ * __ffs: Similar to ffs, but zero based (0-31)
+ */
+static inline __attribute__ ((const)) unsigned long __ffs(unsigned long x)
+{
+	unsigned long n;
+
+	asm volatile(
+	"	ffs.f	%0, %1		\n"  /* 0:31; 31(Z) if src 0 */
+	"	mov.z	%0, 0		\n"  /* 31(Z)-> 0 */
+	: "=r"(n)
+	: "r"(x)
+	: "cc");
+
+	return n;
+
+}
+
+#endif	/* CONFIG_ISA_ARCOMPACT */
+
+/*
+ * ffz = Find First Zero in word.
+ * @return:[0-31], 32 if all 1's
+ */
+#define ffz(x)	__ffs(~(x))
+
+#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/atomic.h>
+#include <asm-generic/bitops/non-atomic.h>
+
+#include <asm-generic/bitops/le.h>
+#include <asm-generic/bitops/ext2-atomic-setbit.h>
+
+#endif /* !__ASSEMBLER__ */
+
+#endif
diff --git a/arch/arc/include/asm/bug.h b/arch/arc/include/asm/bug.h
new file mode 100644
index 000000000..171c16021
--- /dev/null
+++ b/arch/arc/include/asm/bug.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#ifndef _ASM_ARC_BUG_H
+#define _ASM_ARC_BUG_H
+
+#ifndef __ASSEMBLER__
+
+#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,
+		     const char *loglvl);
+void show_kernel_fault_diag(const char *str, struct pt_regs *regs,
+			    unsigned long address);
+void die(const char *str, struct pt_regs *regs, unsigned long address);
+
+#define BUG()	do {								\
+	pr_warn("BUG: failure at %s:%d/%s()!\n", __FILE__, __LINE__, __func__); \
+	barrier_before_unreachable();						\
+	__builtin_trap();							\
+} while (0)
+
+#define HAVE_ARCH_BUG
+
+#include <asm-generic/bug.h>
+
+#endif	/* !__ASSEMBLER__ */
+
+#endif
diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h
new file mode 100644
index 000000000..040a97f4d
--- /dev/null
+++ b/arch/arc/include/asm/cache.h
@@ -0,0 +1,128 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#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 CACHE_LINE_MASK		(~(L1_CACHE_BYTES - 1))
+
+/*
+ * ARC700 doesn't cache any access in top 1G (0xc000_0000 to 0xFFFF_FFFF)
+ * 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
+
+#ifndef __ASSEMBLER__
+
+#include <linux/build_bug.h>
+
+/* 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));		\
+})
+
+/* Largest line length for either L1 or L2 is 128 bytes */
+#define SMP_CACHE_BYTES		128
+#define cache_line_size()	SMP_CACHE_BYTES
+#define ARCH_DMA_MINALIGN	SMP_CACHE_BYTES
+
+/*
+ * Make sure slab-allocated buffers are 64-bit aligned when atomic64_t uses
+ * ARCv2 64-bit atomics (LLOCKD/SCONDD). This guarantess runtime 64-bit
+ * alignment for any atomic64_t embedded in buffer.
+ * Default ARCH_SLAB_MINALIGN is __alignof__(long long) which has a relaxed
+ * value of 4 (and not 8) in ARC ABI.
+ */
+#if defined(CONFIG_ARC_HAS_LL64) && defined(CONFIG_ARC_HAS_LLSC)
+#define ARCH_SLAB_MINALIGN	8
+#endif
+
+extern int ioc_enable;
+extern unsigned long perip_base, perip_end;
+
+#endif	/* !__ASSEMBLER__ */
+
+/* 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_IVIR		0x16
+#define ARC_REG_IC_ENDR		0x17
+#define ARC_REG_IC_IVIL		0x19
+#define ARC_REG_IC_PTAG		0x1E
+#define ARC_REG_IC_PTAG_HI	0x1F
+
+/* Bit val in IC_CTRL */
+#define IC_CTRL_DIS		0x1
+
+/* Data cache related Auxiliary registers */
+#define ARC_REG_DC_BCR		0x72	/* Build Config reg */
+#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
+#define ARC_REG_DC_STARTR	0x4D
+#define ARC_REG_DC_ENDR		0x4E
+#define ARC_REG_DC_PTAG		0x5C
+#define ARC_REG_DC_PTAG_HI	0x5F
+
+/* Bit val in DC_CTRL */
+#define DC_CTRL_DIS		0x001
+#define DC_CTRL_INV_MODE_FLUSH	0x040
+#define DC_CTRL_FLUSH_STATUS	0x100
+#define DC_CTRL_RGN_OP_INV	0x200
+#define DC_CTRL_RGN_OP_MSK	0x200
+
+/*System-level cache (L2 cache) related Auxiliary registers */
+#define ARC_REG_SLC_CFG		0x901
+#define ARC_REG_SLC_CTRL	0x903
+#define ARC_REG_SLC_FLUSH	0x904
+#define ARC_REG_SLC_INVALIDATE	0x905
+#define ARC_AUX_SLC_IVDL	0x910
+#define ARC_AUX_SLC_FLDL	0x912
+#define ARC_REG_SLC_RGN_START	0x914
+#define ARC_REG_SLC_RGN_START1	0x915
+#define ARC_REG_SLC_RGN_END	0x916
+#define ARC_REG_SLC_RGN_END1	0x917
+
+/* Bit val in SLC_CONTROL */
+#define SLC_CTRL_DIS		0x001
+#define SLC_CTRL_IM		0x040
+#define SLC_CTRL_BUSY		0x100
+#define SLC_CTRL_RGN_OP_INV	0x200
+
+/* IO coherency related Auxiliary registers */
+#define ARC_REG_IO_COH_ENABLE	0x500
+#define ARC_IO_COH_ENABLE_BIT	BIT(0)
+#define ARC_REG_IO_COH_PARTIAL	0x501
+#define ARC_IO_COH_PARTIAL_BIT	BIT(0)
+#define ARC_REG_IO_COH_AP0_BASE	0x508
+#define ARC_REG_IO_COH_AP0_SIZE	0x509
+
+#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 000000000..329c94cd4
--- /dev/null
+++ b/arch/arc/include/asm/cacheflush.h
@@ -0,0 +1,69 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ *  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>
+#include <asm/shmparam.h>
+
+void flush_cache_all(void);
+
+void flush_icache_range(unsigned long kstart, unsigned long kend);
+void __sync_icache_dcache(phys_addr_t paddr, unsigned long vaddr, int len);
+void __inv_icache_pages(phys_addr_t paddr, unsigned long vaddr, unsigned nr);
+void __flush_dcache_pages(phys_addr_t paddr, unsigned long vaddr, unsigned nr);
+
+#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
+
+void flush_dcache_page(struct page *page);
+void flush_dcache_folio(struct folio *folio);
+#define flush_dcache_folio flush_dcache_folio
+
+void dma_cache_wback_inv(phys_addr_t start, unsigned long sz);
+void dma_cache_inv(phys_addr_t start, unsigned long sz);
+void dma_cache_wback(phys_addr_t 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_vmap_early(start, end)	do { } while (0)
+#define flush_cache_vunmap(start, end)		flush_cache_all()
+
+#define flush_cache_dup_mm(mm)			/* called on fork (VIVT only) */
+
+#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 */
+
+/*
+ * A new pagecache page has PG_arch_1 clear - thus dcache dirty by default
+ * This works around some PIO based drivers which don't call flush_dcache_page
+ * to record that they dirtied the dcache
+ */
+#define PG_dc_clean	PG_arch_1
+
+#define copy_to_user_page(vma, page, vaddr, dst, src, len)		\
+do {									\
+	memcpy(dst, src, len);						\
+	if (vma->vm_flags & VM_EXEC)					\
+		__sync_icache_dcache((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/cachetype.h b/arch/arc/include/asm/cachetype.h
new file mode 100644
index 000000000..acd3b6cb4
--- /dev/null
+++ b/arch/arc/include/asm/cachetype.h
@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_ARC_CACHETYPE_H
+#define __ASM_ARC_CACHETYPE_H
+
+#define cpu_dcache_is_aliasing()	false
+#define cpu_icache_is_aliasing()	true
+
+#endif
diff --git a/arch/arc/include/asm/checksum.h b/arch/arc/include/asm/checksum.h
new file mode 100644
index 000000000..0b485800a
--- /dev/null
+++ b/arch/arc/include/asm/checksum.h
@@ -0,0 +1,98 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * 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 int 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, __u32 len,
+		   __u8 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/cmpxchg.h b/arch/arc/include/asm/cmpxchg.h
new file mode 100644
index 000000000..76f43db08
--- /dev/null
+++ b/arch/arc/include/asm/cmpxchg.h
@@ -0,0 +1,145 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#ifndef __ASM_ARC_CMPXCHG_H
+#define __ASM_ARC_CMPXCHG_H
+
+#include <linux/build_bug.h>
+#include <linux/types.h>
+#include <linux/cmpxchg-emu.h>
+
+#include <asm/barrier.h>
+#include <asm/smp.h>
+
+#ifdef CONFIG_ARC_HAS_LLSC
+
+/*
+ * if (*ptr == @old)
+ *      *ptr = @new
+ */
+#define __cmpxchg(ptr, old, new)					\
+({									\
+	__typeof__(*(ptr)) _prev;					\
+									\
+	__asm__ __volatile__(						\
+	"1:	llock  %0, [%1]	\n"					\
+	"	brne   %0, %2, 2f	\n"				\
+	"	scond  %3, [%1]	\n"					\
+	"	bnz     1b		\n"				\
+	"2:				\n"				\
+	: "=&r"(_prev)	/* Early clobber prevent reg reuse */		\
+	: "r"(ptr),	/* Not "m": llock only supports reg */		\
+	  "ir"(old),							\
+	  "r"(new)	/* Not "ir": scond can't take LIMM */		\
+	: "cc",								\
+	  "memory");	/* gcc knows memory is clobbered */		\
+									\
+	_prev;								\
+})
+
+#define arch_cmpxchg_relaxed(ptr, old, new)				\
+({									\
+	__typeof__(ptr) _p_ = (ptr);					\
+	__typeof__(*(ptr)) _o_ = (old);					\
+	__typeof__(*(ptr)) _n_ = (new);					\
+	__typeof__(*(ptr)) _prev_;					\
+									\
+	switch(sizeof((_p_))) {						\
+	case 1:								\
+		_prev_ = (__typeof__(*(ptr)))cmpxchg_emu_u8((volatile u8 *__force)_p_, (uintptr_t)_o_, (uintptr_t)_n_);	\
+		break;							\
+	case 4:								\
+		_prev_ = __cmpxchg(_p_, _o_, _n_);			\
+		break;							\
+	default:							\
+		BUILD_BUG();						\
+	}								\
+	_prev_;								\
+})
+
+#else
+
+#define arch_cmpxchg(ptr, old, new)				        \
+({									\
+	volatile __typeof__(ptr) _p_ = (ptr);				\
+	__typeof__(*(ptr)) _o_ = (old);					\
+	__typeof__(*(ptr)) _n_ = (new);					\
+	__typeof__(*(ptr)) _prev_;					\
+	unsigned long __flags;						\
+									\
+	/*								\
+	 * spin lock/unlock provide the needed smp_mb() before/after	\
+	 */								\
+	atomic_ops_lock(__flags);					\
+	_prev_ = *_p_;							\
+	if (_prev_ == _o_)						\
+		*_p_ = _n_;						\
+	atomic_ops_unlock(__flags);					\
+	_prev_;								\
+})
+
+#endif
+
+/*
+ * xchg
+ */
+#ifdef CONFIG_ARC_HAS_LLSC
+
+#define __arch_xchg(ptr, val)						\
+({									\
+	__asm__ __volatile__(						\
+	"	ex  %0, [%1]	\n"	/* set new value */	        \
+	: "+r"(val)							\
+	: "r"(ptr)							\
+	: "memory");							\
+	_val_;		/* get old value */				\
+})
+
+#define arch_xchg_relaxed(ptr, val)					\
+({									\
+	__typeof__(ptr) _p_ = (ptr);					\
+	__typeof__(*(ptr)) _val_ = (val);				\
+									\
+	switch(sizeof(*(_p_))) {					\
+	case 4:								\
+		_val_ = __arch_xchg(_p_, _val_);			\
+		break;							\
+	default:							\
+		BUILD_BUG();						\
+	}								\
+	_val_;								\
+})
+
+#else  /* !CONFIG_ARC_HAS_LLSC */
+
+/*
+ * EX instructions is baseline and present in !LLSC too. But in this
+ * regime it still needs use @atomic_ops_lock spinlock to allow interop
+ * with cmpxchg() which uses spinlock in !LLSC
+ * (llist.h use xchg and cmpxchg on sama data)
+ */
+
+#define arch_xchg(ptr, val)					        \
+({									\
+	__typeof__(ptr) _p_ = (ptr);					\
+	__typeof__(*(ptr)) _val_ = (val);				\
+									\
+	unsigned long __flags;						\
+									\
+	atomic_ops_lock(__flags);					\
+									\
+	__asm__ __volatile__(						\
+	"	ex  %0, [%1]	\n"					\
+	: "+r"(_val_)							\
+	: "r"(_p_)							\
+	: "memory");							\
+									\
+	atomic_ops_unlock(__flags);					\
+	_val_;								\
+})
+
+#endif
+
+#endif
diff --git a/arch/arc/include/asm/current.h b/arch/arc/include/asm/current.h
new file mode 100644
index 000000000..03ffd005f
--- /dev/null
+++ b/arch/arc/include/asm/current.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * Vineetg: May 16th, 2008
+ *  - Current macro is now implemented as "global register" r25
+ */
+
+#ifndef _ASM_ARC_CURRENT_H
+#define _ASM_ARC_CURRENT_H
+
+#ifndef __ASSEMBLER__
+
+#ifdef CONFIG_ARC_CURR_IN_REG
+
+register struct task_struct *curr_arc asm("gp");
+#define current (curr_arc)
+
+#else
+#include <asm-generic/current.h>
+#endif /* ! CONFIG_ARC_CURR_IN_REG */
+
+#endif /* ! __ASSEMBLER__ */
+
+#endif /* _ASM_ARC_CURRENT_H */
diff --git a/arch/arc/include/asm/delay.h b/arch/arc/include/asm/delay.h
new file mode 100644
index 000000000..54db798f0
--- /dev/null
+++ b/arch/arc/include/asm/delay.h
@@ -0,0 +1,69 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * 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-generic/types.h>
+#include <asm/param.h>		/* HZ */
+
+extern unsigned long loops_per_jiffy;
+
+static inline void __delay(unsigned long loops)
+{
+	__asm__ __volatile__(
+	"	mov lp_count, %0	\n"
+	"	lp  1f			\n"
+	"	nop			\n"
+	"1:				\n"
+	:
+        : "r"(loops)
+        : "lp_count");
+}
+
+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;
+
+	/* (u64) cast ensures 64 bit MPY - real or emulated
+	 * HZ * 4295 is pre-evaluated by gcc - hence only 2 mpy ops
+	 */
+	loops = ((u64) usecs * 4295 * HZ * 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 000000000..61fb4d7af
--- /dev/null
+++ b/arch/arc/include/asm/disasm.h
@@ -0,0 +1,113 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * 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)
+ */
+
+#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.h b/arch/arc/include/asm/dma.h
new file mode 100644
index 000000000..02431027e
--- /dev/null
+++ b/arch/arc/include/asm/dma.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#ifndef ASM_ARC_DMA_H
+#define ASM_ARC_DMA_H
+
+#define MAX_DMA_ADDRESS 0xC0000000
+
+#endif
diff --git a/arch/arc/include/asm/dsp-impl.h b/arch/arc/include/asm/dsp-impl.h
new file mode 100644
index 000000000..fd5fdaad9
--- /dev/null
+++ b/arch/arc/include/asm/dsp-impl.h
@@ -0,0 +1,152 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2020 Synopsys, Inc. (www.synopsys.com)
+ *
+ * Author: Eugeniy Paltsev <Eugeniy.Paltsev@synopsys.com>
+ */
+#ifndef __ASM_ARC_DSP_IMPL_H
+#define __ASM_ARC_DSP_IMPL_H
+
+#include <asm/dsp.h>
+
+#define DSP_CTRL_DISABLED_ALL		0
+
+#ifdef __ASSEMBLER__
+
+/* clobbers r5 register */
+.macro DSP_EARLY_INIT
+#ifdef CONFIG_ISA_ARCV2
+	lr	r5, [ARC_AUX_DSP_BUILD]
+	bmsk	r5, r5, 7
+	breq    r5, 0, 1f
+	mov	r5, DSP_CTRL_DISABLED_ALL
+	sr	r5, [ARC_AUX_DSP_CTRL]
+1:
+#endif
+.endm
+
+/* clobbers r10, r11 registers pair */
+.macro DSP_SAVE_REGFILE_IRQ
+#if defined(CONFIG_ARC_DSP_KERNEL)
+	/*
+	 * Drop any changes to DSP_CTRL made by userspace so userspace won't be
+	 * able to break kernel - reset it to DSP_CTRL_DISABLED_ALL value
+	 */
+	mov	r10, DSP_CTRL_DISABLED_ALL
+	sr	r10, [ARC_AUX_DSP_CTRL]
+
+#elif defined(CONFIG_ARC_DSP_SAVE_RESTORE_REGS)
+	/*
+	 * Save DSP_CTRL register and reset it to value suitable for kernel
+	 * (DSP_CTRL_DISABLED_ALL)
+	 */
+	mov	r10, DSP_CTRL_DISABLED_ALL
+	aex	r10, [ARC_AUX_DSP_CTRL]
+	st	r10, [sp, PT_DSP_CTRL]
+
+#endif
+.endm
+
+/* clobbers r10, r11 registers pair */
+.macro DSP_RESTORE_REGFILE_IRQ
+#if defined(CONFIG_ARC_DSP_SAVE_RESTORE_REGS)
+	ld	r10, [sp, PT_DSP_CTRL]
+	sr	r10, [ARC_AUX_DSP_CTRL]
+
+#endif
+.endm
+
+#else /* __ASEMBLY__ */
+
+#include <linux/sched.h>
+#include <asm/asserts.h>
+#include <asm/switch_to.h>
+
+#ifdef CONFIG_ARC_DSP_SAVE_RESTORE_REGS
+
+/*
+ * As we save new and restore old AUX register value in the same place we
+ * can optimize a bit and use AEX instruction (swap contents of an auxiliary
+ * register with a core register) instead of LR + SR pair.
+ */
+#define AUX_SAVE_RESTORE(_saveto, _readfrom, _offt, _aux)		\
+do {									\
+	long unsigned int _scratch;					\
+									\
+	__asm__ __volatile__(						\
+		"ld	%0, [%2, %4]			\n"		\
+		"aex	%0, [%3]			\n"		\
+		"st	%0, [%1, %4]			\n"		\
+		:							\
+		  "=&r" (_scratch)	/* must be early clobber */	\
+		:							\
+		   "r" (_saveto),					\
+		   "r" (_readfrom),					\
+		   "Ir" (_aux),						\
+		   "Ir" (_offt)						\
+		:							\
+		  "memory"						\
+	);								\
+} while (0)
+
+#define DSP_AUX_SAVE_RESTORE(_saveto, _readfrom, _aux)			\
+	AUX_SAVE_RESTORE(_saveto, _readfrom,				\
+		offsetof(struct dsp_callee_regs, _aux),			\
+		ARC_AUX_##_aux)
+
+static inline void dsp_save_restore(struct task_struct *prev,
+					struct task_struct *next)
+{
+	long unsigned int *saveto = &prev->thread.dsp.ACC0_GLO;
+	long unsigned int *readfrom = &next->thread.dsp.ACC0_GLO;
+
+	DSP_AUX_SAVE_RESTORE(saveto, readfrom, ACC0_GLO);
+	DSP_AUX_SAVE_RESTORE(saveto, readfrom, ACC0_GHI);
+
+	DSP_AUX_SAVE_RESTORE(saveto, readfrom, DSP_BFLY0);
+	DSP_AUX_SAVE_RESTORE(saveto, readfrom, DSP_FFT_CTRL);
+
+#ifdef CONFIG_ARC_DSP_AGU_USERSPACE
+	DSP_AUX_SAVE_RESTORE(saveto, readfrom, AGU_AP0);
+	DSP_AUX_SAVE_RESTORE(saveto, readfrom, AGU_AP1);
+	DSP_AUX_SAVE_RESTORE(saveto, readfrom, AGU_AP2);
+	DSP_AUX_SAVE_RESTORE(saveto, readfrom, AGU_AP3);
+
+	DSP_AUX_SAVE_RESTORE(saveto, readfrom, AGU_OS0);
+	DSP_AUX_SAVE_RESTORE(saveto, readfrom, AGU_OS1);
+
+	DSP_AUX_SAVE_RESTORE(saveto, readfrom, AGU_MOD0);
+	DSP_AUX_SAVE_RESTORE(saveto, readfrom, AGU_MOD1);
+	DSP_AUX_SAVE_RESTORE(saveto, readfrom, AGU_MOD2);
+	DSP_AUX_SAVE_RESTORE(saveto, readfrom, AGU_MOD3);
+#endif /* CONFIG_ARC_DSP_AGU_USERSPACE */
+}
+
+#else /* !CONFIG_ARC_DSP_SAVE_RESTORE_REGS */
+#define dsp_save_restore(p, n)
+#endif /* CONFIG_ARC_DSP_SAVE_RESTORE_REGS */
+
+static inline bool dsp_exist(void)
+{
+	struct bcr_generic bcr;
+
+	READ_BCR(ARC_AUX_DSP_BUILD, bcr);
+	return !!bcr.ver;
+}
+
+static inline bool agu_exist(void)
+{
+	struct bcr_generic bcr;
+
+	READ_BCR(ARC_AUX_AGU_BUILD, bcr);
+	return !!bcr.ver;
+}
+
+static inline void dsp_config_check(void)
+{
+	CHK_OPT_STRICT(CONFIG_ARC_DSP_HANDLED, dsp_exist());
+	CHK_OPT_WEAK(CONFIG_ARC_DSP_AGU_USERSPACE, agu_exist());
+}
+
+#endif /* __ASEMBLY__ */
+#endif /* __ASM_ARC_DSP_IMPL_H */
diff --git a/arch/arc/include/asm/dsp.h b/arch/arc/include/asm/dsp.h
new file mode 100644
index 000000000..eeaaf4e4e
--- /dev/null
+++ b/arch/arc/include/asm/dsp.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2020 Synopsys, Inc. (www.synopsys.com)
+ *
+ * Author: Eugeniy Paltsev <Eugeniy.Paltsev@synopsys.com>
+ */
+#ifndef __ASM_ARC_DSP_H
+#define __ASM_ARC_DSP_H
+
+#ifndef __ASSEMBLER__
+
+/*
+ * DSP-related saved registers - need to be saved only when you are
+ * scheduled out.
+ * structure fields name must correspond to aux register definitions for
+ * automatic offset calculation in DSP_AUX_SAVE_RESTORE macros
+ */
+struct dsp_callee_regs {
+	unsigned long ACC0_GLO, ACC0_GHI, DSP_BFLY0, DSP_FFT_CTRL;
+#ifdef CONFIG_ARC_DSP_AGU_USERSPACE
+	unsigned long AGU_AP0, AGU_AP1, AGU_AP2, AGU_AP3;
+	unsigned long AGU_OS0, AGU_OS1;
+	unsigned long AGU_MOD0, AGU_MOD1, AGU_MOD2, AGU_MOD3;
+#endif
+};
+
+#endif /* !__ASSEMBLER__ */
+
+#endif /* __ASM_ARC_DSP_H */
diff --git a/arch/arc/include/asm/dwarf.h b/arch/arc/include/asm/dwarf.h
new file mode 100644
index 000000000..1524c5cf8
--- /dev/null
+++ b/arch/arc/include/asm/dwarf.h
@@ -0,0 +1,43 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2016-17 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#ifndef _ASM_ARC_DWARF_H
+#define _ASM_ARC_DWARF_H
+
+#ifdef __ASSEMBLER__
+
+#ifdef ARC_DW2_UNWIND_AS_CFI
+
+#define CFI_STARTPROC		.cfi_startproc
+#define CFI_ENDPROC		.cfi_endproc
+#define CFI_DEF_CFA		.cfi_def_cfa
+#define CFI_DEF_CFA_OFFSET	.cfi_def_cfa_offset
+#define CFI_DEF_CFA_REGISTER	.cfi_def_cfa_register
+#define CFI_OFFSET		.cfi_offset
+#define CFI_REL_OFFSET		.cfi_rel_offset
+#define CFI_REGISTER		.cfi_register
+#define CFI_RESTORE		.cfi_restore
+#define CFI_UNDEFINED		.cfi_undefined
+
+#else
+
+#define CFI_IGNORE	#
+
+#define CFI_STARTPROC		CFI_IGNORE
+#define CFI_ENDPROC		CFI_IGNORE
+#define CFI_DEF_CFA		CFI_IGNORE
+#define CFI_DEF_CFA_OFFSET	CFI_IGNORE
+#define CFI_DEF_CFA_REGISTER	CFI_IGNORE
+#define CFI_OFFSET		CFI_IGNORE
+#define CFI_REL_OFFSET		CFI_IGNORE
+#define CFI_REGISTER		CFI_IGNORE
+#define CFI_RESTORE		CFI_IGNORE
+#define CFI_UNDEFINED		CFI_IGNORE
+
+#endif	/* !ARC_DW2_UNWIND_AS_CFI */
+
+#endif	/* __ASSEMBLER__ */
+
+#endif	/* _ASM_ARC_DWARF_H */
diff --git a/arch/arc/include/asm/elf.h b/arch/arc/include/asm/elf.h
new file mode 100644
index 000000000..0284ace0e
--- /dev/null
+++ b/arch/arc/include/asm/elf.h
@@ -0,0 +1,72 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#ifndef __ASM_ARC_ELF_H
+#define __ASM_ARC_ELF_H
+
+#include <linux/types.h>
+#include <linux/elf-em.h>
+#include <uapi/asm/elf.h>
+
+#define EM_ARC_INUSE		(IS_ENABLED(CONFIG_ISA_ARCOMPACT) ? \
+					EM_ARCOMPACT : EM_ARCV2)
+
+/* ARC Relocations (kernel Modules only) */
+#define  R_ARC_32		0x4
+#define  R_ARC_32_ME		0x1B
+#define  R_ARC_32_PCREL		0x31
+
+/*to set parameters in the core dumps */
+#define ELF_ARCH		EM_ARC_INUSE
+#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		(2UL * 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)
+
+#endif
diff --git a/arch/arc/include/asm/entry-arcv2.h b/arch/arc/include/asm/entry-arcv2.h
new file mode 100644
index 000000000..3802a2daa
--- /dev/null
+++ b/arch/arc/include/asm/entry-arcv2.h
@@ -0,0 +1,326 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_ARC_ENTRY_ARCV2_H
+#define __ASM_ARC_ENTRY_ARCV2_H
+
+#include <asm/asm-offsets.h>
+#include <asm/dsp-impl.h>
+#include <asm/irqflags-arcv2.h>
+#include <asm/thread_info.h>	/* For THREAD_SIZE */
+
+/*
+ * Interrupt/Exception stack layout (pt_regs) for ARCv2
+ *   (End of struct aligned to end of page [unless nested])
+ *
+ *  INTERRUPT                          EXCEPTION
+ *
+ *    manual    ---------------------  manual
+ *              |      orig_r0      |
+ *              |      event/ECR    |
+ *              |      bta          |
+ *              |      gp           |
+ *              |      fp           |
+ *              |      sp           |
+ *              |      r12          |
+ *              |      r30          |
+ *              |      r58          |
+ *              |      r59          |
+ *  hw autosave ---------------------
+ *    optional  |      r0           |
+ *              |      r1           |
+ *              ~                   ~
+ *              |      r9           |
+ *              |      r10          |
+ *              |      r11          |
+ *              |      blink        |
+ *              |      lpe          |
+ *              |      lps          |
+ *              |      lpc          |
+ *              |      ei base      |
+ *              |      ldi base     |
+ *              |      jli base     |
+ *              ---------------------
+ *  hw autosave |       pc / eret   |
+ *   mandatory  | stat32 / erstatus |
+ *              ---------------------
+ */
+
+/*------------------------------------------------------------------------*/
+.macro INTERRUPT_PROLOGUE
+
+	; Before jumping to Interrupt Vector, hardware micro-ops did following:
+	;   1. SP auto-switched to kernel mode stack
+	;   2. STATUS32.Z flag set if in U mode at time of interrupt (U:1,K:0)
+	;   3. Auto save: (mandatory) Push PC and STAT32 on stack
+	;                 hardware does even if CONFIG_ARC_IRQ_NO_AUTOSAVE
+	;  4a. Auto save: (optional) r0-r11, blink, LPE,LPS,LPC, JLI,LDI,EI
+	;
+	; Now
+	;  4b. If Auto-save (optional) not enabled in hw, manually save them
+	;   5. Manually save: r12,r30, sp,fp,gp, ACCL pair
+	;
+	; At the end, SP points to pt_regs
+
+#ifdef CONFIG_ARC_IRQ_NO_AUTOSAVE
+	; carve pt_regs on stack (case #3), PC/STAT32 already on stack
+	sub	sp, sp, SZ_PT_REGS - 8
+
+	__SAVE_REGFILE_HARD
+#else
+	; carve pt_regs on stack (case #4), which grew partially already
+	sub	sp, sp, PT_r0
+#endif
+
+	__SAVE_REGFILE_SOFT
+.endm
+
+/*------------------------------------------------------------------------*/
+.macro EXCEPTION_PROLOGUE_KEEP_AE
+
+	; Before jumping to Exception Vector, hardware micro-ops did following:
+	;   1. SP auto-switched to kernel mode stack
+	;   2. STATUS32.Z flag set if in U mode at time of exception (U:1,K:0)
+	;
+	; Now manually save rest of reg file
+	; At the end, SP points to pt_regs
+
+	sub	sp, sp, SZ_PT_REGS	; carve space for pt_regs
+
+	; _HARD saves r10 clobbered by _SOFT as scratch hence comes first
+
+	__SAVE_REGFILE_HARD
+	__SAVE_REGFILE_SOFT
+
+	st	r0, [sp]	; orig_r0
+
+	lr	r10, [eret]
+	lr	r11, [erstatus]
+	ST2	r10, r11, PT_ret
+
+	lr	r10, [ecr]
+	lr	r11, [erbta]
+	ST2	r10, r11, PT_event
+
+	; OUTPUT: r10 has ECR expected by EV_Trap
+.endm
+
+.macro EXCEPTION_PROLOGUE
+
+	EXCEPTION_PROLOGUE_KEEP_AE	; return ECR in r10
+
+	lr  r0, [efa]
+	mov r1, sp
+
+	FAKE_RET_FROM_EXCPN		; clobbers r9
+.endm
+
+/*------------------------------------------------------------------------
+ * This macro saves the registers manually which would normally be autosaved
+ * by hardware on taken interrupts. It is used by
+ *   - exception handlers (which don't have autosave)
+ *   - interrupt autosave disabled due to CONFIG_ARC_IRQ_NO_AUTOSAVE
+ */
+.macro __SAVE_REGFILE_HARD
+
+	ST2	r0,  r1,  PT_r0
+	ST2	r2,  r3,  PT_r2
+	ST2	r4,  r5,  PT_r4
+	ST2	r6,  r7,  PT_r6
+	ST2	r8,  r9,  PT_r8
+	ST2	r10, r11, PT_r10
+
+	st	blink, [sp, PT_blink]
+
+	lr	r10, [lp_end]
+	lr	r11, [lp_start]
+	ST2	r10, r11, PT_lpe
+
+	st	lp_count, [sp, PT_lpc]
+
+	; skip JLI, LDI, EI for now
+.endm
+
+/*------------------------------------------------------------------------
+ * This macros saves a bunch of other registers which can't be autosaved for
+ * various reasons:
+ *   - r12: the last caller saved scratch reg since hardware saves in pairs so r0-r11
+ *   - r30: free reg, used by gcc as scratch
+ *   - ACCL/ACCH pair when they exist
+ */
+.macro __SAVE_REGFILE_SOFT
+
+	st	fp,  [sp, PT_fp]	; r27
+	st	r30, [sp, PT_r30]
+	st	r12, [sp, PT_r12]
+	st	r26, [sp, PT_r26]	; gp
+
+	; Saving pt_regs->sp correctly requires some extra work due to the way
+	; Auto stack switch works
+	;  - U mode: retrieve it from AUX_USER_SP
+	;  - K mode: add the offset from current SP where H/w starts auto push
+	;
+	; 1. Utilize the fact that Z bit is set if Intr taken in U mode
+	; 2. Upon entry SP is always saved (for any inspection, unwinding etc),
+	;    but on return, restored only if U mode
+
+	lr	r10, [AUX_USER_SP]	; U mode SP
+
+	; ISA requires ADD.nz to have same dest and src reg operands
+	mov.nz	r10, sp
+	add2.nz	r10, r10, SZ_PT_REGS/4	; K mode SP
+
+	st	r10, [sp, PT_sp]	; SP (pt_regs->sp)
+
+#ifdef CONFIG_ARC_HAS_ACCL_REGS
+	ST2	r58, r59, PT_r58
+#endif
+
+	/* clobbers r10, r11 registers pair */
+	DSP_SAVE_REGFILE_IRQ
+
+#ifdef CONFIG_ARC_CURR_IN_REG
+	GET_CURR_TASK_ON_CPU	gp
+#endif
+
+.endm
+
+/*------------------------------------------------------------------------*/
+.macro __RESTORE_REGFILE_SOFT
+
+	ld	fp,  [sp, PT_fp]
+	ld	r30, [sp, PT_r30]
+	ld	r12, [sp, PT_r12]
+	ld	r26, [sp, PT_r26]
+
+	; Restore SP (into AUX_USER_SP) only if returning to U mode
+	;  - for K mode, it will be implicitly restored as stack is unwound
+	;  - Z flag set on K is inverse of what hardware does on interrupt entry
+	;    but that doesn't really matter
+	bz	1f
+
+	ld	r10, [sp, PT_sp]	; SP (pt_regs->sp)
+	sr	r10, [AUX_USER_SP]
+1:
+
+	/* clobbers r10, r11 registers pair */
+	DSP_RESTORE_REGFILE_IRQ
+
+#ifdef CONFIG_ARC_HAS_ACCL_REGS
+	LD2	r58, r59, PT_r58
+#endif
+.endm
+
+/*------------------------------------------------------------------------*/
+.macro __RESTORE_REGFILE_HARD
+
+	ld	blink, [sp, PT_blink]
+
+	LD2	r10, r11, PT_lpe
+	sr	r10, [lp_end]
+	sr	r11, [lp_start]
+
+	ld	r10, [sp, PT_lpc]	; lp_count can't be target of LD
+	mov	lp_count, r10
+
+	LD2	r0,  r1,  PT_r0
+	LD2	r2,  r3,  PT_r2
+	LD2	r4,  r5,  PT_r4
+	LD2	r6,  r7,  PT_r6
+	LD2	r8,  r9,  PT_r8
+	LD2	r10, r11, PT_r10
+.endm
+
+
+/*------------------------------------------------------------------------*/
+.macro INTERRUPT_EPILOGUE
+
+	; INPUT: r0 has STAT32 of calling context
+	; INPUT: Z flag set if returning to K mode
+
+	; _SOFT clobbers r10 restored by _HARD hence the order
+
+	__RESTORE_REGFILE_SOFT
+
+#ifdef CONFIG_ARC_IRQ_NO_AUTOSAVE
+	__RESTORE_REGFILE_HARD
+
+	; SP points to PC/STAT32: hw restores them despite NO_AUTOSAVE
+	add	sp, sp, SZ_PT_REGS - 8
+#else
+	add	sp, sp, PT_r0
+#endif
+
+.endm
+
+/*------------------------------------------------------------------------*/
+.macro EXCEPTION_EPILOGUE
+
+	; INPUT: r0 has STAT32 of calling context
+
+	btst	r0, STATUS_U_BIT	; Z flag set if K, used in restoring SP
+
+	ld	r10, [sp, PT_bta]
+	sr	r10, [erbta]
+
+	LD2	r10, r11, PT_ret
+	sr	r10, [eret]
+	sr	r11, [erstatus]
+
+	__RESTORE_REGFILE_SOFT
+	__RESTORE_REGFILE_HARD
+
+	add	sp, sp, SZ_PT_REGS
+.endm
+
+.macro FAKE_RET_FROM_EXCPN
+	lr      r9, [status32]
+	bclr    r9, r9, STATUS_AE_BIT
+	bset    r9, r9, STATUS_IE_BIT
+	kflag   r9
+.endm
+
+/* Get thread_info of "current" tsk */
+.macro GET_CURR_THR_INFO_FROM_SP  reg
+	bmskn \reg, sp, THREAD_SHIFT - 1
+.endm
+
+/* Get CPU-ID of this core */
+.macro  GET_CPU_ID  reg
+	lr  \reg, [identity]
+	xbfu \reg, \reg, 0xE8	/* 00111    01000 */
+				/* M = 8-1  N = 8 */
+.endm
+
+.macro SAVE_ABI_CALLEE_REGS
+	push	r13
+	push	r14
+	push	r15
+	push	r16
+	push	r17
+	push	r18
+	push	r19
+	push	r20
+	push	r21
+	push	r22
+	push	r23
+	push	r24
+	push	r25
+.endm
+
+.macro RESTORE_ABI_CALLEE_REGS
+	pop	r25
+	pop	r24
+	pop	r23
+	pop	r22
+	pop	r21
+	pop	r20
+	pop	r19
+	pop	r18
+	pop	r17
+	pop	r16
+	pop	r15
+	pop	r14
+	pop	r13
+.endm
+
+#endif
diff --git a/arch/arc/include/asm/entry-compact.h b/arch/arc/include/asm/entry-compact.h
new file mode 100644
index 000000000..00946fe04
--- /dev/null
+++ b/arch/arc/include/asm/entry-compact.h
@@ -0,0 +1,387 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * 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
+ *  its 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 separate ld/add instn
+ *
+ * Amit Bhor, Sameer Dhavale: Codito Technologies 2004
+ */
+
+#ifndef __ASM_ARC_ENTRY_COMPACT_H
+#define __ASM_ARC_ENTRY_COMPACT_H
+
+#include <asm/asm-offsets.h>
+#include <asm/irqflags-compact.h>
+#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]
+ */
+
+.macro PUSHAX aux
+	lr	r9, [\aux]
+	push	r9
+.endm
+
+.macro POPAX aux
+	pop	r9
+	sr	r9, [\aux]
+.endm
+
+.macro  SAVE_R0_TO_R12
+	push	r0
+	push	r1
+	push	r2
+	push	r3
+	push	r4
+	push	r5
+	push	r6
+	push	r7
+	push	r8
+	push	r9
+	push	r10
+	push	r11
+	push	r12
+.endm
+
+.macro RESTORE_R12_TO_R0
+	pop	r12
+	pop	r11
+	pop	r10
+	pop	r9
+	pop	r8
+	pop	r7
+	pop	r6
+	pop	r5
+	pop	r4
+	pop	r3
+	pop	r2
+	pop	r1
+	pop	r0
+.endm
+
+.macro SAVE_ABI_CALLEE_REGS
+	push	r13
+	push	r14
+	push	r15
+	push	r16
+	push	r17
+	push	r18
+	push	r19
+	push	r20
+	push	r21
+	push	r22
+	push	r23
+	push	r24
+	push	r25
+.endm
+
+.macro RESTORE_ABI_CALLEE_REGS
+	pop	r25
+	pop	r24
+	pop	r23
+	pop	r22
+	pop	r21
+	pop	r20
+	pop	r19
+	pop	r18
+	pop	r17
+	pop	r16
+	pop	r15
+	pop	r14
+	pop	r13
+.endm
+
+/*--------------------------------------------------------------
+ * Switch to Kernel Mode stack if SP points to User Mode stack
+ *
+ * Entry   : r9 contains pre-IRQ/exception/trap status32
+ * Exit    : SP set to K mode stack
+ *           SP at the time of entry (K/U) saved @ pt_regs->sp
+ * 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
+	 * That 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 scenario
+	 * instead of shouting around
+	 * 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
+
+    /*------Intr/Ecxp happened in kernel mode, SP already setup ------ */
+	/* save it nevertheless @ pt_regs->sp for uniformity */
+
+	b.d	66f
+	st	sp, [sp, PT_sp - SZ_PT_REGS]
+
+88: /*------Intr/Ecxp happened in user mode, "switch" stack ------ */
+
+	GET_CURR_TASK_ON_CPU   r9
+
+	/* With current tsk in r9, get its kernel mode stack base */
+	GET_TSK_STACK_BASE  r9, r9
+
+	/* save U mode SP @ pt_regs->sp */
+	st	sp, [r9, PT_sp - SZ_PT_REGS]
+
+	/* final SP switch */
+	mov	sp, r9
+66:
+.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
+
+	lr	r9, [status32]
+	bclr	r9, r9, STATUS_AE_BIT
+	or	r9, r9, (STATUS_E1_MASK|STATUS_E2_MASK)
+	sr	r9, [erstatus]
+	mov	r9, 55f
+	sr	r9, [eret]
+	rtie
+55:
+.endm
+
+/*--------------------------------------------------------------
+ * For early Exception/ISR 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 pt_regs.
+ *-------------------------------------------------------------*/
+.macro PROLOG_FREEUP_REG	reg, mem
+	st  \reg, [\mem]
+.endm
+
+.macro PROLOG_RESTORE_REG	reg, mem
+	ld  \reg, [\mem]
+.endm
+
+/*--------------------------------------------------------------
+ * Exception Entry prologue
+ * -Switches stack to K mode (if not already)
+ * -Saves the register file
+ *
+ * After this it is safe to call the "C" handlers
+ *-------------------------------------------------------------*/
+.macro EXCEPTION_PROLOGUE_KEEP_AE
+
+	/* Need at least 1 reg to code the early exception prologue */
+	PROLOG_FREEUP_REG r9, @ex_saved_reg1
+
+	/* U/K mode at time of exception (stack not switched if already K) */
+	lr  r9, [erstatus]
+
+	/* ARC700 doesn't provide auto-stack switching */
+	SWITCH_TO_KERNEL_STK
+
+	st.a	r0, [sp, -8]    /* orig_r0 needed for syscall (skip ECR slot) */
+	sub	sp, sp, 4	/* skip pt_regs->sp, already saved above */
+
+	/* Restore r9 used to code the early prologue */
+	PROLOG_RESTORE_REG  r9, @ex_saved_reg1
+
+	/* now we are ready to save the regfile */
+	SAVE_R0_TO_R12
+	PUSH	gp
+	PUSH	fp
+	PUSH	blink
+	PUSHAX	eret
+	PUSHAX	erstatus
+	PUSH	lp_count
+	PUSHAX	lp_end
+	PUSHAX	lp_start
+	PUSHAX	erbta
+
+	lr	r10, [ecr]
+	st      r10, [sp, PT_event]
+
+#ifdef CONFIG_ARC_CURR_IN_REG
+	/* gp already saved on stack: now load with "current" */
+	GET_CURR_TASK_ON_CPU   gp
+#endif
+	; OUTPUT: r10 has ECR expected by EV_Trap
+.endm
+
+.macro EXCEPTION_PROLOGUE
+
+	EXCEPTION_PROLOGUE_KEEP_AE	; return ECR in r10
+
+	lr  r0, [efa]
+	mov r1, sp
+
+	FAKE_RET_FROM_EXCPN		; clobbers 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 deferred
+ * by hardware and that is not good.
+ *-------------------------------------------------------------*/
+.macro EXCEPTION_EPILOGUE
+
+	POPAX	erbta
+	POPAX	lp_start
+	POPAX	lp_end
+
+	POP	r9
+	mov	lp_count, r9	;LD to lp_count is not allowed
+
+	POPAX	erstatus
+	POPAX	eret
+	POP	blink
+	POP	fp
+	POP	gp
+	RESTORE_R12_TO_R0
+
+	ld  sp, [sp] /* restore original sp */
+	/* orig_r0, ECR skipped automatically */
+.endm
+
+/* Dummy ECR values for Interrupts */
+#define event_IRQ1		0x0031abcd
+#define event_IRQ2		0x0032abcd
+
+.macro INTERRUPT_PROLOGUE  LVL
+
+	/* free up r9 as scratchpad */
+	PROLOG_FREEUP_REG r9, @int\LVL\()_saved_reg
+
+	/* Which mode (user/kernel) was the system in when intr occurred */
+	lr  r9, [status32_l\LVL\()]
+
+	SWITCH_TO_KERNEL_STK
+
+
+	st.a	0x003\LVL\()abcd, [sp, -4]	/* Dummy ECR */
+	sub	sp, sp, 8	    /* skip orig_r0 (not needed)
+				       skip pt_regs->sp, already saved above */
+
+	/* Restore r9 used to code the early prologue */
+	PROLOG_RESTORE_REG  r9, @int\LVL\()_saved_reg
+
+	SAVE_R0_TO_R12
+	PUSH	gp
+	PUSH	fp
+	PUSH	blink
+	PUSH	ilink\LVL\()
+	PUSHAX	status32_l\LVL\()
+	PUSH	lp_count
+	PUSHAX	lp_end
+	PUSHAX	lp_start
+	PUSHAX	bta_l\LVL\()
+
+#ifdef CONFIG_ARC_CURR_IN_REG
+	/* gp already saved on stack: now load with "current" */
+	GET_CURR_TASK_ON_CPU   gp
+#endif
+.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 deferred
+ * by hardware and that is not good.
+ *-------------------------------------------------------------*/
+.macro INTERRUPT_EPILOGUE  LVL
+
+	POPAX	bta_l\LVL\()
+	POPAX	lp_start
+	POPAX	lp_end
+
+	POP	r9
+	mov	lp_count, r9	;LD to lp_count is not allowed
+
+	POPAX	status32_l\LVL\()
+	POP	ilink\LVL\()
+	POP	blink
+	POP	fp
+	POP	gp
+	RESTORE_R12_TO_R0
+
+	ld  sp, [sp] /* restore original sp; orig_r0, ECR skipped implicitly */
+.endm
+
+/* Get thread_info of "current" tsk */
+.macro GET_CURR_THR_INFO_FROM_SP  reg
+	bic \reg, sp, (THREAD_SIZE - 1)
+.endm
+
+/* Get CPU-ID of this core */
+.macro  GET_CPU_ID  reg
+	lr  \reg, [identity]
+	lsr \reg, \reg, 8
+	bmsk \reg, \reg, 7
+.endm
+
+#endif  /* __ASM_ARC_ENTRY_COMPACT_H */
diff --git a/arch/arc/include/asm/entry.h b/arch/arc/include/asm/entry.h
new file mode 100644
index 000000000..f453af251
--- /dev/null
+++ b/arch/arc/include/asm/entry.h
@@ -0,0 +1,168 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#ifndef __ASM_ARC_ENTRY_H
+#define __ASM_ARC_ENTRY_H
+
+#include <asm/unistd.h>		/* For NR_syscalls definition */
+#include <asm/arcregs.h>
+#include <asm/ptrace.h>
+#include <asm/processor.h>	/* For VMALLOC_START */
+#include <asm/mmu.h>
+
+#ifdef __ASSEMBLER__
+
+#ifdef CONFIG_ISA_ARCOMPACT
+#include <asm/entry-compact.h>	/* ISA specific bits */
+#else
+#include <asm/entry-arcv2.h>
+#endif
+
+/*
+ * save user mode callee regs as struct callee_regs
+ *  - needed by fork/do_signal/unaligned-access-emulation.
+ */
+.macro SAVE_CALLEE_SAVED_USER
+	SAVE_ABI_CALLEE_REGS
+.endm
+
+/*
+ * restore user mode callee regs as struct callee_regs
+ *  - could have been changed by ptrace tracer or unaligned-access fixup
+ */
+.macro RESTORE_CALLEE_SAVED_USER
+	RESTORE_ABI_CALLEE_REGS
+.endm
+
+/*
+ * save/restore kernel mode callee regs at the time of context switch
+ */
+.macro SAVE_CALLEE_SAVED_KERNEL
+	SAVE_ABI_CALLEE_REGS
+.endm
+
+.macro RESTORE_CALLEE_SAVED_KERNEL
+	RESTORE_ABI_CALLEE_REGS
+.endm
+
+/*--------------------------------------------------------------
+ * Super FAST Restore callee saved regs by simply re-adjusting SP
+ *-------------------------------------------------------------*/
+.macro DISCARD_CALLEE_SAVED_USER
+	add     sp, sp, SZ_CALLEE_REGS
+.endm
+
+/*-------------------------------------------------------------
+ * given a tsk struct, get to the base of its 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
+
+.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
+
+#ifdef CONFIG_SMP
+
+/*
+ * Retrieve the current running task on this CPU
+ *  - loads it from backing _current_task[] (and can't use the
+ *    caching reg for 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 gp, \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 gp, \tsk
+#endif
+.endm
+
+#endif /* SMP / UNI */
+
+/*
+ * Get the ptr to some field of Current Task at @off in task struct
+ *  - Uses current task cached in reg if enabled
+ */
+#ifdef CONFIG_ARC_CURR_IN_REG
+
+.macro GET_CURR_TASK_FIELD_PTR  off,  reg
+	add \reg, gp, \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 */
+
+#else	/* !__ASSEMBLER__ */
+
+extern void do_signal(struct pt_regs *);
+extern void do_notify_resume(struct pt_regs *);
+extern int do_privilege_fault(unsigned long, struct pt_regs *);
+extern int do_extension_fault(unsigned long, struct pt_regs *);
+extern int insterror_is_error(unsigned long, struct pt_regs *);
+extern int do_memory_error(unsigned long, struct pt_regs *);
+extern int trap_is_brkpt(unsigned long, struct pt_regs *);
+extern int do_misaligned_error(unsigned long, struct pt_regs *);
+extern int do_trap5_error(unsigned long, struct pt_regs *);
+extern int do_misaligned_access(unsigned long, struct pt_regs *, struct callee_regs *);
+extern void do_machine_check_fault(unsigned long, struct pt_regs *);
+extern void do_non_swi_trap(unsigned long, struct pt_regs *);
+extern void do_insterror_or_kprobe(unsigned long, struct pt_regs *);
+extern void do_page_fault(unsigned long, struct pt_regs *);
+
+#endif
+
+#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 000000000..6134175d9
--- /dev/null
+++ b/arch/arc/include/asm/exec.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#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/fpu.h b/arch/arc/include/asm/fpu.h
new file mode 100644
index 000000000..006bcf88a
--- /dev/null
+++ b/arch/arc/include/asm/fpu.h
@@ -0,0 +1,57 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2020 Synopsys, Inc. (www.synopsys.com)
+ *
+ */
+
+#ifndef _ASM_ARC_FPU_H
+#define _ASM_ARC_FPU_H
+
+#ifdef CONFIG_ARC_FPU_SAVE_RESTORE
+
+#include <asm/ptrace.h>
+
+#ifdef CONFIG_ISA_ARCOMPACT
+
+/* These DPFP regs need to be saved/restored across ctx-sw */
+struct arc_fpu {
+	struct {
+		unsigned int l, h;
+	} aux_dpfp[2];
+};
+
+#define fpu_init_task(regs)
+
+#else
+
+/*
+ * ARCv2 FPU Control aux register
+ *   - bits to enable Traps on Exceptions
+ *   - Rounding mode
+ *
+ * ARCv2 FPU Status aux register
+ *   - FPU exceptions flags (Inv, Div-by-Zero, overflow, underflow, inexact)
+ *   - Flag Write Enable to clear flags explicitly (vs. by fpu instructions
+ *     only
+ */
+
+struct arc_fpu {
+	unsigned int ctrl, status;
+};
+
+extern void fpu_init_task(struct pt_regs *regs);
+
+#endif	/* !CONFIG_ISA_ARCOMPACT */
+
+struct task_struct;
+
+extern void fpu_save_restore(struct task_struct *p, struct task_struct *n);
+
+#else	/* !CONFIG_ARC_FPU_SAVE_RESTORE */
+
+#define fpu_save_restore(p, n)
+#define fpu_init_task(regs)
+
+#endif	/* CONFIG_ARC_FPU_SAVE_RESTORE */
+
+#endif	/* _ASM_ARC_FPU_H */
diff --git a/arch/arc/include/asm/futex.h b/arch/arc/include/asm/futex.h
new file mode 100644
index 000000000..607d1c16d
--- /dev/null
+++ b/arch/arc/include/asm/futex.h
@@ -0,0 +1,169 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * 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>
+
+#ifdef CONFIG_ARC_HAS_LLSC
+
+#define __futex_atomic_op(insn, ret, oldval, uaddr, oparg)\
+							\
+	smp_mb();					\
+	__asm__ __volatile__(				\
+	"1:	llock	%1, [%2]		\n"	\
+		insn				"\n"	\
+	"2:	scond	%0, [%2]		\n"	\
+	"	bnz	1b			\n"	\
+	"	mov %0, 0			\n"	\
+	"3:					\n"	\
+	"	.section .fixup,\"ax\"		\n"	\
+	"	.align  4			\n"	\
+	"4:	mov %0, %4			\n"	\
+	"	j   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");				\
+	smp_mb()					\
+
+#else	/* !CONFIG_ARC_HAS_LLSC */
+
+#define __futex_atomic_op(insn, ret, oldval, uaddr, oparg)\
+							\
+	smp_mb();					\
+	__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"	\
+	"	j   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");				\
+	smp_mb()					\
+
+#endif
+
+static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval,
+		u32 __user *uaddr)
+{
+	int oldval = 0, ret;
+
+	if (!access_ok(uaddr, sizeof(u32)))
+		return -EFAULT;
+
+#ifndef CONFIG_ARC_HAS_LLSC
+	preempt_disable();	/* to guarantee atomic r-m-w of futex op */
+#endif
+
+	switch (op) {
+	case FUTEX_OP_SET:
+		__futex_atomic_op("mov %0, %3", ret, oldval, uaddr, oparg);
+		break;
+	case FUTEX_OP_ADD:
+		/* oldval = *uaddr; *uaddr += oparg ; ret = *uaddr */
+		__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;
+	}
+
+#ifndef CONFIG_ARC_HAS_LLSC
+	preempt_enable();
+#endif
+
+	if (!ret)
+		*oval = oldval;
+
+	return ret;
+}
+
+/*
+ * cmpxchg of futex (pagefaults disabled by caller)
+ * Return 0 for success, -EFAULT otherwise
+ */
+static inline int
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 expval,
+			      u32 newval)
+{
+	int ret = 0;
+	u32 existval;
+
+	if (!access_ok(uaddr, sizeof(u32)))
+		return -EFAULT;
+
+#ifndef CONFIG_ARC_HAS_LLSC
+	preempt_disable();	/* to guarantee atomic r-m-w of futex op */
+#endif
+	smp_mb();
+
+	__asm__ __volatile__(
+#ifdef CONFIG_ARC_HAS_LLSC
+	"1:	llock	%1, [%4]		\n"
+	"	brne	%1, %2, 3f		\n"
+	"2:	scond	%3, [%4]		\n"
+	"	bnz	1b			\n"
+#else
+	"1:	ld	%1, [%4]		\n"
+	"	brne	%1, %2, 3f		\n"
+	"2:	st	%3, [%4]		\n"
+#endif
+	"3:	\n"
+	"	.section .fixup,\"ax\"	\n"
+	"4:	mov %0, %5	\n"
+	"	j   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"(existval)
+	: "r"(expval), "r"(newval), "r"(uaddr), "ir"(-EFAULT)
+	: "cc", "memory");
+
+	smp_mb();
+
+#ifndef CONFIG_ARC_HAS_LLSC
+	preempt_enable();
+#endif
+	*uval = existval;
+	return ret;
+}
+
+#endif
diff --git a/arch/arc/include/asm/highmem.h b/arch/arc/include/asm/highmem.h
new file mode 100644
index 000000000..a6b8e2c35
--- /dev/null
+++ b/arch/arc/include/asm/highmem.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2015 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#ifndef _ASM_HIGHMEM_H
+#define _ASM_HIGHMEM_H
+
+#ifdef CONFIG_HIGHMEM
+
+#include <uapi/asm/page.h>
+#include <asm/kmap_size.h>
+
+#define FIXMAP_SIZE		PGDIR_SIZE
+#define PKMAP_SIZE		PGDIR_SIZE
+
+/* start after vmalloc area */
+#define FIXMAP_BASE		(PAGE_OFFSET - FIXMAP_SIZE - PKMAP_SIZE)
+
+#define FIX_KMAP_SLOTS		(KM_MAX_IDX * NR_CPUS)
+#define FIX_KMAP_BEGIN		(0UL)
+#define FIX_KMAP_END		((FIX_KMAP_BEGIN + FIX_KMAP_SLOTS) - 1)
+
+#define FIXADDR_TOP		(FIXMAP_BASE + (FIX_KMAP_END << PAGE_SHIFT))
+
+/*
+ * This should be converted to the asm-generic version, but of course this
+ * is needlessly different from all other architectures. Sigh - tglx
+ */
+#define __fix_to_virt(x)	(FIXADDR_TOP - ((x) << PAGE_SHIFT))
+#define __virt_to_fix(x)	(((FIXADDR_TOP - ((x) & PAGE_MASK))) >> PAGE_SHIFT)
+
+/* start after fixmap area */
+#define PKMAP_BASE		(FIXMAP_BASE + FIXMAP_SIZE)
+#define LAST_PKMAP		(PKMAP_SIZE >> PAGE_SHIFT)
+#define LAST_PKMAP_MASK		(LAST_PKMAP - 1)
+#define PKMAP_ADDR(nr)		(PKMAP_BASE + ((nr) << PAGE_SHIFT))
+#define PKMAP_NR(virt)		(((virt) - PKMAP_BASE) >> PAGE_SHIFT)
+
+#include <asm/cacheflush.h>
+
+extern void kmap_init(void);
+
+#define arch_kmap_local_post_unmap(vaddr)			\
+	local_flush_tlb_kernel_range(vaddr, vaddr + PAGE_SIZE)
+
+static inline void flush_cache_kmaps(void)
+{
+	flush_cache_all();
+}
+#endif
+
+#endif
diff --git a/arch/arc/include/asm/hugepage.h b/arch/arc/include/asm/hugepage.h
new file mode 100644
index 000000000..7765dc105
--- /dev/null
+++ b/arch/arc/include/asm/hugepage.h
@@ -0,0 +1,72 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2013-15 Synopsys, Inc. (www.synopsys.com)
+ */
+
+
+#ifndef _ASM_ARC_HUGEPAGE_H
+#define _ASM_ARC_HUGEPAGE_H
+
+#include <linux/types.h>
+#include <asm-generic/pgtable-nopmd.h>
+
+/*
+ * Hugetlb definitions.
+ */
+#define HPAGE_SHIFT		PMD_SHIFT
+#define HPAGE_SIZE		(_AC(1, UL) << HPAGE_SHIFT)
+#define HPAGE_MASK		(~(HPAGE_SIZE - 1))
+
+static inline pte_t pmd_pte(pmd_t pmd)
+{
+	return __pte(pmd_val(pmd));
+}
+
+static inline pmd_t pte_pmd(pte_t pte)
+{
+	return __pmd(pte_val(pte));
+}
+
+#define pmd_wrprotect(pmd)	pte_pmd(pte_wrprotect(pmd_pte(pmd)))
+#define pmd_mkwrite_novma(pmd)	pte_pmd(pte_mkwrite_novma(pmd_pte(pmd)))
+#define pmd_mkdirty(pmd)	pte_pmd(pte_mkdirty(pmd_pte(pmd)))
+#define pmd_mkold(pmd)		pte_pmd(pte_mkold(pmd_pte(pmd)))
+#define pmd_mkyoung(pmd)	pte_pmd(pte_mkyoung(pmd_pte(pmd)))
+#define pmd_mkhuge(pmd)		pte_pmd(pte_mkhuge(pmd_pte(pmd)))
+#define pmd_mkinvalid(pmd)	pte_pmd(pte_mknotpresent(pmd_pte(pmd)))
+#define pmd_mkclean(pmd)	pte_pmd(pte_mkclean(pmd_pte(pmd)))
+
+#define pmd_write(pmd)		pte_write(pmd_pte(pmd))
+#define pmd_young(pmd)		pte_young(pmd_pte(pmd))
+#define pmd_dirty(pmd)		pte_dirty(pmd_pte(pmd))
+
+#define pmd_trans_huge(pmd)	(pmd_val(pmd) & _PAGE_HW_SZ)
+
+#define pfn_pmd(pfn, prot)	(__pmd(((pfn) << PAGE_SHIFT) | pgprot_val(prot)))
+
+static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
+{
+        /*
+         * open-coded pte_modify() with additional retaining of HW_SZ bit
+         * so that pmd_trans_huge() remains true for this PMD
+         */
+        return __pmd((pmd_val(pmd) & (_PAGE_CHG_MASK | _PAGE_HW_SZ)) | pgprot_val(newprot));
+}
+
+static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
+			      pmd_t *pmdp, pmd_t pmd)
+{
+	*pmdp = pmd;
+}
+
+extern void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr,
+				 pmd_t *pmd);
+
+#define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE
+extern void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
+				unsigned long end);
+
+/* We don't have hardware dirty/accessed bits, generic_pmdp_establish is fine.*/
+#define pmdp_establish generic_pmdp_establish
+
+#endif
diff --git a/arch/arc/include/asm/io.h b/arch/arc/include/asm/io.h
new file mode 100644
index 000000000..00171a212
--- /dev/null
+++ b/arch/arc/include/asm/io.h
@@ -0,0 +1,231 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#ifndef _ASM_ARC_IO_H
+#define _ASM_ARC_IO_H
+
+#include <linux/types.h>
+#include <asm/byteorder.h>
+#include <asm/page.h>
+#include <linux/unaligned.h>
+
+#ifdef CONFIG_ISA_ARCV2
+#include <asm/barrier.h>
+#define __iormb()		rmb()
+#define __iowmb()		wmb()
+#else
+#define __iormb()		do { } while (0)
+#define __iowmb()		do { } while (0)
+#endif
+
+extern void __iomem *ioremap(phys_addr_t paddr, unsigned long size);
+#define ioremap ioremap
+#define ioremap_prot ioremap_prot
+#define iounmap iounmap
+static inline void __iomem *ioport_map(unsigned long port, unsigned int nr)
+{
+	return (void __iomem *)port;
+}
+
+static inline void ioport_unmap(void __iomem *addr)
+{
+}
+
+/*
+ * io{read,write}{16,32}be() macros
+ */
+#define ioread16be(p)		({ u16 __v = be16_to_cpu((__force __be16)__raw_readw(p)); __iormb(); __v; })
+#define ioread32be(p)		({ u32 __v = be32_to_cpu((__force __be32)__raw_readl(p)); __iormb(); __v; })
+
+#define iowrite16be(v,p)	({ __iowmb(); __raw_writew((__force u16)cpu_to_be16(v), p); })
+#define iowrite32be(v,p)	({ __iowmb(); __raw_writel((__force u32)cpu_to_be32(v), p); })
+
+#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;
+}
+
+/*
+ * {read,write}s{b,w,l}() repeatedly access the same IO address in
+ * native endianness in 8-, 16-, 32-bit chunks {into,from} memory,
+ * @count times
+ */
+#define __raw_readsx(t,f) \
+static inline void __raw_reads##f(const volatile void __iomem *addr,	\
+				  void *ptr, unsigned int count)	\
+{									\
+	bool is_aligned = ((unsigned long)ptr % ((t) / 8)) == 0;	\
+	u##t *buf = ptr;						\
+									\
+	if (!count)							\
+		return;							\
+									\
+	/* Some ARC CPU's don't support unaligned accesses */		\
+	if (is_aligned) {						\
+		do {							\
+			u##t x = __raw_read##f(addr);			\
+			*buf++ = x;					\
+		} while (--count);					\
+	} else {							\
+		do {							\
+			u##t x = __raw_read##f(addr);			\
+			put_unaligned(x, buf++);			\
+		} while (--count);					\
+	}								\
+}
+
+#define __raw_readsb __raw_readsb
+__raw_readsx(8, b)
+#define __raw_readsw __raw_readsw
+__raw_readsx(16, w)
+#define __raw_readsl __raw_readsl
+__raw_readsx(32, l)
+
+#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");
+
+}
+
+#define __raw_writesx(t,f)						\
+static inline void __raw_writes##f(volatile void __iomem *addr, 	\
+				   const void *ptr, unsigned int count)	\
+{									\
+	bool is_aligned = ((unsigned long)ptr % ((t) / 8)) == 0;	\
+	const u##t *buf = ptr;						\
+									\
+	if (!count)							\
+		return;							\
+									\
+	/* Some ARC CPU's don't support unaligned accesses */		\
+	if (is_aligned) {						\
+		do {							\
+			__raw_write##f(*buf++, addr);			\
+		} while (--count);					\
+	} else {							\
+		do {							\
+			__raw_write##f(get_unaligned(buf++), addr);	\
+		} while (--count);					\
+	}								\
+}
+
+#define __raw_writesb __raw_writesb
+__raw_writesx(8, b)
+#define __raw_writesw __raw_writesw
+__raw_writesx(16, w)
+#define __raw_writesl __raw_writesl
+__raw_writesx(32, l)
+
+/*
+ * MMIO can also get buffered/optimized in micro-arch, so barriers needed
+ * Based on ARM model for the typical use case
+ *
+ *	<ST [DMA buffer]>
+ *	<writel MMIO "go" reg>
+ *  or:
+ *	<readl MMIO "status" reg>
+ *	<LD [DMA buffer]>
+ *
+ * http://lkml.kernel.org/r/20150622133656.GG1583@arm.com
+ */
+#define readb(c)		({ u8  __v = readb_relaxed(c); __iormb(); __v; })
+#define readw(c)		({ u16 __v = readw_relaxed(c); __iormb(); __v; })
+#define readl(c)		({ u32 __v = readl_relaxed(c); __iormb(); __v; })
+#define readsb(p,d,l)		({ __raw_readsb(p,d,l); __iormb(); })
+#define readsw(p,d,l)		({ __raw_readsw(p,d,l); __iormb(); })
+#define readsl(p,d,l)		({ __raw_readsl(p,d,l); __iormb(); })
+
+#define writeb(v,c)		({ __iowmb(); writeb_relaxed(v,c); })
+#define writew(v,c)		({ __iowmb(); writew_relaxed(v,c); })
+#define writel(v,c)		({ __iowmb(); writel_relaxed(v,c); })
+#define writesb(p,d,l)		({ __iowmb(); __raw_writesb(p,d,l); })
+#define writesw(p,d,l)		({ __iowmb(); __raw_writesw(p,d,l); })
+#define writesl(p,d,l)		({ __iowmb(); __raw_writesl(p,d,l); })
+
+/*
+ * Relaxed API for drivers which can handle barrier ordering themselves
+ *
+ * Also these are defined to perform little endian accesses.
+ * To provide the typical device register semantics of fixed endian,
+ * swap the byte order for Big Endian
+ *
+ * http://lkml.kernel.org/r/201603100845.30602.arnd@arndb.de
+ */
+#define readb_relaxed(c)	__raw_readb(c)
+#define readw_relaxed(c) ({ u16 __r = le16_to_cpu((__force __le16) \
+					__raw_readw(c)); __r; })
+#define readl_relaxed(c) ({ u32 __r = le32_to_cpu((__force __le32) \
+					__raw_readl(c)); __r; })
+
+#define writeb_relaxed(v,c)	__raw_writeb(v,c)
+#define writew_relaxed(v,c)	__raw_writew((__force u16) cpu_to_le16(v),c)
+#define writel_relaxed(v,c)	__raw_writel((__force u32) cpu_to_le32(v),c)
+
+#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 000000000..9cd79263a
--- /dev/null
+++ b/arch/arc/include/asm/irq.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#ifndef __ASM_ARC_IRQ_H
+#define __ASM_ARC_IRQ_H
+
+/*
+ * ARCv2 can support 240 interrupts in the core interrupts controllers and
+ * 128 interrupts in IDU. Thus 512 virtual IRQs must be enough for most
+ * configurations of boards.
+ * This doesn't affect ARCompact, but we change it to same value
+ */
+#define NR_IRQS		512
+
+/* Platform Independent IRQs */
+#ifdef CONFIG_ISA_ARCV2
+#define IPI_IRQ		19
+#define SOFTIRQ_IRQ	21
+#define FIRST_EXT_IRQ	24
+#endif
+
+#include <linux/interrupt.h>
+#include <asm-generic/irq.h>
+
+extern void arc_init_IRQ(void);
+extern void arch_do_IRQ(unsigned int, struct pt_regs *);
+
+#endif
diff --git a/arch/arc/include/asm/irqflags-arcv2.h b/arch/arc/include/asm/irqflags-arcv2.h
new file mode 100644
index 000000000..30aea562f
--- /dev/null
+++ b/arch/arc/include/asm/irqflags-arcv2.h
@@ -0,0 +1,175 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#ifndef __ASM_IRQFLAGS_ARCV2_H
+#define __ASM_IRQFLAGS_ARCV2_H
+
+#include <asm/arcregs.h>
+
+/* status32 Bits */
+#define STATUS_AD_BIT	19   /* Disable Align chk: core supports non-aligned */
+#define STATUS_IE_BIT	31
+
+#define STATUS_AD_MASK		(1<<STATUS_AD_BIT)
+#define STATUS_IE_MASK		(1<<STATUS_IE_BIT)
+
+/* status32 Bits as encoded/expected by CLRI/SETI */
+#define CLRI_STATUS_IE_BIT	4
+
+#define CLRI_STATUS_E_MASK	0xF
+#define CLRI_STATUS_IE_MASK	(1 << CLRI_STATUS_IE_BIT)
+
+#define AUX_USER_SP		0x00D
+#define AUX_IRQ_CTRL		0x00E
+#define AUX_IRQ_ACT		0x043	/* Active Intr across all levels */
+#define AUX_IRQ_LVL_PEND	0x200	/* Pending Intr across all levels */
+#define AUX_IRQ_HINT		0x201	/* For generating Soft Interrupts */
+#define AUX_IRQ_PRIORITY	0x206
+#define ICAUSE			0x40a
+#define AUX_IRQ_SELECT		0x40b
+#define AUX_IRQ_ENABLE		0x40c
+
+/* Was Intr taken in User Mode */
+#define AUX_IRQ_ACT_BIT_U	31
+
+/*
+ * Hardware supports 16 priorities (0 highest, 15 lowest)
+ * Linux by default runs at 1, priority 0 reserved for NMI style interrupts
+ */
+#define ARCV2_IRQ_DEF_PRIO	1
+
+/* seed value for status register */
+#ifdef CONFIG_ARC_USE_UNALIGNED_MEM_ACCESS
+#define __AD_ENB	STATUS_AD_MASK
+#else
+#define __AD_ENB	0
+#endif
+
+#define ISA_INIT_STATUS_BITS	(STATUS_IE_MASK | __AD_ENB | \
+					(ARCV2_IRQ_DEF_PRIO << 1))
+
+#ifndef __ASSEMBLER__
+
+/*
+ * Save IRQ state and disable IRQs
+ */
+static inline long arch_local_irq_save(void)
+{
+	unsigned long flags;
+
+	__asm__ __volatile__("	clri %0	\n" : "=r" (flags) : : "memory");
+
+	return flags;
+}
+
+/*
+ * restore saved IRQ state
+ */
+static inline void arch_local_irq_restore(unsigned long flags)
+{
+	__asm__ __volatile__("	seti %0	\n" : : "r" (flags) : "memory");
+}
+
+/*
+ * Unconditionally Enable IRQs
+ */
+static inline void arch_local_irq_enable(void)
+{
+	unsigned int irqact = read_aux_reg(AUX_IRQ_ACT);
+
+	if (irqact & 0xffff)
+		write_aux_reg(AUX_IRQ_ACT, irqact & ~0xffff);
+
+	__asm__ __volatile__("	seti	\n" : : : "memory");
+}
+
+/*
+ * Unconditionally Disable IRQs
+ */
+static inline void arch_local_irq_disable(void)
+{
+	__asm__ __volatile__("	clri	\n" : : : "memory");
+}
+
+/*
+ * save IRQ state
+ */
+static inline long arch_local_save_flags(void)
+{
+	unsigned long temp;
+
+	__asm__ __volatile__(
+	"	lr  %0, [status32]	\n"
+	: "=&r"(temp)
+	:
+	: "memory");
+
+	/* To be compatible with irq_save()/irq_restore()
+	 * encode the irq bits as expected by CLRI/SETI
+	 * (this was needed to make CONFIG_TRACE_IRQFLAGS work)
+	 */
+	temp = (1 << 5) |
+		((!!(temp & STATUS_IE_MASK)) << CLRI_STATUS_IE_BIT) |
+		((temp >> 1) & CLRI_STATUS_E_MASK);
+	return temp;
+}
+
+/*
+ * Query IRQ state
+ */
+static inline int arch_irqs_disabled_flags(unsigned long flags)
+{
+	return !(flags & CLRI_STATUS_IE_MASK);
+}
+
+static inline int arch_irqs_disabled(void)
+{
+	return arch_irqs_disabled_flags(arch_local_save_flags());
+}
+
+static inline void arc_softirq_trigger(int irq)
+{
+	write_aux_reg(AUX_IRQ_HINT, irq);
+}
+
+static inline void arc_softirq_clear(int irq)
+{
+	write_aux_reg(AUX_IRQ_HINT, 0);
+}
+
+#else
+
+#ifdef CONFIG_TRACE_IRQFLAGS
+
+.macro TRACE_ASM_IRQ_DISABLE
+	bl	trace_hardirqs_off
+.endm
+
+.macro TRACE_ASM_IRQ_ENABLE
+	bl	trace_hardirqs_on
+.endm
+
+#else
+
+.macro TRACE_ASM_IRQ_DISABLE
+.endm
+
+.macro TRACE_ASM_IRQ_ENABLE
+.endm
+
+#endif
+.macro IRQ_DISABLE  scratch
+	clri
+	TRACE_ASM_IRQ_DISABLE
+.endm
+
+.macro IRQ_ENABLE  scratch
+	TRACE_ASM_IRQ_ENABLE
+	seti
+.endm
+
+#endif	/* __ASSEMBLER__ */
+
+#endif
diff --git a/arch/arc/include/asm/irqflags-compact.h b/arch/arc/include/asm/irqflags-compact.h
new file mode 100644
index 000000000..85c2f6bcd
--- /dev/null
+++ b/arch/arc/include/asm/irqflags-compact.h
@@ -0,0 +1,201 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#ifndef __ASM_IRQFLAGS_ARCOMPACT_H
+#define __ASM_IRQFLAGS_ARCOMPACT_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)
+*/
+
+#include <asm/arcregs.h>
+
+/* status32 Reg bits related to Interrupt Handling */
+#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_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_IE_MASK		(STATUS_E1_MASK | STATUS_E2_MASK)
+
+/* Other Interrupt Handling related Aux regs */
+#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
+
+#define ISA_INIT_STATUS_BITS	STATUS_IE_MASK
+
+#ifndef __ASSEMBLER__
+
+/******************************************************************
+ * IRQ Control Macros
+ *
+ * All of them have "memory" clobber (compiler barrier) which is needed to
+ * ensure that LD/ST requiring irq safety (R-M-W when LLSC is not available)
+ * are redone after IRQs are re-enabled (and gcc doesn't reuse stale register)
+ *
+ * Noted at the time of Abilis Timer List corruption
+ *
+ * Orig Bug + Rejected solution:
+ * https://lore.kernel.org/lkml/1364553218-31255-1-git-send-email-vgupta@synopsys.com
+ *
+ * Reasoning:
+ * https://lore.kernel.org/lkml/CA+55aFyFWjpSVQM6M266tKrG_ZXJzZ-nYejpmXYQXbrr42mGPQ@mail.gmail.com
+ *
+ ******************************************************************/
+
+/*
+ * 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))
+	: "memory", "cc");
+
+	return flags;
+}
+
+/*
+ * restore saved IRQ state
+ */
+static inline void arch_local_irq_restore(unsigned long flags)
+{
+
+	__asm__ __volatile__(
+	"	flag %0			\n"
+	:
+	: "r"(flags)
+	: "memory");
+}
+
+/*
+ * Unconditionally Enable IRQs
+ */
+#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS
+extern void arch_local_irq_enable(void);
+#else
+static inline void arch_local_irq_enable(void)
+{
+	unsigned long temp;
+
+	__asm__ __volatile__(
+	"	lr   %0, [status32]	\n"
+	"	or   %0, %0, %1		\n"
+	"	flag %0			\n"
+	: "=&r"(temp)
+	: "n"((STATUS_E1_MASK | STATUS_E2_MASK))
+	: "cc", "memory");
+}
+#endif
+
+/*
+ * 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))
+	: "memory");
+}
+
+/*
+ * save IRQ state
+ */
+static inline long arch_local_save_flags(void)
+{
+	unsigned long temp;
+
+	__asm__ __volatile__(
+	"	lr  %0, [status32]	\n"
+	: "=&r"(temp)
+	:
+	: "memory");
+
+	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());
+}
+
+#else
+
+#ifdef CONFIG_TRACE_IRQFLAGS
+
+.macro TRACE_ASM_IRQ_DISABLE
+	bl	trace_hardirqs_off
+.endm
+
+.macro TRACE_ASM_IRQ_ENABLE
+	bl	trace_hardirqs_on
+.endm
+
+#else
+
+.macro TRACE_ASM_IRQ_DISABLE
+.endm
+
+.macro TRACE_ASM_IRQ_ENABLE
+.endm
+
+#endif
+
+.macro IRQ_DISABLE  scratch
+	lr	\scratch, [status32]
+	bic	\scratch, \scratch, (STATUS_E1_MASK | STATUS_E2_MASK)
+	flag	\scratch
+	TRACE_ASM_IRQ_DISABLE
+.endm
+
+.macro IRQ_ENABLE  scratch
+	TRACE_ASM_IRQ_ENABLE
+	lr	\scratch, [status32]
+	or	\scratch, \scratch, (STATUS_E1_MASK | STATUS_E2_MASK)
+	flag	\scratch
+.endm
+
+#endif	/* __ASSEMBLER__ */
+
+#endif
diff --git a/arch/arc/include/asm/irqflags.h b/arch/arc/include/asm/irqflags.h
new file mode 100644
index 000000000..edf201a69
--- /dev/null
+++ b/arch/arc/include/asm/irqflags.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#ifndef __ASM_ARC_IRQFLAGS_H
+#define __ASM_ARC_IRQFLAGS_H
+
+#ifdef CONFIG_ISA_ARCOMPACT
+#include <asm/irqflags-compact.h>
+#else
+#include <asm/irqflags-arcv2.h>
+#endif
+
+#endif
diff --git a/arch/arc/include/asm/jump_label.h b/arch/arc/include/asm/jump_label.h
new file mode 100644
index 000000000..66ead7578
--- /dev/null
+++ b/arch/arc/include/asm/jump_label.h
@@ -0,0 +1,72 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_ARC_JUMP_LABEL_H
+#define _ASM_ARC_JUMP_LABEL_H
+
+#ifndef __ASSEMBLER__
+
+#include <linux/stringify.h>
+#include <linux/types.h>
+
+#define JUMP_LABEL_NOP_SIZE 4
+
+/*
+ * NOTE about '.balign 4':
+ *
+ * To make atomic update of patched instruction available we need to guarantee
+ * that this instruction doesn't cross L1 cache line boundary.
+ *
+ * As of today we simply align instruction which can be patched by 4 byte using
+ * ".balign 4" directive. In that case patched instruction is aligned with one
+ * 16-bit NOP_S if this is required.
+ * However 'align by 4' directive is much stricter than it actually required.
+ * It's enough that our 32-bit instruction don't cross L1 cache line boundary /
+ * L1 I$ fetch block boundary which can be achieved by using
+ * ".bundle_align_mode" assembler directive. That will save us from adding
+ * useless NOP_S padding in most of the cases.
+ *
+ * TODO: switch to ".bundle_align_mode" directive using whin it will be
+ * supported by ARC toolchain.
+ */
+
+static __always_inline bool arch_static_branch(struct static_key *key,
+					       bool branch)
+{
+	asm goto(".balign "__stringify(JUMP_LABEL_NOP_SIZE)"		\n"
+		 "1:							\n"
+		 "nop							\n"
+		 ".pushsection __jump_table, \"aw\"			\n"
+		 ".word 1b, %l[l_yes], %c0				\n"
+		 ".popsection						\n"
+		 : : "i" (&((char *)key)[branch]) : : l_yes);
+
+	return false;
+l_yes:
+	return true;
+}
+
+static __always_inline bool arch_static_branch_jump(struct static_key *key,
+						    bool branch)
+{
+	asm goto(".balign "__stringify(JUMP_LABEL_NOP_SIZE)"		\n"
+		 "1:							\n"
+		 "b %l[l_yes]						\n"
+		 ".pushsection __jump_table, \"aw\"			\n"
+		 ".word 1b, %l[l_yes], %c0				\n"
+		 ".popsection						\n"
+		 : : "i" (&((char *)key)[branch]) : : l_yes);
+
+	return false;
+l_yes:
+	return true;
+}
+
+typedef u32 jump_label_t;
+
+struct jump_entry {
+	jump_label_t code;
+	jump_label_t target;
+	jump_label_t key;
+};
+
+#endif  /* __ASSEMBLER__ */
+#endif
diff --git a/arch/arc/include/asm/kdebug.h b/arch/arc/include/asm/kdebug.h
new file mode 100644
index 000000000..f92049d1d
--- /dev/null
+++ b/arch/arc/include/asm/kdebug.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#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 000000000..f9f71b909
--- /dev/null
+++ b/arch/arc/include/asm/kgdb.h
@@ -0,0 +1,60 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * kgdb support for ARC
+ *
+ * Copyright (C) 2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#ifndef __ARC_KGDB_H__
+#define __ARC_KGDB_H__
+
+#ifdef CONFIG_KGDB
+
+#include <asm/ptrace.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		87
+
+#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);
+
+/* This is the numbering of registers according to the GDB. See GDB's
+ * arc-tdep.h for details.
+ *
+ * Registers are ordered for GDB 7.5. It is incompatible with GDB 6.8. */
+enum arc_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,
+	_FP		= 27,
+	__SP		= 28,
+	_R30		= 30,
+	_BLINK		= 31,
+	_LP_COUNT	= 60,
+	_STOP_PC	= 64,
+	_RET		= 64,
+	_LP_START	= 65,
+	_LP_END		= 66,
+	_STATUS32	= 67,
+	_ECR		= 76,
+	_BTA		= 82,
+};
+
+#else
+#define kgdb_trap(regs)
+#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 000000000..68e8301c0
--- /dev/null
+++ b/arch/arc/include/asm/kprobes.h
@@ -0,0 +1,52 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#ifndef _ARC_KPROBES_H
+#define _ARC_KPROBES_H
+
+#include <asm-generic/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);
+
+struct prev_kprobe {
+	struct kprobe *kp;
+	unsigned long status;
+};
+
+struct kprobe_ctlblk {
+	unsigned int kprobe_status;
+	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 address, struct pt_regs *regs);
+#else
+#define trap_is_kprobe(address, regs)
+#endif /* CONFIG_KPROBES */
+
+#endif /* _ARC_KPROBES_H */
diff --git a/arch/arc/include/asm/linkage.h b/arch/arc/include/asm/linkage.h
new file mode 100644
index 000000000..ba3cb65b5
--- /dev/null
+++ b/arch/arc/include/asm/linkage.h
@@ -0,0 +1,80 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#ifndef __ASM_LINKAGE_H
+#define __ASM_LINKAGE_H
+
+#include <asm/dwarf.h>
+
+#define ASM_NL		 `	/* use '`' to mark new line in macro */
+#define __ALIGN		.align 4
+#define __ALIGN_STR	__stringify(__ALIGN)
+
+#ifdef __ASSEMBLER__
+
+.macro ST2 e, o, off
+#ifdef CONFIG_ARC_HAS_LL64
+	std	\e, [sp, \off]
+#else
+	st	\e, [sp, \off]
+	st	\o, [sp, \off+4]
+#endif
+.endm
+
+.macro LD2 e, o, off
+#ifdef CONFIG_ARC_HAS_LL64
+	ldd	\e, [sp, \off]
+#else
+	ld	\e, [sp, \off]
+	ld	\o, [sp, \off+4]
+#endif
+.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
+
+#define ENTRY_CFI(name)		\
+	.globl name ASM_NL	\
+	ALIGN ASM_NL 		\
+	name: ASM_NL		\
+	CFI_STARTPROC ASM_NL
+
+#define END_CFI(name) 		\
+	CFI_ENDPROC ASM_NL	\
+	.size name, .-name
+
+#else	/* !__ASSEMBLER__ */
+
+#ifdef CONFIG_ARC_HAS_ICCM
+#define __arcfp_code __section(".text.arcfp")
+#else
+#define __arcfp_code __section(".text")
+#endif
+
+#ifdef CONFIG_ARC_HAS_DCCM
+#define __arcfp_data __section(".data.arcfp")
+#else
+#define __arcfp_data __section(".data")
+#endif
+
+#endif /* __ASSEMBLER__ */
+
+#endif
diff --git a/arch/arc/include/asm/mach_desc.h b/arch/arc/include/asm/mach_desc.h
new file mode 100644
index 000000000..c4e197059
--- /dev/null
+++ b/arch/arc/include/asm/mach_desc.h
@@ -0,0 +1,64 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * based on METAG mach/arch.h (which in turn was based on ARM)
+ */
+
+#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_per_cpu:	for each CPU as it is coming up (SMP as well as UP)
+ * 			[(M):init_IRQ(), (o):start_kernel_secondary()]
+ * @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_per_cpu)(unsigned int);
+	void			(*init_machine)(void);
+	void			(*init_late)(void);
+
+};
+
+/*
+ * Current machine - only accessible during boot.
+ */
+extern const struct machine_desc *machine_desc;
+
+/*
+ * Machine type table - also only accessible during boot
+ */
+extern const struct machine_desc __arch_info_begin[], __arch_info_end[];
+
+/*
+ * 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 __section(".arch.info.init") = {			\
+	.name		= _name,
+
+#define MACHINE_END				\
+};
+
+extern const struct machine_desc *setup_machine_fdt(void *dt);
+
+#endif
diff --git a/arch/arc/include/asm/mmu-arcv2.h b/arch/arc/include/asm/mmu-arcv2.h
new file mode 100644
index 000000000..5e5482026
--- /dev/null
+++ b/arch/arc/include/asm/mmu-arcv2.h
@@ -0,0 +1,105 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012, 2019-20 Synopsys, Inc. (www.synopsys.com)
+ *
+ * MMUv3 (arc700) / MMUv4 (archs) are software page walked and software managed.
+ * This file contains the TLB access registers and commands
+ */
+
+#ifndef _ASM_ARC_MMU_ARCV2_H
+#define _ASM_ARC_MMU_ARCV2_H
+
+#include <soc/arc/arc_aux.h>
+
+/*
+ * TLB Management regs
+ */
+#define ARC_REG_MMU_BCR		0x06f
+
+#ifdef CONFIG_ARC_MMU_V3
+#define ARC_REG_TLBPD0		0x405
+#define ARC_REG_TLBPD1		0x406
+#define ARC_REG_TLBPD1HI	0	/* Dummy: allows common code */
+#define ARC_REG_TLBINDEX	0x407
+#define ARC_REG_TLBCOMMAND	0x408
+#define ARC_REG_PID		0x409
+#define ARC_REG_SCRATCH_DATA0	0x418
+#else
+#define ARC_REG_TLBPD0		0x460
+#define ARC_REG_TLBPD1		0x461
+#define ARC_REG_TLBPD1HI	0x463
+#define ARC_REG_TLBINDEX	0x464
+#define ARC_REG_TLBCOMMAND	0x465
+#define ARC_REG_PID		0x468
+#define ARC_REG_SCRATCH_DATA0	0x46c
+#endif
+
+/* Bits in MMU PID reg */
+#define __TLB_ENABLE		(1 << 31)
+#define __PROG_ENABLE		(1 << 30)
+#define MMU_ENABLE		(__TLB_ENABLE | __PROG_ENABLE)
+
+/* Bits in TLB Index reg */
+#define TLB_LKUP_ERR		0x80000000
+
+#ifdef CONFIG_ARC_MMU_V3
+#define TLB_DUP_ERR		(TLB_LKUP_ERR | 0x00000001)
+#else
+#define TLB_DUP_ERR		(TLB_LKUP_ERR | 0x40000000)
+#endif
+
+/*
+ * TLB Commands
+ */
+#define TLBWrite    		0x1
+#define TLBRead     		0x2
+#define TLBGetIndex 		0x3
+#define TLBProbe    		0x4
+#define TLBWriteNI		0x5  /* write JTLB without inv uTLBs */
+#define TLBIVUTLB		0x6  /* explicitly inv uTLBs */
+
+#ifdef CONFIG_ARC_MMU_V4
+#define TLBInsertEntry		0x7
+#define TLBDeleteEntry		0x8
+#endif
+
+/* Masks for actual TLB "PD"s */
+#define PTE_BITS_IN_PD0		(_PAGE_GLOBAL | _PAGE_PRESENT | _PAGE_HW_SZ)
+#define PTE_BITS_RWX		(_PAGE_EXECUTE | _PAGE_WRITE | _PAGE_READ)
+
+#define PTE_BITS_NON_RWX_IN_PD1	(PAGE_MASK_PHYS | _PAGE_CACHEABLE)
+
+#ifndef __ASSEMBLER__
+
+struct mm_struct;
+extern int pae40_exist_but_not_enab(void);
+
+static inline int is_pae40_enabled(void)
+{
+	return IS_ENABLED(CONFIG_ARC_HAS_PAE40);
+}
+
+static inline void mmu_setup_asid(struct mm_struct *mm, unsigned long asid)
+{
+	write_aux_reg(ARC_REG_PID, asid | MMU_ENABLE);
+}
+
+static inline void mmu_setup_pgd(struct mm_struct *mm, void *pgd)
+{
+	/* PGD cached in MMU reg to avoid 3 mem lookups: task->mm->pgd */
+#ifdef CONFIG_ISA_ARCV2
+	write_aux_reg(ARC_REG_SCRATCH_DATA0, (unsigned int)pgd);
+#endif
+}
+
+#else
+
+.macro ARC_MMU_REENABLE reg
+	lr \reg, [ARC_REG_PID]
+	or \reg, \reg, MMU_ENABLE
+	sr \reg, [ARC_REG_PID]
+.endm
+
+#endif /* !__ASSEMBLER__ */
+
+#endif
diff --git a/arch/arc/include/asm/mmu.h b/arch/arc/include/asm/mmu.h
new file mode 100644
index 000000000..e3b35ceab
--- /dev/null
+++ b/arch/arc/include/asm/mmu.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#ifndef _ASM_ARC_MMU_H
+#define _ASM_ARC_MMU_H
+
+#ifndef __ASSEMBLER__
+
+#include <linux/threads.h>	/* NR_CPUS */
+
+typedef struct {
+	unsigned long asid[NR_CPUS];	/* 8 bit MMU PID + Generation cycle */
+} mm_context_t;
+
+struct pt_regs;
+extern void do_tlb_overlap_fault(unsigned long, unsigned long, struct pt_regs *);
+
+#endif
+
+#include <asm/mmu-arcv2.h>
+
+#endif
diff --git a/arch/arc/include/asm/mmu_context.h b/arch/arc/include/asm/mmu_context.h
new file mode 100644
index 000000000..9963bb1a5
--- /dev/null
+++ b/arch/arc/include/asm/mmu_context.h
@@ -0,0 +1,174 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * 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 <linux/sched/mm.h>
+
+#include <asm/tlb.h>
+#include <asm-generic/mm_hooks.h>
+
+/*		ARC ASID Management
+ *
+ * MMU tags TLBs with an 8-bit ASID, avoiding need to flush the TLB on
+ * context-switch.
+ *
+ * ASID is managed per cpu, so task threads across CPUs can have different
+ * ASID. Global ASID management is needed if hardware supports TLB shootdown
+ * and/or shared TLB across cores, which ARC doesn't.
+ *
+ * Each task is assigned unique ASID, with a simple round-robin allocator
+ * tracked in @asid_cpu. When 8-bit value rolls over,a new cycle is started
+ * over from 0, and TLB is flushed
+ *
+ * A new allocation cycle, post rollover, could potentially reassign an ASID
+ * to a different task. Thus the rule is to refresh the ASID in a new cycle.
+ * The 32 bit @asid_cpu (and mm->asid) have 8 bits MMU PID and rest 24 bits
+ * serve as cycle/generation indicator and natural 32 bit unsigned math
+ * automagically increments the generation when lower 8 bits rollover.
+ */
+
+#define MM_CTXT_ASID_MASK	0x000000ff /* MMU PID reg :8 bit PID */
+#define MM_CTXT_CYCLE_MASK	(~MM_CTXT_ASID_MASK)
+
+#define MM_CTXT_FIRST_CYCLE	(MM_CTXT_ASID_MASK + 1)
+#define MM_CTXT_NO_ASID		0UL
+
+#define asid_mm(mm, cpu)	mm->context.asid[cpu]
+#define hw_pid(mm, cpu)		(asid_mm(mm, cpu) & MM_CTXT_ASID_MASK)
+
+DECLARE_PER_CPU(unsigned int, asid_cache);
+#define asid_cpu(cpu)		per_cpu(asid_cache, cpu)
+
+/*
+ * Get a new ASID if task doesn't have a valid one (unalloc or from prev cycle)
+ * Also set the MMU PID register to existing/updated ASID
+ */
+static inline void get_new_mmu_context(struct mm_struct *mm)
+{
+	const unsigned int cpu = smp_processor_id();
+	unsigned long flags;
+
+	local_irq_save(flags);
+
+	/*
+	 * Move to new ASID if it was not from current alloc-cycle/generation.
+	 * This is done by ensuring that the generation bits in both mm->ASID
+	 * and cpu's ASID counter are exactly same.
+	 *
+	 * Note: Callers needing new ASID unconditionally, independent of
+	 * 	 generation, e.g. local_flush_tlb_mm() for forking  parent,
+	 * 	 first need to destroy the context, setting it to invalid
+	 * 	 value.
+	 */
+	if (!((asid_mm(mm, cpu) ^ asid_cpu(cpu)) & MM_CTXT_CYCLE_MASK))
+		goto set_hw;
+
+	/* move to new ASID and handle rollover */
+	if (unlikely(!(++asid_cpu(cpu) & MM_CTXT_ASID_MASK))) {
+
+		local_flush_tlb_all();
+
+		/*
+		 * Above check for rollover of 8 bit ASID in 32 bit container.
+		 * If the container itself wrapped around, set it to a non zero
+		 * "generation" to distinguish from no context
+		 */
+		if (!asid_cpu(cpu))
+			asid_cpu(cpu) = MM_CTXT_FIRST_CYCLE;
+	}
+
+	/* Assign new ASID to tsk */
+	asid_mm(mm, cpu) = asid_cpu(cpu);
+
+set_hw:
+	mmu_setup_asid(mm, hw_pid(mm, cpu));
+
+	local_irq_restore(flags);
+}
+
+/*
+ * Initialize the context related info for a new mm_struct
+ * instance.
+ */
+#define init_new_context init_new_context
+static inline int
+init_new_context(struct task_struct *tsk, struct mm_struct *mm)
+{
+	int i;
+
+	for_each_possible_cpu(i)
+		asid_mm(mm, i) = MM_CTXT_NO_ASID;
+
+	return 0;
+}
+
+#define destroy_context destroy_context
+static inline void destroy_context(struct mm_struct *mm)
+{
+	unsigned long flags;
+
+	/* Needed to elide CONFIG_DEBUG_PREEMPT warning */
+	local_irq_save(flags);
+	asid_mm(mm, smp_processor_id()) = MM_CTXT_NO_ASID;
+	local_irq_restore(flags);
+}
+
+/* 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)
+{
+	const int cpu = smp_processor_id();
+
+	/*
+	 * Note that the mm_cpumask is "aggregating" only, we don't clear it
+	 * for the switched-out task, unlike some other arches.
+	 * It is used to enlist cpus for sending TLB flush IPIs and not sending
+	 * it to CPUs where a task once ran-on, could cause stale TLB entry
+	 * re-use, specially for a multi-threaded task.
+	 * e.g. T1 runs on C1, migrates to C3. T2 running on C2 munmaps.
+	 *      For a non-aggregating mm_cpumask, IPI not sent C1, and if T1
+	 *      were to re-migrate to C1, it could access the unmapped region
+	 *      via any existing stale TLB entries.
+	 */
+	cpumask_set_cpu(cpu, mm_cpumask(next));
+
+	mmu_setup_pgd(next, next->pgd);
+
+	get_new_mmu_context(next);
+}
+
+/*
+ * activate_mm defaults (in asm-generic) to switch_mm and is called at the
+ * time of execve() to get a new ASID Note the subtlety here:
+ * get_new_mmu_context() behaves differently here vs. in switch_mm(). Here
+ * it always returns a new ASID, because mm has an unallocated "initial"
+ * value, while in latter, it moves to a new ASID, only if it was
+ * unallocated
+ */
+
+/* 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 its ASID valid
+ * again (this teased me for a whole day).
+ */
+
+#include <asm-generic/mmu_context.h>
+
+#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 000000000..f534a1fef
--- /dev/null
+++ b/arch/arc/include/asm/module.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * Amit Bhor, Sameer Dhavale: Codito Technologies 2004
+ */
+
+#ifndef _ASM_ARC_MODULE_H
+#define _ASM_ARC_MODULE_H
+
+#include <asm-generic/module.h>
+
+struct mod_arch_specific {
+#ifdef CONFIG_ARC_DW2_UNWIND
+	void *unw_info;
+	int unw_sec_idx;
+#endif
+	const char *secstr;
+};
+
+#endif /* _ASM_ARC_MODULE_H */
diff --git a/arch/arc/include/asm/page.h b/arch/arc/include/asm/page.h
new file mode 100644
index 000000000..facc7a03b
--- /dev/null
+++ b/arch/arc/include/asm/page.h
@@ -0,0 +1,143 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+#ifndef __ASM_ARC_PAGE_H
+#define __ASM_ARC_PAGE_H
+
+#include <uapi/asm/page.h>
+
+#ifdef CONFIG_ARC_HAS_PAE40
+
+#define MAX_POSSIBLE_PHYSMEM_BITS	40
+#define PAGE_MASK_PHYS			(0xff00000000ull | PAGE_MASK)
+
+#else /* CONFIG_ARC_HAS_PAE40 */
+
+#define MAX_POSSIBLE_PHYSMEM_BITS	32
+#define PAGE_MASK_PHYS			PAGE_MASK
+
+#endif /* CONFIG_ARC_HAS_PAE40 */
+
+#ifndef __ASSEMBLER__
+
+#define clear_page(paddr)		memset((paddr), 0, PAGE_SIZE)
+#define copy_user_page(to, from, vaddr, pg)	copy_page(to, from)
+#define copy_page(to, from)		memcpy((to), (from), PAGE_SIZE)
+
+struct vm_area_struct;
+struct page;
+
+#define __HAVE_ARCH_COPY_USER_HIGHPAGE
+
+void copy_user_highpage(struct page *to, struct page *from,
+			unsigned long u_vaddr, struct vm_area_struct *vma);
+
+#define clear_user_page clear_user_page
+void clear_user_page(void *to, unsigned long u_vaddr, struct page *page);
+
+typedef struct {
+	unsigned long pgd;
+} pgd_t;
+
+#define pgd_val(x)	((x).pgd)
+#define __pgd(x)	((pgd_t) { (x) })
+
+#if CONFIG_PGTABLE_LEVELS > 3
+
+typedef struct {
+	unsigned long pud;
+} pud_t;
+
+#define pud_val(x)      	((x).pud)
+#define __pud(x)        	((pud_t) { (x) })
+
+#endif
+
+#if CONFIG_PGTABLE_LEVELS > 2
+
+typedef struct {
+	unsigned long pmd;
+} pmd_t;
+
+#define pmd_val(x)	((x).pmd)
+#define __pmd(x)	((pmd_t) { (x) })
+
+#endif
+
+typedef struct {
+#ifdef CONFIG_ARC_HAS_PAE40
+	unsigned long long pte;
+#else
+	unsigned long pte;
+#endif
+} pte_t;
+
+#define pte_val(x)	((x).pte)
+#define __pte(x)	((pte_t) { (x) })
+
+typedef struct {
+	unsigned long pgprot;
+} pgprot_t;
+
+#define pgprot_val(x)	((x).pgprot)
+#define __pgprot(x)	((pgprot_t) { (x) })
+#define pte_pgprot(x)	__pgprot(pte_val(x))
+
+typedef struct page *pgtable_t;
+
+/*
+ * When HIGHMEM is enabled we have holes in the memory map so we need
+ * pfn_valid() that takes into account the actual extents of the physical
+ * memory
+ */
+#ifdef CONFIG_HIGHMEM
+
+extern unsigned long arch_pfn_offset;
+#define ARCH_PFN_OFFSET		arch_pfn_offset
+
+extern int pfn_valid(unsigned long pfn);
+#define pfn_valid		pfn_valid
+
+#else /* CONFIG_HIGHMEM */
+
+#define ARCH_PFN_OFFSET		virt_to_pfn((void *)CONFIG_LINUX_RAM_BASE)
+
+#endif /* CONFIG_HIGHMEM */
+
+/*
+ * __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.
+ * And for ARC, link-addr = physical address
+ */
+#define __pa(vaddr)  		((unsigned long)(vaddr))
+#define __va(paddr)  		((void *)((unsigned long)(paddr)))
+
+/*
+ * Use virt_to_pfn with caution:
+ * If used in pte or paddr related macros, it could cause truncation
+ * in PAE40 builds
+ * As a rule of thumb, only use it in helpers starting with virt_
+ * You have been warned !
+ */
+static inline unsigned long virt_to_pfn(const void *kaddr)
+{
+	return __pa(kaddr) >> PAGE_SHIFT;
+}
+
+#define virt_to_page(kaddr)	pfn_to_page(virt_to_pfn(kaddr))
+#define virt_addr_valid(kaddr)  pfn_valid(virt_to_pfn(kaddr))
+
+/* Default Permissions for stack/heaps pages (Non Executable) */
+#define VMA_DATA_DEFAULT_FLAGS	VMA_DATA_FLAGS_NON_EXEC
+
+#define WANT_PAGE_VIRTUAL   1
+
+#include <asm-generic/memory_model.h>   /* page_to_pfn, pfn_to_page */
+#include <asm-generic/getorder.h>
+
+#endif /* !__ASSEMBLER__ */
+
+#endif
diff --git a/arch/arc/include/asm/pci.h b/arch/arc/include/asm/pci.h
new file mode 100644
index 000000000..a6858e111
--- /dev/null
+++ b/arch/arc/include/asm/pci.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2015-2016 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#ifndef _ASM_ARC_PCI_H
+#define _ASM_ARC_PCI_H
+
+#ifdef __KERNEL__
+#include <linux/ioport.h>
+
+#define PCIBIOS_MIN_IO 0x100
+#define PCIBIOS_MIN_MEM 0x100000
+
+#define pcibios_assign_all_busses()	1
+
+#endif /* __KERNEL__ */
+
+#endif /* _ASM_ARC_PCI_H */
diff --git a/arch/arc/include/asm/perf_event.h b/arch/arc/include/asm/perf_event.h
new file mode 100644
index 000000000..d5719a260
--- /dev/null
+++ b/arch/arc/include/asm/perf_event.h
@@ -0,0 +1,70 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Linux performance counter support for ARC
+ *
+ * Copyright (C) 2014-2015 Synopsys, Inc. (www.synopsys.com)
+ * Copyright (C) 2011-2013 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#ifndef __ASM_PERF_EVENT_H
+#define __ASM_PERF_EVENT_H
+
+/* Max number of counters that PCT block may ever have */
+#define ARC_PERF_MAX_COUNTERS	32
+
+#define ARC_REG_CC_BUILD	0xF6
+#define ARC_REG_CC_INDEX	0x240
+#define ARC_REG_CC_NAME0	0x241
+#define ARC_REG_CC_NAME1	0x242
+
+#define ARC_REG_PCT_BUILD	0xF5
+#define ARC_REG_PCT_COUNTL	0x250
+#define ARC_REG_PCT_COUNTH	0x251
+#define ARC_REG_PCT_SNAPL	0x252
+#define ARC_REG_PCT_SNAPH	0x253
+#define ARC_REG_PCT_CONFIG	0x254
+#define ARC_REG_PCT_CONTROL	0x255
+#define ARC_REG_PCT_INDEX	0x256
+#define ARC_REG_PCT_INT_CNTL	0x25C
+#define ARC_REG_PCT_INT_CNTH	0x25D
+#define ARC_REG_PCT_INT_CTRL	0x25E
+#define ARC_REG_PCT_INT_ACT	0x25F
+
+#define ARC_REG_PCT_CONFIG_USER	(1 << 18)	/* count in user mode */
+#define ARC_REG_PCT_CONFIG_KERN	(1 << 19)	/* count in kernel mode */
+
+#define ARC_REG_PCT_CONTROL_CC	(1 << 16)	/* clear counts */
+#define ARC_REG_PCT_CONTROL_SN	(1 << 17)	/* snapshot */
+
+struct arc_reg_pct_build {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int m:8, c:8, r:5, i:1, s:2, v:8;
+#else
+	unsigned int v:8, s:2, i:1, r:5, c:8, m:8;
+#endif
+};
+
+struct arc_reg_cc_build {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int c:16, r:8, v:8;
+#else
+	unsigned int v:8, r:8, c:16;
+#endif
+};
+
+#define PERF_COUNT_ARC_DCLM	(PERF_COUNT_HW_MAX + 0)
+#define PERF_COUNT_ARC_DCSM	(PERF_COUNT_HW_MAX + 1)
+#define PERF_COUNT_ARC_ICM	(PERF_COUNT_HW_MAX + 2)
+#define PERF_COUNT_ARC_BPOK	(PERF_COUNT_HW_MAX + 3)
+#define PERF_COUNT_ARC_EDTLB	(PERF_COUNT_HW_MAX + 4)
+#define PERF_COUNT_ARC_EITLB	(PERF_COUNT_HW_MAX + 5)
+#define PERF_COUNT_ARC_LDC	(PERF_COUNT_HW_MAX + 6)
+#define PERF_COUNT_ARC_STC	(PERF_COUNT_HW_MAX + 7)
+
+#define PERF_COUNT_ARC_HW_MAX	(PERF_COUNT_HW_MAX + 8)
+
+#ifdef CONFIG_PERF_EVENTS
+#define perf_arch_bpf_user_pt_regs(regs) (struct user_regs_struct *)regs
+#endif
+
+#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 000000000..dfae070fe
--- /dev/null
+++ b/arch/arc/include/asm/pgalloc.h
@@ -0,0 +1,92 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * 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
+ *       deal with struct page. That 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>
+#include <asm-generic/pgalloc.h>
+
+static inline void
+pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte)
+{
+	/*
+	 * The cast to long below is OK in 32-bit PAE40 regime with long long pte
+	 * Despite "wider" pte, the pte table needs to be in non-PAE low memory
+	 * as all higher levels can only hold long pointers.
+	 *
+	 * The cast itself is needed given simplistic definition of set_pmd()
+	 */
+	set_pmd(pmd, __pmd((unsigned long)pte));
+}
+
+static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, pgtable_t pte_page)
+{
+	set_pmd(pmd, __pmd((unsigned long)page_address(pte_page)));
+}
+
+static inline pgd_t *pgd_alloc(struct mm_struct *mm)
+{
+	pgd_t *ret = __pgd_alloc(mm, 0);
+
+	if (ret) {
+		int num, num2;
+
+		num = USER_PTRS_PER_PGD + USER_KERNEL_GUTTER / PGDIR_SIZE;
+		num2 = VMALLOC_SIZE / PGDIR_SIZE;
+		memcpy(ret + num, swapper_pg_dir + num, num2 * sizeof(pgd_t));
+	}
+	return ret;
+}
+
+#if CONFIG_PGTABLE_LEVELS > 3
+
+static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4dp, pud_t *pudp)
+{
+	set_p4d(p4dp, __p4d((unsigned long)pudp));
+}
+
+#define __pud_free_tlb(tlb, pmd, addr)  pud_free((tlb)->mm, pmd)
+
+#endif
+
+#if CONFIG_PGTABLE_LEVELS > 2
+
+static inline void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmdp)
+{
+	set_pud(pudp, __pud((unsigned long)pmdp));
+}
+
+#define __pmd_free_tlb(tlb, pmd, addr)  pmd_free((tlb)->mm, pmd)
+
+#endif
+
+#define __pte_free_tlb(tlb, pte, addr)  pte_free((tlb)->mm, pte)
+
+#endif /* _ASM_ARC_PGALLOC_H */
diff --git a/arch/arc/include/asm/pgtable-bits-arcv2.h b/arch/arc/include/asm/pgtable-bits-arcv2.h
new file mode 100644
index 000000000..4630c5acc
--- /dev/null
+++ b/arch/arc/include/asm/pgtable-bits-arcv2.h
@@ -0,0 +1,147 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+/*
+ * page table flags for software walked/managed MMUv3 (ARC700) and MMUv4 (HS)
+ * There correspond to the corresponding bits in the TLB
+ */
+
+#ifndef _ASM_ARC_PGTABLE_BITS_ARCV2_H
+#define _ASM_ARC_PGTABLE_BITS_ARCV2_H
+
+#ifdef CONFIG_ARC_CACHE_PAGES
+#define _PAGE_CACHEABLE		(1 << 0)  /* Cached (H) */
+#else
+#define _PAGE_CACHEABLE		0
+#endif
+
+#define _PAGE_EXECUTE		(1 << 1)  /* User Execute  (H) */
+#define _PAGE_WRITE		(1 << 2)  /* User Write    (H) */
+#define _PAGE_READ		(1 << 3)  /* User Read     (H) */
+#define _PAGE_ACCESSED		(1 << 4)  /* Accessed      (s) */
+#define _PAGE_DIRTY		(1 << 5)  /* Modified      (s) */
+#define _PAGE_SPECIAL		(1 << 6)
+#define _PAGE_GLOBAL		(1 << 8)  /* ASID agnostic (H) */
+#define _PAGE_PRESENT		(1 << 9)  /* PTE/TLB Valid (H) */
+
+/* We borrow bit 5 to store the exclusive marker in swap PTEs. */
+#define _PAGE_SWP_EXCLUSIVE	_PAGE_DIRTY
+
+#ifdef CONFIG_ARC_MMU_V4
+#define _PAGE_HW_SZ		(1 << 10)  /* Normal/super (H) */
+#else
+#define _PAGE_HW_SZ		0
+#endif
+
+/* Defaults for every user page */
+#define ___DEF		(_PAGE_PRESENT | _PAGE_CACHEABLE)
+
+/* Set of bits not changed in pte_modify */
+#define _PAGE_CHG_MASK	(PAGE_MASK_PHYS | _PAGE_ACCESSED | _PAGE_DIRTY | \
+							   _PAGE_SPECIAL)
+
+/* 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_KERNEL     __pgprot(___DEF | _PAGE_GLOBAL \
+				| _PAGE_READ | _PAGE_WRITE | _PAGE_EXECUTE)
+
+#define PAGE_SHARED	PAGE_U_W_R
+
+#define pgprot_noncached(prot)	(__pgprot(pgprot_val(prot) & ~_PAGE_CACHEABLE))
+
+/*
+ * 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 independently 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 */
+#ifndef __ASSEMBLER__
+
+#define pte_write(pte)		(pte_val(pte) & _PAGE_WRITE)
+#define pte_dirty(pte)		(pte_val(pte) & _PAGE_DIRTY)
+#define pte_young(pte)		(pte_val(pte) & _PAGE_ACCESSED)
+#define pte_special(pte)	(pte_val(pte) & _PAGE_SPECIAL)
+
+#define PTE_BIT_FUNC(fn, op) \
+	static inline pte_t pte_##fn(pte_t pte) { pte_val(pte) op; return pte; }
+
+PTE_BIT_FUNC(mknotpresent,     &= ~(_PAGE_PRESENT));
+PTE_BIT_FUNC(wrprotect,	&= ~(_PAGE_WRITE));
+PTE_BIT_FUNC(mkwrite_novma,	|= (_PAGE_WRITE));
+PTE_BIT_FUNC(mkclean,	&= ~(_PAGE_DIRTY));
+PTE_BIT_FUNC(mkdirty,	|= (_PAGE_DIRTY));
+PTE_BIT_FUNC(mkold,	&= ~(_PAGE_ACCESSED));
+PTE_BIT_FUNC(mkyoung,	|= (_PAGE_ACCESSED));
+PTE_BIT_FUNC(mkspecial,	|= (_PAGE_SPECIAL));
+PTE_BIT_FUNC(mkhuge,	|= (_PAGE_HW_SZ));
+
+static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
+{
+	return __pte((pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot));
+}
+
+struct vm_fault;
+void update_mmu_cache_range(struct vm_fault *vmf, struct vm_area_struct *vma,
+		unsigned long address, pte_t *ptep, unsigned int nr);
+
+#define update_mmu_cache(vma, addr, ptep) \
+	update_mmu_cache_range(NULL, vma, addr, ptep, 1)
+
+/*
+ * Encode/decode swap entries and swap PTEs. Swap PTEs are all PTEs that
+ * are !pte_none() && !pte_present().
+ *
+ * Format of swap PTEs:
+ *
+ *   3 3 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1
+ *   1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0
+ *   <-------------- offset -------------> <--- zero --> E < type ->
+ *
+ *   E is the exclusive marker that is not stored in swap entries.
+ *   The zero'ed bits include _PAGE_PRESENT.
+ */
+#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)
+
+#define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val(pte) })
+#define __swp_entry_to_pte(x)		((pte_t) { (x).val })
+
+static inline bool pte_swp_exclusive(pte_t pte)
+{
+	return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
+}
+
+PTE_BIT_FUNC(swp_mkexclusive, |= (_PAGE_SWP_EXCLUSIVE));
+PTE_BIT_FUNC(swp_clear_exclusive, &= ~(_PAGE_SWP_EXCLUSIVE));
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#include <asm/hugepage.h>
+#endif
+
+#endif /* __ASSEMBLER__ */
+
+#endif
diff --git a/arch/arc/include/asm/pgtable-levels.h b/arch/arc/include/asm/pgtable-levels.h
new file mode 100644
index 000000000..c8f927337
--- /dev/null
+++ b/arch/arc/include/asm/pgtable-levels.h
@@ -0,0 +1,186 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2020 Synopsys, Inc. (www.synopsys.com)
+ */
+
+/*
+ * Helpers for implemenintg paging levels
+ */
+
+#ifndef _ASM_ARC_PGTABLE_LEVELS_H
+#define _ASM_ARC_PGTABLE_LEVELS_H
+
+#if CONFIG_PGTABLE_LEVELS == 2
+
+/*
+ * 2 level paging setup for software walked MMUv3 (ARC700) and MMUv4 (HS)
+ *
+ * [31]            32 bit virtual address              [0]
+ * -------------------------------------------------------
+ * |               | <---------- PGDIR_SHIFT ----------> |
+ * |               |                | <-- PAGE_SHIFT --> |
+ * -------------------------------------------------------
+ *       |                  |                |
+ *       |                  |                --> off in page frame
+ *       |                  ---> index into Page Table
+ *       ----> index into Page Directory
+ *
+ * Given software walk, the vaddr split is arbitrary set to 11:8:13
+ * However enabling of super page in a 2 level regime pegs PGDIR_SHIFT to
+ * super page size.
+ */
+
+#if defined(CONFIG_ARC_HUGEPAGE_16M)
+#define PGDIR_SHIFT		24
+#elif defined(CONFIG_ARC_HUGEPAGE_2M)
+#define PGDIR_SHIFT		21
+#else
+/*
+ * No Super page case
+ * Default value provides 11:8:13 (8K), 10:10:12 (4K)
+ * Limits imposed by pgtable_t only PAGE_SIZE long
+ * (so 4K page can only have 1K entries: or 10 bits)
+ */
+#ifdef CONFIG_ARC_PAGE_SIZE_4K
+#define PGDIR_SHIFT		22
+#else
+#define PGDIR_SHIFT		21
+#endif
+
+#endif
+
+#else /* CONFIG_PGTABLE_LEVELS != 2 */
+
+/*
+ * A default 3 level paging testing setup in software walked MMU
+ *   MMUv4 (8K page): <4> : <7> : <8> : <13>
+ * A default 4 level paging testing setup in software walked MMU
+ *   MMUv4 (8K page): <4> : <3> : <4> : <8> : <13>
+ */
+#define PGDIR_SHIFT		28
+#if CONFIG_PGTABLE_LEVELS > 3
+#define PUD_SHIFT		25
+#endif
+#if CONFIG_PGTABLE_LEVELS > 2
+#define PMD_SHIFT		21
+#endif
+
+#endif /* CONFIG_PGTABLE_LEVELS */
+
+#define PGDIR_SIZE		BIT(PGDIR_SHIFT)
+#define PGDIR_MASK		(~(PGDIR_SIZE - 1))
+#define PTRS_PER_PGD		BIT(32 - PGDIR_SHIFT)
+
+#if CONFIG_PGTABLE_LEVELS > 3
+#define PUD_SIZE		BIT(PUD_SHIFT)
+#define PUD_MASK		(~(PUD_SIZE - 1))
+#define PTRS_PER_PUD		BIT(PGDIR_SHIFT - PUD_SHIFT)
+#endif
+
+#if CONFIG_PGTABLE_LEVELS > 2
+#define PMD_SIZE		BIT(PMD_SHIFT)
+#define PMD_MASK		(~(PMD_SIZE - 1))
+#define PTRS_PER_PMD		BIT(PUD_SHIFT - PMD_SHIFT)
+#endif
+
+#define PTRS_PER_PTE		BIT(PMD_SHIFT - PAGE_SHIFT)
+
+#ifndef __ASSEMBLER__
+
+#if CONFIG_PGTABLE_LEVELS > 3
+#include <asm-generic/pgtable-nop4d.h>
+#elif CONFIG_PGTABLE_LEVELS > 2
+#include <asm-generic/pgtable-nopud.h>
+#else
+#include <asm-generic/pgtable-nopmd.h>
+#endif
+
+/*
+ * 1st level paging: pgd
+ */
+#define pgd_ERROR(e) \
+	pr_crit("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
+
+#if CONFIG_PGTABLE_LEVELS > 3
+
+/* In 4 level paging, p4d_* macros work on pgd */
+#define p4d_none(x)		(!p4d_val(x))
+#define p4d_bad(x)		((p4d_val(x) & ~PAGE_MASK))
+#define p4d_present(x)		(p4d_val(x))
+#define p4d_clear(xp)		do { p4d_val(*(xp)) = 0; } while (0)
+#define p4d_pgtable(p4d)	((pud_t *)(p4d_val(p4d) & PAGE_MASK))
+#define p4d_page(p4d)		virt_to_page(p4d_pgtable(p4d))
+#define set_p4d(p4dp, p4d)	(*(p4dp) = p4d)
+
+/*
+ * 2nd level paging: pud
+ */
+#define pud_ERROR(e) \
+	pr_crit("%s:%d: bad pud %08lx.\n", __FILE__, __LINE__, pud_val(e))
+
+#endif
+
+#if CONFIG_PGTABLE_LEVELS > 2
+
+/*
+ * In 3 level paging, pud_* macros work on pgd
+ * In 4 level paging, pud_* macros work on pud
+ */
+#define pud_none(x)		(!pud_val(x))
+#define pud_bad(x)		((pud_val(x) & ~PAGE_MASK))
+#define pud_present(x)		(pud_val(x))
+#define pud_clear(xp)		do { pud_val(*(xp)) = 0; } while (0)
+#define pud_pgtable(pud)	((pmd_t *)(pud_val(pud) & PAGE_MASK))
+#define pud_page(pud)		virt_to_page(pud_pgtable(pud))
+#define set_pud(pudp, pud)	(*(pudp) = pud)
+
+/*
+ * 3rd level paging: pmd
+ */
+#define pmd_ERROR(e) \
+	pr_crit("%s:%d: bad pmd %08lx.\n", __FILE__, __LINE__, pmd_val(e))
+
+#define pmd_pfn(pmd)		((pmd_val(pmd) & PMD_MASK) >> PAGE_SHIFT)
+#define pfn_pmd(pfn,prot)	__pmd(((pfn) << PAGE_SHIFT) | pgprot_val(prot))
+
+#endif
+
+/*
+ * Due to the strange way generic pgtable level folding works, the pmd_* macros
+ *  - are valid even for 2 levels (which supposedly only has pgd - pte)
+ *  - behave differently for 2 vs. 3
+ * In 2  level paging        (pgd -> pte), pmd_* macros work on pgd
+ * In 3+ level paging (pgd -> pmd -> pte), pmd_* macros work on pmd
+ */
+#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 pmd_page_vaddr(pmd)	(pmd_val(pmd) & PAGE_MASK)
+#define pmd_pfn(pmd)		((pmd_val(pmd) & PAGE_MASK) >> PAGE_SHIFT)
+#define pmd_page(pmd)		virt_to_page((void *)pmd_page_vaddr(pmd))
+#define set_pmd(pmdp, pmd)	(*(pmdp) = pmd)
+#define pmd_pgtable(pmd)	((pgtable_t) pmd_page(pmd))
+
+/*
+ * 4th level paging: pte
+ */
+#define pte_ERROR(e) \
+	pr_crit("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, pte_val(e))
+
+#define PFN_PTE_SHIFT		PAGE_SHIFT
+#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 pte_page(pte)		pfn_to_page(pte_pfn(pte))
+#define set_pte(ptep, pte)	((*(ptep)) = (pte))
+#define pte_pfn(pte)		(pte_val(pte) >> PAGE_SHIFT)
+#define pfn_pte(pfn, prot)	__pte(__pfn_to_phys(pfn) | pgprot_val(prot))
+
+#ifdef CONFIG_ISA_ARCV2
+#define pmd_leaf(x)		(pmd_val(x) & _PAGE_HW_SZ)
+#endif
+
+#endif	/* !__ASSEMBLER__ */
+
+#endif
diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h
new file mode 100644
index 000000000..0fdaea81b
--- /dev/null
+++ b/arch/arc/include/asm/pgtable.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#ifndef _ASM_ARC_PGTABLE_H
+#define _ASM_ARC_PGTABLE_H
+
+#include <linux/bits.h>
+
+#include <asm/pgtable-levels.h>
+#include <asm/pgtable-bits-arcv2.h>
+#include <asm/page.h>
+#include <asm/mmu.h>
+
+/*
+ * 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)
+
+#ifndef __ASSEMBLER__
+
+extern pgd_t swapper_pg_dir[] __aligned(PAGE_SIZE);
+
+/* to cope with aliasing VIPT cache */
+#define HAVE_ARCH_UNMAPPED_AREA
+
+#endif /* __ASSEMBLER__ */
+
+#endif
diff --git a/arch/arc/include/asm/processor.h b/arch/arc/include/asm/processor.h
new file mode 100644
index 000000000..7f7901ac6
--- /dev/null
+++ b/arch/arc/include/asm/processor.h
@@ -0,0 +1,104 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * 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
+
+#ifndef __ASSEMBLER__
+
+#include <asm/ptrace.h>
+#include <asm/dsp.h>
+#include <asm/fpu.h>
+
+/* 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 callee_reg;	/* pointer to callee regs */
+	unsigned long fault_address;	/* dbls as brkpt holder as well */
+#ifdef CONFIG_ARC_DSP_SAVE_RESTORE_REGS
+	struct dsp_callee_regs dsp;
+#endif
+#ifdef CONFIG_ARC_FPU_SAVE_RESTORE
+	struct arc_fpu fpu;
+#endif
+};
+
+#define INIT_THREAD  { }
+
+/* Forward declaration, a strange C thing */
+struct task_struct;
+
+#define task_pt_regs(p) \
+	((struct pt_regs *)(THREAD_SIZE + (void *)task_stack_page(p)) - 1)
+
+/*
+ * A lot of busy-wait loops in SMP are based off of non-volatile data otherwise
+ * get optimised away by gcc
+ */
+#define cpu_relax()		barrier()
+
+#define KSTK_EIP(tsk)   (task_pt_regs(tsk)->ret)
+#define KSTK_ESP(tsk)   (task_pt_regs(tsk)->sp)
+
+/*
+ * Where about of Task's sp, fp, blink when it was last seen in kernel mode.
+ * Look in process.c for details of kernel stack layout
+ */
+#define TSK_K_ESP(tsk)		(task_thread_info(tsk)->ksp)
+
+#define TSK_K_REG(tsk, off)	(*((unsigned long *)(TSK_K_ESP(tsk) + \
+					sizeof(struct callee_regs) + off)))
+
+#define TSK_K_BLINK(tsk)	TSK_K_REG(tsk, 4)
+#define TSK_K_FP(tsk)		TSK_K_REG(tsk, 0)
+
+extern void start_thread(struct pt_regs * regs, unsigned long pc,
+			 unsigned long usp);
+
+extern unsigned int __get_wchan(struct task_struct *p);
+
+#endif /* !__ASSEMBLER__ */
+
+/*
+ * Default System Memory Map on ARC
+ *
+ * ---------------------------- (lower 2G, Translated) -------------------------
+ * 0x0000_0000		0x5FFF_FFFF	(user vaddr: TASK_SIZE)
+ * 0x6000_0000		0x6FFF_FFFF	(reserved gutter between U/K)
+ * 0x7000_0000		0x7FFF_FFFF	(kvaddr: vmalloc/modules/pkmap..)
+ *
+ * PAGE_OFFSET ---------------- (Upper 2G, Untranslated) -----------------------
+ * 0x8000_0000		0xBFFF_FFFF	(kernel direct mapped)
+ * 0xC000_0000		0xFFFF_FFFF	(peripheral uncached space)
+ * -----------------------------------------------------------------------------
+ */
+
+#define TASK_SIZE	0x60000000
+
+#define VMALLOC_START	(PAGE_OFFSET - (CONFIG_ARC_KVADDR_SIZE << 20))
+
+/* 1 PGDIR_SIZE each for fixmap/pkmap, 2 PGDIR_SIZE gutter (see asm/highmem.h) */
+#define VMALLOC_SIZE	((CONFIG_ARC_KVADDR_SIZE << 20) - PMD_SIZE * 4)
+
+#define VMALLOC_END	(VMALLOC_START + VMALLOC_SIZE)
+
+#define USER_KERNEL_GUTTER    (VMALLOC_START - TASK_SIZE)
+
+#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 /* __ASM_ARC_PROCESSOR_H */
diff --git a/arch/arc/include/asm/ptrace.h b/arch/arc/include/asm/ptrace.h
new file mode 100644
index 000000000..f6c052af8
--- /dev/null
+++ b/arch/arc/include/asm/ptrace.h
@@ -0,0 +1,177 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * Amit Bhor, Sameer Dhavale: Codito Technologies 2004
+ */
+#ifndef __ASM_ARC_PTRACE_H
+#define __ASM_ARC_PTRACE_H
+
+#include <uapi/asm/ptrace.h>
+#include <linux/compiler.h>
+
+#ifndef __ASSEMBLER__
+
+typedef union {
+	struct {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+		unsigned long state:8, vec:8, cause:8, param:8;
+#else
+		unsigned long param:8, cause:8, vec:8, state:8;
+#endif
+	};
+	unsigned long full;
+} ecr_reg;
+
+/* THE pt_regs: Defines how regs are saved during entry into kernel */
+
+#ifdef CONFIG_ISA_ARCOMPACT
+struct pt_regs {
+
+	/* Real registers */
+	unsigned long bta;	/* bta_l1, bta_l2, erbta */
+
+	unsigned long lp_start, lp_end, lp_count;
+
+	unsigned long status32;	/* status32_l1, status32_l2, erstatus */
+	unsigned long ret;	/* ilink1, ilink2 or eret */
+	unsigned long blink;
+	unsigned long fp;
+	unsigned long r26;	/* gp */
+
+	unsigned long r12, r11, r10, r9, r8, r7, r6, r5, r4, r3, r2, r1, r0;
+
+	unsigned long sp;	/* User/Kernel depending on where we came from */
+	unsigned long orig_r0;
+
+	/*
+	 * To distinguish bet excp, syscall, irq
+	 * For traps and exceptions, Exception Cause Register.
+	 * 	ECR: <00> <VV> <CC> <PP>
+	 * 	Last word used by Linux for extra state mgmt (syscall-restart)
+	 * For interrupts, use artificial ECR values to note current prio-level
+	 */
+	ecr_reg ecr;
+};
+
+struct callee_regs {
+	unsigned long r25, r24, r23, r22, r21, r20, r19, r18, r17, r16, r15, r14, r13;
+};
+
+#define MAX_REG_OFFSET offsetof(struct pt_regs, ecr)
+
+#else
+
+struct pt_regs {
+
+	unsigned long orig_r0;
+
+	ecr_reg ecr;		/* Exception Cause Reg */
+
+	unsigned long bta;	/* erbta */
+
+	unsigned long fp;
+	unsigned long r30;
+	unsigned long r12;
+	unsigned long r26;	/* gp */
+
+#ifdef CONFIG_ARC_HAS_ACCL_REGS
+	unsigned long r58, r59;	/* ACCL/ACCH used by FPU / DSP MPY */
+#endif
+#ifdef CONFIG_ARC_DSP_SAVE_RESTORE_REGS
+	unsigned long DSP_CTRL;
+#endif
+
+	unsigned long sp;	/* user/kernel sp depending on entry  */
+
+	/*------- Below list auto saved by h/w -----------*/
+	unsigned long r0, r1, r2, r3, r4, r5, r6, r7, r8, r9, r10, r11;
+
+	unsigned long blink;
+	unsigned long lp_end, lp_start, lp_count;
+
+	unsigned long ei, ldi, jli;
+
+	unsigned long ret;
+	unsigned long status32;
+};
+
+struct callee_regs {
+	unsigned long r25, r24, r23, r22, r21, r20, r19, r18, r17, r16, r15, r14, r13;
+};
+
+#define MAX_REG_OFFSET offsetof(struct pt_regs, status32)
+
+#endif
+
+#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->ecr.vec == ECR_V_TRAP) && !regs->ecr.param)
+#define in_brkpt_trap(regs) ((regs->ecr.vec == ECR_V_TRAP) && regs->ecr.param)
+
+#define STATE_SCALL_RESTARTED	0x01
+
+#define syscall_wont_restart(regs) (regs->ecr.state |= STATE_SCALL_RESTARTED)
+#define syscall_restartable(regs) !(regs->ecr.state &  STATE_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) - 1;	\
+})
+
+static inline long regs_return_value(struct pt_regs *regs)
+{
+	return (long)regs->r0;
+}
+
+static inline void instruction_pointer_set(struct pt_regs *regs,
+					   unsigned long val)
+{
+	instruction_pointer(regs) = val;
+}
+
+static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
+{
+	return regs->sp;
+}
+
+extern int regs_query_register_offset(const char *name);
+extern const char *regs_query_register_name(unsigned int offset);
+extern bool regs_within_kernel_stack(struct pt_regs *regs, unsigned long addr);
+extern unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs,
+					       unsigned int n);
+
+static inline unsigned long regs_get_register(struct pt_regs *regs,
+					      unsigned int offset)
+{
+	if (unlikely(offset > MAX_REG_OFFSET))
+		return 0;
+
+	return *(unsigned long *)((unsigned long)regs + offset);
+}
+
+extern int syscall_trace_enter(struct pt_regs *);
+extern void syscall_trace_exit(struct pt_regs *);
+
+#endif /* !__ASSEMBLER__ */
+
+#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 000000000..860b4fd67
--- /dev/null
+++ b/arch/arc/include/asm/sections.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#ifndef _ASM_ARC_SECTIONS_H
+#define _ASM_ARC_SECTIONS_H
+
+#include <asm-generic/sections.h>
+
+extern char __arc_dccm_base[];
+
+#endif
diff --git a/arch/arc/include/asm/serial.h b/arch/arc/include/asm/serial.h
new file mode 100644
index 000000000..83062c8b9
--- /dev/null
+++ b/arch/arc/include/asm/serial.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#ifndef _ASM_ARC_SERIAL_H
+#define _ASM_ARC_SERIAL_H
+
+/*
+ * early 8250 (now earlycon) requires BASE_BAUD to be defined in this header.
+ * However to still determine it dynamically (for multi-platform images)
+ * we do this in a helper by parsing the FDT early
+ */
+
+extern unsigned int __init arc_early_base_baud(void);
+
+#define BASE_BAUD	arc_early_base_baud()
+
+#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 000000000..1c6db599e
--- /dev/null
+++ b/arch/arc/include/asm/setup.h
@@ -0,0 +1,45 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+#ifndef __ASM_ARC_SETUP_H
+#define __ASM_ARC_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;
+};
+
+extern int root_mountflags, end_mem;
+
+void setup_processor(void);
+void __init setup_arch_memory(void);
+long __init arc_get_mem_sz(void);
+
+/* Helpers used in arc_*_mumbojumbo routines */
+#define IS_AVAIL1(v, s)		((v) ? s : "")
+#define IS_DISABLED_RUN(v)	((v) ? "" : "(disabled) ")
+#define IS_USED_RUN(v)		((v) ? "" : "(not used) ")
+#define IS_USED_CFG(cfg)	IS_USED_RUN(IS_ENABLED(cfg))
+#define IS_AVAIL2(v, s, cfg)	IS_AVAIL1(v, s), IS_AVAIL1(v, IS_USED_CFG(cfg))
+#define IS_AVAIL3(v, v2, s)	IS_AVAIL1(v, s), IS_AVAIL1(v, IS_DISABLED_RUN(v2))
+
+extern void arc_mmu_init(void);
+extern int arc_mmu_mumbojumbo(int cpu_id, char *buf, int len);
+
+extern void arc_cache_init(void);
+extern int arc_cache_mumbojumbo(int cpu_id, char *buf, int len);
+
+extern void __init handle_uboot_args(void);
+
+#endif /* __ASMARC_SETUP_H */
diff --git a/arch/arc/include/asm/shmparam.h b/arch/arc/include/asm/shmparam.h
new file mode 100644
index 000000000..719112af0
--- /dev/null
+++ b/arch/arc/include/asm/shmparam.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2013 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#ifndef __ARC_ASM_SHMPARAM_H
+#define __ARC_ASM_SHMPARAM_H
+
+/* Handle up to 2 cache bins */
+#define	SHMLBA	(2 * PAGE_SIZE)
+
+/* Enforce SHMLBA in shmat */
+#define __ARCH_FORCE_SHMLBA
+
+#endif
diff --git a/arch/arc/include/asm/smp.h b/arch/arc/include/asm/smp.h
new file mode 100644
index 000000000..990f83490
--- /dev/null
+++ b/arch/arc/include/asm/smp.h
@@ -0,0 +1,130 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#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 first_lines_of_secondary(void);
+extern const char *arc_platform_smp_cpuinfo(void);
+extern void arc_platform_smp_wait_to_boot(int);
+extern void start_kernel_secondary(void);
+
+/*
+ * API expected BY platform smp code (FROM arch smp code)
+ *
+ * smp_ipi_irq_setup:
+ *	Takes @cpu and @hwirq to which the arch-common ISR is hooked up
+ */
+extern int smp_ipi_irq_setup(int cpu, irq_hw_number_t hwirq);
+
+/*
+ * struct plat_smp_ops	- SMP callbacks provided by platform to ARC SMP
+ *
+ * @info:		SoC SMP specific info for /proc/cpuinfo etc
+ * @init_early_smp:	A SMP specific h/w block can init itself
+ * 			Could be common across platforms so not covered by
+ * 			mach_desc->init_early()
+ * @init_per_cpu:	Called for each core so SMP h/w block driver can do
+ * 			any needed setup per cpu (e.g. IPI request)
+ * @cpu_kick:		For Master to kickstart a cpu (optionally at a PC)
+ * @ipi_send:		To send IPI to a @cpu
+ * @ips_clear:		To clear IPI received at @irq
+ */
+struct plat_smp_ops {
+	const char 	*info;
+	void		(*init_early_smp)(void);
+	void		(*init_per_cpu)(int cpu);
+	void		(*cpu_kick)(int cpu, unsigned long pc);
+	void		(*ipi_send)(int cpu);
+	void		(*ipi_clear)(int irq);
+};
+
+/* TBD: stop exporting it for direct population by platform */
+extern struct plat_smp_ops  plat_smp_ops;
+
+#else /* CONFIG_SMP */
+
+static inline void smp_init_cpus(void) {}
+static inline const char *arc_platform_smp_cpuinfo(void)
+{
+	return "";
+}
+
+#endif  /* !CONFIG_SMP */
+
+/*
+ * ARC700 doesn't support atomic Read-Modify-Write ops.
+ * Originally Interrupts had to be disabled around code to guarantee 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 atomicity across CPUs needs to be
+ *	guaranteed 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;
+
+#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)
+
+#else /* !CONFIG_SMP */
+
+#define atomic_ops_lock(flags)		local_irq_save(flags)
+#define atomic_ops_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 000000000..192871608
--- /dev/null
+++ b/arch/arc/include/asm/spinlock.h
@@ -0,0 +1,382 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#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__)
+
+#ifdef CONFIG_ARC_HAS_LLSC
+
+static inline void arch_spin_lock(arch_spinlock_t *lock)
+{
+	unsigned int val;
+
+	__asm__ __volatile__(
+	"1:	llock	%[val], [%[slock]]	\n"
+	"	breq	%[val], %[LOCKED], 1b	\n"	/* spin while LOCKED */
+	"	scond	%[LOCKED], [%[slock]]	\n"	/* acquire */
+	"	bnz	1b			\n"
+	"					\n"
+	: [val]		"=&r"	(val)
+	: [slock]	"r"	(&(lock->slock)),
+	  [LOCKED]	"r"	(__ARCH_SPIN_LOCK_LOCKED__)
+	: "memory", "cc");
+
+	/*
+	 * ACQUIRE barrier to ensure load/store after taking the lock
+	 * don't "bleed-up" out of the critical section (leak-in is allowed)
+	 * http://www.spinics.net/lists/kernel/msg2010409.html
+	 *
+	 * ARCv2 only has load-load, store-store and all-all barrier
+	 * thus need the full all-all barrier
+	 */
+	smp_mb();
+}
+
+/* 1 - lock taken successfully */
+static inline int arch_spin_trylock(arch_spinlock_t *lock)
+{
+	unsigned int val, got_it = 0;
+
+	__asm__ __volatile__(
+	"1:	llock	%[val], [%[slock]]	\n"
+	"	breq	%[val], %[LOCKED], 4f	\n"	/* already LOCKED, just bail */
+	"	scond	%[LOCKED], [%[slock]]	\n"	/* acquire */
+	"	bnz	1b			\n"
+	"	mov	%[got_it], 1		\n"
+	"4:					\n"
+	"					\n"
+	: [val]		"=&r"	(val),
+	  [got_it]	"+&r"	(got_it)
+	: [slock]	"r"	(&(lock->slock)),
+	  [LOCKED]	"r"	(__ARCH_SPIN_LOCK_LOCKED__)
+	: "memory", "cc");
+
+	smp_mb();
+
+	return got_it;
+}
+
+static inline void arch_spin_unlock(arch_spinlock_t *lock)
+{
+	smp_mb();
+
+	WRITE_ONCE(lock->slock, __ARCH_SPIN_LOCK_UNLOCKED__);
+}
+
+/*
+ * Read-write spinlocks, allowing multiple readers but only one writer.
+ * Unfair locking as Writers could be starved indefinitely by Reader(s)
+ */
+
+static inline void arch_read_lock(arch_rwlock_t *rw)
+{
+	unsigned int val;
+
+	/*
+	 * zero means writer holds the lock exclusively, deny Reader.
+	 * Otherwise grant lock to first/subseq reader
+	 *
+	 * 	if (rw->counter > 0) {
+	 *		rw->counter--;
+	 *		ret = 1;
+	 *	}
+	 */
+
+	__asm__ __volatile__(
+	"1:	llock	%[val], [%[rwlock]]	\n"
+	"	brls	%[val], %[WR_LOCKED], 1b\n"	/* <= 0: spin while write locked */
+	"	sub	%[val], %[val], 1	\n"	/* reader lock */
+	"	scond	%[val], [%[rwlock]]	\n"
+	"	bnz	1b			\n"
+	"					\n"
+	: [val]		"=&r"	(val)
+	: [rwlock]	"r"	(&(rw->counter)),
+	  [WR_LOCKED]	"ir"	(0)
+	: "memory", "cc");
+
+	smp_mb();
+}
+
+/* 1 - lock taken successfully */
+static inline int arch_read_trylock(arch_rwlock_t *rw)
+{
+	unsigned int val, got_it = 0;
+
+	__asm__ __volatile__(
+	"1:	llock	%[val], [%[rwlock]]	\n"
+	"	brls	%[val], %[WR_LOCKED], 4f\n"	/* <= 0: already write locked, bail */
+	"	sub	%[val], %[val], 1	\n"	/* counter-- */
+	"	scond	%[val], [%[rwlock]]	\n"
+	"	bnz	1b			\n"	/* retry if collided with someone */
+	"	mov	%[got_it], 1		\n"
+	"					\n"
+	"4: ; --- done ---			\n"
+
+	: [val]		"=&r"	(val),
+	  [got_it]	"+&r"	(got_it)
+	: [rwlock]	"r"	(&(rw->counter)),
+	  [WR_LOCKED]	"ir"	(0)
+	: "memory", "cc");
+
+	smp_mb();
+
+	return got_it;
+}
+
+static inline void arch_write_lock(arch_rwlock_t *rw)
+{
+	unsigned int val;
+
+	/*
+	 * 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;
+	 *	}
+	 */
+
+	__asm__ __volatile__(
+	"1:	llock	%[val], [%[rwlock]]	\n"
+	"	brne	%[val], %[UNLOCKED], 1b	\n"	/* while !UNLOCKED spin */
+	"	mov	%[val], %[WR_LOCKED]	\n"
+	"	scond	%[val], [%[rwlock]]	\n"
+	"	bnz	1b			\n"
+	"					\n"
+	: [val]		"=&r"	(val)
+	: [rwlock]	"r"	(&(rw->counter)),
+	  [UNLOCKED]	"ir"	(__ARCH_RW_LOCK_UNLOCKED__),
+	  [WR_LOCKED]	"ir"	(0)
+	: "memory", "cc");
+
+	smp_mb();
+}
+
+/* 1 - lock taken successfully */
+static inline int arch_write_trylock(arch_rwlock_t *rw)
+{
+	unsigned int val, got_it = 0;
+
+	__asm__ __volatile__(
+	"1:	llock	%[val], [%[rwlock]]	\n"
+	"	brne	%[val], %[UNLOCKED], 4f	\n"	/* !UNLOCKED, bail */
+	"	mov	%[val], %[WR_LOCKED]	\n"
+	"	scond	%[val], [%[rwlock]]	\n"
+	"	bnz	1b			\n"	/* retry if collided with someone */
+	"	mov	%[got_it], 1		\n"
+	"					\n"
+	"4: ; --- done ---			\n"
+
+	: [val]		"=&r"	(val),
+	  [got_it]	"+&r"	(got_it)
+	: [rwlock]	"r"	(&(rw->counter)),
+	  [UNLOCKED]	"ir"	(__ARCH_RW_LOCK_UNLOCKED__),
+	  [WR_LOCKED]	"ir"	(0)
+	: "memory", "cc");
+
+	smp_mb();
+
+	return got_it;
+}
+
+static inline void arch_read_unlock(arch_rwlock_t *rw)
+{
+	unsigned int val;
+
+	smp_mb();
+
+	/*
+	 * rw->counter++;
+	 */
+	__asm__ __volatile__(
+	"1:	llock	%[val], [%[rwlock]]	\n"
+	"	add	%[val], %[val], 1	\n"
+	"	scond	%[val], [%[rwlock]]	\n"
+	"	bnz	1b			\n"
+	"					\n"
+	: [val]		"=&r"	(val)
+	: [rwlock]	"r"	(&(rw->counter))
+	: "memory", "cc");
+}
+
+static inline void arch_write_unlock(arch_rwlock_t *rw)
+{
+	smp_mb();
+
+	WRITE_ONCE(rw->counter, __ARCH_RW_LOCK_UNLOCKED__);
+}
+
+#else	/* !CONFIG_ARC_HAS_LLSC */
+
+static inline void arch_spin_lock(arch_spinlock_t *lock)
+{
+	unsigned int val = __ARCH_SPIN_LOCK_LOCKED__;
+
+	/*
+	 * Per lkmm, smp_mb() is only required after _lock (and before_unlock)
+	 * for ACQ and REL semantics respectively. However EX based spinlocks
+	 * need the extra smp_mb to workaround a hardware quirk.
+	 */
+	smp_mb();
+
+	__asm__ __volatile__(
+	"1:	ex  %0, [%1]		\n"
+	"	breq  %0, %2, 1b	\n"
+	: "+&r" (val)
+	: "r"(&(lock->slock)), "ir"(__ARCH_SPIN_LOCK_LOCKED__)
+	: "memory");
+
+	smp_mb();
+}
+
+/* 1 - lock taken successfully */
+static inline int arch_spin_trylock(arch_spinlock_t *lock)
+{
+	unsigned int val = __ARCH_SPIN_LOCK_LOCKED__;
+
+	smp_mb();
+
+	__asm__ __volatile__(
+	"1:	ex  %0, [%1]		\n"
+	: "+r" (val)
+	: "r"(&(lock->slock))
+	: "memory");
+
+	smp_mb();
+
+	return (val == __ARCH_SPIN_LOCK_UNLOCKED__);
+}
+
+static inline void arch_spin_unlock(arch_spinlock_t *lock)
+{
+	unsigned int val = __ARCH_SPIN_LOCK_UNLOCKED__;
+
+	/*
+	 * RELEASE barrier: given the instructions avail on ARCv2, full barrier
+	 * is the only option
+	 */
+	smp_mb();
+
+	/*
+	 * EX is not really required here, a simple STore of 0 suffices.
+	 * However this causes tasklist livelocks in SystemC based SMP virtual
+	 * platforms where the systemc core scheduler uses EX as a cue for
+	 * moving to next core. Do a git log of this file for details
+	 */
+	__asm__ __volatile__(
+	"	ex  %0, [%1]		\n"
+	: "+r" (val)
+	: "r"(&(lock->slock))
+	: "memory");
+
+	/*
+	 * see pairing version/comment in arch_spin_lock above
+	 */
+	smp_mb();
+}
+
+/*
+ * Read-write spinlocks, allowing multiple readers but only one writer.
+ * Unfair locking as Writers could be starved indefinitely by Reader(s)
+ *
+ * The spinlock itself is contained in @counter and access to it is
+ * serialized with @lock_mutex.
+ */
+
+/* 1 - lock taken successfully */
+static inline int arch_read_trylock(arch_rwlock_t *rw)
+{
+	int ret = 0;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	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));
+	local_irq_restore(flags);
+
+	return ret;
+}
+
+/* 1 - lock taken successfully */
+static inline int arch_write_trylock(arch_rwlock_t *rw)
+{
+	int ret = 0;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	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));
+	local_irq_restore(flags);
+
+	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)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	arch_spin_lock(&(rw->lock_mutex));
+	rw->counter++;
+	arch_spin_unlock(&(rw->lock_mutex));
+	local_irq_restore(flags);
+}
+
+static inline void arch_write_unlock(arch_rwlock_t *rw)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	arch_spin_lock(&(rw->lock_mutex));
+	rw->counter = __ARCH_RW_LOCK_UNLOCKED__;
+	arch_spin_unlock(&(rw->lock_mutex));
+	local_irq_restore(flags);
+}
+
+#endif
+
+#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 000000000..7cd037399
--- /dev/null
+++ b/arch/arc/include/asm/spinlock_types.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#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     : 0x0100_0000
+ * Read lock(s) : 0x00FF_FFFF to 0x01  (Multiple Readers decrement it)
+ * Write lock   : 0x0, but only if prior value is "unlocked" 0x0100_0000
+ */
+typedef struct {
+	volatile unsigned int	counter;
+#ifndef CONFIG_ARC_HAS_LLSC
+	arch_spinlock_t		lock_mutex;
+#endif
+} 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/stacktrace.h b/arch/arc/include/asm/stacktrace.h
new file mode 100644
index 000000000..4c50fb003
--- /dev/null
+++ b/arch/arc/include/asm/stacktrace.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
+ * Copyright (C) 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#ifndef __ASM_STACKTRACE_H
+#define __ASM_STACKTRACE_H
+
+#include <linux/sched.h>
+
+/**
+ * arc_unwind_core - Unwind the kernel mode stack for an execution context
+ * @tsk:		NULL for current task, specific task otherwise
+ * @regs:		pt_regs used to seed the unwinder {SP, FP, BLINK, PC}
+ * 			If NULL, use pt_regs of @tsk (if !NULL) otherwise
+ * 			use the current values of {SP, FP, BLINK, PC}
+ * @consumer_fn:	Callback invoked for each frame unwound
+ * 			Returns 0 to continue unwinding, -1 to stop
+ * @arg:		Arg to callback
+ *
+ * Returns the address of first function in stack
+ *
+ * Semantics:
+ *  - synchronous unwinding (e.g. dump_stack): @tsk  NULL, @regs  NULL
+ *  - Asynchronous unwinding of sleeping task: @tsk !NULL, @regs  NULL
+ *  - Asynchronous unwinding of intr/excp etc: @tsk !NULL, @regs !NULL
+ */
+notrace noinline unsigned int arc_unwind_core(
+	struct task_struct *tsk, struct pt_regs *regs,
+	int (*consumer_fn) (unsigned int, void *),
+	void *arg);
+
+#endif /* __ASM_STACKTRACE_H */
diff --git a/arch/arc/include/asm/string.h b/arch/arc/include/asm/string.h
new file mode 100644
index 000000000..3182ea9dc
--- /dev/null
+++ b/arch/arc/include/asm/string.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * 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>
+
+#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 /* _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 000000000..5806106a6
--- /dev/null
+++ b/arch/arc/include/asm/switch_to.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#ifndef _ASM_ARC_SWITCH_TO_H
+#define _ASM_ARC_SWITCH_TO_H
+
+#ifndef __ASSEMBLER__
+
+#include <linux/sched.h>
+#include <asm/dsp-impl.h>
+#include <asm/fpu.h>
+
+struct task_struct *__switch_to(struct task_struct *p, struct task_struct *n);
+
+#define switch_to(prev, next, last)	\
+do {					\
+	dsp_save_restore(prev, next);	\
+	fpu_save_restore(prev, next);	\
+	last = __switch_to(prev, 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 000000000..728d625a1
--- /dev/null
+++ b/arch/arc/include/asm/syscall.h
@@ -0,0 +1,105 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#ifndef _ASM_ARC_SYSCALL_H
+#define _ASM_ARC_SYSCALL_H  1
+
+#include <uapi/linux/audit.h>
+#include <linux/err.h>
+#include <linux/sched.h>
+#include <asm/unistd.h>
+#include <asm/ptrace.h>		/* in_syscall() */
+
+extern void *sys_call_table[];
+
+static inline long
+syscall_get_nr(struct task_struct *task, struct pt_regs *regs)
+{
+	if (user_mode(regs) && in_syscall(regs))
+		return regs->r8;
+	else
+		return -1;
+}
+
+static inline void
+syscall_set_nr(struct task_struct *task, struct pt_regs *regs, int nr)
+{
+	/*
+	 * Unlike syscall_get_nr(), syscall_set_nr() can be called only when
+	 * the target task is stopped for tracing on entering syscall, so
+	 * there is no need to have the same check syscall_get_nr() has.
+	 */
+	regs->r8 = nr;
+}
+
+static inline void
+syscall_rollback(struct task_struct *task, struct pt_regs *regs)
+{
+	regs->r0 = regs->orig_r0;
+}
+
+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 long *args)
+{
+	unsigned long *inside_ptregs = &(regs->r0);
+	unsigned int n = 6;
+	unsigned int i = 0;
+
+	while (n--) {
+		args[i++] = (*inside_ptregs);
+		inside_ptregs--;
+	}
+}
+
+static inline void
+syscall_set_arguments(struct task_struct *task, struct pt_regs *regs,
+		      unsigned long *args)
+{
+	unsigned long *inside_ptregs = &regs->r0;
+	unsigned int n = 6;
+	unsigned int i = 0;
+
+	while (n--) {
+		*inside_ptregs = args[i++];
+		inside_ptregs--;
+	}
+}
+
+static inline int
+syscall_get_arch(struct task_struct *task)
+{
+	return IS_ENABLED(CONFIG_ISA_ARCOMPACT)
+		? (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)
+			? AUDIT_ARCH_ARCOMPACTBE : AUDIT_ARCH_ARCOMPACT)
+		: (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)
+			? AUDIT_ARCH_ARCV2BE : AUDIT_ARCH_ARCV2);
+}
+
+#endif
diff --git a/arch/arc/include/asm/syscalls.h b/arch/arc/include/asm/syscalls.h
new file mode 100644
index 000000000..c3f4714a4
--- /dev/null
+++ b/arch/arc/include/asm/syscalls.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#ifndef _ASM_ARC_SYSCALLS_H
+#define _ASM_ARC_SYSCALLS_H  1
+
+#include <linux/compiler.h>
+#include <linux/linkage.h>
+#include <linux/types.h>
+
+int sys_clone_wrapper(int, int, int, int, int);
+int sys_clone3_wrapper(void *, size_t);
+int sys_cacheflush(uint32_t, uint32_t uint32_t);
+int sys_arc_settls(void *);
+int sys_arc_gettls(void);
+int sys_arc_usr_cmpxchg(int *, int, int);
+
+#include <asm-generic/syscalls.h>
+
+#endif
diff --git a/arch/arc/include/asm/thread_info.h b/arch/arc/include/asm/thread_info.h
new file mode 100644
index 000000000..255d2c774
--- /dev/null
+++ b/arch/arc/include/asm/thread_info.h
@@ -0,0 +1,106 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * 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
+
+#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)
+#define THREAD_SHIFT	(PAGE_SHIFT << THREAD_SIZE_ORDER)
+
+#ifndef __ASSEMBLER__
+
+#include <linux/thread_info.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 */
+	unsigned long ksp;		/* kernel mode stack top in __switch_to */
+	int preempt_count;		/* 0 => preemptible, <0 => BUG */
+	int cpu;			/* current CPU */
+	unsigned long thr_ptr;		/* TLS ptr */
+	struct task_struct *task;	/* main task structure */
+};
+
+/*
+ * initilaize thread_info for any @tsk
+ *  - this is not related to init_task per se
+ */
+#define INIT_THREAD_INFO(tsk)			\
+{						\
+	.task       = &tsk,			\
+	.flags      = 0,			\
+	.cpu        = 0,			\
+	.preempt_count  = INIT_PREEMPT_COUNT,	\
+}
+
+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 /* !__ASSEMBLER__ */
+
+/*
+ * 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_NOTIFY_SIGNAL	5	/* signal notifications exist */
+#define TIF_SYSCALL_TRACE	15	/* syscall trace active */
+/* true if poll_idle() is polling TIF_NEED_RESCHED */
+#define TIF_MEMDIE		16
+#define TIF_SYSCALL_TRACEPOINT	17	/* syscall tracepoint instrumentation */
+
+#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_NOTIFY_SIGNAL	(1<<TIF_NOTIFY_SIGNAL)
+#define _TIF_MEMDIE		(1<<TIF_MEMDIE)
+#define _TIF_SYSCALL_TRACEPOINT	(1<<TIF_SYSCALL_TRACEPOINT)
+
+/* work to do on interrupt/exception return */
+#define _TIF_WORK_MASK		(_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
+				 _TIF_NOTIFY_RESUME | _TIF_NOTIFY_SIGNAL)
+
+#define _TIF_SYSCALL_WORK	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_TRACEPOINT)
+
+/*
+ * _TIF_ALLWORK_MASK includes SYSCALL_TRACE, but we don't need it.
+ * SYSCALL_TRACE is anyway separately/unconditionally tested right after a
+ * syscall, so all that remains to be tested is _TIF_WORK_MASK
+ */
+
+#endif /* _ASM_THREAD_INFO_H */
diff --git a/arch/arc/include/asm/tlb.h b/arch/arc/include/asm/tlb.h
new file mode 100644
index 000000000..975b35d37
--- /dev/null
+++ b/arch/arc/include/asm/tlb.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#ifndef _ASM_ARC_TLB_H
+#define _ASM_ARC_TLB_H
+
+#include <linux/pagemap.h>
+#include <asm-generic/tlb.h>
+
+#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 000000000..992a2837a
--- /dev/null
+++ b/arch/arc/include/asm/tlbflush.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#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);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+void local_flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
+			       unsigned long end);
+#endif
+
+#ifndef CONFIG_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)
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define flush_pmd_tlb_range(vma, s, e)	local_flush_pmd_tlb_range(vma, s, e)
+#endif
+#else
+extern void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
+							 unsigned long end);
+extern void flush_tlb_page(struct vm_area_struct *vma, unsigned long page);
+extern void flush_tlb_kernel_range(unsigned long start, unsigned long end);
+extern void flush_tlb_all(void);
+extern void flush_tlb_mm(struct mm_struct *mm);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+extern void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end);
+#endif
+#endif /* CONFIG_SMP */
+#endif
diff --git a/arch/arc/include/asm/uaccess.h b/arch/arc/include/asm/uaccess.h
new file mode 100644
index 000000000..6df220954
--- /dev/null
+++ b/arch/arc/include/asm/uaccess.h
@@ -0,0 +1,637 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * 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/string.h>	/* for generic string functions */
+
+/*********** 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:	# return -EFAULT\n"		\
+	"	mov %0, %3\n"			\
+	"	# zero out dst ptr\n"		\
+	"	mov %1,  0\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:	# return -EFAULT\n"		\
+	"	mov %0, %3\n"			\
+	"	# zero out dst ptr\n"		\
+	"	mov %1,  0\n"			\
+	"	mov %R1, 0\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
+raw_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;
+
+	/* fallback for unaligned access when hardware doesn't support */
+	if (!IS_ENABLED(CONFIG_ARC_USE_UNALIGNED_MEM_ACCESS) &&
+	     (((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", "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;
+}
+
+static inline unsigned long
+raw_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;
+
+	/* fallback for unaligned access when hardware doesn't support */
+	if (!IS_ENABLED(CONFIG_ARC_USE_UNALIGNED_MEM_ACCESS) &&
+	     (((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", "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 __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", "memory");
+
+	return res;
+}
+
+#define INLINE_COPY_USER
+
+#define __clear_user			__clear_user
+
+#include <asm-generic/uaccess.h>
+
+#endif
diff --git a/arch/arc/include/asm/unistd.h b/arch/arc/include/asm/unistd.h
new file mode 100644
index 000000000..211c230d8
--- /dev/null
+++ b/arch/arc/include/asm/unistd.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _ASM_ARC_UNISTD_H
+#define _ASM_ARC_UNISTD_H
+
+#include <uapi/asm/unistd.h>
+
+#define __ARCH_WANT_STAT64
+#define __ARCH_WANT_SYS_CLONE
+#define __ARCH_WANT_SYS_VFORK
+#define __ARCH_WANT_SYS_FORK
+
+#define NR_syscalls __NR_syscalls
+
+#endif
diff --git a/arch/arc/include/asm/unwind.h b/arch/arc/include/asm/unwind.h
new file mode 100644
index 000000000..e95a20453
--- /dev/null
+++ b/arch/arc/include/asm/unwind.h
@@ -0,0 +1,156 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#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 *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)
+{
+}
+
+#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/asm/vermagic.h b/arch/arc/include/asm/vermagic.h
new file mode 100644
index 000000000..a10257d2c
--- /dev/null
+++ b/arch/arc/include/asm/vermagic.h
@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _ASM_VERMAGIC_H
+#define _ASM_VERMAGIC_H
+
+#define MODULE_ARCH_VERMAGIC "ARC700"
+
+#endif /* _ASM_VERMAGIC_H */
diff --git a/arch/arc/include/asm/vmalloc.h b/arch/arc/include/asm/vmalloc.h
new file mode 100644
index 000000000..973095aad
--- /dev/null
+++ b/arch/arc/include/asm/vmalloc.h
@@ -0,0 +1,4 @@
+#ifndef _ASM_ARC_VMALLOC_H
+#define _ASM_ARC_VMALLOC_H
+
+#endif /* _ASM_ARC_VMALLOC_H */
diff --git a/arch/arc/include/uapi/asm/Kbuild b/arch/arc/include/uapi/asm/Kbuild
new file mode 100644
index 000000000..2501e82a1
--- /dev/null
+++ b/arch/arc/include/uapi/asm/Kbuild
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
+syscall-y += unistd_32.h
+
+generic-y += ucontext.h
diff --git a/arch/arc/include/uapi/asm/bpf_perf_event.h b/arch/arc/include/uapi/asm/bpf_perf_event.h
new file mode 100644
index 000000000..6cb1c2823
--- /dev/null
+++ b/arch/arc/include/uapi/asm/bpf_perf_event.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI__ASM_BPF_PERF_EVENT_H__
+#define _UAPI__ASM_BPF_PERF_EVENT_H__
+
+#include <asm/ptrace.h>
+
+typedef struct user_regs_struct bpf_user_pt_regs_t;
+
+#endif /* _UAPI__ASM_BPF_PERF_EVENT_H__ */
diff --git a/arch/arc/include/uapi/asm/byteorder.h b/arch/arc/include/uapi/asm/byteorder.h
new file mode 100644
index 000000000..554011153
--- /dev/null
+++ b/arch/arc/include/uapi/asm/byteorder.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * 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 __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 000000000..0e4f2affc
--- /dev/null
+++ b/arch/arc/include/uapi/asm/cachectl.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * 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 000000000..3c1dae4e5
--- /dev/null
+++ b/arch/arc/include/uapi/asm/elf.h
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * 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_V3		0x00000300   /* v3 (no legacy syscalls) */
+#define EF_ARC_OSABI_V4		0x00000400   /* v4 (64bit data any reg align) */
+
+#if __GNUC__ < 6
+#define EF_ARC_OSABI_CURRENT	EF_ARC_OSABI_V3
+#else
+#define EF_ARC_OSABI_CURRENT	EF_ARC_OSABI_V4
+#endif
+
+typedef unsigned long elf_greg_t;
+typedef unsigned long elf_fpregset_t;
+
+#define ELF_NGREG	(sizeof(struct user_regs_struct) / sizeof(elf_greg_t))
+#define ELF_ARCV2REG	(sizeof(struct user_regs_arcv2) / 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 000000000..4606a326a
--- /dev/null
+++ b/arch/arc/include/uapi/asm/page.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * 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
+
+#include <linux/const.h>
+
+/* PAGE_SHIFT determines the page size */
+#ifdef __KERNEL__
+#include <vdso/page.h>
+#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
+#define PAGE_SIZE	_BITUL(PAGE_SHIFT)	/* Default 8K */
+#define PAGE_MASK	(~(PAGE_SIZE-1))
+#endif
+
+#define PAGE_OFFSET	_AC(0x80000000, UL)	/* Kernel starts at 2G onwrds */
+
+#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 000000000..3ae832db2
--- /dev/null
+++ b/arch/arc/include/uapi/asm/ptrace.h
@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * 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
+
+#define PTRACE_GET_THREAD_AREA	25
+
+#ifndef __ASSEMBLER__
+/*
+ * 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.
+ *
+ * The intermediate pad,pad2 are relics of initial layout based on pt_regs
+ * for optimizations when copying pt_regs to/from user_regs_struct.
+ * We no longer need them, but can't be changed as they are part of ABI now.
+ *
+ * Also, sigcontext only care about the scratch regs as that is what we really
+ * save/restore for signal handling. However gdb also uses the same struct
+ * hence callee regs need to be in there too.
+*/
+struct user_regs_struct {
+
+	unsigned long pad;
+	struct {
+		unsigned long bta, lp_start, lp_end, lp_count;
+		unsigned long status32, ret, blink, fp, gp;
+		unsigned long r12, r11, r10, r9, r8, r7, r6, r5, r4, r3, r2, r1, r0;
+		unsigned long sp;
+	} scratch;
+	unsigned long pad2;
+	struct {
+		unsigned long r25, r24, r23, r22, r21, r20;
+		unsigned long r19, r18, r17, r16, r15, r14, r13;
+	} callee;
+	unsigned long efa;	/* break pt addr, for break points in delay slots */
+	unsigned long stop_pc;	/* give dbg stop_pc after ensuring brkpt trap */
+};
+
+struct user_regs_arcv2 {
+	unsigned long r30, r58, r59;
+};
+
+#endif /* !__ASSEMBLER__ */
+
+#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 000000000..a6d4e4493
--- /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 000000000..7a5449dfc
--- /dev/null
+++ b/arch/arc/include/uapi/asm/sigcontext.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * 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;
+	struct user_regs_arcv2 v2abi;
+};
+
+#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 000000000..ba3143a1b
--- /dev/null
+++ b/arch/arc/include/uapi/asm/signal.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * 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 000000000..417ea30f2
--- /dev/null
+++ b/arch/arc/include/uapi/asm/swab.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * 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>
+
+#define __arch_swab32(x)		\
+({					\
+	unsigned int tmp = x;		\
+	__asm__(			\
+	"	swape	%0, %1	\n"	\
+	: "=r" (tmp)			\
+	: "r" (tmp));			\
+	tmp;				\
+})
+
+#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 000000000..cb2905c7c
--- /dev/null
+++ b/arch/arc/include/uapi/asm/unistd.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * 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/unistd_32.h>
diff --git a/arch/arc/kernel/.gitignore b/arch/arc/kernel/.gitignore
new file mode 100644
index 000000000..bbb90f92d
--- /dev/null
+++ b/arch/arc/kernel/.gitignore
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+vmlinux.lds
diff --git a/arch/arc/kernel/Makefile b/arch/arc/kernel/Makefile
new file mode 100644
index 000000000..fa94fff02
--- /dev/null
+++ b/arch/arc/kernel/Makefile
@@ -0,0 +1,29 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+#
+
+obj-y	:= head.o arcksyms.o setup.o irq.o reset.o ptrace.o process.o devtree.o
+obj-y	+= signal.o traps.o sys.o troubleshoot.o stacktrace.o disasm.o
+obj-y	+= ctx_sw_asm.o
+
+obj-$(CONFIG_ISA_ARCOMPACT)		+= entry-compact.o intc-compact.o
+obj-$(CONFIG_ISA_ARCV2)			+= entry-arcv2.o intc-arcv2.o
+
+obj-$(CONFIG_MODULES)			+= arcksyms.o module.o
+obj-$(CONFIG_SMP) 			+= smp.o
+obj-$(CONFIG_ARC_MCIP)			+= mcip.o
+obj-$(CONFIG_ARC_DW2_UNWIND)		+= unwind.o
+obj-$(CONFIG_KPROBES)      		+= kprobes.o
+obj-$(CONFIG_ARC_EMUL_UNALIGNED) 	+= unaligned.o
+obj-$(CONFIG_KGDB)			+= kgdb.o
+obj-$(CONFIG_ARC_METAWARE_HLINK)	+= arc_hostlink.o
+obj-$(CONFIG_PERF_EVENTS)		+= perf_event.o
+obj-$(CONFIG_JUMP_LABEL)		+= jump_label.o
+
+obj-$(CONFIG_ARC_FPU_SAVE_RESTORE)	+= fpu.o
+ifdef CONFIG_ISA_ARCOMPACT
+CFLAGS_fpu.o   += -mdpfp
+endif
+
+always-$(KBUILD_BUILTIN) := vmlinux.lds
diff --git a/arch/arc/kernel/Makefile.syscalls b/arch/arc/kernel/Makefile.syscalls
new file mode 100644
index 000000000..391d30ab7
--- /dev/null
+++ b/arch/arc/kernel/Makefile.syscalls
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0
+
+syscall_abis_32 += arc time32 renameat stat64 rlimit
diff --git a/arch/arc/kernel/arc_hostlink.c b/arch/arc/kernel/arc_hostlink.c
new file mode 100644
index 000000000..08c5196ef
--- /dev/null
+++ b/arch/arc/kernel/arc_hostlink.c
@@ -0,0 +1,55 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * 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)
+ */
+
+#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 000000000..8851c0a19
--- /dev/null
+++ b/arch/arc/kernel/arcksyms.c
@@ -0,0 +1,54 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * arcksyms.c - Exporting symbols not exportable from their own sources
+ *
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#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);
+extern void __udivdi3(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);
+EXPORT_SYMBOL(__udivdi3);
+
+/* 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 000000000..2978da85f
--- /dev/null
+++ b/arch/arc/kernel/asm-offsets.c
@@ -0,0 +1,85 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+#define COMPILE_OFFSETS
+
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/interrupt.h>
+#include <linux/thread_info.h>
+#include <linux/kbuild.h>
+#include <linux/ptrace.h>
+#include <asm/hardirq.h>
+#include <asm/page.h>
+
+
+int main(void)
+{
+	DEFINE(TASK_THREAD, offsetof(struct task_struct, thread));
+	DEFINE(TASK_THREAD_INFO, offsetof(struct task_struct, stack));
+
+	BLANK();
+
+	DEFINE(THREAD_CALLEE_REG, offsetof(struct thread_struct, callee_reg));
+	DEFINE(THREAD_FAULT_ADDR,
+	       offsetof(struct thread_struct, fault_address));
+
+	BLANK();
+
+	DEFINE(THREAD_INFO_KSP, offsetof(struct thread_info, ksp));
+	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(TASK_PID, offsetof(struct task_struct, pid));
+	DEFINE(TASK_COMM, offsetof(struct task_struct, comm));
+
+	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_event, offsetof(struct pt_regs, ecr));
+	DEFINE(PT_bta, offsetof(struct pt_regs, bta));
+	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));
+	DEFINE(PT_r8, offsetof(struct pt_regs, r8));
+	DEFINE(PT_r10, offsetof(struct pt_regs, r10));
+	DEFINE(PT_r26, offsetof(struct pt_regs, r26));
+	DEFINE(PT_ret, offsetof(struct pt_regs, ret));
+	DEFINE(PT_blink, offsetof(struct pt_regs, blink));
+	OFFSET(PT_fp, pt_regs, fp);
+	DEFINE(PT_lpe, offsetof(struct pt_regs, lp_end));
+	DEFINE(PT_lpc, offsetof(struct pt_regs, lp_count));
+#ifdef CONFIG_ISA_ARCV2
+	OFFSET(PT_r12, pt_regs, r12);
+	OFFSET(PT_r30, pt_regs, r30);
+#endif
+#ifdef CONFIG_ARC_HAS_ACCL_REGS
+	OFFSET(PT_r58, pt_regs, r58);
+	OFFSET(PT_r59, pt_regs, r59);
+#endif
+#ifdef CONFIG_ARC_DSP_SAVE_RESTORE_REGS
+	OFFSET(PT_DSP_CTRL, pt_regs, DSP_CTRL);
+#endif
+
+	DEFINE(SZ_CALLEE_REGS, sizeof(struct callee_regs));
+	DEFINE(SZ_PT_REGS, sizeof(struct pt_regs));
+
+	return 0;
+}
diff --git a/arch/arc/kernel/ctx_sw_asm.S b/arch/arc/kernel/ctx_sw_asm.S
new file mode 100644
index 000000000..48e1f2197
--- /dev/null
+++ b/arch/arc/kernel/ctx_sw_asm.S
@@ -0,0 +1,64 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * Vineetg: Aug 2009
+ *  -Moved core context switch macro out of entry.S into this file.
+ *  -This is the more "natural" hand written assembler
+ */
+
+#include <linux/linkage.h>
+#include <asm/entry.h>       /* For the SAVE_* macros */
+#include <asm/asm-offsets.h>
+
+; IN
+;  - r0: prev task (also current)
+;  - r1: next task
+; OUT
+;  - r0: prev task (so r0 not touched)
+
+	.section .sched.text,"ax",@progbits
+ENTRY_CFI(__switch_to)
+
+	/* save kernel stack frame regs of @prev task */
+	push	blink
+	CFI_DEF_CFA_OFFSET 4
+	CFI_OFFSET r31, -4
+
+	push	fp
+	CFI_DEF_CFA_OFFSET 8
+	CFI_OFFSET r27, -8
+
+	mov	fp, sp
+	CFI_DEF_CFA_REGISTER r27
+
+	/* kernel mode callee regs of @prev */
+	SAVE_CALLEE_SAVED_KERNEL
+
+	/*
+	 * save final SP to @prev->thread_info.ksp
+	 * @prev is "current" so thread_info derived from SP
+	 */
+	GET_CURR_THR_INFO_FROM_SP  r10
+	st	sp,  [r10, THREAD_INFO_KSP]
+
+	/* update @next in _current_task[] and GP register caching it */
+	SET_CURR_TASK_ON_CPU  r1, r10
+
+	/* load SP from @next->thread_info.ksp */
+	ld	r10, [r1, TASK_THREAD_INFO]
+	ld	sp,  [r10, THREAD_INFO_KSP]
+
+	/* restore callee regs, stack frame regs of @next */
+	RESTORE_CALLEE_SAVED_KERNEL
+
+	pop	fp
+	CFI_RESTORE r27
+	CFI_DEF_CFA r28, 4
+
+	pop	blink
+	CFI_RESTORE r31
+	CFI_DEF_CFA_OFFSET 0
+
+	j      [blink]
+END_CFI(__switch_to)
diff --git a/arch/arc/kernel/devtree.c b/arch/arc/kernel/devtree.c
new file mode 100644
index 000000000..cc6ac7d12
--- /dev/null
+++ b/arch/arc/kernel/devtree.c
@@ -0,0 +1,76 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * Based on reduced version of METAG
+ */
+
+
+#include <linux/init.h>
+#include <linux/reboot.h>
+#include <linux/memblock.h>
+#include <linux/of.h>
+#include <linux/of_fdt.h>
+#include <asm/mach_desc.h>
+#include <asm/serial.h>
+
+#ifdef CONFIG_SERIAL_EARLYCON
+
+static unsigned int __initdata arc_base_baud;
+
+unsigned int __init arc_early_base_baud(void)
+{
+	return arc_base_baud/16;
+}
+
+static void __init arc_set_early_base_baud(unsigned long dt_root)
+{
+	if (of_flat_dt_is_compatible(dt_root, "abilis,arc-tb10x"))
+		arc_base_baud = 166666666;	/* Fixed 166.6MHz clk (TB10x) */
+	else if (of_flat_dt_is_compatible(dt_root, "snps,arc-sdp") ||
+		 of_flat_dt_is_compatible(dt_root, "snps,hsdk"))
+		arc_base_baud = 33333333;	/* Fixed 33MHz clk (AXS10x & HSDK) */
+	else
+		arc_base_baud = 50000000;	/* Fixed default 50MHz */
+}
+#else
+#define arc_set_early_base_baud(dt_root)
+#endif
+
+static const void * __init arch_get_next_mach(const char *const **match)
+{
+	static const struct machine_desc *mdesc = __arch_info_begin;
+	const struct machine_desc *m = mdesc;
+
+	if (m >= __arch_info_end)
+		return NULL;
+
+	mdesc++;
+	*match = m->dt_compat;
+	return m;
+}
+
+/**
+ * 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.
+ */
+const struct machine_desc * __init setup_machine_fdt(void *dt)
+{
+	const struct machine_desc *mdesc;
+	unsigned long dt_root;
+
+	if (!early_init_dt_scan(dt, __pa(dt)))
+		return NULL;
+
+	mdesc = of_flat_dt_match_machine(NULL, arch_get_next_mach);
+	if (!mdesc)
+		machine_halt();
+
+	dt_root = of_get_flat_dt_root();
+	arc_set_early_base_baud(dt_root);
+
+	return mdesc;
+}
diff --git a/arch/arc/kernel/disasm.c b/arch/arc/kernel/disasm.c
new file mode 100644
index 000000000..ccc7e8c39
--- /dev/null
+++ b/arch/arc/kernel/disasm.c
@@ -0,0 +1,594 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * 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)
+ */
+
+#include <linux/types.h>
+#include <linux/kprobes.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <asm/disasm.h>
+
+#if defined(CONFIG_KGDB) || defined(CONFIG_ARC_EMUL_UNALIGNED) || \
+	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;
+		fallthrough;
+
+	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 unaligned 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 defined(CONFIG_ISA_ARCOMPACT)
+	if (reg <= 12) {
+		p = &regs->r0;
+		return p[-reg];
+	}
+#else /* CONFIG_ISA_ARCV2 */
+	if (reg <= 11) {
+		p = &regs->r0;
+		return p[reg];
+	}
+
+	if (reg == 12)
+		return regs->r12;
+	if (reg == 30)
+		return regs->r30;
+#ifdef CONFIG_ARC_HAS_ACCL_REGS
+	if (reg == 58)
+		return regs->r58;
+	if (reg == 59)
+		return regs->r59;
+#endif
+#endif
+	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;
+
+#if defined(CONFIG_ISA_ARCOMPACT)
+	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;
+	}
+#else /* CONFIG_ISA_ARCV2 */
+	switch (reg) {
+	case 0 ... 11:
+		p = &regs->r0;
+		p[reg] = val;
+		break;
+	case 12:
+		regs->r12 = 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 30:
+		regs->r30 = val;
+		break;
+	case 31:
+		regs->blink = val;
+		break;
+#ifdef CONFIG_ARC_HAS_ACCL_REGS
+	case 58:
+		regs->r58 = val;
+		break;
+	case 59:
+		regs->r59 = val;
+		break;
+#endif
+	default:
+		break;
+	}
+#endif
+}
+
+/*
+ * 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;
+
+	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_ARC_EMUL_UNALIGNED || CONFIG_KPROBES */
diff --git a/arch/arc/kernel/entry-arcv2.S b/arch/arc/kernel/entry-arcv2.S
new file mode 100644
index 000000000..e238b5fd3
--- /dev/null
+++ b/arch/arc/kernel/entry-arcv2.S
@@ -0,0 +1,249 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * ARCv2 ISA based core Low Level Intr/Traps/Exceptions(non-TLB) Handling
+ *
+ * Copyright (C) 2013 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#include <linux/linkage.h>   /* ARC_{ENTRY,EXIT} */
+#include <asm/entry.h>       /* SAVE_ALL_{INT1,INT2,TRAP...} */
+#include <asm/errno.h>
+#include <asm/arcregs.h>
+#include <asm/irqflags.h>
+#include <asm/mmu.h>
+
+; A maximum number of supported interrupts in the core interrupt controller.
+; This number is not equal to the maximum interrupt number (256) because
+; first 16 lines are reserved for exceptions and are not configurable.
+#define NR_CPU_IRQS	240
+
+	.cpu HS
+
+#define VECTOR	.word
+
+;############################ Vector Table #################################
+
+	.section .vector,"a",@progbits
+	.align 4
+
+# Initial 16 slots are Exception Vectors
+VECTOR	res_service		; Reset Vector
+VECTOR	mem_service		; Mem exception
+VECTOR	instr_service		; Instrn Error
+VECTOR	EV_MachineCheck		; Fatal Machine check
+VECTOR	EV_TLBMissI		; Instruction TLB miss
+VECTOR	EV_TLBMissD		; Data TLB miss
+VECTOR	EV_TLBProtV		; Protection Violation
+VECTOR	EV_PrivilegeV		; Privilege Violation
+VECTOR	EV_SWI			; Software Breakpoint
+VECTOR	EV_Trap			; Trap exception
+VECTOR	EV_Extension		; Extn Instruction Exception
+VECTOR	EV_DivZero		; Divide by Zero
+VECTOR	EV_DCError		; Data Cache Error
+VECTOR	EV_Misaligned		; Misaligned Data Access
+VECTOR	reserved		; Reserved slots
+VECTOR	reserved		; Reserved slots
+
+# Begin Interrupt Vectors
+VECTOR	handle_interrupt	; (16) Timer0
+VECTOR	handle_interrupt	; unused (Timer1)
+VECTOR	handle_interrupt	; unused (WDT)
+VECTOR	handle_interrupt	; (19) Inter core Interrupt (IPI)
+VECTOR	handle_interrupt	; (20) perf Interrupt
+VECTOR	handle_interrupt	; (21) Software Triggered Intr (Self IPI)
+VECTOR	handle_interrupt	; unused
+VECTOR	handle_interrupt	; (23) unused
+# End of fixed IRQs
+
+.rept NR_CPU_IRQS - 8
+	VECTOR	handle_interrupt
+.endr
+
+	.section .text, "ax",@progbits
+
+reserved:
+	flag 1		; Unexpected event, halt
+
+;##################### Interrupt Handling ##############################
+
+ENTRY(handle_interrupt)
+
+	INTERRUPT_PROLOGUE
+
+	# irq control APIs local_irq_save/restore/disable/enable fiddle with
+	# global interrupt enable bits in STATUS32 (.IE for 1 prio, .E[] for 2 prio)
+	# However a taken interrupt doesn't clear these bits. Thus irqs_disabled()
+	# query in hard ISR path would return false (since .IE is set) which would
+	# trips genirq interrupt handling asserts.
+	#
+	# So do a "soft" disable of interrupts here.
+	#
+	# Note this disable is only for consistent book-keeping as further interrupts
+	# will be disabled anyways even w/o this. Hardware tracks active interrupts
+	# separately in AUX_IRQ_ACT.active and will not take new interrupts
+	# unless this one returns (or higher prio becomes pending in 2-prio scheme)
+
+	IRQ_DISABLE
+
+	; icause is banked: one per priority level
+	; so a higher prio interrupt taken here won't clobber prev prio icause
+	lr  r0, [ICAUSE]
+	mov   blink, ret_from_exception
+
+	b.d  arch_do_IRQ
+	mov r1, sp
+
+END(handle_interrupt)
+
+;################### Non TLB Exception Handling #############################
+
+ENTRY(EV_SWI)
+	; TODO: implement this
+	EXCEPTION_PROLOGUE
+	b   ret_from_exception
+END(EV_SWI)
+
+ENTRY(EV_DivZero)
+	; TODO: implement this
+	EXCEPTION_PROLOGUE
+	b   ret_from_exception
+END(EV_DivZero)
+
+ENTRY(EV_DCError)
+	; TODO: implement this
+	EXCEPTION_PROLOGUE
+	b   ret_from_exception
+END(EV_DCError)
+
+; ---------------------------------------------
+; Memory Error Exception Handler
+;   - Unlike ARCompact, handles Bus errors for both User/Kernel mode,
+;     Instruction fetch or Data access, under a single Exception Vector
+; ---------------------------------------------
+
+ENTRY(mem_service)
+
+	EXCEPTION_PROLOGUE
+
+	bl  do_memory_error
+	b   ret_from_exception
+END(mem_service)
+
+ENTRY(EV_Misaligned)
+
+	EXCEPTION_PROLOGUE
+
+	SAVE_CALLEE_SAVED_USER
+	mov r2, sp              ; callee_regs
+
+	bl  do_misaligned_access
+
+	; TBD: optimize - do this only if a callee reg was involved
+	; either a dst of emulated LD/ST or src with address-writeback
+	RESTORE_CALLEE_SAVED_USER
+
+	b   ret_from_exception
+END(EV_Misaligned)
+
+; ---------------------------------------------
+; Protection Violation Exception Handler
+; ---------------------------------------------
+
+ENTRY(EV_TLBProtV)
+
+	EXCEPTION_PROLOGUE
+
+	mov blink, ret_from_exception
+	b   do_page_fault
+
+END(EV_TLBProtV)
+
+; From Linux standpoint Slow Path I/D TLB Miss is same a ProtV as they
+; need to call do_page_fault().
+; ECR in pt_regs provides whether access was R/W/X
+
+.global        call_do_page_fault
+.set call_do_page_fault, EV_TLBProtV
+
+;############# Common Handlers for ARCompact and ARCv2 ##############
+
+#include "entry.S"
+
+;############# Return from Intr/Excp/Trap (ARCv2 ISA Specifics) ##############
+;
+; Restore the saved sys context (common exit-path for EXCPN/IRQ/Trap)
+; IRQ shd definitely not happen between now and rtie
+; All 2 entry points to here already disable interrupts
+
+.Lrestore_regs:
+restore_regs:
+
+	# Interrpts are actually disabled from this point on, but will get
+	# reenabled after we return from interrupt/exception.
+	# But irq tracer needs to be told now...
+	TRACE_ASM_IRQ_ENABLE
+
+	ld	r0, [sp, PT_status32]	; U/K mode at time of entry
+	lr	r10, [AUX_IRQ_ACT]
+
+	bmsk	r11, r10, 15		; extract AUX_IRQ_ACT.active
+	breq	r11, 0, .Lexcept_ret	; No intr active, ret from Exception
+
+;####### Return from Intr #######
+
+.Lisr_ret:
+
+debug_marker_l1:
+	; bbit1.nt r0, STATUS_DE_BIT, .Lintr_ret_to_delay_slot
+	btst	r0, STATUS_DE_BIT		; Z flag set if bit clear
+	bnz	.Lintr_ret_to_delay_slot	; branch if STATUS_DE_BIT set
+
+	; Handle special case #1: (Entry via Exception, Return via IRQ)
+	;
+	; Exception in U mode, preempted in kernel, Intr taken (K mode), orig
+	; task now returning to U mode (riding the Intr)
+	; AUX_IRQ_ACTIVE won't have U bit set (since intr in K mode), hence SP
+	; won't be switched to correct U mode value (from AUX_SP)
+	; So force AUX_IRQ_ACT.U for such a case
+
+	btst	r0, STATUS_U_BIT		; Z flag set if K (Z clear for U)
+	bset.nz	r11, r11, AUX_IRQ_ACT_BIT_U	; NZ means U
+	sr	r11, [AUX_IRQ_ACT]
+
+	INTERRUPT_EPILOGUE
+	rtie
+
+;####### Return from Exception / pure kernel mode #######
+
+.Lexcept_ret:	; Expects r0 has PT_status32
+
+debug_marker_syscall:
+	EXCEPTION_EPILOGUE
+	rtie
+
+;####### Return from Intr to insn in delay slot #######
+
+; Handle special case #2: (Entry via Exception in Delay Slot, Return via IRQ)
+;
+; Intr returning to a Delay Slot (DS) insn
+; (since IRQ NOT allowed in DS in ARCv2, this can only happen if orig
+; entry was via Exception in DS which got preempted in kernel).
+;
+; IRQ RTIE won't reliably restore DE bit and/or BTA, needs workaround
+;
+; Solution is to drop out of interrupt context into pure kernel mode
+; and return from pure kernel mode which does right things for delay slot
+
+.Lintr_ret_to_delay_slot:
+debug_marker_ds:
+
+	ld	r2, [@intr_to_DE_cnt]
+	add	r2, r2, 1
+	st	r2, [@intr_to_DE_cnt]
+
+	; drop out of interrupt context (clear AUX_IRQ_ACT.active)
+	bmskn	r11, r10, 15
+	sr	r11, [AUX_IRQ_ACT]
+	b	.Lexcept_ret
+
+END(ret_from_exception)
diff --git a/arch/arc/kernel/entry-compact.S b/arch/arc/kernel/entry-compact.S
new file mode 100644
index 000000000..774c03cc1
--- /dev/null
+++ b/arch/arc/kernel/entry-compact.S
@@ -0,0 +1,388 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Low Level Interrupts/Traps/Exceptions(non-TLB) Handling for ARCompact ISA
+ *
+ * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * 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() no longer 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 exception 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
+ */
+
+#include <linux/errno.h>
+#include <linux/linkage.h>	/* {ENTRY,EXIT} */
+#include <asm/entry.h>
+#include <asm/irqflags.h>
+
+	.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 guaranteed that 'j somewhere'
+ * will use the 'j limm' form of the instruction as long as somewhere is in
+ * a section other than .vector.
+ */
+
+; ********* Critical System Events **********************
+VECTOR   res_service             ; 0x0, Reset Vector	(0x0)
+VECTOR   mem_service             ; 0x8, Mem exception   (0x1)
+VECTOR   instr_service           ; 0x10, Instrn Error   (0x2)
+
+; ******************** Device ISRs **********************
+#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS
+VECTOR   handle_interrupt_level2
+#else
+VECTOR   handle_interrupt_level1
+#endif
+
+.rept   28
+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, Instruction 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 Instruction Excp (0x26)
+
+.rept   24
+VECTOR   reserved                ; Reserved Exceptions
+.endr
+
+
+;##################### 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 its own scratch */
+ARCFP_DATA int2_saved_reg
+	.type   int2_saved_reg, @object
+	.size   int2_saved_reg, 4
+int2_saved_reg:
+	.zero 4
+
+; ---------------------------------------------
+	.section .text, "ax",@progbits
+
+
+reserved:
+	flag 1		; Unexpected event, halt
+
+;##################### Interrupt Handling ##############################
+
+#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS
+; ---------------------------------------------
+;  Level 2 ISR: Can interrupt a Level 1 ISR
+; ---------------------------------------------
+ENTRY(handle_interrupt_level2)
+
+	INTERRUPT_PROLOGUE 2
+
+	;------------------------------------------------------
+	; if L2 IRQ interrupted a L1 ISR, disable preemption
+	;
+	; This is to avoid a potential L1-L2-L1 scenario
+	;  -L1 IRQ taken
+	;  -L2 interrupts L1 (before L1 ISR could run)
+	;  -preemption off IRQ, user task in syscall picked to run
+	;  -RTIE to userspace
+	;	Returns from L2 context fine
+	;	But both L1 and L2 re-enabled, so another L1 can be taken
+	;	while prev L1 is still unserviced
+	;
+	;------------------------------------------------------
+
+	; L2 interrupting L1 implies both L2 and L1 active
+	; However both A2 and A1 are NOT set in STATUS32, thus
+	; need to check STATUS32_L2 to determine if L1 was active
+
+	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
+
+	; 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
+
+END(handle_interrupt_level2)
+
+#endif
+
+; ---------------------------------------------
+; User Mode Memory Bus Error Interrupt Handler
+; (Kernel mode memory errors handled via separate exception vectors)
+; ---------------------------------------------
+ENTRY(mem_service)
+
+	INTERRUPT_PROLOGUE 2
+
+	mov r0, ilink2
+	mov r1, sp
+
+	; User process needs to be killed with SIGBUS, but first need to get
+	; out of the L2 interrupt context (drop to pure kernel mode) and jump
+	; off to "C" code where SIGBUS in enqueued
+	lr  r3, [status32]
+	bclr r3, r3, STATUS_A2_BIT
+	or  r3, r3, (STATUS_E1_MASK|STATUS_E2_MASK)
+	sr  r3, [status32_l2]
+	mov ilink2, 1f
+	rtie
+1:
+	bl  do_memory_error
+	b   ret_from_exception
+END(mem_service)
+
+; ---------------------------------------------
+;  Level 1 ISR
+; ---------------------------------------------
+ENTRY(handle_interrupt_level1)
+
+	INTERRUPT_PROLOGUE 1
+
+	lr  r0, [icause1]
+	and r0, r0, 0x1f
+
+#ifdef CONFIG_TRACE_IRQFLAGS
+	; icause1 needs to be read early, before calling tracing, which
+	; can clobber scratch regs, hence use of stack to stash it
+	push r0
+	TRACE_ASM_IRQ_DISABLE
+	pop  r0
+#endif
+
+	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
+END(handle_interrupt_level1)
+
+;################### Non TLB Exception Handling #############################
+
+; ---------------------------------------------
+; Protection Violation Exception Handler
+; ---------------------------------------------
+
+ENTRY(EV_TLBProtV)
+
+	EXCEPTION_PROLOGUE	; ECR returned in r10
+
+	;------ (5) Type of Protection Violation? ----------
+	;
+	; ProtV Hardware Exception is triggered for Access Faults of 2 types
+	;   -Access Violation	: 00_23_(00|01|02|03)_00
+	;			         x  r  w  r+w
+	;   -Unaligned Access	: 00_23_04_00
+	bbit1 r10, ECR_C_BIT_PROTV_MISALIG_DATA, 4f
+
+	;========= (6a) Access Violation Processing ========
+	bl  do_page_fault
+	b   ret_from_exception
+
+	;========== (6b) Non aligned access ============
+4:
+
+	SAVE_CALLEE_SAVED_USER
+	mov r2, sp              ; callee_regs
+
+	bl  do_misaligned_access
+
+	; TBD: optimize - do this only if a callee reg was involved
+	; either a dst of emulated LD/ST or src with address-writeback
+	RESTORE_CALLEE_SAVED_USER
+
+	b   ret_from_exception
+
+END(EV_TLBProtV)
+
+; Wrapper for Linux page fault handler called from EV_TLBMiss*
+; Very similar to ProtV handler case (6a) above, but avoids the extra checks
+; for Misaligned access
+;
+ENTRY(call_do_page_fault)
+
+	EXCEPTION_PROLOGUE
+
+	mov blink, ret_from_exception
+	b  do_page_fault
+
+END(call_do_page_fault)
+
+;############# Common Handlers for ARCompact and ARCv2 ##############
+
+#include "entry.S"
+
+;############# 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
+; All 2 entry points to here already disable interrupts
+
+.Lrestore_regs:
+
+	# Interrupts are actually disabled from this point on, but will get
+	# reenabled after we return from interrupt/exception.
+	# But irq tracer needs to be told now...
+	TRACE_ASM_IRQ_ENABLE
+
+	lr	r10, [status32]
+
+	; Restore REG File. In case multiple Events outstanding,
+	; use the same priority as rtie: EXCPN, L2 IRQ, L1 IRQ, None
+	; Note that we use realtime STATUS32 (not pt_regs->status32) to
+	; decide that.
+
+	and.f	0, r10, (STATUS_A1_MASK|STATUS_A2_MASK)
+	bz	.Lexcep_or_pure_K_ret
+
+	; Returning from Interrupts (Level 1 or 2)
+
+#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS
+
+	; Level 2 interrupt return Path - from hardware standpoint
+	bbit0  r10, STATUS_A2_BIT, not_level2_interrupt
+
+	;------------------------------------------------------------------
+	; However the context returning might not have taken L2 intr itself
+	; e.g. Task'A' user-code -> L2 intr -> schedule -> 'B' user-code ret
+	; Special considerations needed for the context which took L2 intr
+
+	ld   r9, [sp, PT_event]        ; Ensure this is L2 intr context
+	brne r9, event_IRQ2, 149f
+
+	;------------------------------------------------------------------
+	; if L2 IRQ interrupted an L1 ISR,  we'd disabled preemption earlier
+	; so that sched doesn't move to new task, causing L1 to be delayed
+	; undeterministically. Now that we've achieved that, let's reset
+	; things to what they were, before returning from L2 context
+	;----------------------------------------------------------------
+
+	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
+
+	; 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 because 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:
+	INTERRUPT_EPILOGUE 2	; return from level 2 interrupt
+debug_marker_l2:
+	rtie
+
+not_level2_interrupt:
+
+#endif
+
+	INTERRUPT_EPILOGUE 1	; return from level 1 interrupt
+debug_marker_l1:
+	rtie
+
+.Lexcep_or_pure_K_ret:
+
+	;this case is for syscalls or Exceptions or pure kernel mode
+
+	EXCEPTION_EPILOGUE
+debug_marker_syscall:
+	rtie
+
+END(ret_from_exception)
diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S
new file mode 100644
index 000000000..3c7e74aba
--- /dev/null
+++ b/arch/arc/kernel/entry.S
@@ -0,0 +1,347 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Common Low Level Interrupts/Traps/Exceptions(non-TLB) Handling for ARC
+ * (included from entry-<isa>.S
+ *
+ * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+/*------------------------------------------------------------------
+ *    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
+ *  Branch link register (blink)        r31
+ *------------------------------------------------------------------
+ */
+
+;################### Special Sys Call Wrappers ##########################
+
+ENTRY(sys_clone_wrapper)
+	SAVE_CALLEE_SAVED_USER
+	bl  @sys_clone
+	DISCARD_CALLEE_SAVED_USER
+
+	GET_CURR_THR_INFO_FLAGS   r10
+	and.f 0, r10, _TIF_SYSCALL_WORK
+	bnz   tracesys_exit
+
+	b .Lret_from_system_call
+END(sys_clone_wrapper)
+
+ENTRY(sys_clone3_wrapper)
+	SAVE_CALLEE_SAVED_USER
+	bl  @sys_clone3
+	DISCARD_CALLEE_SAVED_USER
+
+	GET_CURR_THR_INFO_FLAGS   r10
+	and.f 0, r10, _TIF_SYSCALL_WORK
+	bnz   tracesys_exit
+
+	b .Lret_from_system_call
+END(sys_clone3_wrapper)
+
+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
+	jl   @schedule_tail
+
+	ld   r9, [sp, PT_status32]
+	brne r9, 0, 1f
+
+	jl.d [r14]		; kernel thread entry point
+	mov  r0, r13		; (see PF_KTHREAD block in copy_thread)
+
+1:
+	; Return to user space
+	; 1. Any forked task (Reach here via BRne above)
+	; 2. First ever init task (Reach here via return from JL above)
+	;    This is the historic "kernel_execve" use-case, to return to init
+	;    user mode, in a round about way since that is always done from
+	;    a kernel thread which is executed via JL above but always returns
+	;    out whenever kernel_execve (now inline do_fork()) is involved
+	b    ret_from_exception
+END(ret_from_fork)
+
+;################### Non TLB Exception Handling #############################
+
+; ---------------------------------------------
+; Instruction Error Exception Handler
+; ---------------------------------------------
+
+ENTRY(instr_service)
+
+	EXCEPTION_PROLOGUE
+
+	bl  do_insterror_or_kprobe
+	b   ret_from_exception
+END(instr_service)
+
+; ---------------------------------------------
+; Machine Check Exception Handler
+; ---------------------------------------------
+
+ENTRY(EV_MachineCheck)
+
+	EXCEPTION_PROLOGUE_KEEP_AE	; ECR returned in r10
+
+	lr  r0, [efa]
+	mov r1, sp
+
+	; MC exceptions disable MMU
+	ARC_MMU_REENABLE r3
+
+	lsr  	r3, r10, 8
+	bmsk 	r3, r3, 7
+	brne    r3, ECR_C_MCHK_DUP_TLB, 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
+
+END(EV_MachineCheck)
+
+; ---------------------------------------------
+; Privilege Violation Exception Handler
+; ---------------------------------------------
+ENTRY(EV_PrivilegeV)
+
+	EXCEPTION_PROLOGUE
+
+	bl  do_privilege_fault
+	b   ret_from_exception
+END(EV_PrivilegeV)
+
+; ---------------------------------------------
+; Extension Instruction Exception Handler
+; ---------------------------------------------
+ENTRY(EV_Extension)
+
+	EXCEPTION_PROLOGUE
+
+	bl  do_extension_fault
+	b   ret_from_exception
+END(EV_Extension)
+
+;################ Trap Handling (Syscall, Breakpoint) ##################
+
+; ---------------------------------------------
+; syscall Tracing
+; ---------------------------------------------
+tracesys:
+	; safekeep EFA (r12) if syscall tracer wanted PC
+	; for traps, ERET is pre-commit so points to next-PC
+	GET_CURR_TASK_FIELD_PTR   TASK_THREAD, r11
+	st  r12, [r11, THREAD_FAULT_ADDR]	; thread.fault_address
+
+	; PRE syscall trace hook
+	mov r0, sp				; pt_regs
+	bl  @syscall_trace_enter
+
+	; Tracing code now returns the syscall num (orig or modif)
+	mov r8, r0
+
+	; Do the Sys Call as we normally would.
+	cmp     r8,  NR_syscalls - 1
+	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]
+
+tracesys_exit:
+	st  r0, [sp, PT_r0]
+
+	; POST syscall trace hook
+	mov r0, sp		; pt_regs needed
+	bl  @syscall_trace_exit
+
+	; don't call ret_from_system_call as it saves r0, already done above
+	b   ret_from_exception
+
+; ---------------------------------------------
+; Breakpoint TRAP
+; ---------------------------------------------
+trap_with_param:
+	mov r0, r12	; EFA in case ptracer/gdb wants stop_pc
+	mov r1, sp	; pt_regs
+
+	; save callee regs in case tracer/gdb wants to peek
+	SAVE_CALLEE_SAVED_USER
+
+	; safekeep ref to callee regs
+	GET_CURR_TASK_FIELD_PTR   TASK_THREAD, r10
+	st  sp, [r10, THREAD_CALLEE_REG]
+
+	; call the non syscall trap handler
+	bl  do_non_swi_trap
+
+	; unwind stack to discard callee regs
+	DISCARD_CALLEE_SAVED_USER
+
+	b   ret_from_exception
+
+; ---------------------------------------------
+; syscall TRAP
+; ABI: (r0-r7) up to 8 args, (r8) syscall number
+; ---------------------------------------------
+
+ENTRY(EV_Trap)
+
+	EXCEPTION_PROLOGUE_KEEP_AE
+
+	lr  r12, [efa]
+
+	FAKE_RET_FROM_EXCPN
+
+	;============ TRAP N : breakpoints, kprobes etc
+	bmsk.f 0, r10, 7
+	bnz    trap_with_param
+
+	;============ TRAP 0 (no param): syscall
+
+	; syscall tracing ongoing, invoke pre-post-hooks around syscall
+	GET_CURR_THR_INFO_FLAGS   r10
+	and.f 0, r10, _TIF_SYSCALL_WORK
+	bnz   tracesys  ; this never comes back
+
+	;============ Normal syscall case
+
+	cmp     r8,  NR_syscalls - 1
+	mov.hi  r0, -ENOSYS
+	bhi     .Lret_from_system_call
+
+	ld.as   r9,[sys_call_table, r8]
+	jl      [r9]
+
+.Lret_from_system_call:
+	st  r0, [sp, PT_r0]     ; sys call return value in pt_regs
+
+	; fall through to ret_from_exception
+END(EV_Trap)
+
+;############# Return from Intr/Excp/Trap (Linux Specifics) ##############
+;
+; If ret to user mode do we need to handle signals, schedule() et al.
+
+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
+
+	bbit0  r8, STATUS_U_BIT, resume_kernel_mode
+
+	; 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     .Lrestore_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
+	j      @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()
+
+	GET_CURR_THR_INFO_FLAGS   r9
+	and.f  0,  r9, _TIF_SIGPENDING|_TIF_NOTIFY_SIGNAL
+	bz .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
+
+	; 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
+
+resume_kernel_mode:
+
+	; Disable Interrupts from this point on
+	; CONFIG_PREEMPTION: This is a must for preempt_schedule_irq()
+	; !CONFIG_PREEMPTION: To ensure restore_regs is intr safe
+	IRQ_DISABLE	r9
+
+#ifdef CONFIG_PREEMPTION
+
+	; Can't preempt if preemption disabled
+	GET_CURR_THR_INFO_FROM_SP   r10
+	ld  r8, [r10, THREAD_INFO_PREEMPT_COUNT]
+	brne  r8, 0, .Lrestore_regs
+
+	; check if this task's NEED_RESCHED flag set
+	ld  r9, [r10, THREAD_INFO_FLAGS]
+	bbit0  r9, TIF_NEED_RESCHED, .Lrestore_regs
+
+	; Invoke PREEMPTION
+	jl      preempt_schedule_irq
+
+	; preempt_schedule_irq() always returns with IRQ disabled
+#endif
+
+	b	.Lrestore_regs
+
+##### DONT ADD CODE HERE - .Lrestore_regs actually follows in entry-<isa>.S
+
diff --git a/arch/arc/kernel/fpu.c b/arch/arc/kernel/fpu.c
new file mode 100644
index 000000000..ec640219d
--- /dev/null
+++ b/arch/arc/kernel/fpu.c
@@ -0,0 +1,82 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * fpu.c - save/restore of Floating Point Unit Registers on task switch
+ *
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#include <linux/sched.h>
+#include <asm/fpu.h>
+
+#ifdef CONFIG_ISA_ARCOMPACT
+
+/*
+ * 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))
+	);
+}
+
+#else
+
+void fpu_init_task(struct pt_regs *regs)
+{
+	const unsigned int fwe = 0x80000000;
+
+	/* default rounding mode */
+	write_aux_reg(ARC_REG_FPU_CTRL, 0x100);
+
+	/* Initialize to zero: setting requires FWE be set */
+	write_aux_reg(ARC_REG_FPU_STATUS, fwe);
+}
+
+void fpu_save_restore(struct task_struct *prev, struct task_struct *next)
+{
+	struct arc_fpu *save = &prev->thread.fpu;
+	struct arc_fpu *restore = &next->thread.fpu;
+	const unsigned int fwe = 0x80000000;
+
+	save->ctrl = read_aux_reg(ARC_REG_FPU_CTRL);
+	save->status = read_aux_reg(ARC_REG_FPU_STATUS);
+
+	write_aux_reg(ARC_REG_FPU_CTRL, restore->ctrl);
+	write_aux_reg(ARC_REG_FPU_STATUS, (fwe | restore->status));
+}
+
+#endif
diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S
new file mode 100644
index 000000000..8d541f53f
--- /dev/null
+++ b/arch/arc/kernel/head.S
@@ -0,0 +1,173 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * ARC CPU startup Code
+ *
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * Vineetg: Dec 2007
+ *  -Check if we are running on Simulator or on real hardware
+ *      to skip certain things during boot on simulator
+ */
+
+#include <linux/linkage.h>
+#include <asm/asm-offsets.h>
+#include <asm/entry.h>
+#include <asm/arcregs.h>
+#include <asm/cache.h>
+#include <asm/dsp-impl.h>
+#include <asm/irqflags.h>
+
+.macro CPU_EARLY_SETUP
+
+	; Setting up Vectror Table (in case exception happens in early boot
+	sr	@_int_vec_base_lds, [AUX_INTR_VEC_BASE]
+
+	; Disable I-cache/D-cache if kernel so configured
+	lr	r5, [ARC_REG_IC_BCR]
+	breq    r5, 0, 1f		; I$ doesn't exist
+	lr	r5, [ARC_REG_IC_CTRL]
+#ifdef CONFIG_ARC_HAS_ICACHE
+	bclr	r5, r5, 0		; 0 - Enable, 1 is Disable
+#else
+	bset	r5, r5, 0		; I$ exists, but is not used
+#endif
+	sr	r5, [ARC_REG_IC_CTRL]
+
+1:
+	lr	r5, [ARC_REG_DC_BCR]
+	breq    r5, 0, 1f		; D$ doesn't exist
+	lr	r5, [ARC_REG_DC_CTRL]
+	bclr	r5, r5, 6		; Invalidate (discard w/o wback)
+#ifdef CONFIG_ARC_HAS_DCACHE
+	bclr	r5, r5, 0		; Enable (+Inv)
+#else
+	bset	r5, r5, 0		; Disable (+Inv)
+#endif
+	sr	r5, [ARC_REG_DC_CTRL]
+
+1:
+
+#ifdef CONFIG_ISA_ARCV2
+	; Unaligned access is disabled at reset, so re-enable early as
+	; gcc 7.3.1 (ARC GNU 2018.03) onwards generates unaligned access
+	; by default
+	lr	r5, [status32]
+#ifdef CONFIG_ARC_USE_UNALIGNED_MEM_ACCESS
+	bset	r5, r5, STATUS_AD_BIT
+#else
+	; Although disabled at reset, bootloader might have enabled it
+	bclr	r5, r5, STATUS_AD_BIT
+#endif
+	kflag	r5
+
+#ifdef CONFIG_ARC_LPB_DISABLE
+	lr	r5, [ARC_REG_LPB_BUILD]
+	breq    r5, 0, 1f		; LPB doesn't exist
+	mov	r5, 1
+	sr	r5, [ARC_REG_LPB_CTRL]
+1:
+#endif /* CONFIG_ARC_LPB_DISABLE */
+
+	/* On HSDK, CCMs need to remapped super early */
+#ifdef CONFIG_ARC_SOC_HSDK
+	mov	r6, 0x60000000
+	lr	r5, [ARC_REG_ICCM_BUILD]
+	breq	r5, 0, 1f
+	sr	r6, [ARC_REG_AUX_ICCM]
+1:
+	lr	r5, [ARC_REG_DCCM_BUILD]
+	breq	r5, 0, 2f
+	sr	r6, [ARC_REG_AUX_DCCM]
+2:
+#endif	/* CONFIG_ARC_SOC_HSDK */
+
+#endif	/* CONFIG_ISA_ARCV2 */
+
+	; Config DSP_CTRL properly, so kernel may use integer multiply,
+	; multiply-accumulate, and divide operations
+	DSP_EARLY_INIT
+.endm
+
+	.section .init.text, "ax",@progbits
+
+;----------------------------------------------------------------
+; Default Reset Handler (jumped into from Reset vector)
+; - Don't clobber r0,r1,r2 as they might have u-boot provided args
+; - Platforms can override this weak version if needed
+;----------------------------------------------------------------
+WEAK(res_service)
+	j	stext
+END(res_service)
+
+;----------------------------------------------------------------
+; Kernel Entry point
+;----------------------------------------------------------------
+ENTRY(stext)
+
+	CPU_EARLY_SETUP
+
+#ifdef CONFIG_SMP
+	GET_CPU_ID  r5
+	cmp	r5, 0
+	mov.nz	r0, r5
+	bz	.Lmaster_proceed
+
+	; Non-Masters wait for Master to boot enough and bring them up
+	; when they resume, tail-call to entry point
+	mov	blink, @first_lines_of_secondary
+	j	arc_platform_smp_wait_to_boot
+
+.Lmaster_proceed:
+#endif
+
+	; Clear BSS before updating any globals
+	; XXX: use ZOL here
+	mov	r5, __bss_start
+	sub	r6, __bss_stop, r5
+	lsr.f	lp_count, r6, 2
+	lpnz	1f
+	st.ab   0, [r5, 4]
+1:
+
+	; Uboot - kernel ABI
+	;    r0 = [0] No uboot interaction, [1] cmdline in r2, [2] DTB in r2
+	;    r1 = magic number (always zero as of now)
+	;    r2 = pointer to uboot provided cmdline or external DTB in mem
+	; These are handled later in handle_uboot_args()
+	st	r0, [@uboot_tag]
+	st      r1, [@uboot_magic]
+	st	r2, [@uboot_arg]
+
+	; 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
+END(stext)
+
+#ifdef CONFIG_SMP
+;----------------------------------------------------------------
+;     First lines of code run by secondary before jumping to 'C'
+;----------------------------------------------------------------
+	.section .text, "ax",@progbits
+ENTRY(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 its stack base to tsk->thread_info bottom
+	GET_TSK_STACK_BASE r0, sp
+
+	j	start_kernel_secondary
+END(first_lines_of_secondary)
+#endif
diff --git a/arch/arc/kernel/intc-arcv2.c b/arch/arc/kernel/intc-arcv2.c
new file mode 100644
index 000000000..809edc59a
--- /dev/null
+++ b/arch/arc/kernel/intc-arcv2.c
@@ -0,0 +1,191 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2014 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/irqdomain.h>
+#include <linux/irqchip.h>
+#include <asm/irq.h>
+
+#define NR_EXCEPTIONS	16
+
+struct bcr_irq_arcv2 {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int pad:3, firq:1, prio:4, exts:8, irqs:8, ver:8;
+#else
+	unsigned int ver:8, irqs:8, exts:8, prio:4, firq:1, pad:3;
+#endif
+};
+
+/*
+ * Early Hardware specific Interrupt setup
+ * -Called very early (start_kernel -> setup_arch -> setup_processor)
+ * -Platform Independent (must for any ARC Core)
+ * -Needed for each CPU (hence not foldable into init_IRQ)
+ */
+void arc_init_IRQ(void)
+{
+	unsigned int tmp, irq_prio, i;
+	struct bcr_irq_arcv2 irq_bcr;
+
+	struct aux_irq_ctrl {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+		unsigned int res3:18, save_idx_regs:1, res2:1,
+			     save_u_to_u:1, save_lp_regs:1, save_blink:1,
+			     res:4, save_nr_gpr_pairs:5;
+#else
+		unsigned int save_nr_gpr_pairs:5, res:4,
+			     save_blink:1, save_lp_regs:1, save_u_to_u:1,
+			     res2:1, save_idx_regs:1, res3:18;
+#endif
+	} ictrl;
+
+	*(unsigned int *)&ictrl = 0;
+
+#ifndef CONFIG_ARC_IRQ_NO_AUTOSAVE
+	ictrl.save_nr_gpr_pairs = 6;	/* r0 to r11 (r12 saved manually) */
+	ictrl.save_blink = 1;
+	ictrl.save_lp_regs = 1;		/* LP_COUNT, LP_START, LP_END */
+	ictrl.save_u_to_u = 0;		/* user ctxt saved on kernel stack */
+	ictrl.save_idx_regs = 1;	/* JLI, LDI, EI */
+#endif
+
+	WRITE_AUX(AUX_IRQ_CTRL, ictrl);
+
+	/*
+	 * ARCv2 core intc provides multiple interrupt priorities (up to 16).
+	 * Typical builds though have only two levels (0-high, 1-low)
+	 * Linux by default uses lower prio 1 for most irqs, reserving 0 for
+	 * NMI style interrupts in future (say perf)
+	 */
+
+	READ_BCR(ARC_REG_IRQ_BCR, irq_bcr);
+
+	irq_prio = irq_bcr.prio;	/* Encoded as N-1 for N levels */
+	pr_info("archs-intc\t: %d priority levels (default %d)%s\n",
+		irq_prio + 1, ARCV2_IRQ_DEF_PRIO,
+		irq_bcr.firq ? " FIRQ (not used)":"");
+
+	/*
+	 * Set a default priority for all available interrupts to prevent
+	 * switching of register banks if Fast IRQ and multiple register banks
+	 * are supported by CPU.
+	 * Also disable private-per-core IRQ lines so faulty external HW won't
+	 * trigger interrupt that kernel is not ready to handle.
+	 */
+	for (i = NR_EXCEPTIONS; i < irq_bcr.irqs + NR_EXCEPTIONS; i++) {
+		write_aux_reg(AUX_IRQ_SELECT, i);
+		write_aux_reg(AUX_IRQ_PRIORITY, ARCV2_IRQ_DEF_PRIO);
+
+		/*
+		 * Only mask cpu private IRQs here.
+		 * "common" interrupts are masked at IDU, otherwise it would
+		 * need to be unmasked at each cpu, with IPIs
+		 */
+		if (i < FIRST_EXT_IRQ)
+			write_aux_reg(AUX_IRQ_ENABLE, 0);
+	}
+
+	/* setup status32, don't enable intr yet as kernel doesn't want */
+	tmp = read_aux_reg(ARC_REG_STATUS32);
+	tmp |= ARCV2_IRQ_DEF_PRIO << 1;
+	tmp &= ~STATUS_IE_MASK;
+	asm volatile("kflag %0	\n"::"r"(tmp));
+}
+
+static void arcv2_irq_mask(struct irq_data *data)
+{
+	write_aux_reg(AUX_IRQ_SELECT, data->hwirq);
+	write_aux_reg(AUX_IRQ_ENABLE, 0);
+}
+
+static void arcv2_irq_unmask(struct irq_data *data)
+{
+	write_aux_reg(AUX_IRQ_SELECT, data->hwirq);
+	write_aux_reg(AUX_IRQ_ENABLE, 1);
+}
+
+static void arcv2_irq_enable(struct irq_data *data)
+{
+	/* set default priority */
+	write_aux_reg(AUX_IRQ_SELECT, data->hwirq);
+	write_aux_reg(AUX_IRQ_PRIORITY, ARCV2_IRQ_DEF_PRIO);
+
+	/*
+	 * hw auto enables (linux unmask) all by default
+	 * So no need to do IRQ_ENABLE here
+	 * XXX: However OSCI LAN need it
+	 */
+	write_aux_reg(AUX_IRQ_ENABLE, 1);
+}
+
+static struct irq_chip arcv2_irq_chip = {
+	.name           = "ARCv2 core Intc",
+	.irq_mask	= arcv2_irq_mask,
+	.irq_unmask	= arcv2_irq_unmask,
+	.irq_enable	= arcv2_irq_enable
+};
+
+static int arcv2_irq_map(struct irq_domain *d, unsigned int irq,
+			 irq_hw_number_t hw)
+{
+	/*
+	 * core intc IRQs [16, 23]:
+	 * Statically assigned always private-per-core (Timers, WDT, IPI, PCT)
+	 */
+	if (hw < FIRST_EXT_IRQ) {
+		/*
+		 * A subsequent request_percpu_irq() fails if percpu_devid is
+		 * not set. That in turns sets NOAUTOEN, meaning each core needs
+		 * to call enable_percpu_irq()
+		 */
+		irq_set_percpu_devid(irq);
+		irq_set_chip_and_handler(irq, &arcv2_irq_chip, handle_percpu_irq);
+	} else {
+		irq_set_chip_and_handler(irq, &arcv2_irq_chip, handle_level_irq);
+	}
+
+	return 0;
+}
+
+static const struct irq_domain_ops arcv2_irq_ops = {
+	.xlate = irq_domain_xlate_onecell,
+	.map = arcv2_irq_map,
+};
+
+
+static int __init
+init_onchip_IRQ(struct device_node *intc, struct device_node *parent)
+{
+	struct irq_domain *root_domain;
+	struct bcr_irq_arcv2 irq_bcr;
+	unsigned int nr_cpu_irqs;
+
+	READ_BCR(ARC_REG_IRQ_BCR, irq_bcr);
+	nr_cpu_irqs = irq_bcr.irqs + NR_EXCEPTIONS;
+
+	if (parent)
+		panic("DeviceTree incore intc not a root irq controller\n");
+
+	root_domain = irq_domain_create_linear(of_fwnode_handle(intc), nr_cpu_irqs, &arcv2_irq_ops, NULL);
+	if (!root_domain)
+		panic("root irq domain not avail\n");
+
+	/*
+	 * Needed for primary domain lookup to succeed
+	 * This is a primary irqchip, and can never have a parent
+	 */
+	irq_set_default_domain(root_domain);
+
+#ifdef CONFIG_SMP
+	irq_create_mapping(root_domain, IPI_IRQ);
+#endif
+	irq_create_mapping(root_domain, SOFTIRQ_IRQ);
+
+	return 0;
+}
+
+IRQCHIP_DECLARE(arc_intc, "snps,archs-intc", init_onchip_IRQ);
diff --git a/arch/arc/kernel/intc-compact.c b/arch/arc/kernel/intc-compact.c
new file mode 100644
index 000000000..1b159e9e0
--- /dev/null
+++ b/arch/arc/kernel/intc-compact.c
@@ -0,0 +1,171 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2011-12 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/irqdomain.h>
+#include <linux/irqchip.h>
+#include <asm/irq.h>
+
+#define NR_CPU_IRQS	32	/* number of irq lines coming in */
+#define TIMER0_IRQ	3	/* Fixed by ISA */
+
+/*
+ * Early Hardware specific Interrupt setup
+ * -Platform independent, needed for each CPU (not foldable into init_IRQ)
+ * -Called very early (start_kernel -> setup_arch -> setup_processor)
+ *
+ * what it does ?
+ * -Optionally, setup the High priority Interrupts as Level 2 IRQs
+ */
+void arc_init_IRQ(void)
+{
+	unsigned int level_mask = 0, i;
+
+       /* Is timer high priority Interrupt (Level2 in ARCompact jargon) */
+	level_mask |= IS_ENABLED(CONFIG_ARC_COMPACT_IRQ_LEVELS) << TIMER0_IRQ;
+
+	/*
+	 * Write to register, even if no LV2 IRQs configured to reset it
+	 * in case bootloader had mucked with it
+	 */
+	write_aux_reg(AUX_IRQ_LEV, level_mask);
+
+	if (level_mask)
+		pr_info("Level-2 interrupts bitset %x\n", level_mask);
+
+	/*
+	 * Disable all IRQ lines so faulty external hardware won't
+	 * trigger interrupt that kernel is not ready to handle.
+	 */
+	for (i = TIMER0_IRQ; i < NR_CPU_IRQS; i++) {
+		unsigned int ienb;
+
+		ienb = read_aux_reg(AUX_IENABLE);
+		ienb &= ~(1 << i);
+		write_aux_reg(AUX_IENABLE, ienb);
+	}
+}
+
+/*
+ * 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_irq_mask(struct irq_data *data)
+{
+	unsigned int ienb;
+
+	ienb = read_aux_reg(AUX_IENABLE);
+	ienb &= ~(1 << data->hwirq);
+	write_aux_reg(AUX_IENABLE, ienb);
+}
+
+static void arc_irq_unmask(struct irq_data *data)
+{
+	unsigned int ienb;
+
+	ienb = read_aux_reg(AUX_IENABLE);
+	ienb |= (1 << data->hwirq);
+	write_aux_reg(AUX_IENABLE, ienb);
+}
+
+static struct irq_chip onchip_intc = {
+	.name           = "ARC In-core Intc",
+	.irq_mask	= arc_irq_mask,
+	.irq_unmask	= arc_irq_unmask,
+};
+
+static int arc_intc_domain_map(struct irq_domain *d, unsigned int irq,
+			       irq_hw_number_t hw)
+{
+	switch (hw) {
+	case TIMER0_IRQ:
+		irq_set_percpu_devid(irq);
+		irq_set_chip_and_handler(irq, &onchip_intc, handle_percpu_irq);
+		break;
+	default:
+		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 int __init
+init_onchip_IRQ(struct device_node *intc, struct device_node *parent)
+{
+	struct irq_domain *root_domain;
+
+	if (parent)
+		panic("DeviceTree incore intc not a root irq controller\n");
+
+	root_domain = irq_domain_create_linear(of_fwnode_handle(intc),
+					       NR_CPU_IRQS,
+					       &arc_intc_domain_ops, NULL);
+	if (!root_domain)
+		panic("root irq domain not avail\n");
+
+	/*
+	 * Needed for primary domain lookup to succeed
+	 * This is a primary irqchip, and can never have a parent
+	 */
+	irq_set_default_domain(root_domain);
+
+	return 0;
+}
+
+IRQCHIP_DECLARE(arc_intc, "snps,arc700-intc", init_onchip_IRQ);
+
+/*
+ * 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 priority 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 = arch_local_save_flags();
+
+	if (flags & STATUS_A2_MASK)
+		flags |= STATUS_E2_MASK;
+	else if (flags & STATUS_A1_MASK)
+		flags |= STATUS_E1_MASK;
+
+	arch_local_irq_restore(flags);
+}
+
+EXPORT_SYMBOL(arch_local_irq_enable);
+#endif
diff --git a/arch/arc/kernel/irq.c b/arch/arc/kernel/irq.c
new file mode 100644
index 000000000..dd09b58ff
--- /dev/null
+++ b/arch/arc/kernel/irq.c
@@ -0,0 +1,51 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2011-12 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#include <linux/interrupt.h>
+#include <linux/irqchip.h>
+#include <asm/mach_desc.h>
+
+#include <asm/irq_regs.h>
+#include <asm/smp.h>
+
+/*
+ * 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)
+{
+	/*
+	 * process the entire interrupt tree in one go
+	 * Any external intc will be setup provided DT chains them
+	 * properly
+	 */
+	irqchip_init();
+
+#ifdef CONFIG_SMP
+	/* a SMP H/w block could do IPI IRQ request here */
+	if (plat_smp_ops.init_per_cpu)
+		plat_smp_ops.init_per_cpu(smp_processor_id());
+#endif
+
+	if (machine_desc->init_per_cpu)
+		machine_desc->init_per_cpu(smp_processor_id());
+}
+
+/*
+ * "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 hwirq, struct pt_regs *regs)
+{
+	struct pt_regs *old_regs;
+
+	irq_enter();
+	old_regs = set_irq_regs(regs);
+	generic_handle_domain_irq(NULL, hwirq);
+	set_irq_regs(old_regs);
+	irq_exit();
+}
diff --git a/arch/arc/kernel/jump_label.c b/arch/arc/kernel/jump_label.c
new file mode 100644
index 000000000..70b74a5d0
--- /dev/null
+++ b/arch/arc/kernel/jump_label.c
@@ -0,0 +1,157 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/kernel.h>
+#include <linux/jump_label.h>
+
+#include "asm/cacheflush.h"
+
+#define JUMPLABEL_ERR	"ARC: jump_label: ERROR: "
+
+/* Halt system on fatal error to make debug easier */
+#define arc_jl_fatal(format...)						\
+({									\
+	pr_err(JUMPLABEL_ERR format);					\
+	BUG();								\
+})
+
+static inline u32 arc_gen_nop(void)
+{
+	/* 1x 32bit NOP in middle endian */
+	return 0x7000264a;
+}
+
+/*
+ * Atomic update of patched instruction is only available if this
+ * instruction doesn't cross L1 cache line boundary. You can read about
+ * the way we achieve this in arc/include/asm/jump_label.h
+ */
+static inline void instruction_align_assert(void *addr, int len)
+{
+	unsigned long a = (unsigned long)addr;
+
+	if ((a >> L1_CACHE_SHIFT) != ((a + len - 1) >> L1_CACHE_SHIFT))
+		arc_jl_fatal("instruction (addr %px) cross L1 cache line border",
+			     addr);
+}
+
+/*
+ * ARCv2 'Branch unconditionally' instruction:
+ * 00000ssssssssss1SSSSSSSSSSNRtttt
+ * s S[n:0] lower bits signed immediate (number is bitfield size)
+ * S S[m:n+1] upper bits signed immediate (number is bitfield size)
+ * t S[24:21] upper bits signed immediate (branch unconditionally far)
+ * N N <.d> delay slot mode
+ * R R Reserved
+ */
+static inline u32 arc_gen_branch(jump_label_t pc, jump_label_t target)
+{
+	u32 instruction_l, instruction_r;
+	u32 pcl = pc & GENMASK(31, 2);
+	u32 u_offset = target - pcl;
+	u32 s, S, t;
+
+	/*
+	 * Offset in 32-bit branch instruction must to fit into s25.
+	 * Something is terribly broken if we get such huge offset within one
+	 * function.
+	 */
+	if ((s32)u_offset < -16777216 || (s32)u_offset > 16777214)
+		arc_jl_fatal("gen branch with offset (%d) not fit in s25",
+			     (s32)u_offset);
+
+	/*
+	 * All instructions are aligned by 2 bytes so we should never get offset
+	 * here which is not 2 bytes aligned.
+	 */
+	if (u_offset & 0x1)
+		arc_jl_fatal("gen branch with offset (%d) unaligned to 2 bytes",
+			     (s32)u_offset);
+
+	s = (u_offset >> 1)  & GENMASK(9, 0);
+	S = (u_offset >> 11) & GENMASK(9, 0);
+	t = (u_offset >> 21) & GENMASK(3, 0);
+
+	/* 00000ssssssssss1 */
+	instruction_l = (s << 1) | 0x1;
+	/* SSSSSSSSSSNRtttt */
+	instruction_r = (S << 6) | t;
+
+	return (instruction_r << 16) | (instruction_l & GENMASK(15, 0));
+}
+
+void arch_jump_label_transform(struct jump_entry *entry,
+			       enum jump_label_type type)
+{
+	jump_label_t *instr_addr = (jump_label_t *)entry->code;
+	u32 instr;
+
+	instruction_align_assert(instr_addr, JUMP_LABEL_NOP_SIZE);
+
+	if (type == JUMP_LABEL_JMP)
+		instr = arc_gen_branch(entry->code, entry->target);
+	else
+		instr = arc_gen_nop();
+
+	WRITE_ONCE(*instr_addr, instr);
+	flush_icache_range(entry->code, entry->code + JUMP_LABEL_NOP_SIZE);
+}
+
+#ifdef CONFIG_ARC_DBG_JUMP_LABEL
+#define SELFTEST_MSG	"ARC: instruction generation self-test: "
+
+struct arc_gen_branch_testdata {
+	jump_label_t pc;
+	jump_label_t target_address;
+	u32 expected_instr;
+};
+
+static __init int branch_gen_test(const struct arc_gen_branch_testdata *test)
+{
+	u32 instr_got;
+
+	instr_got = arc_gen_branch(test->pc, test->target_address);
+	if (instr_got == test->expected_instr)
+		return 0;
+
+	pr_err(SELFTEST_MSG "FAIL:\n arc_gen_branch(0x%08x, 0x%08x) != 0x%08x, got 0x%08x\n",
+	       test->pc, test->target_address,
+	       test->expected_instr, instr_got);
+
+	return -EFAULT;
+}
+
+/*
+ * Offset field in branch instruction is not continuous. Test all
+ * available offset field and sign combinations. Test data is generated
+ * from real working code.
+ */
+static const struct arc_gen_branch_testdata arcgenbr_test_data[] __initconst = {
+	{0x90007548, 0x90007514, 0xffcf07cd}, /* tiny (-52) offs */
+	{0x9000c9c0, 0x9000c782, 0xffcf05c3}, /* tiny (-574) offs */
+	{0x9000cc1c, 0x9000c782, 0xffcf0367}, /* tiny (-1178) offs */
+	{0x9009dce0, 0x9009d106, 0xff8f0427}, /* small (-3034) offs */
+	{0x9000f5de, 0x90007d30, 0xfc0f0755}, /* big  (-30892) offs */
+	{0x900a2444, 0x90035f64, 0xc9cf0321}, /* huge (-443616) offs */
+	{0x90007514, 0x9000752c, 0x00000019}, /* tiny (+24) offs */
+	{0x9001a578, 0x9001a77a, 0x00000203}, /* tiny (+514) offs */
+	{0x90031ed8, 0x90032634, 0x0000075d}, /* tiny (+1884) offs */
+	{0x9008c7f2, 0x9008d3f0, 0x00400401}, /* small (+3072) offs */
+	{0x9000bb38, 0x9003b340, 0x17c00009}, /* big  (+194568) offs */
+	{0x90008f44, 0x90578d80, 0xb7c2063d}  /* huge (+5701180) offs */
+};
+
+static __init int instr_gen_test(void)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(arcgenbr_test_data); i++)
+		if (branch_gen_test(&arcgenbr_test_data[i]))
+			return -EFAULT;
+
+	pr_info(SELFTEST_MSG "OK\n");
+
+	return 0;
+}
+early_initcall(instr_gen_test);
+
+#endif /* CONFIG_ARC_DBG_JUMP_LABEL */
diff --git a/arch/arc/kernel/kgdb.c b/arch/arc/kernel/kgdb.c
new file mode 100644
index 000000000..4f2b59514
--- /dev/null
+++ b/arch/arc/kernel/kgdb.c
@@ -0,0 +1,206 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * kgdb support for ARC
+ *
+ * Copyright (C) 2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#include <linux/kgdb.h>
+#include <linux/sched.h>
+#include <linux/sched/task_stack.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;
+		fallthrough;
+
+	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;
+}
+
+int kgdb_arch_init(void)
+{
+	single_step_data.armed = 0;
+	return 0;
+}
+
+void kgdb_trap(struct pt_regs *regs)
+{
+	/* 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 (regs->ecr.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;
+}
+
+void kgdb_call_nmi_hook(void *ignored)
+{
+	/* Default implementation passes get_irq_regs() but we don't */
+	kgdb_nmicallback(raw_smp_processor_id(), NULL);
+}
+
+const 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 000000000..f8e296083
--- /dev/null
+++ b/arch/arc/kernel/kprobes.c
@@ -0,0 +1,416 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#include <linux/types.h>
+#include <linux/kprobes.h>
+#include <linux/slab.h>
+#include <linux/module.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)
+{
+	__this_cpu_write(current_kprobe, kcb->prev_kprobe.kp);
+	kcb->kprobe_status = kcb->prev_kprobe.status;
+}
+
+static inline void __kprobes set_current_kprobe(struct kprobe *p)
+{
+	__this_cpu_write(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));
+	}
+}
+
+static 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 means user handler setup registers to exit
+		 * to another instruction, we must skip the single stepping.
+		 */
+		if (!p->pre_handler || !p->pre_handler(p, regs)) {
+			setup_singlestep(p, regs);
+			kcb->kprobe_status = KPROBE_HIT_SS;
+		} else {
+			reset_current_kprobe();
+			preempt_enable_no_resched();
+		}
+
+		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.
+		 */
+
+		/*
+		 * 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;
+}
+
+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;
+	ri->fp = NULL;
+
+	/* 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)
+{
+	regs->ret = __kretprobe_trampoline_handler(regs, NULL);
+
+	/* 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 address, struct pt_regs *regs)
+{
+	notify_die(DIE_TRAP, "kprobe_trap", regs, address, 0, SIGTRAP);
+}
diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c
new file mode 100644
index 000000000..02b28a932
--- /dev/null
+++ b/arch/arc/kernel/mcip.c
@@ -0,0 +1,418 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * ARC ARConnect (MultiCore IP) support (formerly known as MCIP)
+ *
+ * Copyright (C) 2013 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#include <linux/smp.h>
+#include <linux/irq.h>
+#include <linux/irqchip/chained_irq.h>
+#include <linux/spinlock.h>
+#include <soc/arc/mcip.h>
+#include <asm/irqflags-arcv2.h>
+#include <asm/setup.h>
+
+static DEFINE_RAW_SPINLOCK(mcip_lock);
+
+#ifdef CONFIG_SMP
+
+static char smp_cpuinfo_buf[128];
+
+/*
+ * Set mask to halt GFRC if any online core in SMP cluster is halted.
+ * Only works for ARC HS v3.0+, on earlier versions has no effect.
+ */
+static void mcip_update_gfrc_halt_mask(int cpu)
+{
+	struct bcr_generic gfrc;
+	unsigned long flags;
+	u32 gfrc_halt_mask;
+
+	READ_BCR(ARC_REG_GFRC_BUILD, gfrc);
+
+	/*
+	 * CMD_GFRC_SET_CORE and CMD_GFRC_READ_CORE commands were added in
+	 * GFRC 0x3 version.
+	 */
+	if (gfrc.ver < 0x3)
+		return;
+
+	raw_spin_lock_irqsave(&mcip_lock, flags);
+
+	__mcip_cmd(CMD_GFRC_READ_CORE, 0);
+	gfrc_halt_mask = read_aux_reg(ARC_REG_MCIP_READBACK);
+	gfrc_halt_mask |= BIT(cpu);
+	__mcip_cmd_data(CMD_GFRC_SET_CORE, 0, gfrc_halt_mask);
+
+	raw_spin_unlock_irqrestore(&mcip_lock, flags);
+}
+
+static void mcip_update_debug_halt_mask(int cpu)
+{
+	u32 mcip_mask = 0;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&mcip_lock, flags);
+
+	/*
+	 * mcip_mask is same for CMD_DEBUG_SET_SELECT and CMD_DEBUG_SET_MASK
+	 * commands. So read it once instead of reading both CMD_DEBUG_READ_MASK
+	 * and CMD_DEBUG_READ_SELECT.
+	 */
+	__mcip_cmd(CMD_DEBUG_READ_SELECT, 0);
+	mcip_mask = read_aux_reg(ARC_REG_MCIP_READBACK);
+
+	mcip_mask |= BIT(cpu);
+
+	__mcip_cmd_data(CMD_DEBUG_SET_SELECT, 0, mcip_mask);
+	/*
+	 * Parameter specified halt cause:
+	 * STATUS32[H]/actionpoint/breakpoint/self-halt
+	 * We choose all of them (0xF).
+	 */
+	__mcip_cmd_data(CMD_DEBUG_SET_MASK, 0xF, mcip_mask);
+
+	raw_spin_unlock_irqrestore(&mcip_lock, flags);
+}
+
+static void mcip_setup_per_cpu(int cpu)
+{
+	struct mcip_bcr mp;
+
+	READ_BCR(ARC_REG_MCIP_BCR, mp);
+
+	smp_ipi_irq_setup(cpu, IPI_IRQ);
+	smp_ipi_irq_setup(cpu, SOFTIRQ_IRQ);
+
+	/* Update GFRC halt mask as new CPU came online */
+	if (mp.gfrc)
+		mcip_update_gfrc_halt_mask(cpu);
+
+	/* Update MCIP debug mask as new CPU came online */
+	if (mp.dbg)
+		mcip_update_debug_halt_mask(cpu);
+}
+
+static void mcip_ipi_send(int cpu)
+{
+	unsigned long flags;
+	int ipi_was_pending;
+
+	/* ARConnect can only send IPI to others */
+	if (unlikely(cpu == raw_smp_processor_id())) {
+		arc_softirq_trigger(SOFTIRQ_IRQ);
+		return;
+	}
+
+	raw_spin_lock_irqsave(&mcip_lock, flags);
+
+	/*
+	 * If receiver already has a pending interrupt, elide sending this one.
+	 * Linux cross core calling works well with concurrent IPIs
+	 * coalesced into one
+	 * see arch/arc/kernel/smp.c: ipi_send_msg_one()
+	 */
+	__mcip_cmd(CMD_INTRPT_READ_STATUS, cpu);
+	ipi_was_pending = read_aux_reg(ARC_REG_MCIP_READBACK);
+	if (!ipi_was_pending)
+		__mcip_cmd(CMD_INTRPT_GENERATE_IRQ, cpu);
+
+	raw_spin_unlock_irqrestore(&mcip_lock, flags);
+}
+
+static void mcip_ipi_clear(int irq)
+{
+	unsigned int cpu, c;
+	unsigned long flags;
+
+	if (unlikely(irq == SOFTIRQ_IRQ)) {
+		arc_softirq_clear(irq);
+		return;
+	}
+
+	raw_spin_lock_irqsave(&mcip_lock, flags);
+
+	/* Who sent the IPI */
+	__mcip_cmd(CMD_INTRPT_CHECK_SOURCE, 0);
+
+	cpu = read_aux_reg(ARC_REG_MCIP_READBACK);	/* 1,2,4,8... */
+
+	/*
+	 * In rare case, multiple concurrent IPIs sent to same target can
+	 * possibly be coalesced by MCIP into 1 asserted IRQ, so @cpus can be
+	 * "vectored" (multiple bits sets) as opposed to typical single bit
+	 */
+	do {
+		c = __ffs(cpu);			/* 0,1,2,3 */
+		__mcip_cmd(CMD_INTRPT_GENERATE_ACK, c);
+		cpu &= ~(1U << c);
+	} while (cpu);
+
+	raw_spin_unlock_irqrestore(&mcip_lock, flags);
+}
+
+static void mcip_probe_n_setup(void)
+{
+	struct mcip_bcr mp;
+
+	READ_BCR(ARC_REG_MCIP_BCR, mp);
+
+	sprintf(smp_cpuinfo_buf,
+		"Extn [SMP]\t: ARConnect (v%d): %d cores with %s%s%s%s\n",
+		mp.ver, mp.num_cores,
+		IS_AVAIL1(mp.ipi, "IPI "),
+		IS_AVAIL1(mp.idu, "IDU "),
+		IS_AVAIL1(mp.dbg, "DEBUG "),
+		IS_AVAIL1(mp.gfrc, "GFRC"));
+}
+
+struct plat_smp_ops plat_smp_ops = {
+	.info		= smp_cpuinfo_buf,
+	.init_early_smp	= mcip_probe_n_setup,
+	.init_per_cpu	= mcip_setup_per_cpu,
+	.ipi_send	= mcip_ipi_send,
+	.ipi_clear	= mcip_ipi_clear,
+};
+
+#endif
+
+/***************************************************************************
+ * ARCv2 Interrupt Distribution Unit (IDU)
+ *
+ * Connects external "COMMON" IRQs to core intc, providing:
+ *  -dynamic routing (IRQ affinity)
+ *  -load balancing (Round Robin interrupt distribution)
+ *  -1:N distribution
+ *
+ * It physically resides in the MCIP hw block
+ */
+
+#include <linux/irqchip.h>
+#include <linux/of.h>
+#include <linux/of_irq.h>
+
+/*
+ * Set the DEST for @cmn_irq to @cpu_mask (1 bit per core)
+ */
+static void idu_set_dest(unsigned int cmn_irq, unsigned int cpu_mask)
+{
+	__mcip_cmd_data(CMD_IDU_SET_DEST, cmn_irq, cpu_mask);
+}
+
+static void idu_set_mode(unsigned int cmn_irq, bool set_lvl, unsigned int lvl,
+			 bool set_distr, unsigned int distr)
+{
+	union {
+		unsigned int word;
+		struct {
+			unsigned int distr:2, pad:2, lvl:1, pad2:27;
+		};
+	} data;
+
+	data.word = __mcip_cmd_read(CMD_IDU_READ_MODE, cmn_irq);
+	if (set_distr)
+		data.distr = distr;
+	if (set_lvl)
+		data.lvl = lvl;
+	__mcip_cmd_data(CMD_IDU_SET_MODE, cmn_irq, data.word);
+}
+
+static void idu_irq_mask_raw(irq_hw_number_t hwirq)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&mcip_lock, flags);
+	__mcip_cmd_data(CMD_IDU_SET_MASK, hwirq, 1);
+	raw_spin_unlock_irqrestore(&mcip_lock, flags);
+}
+
+static void idu_irq_mask(struct irq_data *data)
+{
+	idu_irq_mask_raw(data->hwirq);
+}
+
+static void idu_irq_unmask(struct irq_data *data)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&mcip_lock, flags);
+	__mcip_cmd_data(CMD_IDU_SET_MASK, data->hwirq, 0);
+	raw_spin_unlock_irqrestore(&mcip_lock, flags);
+}
+
+static void idu_irq_ack(struct irq_data *data)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&mcip_lock, flags);
+	__mcip_cmd(CMD_IDU_ACK_CIRQ, data->hwirq);
+	raw_spin_unlock_irqrestore(&mcip_lock, flags);
+}
+
+static void idu_irq_mask_ack(struct irq_data *data)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&mcip_lock, flags);
+	__mcip_cmd_data(CMD_IDU_SET_MASK, data->hwirq, 1);
+	__mcip_cmd(CMD_IDU_ACK_CIRQ, data->hwirq);
+	raw_spin_unlock_irqrestore(&mcip_lock, flags);
+}
+
+static int
+idu_irq_set_affinity(struct irq_data *data, const struct cpumask *cpumask,
+		     bool force)
+{
+	unsigned long flags;
+	cpumask_t online;
+	unsigned int destination_bits;
+	unsigned int distribution_mode;
+
+	/* errout if no online cpu per @cpumask */
+	if (!cpumask_and(&online, cpumask, cpu_online_mask))
+		return -EINVAL;
+
+	raw_spin_lock_irqsave(&mcip_lock, flags);
+
+	destination_bits = cpumask_bits(&online)[0];
+	idu_set_dest(data->hwirq, destination_bits);
+
+	if (ffs(destination_bits) == fls(destination_bits))
+		distribution_mode = IDU_M_DISTRI_DEST;
+	else
+		distribution_mode = IDU_M_DISTRI_RR;
+
+	idu_set_mode(data->hwirq, false, 0, true, distribution_mode);
+
+	raw_spin_unlock_irqrestore(&mcip_lock, flags);
+
+	return IRQ_SET_MASK_OK;
+}
+
+static int idu_irq_set_type(struct irq_data *data, u32 type)
+{
+	unsigned long flags;
+
+	/*
+	 * ARCv2 IDU HW does not support inverse polarity, so these are the
+	 * only interrupt types supported.
+	 */
+	if (type & ~(IRQ_TYPE_EDGE_RISING | IRQ_TYPE_LEVEL_HIGH))
+		return -EINVAL;
+
+	raw_spin_lock_irqsave(&mcip_lock, flags);
+
+	idu_set_mode(data->hwirq, true,
+		     type & IRQ_TYPE_EDGE_RISING ? IDU_M_TRIG_EDGE :
+						   IDU_M_TRIG_LEVEL,
+		     false, 0);
+
+	raw_spin_unlock_irqrestore(&mcip_lock, flags);
+
+	return 0;
+}
+
+static void idu_irq_enable(struct irq_data *data)
+{
+	/*
+	 * By default send all common interrupts to all available online CPUs.
+	 * The affinity of common interrupts in IDU must be set manually since
+	 * in some cases the kernel will not call irq_set_affinity() by itself:
+	 *   1. When the kernel is not configured with support of SMP.
+	 *   2. When the kernel is configured with support of SMP but upper
+	 *      interrupt controllers does not support setting of the affinity
+	 *      and cannot propagate it to IDU.
+	 */
+	idu_irq_set_affinity(data, cpu_online_mask, false);
+	idu_irq_unmask(data);
+}
+
+static struct irq_chip idu_irq_chip = {
+	.name			= "MCIP IDU Intc",
+	.irq_mask		= idu_irq_mask,
+	.irq_unmask		= idu_irq_unmask,
+	.irq_ack		= idu_irq_ack,
+	.irq_mask_ack		= idu_irq_mask_ack,
+	.irq_enable		= idu_irq_enable,
+	.irq_set_type		= idu_irq_set_type,
+#ifdef CONFIG_SMP
+	.irq_set_affinity       = idu_irq_set_affinity,
+#endif
+
+};
+
+static void idu_cascade_isr(struct irq_desc *desc)
+{
+	struct irq_domain *idu_domain = irq_desc_get_handler_data(desc);
+	struct irq_chip *core_chip = irq_desc_get_chip(desc);
+	irq_hw_number_t core_hwirq = irqd_to_hwirq(irq_desc_get_irq_data(desc));
+	irq_hw_number_t idu_hwirq = core_hwirq - FIRST_EXT_IRQ;
+
+	chained_irq_enter(core_chip, desc);
+	generic_handle_domain_irq(idu_domain, idu_hwirq);
+	chained_irq_exit(core_chip, desc);
+}
+
+static int idu_irq_map(struct irq_domain *d, unsigned int virq, irq_hw_number_t hwirq)
+{
+	irq_set_chip_and_handler(virq, &idu_irq_chip, handle_level_irq);
+	return 0;
+}
+
+static const struct irq_domain_ops idu_irq_ops = {
+	.xlate	= irq_domain_xlate_onetwocell,
+	.map	= idu_irq_map,
+};
+
+/*
+ * [16, 23]: Statically assigned always private-per-core (Timers, WDT, IPI)
+ * [24, 23+C]: If C > 0 then "C" common IRQs
+ * [24+C, N]: Not statically assigned, private-per-core
+ */
+
+
+static int __init
+idu_of_init(struct device_node *intc, struct device_node *parent)
+{
+	struct irq_domain *domain;
+	int nr_irqs;
+	int i, virq;
+	struct mcip_bcr mp;
+	struct mcip_idu_bcr idu_bcr;
+
+	READ_BCR(ARC_REG_MCIP_BCR, mp);
+
+	if (!mp.idu)
+		panic("IDU not detected, but DeviceTree using it");
+
+	READ_BCR(ARC_REG_MCIP_IDU_BCR, idu_bcr);
+	nr_irqs = mcip_idu_bcr_to_nr_irqs(idu_bcr);
+
+	pr_info("MCIP: IDU supports %u common irqs\n", nr_irqs);
+
+	domain = irq_domain_create_linear(of_fwnode_handle(intc), nr_irqs,
+					  &idu_irq_ops, NULL);
+
+	/* Parent interrupts (core-intc) are already mapped */
+
+	for (i = 0; i < nr_irqs; i++) {
+		/* Mask all common interrupts by default */
+		idu_irq_mask_raw(i);
+
+		/*
+		 * Return parent uplink IRQs (towards core intc) 24,25,.....
+		 * this step has been done before already
+		 * however we need it to get the parent virq and set IDU handler
+		 * as first level isr
+		 */
+		virq = irq_create_mapping(NULL, i + FIRST_EXT_IRQ);
+		BUG_ON(!virq);
+		irq_set_chained_handler_and_data(virq, idu_cascade_isr, domain);
+	}
+
+	__mcip_cmd(CMD_IDU_ENABLE, 0);
+
+	return 0;
+}
+IRQCHIP_DECLARE(arcv2_idu_intc, "snps,archs-idu-intc", idu_of_init);
diff --git a/arch/arc/kernel/module.c b/arch/arc/kernel/module.c
new file mode 100644
index 000000000..c90c27904
--- /dev/null
+++ b/arch/arc/kernel/module.c
@@ -0,0 +1,146 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#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);
+}
+
+/*
+ * This gets called before relocation loop in generic loader
+ * Make a note of the section index of unwinding section
+ */
+int module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs,
+			      char *secstr, struct module *mod)
+{
+#ifdef CONFIG_ARC_DW2_UNWIND
+	mod->arch.unw_sec_idx = 0;
+	mod->arch.unw_info = NULL;
+#endif
+	mod->arch.secstr = secstr;
+	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, relo_type;
+	Elf32_Rela *rel_entry = (void *)sechdrs[relsec].sh_addr;
+	Elf32_Sym *sym_entry, *sym_sec;
+	Elf32_Addr relocation, location, tgt_addr;
+	unsigned int tgtsec;
+
+	/*
+	 * @relsec has relocations e.g. .rela.init.text
+	 * @tgtsec is section to patch e.g. .init.text
+	 */
+	tgtsec = sechdrs[relsec].sh_info;
+	tgt_addr = sechdrs[tgtsec].sh_addr;
+	sym_sec = (Elf32_Sym *) sechdrs[symindex].sh_addr;
+	n = sechdrs[relsec].sh_size / sizeof(*rel_entry);
+
+	pr_debug("\nSection to fixup %s @%x\n",
+		 module->arch.secstr + sechdrs[tgtsec].sh_name, tgt_addr);
+	pr_debug("=========================================================\n");
+	pr_debug("r_off\tr_add\tst_value ADDRESS  VALUE\n");
+	pr_debug("=========================================================\n");
+
+	/* Loop thru entries in relocation section */
+	for (i = 0; i < n; i++) {
+		const char *s;
+
+		/* This is where to make the change */
+		location = tgt_addr + 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;
+
+		if (sym_entry->st_name == 0 && ELF_ST_TYPE (sym_entry->st_info) == STT_SECTION) {
+			s = module->arch.secstr + sechdrs[sym_entry->st_shndx].sh_name;
+		} else {
+			s = strtab + sym_entry->st_name;
+		}
+
+		pr_debug("   %x\t%x\t%x %x %x [%s]\n",
+			 rel_entry[i].r_offset, rel_entry[i].r_addend,
+			 sym_entry->st_value, location, relocation, s);
+
+		/* 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))	/* ME ( S + A ) */
+			arc_write_me((unsigned short *)location, relocation);
+		else if (R_ARC_32 == relo_type)		/* ( S + A ) */
+			*((Elf32_Addr *) location) = relocation;
+		else if (R_ARC_32_PCREL == relo_type)	/* ( S + A ) - PDATA ) */
+			*((Elf32_Addr *) location) = relocation - location;
+		else
+			goto relo_err;
+
+	}
+
+#ifdef CONFIG_ARC_DW2_UNWIND
+	if (strcmp(module->arch.secstr+sechdrs[tgtsec].sh_name, ".eh_frame") == 0)
+		module->arch.unw_sec_idx = tgtsec;
+#endif
+
+	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/perf_event.c b/arch/arc/kernel/perf_event.c
new file mode 100644
index 000000000..ed6d4f0cd
--- /dev/null
+++ b/arch/arc/kernel/perf_event.c
@@ -0,0 +1,848 @@
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Linux performance counter support for ARC CPUs.
+// This code is inspired by the perf support of various other architectures.
+//
+// Copyright (C) 2013-2018 Synopsys, Inc. (www.synopsys.com)
+
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/perf_event.h>
+#include <linux/platform_device.h>
+#include <asm/arcregs.h>
+#include <asm/stacktrace.h>
+
+/* HW holds 8 symbols + one for null terminator */
+#define ARCPMU_EVENT_NAME_LEN	9
+
+/*
+ * Some ARC pct quirks:
+ *
+ * PERF_COUNT_HW_STALLED_CYCLES_BACKEND
+ * PERF_COUNT_HW_STALLED_CYCLES_FRONTEND
+ *	The ARC 700 can either measure stalls per pipeline stage, or all stalls
+ *	combined; for now we assign all stalls to STALLED_CYCLES_BACKEND
+ *	and all pipeline flushes (e.g. caused by mispredicts, etc.) to
+ *	STALLED_CYCLES_FRONTEND.
+ *
+ *	We could start multiple performance counters and combine everything
+ *	afterwards, but that makes it complicated.
+ *
+ *	Note that I$ cache misses aren't counted by either of the two!
+ */
+
+/*
+ * ARC PCT has hardware conditions with fixed "names" but variable "indexes"
+ * (based on a specific RTL build)
+ * Below is the static map between perf generic/arc specific event_id and
+ * h/w condition names.
+ * At the time of probe, we loop thru each index and find its name to
+ * complete the mapping of perf event_id to h/w index as latter is needed
+ * to program the counter really
+ */
+static const char * const arc_pmu_ev_hw_map[] = {
+	/* count cycles */
+	[PERF_COUNT_HW_CPU_CYCLES] = "crun",
+	[PERF_COUNT_HW_REF_CPU_CYCLES] = "crun",
+	[PERF_COUNT_HW_BUS_CYCLES] = "crun",
+
+	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = "bflush",
+	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = "bstall",
+
+	/* counts condition */
+	[PERF_COUNT_HW_INSTRUCTIONS] = "iall",
+	/* All jump instructions that are taken */
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = "ijmptak",
+#ifdef CONFIG_ISA_ARCV2
+	[PERF_COUNT_HW_BRANCH_MISSES] = "bpmp",
+#else
+	[PERF_COUNT_ARC_BPOK]         = "bpok",	  /* NP-NT, PT-T, PNT-NT */
+	[PERF_COUNT_HW_BRANCH_MISSES] = "bpfail", /* NP-T, PT-NT, PNT-T */
+#endif
+	[PERF_COUNT_ARC_LDC] = "imemrdc",	/* Instr: mem read cached */
+	[PERF_COUNT_ARC_STC] = "imemwrc",	/* Instr: mem write cached */
+
+	[PERF_COUNT_ARC_DCLM] = "dclm",		/* D-cache Load Miss */
+	[PERF_COUNT_ARC_DCSM] = "dcsm",		/* D-cache Store Miss */
+	[PERF_COUNT_ARC_ICM] = "icm",		/* I-cache Miss */
+	[PERF_COUNT_ARC_EDTLB] = "edtlb",	/* D-TLB Miss */
+	[PERF_COUNT_ARC_EITLB] = "eitlb",	/* I-TLB Miss */
+
+	[PERF_COUNT_HW_CACHE_REFERENCES] = "imemrdc",	/* Instr: mem read cached */
+	[PERF_COUNT_HW_CACHE_MISSES] = "dclm",		/* D-cache Load Miss */
+};
+
+#define C(_x)			PERF_COUNT_HW_CACHE_##_x
+#define CACHE_OP_UNSUPPORTED	0xffff
+
+static const unsigned int arc_pmu_cache_map[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+	[C(L1D)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= PERF_COUNT_ARC_LDC,
+			[C(RESULT_MISS)]	= PERF_COUNT_ARC_DCLM,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= PERF_COUNT_ARC_STC,
+			[C(RESULT_MISS)]	= PERF_COUNT_ARC_DCSM,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(L1I)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= PERF_COUNT_HW_INSTRUCTIONS,
+			[C(RESULT_MISS)]	= PERF_COUNT_ARC_ICM,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(LL)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(DTLB)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= PERF_COUNT_ARC_LDC,
+			[C(RESULT_MISS)]	= PERF_COUNT_ARC_EDTLB,
+		},
+			/* DTLB LD/ST Miss not segregated by h/w*/
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(ITLB)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= PERF_COUNT_ARC_EITLB,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(BPU)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)] = PERF_COUNT_HW_BRANCH_INSTRUCTIONS,
+			[C(RESULT_MISS)]	= PERF_COUNT_HW_BRANCH_MISSES,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(NODE)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+};
+
+enum arc_pmu_attr_groups {
+	ARCPMU_ATTR_GR_EVENTS,
+	ARCPMU_ATTR_GR_FORMATS,
+	ARCPMU_NR_ATTR_GR
+};
+
+struct arc_pmu_raw_event_entry {
+	char name[ARCPMU_EVENT_NAME_LEN];
+};
+
+struct arc_pmu {
+	struct pmu	pmu;
+	unsigned int	irq;
+	int		n_counters;
+	int		n_events;
+	u64		max_period;
+	int		ev_hw_idx[PERF_COUNT_ARC_HW_MAX];
+
+	struct arc_pmu_raw_event_entry	*raw_entry;
+	struct attribute		**attrs;
+	struct perf_pmu_events_attr	*attr;
+	const struct attribute_group	*attr_groups[ARCPMU_NR_ATTR_GR + 1];
+};
+
+struct arc_pmu_cpu {
+	/*
+	 * A 1 bit for an index indicates that the counter is being used for
+	 * an event. A 0 means that the counter can be used.
+	 */
+	unsigned long	used_mask[BITS_TO_LONGS(ARC_PERF_MAX_COUNTERS)];
+
+	/*
+	 * The events that are active on the PMU for the given index.
+	 */
+	struct perf_event *act_counter[ARC_PERF_MAX_COUNTERS];
+};
+
+struct arc_callchain_trace {
+	int depth;
+	void *perf_stuff;
+};
+
+static int callchain_trace(unsigned int addr, void *data)
+{
+	struct arc_callchain_trace *ctrl = data;
+	struct perf_callchain_entry_ctx *entry = ctrl->perf_stuff;
+
+	perf_callchain_store(entry, addr);
+
+	if (ctrl->depth++ < 3)
+		return 0;
+
+	return -1;
+}
+
+void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
+			   struct pt_regs *regs)
+{
+	struct arc_callchain_trace ctrl = {
+		.depth = 0,
+		.perf_stuff = entry,
+	};
+
+	arc_unwind_core(NULL, regs, callchain_trace, &ctrl);
+}
+
+void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
+			 struct pt_regs *regs)
+{
+	/*
+	 * User stack can't be unwound trivially with kernel dwarf unwinder
+	 * So for now just record the user PC
+	 */
+	perf_callchain_store(entry, instruction_pointer(regs));
+}
+
+static struct arc_pmu *arc_pmu;
+static DEFINE_PER_CPU(struct arc_pmu_cpu, arc_pmu_cpu);
+
+/* read counter #idx; note that counter# != event# on ARC! */
+static u64 arc_pmu_read_counter(int idx)
+{
+	u32 tmp;
+	u64 result;
+
+	/*
+	 * ARC supports making 'snapshots' of the counters, so we don't
+	 * need to care about counters wrapping to 0 underneath our feet
+	 */
+	write_aux_reg(ARC_REG_PCT_INDEX, idx);
+	tmp = read_aux_reg(ARC_REG_PCT_CONTROL);
+	write_aux_reg(ARC_REG_PCT_CONTROL, tmp | ARC_REG_PCT_CONTROL_SN);
+	result = (u64) (read_aux_reg(ARC_REG_PCT_SNAPH)) << 32;
+	result |= read_aux_reg(ARC_REG_PCT_SNAPL);
+
+	return result;
+}
+
+static void arc_perf_event_update(struct perf_event *event,
+				  struct hw_perf_event *hwc, int idx)
+{
+	u64 prev_raw_count = local64_read(&hwc->prev_count);
+	u64 new_raw_count = arc_pmu_read_counter(idx);
+	s64 delta = new_raw_count - prev_raw_count;
+
+	/*
+	 * We aren't afraid of hwc->prev_count changing beneath our feet
+	 * because there's no way for us to re-enter this function anytime.
+	 */
+	local64_set(&hwc->prev_count, new_raw_count);
+	local64_add(delta, &event->count);
+	local64_sub(delta, &hwc->period_left);
+}
+
+static void arc_pmu_read(struct perf_event *event)
+{
+	arc_perf_event_update(event, &event->hw, event->hw.idx);
+}
+
+static int arc_pmu_cache_event(u64 config)
+{
+	unsigned int cache_type, cache_op, cache_result;
+	int ret;
+
+	cache_type	= (config >>  0) & 0xff;
+	cache_op	= (config >>  8) & 0xff;
+	cache_result	= (config >> 16) & 0xff;
+	if (cache_type >= PERF_COUNT_HW_CACHE_MAX)
+		return -EINVAL;
+	if (cache_op >= PERF_COUNT_HW_CACHE_OP_MAX)
+		return -EINVAL;
+	if (cache_result >= PERF_COUNT_HW_CACHE_RESULT_MAX)
+		return -EINVAL;
+
+	ret = arc_pmu_cache_map[cache_type][cache_op][cache_result];
+
+	if (ret == CACHE_OP_UNSUPPORTED)
+		return -ENOENT;
+
+	pr_debug("init cache event: type/op/result %d/%d/%d with h/w %d \'%s\'\n",
+		 cache_type, cache_op, cache_result, ret,
+		 arc_pmu_ev_hw_map[ret]);
+
+	return ret;
+}
+
+/* initializes hw_perf_event structure if event is supported */
+static int arc_pmu_event_init(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	int ret;
+
+	if (!is_sampling_event(event)) {
+		hwc->sample_period = arc_pmu->max_period;
+		hwc->last_period = hwc->sample_period;
+		local64_set(&hwc->period_left, hwc->sample_period);
+	}
+
+	hwc->config = 0;
+
+	if (is_isa_arcv2()) {
+		/* "exclude user" means "count only kernel" */
+		if (event->attr.exclude_user)
+			hwc->config |= ARC_REG_PCT_CONFIG_KERN;
+
+		/* "exclude kernel" means "count only user" */
+		if (event->attr.exclude_kernel)
+			hwc->config |= ARC_REG_PCT_CONFIG_USER;
+	}
+
+	switch (event->attr.type) {
+	case PERF_TYPE_HARDWARE:
+		if (event->attr.config >= PERF_COUNT_HW_MAX)
+			return -ENOENT;
+		if (arc_pmu->ev_hw_idx[event->attr.config] < 0)
+			return -ENOENT;
+		hwc->config |= arc_pmu->ev_hw_idx[event->attr.config];
+		pr_debug("init event %d with h/w %08x \'%s\'\n",
+			 (int)event->attr.config, (int)hwc->config,
+			 arc_pmu_ev_hw_map[event->attr.config]);
+		return 0;
+
+	case PERF_TYPE_HW_CACHE:
+		ret = arc_pmu_cache_event(event->attr.config);
+		if (ret < 0)
+			return ret;
+		hwc->config |= arc_pmu->ev_hw_idx[ret];
+		pr_debug("init cache event with h/w %08x \'%s\'\n",
+			 (int)hwc->config, arc_pmu_ev_hw_map[ret]);
+		return 0;
+
+	case PERF_TYPE_RAW:
+		if (event->attr.config >= arc_pmu->n_events)
+			return -ENOENT;
+
+		hwc->config |= event->attr.config;
+		pr_debug("init raw event with idx %lld \'%s\'\n",
+			 event->attr.config,
+			 arc_pmu->raw_entry[event->attr.config].name);
+
+		return 0;
+
+	default:
+		return -ENOENT;
+	}
+}
+
+/* starts all counters */
+static void arc_pmu_enable(struct pmu *pmu)
+{
+	u32 tmp;
+	tmp = read_aux_reg(ARC_REG_PCT_CONTROL);
+	write_aux_reg(ARC_REG_PCT_CONTROL, (tmp & 0xffff0000) | 0x1);
+}
+
+/* stops all counters */
+static void arc_pmu_disable(struct pmu *pmu)
+{
+	u32 tmp;
+	tmp = read_aux_reg(ARC_REG_PCT_CONTROL);
+	write_aux_reg(ARC_REG_PCT_CONTROL, (tmp & 0xffff0000) | 0x0);
+}
+
+static int arc_pmu_event_set_period(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	s64 left = local64_read(&hwc->period_left);
+	s64 period = hwc->sample_period;
+	int idx = hwc->idx;
+	int overflow = 0;
+	u64 value;
+
+	if (unlikely(left <= -period)) {
+		/* left underflowed by more than period. */
+		left = period;
+		local64_set(&hwc->period_left, left);
+		hwc->last_period = period;
+		overflow = 1;
+	} else if (unlikely(left <= 0)) {
+		/* left underflowed by less than period. */
+		left += period;
+		local64_set(&hwc->period_left, left);
+		hwc->last_period = period;
+		overflow = 1;
+	}
+
+	if (left > arc_pmu->max_period)
+		left = arc_pmu->max_period;
+
+	value = arc_pmu->max_period - left;
+	local64_set(&hwc->prev_count, value);
+
+	/* Select counter */
+	write_aux_reg(ARC_REG_PCT_INDEX, idx);
+
+	/* Write value */
+	write_aux_reg(ARC_REG_PCT_COUNTL, lower_32_bits(value));
+	write_aux_reg(ARC_REG_PCT_COUNTH, upper_32_bits(value));
+
+	perf_event_update_userpage(event);
+
+	return overflow;
+}
+
+/*
+ * Assigns hardware counter to hardware condition.
+ * Note that there is no separate start/stop mechanism;
+ * stopping is achieved by assigning the 'never' condition
+ */
+static void arc_pmu_start(struct perf_event *event, int flags)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	int idx = hwc->idx;
+
+	if (WARN_ON_ONCE(idx == -1))
+		return;
+
+	if (flags & PERF_EF_RELOAD)
+		WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE));
+
+	hwc->state = 0;
+
+	arc_pmu_event_set_period(event);
+
+	/* Enable interrupt for this counter */
+	if (is_sampling_event(event))
+		write_aux_reg(ARC_REG_PCT_INT_CTRL,
+			      read_aux_reg(ARC_REG_PCT_INT_CTRL) | BIT(idx));
+
+	/* enable ARC pmu here */
+	write_aux_reg(ARC_REG_PCT_INDEX, idx);		/* counter # */
+	write_aux_reg(ARC_REG_PCT_CONFIG, hwc->config);	/* condition */
+}
+
+static void arc_pmu_stop(struct perf_event *event, int flags)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	int idx = hwc->idx;
+
+	/* Disable interrupt for this counter */
+	if (is_sampling_event(event)) {
+		/*
+		 * Reset interrupt flag by writing of 1. This is required
+		 * to make sure pending interrupt was not left.
+		 */
+		write_aux_reg(ARC_REG_PCT_INT_ACT, BIT(idx));
+		write_aux_reg(ARC_REG_PCT_INT_CTRL,
+			      read_aux_reg(ARC_REG_PCT_INT_CTRL) & ~BIT(idx));
+	}
+
+	if (!(event->hw.state & PERF_HES_STOPPED)) {
+		/* stop hw counter here */
+		write_aux_reg(ARC_REG_PCT_INDEX, idx);
+
+		/* condition code #0 is always "never" */
+		write_aux_reg(ARC_REG_PCT_CONFIG, 0);
+
+		event->hw.state |= PERF_HES_STOPPED;
+	}
+
+	if ((flags & PERF_EF_UPDATE) &&
+	    !(event->hw.state & PERF_HES_UPTODATE)) {
+		arc_perf_event_update(event, &event->hw, idx);
+		event->hw.state |= PERF_HES_UPTODATE;
+	}
+}
+
+static void arc_pmu_del(struct perf_event *event, int flags)
+{
+	struct arc_pmu_cpu *pmu_cpu = this_cpu_ptr(&arc_pmu_cpu);
+
+	arc_pmu_stop(event, PERF_EF_UPDATE);
+	__clear_bit(event->hw.idx, pmu_cpu->used_mask);
+
+	pmu_cpu->act_counter[event->hw.idx] = 0;
+
+	perf_event_update_userpage(event);
+}
+
+/* allocate hardware counter and optionally start counting */
+static int arc_pmu_add(struct perf_event *event, int flags)
+{
+	struct arc_pmu_cpu *pmu_cpu = this_cpu_ptr(&arc_pmu_cpu);
+	struct hw_perf_event *hwc = &event->hw;
+	int idx;
+
+	idx = ffz(pmu_cpu->used_mask[0]);
+	if (idx == arc_pmu->n_counters)
+		return -EAGAIN;
+
+	__set_bit(idx, pmu_cpu->used_mask);
+	hwc->idx = idx;
+
+	write_aux_reg(ARC_REG_PCT_INDEX, idx);
+
+	pmu_cpu->act_counter[idx] = event;
+
+	if (is_sampling_event(event)) {
+		/* Mimic full counter overflow as other arches do */
+		write_aux_reg(ARC_REG_PCT_INT_CNTL,
+			      lower_32_bits(arc_pmu->max_period));
+		write_aux_reg(ARC_REG_PCT_INT_CNTH,
+			      upper_32_bits(arc_pmu->max_period));
+	}
+
+	write_aux_reg(ARC_REG_PCT_CONFIG, 0);
+	write_aux_reg(ARC_REG_PCT_COUNTL, 0);
+	write_aux_reg(ARC_REG_PCT_COUNTH, 0);
+	local64_set(&hwc->prev_count, 0);
+
+	hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
+	if (flags & PERF_EF_START)
+		arc_pmu_start(event, PERF_EF_RELOAD);
+
+	perf_event_update_userpage(event);
+
+	return 0;
+}
+
+#ifdef CONFIG_ISA_ARCV2
+static irqreturn_t arc_pmu_intr(int irq, void *dev)
+{
+	struct perf_sample_data data;
+	struct arc_pmu_cpu *pmu_cpu = this_cpu_ptr(&arc_pmu_cpu);
+	struct pt_regs *regs;
+	unsigned int active_ints;
+	int idx;
+
+	arc_pmu_disable(&arc_pmu->pmu);
+
+	active_ints = read_aux_reg(ARC_REG_PCT_INT_ACT);
+	if (!active_ints)
+		goto done;
+
+	regs = get_irq_regs();
+
+	do {
+		struct perf_event *event;
+		struct hw_perf_event *hwc;
+
+		idx = __ffs(active_ints);
+
+		/* Reset interrupt flag by writing of 1 */
+		write_aux_reg(ARC_REG_PCT_INT_ACT, BIT(idx));
+
+		/*
+		 * On reset of "interrupt active" bit corresponding
+		 * "interrupt enable" bit gets automatically reset as well.
+		 * Now we need to re-enable interrupt for the counter.
+		 */
+		write_aux_reg(ARC_REG_PCT_INT_CTRL,
+			read_aux_reg(ARC_REG_PCT_INT_CTRL) | BIT(idx));
+
+		event = pmu_cpu->act_counter[idx];
+		hwc = &event->hw;
+
+		WARN_ON_ONCE(hwc->idx != idx);
+
+		arc_perf_event_update(event, &event->hw, event->hw.idx);
+		perf_sample_data_init(&data, 0, hwc->last_period);
+		if (arc_pmu_event_set_period(event))
+			perf_event_overflow(event, &data, regs);
+
+		active_ints &= ~BIT(idx);
+	} while (active_ints);
+
+done:
+	arc_pmu_enable(&arc_pmu->pmu);
+
+	return IRQ_HANDLED;
+}
+#else
+
+static irqreturn_t arc_pmu_intr(int irq, void *dev)
+{
+	return IRQ_NONE;
+}
+
+#endif /* CONFIG_ISA_ARCV2 */
+
+static void arc_cpu_pmu_irq_init(void *data)
+{
+	int irq = *(int *)data;
+
+	enable_percpu_irq(irq, IRQ_TYPE_NONE);
+
+	/* Clear all pending interrupt flags */
+	write_aux_reg(ARC_REG_PCT_INT_ACT, 0xffffffff);
+}
+
+/* Event field occupies the bottom 15 bits of our config field */
+PMU_FORMAT_ATTR(event, "config:0-14");
+static struct attribute *arc_pmu_format_attrs[] = {
+	&format_attr_event.attr,
+	NULL,
+};
+
+static struct attribute_group arc_pmu_format_attr_gr = {
+	.name = "format",
+	.attrs = arc_pmu_format_attrs,
+};
+
+static ssize_t arc_pmu_events_sysfs_show(struct device *dev,
+					 struct device_attribute *attr,
+					 char *page)
+{
+	struct perf_pmu_events_attr *pmu_attr;
+
+	pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr);
+	return sprintf(page, "event=0x%04llx\n", pmu_attr->id);
+}
+
+/*
+ * We don't add attrs here as we don't have pre-defined list of perf events.
+ * We will generate and add attrs dynamically in probe() after we read HW
+ * configuration.
+ */
+static struct attribute_group arc_pmu_events_attr_gr = {
+	.name = "events",
+};
+
+static void arc_pmu_add_raw_event_attr(int j, char *str)
+{
+	memmove(arc_pmu->raw_entry[j].name, str, ARCPMU_EVENT_NAME_LEN - 1);
+	arc_pmu->attr[j].attr.attr.name = arc_pmu->raw_entry[j].name;
+	arc_pmu->attr[j].attr.attr.mode = VERIFY_OCTAL_PERMISSIONS(0444);
+	arc_pmu->attr[j].attr.show = arc_pmu_events_sysfs_show;
+	arc_pmu->attr[j].id = j;
+	arc_pmu->attrs[j] = &(arc_pmu->attr[j].attr.attr);
+}
+
+static int arc_pmu_raw_alloc(struct device *dev)
+{
+	arc_pmu->attr = devm_kmalloc_array(dev, arc_pmu->n_events + 1,
+		sizeof(*arc_pmu->attr), GFP_KERNEL | __GFP_ZERO);
+	if (!arc_pmu->attr)
+		return -ENOMEM;
+
+	arc_pmu->attrs = devm_kmalloc_array(dev, arc_pmu->n_events + 1,
+		sizeof(*arc_pmu->attrs), GFP_KERNEL | __GFP_ZERO);
+	if (!arc_pmu->attrs)
+		return -ENOMEM;
+
+	arc_pmu->raw_entry = devm_kmalloc_array(dev, arc_pmu->n_events,
+		sizeof(*arc_pmu->raw_entry), GFP_KERNEL | __GFP_ZERO);
+	if (!arc_pmu->raw_entry)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static inline bool event_in_hw_event_map(int i, char *name)
+{
+	if (!arc_pmu_ev_hw_map[i])
+		return false;
+
+	if (!strlen(arc_pmu_ev_hw_map[i]))
+		return false;
+
+	if (strcmp(arc_pmu_ev_hw_map[i], name))
+		return false;
+
+	return true;
+}
+
+static void arc_pmu_map_hw_event(int j, char *str)
+{
+	int i;
+
+	/* See if HW condition has been mapped to a perf event_id */
+	for (i = 0; i < ARRAY_SIZE(arc_pmu_ev_hw_map); i++) {
+		if (event_in_hw_event_map(i, str)) {
+			pr_debug("mapping perf event %2d to h/w event \'%8s\' (idx %d)\n",
+				 i, str, j);
+			arc_pmu->ev_hw_idx[i] = j;
+		}
+	}
+}
+
+static int arc_pmu_device_probe(struct platform_device *pdev)
+{
+	struct arc_reg_pct_build pct_bcr;
+	struct arc_reg_cc_build cc_bcr;
+	int i, has_interrupts, irq = -1;
+	int counter_size;	/* in bits */
+
+	union cc_name {
+		struct {
+			u32 word0, word1;
+			char sentinel;
+		} indiv;
+		char str[ARCPMU_EVENT_NAME_LEN];
+	} cc_name;
+
+
+	READ_BCR(ARC_REG_PCT_BUILD, pct_bcr);
+	if (!pct_bcr.v) {
+		pr_err("This core does not have performance counters!\n");
+		return -ENODEV;
+	}
+	BUILD_BUG_ON(ARC_PERF_MAX_COUNTERS > 32);
+	if (WARN_ON(pct_bcr.c > ARC_PERF_MAX_COUNTERS))
+		return -EINVAL;
+
+	READ_BCR(ARC_REG_CC_BUILD, cc_bcr);
+	if (WARN(!cc_bcr.v, "Counters exist but No countable conditions?"))
+		return -EINVAL;
+
+	arc_pmu = devm_kzalloc(&pdev->dev, sizeof(struct arc_pmu), GFP_KERNEL);
+	if (!arc_pmu)
+		return -ENOMEM;
+
+	arc_pmu->n_events = cc_bcr.c;
+
+	if (arc_pmu_raw_alloc(&pdev->dev))
+		return -ENOMEM;
+
+	has_interrupts = is_isa_arcv2() ? pct_bcr.i : 0;
+
+	arc_pmu->n_counters = pct_bcr.c;
+	counter_size = 32 + (pct_bcr.s << 4);
+
+	arc_pmu->max_period = (1ULL << counter_size) / 2 - 1ULL;
+
+	pr_info("ARC perf\t: %d counters (%d bits), %d conditions%s\n",
+		arc_pmu->n_counters, counter_size, cc_bcr.c,
+		has_interrupts ? ", [overflow IRQ support]" : "");
+
+	cc_name.str[ARCPMU_EVENT_NAME_LEN - 1] = 0;
+	for (i = 0; i < PERF_COUNT_ARC_HW_MAX; i++)
+		arc_pmu->ev_hw_idx[i] = -1;
+
+	/* loop thru all available h/w condition indexes */
+	for (i = 0; i < cc_bcr.c; i++) {
+		write_aux_reg(ARC_REG_CC_INDEX, i);
+		cc_name.indiv.word0 = le32_to_cpu(read_aux_reg(ARC_REG_CC_NAME0));
+		cc_name.indiv.word1 = le32_to_cpu(read_aux_reg(ARC_REG_CC_NAME1));
+
+		arc_pmu_map_hw_event(i, cc_name.str);
+		arc_pmu_add_raw_event_attr(i, cc_name.str);
+	}
+
+	arc_pmu_events_attr_gr.attrs = arc_pmu->attrs;
+	arc_pmu->attr_groups[ARCPMU_ATTR_GR_EVENTS] = &arc_pmu_events_attr_gr;
+	arc_pmu->attr_groups[ARCPMU_ATTR_GR_FORMATS] = &arc_pmu_format_attr_gr;
+
+	arc_pmu->pmu = (struct pmu) {
+		.pmu_enable	= arc_pmu_enable,
+		.pmu_disable	= arc_pmu_disable,
+		.event_init	= arc_pmu_event_init,
+		.add		= arc_pmu_add,
+		.del		= arc_pmu_del,
+		.start		= arc_pmu_start,
+		.stop		= arc_pmu_stop,
+		.read		= arc_pmu_read,
+		.attr_groups	= arc_pmu->attr_groups,
+	};
+
+	if (has_interrupts) {
+		irq = platform_get_irq(pdev, 0);
+		if (irq >= 0) {
+			int ret;
+
+			arc_pmu->irq = irq;
+
+			/* intc map function ensures irq_set_percpu_devid() called */
+			ret = request_percpu_irq(irq, arc_pmu_intr, "ARC perf counters",
+						 this_cpu_ptr(&arc_pmu_cpu));
+
+			if (!ret)
+				on_each_cpu(arc_cpu_pmu_irq_init, &irq, 1);
+			else
+				irq = -1;
+		}
+
+	}
+
+	if (irq == -1)
+		arc_pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
+
+	/*
+	 * perf parser doesn't really like '-' symbol in events name, so let's
+	 * use '_' in arc pct name as it goes to kernel PMU event prefix.
+	 */
+	return perf_pmu_register(&arc_pmu->pmu, "arc_pct", PERF_TYPE_RAW);
+}
+
+static const struct of_device_id arc_pmu_match[] = {
+	{ .compatible = "snps,arc700-pct" },
+	{ .compatible = "snps,archs-pct" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, arc_pmu_match);
+
+static struct platform_driver arc_pmu_driver = {
+	.driver	= {
+		.name		= "arc-pct",
+		.of_match_table = of_match_ptr(arc_pmu_match),
+	},
+	.probe		= arc_pmu_device_probe,
+};
+
+module_platform_driver(arc_pmu_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Mischa Jonker <mjonker@synopsys.com>");
+MODULE_DESCRIPTION("ARC PMU driver");
diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c
new file mode 100644
index 000000000..8166d0908
--- /dev/null
+++ b/arch/arc/kernel/process.c
@@ -0,0 +1,296 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * Amit Bhor, Kanika Nema: Codito Technologies 2004
+ */
+
+#include <linux/errno.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/sched/task.h>
+#include <linux/sched/task_stack.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>
+
+#include <asm/fpu.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;
+}
+
+SYSCALL_DEFINE3(arc_usr_cmpxchg, int __user *, uaddr, int, expected, int, new)
+{
+	struct pt_regs *regs = current_pt_regs();
+	u32 uval;
+	int ret;
+
+	/*
+	 * This is only for old cores lacking LLOCK/SCOND, which by definition
+	 * can't possibly be SMP. Thus doesn't need to be SMP safe.
+	 * And this also helps reduce the overhead for serializing in
+	 * the UP case
+	 */
+	WARN_ON_ONCE(IS_ENABLED(CONFIG_SMP));
+
+	/* Z indicates to userspace if operation succeeded */
+	regs->status32 &= ~STATUS_Z_MASK;
+
+	ret = access_ok(uaddr, sizeof(*uaddr));
+	if (!ret)
+		 goto fail;
+
+again:
+	preempt_disable();
+
+	ret = __get_user(uval, uaddr);
+	if (ret)
+		 goto fault;
+
+	if (uval != expected)
+		 goto out;
+
+	ret = __put_user(new, uaddr);
+	if (ret)
+		 goto fault;
+
+	regs->status32 |= STATUS_Z_MASK;
+
+out:
+	preempt_enable();
+	return uval;
+
+fault:
+	preempt_enable();
+
+	if (unlikely(ret != -EFAULT))
+		 goto fail;
+
+	mmap_read_lock(current->mm);
+	ret = fixup_user_fault(current->mm, (unsigned long) uaddr,
+			       FAULT_FLAG_WRITE, NULL);
+	mmap_read_unlock(current->mm);
+
+	if (likely(!ret))
+		 goto again;
+
+fail:
+	force_sig(SIGSEGV);
+	return ret;
+}
+
+#ifdef CONFIG_ISA_ARCV2
+
+void arch_cpu_idle(void)
+{
+	/* Re-enable interrupts <= default irq priority before committing SLEEP */
+	const unsigned int arg = 0x10 | ARCV2_IRQ_DEF_PRIO;
+
+	__asm__ __volatile__(
+		"sleep %0	\n"
+		:
+		:"I"(arg)); /* can't be "r" has to be embedded const */
+
+	raw_local_irq_disable();
+}
+
+#else	/* ARC700 */
+
+void arch_cpu_idle(void)
+{
+	/* sleep, but enable both set E1/E2 (levels of interrupts) before committing */
+	__asm__ __volatile__("sleep 0x3	\n");
+	raw_local_irq_disable();
+}
+
+#endif
+
+asmlinkage void ret_from_fork(void);
+
+/*
+ * Copy architecture-specific thread state
+ *
+ * Layout of Child kernel mode stack as setup at the end of this function is
+ *
+ * |     ...        |
+ * |     ...        |
+ * |    unused      |
+ * |                |
+ * ------------------
+ * |     r25        |   <==== top of Stack (thread_info.ksp)
+ * ~                ~
+ * |    --to--      |   (CALLEE Regs of kernel mode)
+ * |     r13        |
+ * ------------------
+ * |     fp         |
+ * |    blink       |   @ret_from_fork
+ * ------------------
+ * |                |
+ * ~                ~
+ * ~                ~
+ * |                |
+ * ------------------
+ * |     r12        |
+ * ~                ~
+ * |    --to--      |   (scratch Regs of user mode)
+ * |     r0         |
+ * ------------------
+ * |      SP        |
+ * |    orig_r0     |
+ * |    event/ECR   |
+ * ------------------  <===== END of PAGE
+ */
+int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
+{
+	u64 clone_flags = args->flags;
+	unsigned long usp = args->stack;
+	unsigned long tls = args->tls;
+	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_info.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.
+	 */
+	task_thread_info(p)->ksp = (unsigned long)c_callee;	/* THREAD_INFO_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(args->fn)) {
+		memset(c_regs, 0, sizeof(struct pt_regs));
+
+		c_callee->r13 = (unsigned long)args->fn_arg;
+		c_callee->r14 = (unsigned long)args->fn;
+
+		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 = tls;
+	} else {
+		/* Normal fork case: set parent's TLS ptr in child */
+		task_thread_info(p)->thr_ptr =
+		task_thread_info(current)->thr_ptr;
+	}
+
+
+	/*
+	 * setup usermode thread pointer #1:
+	 * when child is picked by scheduler, __switch_to() uses @c_callee to
+	 * populate usermode callee regs: this works (despite being in a kernel
+	 * function) since special return path for child @ret_from_fork()
+	 * ensures those regs are not clobbered all the way to RTIE to usermode
+	 */
+	c_callee->r25 = task_thread_info(p)->thr_ptr;
+
+	return 0;
+}
+
+/*
+ * Do necessary setup to start up a new user task
+ */
+void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long usp)
+{
+	regs->sp = usp;
+	regs->ret = pc;
+
+	/*
+	 * [U]ser Mode bit set
+	 * [L] ZOL loop inhibited to begin with - cleared by a LP insn
+	 * Interrupts enabled
+	 */
+	regs->status32 = STATUS_U_MASK | STATUS_L_MASK | ISA_INIT_STATUS_BITS;
+
+	fpu_init_task(regs);
+
+	/* bogus seed values for debugging */
+	regs->lp_start = 0x10;
+	regs->lp_end = 0x80;
+}
+
+/*
+ * Some archs flush debug and FPU info here
+ */
+void flush_thread(void)
+{
+}
+
+int elf_check_arch(const struct elf32_hdr *x)
+{
+	unsigned int eflags;
+
+	if (x->e_machine != EM_ARC_INUSE) {
+		pr_err("ELF not built for %s ISA\n",
+			is_isa_arcompact() ? "ARCompact":"ARCv2");
+		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_fatal_sig(SIGSEGV);
+		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 000000000..fe2b6572e
--- /dev/null
+++ b/arch/arc/kernel/ptrace.c
@@ -0,0 +1,401 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#include <linux/ptrace.h>
+#include <linux/sched/task_stack.h>
+#include <linux/regset.h>
+#include <linux/unistd.h>
+#include <linux/elf.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/syscalls.h>
+
+struct pt_regs_offset {
+	const char *name;
+	int offset;
+};
+
+#define REG_OFFSET_NAME(r) {.name = #r, .offset = offsetof(struct pt_regs, r)}
+#define REG_OFFSET_END {.name = NULL, .offset = 0}
+
+#ifdef CONFIG_ISA_ARCOMPACT
+static const struct pt_regs_offset regoffset_table[] = {
+	REG_OFFSET_NAME(bta),
+	REG_OFFSET_NAME(lp_start),
+	REG_OFFSET_NAME(lp_end),
+	REG_OFFSET_NAME(lp_count),
+	REG_OFFSET_NAME(status32),
+	REG_OFFSET_NAME(ret),
+	REG_OFFSET_NAME(blink),
+	REG_OFFSET_NAME(fp),
+	REG_OFFSET_NAME(r26),
+	REG_OFFSET_NAME(r12),
+	REG_OFFSET_NAME(r11),
+	REG_OFFSET_NAME(r10),
+	REG_OFFSET_NAME(r9),
+	REG_OFFSET_NAME(r8),
+	REG_OFFSET_NAME(r7),
+	REG_OFFSET_NAME(r6),
+	REG_OFFSET_NAME(r5),
+	REG_OFFSET_NAME(r4),
+	REG_OFFSET_NAME(r3),
+	REG_OFFSET_NAME(r2),
+	REG_OFFSET_NAME(r1),
+	REG_OFFSET_NAME(r0),
+	REG_OFFSET_NAME(sp),
+	REG_OFFSET_NAME(orig_r0),
+	REG_OFFSET_NAME(ecr),
+	REG_OFFSET_END,
+};
+
+#else
+
+static const struct pt_regs_offset regoffset_table[] = {
+	REG_OFFSET_NAME(orig_r0),
+	REG_OFFSET_NAME(ecr),
+	REG_OFFSET_NAME(bta),
+	REG_OFFSET_NAME(r26),
+	REG_OFFSET_NAME(fp),
+	REG_OFFSET_NAME(sp),
+	REG_OFFSET_NAME(r12),
+	REG_OFFSET_NAME(r30),
+#ifdef CONFIG_ARC_HAS_ACCL_REGS
+	REG_OFFSET_NAME(r58),
+	REG_OFFSET_NAME(r59),
+#endif
+#ifdef CONFIG_ARC_DSP_SAVE_RESTORE_REGS
+	REG_OFFSET_NAME(DSP_CTRL),
+#endif
+	REG_OFFSET_NAME(r0),
+	REG_OFFSET_NAME(r1),
+	REG_OFFSET_NAME(r2),
+	REG_OFFSET_NAME(r3),
+	REG_OFFSET_NAME(r4),
+	REG_OFFSET_NAME(r5),
+	REG_OFFSET_NAME(r6),
+	REG_OFFSET_NAME(r7),
+	REG_OFFSET_NAME(r8),
+	REG_OFFSET_NAME(r9),
+	REG_OFFSET_NAME(r10),
+	REG_OFFSET_NAME(r11),
+	REG_OFFSET_NAME(blink),
+	REG_OFFSET_NAME(lp_end),
+	REG_OFFSET_NAME(lp_start),
+	REG_OFFSET_NAME(lp_count),
+	REG_OFFSET_NAME(ei),
+	REG_OFFSET_NAME(ldi),
+	REG_OFFSET_NAME(jli),
+	REG_OFFSET_NAME(ret),
+	REG_OFFSET_NAME(status32),
+	REG_OFFSET_END,
+};
+#endif
+
+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,
+		       struct membuf to)
+{
+	const struct pt_regs *ptregs = task_pt_regs(target);
+	const struct callee_regs *cregs = task_callee_regs(target);
+	unsigned int stop_pc_val;
+
+	membuf_zero(&to, 4);	// pad
+	membuf_store(&to, ptregs->bta);
+	membuf_store(&to, ptregs->lp_start);
+	membuf_store(&to, ptregs->lp_end);
+	membuf_store(&to, ptregs->lp_count);
+	membuf_store(&to, ptregs->status32);
+	membuf_store(&to, ptregs->ret);
+	membuf_store(&to, ptregs->blink);
+	membuf_store(&to, ptregs->fp);
+	membuf_store(&to, ptregs->r26);	// gp
+	membuf_store(&to, ptregs->r12);
+	membuf_store(&to, ptregs->r11);
+	membuf_store(&to, ptregs->r10);
+	membuf_store(&to, ptregs->r9);
+	membuf_store(&to, ptregs->r8);
+	membuf_store(&to, ptregs->r7);
+	membuf_store(&to, ptregs->r6);
+	membuf_store(&to, ptregs->r5);
+	membuf_store(&to, ptregs->r4);
+	membuf_store(&to, ptregs->r3);
+	membuf_store(&to, ptregs->r2);
+	membuf_store(&to, ptregs->r1);
+	membuf_store(&to, ptregs->r0);
+	membuf_store(&to, ptregs->sp);
+	membuf_zero(&to, 4);	// pad2
+	membuf_store(&to, cregs->r25);
+	membuf_store(&to, cregs->r24);
+	membuf_store(&to, cregs->r23);
+	membuf_store(&to, cregs->r22);
+	membuf_store(&to, cregs->r21);
+	membuf_store(&to, cregs->r20);
+	membuf_store(&to, cregs->r19);
+	membuf_store(&to, cregs->r18);
+	membuf_store(&to, cregs->r17);
+	membuf_store(&to, cregs->r16);
+	membuf_store(&to, cregs->r15);
+	membuf_store(&to, cregs->r14);
+	membuf_store(&to, cregs->r13);
+	membuf_store(&to, target->thread.fault_address); // efa
+
+	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");
+	}
+
+	return membuf_store(&to, stop_pc_val); // stop_pc
+}
+
+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)			\
+		user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf, \
+			offsetof(struct user_regs_struct, LOC), \
+			offsetof(struct user_regs_struct, LOC) + 4);
+
+	REG_IGNORE_ONE(pad);
+
+	REG_IN_ONE(scratch.bta, &ptregs->bta);
+	REG_IN_ONE(scratch.lp_start, &ptregs->lp_start);
+	REG_IN_ONE(scratch.lp_end, &ptregs->lp_end);
+	REG_IN_ONE(scratch.lp_count, &ptregs->lp_count);
+
+	REG_IGNORE_ONE(scratch.status32);
+
+	REG_IN_ONE(scratch.ret, &ptregs->ret);
+	REG_IN_ONE(scratch.blink, &ptregs->blink);
+	REG_IN_ONE(scratch.fp, &ptregs->fp);
+	REG_IN_ONE(scratch.gp, &ptregs->r26);
+	REG_IN_ONE(scratch.r12, &ptregs->r12);
+	REG_IN_ONE(scratch.r11, &ptregs->r11);
+	REG_IN_ONE(scratch.r10, &ptregs->r10);
+	REG_IN_ONE(scratch.r9, &ptregs->r9);
+	REG_IN_ONE(scratch.r8, &ptregs->r8);
+	REG_IN_ONE(scratch.r7, &ptregs->r7);
+	REG_IN_ONE(scratch.r6, &ptregs->r6);
+	REG_IN_ONE(scratch.r5, &ptregs->r5);
+	REG_IN_ONE(scratch.r4, &ptregs->r4);
+	REG_IN_ONE(scratch.r3, &ptregs->r3);
+	REG_IN_ONE(scratch.r2, &ptregs->r2);
+	REG_IN_ONE(scratch.r1, &ptregs->r1);
+	REG_IN_ONE(scratch.r0, &ptregs->r0);
+	REG_IN_ONE(scratch.sp, &ptregs->sp);
+
+	REG_IGNORE_ONE(pad2);
+
+	REG_IN_ONE(callee.r25, &cregs->r25);
+	REG_IN_ONE(callee.r24, &cregs->r24);
+	REG_IN_ONE(callee.r23, &cregs->r23);
+	REG_IN_ONE(callee.r22, &cregs->r22);
+	REG_IN_ONE(callee.r21, &cregs->r21);
+	REG_IN_ONE(callee.r20, &cregs->r20);
+	REG_IN_ONE(callee.r19, &cregs->r19);
+	REG_IN_ONE(callee.r18, &cregs->r18);
+	REG_IN_ONE(callee.r17, &cregs->r17);
+	REG_IN_ONE(callee.r16, &cregs->r16);
+	REG_IN_ONE(callee.r15, &cregs->r15);
+	REG_IN_ONE(callee.r14, &cregs->r14);
+	REG_IN_ONE(callee.r13, &cregs->r13);
+
+	REG_IGNORE_ONE(efa);			/* efa update invalid */
+	REG_IGNORE_ONE(stop_pc);		/* PC updated via @ret */
+
+	return ret;
+}
+
+#ifdef CONFIG_ISA_ARCV2
+static int arcv2regs_get(struct task_struct *target,
+		       const struct user_regset *regset,
+		       struct membuf to)
+{
+	const struct pt_regs *regs = task_pt_regs(target);
+
+	if (IS_ENABLED(CONFIG_ARC_HAS_ACCL_REGS))
+		/*
+		 * itemized copy not needed like above as layout of regs (r30,r58,r59)
+		 * is exactly same in kernel (pt_regs) and userspace (user_regs_arcv2)
+		 */
+		return membuf_write(&to, &regs->r30, sizeof(struct user_regs_arcv2));
+
+
+	membuf_write(&to, &regs->r30, 4); /* r30 only */
+	return membuf_zero(&to, sizeof(struct user_regs_arcv2) - 4);
+}
+
+static int arcv2regs_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 *regs = task_pt_regs(target);
+	int ret, copy_sz;
+
+	if (IS_ENABLED(CONFIG_ARC_HAS_ACCL_REGS))
+		copy_sz = sizeof(struct user_regs_arcv2);
+	else
+		copy_sz = 4;	/* r30 only */
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, (void *)&regs->r30,
+				  0, copy_sz);
+
+	return ret;
+}
+
+#endif
+
+enum arc_getset {
+	REGSET_CMN,
+	REGSET_ARCV2,
+};
+
+static const struct user_regset arc_regsets[] = {
+	[REGSET_CMN] = {
+	       USER_REGSET_NOTE_TYPE(PRSTATUS),
+	       .n = ELF_NGREG,
+	       .size = sizeof(unsigned long),
+	       .align = sizeof(unsigned long),
+	       .regset_get = genregs_get,
+	       .set = genregs_set,
+	},
+#ifdef CONFIG_ISA_ARCV2
+	[REGSET_ARCV2] = {
+	       USER_REGSET_NOTE_TYPE(ARC_V2),
+	       .n = ELF_ARCV2REG,
+	       .size = sizeof(unsigned long),
+	       .align = sizeof(unsigned long),
+	       .regset_get = arcv2regs_get,
+	       .set = arcv2regs_set,
+	},
+#endif
+};
+
+static const struct user_regset_view user_arc_view = {
+	.name		= "arc",
+	.e_machine	= EM_ARC_INUSE,
+	.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) {
+	case PTRACE_GET_THREAD_AREA:
+		ret = put_user(task_thread_info(child)->thr_ptr,
+			       (unsigned long __user *)data);
+		break;
+	default:
+		ret = ptrace_request(child, request, addr, data);
+		break;
+	}
+
+	return ret;
+}
+
+asmlinkage int syscall_trace_enter(struct pt_regs *regs)
+{
+	if (test_thread_flag(TIF_SYSCALL_TRACE))
+		if (!ptrace_report_syscall_permit_entry(regs))
+			return ULONG_MAX;
+
+#ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS
+	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
+		trace_sys_enter(regs, syscall_get_nr(current, regs));
+#endif
+
+	return regs->r8;
+}
+
+asmlinkage void syscall_trace_exit(struct pt_regs *regs)
+{
+	if (test_thread_flag(TIF_SYSCALL_TRACE))
+		ptrace_report_syscall_exit(regs, 0);
+
+#ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS
+	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
+		trace_sys_exit(regs, regs_return_value(regs));
+#endif
+}
+
+int regs_query_register_offset(const char *name)
+{
+	const struct pt_regs_offset *roff;
+
+	for (roff = regoffset_table; roff->name != NULL; roff++)
+		if (!strcmp(roff->name, name))
+			return roff->offset;
+	return -EINVAL;
+}
+
+const char *regs_query_register_name(unsigned int offset)
+{
+	const struct pt_regs_offset *roff;
+	for (roff = regoffset_table; roff->name != NULL; roff++)
+		if (roff->offset == offset)
+			return roff->name;
+	return NULL;
+}
+
+bool regs_within_kernel_stack(struct pt_regs *regs, unsigned long addr)
+{
+	return (addr & ~(THREAD_SIZE - 1))  ==
+		(kernel_stack_pointer(regs) & ~(THREAD_SIZE - 1));
+}
+
+unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n)
+{
+	unsigned long *addr = (unsigned long *)kernel_stack_pointer(regs);
+
+	addr += n;
+	if (regs_within_kernel_stack(regs, (unsigned long)addr))
+		return *addr;
+	else
+		return 0;
+}
diff --git a/arch/arc/kernel/reset.c b/arch/arc/kernel/reset.c
new file mode 100644
index 000000000..fd6c3eb93
--- /dev/null
+++ b/arch/arc/kernel/reset.c
@@ -0,0 +1,31 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#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;
+EXPORT_SYMBOL(pm_power_off);
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
new file mode 100644
index 000000000..7b6a9beba
--- /dev/null
+++ b/arch/arc/kernel/setup.c
@@ -0,0 +1,654 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#include <linux/seq_file.h>
+#include <linux/fs.h>
+#include <linux/delay.h>
+#include <linux/root_dev.h>
+#include <linux/clk.h>
+#include <linux/clocksource.h>
+#include <linux/console.h>
+#include <linux/module.h>
+#include <linux/sizes.h>
+#include <linux/cpu.h>
+#include <linux/of_clk.h>
+#include <linux/of_fdt.h>
+#include <linux/of.h>
+#include <linux/cache.h>
+#include <uapi/linux/mount.h>
+#include <asm/sections.h>
+#include <asm/arcregs.h>
+#include <asm/asserts.h>
+#include <asm/tlb.h>
+#include <asm/setup.h>
+#include <asm/page.h>
+#include <asm/irq.h>
+#include <asm/unwind.h>
+#include <asm/mach_desc.h>
+#include <asm/smp.h>
+#include <asm/dsp-impl.h>
+#include <soc/arc/mcip.h>
+
+#define FIX_PTR(x)  __asm__ __volatile__(";" : "+r"(x))
+
+unsigned int intr_to_DE_cnt;
+
+/* Part of U-boot ABI: see head.S */
+int __initdata uboot_tag;
+int __initdata uboot_magic;
+char __initdata *uboot_arg;
+
+const struct machine_desc *machine_desc;
+
+struct task_struct *_current_task[NR_CPUS];	/* For stack switching */
+
+struct cpuinfo_arc {
+	int arcver;
+	unsigned int t0:1, t1:1;
+	struct {
+		unsigned long base;
+		unsigned int sz;
+	} iccm, dccm;
+};
+
+#ifdef CONFIG_ISA_ARCV2
+
+static const struct id_to_str arc_hs_rel[] = {
+	/* ID.ARCVER,	Release */
+	{ 0x51, 	"R2.0" },
+	{ 0x52, 	"R2.1" },
+	{ 0x53,		"R3.0" },
+};
+
+static const struct id_to_str arc_hs_ver54_rel[] = {
+	/* UARCH.MAJOR,	Release */
+	{  0,		"R3.10a"},
+	{  1,		"R3.50a"},
+	{  2,		"R3.60a"},
+	{  3,		"R4.00a"},
+	{  0xFF,	NULL   }
+};
+#endif
+
+static int
+arcompact_mumbojumbo(int c, struct cpuinfo_arc *info, char *buf, int len)
+{
+	int n = 0;
+#ifdef CONFIG_ISA_ARCOMPACT
+	char *cpu_nm, *isa_nm = "ARCompact";
+	struct bcr_fp_arcompact fpu_sp, fpu_dp;
+	int atomic = 0, be, present;
+	int bpu_full, bpu_cache, bpu_pred;
+	struct bcr_bpu_arcompact bpu;
+	struct bcr_iccm_arcompact iccm;
+	struct bcr_dccm_arcompact dccm;
+	struct bcr_generic isa;
+
+	READ_BCR(ARC_REG_ISA_CFG_BCR, isa);
+
+	if (!isa.ver)	/* ISA BCR absent, use Kconfig info */
+		atomic = IS_ENABLED(CONFIG_ARC_HAS_LLSC);
+	else {
+		/* ARC700_BUILD only has 2 bits of isa info */
+		atomic = isa.info & 1;
+	}
+
+	be = IS_ENABLED(CONFIG_CPU_BIG_ENDIAN);
+
+	if (info->arcver < 0x34)
+		cpu_nm = "ARC750";
+	else
+		cpu_nm = "ARC770";
+
+	n += scnprintf(buf + n, len - n, "processor [%d]\t: %s (%s ISA) %s%s%s\n",
+		       c, cpu_nm, isa_nm,
+		       IS_AVAIL2(atomic, "atomic ", CONFIG_ARC_HAS_LLSC),
+		       IS_AVAIL1(be, "[Big-Endian]"));
+
+	READ_BCR(ARC_REG_FP_BCR, fpu_sp);
+	READ_BCR(ARC_REG_DPFP_BCR, fpu_dp);
+
+	if (fpu_sp.ver | fpu_dp.ver)
+		n += scnprintf(buf + n, len - n, "FPU\t\t: %s%s\n",
+			       IS_AVAIL1(fpu_sp.ver, "SP "),
+			       IS_AVAIL1(fpu_dp.ver, "DP "));
+
+	READ_BCR(ARC_REG_BPU_BCR, bpu);
+	bpu_full = bpu.fam ? 1 : 0;
+	bpu_cache = 256 << (bpu.ent - 1);
+	bpu_pred = 256 << (bpu.ent - 1);
+
+	n += scnprintf(buf + n, len - n,
+			"BPU\t\t: %s%s match, cache:%d, Predict Table:%d\n",
+			IS_AVAIL1(bpu_full, "full"),
+			IS_AVAIL1(!bpu_full, "partial"),
+			bpu_cache, bpu_pred);
+
+	READ_BCR(ARC_REG_ICCM_BUILD, iccm);
+	if (iccm.ver) {
+		info->iccm.sz = 4096 << iccm.sz;	/* 8K to 512K */
+		info->iccm.base = iccm.base << 16;
+	}
+
+	READ_BCR(ARC_REG_DCCM_BUILD, dccm);
+	if (dccm.ver) {
+		unsigned long base;
+		info->dccm.sz = 2048 << dccm.sz;	/* 2K to 256K */
+
+		base = read_aux_reg(ARC_REG_DCCM_BASE_BUILD);
+		info->dccm.base = base & ~0xF;
+	}
+
+	/* ARCompact ISA specific sanity checks */
+	present = fpu_dp.ver;	/* SP has no arch visible regs */
+	CHK_OPT_STRICT(CONFIG_ARC_FPU_SAVE_RESTORE, present);
+#endif
+	return n;
+
+}
+
+static int arcv2_mumbojumbo(int c, struct cpuinfo_arc *info, char *buf, int len)
+{
+	int n = 0;
+#ifdef CONFIG_ISA_ARCV2
+	const char *release = "", *cpu_nm = "HS38", *isa_nm = "ARCv2";
+	int dual_issue = 0, dual_enb = 0, mpy_opt, present;
+	int bpu_full, bpu_cache, bpu_pred, bpu_ret_stk;
+	char mpy_nm[16], lpb_nm[32];
+	struct bcr_isa_arcv2 isa;
+	struct bcr_mpy mpy;
+	struct bcr_fp_arcv2 fpu;
+	struct bcr_bpu_arcv2 bpu;
+	struct bcr_lpb lpb;
+	struct bcr_iccm_arcv2 iccm;
+	struct bcr_dccm_arcv2 dccm;
+	struct bcr_erp erp;
+
+	/*
+	 * Initial HS cores bumped AUX IDENTITY.ARCVER for each release until
+	 * ARCVER 0x54 which introduced AUX MICRO_ARCH_BUILD and subsequent
+	 * releases only update it.
+	 */
+
+	if (info->arcver > 0x50 && info->arcver <= 0x53) {
+		release = arc_hs_rel[info->arcver - 0x51].str;
+	} else {
+		const struct id_to_str *tbl;
+		struct bcr_uarch_build uarch;
+
+		READ_BCR(ARC_REG_MICRO_ARCH_BCR, uarch);
+
+		for (tbl = &arc_hs_ver54_rel[0]; tbl->id != 0xFF; tbl++) {
+			if (uarch.maj == tbl->id) {
+				release = tbl->str;
+				break;
+			}
+		}
+		if (uarch.prod == 4) {
+			unsigned int exec_ctrl;
+
+			cpu_nm = "HS48";
+			dual_issue = 1;
+			/* if dual issue hardware, is it enabled ? */
+			READ_BCR(AUX_EXEC_CTRL, exec_ctrl);
+			dual_enb = !(exec_ctrl & 1);
+		}
+	}
+
+	READ_BCR(ARC_REG_ISA_CFG_BCR, isa);
+
+	n += scnprintf(buf + n, len - n, "processor [%d]\t: %s %s (%s ISA) %s%s%s\n",
+		       c, cpu_nm, release, isa_nm,
+		       IS_AVAIL1(isa.be, "[Big-Endian]"),
+		       IS_AVAIL3(dual_issue, dual_enb, " Dual-Issue "));
+
+	READ_BCR(ARC_REG_MPY_BCR, mpy);
+	mpy_opt = 2;	/* stock MPY/MPYH */
+	if (mpy.dsp)	/* OPT 7-9 */
+		mpy_opt = mpy.dsp + 6;
+
+	scnprintf(mpy_nm, 16, "mpy[opt %d] ", mpy_opt);
+
+	READ_BCR(ARC_REG_FP_V2_BCR, fpu);
+
+	n += scnprintf(buf + n, len - n, "ISA Extn\t: %s%s%s%s%s%s%s%s%s%s%s\n",
+		       IS_AVAIL2(isa.atomic, "atomic ", CONFIG_ARC_HAS_LLSC),
+		       IS_AVAIL2(isa.ldd, "ll64 ", CONFIG_ARC_HAS_LL64),
+		       IS_AVAIL2(isa.unalign, "unalign ", CONFIG_ARC_USE_UNALIGNED_MEM_ACCESS),
+		       IS_AVAIL1(mpy.ver, mpy_nm),
+		       IS_AVAIL1(isa.div_rem, "div_rem "),
+		       IS_AVAIL1((fpu.sp | fpu.dp), "  FPU:"),
+		       IS_AVAIL1(fpu.sp, " sp"),
+		       IS_AVAIL1(fpu.dp, " dp"));
+
+	READ_BCR(ARC_REG_BPU_BCR, bpu);
+	bpu_full = bpu.ft;
+	bpu_cache = 256 << bpu.bce;
+	bpu_pred = 2048 << bpu.pte;
+	bpu_ret_stk = 4 << bpu.rse;
+
+	READ_BCR(ARC_REG_LPB_BUILD, lpb);
+	if (lpb.ver) {
+		unsigned int ctl;
+		ctl = read_aux_reg(ARC_REG_LPB_CTRL);
+
+		scnprintf(lpb_nm, sizeof(lpb_nm), " Loop Buffer:%d %s",
+			  lpb.entries, IS_DISABLED_RUN(!ctl));
+	}
+
+	n += scnprintf(buf + n, len - n,
+			"BPU\t\t: %s%s match, cache:%d, Predict Table:%d Return stk: %d%s\n",
+			IS_AVAIL1(bpu_full, "full"),
+			IS_AVAIL1(!bpu_full, "partial"),
+			bpu_cache, bpu_pred, bpu_ret_stk,
+			lpb_nm);
+
+	READ_BCR(ARC_REG_ICCM_BUILD, iccm);
+	if (iccm.ver) {
+		unsigned long base;
+		info->iccm.sz = 256 << iccm.sz00;	/* 512B to 16M */
+		if (iccm.sz00 == 0xF && iccm.sz01 > 0)
+			info->iccm.sz <<= iccm.sz01;
+		base = read_aux_reg(ARC_REG_AUX_ICCM);
+		info->iccm.base = base & 0xF0000000;
+	}
+
+	READ_BCR(ARC_REG_DCCM_BUILD, dccm);
+	if (dccm.ver) {
+		unsigned long base;
+		info->dccm.sz = 256 << dccm.sz0;
+		if (dccm.sz0 == 0xF && dccm.sz1 > 0)
+			info->dccm.sz <<= dccm.sz1;
+		base = read_aux_reg(ARC_REG_AUX_DCCM);
+		info->dccm.base = base & 0xF0000000;
+	}
+
+	/* Error Protection: ECC/Parity */
+	READ_BCR(ARC_REG_ERP_BUILD, erp);
+	if (erp.ver) {
+		struct ctl_erp ctl;
+		READ_BCR(ARC_REG_ERP_CTRL, ctl);
+		/* inverted bits: 0 means enabled */
+		n += scnprintf(buf + n, len - n, "Extn [ECC]\t: %s%s%s%s%s%s\n",
+				IS_AVAIL3(erp.ic,  !ctl.dpi, "IC "),
+				IS_AVAIL3(erp.dc,  !ctl.dpd, "DC "),
+				IS_AVAIL3(erp.mmu, !ctl.mpd, "MMU "));
+	}
+
+	/* ARCv2 ISA specific sanity checks */
+	present = fpu.sp | fpu.dp | mpy.dsp;	/* DSP and/or FPU */
+	CHK_OPT_STRICT(CONFIG_ARC_HAS_ACCL_REGS, present);
+
+	dsp_config_check();
+#endif
+	return n;
+}
+
+static char *arc_cpu_mumbojumbo(int c, struct cpuinfo_arc *info, char *buf, int len)
+{
+	struct bcr_identity ident;
+	struct bcr_timer timer;
+	struct bcr_generic bcr;
+	struct mcip_bcr mp;
+	struct bcr_actionpoint ap;
+	unsigned long vec_base;
+	int ap_num, ap_full, smart, rtt, n;
+
+	memset(info, 0, sizeof(struct cpuinfo_arc));
+
+	READ_BCR(AUX_IDENTITY, ident);
+	info->arcver = ident.family;
+
+	n = scnprintf(buf, len,
+		       "\nIDENTITY\t: ARCVER [%#02x] ARCNUM [%#02x] CHIPID [%#4x]\n",
+		       ident.family, ident.cpu_id, ident.chip_id);
+
+	if (is_isa_arcompact()) {
+		n += arcompact_mumbojumbo(c, info, buf + n, len - n);
+	} else if (is_isa_arcv2()){
+		n += arcv2_mumbojumbo(c, info, buf + n, len - n);
+	}
+
+	n += arc_mmu_mumbojumbo(c, buf + n, len - n);
+	n += arc_cache_mumbojumbo(c, buf + n, len - n);
+
+	READ_BCR(ARC_REG_TIMERS_BCR, timer);
+	info->t0 = timer.t0;
+	info->t1 = timer.t1;
+
+	READ_BCR(ARC_REG_MCIP_BCR, mp);
+	vec_base = read_aux_reg(AUX_INTR_VEC_BASE);
+
+	n += scnprintf(buf + n, len - n,
+		       "Timers\t\t: %s%s%s%s%s%s\nVector Table\t: %#lx\n",
+		       IS_AVAIL1(timer.t0, "Timer0 "),
+		       IS_AVAIL1(timer.t1, "Timer1 "),
+		       IS_AVAIL2(timer.rtc, "RTC [UP 64-bit] ", CONFIG_ARC_TIMERS_64BIT),
+		       IS_AVAIL2(mp.gfrc, "GFRC [SMP 64-bit] ", CONFIG_ARC_TIMERS_64BIT),
+		       vec_base);
+
+	READ_BCR(ARC_REG_AP_BCR, ap);
+	if (ap.ver) {
+		ap_num = 2 << ap.num;
+		ap_full = !ap.min;
+	}
+
+	READ_BCR(ARC_REG_SMART_BCR, bcr);
+	smart = bcr.ver ? 1 : 0;
+
+	READ_BCR(ARC_REG_RTT_BCR, bcr);
+	rtt = bcr.ver ? 1 : 0;
+
+	if (ap.ver | smart | rtt) {
+		n += scnprintf(buf + n, len - n, "DEBUG\t\t: %s%s",
+			       IS_AVAIL1(smart, "smaRT "),
+			       IS_AVAIL1(rtt, "RTT "));
+		if (ap.ver) {
+			n += scnprintf(buf + n, len - n, "ActionPoint %d/%s",
+				       ap_num,
+				       ap_full ? "full":"min");
+		}
+		n += scnprintf(buf + n, len - n, "\n");
+	}
+
+	if (info->dccm.sz || info->iccm.sz)
+		n += scnprintf(buf + n, len - n,
+			       "Extn [CCM]\t: DCCM @ %lx, %d KB / ICCM: @ %lx, %d KB\n",
+			       info->dccm.base, TO_KB(info->dccm.sz),
+			       info->iccm.base, TO_KB(info->iccm.sz));
+
+	return buf;
+}
+
+void chk_opt_strict(char *opt_name, bool hw_exists, bool opt_ena)
+{
+	if (hw_exists && !opt_ena)
+		pr_warn(" ! Enable %s for working apps\n", opt_name);
+	else if (!hw_exists && opt_ena)
+		panic("Disable %s, hardware NOT present\n", opt_name);
+}
+
+void chk_opt_weak(char *opt_name, bool hw_exists, bool opt_ena)
+{
+	if (!hw_exists && opt_ena)
+		panic("Disable %s, hardware NOT present\n", opt_name);
+}
+
+/*
+ * ISA agnostic sanity checks
+ */
+static void arc_chk_core_config(struct cpuinfo_arc *info)
+{
+	if (!info->t0)
+		panic("Timer0 is not present!\n");
+
+	if (!info->t1)
+		panic("Timer1 is not present!\n");
+
+#ifdef CONFIG_ARC_HAS_DCCM
+	/*
+	 * DCCM can be arbit placed in hardware.
+	 * Make sure its placement/sz matches what Linux is built with
+	 */
+	if ((unsigned int)__arc_dccm_base != info->dccm.base)
+		panic("Linux built with incorrect DCCM Base address\n");
+
+	if (CONFIG_ARC_DCCM_SZ * SZ_1K != info->dccm.sz)
+		panic("Linux built with incorrect DCCM Size\n");
+#endif
+
+#ifdef CONFIG_ARC_HAS_ICCM
+	if (CONFIG_ARC_ICCM_SZ * SZ_1K != info->iccm.sz)
+		panic("Linux built with incorrect ICCM Size\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 setup_processor(void)
+{
+	struct cpuinfo_arc info;
+	int c = smp_processor_id();
+	char str[512];
+
+	pr_info("%s", arc_cpu_mumbojumbo(c, &info, str, sizeof(str)));
+	pr_info("%s", arc_platform_smp_cpuinfo());
+
+	arc_chk_core_config(&info);
+
+	arc_init_IRQ();
+	arc_mmu_init();
+	arc_cache_init();
+
+}
+
+static inline bool uboot_arg_invalid(unsigned long addr)
+{
+	/*
+	 * Check that it is a untranslated address (although MMU is not enabled
+	 * yet, it being a high address ensures this is not by fluke)
+	 */
+	if (addr < PAGE_OFFSET)
+		return true;
+
+	/* Check that address doesn't clobber resident kernel image */
+	return addr >= (unsigned long)_stext && addr <= (unsigned long)_end;
+}
+
+#define IGNORE_ARGS		"Ignore U-boot args: "
+
+/* uboot_tag values for U-boot - kernel ABI revision 0; see head.S */
+#define UBOOT_TAG_NONE		0
+#define UBOOT_TAG_CMDLINE	1
+#define UBOOT_TAG_DTB		2
+/* We always pass 0 as magic from U-boot */
+#define UBOOT_MAGIC_VALUE	0
+
+void __init handle_uboot_args(void)
+{
+	bool use_embedded_dtb = true;
+	bool append_cmdline = false;
+
+	/* check that we know this tag */
+	if (uboot_tag != UBOOT_TAG_NONE &&
+	    uboot_tag != UBOOT_TAG_CMDLINE &&
+	    uboot_tag != UBOOT_TAG_DTB) {
+		pr_warn(IGNORE_ARGS "invalid uboot tag: '%08x'\n", uboot_tag);
+		goto ignore_uboot_args;
+	}
+
+	if (uboot_magic != UBOOT_MAGIC_VALUE) {
+		pr_warn(IGNORE_ARGS "non zero uboot magic\n");
+		goto ignore_uboot_args;
+	}
+
+	if (uboot_tag != UBOOT_TAG_NONE &&
+            uboot_arg_invalid((unsigned long)uboot_arg)) {
+		pr_warn(IGNORE_ARGS "invalid uboot arg: '%px'\n", uboot_arg);
+		goto ignore_uboot_args;
+	}
+
+	/* see if U-boot passed an external Device Tree blob */
+	if (uboot_tag == UBOOT_TAG_DTB) {
+		machine_desc = setup_machine_fdt((void *)uboot_arg);
+
+		/* external Device Tree blob is invalid - use embedded one */
+		use_embedded_dtb = !machine_desc;
+	}
+
+	if (uboot_tag == UBOOT_TAG_CMDLINE)
+		append_cmdline = true;
+
+ignore_uboot_args:
+
+	if (use_embedded_dtb) {
+		machine_desc = setup_machine_fdt(__dtb_start);
+		if (!machine_desc)
+			panic("Embedded DT invalid\n");
+	}
+
+	/*
+	 * NOTE: @boot_command_line is populated by setup_machine_fdt() so this
+	 * append processing can only happen after.
+	 */
+	if (append_cmdline) {
+		/* Ensure a whitespace between the 2 cmdlines */
+		strlcat(boot_command_line, " ", COMMAND_LINE_SIZE);
+		strlcat(boot_command_line, uboot_arg, COMMAND_LINE_SIZE);
+	}
+}
+
+void __init setup_arch(char **cmdline_p)
+{
+	handle_uboot_args();
+
+	/* Save unparsed command line copy for /proc/cmdline */
+	*cmdline_p = boot_command_line;
+
+	/* 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();
+
+	smp_init_cpus();
+
+	setup_processor();
+	setup_arch_memory();
+
+	/* copy flat DT out of .init and then unflatten it */
+	unflatten_and_copy_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;
+
+	arc_unwind_init();
+}
+
+/*
+ * Called from start_kernel() - boot CPU only
+ */
+void __init time_init(void)
+{
+	of_clk_init(NULL);
+	timer_probe();
+}
+
+static int __init customize_machine(void)
+{
+	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);
+	struct device *cpu_dev = get_cpu_device(cpu_id);
+	struct cpuinfo_arc info;
+	struct clk *cpu_clk;
+	unsigned long freq = 0;
+
+	if (!cpu_online(cpu_id)) {
+		seq_printf(m, "processor [%d]\t: Offline\n", cpu_id);
+		goto done;
+	}
+
+	str = (char *)__get_free_page(GFP_KERNEL);
+	if (!str)
+		goto done;
+
+	seq_printf(m, arc_cpu_mumbojumbo(cpu_id, &info, str, PAGE_SIZE));
+
+	cpu_clk = clk_get(cpu_dev, NULL);
+	if (IS_ERR(cpu_clk)) {
+		seq_printf(m, "CPU speed \t: Cannot get clock for processor [%d]\n",
+			   cpu_id);
+	} else {
+		freq = clk_get_rate(cpu_clk);
+	}
+	if (freq)
+		seq_printf(m, "CPU speed\t: %lu.%02lu Mhz\n",
+			   freq / 1000000, (freq / 10000) % 100);
+
+	seq_printf(m, "Bogo MIPS\t: %lu.%02lu\n",
+		   loops_per_jiffy / (500000 / HZ),
+		   (loops_per_jiffy / (5000 / HZ)) % 100);
+
+	seq_printf(m, arc_platform_smp_cpuinfo());
+
+	free_page((unsigned long)str);
+done:
+	seq_printf(m, "\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 < nr_cpu_ids ? 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 000000000..fefa705a8
--- /dev/null
+++ b/arch/arc/kernel/signal.c
@@ -0,0 +1,444 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Signal Handling for ARC
+ *
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * 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 longer needs oldset, required by OLD sys_sigsuspend
+ *  -sys_rt_sigsuspend() now comes from generic code, so discard arch
+ *   implementation
+ *  -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 synthesizing 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 causing 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/resume_user_mode.h>
+#include <linux/sched/task_stack.h>
+
+#include <asm/ucontext.h>
+#include <asm/entry.h>
+
+struct rt_sigframe {
+	struct siginfo info;
+	struct ucontext uc;
+#define MAGIC_SIGALTSTK		0x07302004
+	unsigned int sigret_magic;
+};
+
+static int save_arcv2_regs(struct sigcontext __user *mctx, struct pt_regs *regs)
+{
+	int err = 0;
+#ifndef CONFIG_ISA_ARCOMPACT
+	struct user_regs_arcv2 v2abi;
+
+	v2abi.r30 = regs->r30;
+#ifdef CONFIG_ARC_HAS_ACCL_REGS
+	v2abi.r58 = regs->r58;
+	v2abi.r59 = regs->r59;
+#else
+	v2abi.r58 = v2abi.r59 = 0;
+#endif
+	err = __copy_to_user(&mctx->v2abi, (void const *)&v2abi, sizeof(v2abi));
+#endif
+	return err;
+}
+
+static int restore_arcv2_regs(struct sigcontext __user *mctx, struct pt_regs *regs)
+{
+	int err = 0;
+#ifndef CONFIG_ISA_ARCOMPACT
+	struct user_regs_arcv2 v2abi;
+
+	err = __copy_from_user(&v2abi, &mctx->v2abi, sizeof(v2abi));
+
+	regs->r30 = v2abi.r30;
+#ifdef CONFIG_ARC_HAS_ACCL_REGS
+	regs->r58 = v2abi.r58;
+	regs->r59 = v2abi.r59;
+#endif
+#endif
+	return err;
+}
+
+static int
+stash_usr_regs(struct rt_sigframe __user *sf, struct pt_regs *regs,
+	       sigset_t *set)
+{
+	int err;
+	struct user_regs_struct uregs;
+
+	uregs.scratch.bta	= regs->bta;
+	uregs.scratch.lp_start	= regs->lp_start;
+	uregs.scratch.lp_end	= regs->lp_end;
+	uregs.scratch.lp_count	= regs->lp_count;
+	uregs.scratch.status32	= regs->status32;
+	uregs.scratch.ret	= regs->ret;
+	uregs.scratch.blink	= regs->blink;
+	uregs.scratch.fp	= regs->fp;
+	uregs.scratch.gp	= regs->r26;
+	uregs.scratch.r12	= regs->r12;
+	uregs.scratch.r11	= regs->r11;
+	uregs.scratch.r10	= regs->r10;
+	uregs.scratch.r9	= regs->r9;
+	uregs.scratch.r8	= regs->r8;
+	uregs.scratch.r7	= regs->r7;
+	uregs.scratch.r6	= regs->r6;
+	uregs.scratch.r5	= regs->r5;
+	uregs.scratch.r4	= regs->r4;
+	uregs.scratch.r3	= regs->r3;
+	uregs.scratch.r2	= regs->r2;
+	uregs.scratch.r1	= regs->r1;
+	uregs.scratch.r0	= regs->r0;
+	uregs.scratch.sp	= regs->sp;
+
+	err = __copy_to_user(&(sf->uc.uc_mcontext.regs.scratch), &uregs.scratch,
+			     sizeof(sf->uc.uc_mcontext.regs.scratch));
+
+	if (is_isa_arcv2())
+		err |= save_arcv2_regs(&(sf->uc.uc_mcontext), regs);
+
+	err |= __copy_to_user(&sf->uc.uc_sigmask, set, sizeof(sigset_t));
+
+	return err ? -EFAULT : 0;
+}
+
+static int restore_usr_regs(struct pt_regs *regs, struct rt_sigframe __user *sf)
+{
+	sigset_t set;
+	int err;
+	struct user_regs_struct uregs;
+
+	err = __copy_from_user(&set, &sf->uc.uc_sigmask, sizeof(set));
+	err |= __copy_from_user(&uregs.scratch,
+				&(sf->uc.uc_mcontext.regs.scratch),
+				sizeof(sf->uc.uc_mcontext.regs.scratch));
+
+	if (is_isa_arcv2())
+		err |= restore_arcv2_regs(&(sf->uc.uc_mcontext), regs);
+
+	if (err)
+		return -EFAULT;
+
+	set_current_blocked(&set);
+	regs->bta	= uregs.scratch.bta;
+	regs->lp_start	= uregs.scratch.lp_start;
+	regs->lp_end	= uregs.scratch.lp_end;
+	regs->lp_count	= uregs.scratch.lp_count;
+	regs->status32	= uregs.scratch.status32;
+	regs->ret	= uregs.scratch.ret;
+	regs->blink	= uregs.scratch.blink;
+	regs->fp	= uregs.scratch.fp;
+	regs->r26	= uregs.scratch.gp;
+	regs->r12	= uregs.scratch.r12;
+	regs->r11	= uregs.scratch.r11;
+	regs->r10	= uregs.scratch.r10;
+	regs->r9	= uregs.scratch.r9;
+	regs->r8	= uregs.scratch.r8;
+	regs->r7	= uregs.scratch.r7;
+	regs->r6	= uregs.scratch.r6;
+	regs->r5	= uregs.scratch.r5;
+	regs->r4	= uregs.scratch.r4;
+	regs->r3	= uregs.scratch.r3;
+	regs->r2	= uregs.scratch.r2;
+	regs->r1	= uregs.scratch.r1;
+	regs->r0	= uregs.scratch.r0;
+	regs->sp	= uregs.scratch.sp;
+
+	return 0;
+}
+
+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;
+	struct pt_regs *regs = current_pt_regs();
+
+	/* Always make any pending restarted system calls return -EINTR */
+	current->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(sf, sizeof(*sf)))
+		goto badframe;
+
+	if (__get_user(magic, &sf->sigret_magic))
+		goto badframe;
+
+	if (unlikely(is_do_ss_needed(magic)))
+		if (restore_altstack(&sf->uc.uc_stack))
+			goto badframe;
+
+	if (restore_usr_regs(regs, sf))
+		goto badframe;
+
+	/* Don't restart from sigreturn */
+	syscall_wont_restart(regs);
+
+	/*
+	 * Ensure that sigreturn always returns to user mode (in case the
+	 * regs saved on user stack got fudged between save and sigreturn)
+	 * Otherwise it is easy to panic the kernel with a custom
+	 * signal handler and/or restorer which clobberes the status32/ret
+	 * to return to a bogus location in kernel mode.
+	 */
+	regs->status32 |= STATUS_U_MASK;
+
+	return regs->r0;
+
+badframe:
+	force_sig(SIGSEGV);
+	return 0;
+}
+
+/*
+ * Determine which stack to use..
+ */
+static inline void __user *get_sigframe(struct ksignal *ksig,
+					struct pt_regs *regs,
+					unsigned long framesize)
+{
+	unsigned long sp = sigsp(regs->sp, ksig);
+	void __user *frame;
+
+	/* 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(frame, framesize))
+		frame = NULL;
+
+	return frame;
+}
+
+static int
+setup_rt_frame(struct ksignal *ksig, sigset_t *set, struct pt_regs *regs)
+{
+	struct rt_sigframe __user *sf;
+	unsigned int magic = 0;
+	int err = 0;
+
+	sf = get_sigframe(ksig, regs, sizeof(struct rt_sigframe));
+	if (!sf)
+		return 1;
+
+	/*
+	 * 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);
+
+	/*
+	 * 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(ksig->ka.sa.sa_flags & SA_SIGINFO)) {
+		err |= copy_siginfo_to_user(&sf->info, &ksig->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 unconditionally calling do_sigaltstack
+		 * in sigreturn path, now that we only have rt_sigreturn
+		 */
+		magic = MAGIC_SIGALTSTK;
+	}
+
+	err |= __put_user(magic, &sf->sigret_magic);
+	if (err)
+		return err;
+
+	/* #1 arg to the user Signal handler */
+	regs->r0 = ksig->sig;
+
+	/* setup PC of user space signal handler */
+	regs->ret = (unsigned long)ksig->ka.sa.sa_handler;
+
+	/*
+	 * handler returns using sigreturn stub provided already by userspace
+	 * If not, nuke the process right away
+	 */
+	if(!(ksig->ka.sa.sa_flags & SA_RESTORER))
+		return 1;
+
+	regs->blink = (unsigned long)ksig->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 -= is_isa_arcv2() ? 2 : 4;
+		break;
+	}
+}
+
+/*
+ * OK, we're invoking a handler
+ */
+static void
+handle_signal(struct ksignal *ksig, struct pt_regs *regs)
+{
+	sigset_t *oldset = sigmask_to_save();
+	int failed;
+
+	/* Set up the stack frame */
+	failed = setup_rt_frame(ksig, oldset, regs);
+
+	signal_setup_done(failed, ksig, 0);
+}
+
+void do_signal(struct pt_regs *regs)
+{
+	struct ksignal ksig;
+	int restart_scall;
+
+	restart_scall = in_syscall(regs) && syscall_restartable(regs);
+
+	if (test_thread_flag(TIF_SIGPENDING) && get_signal(&ksig)) {
+		if (restart_scall) {
+			arc_restart_syscall(&ksig.ka, regs);
+			syscall_wont_restart(regs);	/* No more restarts */
+		}
+		handle_signal(&ksig, 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 -= is_isa_arcv2() ? 2 : 4;
+		} else if (regs->r0 == -ERESTART_RESTARTBLOCK) {
+			regs->r8 = __NR_restart_syscall;
+			regs->ret -= is_isa_arcv2() ? 2 : 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 guarantees that this is only called when returning to
+	 * user mode
+	 */
+	if (test_thread_flag(TIF_NOTIFY_RESUME))
+		resume_user_mode_work(regs);
+}
diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c
new file mode 100644
index 000000000..2d99dffed
--- /dev/null
+++ b/arch/arc/kernel/smp.c
@@ -0,0 +1,411 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * RajeshwarR: Dec 11, 2007
+ *   -- Added support for Inter Processor Interrupts
+ *
+ * Vineetg: Nov 1st, 2007
+ *    -- Initial Write (Borrowed heavily from ARM)
+ */
+
+#include <linux/spinlock.h>
+#include <linux/sched/mm.h>
+#include <linux/interrupt.h>
+#include <linux/profile.h>
+#include <linux/mm.h>
+#include <linux/cpu.h>
+#include <linux/irq.h>
+#include <linux/atomic.h>
+#include <linux/cpumask.h>
+#include <linux/reboot.h>
+#include <linux/irqdomain.h>
+#include <linux/export.h>
+#include <linux/of_fdt.h>
+#include <linux/string.h>
+
+#include <asm/mach_desc.h>
+#include <asm/setup.h>
+#include <asm/smp.h>
+#include <asm/processor.h>
+
+#ifndef CONFIG_ARC_HAS_LLSC
+arch_spinlock_t smp_atomic_ops_lock = __ARCH_SPIN_LOCK_UNLOCKED;
+
+EXPORT_SYMBOL_GPL(smp_atomic_ops_lock);
+#endif
+
+struct plat_smp_ops  __weak plat_smp_ops;
+
+/* XXX: per cpu ? Only needed once in early secondary boot */
+struct task_struct *secondary_idle_tsk;
+
+static int __init arc_get_cpu_map(const char *name, struct cpumask *cpumask)
+{
+	unsigned long dt_root = of_get_flat_dt_root();
+	const char *buf;
+	int len;
+
+	buf = of_get_flat_dt_prop(dt_root, name, &len);
+	if (!buf || !memchr(buf, '\0', len))
+		return -EINVAL;
+
+	if (cpulist_parse(buf, cpumask))
+		return -EINVAL;
+
+	return 0;
+}
+
+/*
+ * Read from DeviceTree and setup cpu possible mask. If there is no
+ * "possible-cpus" property in DeviceTree pretend all [0..NR_CPUS-1] exist.
+ */
+static void __init arc_init_cpu_possible(void)
+{
+	struct cpumask cpumask;
+
+	if (arc_get_cpu_map("possible-cpus", &cpumask)) {
+		pr_warn("Failed to get possible-cpus from dtb, pretending all %u cpus exist\n",
+			NR_CPUS);
+
+		cpumask_setall(&cpumask);
+	}
+
+	if (!cpumask_test_cpu(0, &cpumask))
+		panic("Master cpu (cpu[0]) is missed in cpu possible mask!");
+
+	init_cpu_possible(&cpumask);
+}
+
+/*
+ * Called from setup_arch() before calling setup_processor()
+ *
+ * - Initialise the CPU possible map early - this describes the CPUs
+ *   which may be present or become present in the system.
+ * - Call early smp init hook. This can initialize a specific multi-core
+ *   IP which is say common to several platforms (hence not part of
+ *   platform specific int_early() hook)
+ */
+void __init smp_init_cpus(void)
+{
+	arc_init_cpu_possible();
+
+	if (plat_smp_ops.init_early_smp)
+		plat_smp_ops.init_early_smp();
+}
+
+/* called from init ( ) =>  process 1 */
+void __init smp_prepare_cpus(unsigned int max_cpus)
+{
+	/*
+	 * if platform didn't set the present map already, do it now
+	 * boot cpu is set to present already by init/main.c
+	 */
+	if (num_present_cpus() <= 1)
+		init_cpu_present(cpu_possible_mask);
+}
+
+void __init smp_cpus_done(unsigned int max_cpus)
+{
+
+}
+
+/*
+ * Default smp boot helper for Run-on-reset case where all cores start off
+ * together. Non-masters need to wait for Master to start running.
+ * This is implemented using a flag in memory, which Non-masters spin-wait on.
+ * Master sets it to cpu-id of core to "ungate" it.
+ */
+static volatile int wake_flag;
+
+#ifdef CONFIG_ISA_ARCOMPACT
+
+#define __boot_read(f)		f
+#define __boot_write(f, v)	f = v
+
+#else
+
+#define __boot_read(f)		arc_read_uncached_32(&f)
+#define __boot_write(f, v)	arc_write_uncached_32(&f, v)
+
+#endif
+
+static void arc_default_smp_cpu_kick(int cpu, unsigned long pc)
+{
+	BUG_ON(cpu == 0);
+
+	__boot_write(wake_flag, cpu);
+}
+
+void arc_platform_smp_wait_to_boot(int cpu)
+{
+	/* for halt-on-reset, we've waited already */
+	if (IS_ENABLED(CONFIG_ARC_SMP_HALT_ON_RESET))
+		return;
+
+	while (__boot_read(wake_flag) != cpu)
+		;
+
+	__boot_write(wake_flag, 0);
+}
+
+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 start_kernel_secondary(void)
+{
+	struct mm_struct *mm = &init_mm;
+	unsigned int cpu = smp_processor_id();
+
+	/* MMU, Caches, Vector Table, Interrupts etc */
+	setup_processor();
+
+	mmget(mm);
+	mmgrab(mm);
+	current->active_mm = mm;
+	cpumask_set_cpu(cpu, mm_cpumask(mm));
+
+	/* Some SMP H/w setup - for each cpu */
+	if (plat_smp_ops.init_per_cpu)
+		plat_smp_ops.init_per_cpu(cpu);
+
+	if (machine_desc->init_per_cpu)
+		machine_desc->init_per_cpu(cpu);
+
+	notify_cpu_starting(cpu);
+	set_cpu_online(cpu, true);
+
+	pr_info("## CPU%u LIVE ##: Executing Code...\n", cpu);
+
+	local_irq_enable();
+	cpu_startup_entry(CPUHP_AP_ONLINE_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 __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);
+	else
+		arc_default_smp_cpu_kick(cpu, (unsigned long)NULL);
+
+	/* 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 come up !!!\n", cpu);
+		return -1;
+	}
+
+	secondary_idle_tsk = NULL;
+
+	return 0;
+}
+
+/*****************************************************************************/
+/*              Inter Processor Interrupt Handling                           */
+/*****************************************************************************/
+
+enum ipi_msg_type {
+	IPI_EMPTY = 0,
+	IPI_RESCHEDULE = 1,
+	IPI_CALL_FUNC,
+	IPI_CPU_STOP,
+};
+
+/*
+ * In arches with IRQ for each msg type (above), receiver can use IRQ-id  to
+ * figure out what msg was sent. For those which don't (ARC has dedicated IPI
+ * IRQ), the msg-type needs to be conveyed via per-cpu data
+ */
+
+static DEFINE_PER_CPU(unsigned long, ipi_data);
+
+static void ipi_send_msg_one(int cpu, enum ipi_msg_type msg)
+{
+	unsigned long __percpu *ipi_data_ptr = per_cpu_ptr(&ipi_data, cpu);
+	unsigned long old, new;
+	unsigned long flags;
+
+	pr_debug("%d Sending msg [%d] to %d\n", smp_processor_id(), msg, cpu);
+
+	local_irq_save(flags);
+
+	/*
+	 * Atomically write new msg bit (in case others are writing too),
+	 * and read back old value
+	 */
+	do {
+		new = old = *ipi_data_ptr;
+		new |= 1U << msg;
+	} while (cmpxchg(ipi_data_ptr, old, new) != old);
+
+	/*
+	 * Call the platform specific IPI kick function, but avoid if possible:
+	 * Only do so if there's no pending msg from other concurrent sender(s).
+	 * Otherwise, receiver will see this msg as well when it takes the
+	 * IPI corresponding to that msg. This is true, even if it is already in
+	 * IPI handler, because !@old means it has not yet dequeued the msg(s)
+	 * so @new msg can be a free-loader
+	 */
+	if (plat_smp_ops.ipi_send && !old)
+		plat_smp_ops.ipi_send(cpu);
+
+	local_irq_restore(flags);
+}
+
+static void ipi_send_msg(const struct cpumask *callmap, enum ipi_msg_type msg)
+{
+	unsigned int cpu;
+
+	for_each_cpu(cpu, callmap)
+		ipi_send_msg_one(cpu, msg);
+}
+
+void arch_smp_send_reschedule(int cpu)
+{
+	ipi_send_msg_one(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_one(cpu, IPI_CALL_FUNC);
+}
+
+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(void)
+{
+	machine_halt();
+}
+
+static inline int __do_IPI(unsigned long msg)
+{
+	int rc = 0;
+
+	switch (msg) {
+	case IPI_RESCHEDULE:
+		scheduler_ipi();
+		break;
+
+	case IPI_CALL_FUNC:
+		generic_smp_call_function_interrupt();
+		break;
+
+	case IPI_CPU_STOP:
+		ipi_cpu_stop();
+		break;
+
+	default:
+		rc = 1;
+	}
+
+	return rc;
+}
+
+/*
+ * arch-common ISR to handle for inter-processor interrupts
+ * Has hooks for platform specific IPI
+ */
+static irqreturn_t do_IPI(int irq, void *dev_id)
+{
+	unsigned long pending;
+	unsigned long __maybe_unused copy;
+
+	pr_debug("IPI [%ld] received on cpu %d\n",
+		 *this_cpu_ptr(&ipi_data), smp_processor_id());
+
+	if (plat_smp_ops.ipi_clear)
+		plat_smp_ops.ipi_clear(irq);
+
+	/*
+	 * "dequeue" the msg corresponding to this IPI (and possibly other
+	 * piggybacked msg from elided IPIs: see ipi_send_msg_one() above)
+	 */
+	copy = pending = xchg(this_cpu_ptr(&ipi_data), 0);
+
+	do {
+		unsigned long msg = __ffs(pending);
+		int rc;
+
+		rc = __do_IPI(msg);
+		if (rc)
+			pr_info("IPI with bogus msg %ld in %ld\n", msg, copy);
+		pending &= ~(1U << msg);
+	} while (pending);
+
+	return IRQ_HANDLED;
+}
+
+/*
+ * API called by platform code to hookup arch-common ISR to their IPI IRQ
+ *
+ * Note: If IPI is provided by platform (vs. say ARC MCIP), their intc setup/map
+ * function needs to call irq_set_percpu_devid() for IPI IRQ, otherwise
+ * request_percpu_irq() below will fail
+ */
+static DEFINE_PER_CPU(int, ipi_dev);
+
+int smp_ipi_irq_setup(int cpu, irq_hw_number_t hwirq)
+{
+	int *dev = per_cpu_ptr(&ipi_dev, cpu);
+	unsigned int virq = irq_find_mapping(NULL, hwirq);
+
+	if (!virq)
+		panic("Cannot find virq for root domain and hwirq=%lu", hwirq);
+
+	/* Boot cpu calls request, all call enable */
+	if (!cpu) {
+		int rc;
+
+		rc = request_percpu_irq(virq, do_IPI, "IPI Interrupt", dev);
+		if (rc)
+			panic("Percpu IRQ request failed for %u\n", virq);
+	}
+
+	enable_percpu_irq(virq, 0);
+
+	return 0;
+}
diff --git a/arch/arc/kernel/stacktrace.c b/arch/arc/kernel/stacktrace.c
new file mode 100644
index 000000000..ea99c066e
--- /dev/null
+++ b/arch/arc/kernel/stacktrace.c
@@ -0,0 +1,275 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *	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)
+ *
+ *  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 <linux/sched/debug.h>
+
+#include <asm/arcregs.h>
+#include <asm/unwind.h>
+#include <asm/stacktrace.h>
+#include <asm/switch_to.h>
+
+/*-------------------------------------------------------------------------
+ *              Unwinder Iterator
+ *-------------------------------------------------------------------------
+ */
+
+#ifdef CONFIG_ARC_DW2_UNWIND
+
+static int
+seed_unwind_frame_info(struct task_struct *tsk, struct pt_regs *regs,
+		       struct unwind_frame_info *frame_info)
+{
+	if (regs) {
+		/*
+		 * Asynchronous unwinding of intr/exception
+		 *  - Just uses the pt_regs passed
+		 */
+		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;
+	} else if (tsk == NULL || tsk == current) {
+		/*
+		 * synchronous unwinding (e.g. dump_stack)
+		 *  - uses current values of SP and friends
+		 */
+		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 {
+		/*
+		 * Asynchronous unwinding of a likely sleeping task
+		 *  - first ensure it is actually sleeping
+		 *  - if so, it will be in __switch_to, kernel mode SP of task
+		 *    is safe-kept and BLINK at a well known location in there
+		 */
+
+		if (task_is_running(tsk))
+			return -1;
+
+		frame_info->task = tsk;
+
+		frame_info->regs.r27 = TSK_K_FP(tsk);
+		frame_info->regs.r28 = TSK_K_ESP(tsk);
+		frame_info->regs.r31 = TSK_K_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 += 60;
+		frame_info->call_frame = 0;
+
+	}
+	return 0;
+}
+
+#endif
+
+notrace 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, cnt = 0;
+	unsigned int address;
+	struct unwind_frame_info frame_info;
+
+	if (seed_unwind_frame_info(tsk, regs, &frame_info))
+		return 0;
+
+	while (1) {
+		address = UNW_PC(&frame_info);
+
+		if (!address || !__kernel_text_address(address))
+			break;
+
+		if (consumer_fn(address, arg) == -1)
+			break;
+
+		ret = arc_unwind(&frame_info);
+		if (ret)
+			break;
+
+		frame_info.regs.r63 = frame_info.regs.r31;
+
+		if (cnt++ > 128) {
+			printk("unwinder looping too long, aborting !\n");
+			return 0;
+		}
+	}
+
+	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
+	 * prologue is setup (callee regs saved and then fp set and not other
+	 * way around
+	 */
+	pr_warn_once("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 *arg)
+{
+	const char *loglvl = arg;
+
+	printk("%s  %pS\n", loglvl, (void *)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,
+			      const char *loglvl)
+{
+	printk("%s\nStack Trace:\n", loglvl);
+	arc_unwind_core(tsk, regs, __print_sym, (void *)loglvl);
+}
+EXPORT_SYMBOL(show_stacktrace);
+
+/* Expected by sched Code */
+void show_stack(struct task_struct *tsk, unsigned long *sp, const char *loglvl)
+{
+	show_stacktrace(tsk, NULL, loglvl);
+}
+
+/* Another API expected by schedular, shows up in "ps" as Wait Channel
+ * Of course 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)
+{
+	/* Assumes @tsk is sleeping so unwinds from __switch_to */
+	arc_unwind_core(tsk, NULL, __collect_all_but_sched, trace);
+}
+
+void save_stack_trace(struct stack_trace *trace)
+{
+	/* Pass NULL for task so it unwinds the current call frame */
+	arc_unwind_core(NULL, NULL, __collect_all, trace);
+}
+EXPORT_SYMBOL_GPL(save_stack_trace);
+#endif
diff --git a/arch/arc/kernel/sys.c b/arch/arc/kernel/sys.c
new file mode 100644
index 000000000..36a2a95c0
--- /dev/null
+++ b/arch/arc/kernel/sys.c
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/syscalls.h>
+#include <linux/signal.h>
+#include <linux/unistd.h>
+
+#include <asm/syscalls.h>
+
+#define sys_clone	sys_clone_wrapper
+#define sys_clone3	sys_clone3_wrapper
+#define sys_mmap2	sys_mmap_pgoff
+
+#define __SYSCALL(nr, call) [nr] = (call),
+#define __SYSCALL_WITH_COMPAT(nr, native, compat)  __SYSCALL(nr, native)
+
+void *sys_call_table[NR_syscalls] = {
+	[0 ... NR_syscalls-1] = sys_ni_syscall,
+#include <asm/syscall_table_32.h>
+};
diff --git a/arch/arc/kernel/traps.c b/arch/arc/kernel/traps.c
new file mode 100644
index 000000000..8d2ea2cbd
--- /dev/null
+++ b/arch/arc/kernel/traps.c
@@ -0,0 +1,159 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Traps/Non-MMU Exception handling for ARC
+ *
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * vineetg: May 2011
+ *  -user-space unaligned access emulation
+ *
+ * Rahul Trivedi: Codito Technologies 2004
+ */
+
+#include <linux/sched/signal.h>
+#include <linux/kdebug.h>
+#include <linux/uaccess.h>
+#include <linux/ptrace.h>
+#include <linux/kprobes.h>
+#include <linux/kgdb.h>
+#include <asm/entry.h>
+#include <asm/setup.h>
+#include <linux/unaligned.h>
+#include <asm/kprobes.h>
+#include "unaligned.h"
+
+void die(const char *str, struct pt_regs *regs, unsigned long address)
+{
+	show_kernel_fault_diag(str, regs, address);
+
+	/* 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
+unhandled_exception(const char *str, struct pt_regs *regs,
+		    int signo, int si_code, void __user *addr)
+{
+	if (user_mode(regs)) {
+		struct task_struct *tsk = current;
+
+		tsk->thread.fault_address = (__force unsigned int)addr;
+
+		force_sig_fault(signo, si_code, addr);
+
+	} else {
+		/* If not due to copy_(to|from)_user, we are doomed */
+		if (fixup_exception(regs))
+			return 0;
+
+		die(str, regs, (unsigned long)addr);
+	}
+
+	return 1;
+}
+
+#define DO_ERROR_INFO(signr, str, name, sicode) \
+int name(unsigned long address, struct pt_regs *regs) \
+{								\
+	return unhandled_exception(str, regs, signr, sicode,	\
+				   (void __user *)address);	\
+}
+
+/*
+ * 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", __weak do_memory_error, BUS_ADRERR)
+DO_ERROR_INFO(SIGTRAP, "Breakpoint Set", trap_is_brkpt, TRAP_BRKPT)
+DO_ERROR_INFO(SIGBUS, "Misaligned Access", do_misaligned_error, BUS_ADRALN)
+DO_ERROR_INFO(SIGSEGV, "gcc generated __builtin_trap", do_trap5_error, 0)
+
+/*
+ * Entry Point for Misaligned Data access Exception, for emulating in software
+ */
+int do_misaligned_access(unsigned long address, struct pt_regs *regs,
+			 struct callee_regs *cregs)
+{
+	/* If emulation not enabled, or failed, kill the task */
+	if (misaligned_fixup(address, regs, cregs) != 0)
+		return do_misaligned_error(address, regs);
+
+	return 0;
+}
+
+/*
+ * Entry point for miscll errors such as Nested Exceptions
+ *  -Duplicate TLB entry is handled separately though
+ */
+void do_machine_check_fault(unsigned long address, struct pt_regs *regs)
+{
+	die("Unhandled Machine Check Exception", regs, address);
+}
+
+
+/*
+ * 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
+ *  -5 __builtin_trap() generated by gcc (2018.03 onwards) for toggle such as
+ *     -fno-isolate-erroneous-paths-dereference
+ */
+void do_non_swi_trap(unsigned long address, struct pt_regs *regs)
+{
+	switch (regs->ecr.param) {
+	case 1:
+		trap_is_brkpt(address, regs);
+		break;
+
+	case 2:
+		trap_is_kprobe(address, regs);
+		break;
+
+	case 3:
+	case 4:
+		kgdb_trap(regs);
+		break;
+
+	case 5:
+		do_trap5_error(address, regs);
+		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 address, struct pt_regs *regs)
+{
+	int rc;
+
+	/* Check if this exception is caused by kprobes */
+	rc = notify_die(DIE_IERR, "kprobe_ierr", regs, address, 0, SIGILL);
+	if (rc == NOTIFY_STOP)
+		return;
+
+	insterror_is_error(address, regs);
+}
+
+/*
+ * abort() call generated by older gcc for __builtin_trap()
+ */
+void abort(void)
+{
+	__asm__ __volatile__("trap_s  5\n");
+}
diff --git a/arch/arc/kernel/troubleshoot.c b/arch/arc/kernel/troubleshoot.c
new file mode 100644
index 000000000..c380d8c30
--- /dev/null
+++ b/arch/arc/kernel/troubleshoot.c
@@ -0,0 +1,230 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#include <linux/ptrace.h>
+#include <linux/module.h>
+#include <linux/mm.h>
+#include <linux/fs.h>
+#include <linux/kdev_t.h>
+#include <linux/proc_fs.h>
+#include <linux/file.h>
+#include <linux/sched/mm.h>
+#include <linux/sched/debug.h>
+
+#include <asm/arcregs.h>
+#include <asm/irqflags.h>
+
+#define ARC_PATH_MAX	256
+
+static noinline void print_regs_scratch(struct pt_regs *regs)
+{
+	pr_cont("BTA: 0x%08lx\n SP: 0x%08lx  FP: 0x%08lx BLK: %pS\n",
+		regs->bta, regs->sp, regs->fp, (void *)regs->blink);
+	pr_cont("LPS: 0x%08lx\tLPE: 0x%08lx\tLPC: 0x%08lx\n",
+		regs->lp_start, regs->lp_end, regs->lp_count);
+
+	pr_info("r00: 0x%08lx\tr01: 0x%08lx\tr02: 0x%08lx\n"	\
+		"r03: 0x%08lx\tr04: 0x%08lx\tr05: 0x%08lx\n"	\
+		"r06: 0x%08lx\tr07: 0x%08lx\tr08: 0x%08lx\n"	\
+		"r09: 0x%08lx\tr10: 0x%08lx\tr11: 0x%08lx\n"	\
+		"r12: 0x%08lx\t",
+		regs->r0, regs->r1, regs->r2,
+		regs->r3, regs->r4, regs->r5,
+		regs->r6, regs->r7, regs->r8,
+		regs->r9, regs->r10, regs->r11,
+		regs->r12);
+}
+
+static void print_regs_callee(struct callee_regs *regs)
+{
+	pr_cont("r13: 0x%08lx\tr14: 0x%08lx\n"			\
+		"r15: 0x%08lx\tr16: 0x%08lx\tr17: 0x%08lx\n"	\
+		"r18: 0x%08lx\tr19: 0x%08lx\tr20: 0x%08lx\n"	\
+		"r21: 0x%08lx\tr22: 0x%08lx\tr23: 0x%08lx\n"	\
+		"r24: 0x%08lx\tr25: 0x%08lx\n",
+		regs->r13, regs->r14,
+		regs->r15, regs->r16, regs->r17,
+		regs->r18, regs->r19, regs->r20,
+		regs->r21, regs->r22, regs->r23,
+		regs->r24, regs->r25);
+}
+
+static void print_task_path_n_nm(struct task_struct *tsk)
+{
+	char *path_nm = NULL;
+	struct mm_struct *mm;
+	struct file *exe_file;
+	char buf[ARC_PATH_MAX];
+
+	mm = get_task_mm(tsk);
+	if (!mm)
+		goto done;
+
+	exe_file = get_mm_exe_file(mm);
+	mmput(mm);
+
+	if (exe_file) {
+		path_nm = file_path(exe_file, buf, ARC_PATH_MAX-1);
+		fput(exe_file);
+	}
+
+done:
+	pr_info("Path: %s\n", !IS_ERR(path_nm) ? path_nm : "?");
+}
+
+static void show_faulting_vma(unsigned long address)
+{
+	struct vm_area_struct *vma;
+	struct mm_struct *active_mm = current->active_mm;
+
+	/* can't use print_vma_addr() yet as it doesn't check for
+	 * non-inclusive vma
+	 */
+	mmap_read_lock(active_mm);
+	vma = vma_lookup(active_mm, address);
+
+	/* Lookup the vma at the address and report if the container VMA is not
+	 * found
+	 */
+	if (vma) {
+		char buf[ARC_PATH_MAX];
+		char *nm = "anon";
+
+		if (vma->vm_file) {
+			/* XXX: can we use %pD below and get rid of buf? */
+			nm = d_path(file_user_path(vma->vm_file), buf,
+				    ARC_PATH_MAX-1);
+			if (IS_ERR(nm))
+				nm = "?";
+		}
+		pr_info("  @off 0x%lx in [%s]  VMA: 0x%08lx to 0x%08lx\n",
+			vma->vm_start < TASK_UNMAPPED_BASE ?
+				address : address - vma->vm_start,
+			nm, vma->vm_start, vma->vm_end);
+	} else
+		pr_info("    @No matching VMA found\n");
+
+	mmap_read_unlock(active_mm);
+}
+
+static void show_ecr_verbose(struct pt_regs *regs)
+{
+	unsigned int vec, cause_code;
+	unsigned long address;
+
+	/* For Data fault, this is data address not instruction addr */
+	address = current->thread.fault_address;
+
+	vec = regs->ecr.vec;
+	cause_code = regs->ecr.cause;
+
+	/* For DTLB Miss or ProtV, display the memory involved too */
+	if (vec == ECR_V_DTLB_MISS) {
+		pr_cont("Invalid %s @ 0x%08lx by insn @ %pS\n",
+		       (cause_code == 0x01) ? "Read" :
+		       ((cause_code == 0x02) ? "Write" : "EX"),
+		       address, (void *)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("Machine Check (%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_MISALIG_DATA &&
+		         IS_ENABLED(CONFIG_ISA_ARCOMPACT))
+			pr_cont("Misaligned r/w from 0x%08lx\n", address);
+		else
+			pr_cont("%s access not allowed on page\n",
+				(cause_code == 0x01) ? "Read" :
+				((cause_code == 0x02) ? "Write" : "EX"));
+	} else if (vec == ECR_V_INSN_ERR) {
+		pr_cont("Illegal Insn\n");
+#ifdef CONFIG_ISA_ARCV2
+	} else if (vec == ECR_V_MEM_ERR) {
+		if (cause_code == 0x00)
+			pr_cont("Bus Error from Insn Mem\n");
+		else if (cause_code == 0x10)
+			pr_cont("Bus Error from Data Mem\n");
+		else
+			pr_cont("Bus Error, check PRM\n");
+	} else if (vec == ECR_V_MISALIGN) {
+		pr_cont("Misaligned r/w from 0x%08lx\n", address);
+#endif
+	} else if (vec == ECR_V_TRAP) {
+		if (regs->ecr.param == 5)
+			pr_cont("gcc generated __builtin_trap\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 = (struct callee_regs *)tsk->thread.callee_reg;
+
+	/*
+	 * generic code calls us with preemption disabled, but some calls
+	 * here could sleep, so re-enable to avoid lockdep splat
+	 */
+	preempt_enable();
+
+	print_task_path_n_nm(tsk);
+	show_regs_print_info(KERN_INFO);
+
+	show_ecr_verbose(regs);
+
+	if (user_mode(regs))
+		show_faulting_vma(regs->ret); /* faulting code, not data */
+
+	pr_info("ECR: 0x%08lx EFA: 0x%08lx ERET: 0x%08lx\n",
+		regs->ecr.full, current->thread.fault_address, regs->ret);
+
+	pr_info("STAT32: 0x%08lx", regs->status32);
+
+#define STS_BIT(r, bit)	r->status32 & STATUS_##bit##_MASK ? #bit" " : ""
+
+#ifdef CONFIG_ISA_ARCOMPACT
+	pr_cont(" [%2s%2s%2s%2s%2s%2s%2s]",
+			(regs->status32 & STATUS_U_MASK) ? "U " : "K ",
+			STS_BIT(regs, DE), STS_BIT(regs, AE),
+			STS_BIT(regs, A2), STS_BIT(regs, A1),
+			STS_BIT(regs, E2), STS_BIT(regs, E1));
+#else
+	pr_cont(" [%2s%2s%2s%2s]   ",
+			STS_BIT(regs, IE),
+			(regs->status32 & STATUS_U_MASK) ? "U " : "K ",
+			STS_BIT(regs, DE), STS_BIT(regs, AE));
+#endif
+
+	print_regs_scratch(regs);
+	if (cregs)
+		print_regs_callee(cregs);
+
+	preempt_disable();
+}
+
+void show_kernel_fault_diag(const char *str, struct pt_regs *regs,
+			    unsigned long address)
+{
+	current->thread.fault_address = address;
+
+	/* Show fault description */
+	pr_info("\n%s\n", str);
+
+	/* 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, KERN_DEFAULT);
+}
diff --git a/arch/arc/kernel/unaligned.c b/arch/arc/kernel/unaligned.c
new file mode 100644
index 000000000..3b2d8b1bd
--- /dev/null
+++ b/arch/arc/kernel/unaligned.c
@@ -0,0 +1,262 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2011-2012 Synopsys (www.synopsys.com)
+ *
+ * vineetg : May 2011
+ *  -Adapted (from .26 to .35)
+ *  -original contribution by Tim.yao@amlogic.com
+ */
+
+#include <linux/types.h>
+#include <linux/perf_event.h>
+#include <linux/ptrace.h>
+#include <linux/uaccess.h>
+#include <asm/disasm.h>
+#include "unaligned.h"
+
+#ifdef CONFIG_CPU_BIG_ENDIAN
+#define BE		1
+#define FIRST_BYTE_16	"swap %1, %1\n swape %1, %1\n"
+#define FIRST_BYTE_32	"swape %1, %1\n"
+#else
+#define BE		0
+#define FIRST_BYTE_16
+#define FIRST_BYTE_32
+#endif
+
+#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"			\
+	"	j	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 << ((BE) ? 8 : 0);		\
+		__get8_unaligned_check(v, a, err);	\
+		val |= v << ((BE) ? 0 : 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 << ((BE) ? 24 : 0);		\
+		__get8_unaligned_check(v, a, err);	\
+		val |= v << ((BE) ? 16 : 8);		\
+		__get8_unaligned_check(v, a, err);	\
+		val |= v << ((BE) ? 8 : 16);		\
+		__get8_unaligned_check(v, a, err);	\
+		val |= v << ((BE) ? 0 : 24);		\
+		if (err)				\
+			goto fault;			\
+	} while (0)
+
+#define put16_unaligned_check(val, addr)		\
+	do {						\
+		unsigned int err = 0, v = val, a = addr;\
+							\
+		__asm__(				\
+		FIRST_BYTE_16				\
+		"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"		\
+		"	j	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__(				\
+		FIRST_BYTE_32				\
+		"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"		\
+		"	j	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,
+		     struct callee_regs *cregs)
+{
+	struct disasm_state state;
+
+	/* 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",
+			     current->comm, 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",
+			current->comm, 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;
+
+	/* clear any remnants of delay slot */
+	if (delay_mode(regs)) {
+		regs->ret = regs->bta & ~1U;
+		regs->status32 &= ~STATUS_DE_MASK;
+	} else {
+		regs->ret += state.instr_len;
+
+		/* handle zero-overhead-loop */
+		if ((regs->ret == regs->lp_end) && (regs->lp_count)) {
+			regs->ret = regs->lp_start;
+			regs->lp_count--;
+		}
+	}
+
+	perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, address);
+	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/unaligned.h b/arch/arc/kernel/unaligned.h
new file mode 100644
index 000000000..5244453bb
--- /dev/null
+++ b/arch/arc/kernel/unaligned.h
@@ -0,0 +1,16 @@
+struct pt_regs;
+struct callee_regs;
+
+#ifdef CONFIG_ARC_EMUL_UNALIGNED
+int misaligned_fixup(unsigned long address, struct pt_regs *regs,
+		     struct callee_regs *cregs);
+#else
+static inline int
+misaligned_fixup(unsigned long address, struct pt_regs *regs,
+		 struct callee_regs *cregs)
+{
+	/* Not fixed */
+	return 1;
+}
+#endif
+
diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c
new file mode 100644
index 000000000..6fdc751f9
--- /dev/null
+++ b/arch/arc/kernel/unwind.c
@@ -0,0 +1,1306 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ * Copyright (C) 2002-2006 Novell, Inc.
+ *	Jan Beulich <jbeulich@novell.com>
+ *
+ * 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/memblock.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 <linux/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) \
+				% sizeof_field(struct unwind_frame_info, f)) \
+				+ offsetof(struct unwind_frame_info, f) \
+				/ sizeof_field(struct unwind_frame_info, f), \
+				sizeof_field(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
+
+#define CIE_ID	0
+
+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_hdr(struct unwind_table *table,
+			    void *(*alloc) (unsigned long));
+
+/*
+ * wrappers for header alloc (vs. calling one vs. other at call site)
+ * to elide section mismatches warnings
+ */
+static void *__init unw_hdr_alloc_early(unsigned long sz)
+{
+	return memblock_alloc_from(sz, sizeof(unsigned int), MAX_DMA_ADDRESS);
+}
+
+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)
+{
+	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;
+	/* To avoid the pointer addition with NULL pointer.*/
+	if (header_start != NULL) {
+		const u8 *ptr = header_start + 4;
+		const u8 *end = header_start + header_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);*/
+
+	init_unwind_hdr(&root_table, unw_hdr_alloc_early);
+}
+
+static const u32 bad_cie, not_fde;
+static const u32 *cie_for_fde(const u32 *fde, const struct unwind_table *);
+static const u32 *__cie_for_fde(const u32 *fde);
+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 init_unwind_hdr(struct unwind_table *table,
+			    void *(*alloc) (unsigned long))
+{
+	const u8 *ptr;
+	unsigned long tableSize = table->size, hdrSize;
+	unsigned int 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)
+			goto ret_err;
+		ptrType = fde_pointer_type(cie);
+		if (ptrType < 0)
+			goto ret_err;
+
+		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;
+			 */
+			WARN(1, "unwinder: FDE->initial_location NULL %p\n",
+				(const u8 *)(fde + 1) + *fde);
+		}
+		++n;
+	}
+
+	if (tableSize || !n)
+		goto ret_err;
+
+	hdrSize = 4 + sizeof(unsigned long) + sizeof(unsigned int)
+	    + 2 * n * sizeof(unsigned long);
+
+	header = alloc(hdrSize);
+	if (!header)
+		goto ret_err;
+
+	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 = __cie_for_fde(fde);
+
+		if (fde[1] == CIE_ID)
+			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, NULL);
+
+	table->hdrsz = hdrSize;
+	smp_wmb();
+	table->header = (const void *)header;
+	return;
+
+ret_err:
+	panic("Attention !!! Dwarf FDE parsing errors\n");
+}
+
+#ifdef CONFIG_MODULES
+static void *unw_hdr_alloc(unsigned long sz)
+{
+	return kmalloc(sz, GFP_KERNEL);
+}
+
+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;
+	struct module_memory *core_text;
+	struct module_memory *init_text;
+
+	if (table_size <= 0)
+		return NULL;
+
+	table = kmalloc_obj(*table);
+	if (!table)
+		return NULL;
+
+	core_text = &module->mem[MOD_TEXT];
+	init_text = &module->mem[MOD_INIT_TEXT];
+
+	init_unwind_table(table, module->name, core_text->base, core_text->size,
+			  init_text->base, init_text->size, table_start, table_size, NULL, 0);
+
+	init_unwind_hdr(table, unw_hdr_alloc);
+
+#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->header);
+	kfree(table);
+}
+
+#endif /* CONFIG_MODULES */
+
+static uleb128_t get_uleb128(const u8 **pcur, const u8 *end)
+{
+	const u8 *cur = *pcur;
+	uleb128_t value;
+	unsigned int 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 int 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 u32 *cie;
+
+	cie = fde + 1 - fde[1] / sizeof(*fde);
+
+	return cie;
+}
+
+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] == CIE_ID)
+		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 = __cie_for_fde(fde);
+
+	if (*cie <= sizeof(*cie) + 4 || *cie >= fde[1] - sizeof(*fde)
+	    || (*cie & (sizeof(*cie) - 1))
+	    || (cie[1] != CIE_ID))
+		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
+		fallthrough;
+	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 int version = *ptr;
+
+	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);
+				fallthrough;
+			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);
+				fallthrough;
+			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_register: ");
+				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("UNKNOWN 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 int 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;
+					cie = NULL;
+				}
+			} else {
+				fde = NULL;
+				cie = NULL;
+			}
+		}
+	}
+	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 (*++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 alignment factor */
+		state.codeAlign = get_uleb128(&ptr, end);
+		/* get data alignment 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 */
+	if (frame->call_frame
+	    && !UNW_DEFAULT_RA(state.regs[retAddrReg], state.dataAlign))
+		frame->call_frame = 0;
+	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 000000000..6af63084f
--- /dev/null
+++ b/arch/arc/kernel/vmlinux.lds.S
@@ -0,0 +1,156 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#include <asm-generic/vmlinux.lds.h>
+#include <asm/cache.h>
+#include <asm/page.h>
+#include <asm/thread_info.h>
+
+OUTPUT_ARCH(arc)
+ENTRY(res_service)
+
+#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 separate subsection .init.ramfs is to
+	 * prevent objdump 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);
+
+	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
+	}
+
+	.init.arch.info : {
+		__arch_info_begin = .;
+		*(.arch.info.init)
+		__arch_info_end = .;
+	}
+
+	PERCPU_SECTION(L1_CACHE_BYTES)
+
+	. = ALIGN(PAGE_SIZE);
+	__init_end = .;
+
+	.text : {
+		_text = .;
+		_stext = .;
+		TEXT_TEXT
+		SCHED_TEXT
+		LOCK_TEXT
+		KPROBES_TEXT
+		IRQENTRY_TEXT
+		SOFTIRQENTRY_TEXT
+		*(.fixup)
+		*(.gnu.warning)
+	}
+	EXCEPTION_TABLE(L1_CACHE_BYTES)
+	_etext = .;
+
+	_sdata = .;
+	RO_DATA(PAGE_SIZE)
+
+	/*
+	 * 1. this is .data essentially
+	 * 2. THREAD_SIZE for init.task, must be kernel-stk sz aligned
+	 */
+	RW_DATA(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
+
+	_edata = .;
+
+	BSS_SECTION(4, 4, 4)
+
+#ifdef CONFIG_ARC_DW2_UNWIND
+	. = ALIGN(PAGE_SIZE);
+	.eh_frame  : {
+		__start_unwind = .;
+		*(.eh_frame)
+		__end_unwind = .;
+	}
+#else
+	/DISCARD/ : {	*(.eh_frame) }
+#endif
+
+	. = ALIGN(PAGE_SIZE);
+	_end = . ;
+
+	STABS_DEBUG
+	MODINFO
+	ELF_DETAILS
+	DISCARDS
+
+	.arcextmap 0 : {
+		*(.gnu.linkonce.arcextmap.*)
+		*(.arcextmap.*)
+	}
+
+#ifndef CONFIG_DEBUG_INFO
+	/DISCARD/ : { *(.debug_frame) }
+	/DISCARD/ : { *(.debug_aranges) }
+	/DISCARD/ : { *(.debug_pubnames) }
+	/DISCARD/ : { *(.debug_info) }
+	/DISCARD/ : { *(.debug_abbrev) }
+	/DISCARD/ : { *(.debug_line) }
+	/DISCARD/ : { *(.debug_str) }
+	/DISCARD/ : { *(.debug_loc) }
+	/DISCARD/ : { *(.debug_macinfo) }
+	/DISCARD/ : { *(.debug_ranges) }
+#endif
+
+#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 000000000..30158ae69
--- /dev/null
+++ b/arch/arc/lib/Makefile
@@ -0,0 +1,15 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+#
+
+lib-y	:= strchr-700.o strcpy-700.o strlen.o memcmp.o
+
+lib-$(CONFIG_ISA_ARCOMPACT)	+= memcpy-700.o memset.o strcmp.o
+lib-$(CONFIG_ISA_ARCV2)		+= memset-archs.o strcmp-archs.o
+
+ifdef CONFIG_ARC_USE_UNALIGNED_MEM_ACCESS
+lib-$(CONFIG_ISA_ARCV2)		+=memcpy-archs-unaligned.o
+else
+lib-$(CONFIG_ISA_ARCV2)		+=memcpy-archs.o
+endif
diff --git a/arch/arc/lib/memcmp.S b/arch/arc/lib/memcmp.S
new file mode 100644
index 000000000..d6dc5e9bc
--- /dev/null
+++ b/arch/arc/lib/memcmp.S
@@ -0,0 +1,149 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#include <linux/linkage.h>
+
+#ifdef __LITTLE_ENDIAN__
+#define WORD2 r2
+#define SHIFT r3
+#else /* BIG ENDIAN */
+#define WORD2 r3
+#define SHIFT r2
+#endif
+
+ENTRY_CFI(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
+#ifdef CONFIG_ISA_ARCV2
+	/* In ARCv2 a branch can't be the last instruction in a zero overhead
+	 * loop.
+	 * So we move the branch to the start of the loop, duplicate it
+	 * after the end, and set up r12 so that the branch isn't taken
+	 *  initially.
+	 */
+	mov_s	r12,WORD2
+	lpne	.Loop_end
+	brne	WORD2,r12,.Lodd
+	ld	WORD2,[r0,4]
+#else
+	lpne	.Loop_end
+	ld_s	WORD2,[r0,4]
+#endif
+	ld_s	r12,[r1,4]
+	brne	r4,r5,.Leven
+	ld.a	r4,[r0,8]
+	ld.a	r5,[r1,8]
+#ifdef CONFIG_ISA_ARCV2
+.Loop_end:
+	brne	WORD2,r12,.Lodd
+#else
+	brne	WORD2,r12,.Lodd
+.Loop_end:
+#endif
+	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
+#ifdef CONFIG_ISA_ARCV2
+	mov	r12,r3
+	lpne	.Lbyte_end
+	brne	r3,r12,.Lbyte_odd
+#else
+	lpne	.Lbyte_end
+#endif
+	ldb_s	r3,[r0,1]
+	ldb	r12,[r1,1]
+	brne	r4,r5,.Lbyte_even
+	ldb.a	r4,[r0,2]
+	ldb.a	r5,[r1,2]
+#ifdef CONFIG_ISA_ARCV2
+.Lbyte_end:
+	brne	r3,r12,.Lbyte_odd
+#else
+	brne	r3,r12,.Lbyte_odd
+.Lbyte_end:
+#endif
+	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
+END_CFI(memcmp)
diff --git a/arch/arc/lib/memcpy-700.S b/arch/arc/lib/memcpy-700.S
new file mode 100644
index 000000000..f2e239e21
--- /dev/null
+++ b/arch/arc/lib/memcpy-700.S
@@ -0,0 +1,63 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#include <linux/linkage.h>
+
+ENTRY_CFI(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]
+END_CFI(memcpy)
diff --git a/arch/arc/lib/memcpy-archs-unaligned.S b/arch/arc/lib/memcpy-archs-unaligned.S
new file mode 100644
index 000000000..28993a73f
--- /dev/null
+++ b/arch/arc/lib/memcpy-archs-unaligned.S
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * ARCv2 memcpy implementation optimized for unaligned memory access using.
+ *
+ * Copyright (C) 2019 Synopsys
+ * Author: Eugeniy Paltsev <Eugeniy.Paltsev@synopsys.com>
+ */
+
+#include <linux/linkage.h>
+
+#ifdef CONFIG_ARC_HAS_LL64
+# define LOADX(DST,RX)		ldd.ab	DST, [RX, 8]
+# define STOREX(SRC,RX)		std.ab	SRC, [RX, 8]
+# define ZOLSHFT		5
+# define ZOLAND			0x1F
+#else
+# define LOADX(DST,RX)		ld.ab	DST, [RX, 4]
+# define STOREX(SRC,RX)		st.ab	SRC, [RX, 4]
+# define ZOLSHFT		4
+# define ZOLAND			0xF
+#endif
+
+ENTRY_CFI(memcpy)
+	mov	r3, r0		; don;t clobber ret val
+
+	lsr.f	lp_count, r2, ZOLSHFT
+	lpnz	@.Lcopy32_64bytes
+	;; LOOP START
+	LOADX	(r6, r1)
+	LOADX	(r8, r1)
+	LOADX	(r10, r1)
+	LOADX	(r4, r1)
+	STOREX	(r6, r3)
+	STOREX	(r8, r3)
+	STOREX	(r10, r3)
+	STOREX	(r4, r3)
+.Lcopy32_64bytes:
+
+	and.f	lp_count, r2, ZOLAND ;Last remaining 31 bytes
+	lpnz	@.Lcopyremainingbytes
+	;; LOOP START
+	ldb.ab	r5, [r1, 1]
+	stb.ab	r5, [r3, 1]
+.Lcopyremainingbytes:
+
+	j	[blink]
+END_CFI(memcpy)
diff --git a/arch/arc/lib/memcpy-archs.S b/arch/arc/lib/memcpy-archs.S
new file mode 100644
index 000000000..0051a84f6
--- /dev/null
+++ b/arch/arc/lib/memcpy-archs.S
@@ -0,0 +1,219 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#include <linux/linkage.h>
+
+#ifdef __LITTLE_ENDIAN__
+# define SHIFT_1(RX,RY,IMM)	asl	RX, RY, IMM	; <<
+# define SHIFT_2(RX,RY,IMM)	lsr	RX, RY, IMM	; >>
+# define MERGE_1(RX,RY,IMM)	asl	RX, RY, IMM
+# define MERGE_2(RX,RY,IMM)
+# define EXTRACT_1(RX,RY,IMM)	and	RX, RY, 0xFFFF
+# define EXTRACT_2(RX,RY,IMM)	lsr	RX, RY, IMM
+#else
+# define SHIFT_1(RX,RY,IMM)	lsr	RX, RY, IMM	; >>
+# define SHIFT_2(RX,RY,IMM)	asl	RX, RY, IMM	; <<
+# define MERGE_1(RX,RY,IMM)	asl	RX, RY, IMM	; <<
+# define MERGE_2(RX,RY,IMM)	asl	RX, RY, IMM	; <<
+# define EXTRACT_1(RX,RY,IMM)	lsr	RX, RY, IMM
+# define EXTRACT_2(RX,RY,IMM)	lsr	RX, RY, 0x08
+#endif
+
+#ifdef CONFIG_ARC_HAS_LL64
+# define LOADX(DST,RX)		ldd.ab	DST, [RX, 8]
+# define STOREX(SRC,RX)		std.ab	SRC, [RX, 8]
+# define ZOLSHFT		5
+# define ZOLAND			0x1F
+#else
+# define LOADX(DST,RX)		ld.ab	DST, [RX, 4]
+# define STOREX(SRC,RX)		st.ab	SRC, [RX, 4]
+# define ZOLSHFT		4
+# define ZOLAND			0xF
+#endif
+
+ENTRY_CFI(memcpy)
+	mov.f	0, r2
+;;; if size is zero
+	jz.d	[blink]
+	mov	r3, r0		; don;t clobber ret val
+
+;;; if size <= 8
+	cmp	r2, 8
+	bls.d	@.Lsmallchunk
+	mov.f	lp_count, r2
+
+	and.f	r4, r0, 0x03
+	rsub	lp_count, r4, 4
+	lpnz	@.Laligndestination
+	;; LOOP BEGIN
+	ldb.ab	r5, [r1,1]
+	sub	r2, r2, 1
+	stb.ab	r5, [r3,1]
+.Laligndestination:
+
+;;; Check the alignment of the source
+	and.f	r4, r1, 0x03
+	bnz.d	@.Lsourceunaligned
+
+;;; CASE 0: Both source and destination are 32bit aligned
+;;; Convert len to Dwords, unfold x4
+	lsr.f	lp_count, r2, ZOLSHFT
+	lpnz	@.Lcopy32_64bytes
+	;; LOOP START
+	LOADX (r6, r1)
+	LOADX (r8, r1)
+	LOADX (r10, r1)
+	LOADX (r4, r1)
+	STOREX (r6, r3)
+	STOREX (r8, r3)
+	STOREX (r10, r3)
+	STOREX (r4, r3)
+.Lcopy32_64bytes:
+
+	and.f	lp_count, r2, ZOLAND ;Last remaining 31 bytes
+.Lsmallchunk:
+	lpnz	@.Lcopyremainingbytes
+	;; LOOP START
+	ldb.ab	r5, [r1,1]
+	stb.ab	r5, [r3,1]
+.Lcopyremainingbytes:
+
+	j	[blink]
+;;; END CASE 0
+
+.Lsourceunaligned:
+	cmp	r4, 2
+	beq.d	@.LunalignedOffby2
+	sub	r2, r2, 1
+
+	bhi.d	@.LunalignedOffby3
+	ldb.ab	r5, [r1, 1]
+
+;;; CASE 1: The source is unaligned, off by 1
+	;; Hence I need to read 1 byte for a 16bit alignment
+	;; and 2bytes to reach 32bit alignment
+	ldh.ab	r6, [r1, 2]
+	sub	r2, r2, 2
+	;; Convert to words, unfold x2
+	lsr.f	lp_count, r2, 3
+	MERGE_1 (r6, r6, 8)
+	MERGE_2 (r5, r5, 24)
+	or	r5, r5, r6
+
+	;; Both src and dst are aligned
+	lpnz	@.Lcopy8bytes_1
+	;; LOOP START
+	ld.ab	r6, [r1, 4]
+	ld.ab	r8, [r1,4]
+
+	SHIFT_1	(r7, r6, 24)
+	or	r7, r7, r5
+	SHIFT_2	(r5, r6, 8)
+
+	SHIFT_1	(r9, r8, 24)
+	or	r9, r9, r5
+	SHIFT_2	(r5, r8, 8)
+
+	st.ab	r7, [r3, 4]
+	st.ab	r9, [r3, 4]
+.Lcopy8bytes_1:
+
+	;; Write back the remaining 16bits
+	EXTRACT_1 (r6, r5, 16)
+	sth.ab	r6, [r3, 2]
+	;; Write back the remaining 8bits
+	EXTRACT_2 (r5, r5, 16)
+	stb.ab	r5, [r3, 1]
+
+	and.f	lp_count, r2, 0x07 ;Last 8bytes
+	lpnz	@.Lcopybytewise_1
+	;; LOOP START
+	ldb.ab	r6, [r1,1]
+	stb.ab	r6, [r3,1]
+.Lcopybytewise_1:
+	j	[blink]
+
+.LunalignedOffby2:
+;;; CASE 2: The source is unaligned, off by 2
+	ldh.ab	r5, [r1, 2]
+	sub	r2, r2, 1
+
+	;; Both src and dst are aligned
+	;; Convert to words, unfold x2
+	lsr.f	lp_count, r2, 3
+#ifdef __BIG_ENDIAN__
+	asl.nz	r5, r5, 16
+#endif
+	lpnz	@.Lcopy8bytes_2
+	;; LOOP START
+	ld.ab	r6, [r1, 4]
+	ld.ab	r8, [r1,4]
+
+	SHIFT_1	(r7, r6, 16)
+	or	r7, r7, r5
+	SHIFT_2	(r5, r6, 16)
+
+	SHIFT_1	(r9, r8, 16)
+	or	r9, r9, r5
+	SHIFT_2	(r5, r8, 16)
+
+	st.ab	r7, [r3, 4]
+	st.ab	r9, [r3, 4]
+.Lcopy8bytes_2:
+
+#ifdef __BIG_ENDIAN__
+	lsr.nz	r5, r5, 16
+#endif
+	sth.ab	r5, [r3, 2]
+
+	and.f	lp_count, r2, 0x07 ;Last 8bytes
+	lpnz	@.Lcopybytewise_2
+	;; LOOP START
+	ldb.ab	r6, [r1,1]
+	stb.ab	r6, [r3,1]
+.Lcopybytewise_2:
+	j	[blink]
+
+.LunalignedOffby3:
+;;; CASE 3: The source is unaligned, off by 3
+;;; Hence, I need to read 1byte for achieve the 32bit alignment
+
+	;; Both src and dst are aligned
+	;; Convert to words, unfold x2
+	lsr.f	lp_count, r2, 3
+#ifdef __BIG_ENDIAN__
+	asl.ne	r5, r5, 24
+#endif
+	lpnz	@.Lcopy8bytes_3
+	;; LOOP START
+	ld.ab	r6, [r1, 4]
+	ld.ab	r8, [r1,4]
+
+	SHIFT_1	(r7, r6, 8)
+	or	r7, r7, r5
+	SHIFT_2	(r5, r6, 24)
+
+	SHIFT_1	(r9, r8, 8)
+	or	r9, r9, r5
+	SHIFT_2	(r5, r8, 24)
+
+	st.ab	r7, [r3, 4]
+	st.ab	r9, [r3, 4]
+.Lcopy8bytes_3:
+
+#ifdef __BIG_ENDIAN__
+	lsr.nz	r5, r5, 24
+#endif
+	stb.ab	r5, [r3, 1]
+
+	and.f	lp_count, r2, 0x07 ;Last 8bytes
+	lpnz	@.Lcopybytewise_3
+	;; LOOP START
+	ldb.ab	r6, [r1,1]
+	stb.ab	r6, [r3,1]
+.Lcopybytewise_3:
+	j	[blink]
+
+END_CFI(memcpy)
diff --git a/arch/arc/lib/memset-archs.S b/arch/arc/lib/memset-archs.S
new file mode 100644
index 000000000..d0a5cec4c
--- /dev/null
+++ b/arch/arc/lib/memset-archs.S
@@ -0,0 +1,144 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#include <linux/linkage.h>
+#include <asm/cache.h>
+
+/*
+ * The memset implementation below is optimized to use prefetchw and prealloc
+ * instruction in case of CPU with 64B L1 data cache line (L1_CACHE_SHIFT == 6)
+ * If you want to implement optimized memset for other possible L1 data cache
+ * line lengths (32B and 128B) you should rewrite code carefully checking
+ * we don't call any prefetchw/prealloc instruction for L1 cache lines which
+ * don't belongs to memset area.
+ */
+
+#if L1_CACHE_SHIFT == 6
+
+.macro PREALLOC_INSTR	reg, off
+	prealloc	[\reg, \off]
+.endm
+
+.macro PREFETCHW_INSTR	reg, off
+	prefetchw	[\reg, \off]
+.endm
+
+#else
+
+.macro PREALLOC_INSTR	reg, off
+.endm
+
+.macro PREFETCHW_INSTR	reg, off
+.endm
+
+#endif
+
+ENTRY_CFI(memset)
+	mov.f	0, r2
+;;; if size is zero
+	jz.d	[blink]
+	mov	r3, r0		; don't clobber ret val
+
+	PREFETCHW_INSTR	r0, 0	; Prefetch the first write location
+
+;;; if length < 8
+	brls.d.nt	r2, 8, .Lsmallchunk
+	mov.f	lp_count,r2
+
+	and.f	r4, r0, 0x03
+	rsub	lp_count, r4, 4
+	lpnz	@.Laligndestination
+	;; LOOP BEGIN
+	stb.ab	r1, [r3,1]
+	sub	r2, r2, 1
+.Laligndestination:
+
+;;; Destination is aligned
+	and	r1, r1, 0xFF
+	asl	r4, r1, 8
+	or	r4, r4, r1
+	asl	r5, r4, 16
+	or	r5, r5, r4
+	mov	r4, r5
+
+	sub3	lp_count, r2, 8
+	cmp     r2, 64
+	bmsk.hi	r2, r2, 5
+	mov.ls	lp_count, 0
+	add3.hi	r2, r2, 8
+
+;;; Convert len to Dwords, unfold x8
+	lsr.f	lp_count, lp_count, 6
+
+	lpnz	@.Lset64bytes
+	;; LOOP START
+	PREALLOC_INSTR	r3, 64	; alloc next line w/o fetching
+
+#ifdef CONFIG_ARC_HAS_LL64
+	std.ab	r4, [r3, 8]
+	std.ab	r4, [r3, 8]
+	std.ab	r4, [r3, 8]
+	std.ab	r4, [r3, 8]
+	std.ab	r4, [r3, 8]
+	std.ab	r4, [r3, 8]
+	std.ab	r4, [r3, 8]
+	std.ab	r4, [r3, 8]
+#else
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+#endif
+.Lset64bytes:
+
+	lsr.f	lp_count, r2, 5 ;Last remaining  max 124 bytes
+	lpnz	.Lset32bytes
+	;; LOOP START
+#ifdef CONFIG_ARC_HAS_LL64
+	std.ab	r4, [r3, 8]
+	std.ab	r4, [r3, 8]
+	std.ab	r4, [r3, 8]
+	std.ab	r4, [r3, 8]
+#else
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+#endif
+.Lset32bytes:
+
+	and.f	lp_count, r2, 0x1F ;Last remaining 31 bytes
+.Lsmallchunk:
+	lpnz	.Lcopy3bytes
+	;; LOOP START
+	stb.ab	r1, [r3, 1]
+.Lcopy3bytes:
+
+	j	[blink]
+
+END_CFI(memset)
+
+ENTRY_CFI(memzero)
+    ; adjust bzero args to memset args
+    mov r2, r1
+    b.d  memset    ;tail call so need to tinker with blink
+    mov r1, 0
+END_CFI(memzero)
diff --git a/arch/arc/lib/memset.S b/arch/arc/lib/memset.S
new file mode 100644
index 000000000..9f35960da
--- /dev/null
+++ b/arch/arc/lib/memset.S
@@ -0,0 +1,56 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#include <linux/linkage.h>
+
+#define SMALL	7 /* Must be at least 6 to deal with alignment/loop issues.  */
+
+ENTRY_CFI(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]
+END_CFI(memset)
+
+; memzero: @r0 = mem, @r1 = size_t
+; memset:  @r0 = mem, @r1 = char, @r2 = size_t
+
+ENTRY_CFI(memzero)
+    ; adjust bzero args to memset args
+    mov r2, r1
+    mov r1, 0
+    b  memset    ;tail call so need to tinker with blink
+END_CFI(memzero)
diff --git a/arch/arc/lib/strchr-700.S b/arch/arc/lib/strchr-700.S
new file mode 100644
index 000000000..d52e2833f
--- /dev/null
+++ b/arch/arc/lib/strchr-700.S
@@ -0,0 +1,130 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+/* 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 <linux/linkage.h>
+
+ENTRY_CFI(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
+#ifdef __LITTLE_ENDIAN__
+	and	r7,r12,r4
+	breq	r7,0,.Loop ; For speed, we want this branch to be unaligned.
+	b	.Lfound_char ; Likewise this one.
+#else
+	and	r12,r12,r4
+	breq	r12,0,.Loop ; For speed, we want this branch to be unaligned.
+	lsr_s	r12,r12,7
+	bic 	r2,r7,r6
+	b.d	.Lfound_char_b
+	and_s	r2,r2,r12
+#endif
+; /* 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
+.Lfound_char_b:
+	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 */
+END_CFI(strchr)
diff --git a/arch/arc/lib/strcmp-archs.S b/arch/arc/lib/strcmp-archs.S
new file mode 100644
index 000000000..7cffb3717
--- /dev/null
+++ b/arch/arc/lib/strcmp-archs.S
@@ -0,0 +1,75 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#include <linux/linkage.h>
+
+ENTRY_CFI(strcmp)
+	or	r2, r0, r1
+	bmsk_s	r2, r2, 1
+	brne	r2, 0, @.Lcharloop
+
+;;; s1 and s2 are word aligned
+	ld.ab	r2, [r0, 4]
+
+	mov_s	r12, 0x01010101
+	ror	r11, r12
+	.align  4
+.LwordLoop:
+	ld.ab	r3, [r1, 4]
+	;; Detect NULL char in str1
+	sub	r4, r2, r12
+	ld.ab	r5, [r0, 4]
+	bic	r4, r4, r2
+	and	r4, r4, r11
+	brne.d.nt	r4, 0, .LfoundNULL
+	;; Check if the read locations are the same
+	cmp	r2, r3
+	beq.d	.LwordLoop
+	mov.eq	r2, r5
+
+	;; A match is found, spot it out
+#ifdef __LITTLE_ENDIAN__
+	swape	r3, r3
+	mov_s	r0, 1
+	swape	r2, r2
+#else
+	mov_s	r0, 1
+#endif
+	cmp_s	r2, r3
+	j_s.d	[blink]
+	bset.lo	r0, r0, 31
+
+	.align 4
+.LfoundNULL:
+#ifdef __BIG_ENDIAN__
+	swape	r4, r4
+	swape	r2, r2
+	swape	r3, r3
+#endif
+	;; Find null byte
+	ffs	r0, r4
+	bmsk	r2, r2, r0
+	bmsk	r3, r3, r0
+	swape	r2, r2
+	swape	r3, r3
+	;; make the return value
+	sub.f	r0, r2, r3
+	mov.hi	r0, 1
+	j_s.d	[blink]
+	bset.lo	r0, r0, 31
+
+	.align 4
+.Lcharloop:
+	ldb.ab	r2, [r0, 1]
+	ldb.ab	r3, [r1, 1]
+	nop
+	breq	r2, 0, .Lcmpend
+	breq	r2, r3, .Lcharloop
+
+	.align 4
+.Lcmpend:
+	j_s.d	[blink]
+	sub	r0, r2, r3
+END_CFI(strcmp)
diff --git a/arch/arc/lib/strcmp.S b/arch/arc/lib/strcmp.S
new file mode 100644
index 000000000..b20c98fb3
--- /dev/null
+++ b/arch/arc/lib/strcmp.S
@@ -0,0 +1,93 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+/* 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 <linux/linkage.h>
+
+ENTRY_CFI(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
+END_CFI(strcmp)
diff --git a/arch/arc/lib/strcpy-700.S b/arch/arc/lib/strcpy-700.S
new file mode 100644
index 000000000..6e2294d13
--- /dev/null
+++ b/arch/arc/lib/strcpy-700.S
@@ -0,0 +1,67 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+/* 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 <linux/linkage.h>
+
+ENTRY_CFI(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]
+END_CFI(strcpy)
diff --git a/arch/arc/lib/strlen.S b/arch/arc/lib/strlen.S
new file mode 100644
index 000000000..dae428ceb
--- /dev/null
+++ b/arch/arc/lib/strlen.S
@@ -0,0 +1,80 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#include <linux/linkage.h>
+
+ENTRY_CFI(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
+END_CFI(strlen)
diff --git a/arch/arc/mm/Makefile b/arch/arc/mm/Makefile
new file mode 100644
index 000000000..633a77336
--- /dev/null
+++ b/arch/arc/mm/Makefile
@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+#
+
+obj-y	:= extable.o ioremap.o dma.o fault.o init.o
+obj-y	+= tlb.o tlbex.o cache.o mmap.o
+obj-$(CONFIG_HIGHMEM)	+= highmem.o
diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c
new file mode 100644
index 000000000..7d2f93dc1
--- /dev/null
+++ b/arch/arc/mm/cache.c
@@ -0,0 +1,1094 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * ARC Cache Management
+ *
+ * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#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 <linux/pagemap.h>
+#include <asm/cacheflush.h>
+#include <asm/cachectl.h>
+#include <asm/setup.h>
+
+#ifdef CONFIG_ISA_ARCV2
+#define USE_RGN_FLSH	1
+#endif
+
+static int l2_line_sz;
+static int ioc_exists;
+int slc_enable = 1, ioc_enable = 1;
+unsigned long perip_base = ARC_UNCACHED_ADDR_SPACE; /* legacy value for boot */
+unsigned long perip_end = 0xFFFFFFFF; /* legacy value */
+
+static struct cpuinfo_arc_cache {
+	unsigned int sz_k, line_len, colors;
+} ic_info, dc_info, slc_info;
+
+void (*_cache_line_loop_ic_fn)(phys_addr_t paddr, unsigned long vaddr,
+			       unsigned long sz, const int op, const int full_page);
+
+void (*__dma_cache_wback_inv)(phys_addr_t start, unsigned long sz);
+void (*__dma_cache_inv)(phys_addr_t start, unsigned long sz);
+void (*__dma_cache_wback)(phys_addr_t start, unsigned long sz);
+
+static int read_decode_cache_bcr_arcv2(int c, char *buf, int len)
+{
+	struct cpuinfo_arc_cache *p_slc = &slc_info;
+	struct bcr_identity ident;
+	struct bcr_generic sbcr;
+	struct bcr_clust_cfg cbcr;
+	struct bcr_volatile vol;
+	int n = 0;
+
+	READ_BCR(ARC_REG_SLC_BCR, sbcr);
+	if (sbcr.ver) {
+		struct bcr_slc_cfg  slc_cfg;
+		READ_BCR(ARC_REG_SLC_CFG, slc_cfg);
+		p_slc->sz_k = 128 << slc_cfg.sz;
+		l2_line_sz = p_slc->line_len = (slc_cfg.lsz == 0) ? 128 : 64;
+		n += scnprintf(buf + n, len - n,
+			       "SLC\t\t: %uK, %uB Line%s\n",
+			       p_slc->sz_k, p_slc->line_len, IS_USED_RUN(slc_enable));
+	}
+
+	READ_BCR(ARC_REG_CLUSTER_BCR, cbcr);
+	if (cbcr.c) {
+		ioc_exists = 1;
+
+		/*
+		 * As for today we don't support both IOC and ZONE_HIGHMEM enabled
+		 * simultaneously. This happens because as of today IOC aperture covers
+		 * only ZONE_NORMAL (low mem) and any dma transactions outside this
+		 * region won't be HW coherent.
+		 * If we want to use both IOC and ZONE_HIGHMEM we can use
+		 * bounce_buffer to handle dma transactions to HIGHMEM.
+		 * Also it is possible to modify dma_direct cache ops or increase IOC
+		 * aperture size if we are planning to use HIGHMEM without PAE.
+		 */
+		if (IS_ENABLED(CONFIG_HIGHMEM) || is_pae40_enabled())
+			ioc_enable = 0;
+	} else {
+		ioc_enable = 0;
+	}
+
+	READ_BCR(AUX_IDENTITY, ident);
+
+	/* HS 2.0 didn't have AUX_VOL */
+	if (ident.family > 0x51) {
+		READ_BCR(AUX_VOL, vol);
+		perip_base = vol.start << 28;
+		/* HS 3.0 has limit and strict-ordering fields */
+		if (ident.family > 0x52)
+			perip_end = (vol.limit << 28) - 1;
+	}
+
+	n += scnprintf(buf + n, len - n, "Peripherals\t: %#lx%s%s\n",
+		       perip_base,
+		       IS_AVAIL3(ioc_exists, ioc_enable, ", IO-Coherency (per-device) "));
+
+	return n;
+}
+
+int arc_cache_mumbojumbo(int c, char *buf, int len)
+{
+	struct cpuinfo_arc_cache *p_ic = &ic_info, *p_dc = &dc_info;
+	struct bcr_cache ibcr, dbcr;
+	int vipt, assoc;
+	int n = 0;
+
+	READ_BCR(ARC_REG_IC_BCR, ibcr);
+	if (!ibcr.ver)
+		goto dc_chk;
+
+	if (is_isa_arcompact() && (ibcr.ver <= 3)) {
+		BUG_ON(ibcr.config != 3);
+		assoc = 2;		/* Fixed to 2w set assoc */
+	} else if (is_isa_arcv2() && (ibcr.ver >= 4)) {
+		assoc = 1 << ibcr.config;	/* 1,2,4,8 */
+	}
+
+	p_ic->line_len = 8 << ibcr.line_len;
+	p_ic->sz_k = 1 << (ibcr.sz - 1);
+	p_ic->colors = p_ic->sz_k/assoc/TO_KB(PAGE_SIZE);
+
+	n += scnprintf(buf + n, len - n,
+			"I-Cache\t\t: %uK, %dway/set, %uB Line, VIPT%s%s\n",
+			p_ic->sz_k, assoc, p_ic->line_len,
+			p_ic->colors > 1 ? " aliasing" : "",
+			IS_USED_CFG(CONFIG_ARC_HAS_ICACHE));
+
+dc_chk:
+	READ_BCR(ARC_REG_DC_BCR, dbcr);
+	if (!dbcr.ver)
+		goto slc_chk;
+
+	if (is_isa_arcompact() && (dbcr.ver <= 3)) {
+		BUG_ON(dbcr.config != 2);
+		vipt = 1;
+		assoc = 4;		/* Fixed to 4w set assoc */
+		p_dc->colors = p_dc->sz_k/assoc/TO_KB(PAGE_SIZE);
+	} else if (is_isa_arcv2() && (dbcr.ver >= 4)) {
+		vipt = 0;
+		assoc = 1 << dbcr.config;	/* 1,2,4,8 */
+		p_dc->colors = 1;		/* PIPT so can't VIPT alias */
+	}
+
+	p_dc->line_len = 16 << dbcr.line_len;
+	p_dc->sz_k = 1 << (dbcr.sz - 1);
+
+	n += scnprintf(buf + n, len - n,
+			"D-Cache\t\t: %uK, %dway/set, %uB Line, %s%s\n",
+			p_dc->sz_k, assoc, p_dc->line_len,
+			vipt ? "VIPT" : "PIPT",
+			IS_USED_CFG(CONFIG_ARC_HAS_DCACHE));
+
+slc_chk:
+	if (is_isa_arcv2())
+		n += read_decode_cache_bcr_arcv2(c, buf + n, len - n);
+
+	return n;
+}
+
+/*
+ * Line Operation on {I,D}-Cache
+ */
+
+#define OP_INV		0x1
+#define OP_FLUSH	0x2
+#define OP_FLUSH_N_INV	0x3
+#define OP_INV_IC	0x4
+
+/*
+ * Cache Flush programming model
+ *
+ * ARC700 MMUv3 I$ and D$ are both VIPT and can potentially alias.
+ * Programming model requires both paddr and vaddr irrespecive of aliasing
+ * considerations:
+ *  - vaddr in {I,D}C_IV?L
+ *  - paddr in {I,D}C_PTAG
+ *
+ * In HS38x (MMUv4), D$ is PIPT, I$ is VIPT and can still alias.
+ * Programming model is different for aliasing vs. non-aliasing I$
+ *  - D$ / Non-aliasing I$: only paddr in {I,D}C_IV?L
+ *  - Aliasing I$: same as ARC700 above (so MMUv3 routine used for MMUv4 I$)
+ *
+ *  - If PAE40 is enabled, independent of aliasing considerations, the higher
+ *    bits needs to be written into PTAG_HI
+ */
+
+static inline
+void __cache_line_loop_v3(phys_addr_t paddr, unsigned long vaddr,
+			  unsigned long sz, const int op, const int full_page)
+{
+	unsigned int aux_cmd, aux_tag;
+	int num_lines;
+
+	if (op == OP_INV_IC) {
+		aux_cmd = ARC_REG_IC_IVIL;
+		aux_tag = ARC_REG_IC_PTAG;
+	} else {
+		aux_cmd = op & OP_INV ? ARC_REG_DC_IVDL : ARC_REG_DC_FLDL;
+		aux_tag = ARC_REG_DC_PTAG;
+	}
+
+	/* Ensure we properly floor/ceil the non-line aligned/sized requests
+	 * and have @paddr - aligned to cache line and integral @num_lines.
+	 * This however can be avoided for page sized since:
+	 *  -@paddr will be cache-line aligned already (being page aligned)
+	 *  -@sz will be integral multiple of line size (being page sized).
+	 */
+	if (!full_page) {
+		sz += paddr & ~CACHE_LINE_MASK;
+		paddr &= CACHE_LINE_MASK;
+		vaddr &= CACHE_LINE_MASK;
+	}
+	num_lines = DIV_ROUND_UP(sz, L1_CACHE_BYTES);
+
+	/*
+	 * MMUv3, cache ops require paddr in PTAG reg
+	 * if V-P const for loop, PTAG can be written once outside loop
+	 */
+	if (full_page)
+		write_aux_reg(aux_tag, paddr);
+
+	/*
+	 * This is technically for MMU v4, using the MMU v3 programming model
+	 * Special work for HS38 aliasing I-cache configuration with PAE40
+	 *   - upper 8 bits of paddr need to be written into PTAG_HI
+	 *   - (and needs to be written before the lower 32 bits)
+	 * Note that PTAG_HI is hoisted outside the line loop
+	 */
+	if (is_pae40_enabled() && op == OP_INV_IC)
+		write_aux_reg(ARC_REG_IC_PTAG_HI, (u64)paddr >> 32);
+
+	while (num_lines-- > 0) {
+		if (!full_page) {
+			write_aux_reg(aux_tag, paddr);
+			paddr += L1_CACHE_BYTES;
+		}
+
+		write_aux_reg(aux_cmd, vaddr);
+		vaddr += L1_CACHE_BYTES;
+	}
+}
+
+#ifndef USE_RGN_FLSH
+
+/*
+ */
+static inline
+void __cache_line_loop_v4(phys_addr_t paddr, unsigned long vaddr,
+			  unsigned long sz, const int op, const int full_page)
+{
+	unsigned int aux_cmd;
+	int num_lines;
+
+	if (op == OP_INV_IC) {
+		aux_cmd = ARC_REG_IC_IVIL;
+	} else {
+		/* d$ cmd: INV (discard or wback-n-discard) OR FLUSH (wback) */
+		aux_cmd = op & OP_INV ? ARC_REG_DC_IVDL : ARC_REG_DC_FLDL;
+	}
+
+	/* Ensure we properly floor/ceil the non-line aligned/sized requests
+	 * and have @paddr - aligned to cache line and integral @num_lines.
+	 * This however can be avoided for page sized since:
+	 *  -@paddr will be cache-line aligned already (being page aligned)
+	 *  -@sz will be integral multiple of line size (being page sized).
+	 */
+	if (!full_page) {
+		sz += paddr & ~CACHE_LINE_MASK;
+		paddr &= CACHE_LINE_MASK;
+	}
+
+	num_lines = DIV_ROUND_UP(sz, L1_CACHE_BYTES);
+
+	/*
+	 * For HS38 PAE40 configuration
+	 *   - upper 8 bits of paddr need to be written into PTAG_HI
+	 *   - (and needs to be written before the lower 32 bits)
+	 */
+	if (is_pae40_enabled()) {
+		if (op == OP_INV_IC)
+			/*
+			 * Non aliasing I-cache in HS38,
+			 * aliasing I-cache handled in __cache_line_loop_v3()
+			 */
+			write_aux_reg(ARC_REG_IC_PTAG_HI, (u64)paddr >> 32);
+		else
+			write_aux_reg(ARC_REG_DC_PTAG_HI, (u64)paddr >> 32);
+	}
+
+	while (num_lines-- > 0) {
+		write_aux_reg(aux_cmd, paddr);
+		paddr += L1_CACHE_BYTES;
+	}
+}
+
+#else
+
+/*
+ * optimized flush operation which takes a region as opposed to iterating per line
+ */
+static inline
+void __cache_line_loop_v4(phys_addr_t paddr, unsigned long vaddr,
+			  unsigned long sz, const int op, const int full_page)
+{
+	unsigned int s, e;
+
+	/* Only for Non aliasing I-cache in HS38 */
+	if (op == OP_INV_IC) {
+		s = ARC_REG_IC_IVIR;
+		e = ARC_REG_IC_ENDR;
+	} else {
+		s = ARC_REG_DC_STARTR;
+		e = ARC_REG_DC_ENDR;
+	}
+
+	if (!full_page) {
+		/* for any leading gap between @paddr and start of cache line */
+		sz += paddr & ~CACHE_LINE_MASK;
+		paddr &= CACHE_LINE_MASK;
+
+		/*
+		 *  account for any trailing gap to end of cache line
+		 *  this is equivalent to DIV_ROUND_UP() in line ops above
+		 */
+		sz += L1_CACHE_BYTES - 1;
+	}
+
+	if (is_pae40_enabled()) {
+		/* TBD: check if crossing 4TB boundary */
+		if (op == OP_INV_IC)
+			write_aux_reg(ARC_REG_IC_PTAG_HI, (u64)paddr >> 32);
+		else
+			write_aux_reg(ARC_REG_DC_PTAG_HI, (u64)paddr >> 32);
+	}
+
+	/* ENDR needs to be set ahead of START */
+	write_aux_reg(e, paddr + sz);	/* ENDR is exclusive */
+	write_aux_reg(s, paddr);
+
+	/* caller waits on DC_CTRL.FS */
+}
+
+#endif
+
+#ifdef CONFIG_ARC_MMU_V3
+#define __cache_line_loop	__cache_line_loop_v3
+#else
+#define __cache_line_loop	__cache_line_loop_v4
+#endif
+
+#ifdef CONFIG_ARC_HAS_DCACHE
+
+/***************************************************************
+ * Machine specific helpers for Entire D-Cache or Per Line ops
+ */
+
+#ifndef USE_RGN_FLSH
+/*
+ * this version avoids extra read/write of DC_CTRL for flush or invalid ops
+ * in the non region flush regime (such as for ARCompact)
+ */
+static inline void __before_dc_op(const int op)
+{
+	if (op == OP_FLUSH_N_INV) {
+		/* Dcache provides 2 cmd: FLUSH or INV
+		 * INV in turn has sub-modes: DISCARD or FLUSH-BEFORE
+		 * flush-n-inv is achieved by INV cmd but with IM=1
+		 * So toggle INV sub-mode depending on op request and default
+		 */
+		const unsigned int ctl = ARC_REG_DC_CTRL;
+		write_aux_reg(ctl, read_aux_reg(ctl) | DC_CTRL_INV_MODE_FLUSH);
+	}
+}
+
+#else
+
+static inline void __before_dc_op(const int op)
+{
+	const unsigned int ctl = ARC_REG_DC_CTRL;
+	unsigned int val = read_aux_reg(ctl);
+
+	if (op == OP_FLUSH_N_INV) {
+		val |= DC_CTRL_INV_MODE_FLUSH;
+	}
+
+	if (op != OP_INV_IC) {
+		/*
+		 * Flush / Invalidate is provided by DC_CTRL.RNG_OP 0 or 1
+		 * combined Flush-n-invalidate uses DC_CTRL.IM = 1 set above
+		 */
+		val &= ~DC_CTRL_RGN_OP_MSK;
+		if (op & OP_INV)
+			val |= DC_CTRL_RGN_OP_INV;
+	}
+	write_aux_reg(ctl, val);
+}
+
+#endif
+
+
+static inline void __after_dc_op(const int op)
+{
+	if (op & OP_FLUSH) {
+		const unsigned int ctl = ARC_REG_DC_CTRL;
+		unsigned int reg;
+
+		/* flush / flush-n-inv both wait */
+		while ((reg = read_aux_reg(ctl)) & DC_CTRL_FLUSH_STATUS)
+			;
+
+		/* Switch back to default Invalidate mode */
+		if (op == OP_FLUSH_N_INV)
+			write_aux_reg(ctl, reg & ~DC_CTRL_INV_MODE_FLUSH);
+	}
+}
+
+/*
+ * Operation on Entire D-Cache
+ * @op = {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 op)
+{
+	int aux;
+
+	__before_dc_op(op);
+
+	if (op & 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);
+
+	__after_dc_op(op);
+}
+
+static inline void __dc_disable(void)
+{
+	const int r = ARC_REG_DC_CTRL;
+
+	__dc_entire_op(OP_FLUSH_N_INV);
+	write_aux_reg(r, read_aux_reg(r) | DC_CTRL_DIS);
+}
+
+static void __dc_enable(void)
+{
+	const int r = ARC_REG_DC_CTRL;
+
+	write_aux_reg(r, read_aux_reg(r) & ~DC_CTRL_DIS);
+}
+
+/* For kernel mappings cache operation: index is same as paddr */
+#define __dc_line_op_k(p, sz, op)	__dc_line_op(p, p, sz, op)
+
+/*
+ * D-Cache Line ops: Per Line INV (discard or wback+discard) or FLUSH (wback)
+ */
+static inline void __dc_line_op(phys_addr_t paddr, unsigned long vaddr,
+				unsigned long sz, const int op)
+{
+	const int full_page = __builtin_constant_p(sz) && sz == PAGE_SIZE;
+	unsigned long flags;
+
+	local_irq_save(flags);
+
+	__before_dc_op(op);
+
+	__cache_line_loop(paddr, vaddr, sz, op, full_page);
+
+	__after_dc_op(op);
+
+	local_irq_restore(flags);
+}
+
+#else
+
+#define __dc_entire_op(op)
+#define __dc_disable()
+#define __dc_enable()
+#define __dc_line_op(paddr, vaddr, sz, op)
+#define __dc_line_op_k(paddr, sz, op)
+
+#endif /* CONFIG_ARC_HAS_DCACHE */
+
+#ifdef CONFIG_ARC_HAS_ICACHE
+
+static inline void __ic_entire_inv(void)
+{
+	write_aux_reg(ARC_REG_IC_IVIC, 1);
+	read_aux_reg(ARC_REG_IC_CTRL);	/* blocks */
+}
+
+static inline void
+__ic_line_inv_vaddr_local(phys_addr_t paddr, unsigned long vaddr,
+			  unsigned long sz)
+{
+	const int full_page = __builtin_constant_p(sz) && sz == PAGE_SIZE;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	(*_cache_line_loop_ic_fn)(paddr, vaddr, sz, OP_INV_IC, full_page);
+	local_irq_restore(flags);
+}
+
+#ifndef CONFIG_SMP
+
+#define __ic_line_inv_vaddr(p, v, s)	__ic_line_inv_vaddr_local(p, v, s)
+
+#else
+
+struct ic_inv_args {
+	phys_addr_t paddr, vaddr;
+	int sz;
+};
+
+static void __ic_line_inv_vaddr_helper(void *info)
+{
+        struct ic_inv_args *ic_inv = info;
+
+        __ic_line_inv_vaddr_local(ic_inv->paddr, ic_inv->vaddr, ic_inv->sz);
+}
+
+static void __ic_line_inv_vaddr(phys_addr_t paddr, unsigned long vaddr,
+				unsigned long sz)
+{
+	struct ic_inv_args ic_inv = {
+		.paddr = paddr,
+		.vaddr = vaddr,
+		.sz    = sz
+	};
+
+	on_each_cpu(__ic_line_inv_vaddr_helper, &ic_inv, 1);
+}
+
+#endif	/* CONFIG_SMP */
+
+#else	/* !CONFIG_ARC_HAS_ICACHE */
+
+#define __ic_entire_inv()
+#define __ic_line_inv_vaddr(pstart, vstart, sz)
+
+#endif /* CONFIG_ARC_HAS_ICACHE */
+
+static noinline void slc_op_rgn(phys_addr_t paddr, unsigned long sz, const int op)
+{
+#ifdef CONFIG_ISA_ARCV2
+	/*
+	 * SLC is shared between all cores and concurrent aux operations from
+	 * multiple cores need to be serialized using a spinlock
+	 * A concurrent operation can be silently ignored and/or the old/new
+	 * operation can remain incomplete forever (lockup in SLC_CTRL_BUSY loop
+	 * below)
+	 */
+	static DEFINE_SPINLOCK(lock);
+	unsigned long flags;
+	unsigned int ctrl;
+	phys_addr_t end;
+
+	spin_lock_irqsave(&lock, flags);
+
+	/*
+	 * The Region Flush operation is specified by CTRL.RGN_OP[11..9]
+	 *  - b'000 (default) is Flush,
+	 *  - b'001 is Invalidate if CTRL.IM == 0
+	 *  - b'001 is Flush-n-Invalidate if CTRL.IM == 1
+	 */
+	ctrl = read_aux_reg(ARC_REG_SLC_CTRL);
+
+	/* Don't rely on default value of IM bit */
+	if (!(op & OP_FLUSH))		/* i.e. OP_INV */
+		ctrl &= ~SLC_CTRL_IM;	/* clear IM: Disable flush before Inv */
+	else
+		ctrl |= SLC_CTRL_IM;
+
+	if (op & OP_INV)
+		ctrl |= SLC_CTRL_RGN_OP_INV;	/* Inv or flush-n-inv */
+	else
+		ctrl &= ~SLC_CTRL_RGN_OP_INV;
+
+	write_aux_reg(ARC_REG_SLC_CTRL, ctrl);
+
+	/*
+	 * Lower bits are ignored, no need to clip
+	 * END needs to be setup before START (latter triggers the operation)
+	 * END can't be same as START, so add (l2_line_sz - 1) to sz
+	 */
+	end = paddr + sz + l2_line_sz - 1;
+	if (is_pae40_enabled())
+		write_aux_reg(ARC_REG_SLC_RGN_END1, upper_32_bits(end));
+
+	write_aux_reg(ARC_REG_SLC_RGN_END, lower_32_bits(end));
+
+	if (is_pae40_enabled())
+		write_aux_reg(ARC_REG_SLC_RGN_START1, upper_32_bits(paddr));
+
+	write_aux_reg(ARC_REG_SLC_RGN_START, lower_32_bits(paddr));
+
+	/* Make sure "busy" bit reports correct stataus, see STAR 9001165532 */
+	read_aux_reg(ARC_REG_SLC_CTRL);
+
+	while (read_aux_reg(ARC_REG_SLC_CTRL) & SLC_CTRL_BUSY);
+
+	spin_unlock_irqrestore(&lock, flags);
+#endif
+}
+
+static __maybe_unused noinline void slc_op_line(phys_addr_t paddr, unsigned long sz, const int op)
+{
+#ifdef CONFIG_ISA_ARCV2
+	/*
+	 * SLC is shared between all cores and concurrent aux operations from
+	 * multiple cores need to be serialized using a spinlock
+	 * A concurrent operation can be silently ignored and/or the old/new
+	 * operation can remain incomplete forever (lockup in SLC_CTRL_BUSY loop
+	 * below)
+	 */
+	static DEFINE_SPINLOCK(lock);
+
+	const unsigned long SLC_LINE_MASK = ~(l2_line_sz - 1);
+	unsigned int ctrl, cmd;
+	unsigned long flags;
+	int num_lines;
+
+	spin_lock_irqsave(&lock, flags);
+
+	ctrl = read_aux_reg(ARC_REG_SLC_CTRL);
+
+	/* Don't rely on default value of IM bit */
+	if (!(op & OP_FLUSH))		/* i.e. OP_INV */
+		ctrl &= ~SLC_CTRL_IM;	/* clear IM: Disable flush before Inv */
+	else
+		ctrl |= SLC_CTRL_IM;
+
+	write_aux_reg(ARC_REG_SLC_CTRL, ctrl);
+
+	cmd = op & OP_INV ? ARC_AUX_SLC_IVDL : ARC_AUX_SLC_FLDL;
+
+	sz += paddr & ~SLC_LINE_MASK;
+	paddr &= SLC_LINE_MASK;
+
+	num_lines = DIV_ROUND_UP(sz, l2_line_sz);
+
+	while (num_lines-- > 0) {
+		write_aux_reg(cmd, paddr);
+		paddr += l2_line_sz;
+	}
+
+	/* Make sure "busy" bit reports correct stataus, see STAR 9001165532 */
+	read_aux_reg(ARC_REG_SLC_CTRL);
+
+	while (read_aux_reg(ARC_REG_SLC_CTRL) & SLC_CTRL_BUSY);
+
+	spin_unlock_irqrestore(&lock, flags);
+#endif
+}
+
+#define slc_op(paddr, sz, op)	slc_op_rgn(paddr, sz, op)
+
+noinline static void slc_entire_op(const int op)
+{
+	unsigned int ctrl, r = ARC_REG_SLC_CTRL;
+
+	ctrl = read_aux_reg(r);
+
+	if (!(op & OP_FLUSH))		/* i.e. OP_INV */
+		ctrl &= ~SLC_CTRL_IM;	/* clear IM: Disable flush before Inv */
+	else
+		ctrl |= SLC_CTRL_IM;
+
+	write_aux_reg(r, ctrl);
+
+	if (op & OP_INV)	/* Inv or flush-n-inv use same cmd reg */
+		write_aux_reg(ARC_REG_SLC_INVALIDATE, 0x1);
+	else
+		write_aux_reg(ARC_REG_SLC_FLUSH, 0x1);
+
+	/* Make sure "busy" bit reports correct stataus, see STAR 9001165532 */
+	read_aux_reg(r);
+
+	/* Important to wait for flush to complete */
+	while (read_aux_reg(r) & SLC_CTRL_BUSY);
+}
+
+static inline void arc_slc_disable(void)
+{
+	const int r = ARC_REG_SLC_CTRL;
+
+	slc_entire_op(OP_FLUSH_N_INV);
+	write_aux_reg(r, read_aux_reg(r) | SLC_CTRL_DIS);
+}
+
+static inline void arc_slc_enable(void)
+{
+	const int r = ARC_REG_SLC_CTRL;
+
+	write_aux_reg(r, read_aux_reg(r) & ~SLC_CTRL_DIS);
+}
+
+/***********************************************************
+ * Exported APIs
+ */
+
+void flush_dcache_folio(struct folio *folio)
+{
+	clear_bit(PG_dc_clean, &folio->flags.f);
+	return;
+}
+EXPORT_SYMBOL(flush_dcache_folio);
+
+void flush_dcache_page(struct page *page)
+{
+	return flush_dcache_folio(page_folio(page));
+}
+EXPORT_SYMBOL(flush_dcache_page);
+
+/*
+ * DMA ops for systems with L1 cache only
+ * Make memory coherent with L1 cache by flushing/invalidating L1 lines
+ */
+static void __dma_cache_wback_inv_l1(phys_addr_t start, unsigned long sz)
+{
+	__dc_line_op_k(start, sz, OP_FLUSH_N_INV);
+}
+
+static void __dma_cache_inv_l1(phys_addr_t start, unsigned long sz)
+{
+	__dc_line_op_k(start, sz, OP_INV);
+}
+
+static void __dma_cache_wback_l1(phys_addr_t start, unsigned long sz)
+{
+	__dc_line_op_k(start, sz, OP_FLUSH);
+}
+
+/*
+ * DMA ops for systems with both L1 and L2 caches, but without IOC
+ * Both L1 and L2 lines need to be explicitly flushed/invalidated
+ */
+static void __dma_cache_wback_inv_slc(phys_addr_t start, unsigned long sz)
+{
+	__dc_line_op_k(start, sz, OP_FLUSH_N_INV);
+	slc_op(start, sz, OP_FLUSH_N_INV);
+}
+
+static void __dma_cache_inv_slc(phys_addr_t start, unsigned long sz)
+{
+	__dc_line_op_k(start, sz, OP_INV);
+	slc_op(start, sz, OP_INV);
+}
+
+static void __dma_cache_wback_slc(phys_addr_t start, unsigned long sz)
+{
+	__dc_line_op_k(start, sz, OP_FLUSH);
+	slc_op(start, sz, OP_FLUSH);
+}
+
+/*
+ * Exported DMA API
+ */
+void dma_cache_wback_inv(phys_addr_t start, unsigned long sz)
+{
+	__dma_cache_wback_inv(start, sz);
+}
+EXPORT_SYMBOL(dma_cache_wback_inv);
+
+void dma_cache_inv(phys_addr_t start, unsigned long sz)
+{
+	__dma_cache_inv(start, sz);
+}
+EXPORT_SYMBOL(dma_cache_inv);
+
+void dma_cache_wback(phys_addr_t start, unsigned long sz)
+{
+	__dma_cache_wback(start, sz);
+}
+EXPORT_SYMBOL(dma_cache_wback);
+
+/*
+ * This is API for making I/D Caches consistent when modifying
+ * kernel code (loadable modules, kprobes, kgdb...)
+ * 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;
+
+	WARN(kstart < TASK_SIZE, "%s() can't handle user vaddr", __func__);
+
+	/* 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)) {
+		/*
+		 * The 2nd arg despite being paddr will be used to index icache
+		 * This is OK since no alternate virtual mappings will exist
+		 * given the callers for this case: kprobe/kgdb in built-in
+		 * kernel code only.
+		 */
+		__sync_icache_dcache(kstart, kstart, kend - kstart);
+		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) {
+		unsigned int off, sz;
+		unsigned long phy, pfn;
+
+		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);
+		__sync_icache_dcache(phy, kstart, sz);
+		kstart += sz;
+		tot_sz -= sz;
+	}
+}
+EXPORT_SYMBOL(flush_icache_range);
+
+/*
+ * General purpose helper to make I and D cache lines consistent.
+ * @paddr is phy addr of region
+ * @vaddr is typically user vaddr (breakpoint) or kernel vaddr (vmalloc)
+ *    However in one instance, when called by kprobe (for a breakpt in
+ *    builtin kernel code) @vaddr will be paddr only, meaning CDU operation will
+ *    use a paddr to index the cache (despite VIPT). This is fine since a
+ *    builtin kernel page will not have any virtual mappings.
+ *    kprobe on loadable module will be kernel vaddr.
+ */
+void __sync_icache_dcache(phys_addr_t paddr, unsigned long vaddr, int len)
+{
+	__dc_line_op(paddr, vaddr, len, OP_FLUSH_N_INV);
+	__ic_line_inv_vaddr(paddr, vaddr, len);
+}
+
+/* wrapper to compile time eliminate alignment checks in flush loop */
+void __inv_icache_pages(phys_addr_t paddr, unsigned long vaddr, unsigned nr)
+{
+	__ic_line_inv_vaddr(paddr, vaddr, nr * PAGE_SIZE);
+}
+
+/*
+ * wrapper to clearout kernel or userspace mappings of a page
+ * For kernel mappings @vaddr == @paddr
+ */
+void __flush_dcache_pages(phys_addr_t paddr, unsigned long vaddr, unsigned nr)
+{
+	__dc_line_op(paddr, vaddr & PAGE_MASK, nr * PAGE_SIZE, OP_FLUSH_N_INV);
+}
+
+noinline void flush_cache_all(void)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+
+	__ic_entire_inv();
+	__dc_entire_op(OP_FLUSH_N_INV);
+
+	local_irq_restore(flags);
+
+}
+
+void copy_user_highpage(struct page *to, struct page *from,
+	unsigned long u_vaddr, struct vm_area_struct *vma)
+{
+	struct folio *src = page_folio(from);
+	struct folio *dst = page_folio(to);
+	void *kfrom = kmap_atomic(from);
+	void *kto = kmap_atomic(to);
+
+	copy_page(kto, kfrom);
+
+	clear_bit(PG_dc_clean, &dst->flags.f);
+	clear_bit(PG_dc_clean, &src->flags.f);
+
+	kunmap_atomic(kto);
+	kunmap_atomic(kfrom);
+}
+
+void clear_user_page(void *to, unsigned long u_vaddr, struct page *page)
+{
+	struct folio *folio = page_folio(page);
+	clear_page(to);
+	clear_bit(PG_dc_clean, &folio->flags.f);
+}
+EXPORT_SYMBOL(clear_user_page);
+
+/**********************************************************************
+ * 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;
+}
+
+/*
+ * IO-Coherency (IOC) setup rules:
+ *
+ * 1. Needs to be at system level, so only once by Master core
+ *    Non-Masters need not be accessing caches at that time
+ *    - They are either HALT_ON_RESET and kick started much later or
+ *    - if run on reset, need to ensure that arc_platform_smp_wait_to_boot()
+ *      doesn't perturb caches or coherency unit
+ *
+ * 2. caches (L1 and SLC) need to be purged (flush+inv) before setting up IOC,
+ *    otherwise any straggler data might behave strangely post IOC enabling
+ *
+ * 3. All Caches need to be disabled when setting up IOC to elide any in-flight
+ *    Coherency transactions
+ */
+static noinline void __init arc_ioc_setup(void)
+{
+	unsigned int ioc_base, mem_sz;
+
+	/*
+	 * If IOC was already enabled (due to bootloader) it technically needs to
+	 * be reconfigured with aperture base,size corresponding to Linux memory map
+	 * which will certainly be different than uboot's. But disabling and
+	 * reenabling IOC when DMA might be potentially active is tricky business.
+	 * To avoid random memory issues later, just panic here and ask user to
+	 * upgrade bootloader to one which doesn't enable IOC
+	 */
+	if (read_aux_reg(ARC_REG_IO_COH_ENABLE) & ARC_IO_COH_ENABLE_BIT)
+		panic("IOC already enabled, please upgrade bootloader!\n");
+
+	if (!ioc_enable)
+		return;
+
+	/* Flush + invalidate + disable L1 dcache */
+	__dc_disable();
+
+	/* Flush + invalidate SLC */
+	if (read_aux_reg(ARC_REG_SLC_BCR))
+		slc_entire_op(OP_FLUSH_N_INV);
+
+	/*
+	 * currently IOC Aperture covers entire DDR
+	 * TBD: fix for PGU + 1GB of low mem
+	 * TBD: fix for PAE
+	 */
+	mem_sz = arc_get_mem_sz();
+
+	if (!is_power_of_2(mem_sz) || mem_sz < 4096)
+		panic("IOC Aperture size must be power of 2 larger than 4KB");
+
+	/*
+	 * IOC Aperture size decoded as 2 ^ (SIZE + 2) KB,
+	 * so setting 0x11 implies 512MB, 0x12 implies 1GB...
+	 */
+	write_aux_reg(ARC_REG_IO_COH_AP0_SIZE, order_base_2(mem_sz >> 10) - 2);
+
+	/* for now assume kernel base is start of IOC aperture */
+	ioc_base = CONFIG_LINUX_RAM_BASE;
+
+	if (ioc_base % mem_sz != 0)
+		panic("IOC Aperture start must be aligned to the size of the aperture");
+
+	write_aux_reg(ARC_REG_IO_COH_AP0_BASE, ioc_base >> 12);
+	write_aux_reg(ARC_REG_IO_COH_PARTIAL, ARC_IO_COH_PARTIAL_BIT);
+	write_aux_reg(ARC_REG_IO_COH_ENABLE, ARC_IO_COH_ENABLE_BIT);
+
+	/* Re-enable L1 dcache */
+	__dc_enable();
+}
+
+/*
+ * Cache related boot time checks/setups only needed on master CPU:
+ *  - Geometry checks (kernel build and hardware agree: e.g. L1_CACHE_BYTES)
+ *    Assume SMP only, so all cores will have same cache config. A check on
+ *    one core suffices for all
+ *  - IOC setup / dma callbacks only need to be done once
+ */
+static noinline void __init arc_cache_init_master(void)
+{
+	if (IS_ENABLED(CONFIG_ARC_HAS_ICACHE)) {
+		struct cpuinfo_arc_cache *ic = &ic_info;
+
+		if (!ic->line_len)
+			panic("cache support enabled but non-existent cache\n");
+
+		if (ic->line_len != L1_CACHE_BYTES)
+			panic("ICache line [%d] != kernel Config [%d]",
+			      ic->line_len, L1_CACHE_BYTES);
+
+		/*
+		 * In MMU v4 (HS38x) the aliasing icache config uses IVIL/PTAG
+		 * pair to provide vaddr/paddr respectively, just as in MMU v3
+		 */
+		if (is_isa_arcv2() && ic->colors > 1)
+			_cache_line_loop_ic_fn = __cache_line_loop_v3;
+		else
+			_cache_line_loop_ic_fn = __cache_line_loop;
+	}
+
+	if (IS_ENABLED(CONFIG_ARC_HAS_DCACHE)) {
+		struct cpuinfo_arc_cache *dc = &dc_info;
+
+		if (!dc->line_len)
+			panic("cache support enabled but non-existent cache\n");
+
+		if (dc->line_len != L1_CACHE_BYTES)
+			panic("DCache line [%d] != kernel Config [%d]",
+			      dc->line_len, L1_CACHE_BYTES);
+
+		/* check for D-Cache aliasing on ARCompact: ARCv2 has PIPT */
+		if (is_isa_arcompact() && dc->colors > 1) {
+			panic("Aliasing VIPT cache not supported\n");
+		}
+	}
+
+	/*
+	 * Check that SMP_CACHE_BYTES (and hence ARCH_DMA_MINALIGN) is larger
+	 * or equal to any cache line length.
+	 */
+	BUILD_BUG_ON_MSG(L1_CACHE_BYTES > SMP_CACHE_BYTES,
+			 "SMP_CACHE_BYTES must be >= any cache line length");
+	if (is_isa_arcv2() && (l2_line_sz > SMP_CACHE_BYTES))
+		panic("L2 Cache line [%d] > kernel Config [%d]\n",
+		      l2_line_sz, SMP_CACHE_BYTES);
+
+	/* Note that SLC disable not formally supported till HS 3.0 */
+	if (is_isa_arcv2() && l2_line_sz && !slc_enable)
+		arc_slc_disable();
+
+	if (is_isa_arcv2() && ioc_exists)
+		arc_ioc_setup();
+
+	if (is_isa_arcv2() && l2_line_sz && slc_enable) {
+		__dma_cache_wback_inv = __dma_cache_wback_inv_slc;
+		__dma_cache_inv = __dma_cache_inv_slc;
+		__dma_cache_wback = __dma_cache_wback_slc;
+	} else {
+		__dma_cache_wback_inv = __dma_cache_wback_inv_l1;
+		__dma_cache_inv = __dma_cache_inv_l1;
+		__dma_cache_wback = __dma_cache_wback_l1;
+	}
+	/*
+	 * In case of IOC (say IOC+SLC case), pointers above could still be set
+	 * but end up not being relevant as the first function in chain is not
+	 * called at all for devices using coherent DMA.
+	 *     arch_sync_dma_for_cpu() -> dma_cache_*() -> __dma_cache_*()
+	 */
+}
+
+void __ref arc_cache_init(void)
+{
+	unsigned int __maybe_unused cpu = smp_processor_id();
+
+	if (!cpu)
+		arc_cache_init_master();
+
+	/*
+	 * In PAE regime, TLB and cache maintenance ops take wider addresses
+	 * And even if PAE is not enabled in kernel, the upper 32-bits still need
+	 * to be zeroed to keep the ops sane.
+	 * As an optimization for more common !PAE enabled case, zero them out
+	 * once at init, rather than checking/setting to 0 for every runtime op
+	 */
+	if (is_isa_arcv2() && pae40_exist_but_not_enab()) {
+
+		if (IS_ENABLED(CONFIG_ARC_HAS_ICACHE))
+			write_aux_reg(ARC_REG_IC_PTAG_HI, 0);
+
+		if (IS_ENABLED(CONFIG_ARC_HAS_DCACHE))
+			write_aux_reg(ARC_REG_DC_PTAG_HI, 0);
+
+		if (l2_line_sz) {
+			write_aux_reg(ARC_REG_SLC_RGN_END1, 0);
+			write_aux_reg(ARC_REG_SLC_RGN_START1, 0);
+		}
+	}
+}
diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c
new file mode 100644
index 000000000..9b9adb02b
--- /dev/null
+++ b/arch/arc/mm/dma.c
@@ -0,0 +1,105 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#include <linux/dma-map-ops.h>
+#include <asm/cache.h>
+#include <asm/cacheflush.h>
+
+/*
+ * ARCH specific callbacks for generic noncoherent DMA ops
+ *  - hardware IOC not available (or "dma-coherent" not set for device in DT)
+ *  - But still handle both coherent and non-coherent requests from caller
+ *
+ * For DMA coherent hardware (IOC) generic code suffices
+ */
+
+void arch_dma_prep_coherent(struct page *page, size_t size)
+{
+	/*
+	 * Evict any existing L1 and/or L2 lines for the backing page
+	 * in case it was used earlier as a normal "cached" page.
+	 * Yeah this bit us - STAR 9000898266
+	 *
+	 * Although core does call flush_cache_vmap(), it gets kvaddr hence
+	 * can't be used to efficiently flush L1 and/or L2 which need paddr
+	 * Currently flush_cache_vmap nukes the L1 cache completely which
+	 * will be optimized as a separate commit
+	 */
+	dma_cache_wback_inv(page_to_phys(page), size);
+}
+
+/*
+ * Cache operations depending on function and direction argument, inspired by
+ * https://lore.kernel.org/lkml/20180518175004.GF17671@n2100.armlinux.org.uk
+ * "dma_sync_*_for_cpu and direction=TO_DEVICE (was Re: [PATCH 02/20]
+ * dma-mapping: provide a generic dma-noncoherent implementation)"
+ *
+ *          |   map          ==  for_device     |   unmap     ==  for_cpu
+ *          |----------------------------------------------------------------
+ * TO_DEV   |   writeback        writeback      |   none          none
+ * FROM_DEV |   invalidate       invalidate     |   invalidate*   invalidate*
+ * BIDIR    |   writeback+inv    writeback+inv  |   invalidate    invalidate
+ *
+ *     [*] needed for CPU speculative prefetches
+ *
+ * NOTE: we don't check the validity of direction argument as it is done in
+ * upper layer functions (in include/linux/dma-mapping.h)
+ */
+
+void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
+{
+	switch (dir) {
+	case DMA_TO_DEVICE:
+		dma_cache_wback(paddr, size);
+		break;
+
+	case DMA_FROM_DEVICE:
+		dma_cache_inv(paddr, size);
+		break;
+
+	case DMA_BIDIRECTIONAL:
+		dma_cache_wback_inv(paddr, size);
+		break;
+
+	default:
+		break;
+	}
+}
+
+void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
+{
+	switch (dir) {
+	case DMA_TO_DEVICE:
+		break;
+
+	/* FROM_DEVICE invalidate needed if speculative CPU prefetch only */
+	case DMA_FROM_DEVICE:
+	case DMA_BIDIRECTIONAL:
+		dma_cache_inv(paddr, size);
+		break;
+
+	default:
+		break;
+	}
+}
+
+/*
+ * Plug in direct dma map ops.
+ */
+void arch_setup_dma_ops(struct device *dev, bool coherent)
+{
+	/*
+	 * IOC hardware snoops all DMA traffic keeping the caches consistent
+	 * with memory - eliding need for any explicit cache maintenance of
+	 * DMA buffers.
+	 */
+	if (is_isa_arcv2() && ioc_enable && coherent)
+		dev_set_dma_coherent(dev);
+
+	dev_info(dev, "use %scoherent DMA ops\n",
+		 dev_dma_coherent(dev) ? "" : "non");
+}
diff --git a/arch/arc/mm/extable.c b/arch/arc/mm/extable.c
new file mode 100644
index 000000000..88fa3a4d4
--- /dev/null
+++ b/arch/arc/mm/extable.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * Borrowed heavily from MIPS
+ */
+
+#include <linux/export.h>
+#include <linux/extable.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;
+}
diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c
new file mode 100644
index 000000000..95119a5e7
--- /dev/null
+++ b/arch/arc/mm/fault.c
@@ -0,0 +1,193 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Page Fault Handling for ARC (TLB Miss / ProtV)
+ *
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#include <linux/signal.h>
+#include <linux/interrupt.h>
+#include <linux/sched/signal.h>
+#include <linux/errno.h>
+#include <linux/ptrace.h>
+#include <linux/uaccess.h>
+#include <linux/kdebug.h>
+#include <linux/perf_event.h>
+#include <linux/mm_types.h>
+#include <asm/entry.h>
+#include <asm/mmu.h>
+
+/*
+ * kernel virtual address is required to implement vmalloc/pkmap/fixmap
+ * Refer to asm/processor.h for System Memory Map
+ *
+ * It simply copies the PMD entry (pointer to 2nd level page table or hugepage)
+ * from swapper pgdir to task pgdir. The 2nd level table/page is thus shared
+ */
+noinline static int handle_kernel_vaddr_fault(unsigned long address)
+{
+	/*
+	 * Synchronize this task's top level page-table
+	 * with the 'reference' page table.
+	 */
+	pgd_t *pgd, *pgd_k;
+	p4d_t *p4d, *p4d_k;
+	pud_t *pud, *pud_k;
+	pmd_t *pmd, *pmd_k;
+
+	pgd = pgd_offset(current->active_mm, address);
+	pgd_k = pgd_offset_k(address);
+
+	if (pgd_none (*pgd_k))
+		goto bad_area;
+	if (!pgd_present(*pgd))
+		set_pgd(pgd, *pgd_k);
+
+	p4d = p4d_offset(pgd, address);
+	p4d_k = p4d_offset(pgd_k, address);
+	if (p4d_none(*p4d_k))
+		goto bad_area;
+	if (!p4d_present(*p4d))
+		set_p4d(p4d, *p4d_k);
+
+	pud = pud_offset(p4d, address);
+	pud_k = pud_offset(p4d_k, address);
+	if (pud_none(*pud_k))
+		goto bad_area;
+	if (!pud_present(*pud))
+		set_pud(pud, *pud_k);
+
+	pmd = pmd_offset(pud, address);
+	pmd_k = pmd_offset(pud_k, address);
+	if (pmd_none(*pmd_k))
+		goto bad_area;
+	if (!pmd_present(*pmd))
+		set_pmd(pmd, *pmd_k);
+
+	/* XXX: create the TLB entry here */
+	return 0;
+
+bad_area:
+	return 1;
+}
+
+void do_page_fault(unsigned long address, struct pt_regs *regs)
+{
+	struct vm_area_struct *vma = NULL;
+	struct task_struct *tsk = current;
+	struct mm_struct *mm = tsk->mm;
+	int sig, si_code = SEGV_MAPERR;
+	unsigned int write = 0, exec = 0, mask;
+	vm_fault_t fault = VM_FAULT_SIGSEGV;	/* handle_mm_fault() output */
+	unsigned int flags;			/* handle_mm_fault() input */
+
+	/*
+	 * 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 && !user_mode(regs)) {
+		if (unlikely(handle_kernel_vaddr_fault(address)))
+			goto no_context;
+		else
+			return;
+	}
+
+	/*
+	 * If we're in an interrupt or have no user
+	 * context, we must not take the fault..
+	 */
+	if (faulthandler_disabled() || !mm)
+		goto no_context;
+
+	if (regs->ecr.cause & ECR_C_PROTV_STORE)	/* ST/EX */
+		write = 1;
+	else if ((regs->ecr.vec == ECR_V_PROTV) &&
+	         (regs->ecr.cause == ECR_C_PROTV_INST_FETCH))
+		exec = 1;
+
+	flags = FAULT_FLAG_DEFAULT;
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
+	if (write)
+		flags |= FAULT_FLAG_WRITE;
+
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
+retry:
+	vma = lock_mm_and_find_vma(mm, address, regs);
+	if (!vma)
+		goto bad_area_nosemaphore;
+
+	/*
+	 * vm_area is good, now check permissions for this memory access
+	 */
+	mask = VM_READ;
+	if (write)
+		mask = VM_WRITE;
+	if (exec)
+		mask = VM_EXEC;
+
+	if (!(vma->vm_flags & mask)) {
+		si_code = SEGV_ACCERR;
+		goto bad_area;
+	}
+
+	fault = handle_mm_fault(vma, address, flags, regs);
+
+	/* Quick path to respond to signals */
+	if (fault_signal_pending(fault, regs)) {
+		if (!user_mode(regs))
+			goto no_context;
+		return;
+	}
+
+	/* The fault is fully completed (including releasing mmap lock) */
+	if (fault & VM_FAULT_COMPLETED)
+		return;
+
+	/*
+	 * Fault retry nuances, mmap_lock already relinquished by core mm
+	 */
+	if (unlikely(fault & VM_FAULT_RETRY)) {
+		flags |= FAULT_FLAG_TRIED;
+		goto retry;
+	}
+
+bad_area:
+	mmap_read_unlock(mm);
+
+bad_area_nosemaphore:
+	/*
+	 * Major/minor page fault accounting
+	 * (in case of retry we only land here once)
+	 */
+	if (likely(!(fault & VM_FAULT_ERROR)))
+		/* Normal return path: fault Handled Gracefully */
+		return;
+
+	if (!user_mode(regs))
+		goto no_context;
+
+	if (fault & VM_FAULT_OOM) {
+		pagefault_out_of_memory();
+		return;
+	}
+
+	if (fault & VM_FAULT_SIGBUS) {
+		sig = SIGBUS;
+		si_code = BUS_ADRERR;
+	}
+	else {
+		sig = SIGSEGV;
+	}
+
+	tsk->thread.fault_address = address;
+	force_sig_fault(sig, si_code, (void __user *)address);
+	return;
+
+no_context:
+	if (fixup_exception(regs))
+		return;
+
+	die("Oops", regs, address);
+}
diff --git a/arch/arc/mm/highmem.c b/arch/arc/mm/highmem.c
new file mode 100644
index 000000000..c79912a6b
--- /dev/null
+++ b/arch/arc/mm/highmem.c
@@ -0,0 +1,73 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2015 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#include <linux/memblock.h>
+#include <linux/export.h>
+#include <linux/highmem.h>
+#include <linux/pgtable.h>
+#include <asm/processor.h>
+#include <asm/pgalloc.h>
+#include <asm/tlbflush.h>
+
+/*
+ * HIGHMEM API:
+ *
+ * kmap() API provides sleep semantics hence referred to as "permanent maps"
+ * It allows mapping LAST_PKMAP pages, using @last_pkmap_nr as the cursor
+ * for book-keeping
+ *
+ * kmap_atomic() can't sleep (calls pagefault_disable()), thus it provides
+ * shortlived ala "temporary mappings" which historically were implemented as
+ * fixmaps (compile time addr etc). Their book-keeping is done per cpu.
+ *
+ *	Both these facts combined (preemption disabled and per-cpu allocation)
+ *	means the total number of concurrent fixmaps will be limited to max
+ *	such allocations in a single control path. Thus KM_TYPE_NR (another
+ *	historic relic) is a small'ish number which caps max percpu fixmaps
+ *
+ * ARC HIGHMEM Details
+ *
+ * - the kernel vaddr space from 0x7z to 0x8z (currently used by vmalloc/module)
+ *   is now shared between vmalloc and kmap (non overlapping though)
+ *
+ * - Both fixmap/pkmap use a dedicated page table each, hooked up to swapper PGD
+ *   This means each only has 1 PGDIR_SIZE worth of kvaddr mappings, which means
+ *   2M of kvaddr space for typical config (8K page and 11:8:13 traversal split)
+ *
+ * - The fixed KMAP slots for kmap_local/atomic() require KM_MAX_IDX slots per
+ *   CPU. So the number of CPUs sharing a single PTE page is limited.
+ *
+ * - pkmap being preemptible, in theory could do with more than 256 concurrent
+ *   mappings. However, generic pkmap code: map_new_virtual(), doesn't traverse
+ *   the PGD and only works with a single page table @pkmap_page_table, hence
+ *   sets the limit
+ */
+
+extern pte_t * pkmap_page_table;
+
+static noinline pte_t * __init alloc_kmap_pgtable(unsigned long kvaddr)
+{
+	pmd_t *pmd_k = pmd_off_k(kvaddr);
+	pte_t *pte_k;
+
+	pte_k = (pte_t *)memblock_alloc_low(PAGE_SIZE, PAGE_SIZE);
+	if (!pte_k)
+		panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
+		      __func__, PAGE_SIZE, PAGE_SIZE);
+
+	pmd_populate_kernel(&init_mm, pmd_k, pte_k);
+	return pte_k;
+}
+
+void __init kmap_init(void)
+{
+	/* Due to recursive include hell, we can't do this in processor.h */
+	BUILD_BUG_ON(PAGE_OFFSET < (VMALLOC_END + FIXMAP_SIZE + PKMAP_SIZE));
+	BUILD_BUG_ON(LAST_PKMAP > PTRS_PER_PTE);
+	BUILD_BUG_ON(FIX_KMAP_SLOTS > PTRS_PER_PTE);
+
+	pkmap_page_table = alloc_kmap_pgtable(PKMAP_BASE);
+	alloc_kmap_pgtable(FIXMAP_BASE);
+}
diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c
new file mode 100644
index 000000000..d6b5c27a0
--- /dev/null
+++ b/arch/arc/mm/init.c
@@ -0,0 +1,178 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/memblock.h>
+#ifdef CONFIG_BLK_DEV_INITRD
+#include <linux/initrd.h>
+#endif
+#include <linux/of_fdt.h>
+#include <linux/swap.h>
+#include <linux/module.h>
+#include <linux/highmem.h>
+#include <asm/page.h>
+#include <asm/sections.h>
+#include <asm/setup.h>
+#include <asm/arcregs.h>
+
+pgd_t swapper_pg_dir[PTRS_PER_PGD] __aligned(PAGE_SIZE);
+
+static const unsigned long low_mem_start = CONFIG_LINUX_RAM_BASE;
+static unsigned long low_mem_sz;
+
+#ifdef CONFIG_HIGHMEM
+static unsigned long min_high_pfn, max_high_pfn;
+static phys_addr_t high_mem_start;
+static phys_addr_t high_mem_sz;
+unsigned long arch_pfn_offset;
+EXPORT_SYMBOL(arch_pfn_offset);
+#endif
+
+long __init arc_get_mem_sz(void)
+{
+	return low_mem_sz;
+}
+
+/* User can over-ride above with "mem=nnn[KkMm]" in cmdline */
+static int __init setup_mem_sz(char *str)
+{
+	low_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(low_mem_sz));
+
+	return 0;
+}
+early_param("mem", setup_mem_sz);
+
+void __init early_init_dt_add_memory_arch(u64 base, u64 size)
+{
+	int in_use = 0;
+
+	if (!low_mem_sz) {
+		if (base != low_mem_start)
+			panic("CONFIG_LINUX_RAM_BASE != DT memory { }");
+
+		low_mem_sz = size;
+		in_use = 1;
+		memblock_add_node(base, size, 0, MEMBLOCK_NONE);
+	} else {
+#ifdef CONFIG_HIGHMEM
+		high_mem_start = base;
+		high_mem_sz = size;
+		in_use = 1;
+		memblock_add_node(base, size, 1, MEMBLOCK_NONE);
+		memblock_reserve(base, size);
+#endif
+	}
+
+	pr_info("Memory @ %llx [%lldM] %s\n",
+		base, TO_MB(size), !in_use ? "Not used":"");
+}
+
+void __init arch_zone_limits_init(unsigned long *max_zone_pfn)
+{
+	/*----------------- node/zones setup --------------------------*/
+	max_zone_pfn[ZONE_NORMAL] = max_low_pfn;
+
+#ifdef CONFIG_HIGHMEM
+	/*
+	 * max_high_pfn should be ok here for both HIGHMEM and HIGHMEM+PAE.
+	 * For HIGHMEM without PAE max_high_pfn should be less than
+	 * min_low_pfn to guarantee that these two regions don't overlap.
+	 * For PAE case highmem is greater than lowmem, so it is natural
+	 * to use max_high_pfn.
+	 *
+	 * In both cases, holes should be handled by pfn_valid().
+	 */
+	max_zone_pfn[ZONE_HIGHMEM] = max_high_pfn;
+#endif
+}
+
+/*
+ * 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)
+{
+	setup_initial_init_mm(_text, _etext, _edata, _end);
+
+	/* first page of system - kernel .vector starts here */
+	min_low_pfn = virt_to_pfn((void *)CONFIG_LINUX_RAM_BASE);
+
+	/* Last usable page of low mem */
+	max_low_pfn = max_pfn = PFN_DOWN(low_mem_start + low_mem_sz);
+
+	/*------------- bootmem allocator setup -----------------------*/
+
+	/*
+	 * seed the bootmem allocator after any DT memory node parsing or
+	 * "mem=xxx" cmdline overrides have potentially updated @arc_mem_sz
+	 *
+	 * Only low mem is added, otherwise we have crashes when allocating
+	 * mem_map[] itself. NO_BOOTMEM allocates mem_map[] at the end of
+	 * avail memory, ending in highmem with a > 32-bit address. However
+	 * it then tries to memset it with a truncaed 32-bit handle, causing
+	 * the crash
+	 */
+
+	memblock_reserve(CONFIG_LINUX_LINK_BASE,
+			 __pa(_end) - CONFIG_LINUX_LINK_BASE);
+
+#ifdef CONFIG_BLK_DEV_INITRD
+	if (phys_initrd_size) {
+		memblock_reserve(phys_initrd_start, phys_initrd_size);
+		initrd_start = (unsigned long)__va(phys_initrd_start);
+		initrd_end = initrd_start + phys_initrd_size;
+	}
+#endif
+
+	early_init_fdt_reserve_self();
+	early_init_fdt_scan_reserved_mem();
+
+	memblock_dump_all();
+
+#ifdef CONFIG_HIGHMEM
+	/*
+	 * On ARC (w/o PAE) HIGHMEM addresses are actually smaller (0 based)
+	 * than addresses in normal aka low memory (0x8000_0000 based).
+	 * Even with PAE, the huge peripheral space hole would waste a lot of
+	 * mem with single contiguous mem_map[].
+	 * Thus when HIGHMEM on ARC is enabled the memory map corresponding
+	 * to the hole is freed and ARC specific version of pfn_valid()
+	 * handles the hole in the memory map.
+	 */
+
+	min_high_pfn = PFN_DOWN(high_mem_start);
+	max_high_pfn = PFN_DOWN(high_mem_start + high_mem_sz);
+
+	arch_pfn_offset = min(min_low_pfn, min_high_pfn);
+	kmap_init();
+#endif /* CONFIG_HIGHMEM */
+}
+
+void __init arch_mm_preinit(void)
+{
+#ifdef CONFIG_HIGHMEM
+	memblock_phys_free(high_mem_start, high_mem_sz);
+#endif
+
+	BUILD_BUG_ON((PTRS_PER_PGD * sizeof(pgd_t)) > PAGE_SIZE);
+	BUILD_BUG_ON((PTRS_PER_PUD * sizeof(pud_t)) > PAGE_SIZE);
+	BUILD_BUG_ON((PTRS_PER_PMD * sizeof(pmd_t)) > PAGE_SIZE);
+	BUILD_BUG_ON((PTRS_PER_PTE * sizeof(pte_t)) > PAGE_SIZE);
+}
+
+#ifdef CONFIG_HIGHMEM
+int pfn_valid(unsigned long pfn)
+{
+	return (pfn >= min_high_pfn && pfn <= max_high_pfn) ||
+		(pfn >= min_low_pfn && pfn <= max_low_pfn);
+}
+EXPORT_SYMBOL(pfn_valid);
+#endif
diff --git a/arch/arc/mm/ioremap.c b/arch/arc/mm/ioremap.c
new file mode 100644
index 000000000..fd8897a0e
--- /dev/null
+++ b/arch/arc/mm/ioremap.c
@@ -0,0 +1,62 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#include <linux/vmalloc.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/io.h>
+#include <linux/mm.h>
+#include <linux/cache.h>
+
+static inline bool arc_uncached_addr_space(phys_addr_t paddr)
+{
+	if (is_isa_arcompact()) {
+		if (paddr >= ARC_UNCACHED_ADDR_SPACE)
+			return true;
+	} else if (paddr >= perip_base && paddr <= perip_end) {
+		return true;
+	}
+
+	return false;
+}
+
+void __iomem *ioremap(phys_addr_t paddr, unsigned long size)
+{
+	/*
+	 * If the region is h/w uncached, MMU mapping can be elided as optim
+	 * The cast to u32 is fine as this region can only be inside 4GB
+	 */
+	if (arc_uncached_addr_space(paddr))
+		return (void __iomem *)(u32)paddr;
+
+	return ioremap_prot(paddr, size,
+			    pgprot_noncached(PAGE_KERNEL));
+}
+EXPORT_SYMBOL(ioremap);
+
+/*
+ * ioremap with access flags
+ * Cache semantics wise it is same as ioremap - "forced" uncached.
+ * However unlike 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, size_t size,
+			   pgprot_t prot)
+{
+	/* force uncached */
+	return generic_ioremap_prot(paddr, size, pgprot_noncached(prot));
+}
+EXPORT_SYMBOL(ioremap_prot);
+
+void iounmap(volatile void __iomem *addr)
+{
+	/* weird double cast to handle phys_addr_t > 32 bits */
+	if (arc_uncached_addr_space((phys_addr_t)(u32)addr))
+		return;
+
+	generic_iounmap(addr);
+}
+EXPORT_SYMBOL(iounmap);
diff --git a/arch/arc/mm/mmap.c b/arch/arc/mm/mmap.c
new file mode 100644
index 000000000..2185afe8d
--- /dev/null
+++ b/arch/arc/mm/mmap.c
@@ -0,0 +1,80 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * ARC700 mmap
+ *
+ * (started from arm version - for VIPT alias handling)
+ *
+ * Copyright (C) 2013 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/sched/mm.h>
+
+#include <asm/cacheflush.h>
+
+/*
+ * Ensure that shared mappings are correctly aligned to
+ * avoid aliasing issues with VIPT caches.
+ * We need to ensure that
+ * a specific page of an object is always mapped at a multiple of
+ * SHMLBA bytes.
+ */
+unsigned long
+arch_get_unmapped_area(struct file *filp, unsigned long addr,
+		unsigned long len, unsigned long pgoff,
+		unsigned long flags, vm_flags_t vm_flags)
+{
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma;
+	struct vm_unmapped_area_info info = {};
+
+	/*
+	 * We enforce the MAP_FIXED case.
+	 */
+	if (flags & MAP_FIXED) {
+		if (flags & MAP_SHARED &&
+		    (addr - (pgoff << PAGE_SHIFT)) & (SHMLBA - 1))
+			return -EINVAL;
+		return addr;
+	}
+
+	if (len > TASK_SIZE)
+		return -ENOMEM;
+
+	if (addr) {
+		addr = PAGE_ALIGN(addr);
+
+		vma = find_vma(mm, addr);
+		if (TASK_SIZE - len >= addr &&
+		    (!vma || addr + len <= vm_start_gap(vma)))
+			return addr;
+	}
+
+	info.length = len;
+	info.low_limit = mm->mmap_base;
+	info.high_limit = TASK_SIZE;
+	info.align_offset = pgoff << PAGE_SHIFT;
+	return vm_unmapped_area(&info);
+}
+
+static const pgprot_t protection_map[16] = {
+	[VM_NONE]					= PAGE_U_NONE,
+	[VM_READ]					= PAGE_U_R,
+	[VM_WRITE]					= PAGE_U_R,
+	[VM_WRITE | VM_READ]				= PAGE_U_R,
+	[VM_EXEC]					= PAGE_U_X_R,
+	[VM_EXEC | VM_READ]				= PAGE_U_X_R,
+	[VM_EXEC | VM_WRITE]				= PAGE_U_X_R,
+	[VM_EXEC | VM_WRITE | VM_READ]			= PAGE_U_X_R,
+	[VM_SHARED]					= PAGE_U_NONE,
+	[VM_SHARED | VM_READ]				= PAGE_U_R,
+	[VM_SHARED | VM_WRITE]				= PAGE_U_W_R,
+	[VM_SHARED | VM_WRITE | VM_READ]		= PAGE_U_W_R,
+	[VM_SHARED | VM_EXEC]				= PAGE_U_X_R,
+	[VM_SHARED | VM_EXEC | VM_READ]			= PAGE_U_X_R,
+	[VM_SHARED | VM_EXEC | VM_WRITE]		= PAGE_U_X_W_R,
+	[VM_SHARED | VM_EXEC | VM_WRITE | VM_READ]	= PAGE_U_X_W_R
+};
+DECLARE_VM_GET_PAGE_PROT
diff --git a/arch/arc/mm/tlb.c b/arch/arc/mm/tlb.c
new file mode 100644
index 000000000..ed6915ba7
--- /dev/null
+++ b/arch/arc/mm/tlb.c
@@ -0,0 +1,755 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * TLB Management (flush/create/diagnostics) for MMUv3 and MMUv4
+ *
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/bug.h>
+#include <linux/mm_types.h>
+
+#include <asm/arcregs.h>
+#include <asm/setup.h>
+#include <asm/mmu_context.h>
+#include <asm/mmu.h>
+
+/* A copy of the ASID from the PID reg is kept in asid_cache */
+DEFINE_PER_CPU(unsigned int, asid_cache) = MM_CTXT_FIRST_CYCLE;
+
+static struct cpuinfo_arc_mmu {
+	unsigned int ver, pg_sz_k, s_pg_sz_m, pae, sets, ways;
+} mmuinfo;
+
+/*
+ * Utility Routine to erase a J-TLB entry
+ * Caller needs to setup Index Reg (manually or via getIndex)
+ */
+static inline void __tlb_entry_erase(void)
+{
+	write_aux_reg(ARC_REG_TLBPD1, 0);
+
+	if (is_pae40_enabled())
+		write_aux_reg(ARC_REG_TLBPD1HI, 0);
+
+	write_aux_reg(ARC_REG_TLBPD0, 0);
+	write_aux_reg(ARC_REG_TLBCOMMAND, TLBWrite);
+}
+
+static void utlb_invalidate(void)
+{
+	write_aux_reg(ARC_REG_TLBCOMMAND, TLBIVUTLB);
+}
+
+#ifdef CONFIG_ARC_MMU_V3
+
+static inline unsigned int tlb_entry_lkup(unsigned long vaddr_n_asid)
+{
+	unsigned int idx;
+
+	write_aux_reg(ARC_REG_TLBPD0, vaddr_n_asid);
+
+	write_aux_reg(ARC_REG_TLBCOMMAND, TLBProbe);
+	idx = read_aux_reg(ARC_REG_TLBINDEX);
+
+	return idx;
+}
+
+static void tlb_entry_erase(unsigned int vaddr_n_asid)
+{
+	unsigned int idx;
+
+	/* Locate the TLB entry for this vaddr + ASID */
+	idx = tlb_entry_lkup(vaddr_n_asid);
+
+	/* No error means entry found, zero it out */
+	if (likely(!(idx & TLB_LKUP_ERR))) {
+		__tlb_entry_erase();
+	} else {
+		/* Duplicate entry error */
+		WARN(idx == TLB_DUP_ERR, "Probe returned Dup PD for %x\n",
+					   vaddr_n_asid);
+	}
+}
+
+static void tlb_entry_insert(unsigned int pd0, phys_addr_t pd1)
+{
+	unsigned int idx;
+
+	/*
+	 * First verify if entry for this vaddr+ASID already exists
+	 * This also sets up PD0 (vaddr, ASID..) for final commit
+	 */
+	idx = tlb_entry_lkup(pd0);
+
+	/*
+	 * 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);
+
+	/* setup the other half of TLB entry (pfn, rwx..) */
+	write_aux_reg(ARC_REG_TLBPD1, pd1);
+
+	/*
+	 * Commit the Entry to MMU
+	 * It doesn't 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);
+}
+
+#else	/* MMUv4 */
+
+static void tlb_entry_erase(unsigned int vaddr_n_asid)
+{
+	write_aux_reg(ARC_REG_TLBPD0, vaddr_n_asid | _PAGE_PRESENT);
+	write_aux_reg(ARC_REG_TLBCOMMAND, TLBDeleteEntry);
+}
+
+static void tlb_entry_insert(unsigned int pd0, phys_addr_t pd1)
+{
+	write_aux_reg(ARC_REG_TLBPD0, pd0);
+
+	if (!is_pae40_enabled()) {
+		write_aux_reg(ARC_REG_TLBPD1, pd1);
+	} else {
+		write_aux_reg(ARC_REG_TLBPD1, pd1 & 0xFFFFFFFF);
+		write_aux_reg(ARC_REG_TLBPD1HI, (u64)pd1 >> 32);
+	}
+
+	write_aux_reg(ARC_REG_TLBCOMMAND, TLBInsertEntry);
+}
+
+#endif
+
+/*
+ * Un-conditionally (without lookup) erase the entire MMU contents
+ */
+
+noinline void local_flush_tlb_all(void)
+{
+	struct cpuinfo_arc_mmu *mmu = &mmuinfo;
+	unsigned long flags;
+	unsigned int entry;
+	int num_tlb = mmu->sets * mmu->ways;
+
+	local_irq_save(flags);
+
+	/* Load PD0 and PD1 with template for a Blank Entry */
+	write_aux_reg(ARC_REG_TLBPD1, 0);
+
+	if (is_pae40_enabled())
+		write_aux_reg(ARC_REG_TLBPD1HI, 0);
+
+	write_aux_reg(ARC_REG_TLBPD0, 0);
+
+	for (entry = 0; entry < num_tlb; entry++) {
+		/* write this entry to the TLB */
+		write_aux_reg(ARC_REG_TLBINDEX, entry);
+		write_aux_reg(ARC_REG_TLBCOMMAND, TLBWriteNI);
+	}
+
+	if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) {
+		const int stlb_idx = 0x800;
+
+		/* Blank sTLB entry */
+		write_aux_reg(ARC_REG_TLBPD0, _PAGE_HW_SZ);
+
+		for (entry = stlb_idx; entry < stlb_idx + 16; entry++) {
+			write_aux_reg(ARC_REG_TLBINDEX, entry);
+			write_aux_reg(ARC_REG_TLBCOMMAND, TLBWriteNI);
+		}
+	}
+
+	utlb_invalidate();
+
+	local_irq_restore(flags);
+}
+
+/*
+ * Flush the entire 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;
+
+	/*
+	 * - Move to a new ASID, but only if the mm is still wired in
+	 *   (Android Binder ended up calling this for vma->mm != tsk->mm,
+	 *    causing h/w - s/w ASID to get out of sync)
+	 * - Also get_new_mmu_context() new implementation allocates a new
+	 *   ASID only if it is not allocated already - so unallocate first
+	 */
+	destroy_context(mm);
+	if (current->mm == mm)
+		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 explicitly
+ */
+void local_flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
+			   unsigned long end)
+{
+	const unsigned int cpu = smp_processor_id();
+	unsigned long flags;
+
+	/* If range @start to @end is more than 32 TLB entries deep,
+	 * it's 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);
+
+	if (asid_mm(vma->vm_mm, cpu) != MM_CTXT_NO_ASID) {
+		while (start < end) {
+			tlb_entry_erase(start | hw_pid(vma->vm_mm, cpu));
+			start += PAGE_SIZE;
+		}
+	}
+
+	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;
+	}
+
+	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)
+{
+	const unsigned int cpu = smp_processor_id();
+	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 (asid_mm(vma->vm_mm, cpu) != MM_CTXT_NO_ASID) {
+		tlb_entry_erase((page & PAGE_MASK) | hw_pid(vma->vm_mm, cpu));
+	}
+
+	local_irq_restore(flags);
+}
+
+#ifdef CONFIG_SMP
+
+struct tlb_args {
+	struct vm_area_struct *ta_vma;
+	unsigned long ta_start;
+	unsigned long ta_end;
+};
+
+static inline void ipi_flush_tlb_page(void *arg)
+{
+	struct tlb_args *ta = arg;
+
+	local_flush_tlb_page(ta->ta_vma, ta->ta_start);
+}
+
+static inline void ipi_flush_tlb_range(void *arg)
+{
+	struct tlb_args *ta = arg;
+
+	local_flush_tlb_range(ta->ta_vma, ta->ta_start, ta->ta_end);
+}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline void ipi_flush_pmd_tlb_range(void *arg)
+{
+	struct tlb_args *ta = arg;
+
+	local_flush_pmd_tlb_range(ta->ta_vma, ta->ta_start, ta->ta_end);
+}
+#endif
+
+static inline void ipi_flush_tlb_kernel_range(void *arg)
+{
+	struct tlb_args *ta = (struct tlb_args *)arg;
+
+	local_flush_tlb_kernel_range(ta->ta_start, ta->ta_end);
+}
+
+void flush_tlb_all(void)
+{
+	on_each_cpu((smp_call_func_t)local_flush_tlb_all, NULL, 1);
+}
+
+void flush_tlb_mm(struct mm_struct *mm)
+{
+	on_each_cpu_mask(mm_cpumask(mm), (smp_call_func_t)local_flush_tlb_mm,
+			 mm, 1);
+}
+
+void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
+{
+	struct tlb_args ta = {
+		.ta_vma = vma,
+		.ta_start = uaddr
+	};
+
+	on_each_cpu_mask(mm_cpumask(vma->vm_mm), ipi_flush_tlb_page, &ta, 1);
+}
+
+void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
+		     unsigned long end)
+{
+	struct tlb_args ta = {
+		.ta_vma = vma,
+		.ta_start = start,
+		.ta_end = end
+	};
+
+	on_each_cpu_mask(mm_cpumask(vma->vm_mm), ipi_flush_tlb_range, &ta, 1);
+}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
+			 unsigned long end)
+{
+	struct tlb_args ta = {
+		.ta_vma = vma,
+		.ta_start = start,
+		.ta_end = end
+	};
+
+	on_each_cpu_mask(mm_cpumask(vma->vm_mm), ipi_flush_pmd_tlb_range, &ta, 1);
+}
+#endif
+
+void flush_tlb_kernel_range(unsigned long start, unsigned long end)
+{
+	struct tlb_args ta = {
+		.ta_start = start,
+		.ta_end = end
+	};
+
+	on_each_cpu(ipi_flush_tlb_kernel_range, &ta, 1);
+}
+#endif
+
+/*
+ * Routine to create a TLB entry
+ */
+static void create_tlb(struct vm_area_struct *vma, unsigned long vaddr, pte_t *ptep)
+{
+	unsigned long flags;
+	unsigned int asid_or_sasid, rwx;
+	unsigned long pd0;
+	phys_addr_t pd1;
+
+	/*
+	 * 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.
+	 * -More importantly it makes this handler inconsistent with fast-path
+	 *  TLB Refill handler which always deals with "current"
+	 *
+	 * Let's 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);
+
+	vaddr &= PAGE_MASK;
+
+	/* update this PTE credentials */
+	pte_val(*ptep) |= (_PAGE_PRESENT | _PAGE_ACCESSED);
+
+	/* Create HW TLB(PD0,PD1) from PTE  */
+
+	/* ASID for this task */
+	asid_or_sasid = read_aux_reg(ARC_REG_PID) & 0xff;
+
+	pd0 = vaddr | asid_or_sasid | (pte_val(*ptep) & PTE_BITS_IN_PD0);
+
+	/*
+	 * ARC MMU provides fully orthogonal access bits for K/U mode,
+	 * however Linux only saves 1 set to save PTE real-estate
+	 * Here we convert 3 PTE bits into 6 MMU bits:
+	 * -Kernel only entries have Kr Kw Kx 0 0 0
+	 * -User entries have mirrored K and U bits
+	 */
+	rwx = pte_val(*ptep) & PTE_BITS_RWX;
+
+	if (pte_val(*ptep) & _PAGE_GLOBAL)
+		rwx <<= 3;		/* r w x => Kr Kw Kx 0 0 0 */
+	else
+		rwx |= (rwx << 3);	/* r w x => Kr Kw Kx Ur Uw Ux */
+
+	pd1 = rwx | (pte_val(*ptep) & PTE_BITS_NON_RWX_IN_PD1);
+
+	tlb_entry_insert(pd0, pd1);
+
+	local_irq_restore(flags);
+}
+
+/*
+ * Called at the end of pagefault, for a userspace mapped page
+ *  -pre-install the corresponding TLB entry into MMU
+ *  -Finalize the delayed D-cache flush of kernel mapping of page due to
+ *  	flush_dcache_page(), copy_user_page()
+ *
+ * Note that flush (when done) involves both WBACK - so physical page is
+ * in sync as well as INV - so any non-congruent aliases don't remain
+ */
+void update_mmu_cache_range(struct vm_fault *vmf, struct vm_area_struct *vma,
+		unsigned long vaddr_unaligned, pte_t *ptep, unsigned int nr)
+{
+	unsigned long vaddr = vaddr_unaligned & PAGE_MASK;
+	phys_addr_t paddr = pte_val(*ptep) & PAGE_MASK_PHYS;
+	struct page *page = pfn_to_page(pte_pfn(*ptep));
+
+	create_tlb(vma, vaddr, ptep);
+
+	if (page == ZERO_PAGE(0))
+		return;
+
+	/*
+	 * For executable pages, since icache doesn't snoop dcache, any
+	 * dirty K-mapping of a code page needs to be wback+inv so that
+	 * icache fetch by userspace sees code correctly.
+	 */
+	if (vma->vm_flags & VM_EXEC) {
+		struct folio *folio = page_folio(page);
+		int dirty = !test_and_set_bit(PG_dc_clean, &folio->flags.f);
+		if (dirty) {
+			unsigned long offset = offset_in_folio(folio, paddr);
+			nr = folio_nr_pages(folio);
+			paddr -= offset;
+			vaddr -= offset;
+			/* wback + inv dcache lines (K-mapping) */
+			__flush_dcache_pages(paddr, paddr, nr);
+
+			/* invalidate any existing icache lines (U-mapping) */
+			if (vma->vm_flags & VM_EXEC)
+				__inv_icache_pages(paddr, vaddr, nr);
+		}
+	}
+}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+
+/*
+ * MMUv4 in HS38x cores supports Super Pages which are basis for Linux THP
+ * support.
+ *
+ * Normal and Super pages can co-exist (ofcourse not overlap) in TLB with a
+ * new bit "SZ" in TLB page descriptor to distinguish between them.
+ * Super Page size is configurable in hardware (4K to 16M), but fixed once
+ * RTL builds.
+ *
+ * The exact THP size a Linux configuration will support is a function of:
+ *  - MMU page size (typical 8K, RTL fixed)
+ *  - software page walker address split between PGD:PTE:PFN (typical
+ *    11:8:13, but can be changed with 1 line)
+ * So for above default, THP size supported is 8K * (2^8) = 2M
+ *
+ * Default Page Walker is 2 levels, PGD:PTE:PFN, which in THP regime
+ * reduces to 1 level (as PTE is folded into PGD and canonically referred
+ * to as PMD).
+ * Thus THP PMD accessors are implemented in terms of PTE (just like sparc)
+ */
+
+void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr,
+				 pmd_t *pmd)
+{
+	pte_t pte = __pte(pmd_val(*pmd));
+	update_mmu_cache_range(NULL, vma, addr, &pte, HPAGE_PMD_NR);
+}
+
+void local_flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
+			       unsigned long end)
+{
+	unsigned int cpu;
+	unsigned long flags;
+
+	local_irq_save(flags);
+
+	cpu = smp_processor_id();
+
+	if (likely(asid_mm(vma->vm_mm, cpu) != MM_CTXT_NO_ASID)) {
+		unsigned int asid = hw_pid(vma->vm_mm, cpu);
+
+		/* No need to loop here: this will always be for 1 Huge Page */
+		tlb_entry_erase(start | _PAGE_HW_SZ | asid);
+	}
+
+	local_irq_restore(flags);
+}
+
+#endif
+
+/* Read the Cache Build Configuration Registers, Decode them and save into
+ * the cpuinfo structure for later use.
+ * No Validation is done here, simply read/convert the BCRs
+ */
+int arc_mmu_mumbojumbo(int c, char *buf, int len)
+{
+	struct cpuinfo_arc_mmu *mmu = &mmuinfo;
+	unsigned int bcr, u_dtlb, u_itlb, sasid;
+	struct bcr_mmu_3 *mmu3;
+	struct bcr_mmu_4 *mmu4;
+	char super_pg[64] = "";
+	int n = 0;
+
+	bcr = read_aux_reg(ARC_REG_MMU_BCR);
+	mmu->ver = (bcr >> 24);
+
+	if (is_isa_arcompact() && mmu->ver == 3) {
+		mmu3 = (struct bcr_mmu_3 *)&bcr;
+		mmu->pg_sz_k = 1 << (mmu3->pg_sz - 1);
+		mmu->sets = 1 << mmu3->sets;
+		mmu->ways = 1 << mmu3->ways;
+		u_dtlb = mmu3->u_dtlb;
+		u_itlb = mmu3->u_itlb;
+		sasid = mmu3->sasid;
+	} else {
+		mmu4 = (struct bcr_mmu_4 *)&bcr;
+		mmu->pg_sz_k = 1 << (mmu4->sz0 - 1);
+		mmu->s_pg_sz_m = 1 << (mmu4->sz1 - 11);
+		mmu->sets = 64 << mmu4->n_entry;
+		mmu->ways = mmu4->n_ways * 2;
+		u_dtlb = mmu4->u_dtlb * 4;
+		u_itlb = mmu4->u_itlb * 4;
+		sasid = mmu4->sasid;
+		mmu->pae = mmu4->pae;
+	}
+
+	if (mmu->s_pg_sz_m)
+		scnprintf(super_pg, 64, "/%dM%s",
+			  mmu->s_pg_sz_m,
+			  IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) ? " (THP enabled)":"");
+
+	n += scnprintf(buf + n, len - n,
+		      "MMU [v%x]\t: %dk%s, swalk %d lvl, JTLB %dx%d, uDTLB %d, uITLB %d%s%s%s\n",
+		       mmu->ver, mmu->pg_sz_k, super_pg, CONFIG_PGTABLE_LEVELS,
+		       mmu->sets, mmu->ways,
+		       u_dtlb, u_itlb,
+		       IS_AVAIL1(sasid, ", SASID"),
+		       IS_AVAIL2(mmu->pae, ", PAE40 ", CONFIG_ARC_HAS_PAE40));
+
+	return n;
+}
+
+int pae40_exist_but_not_enab(void)
+{
+	return mmuinfo.pae && !is_pae40_enabled();
+}
+
+void arc_mmu_init(void)
+{
+	struct cpuinfo_arc_mmu *mmu = &mmuinfo;
+	int compat = 0;
+
+	/*
+	 * Can't be done in processor.h due to header include dependencies
+	 */
+	BUILD_BUG_ON(!IS_ALIGNED((CONFIG_ARC_KVADDR_SIZE << 20), PMD_SIZE));
+
+	/*
+	 * stack top size sanity check,
+	 * Can't be done in processor.h due to header include dependencies
+	 */
+	BUILD_BUG_ON(!IS_ALIGNED(STACK_TOP, PMD_SIZE));
+
+	/*
+	 * Ensure that MMU features assumed by kernel exist in hardware.
+	 *  - For older ARC700 cpus, only v3 supported
+	 *  - For HS cpus, v4 was baseline and v5 is backwards compatible
+	 *    (will run older software).
+	 */
+	if (is_isa_arcompact() && mmu->ver == 3)
+		compat = 1;
+	else if (is_isa_arcv2() && mmu->ver >= 4)
+		compat = 1;
+
+	if (!compat)
+		panic("MMU ver %d doesn't match kernel built for\n", mmu->ver);
+
+	if (mmu->pg_sz_k != TO_KB(PAGE_SIZE))
+		panic("MMU pg size != PAGE_SIZE (%luk)\n", TO_KB(PAGE_SIZE));
+
+	if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) &&
+	    mmu->s_pg_sz_m != TO_MB(HPAGE_PMD_SIZE))
+		panic("MMU Super pg size != Linux HPAGE_PMD_SIZE (%luM)\n",
+		      (unsigned long)TO_MB(HPAGE_PMD_SIZE));
+
+	if (IS_ENABLED(CONFIG_ARC_HAS_PAE40) && !mmu->pae)
+		panic("Hardware doesn't support PAE40\n");
+
+	/* Enable the MMU with ASID 0 */
+	mmu_setup_asid(NULL, 0);
+
+	/* cache the pgd pointer in MMU SCRATCH reg (ARCv2 only) */
+	mmu_setup_pgd(NULL, swapper_pg_dir);
+
+	if (pae40_exist_but_not_enab())
+		write_aux_reg(ARC_REG_TLBPD1HI, 0);
+}
+
+/*
+ * 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_silent; /* Be silent abt it or complain (default) */
+
+void do_tlb_overlap_fault(unsigned long cause, unsigned long address,
+			  struct pt_regs *regs)
+{
+	struct cpuinfo_arc_mmu *mmu = &mmuinfo;
+	unsigned long flags;
+	int set, n_ways = mmu->ways;
+
+	n_ways = min(n_ways, 4);
+	BUG_ON(mmu->ways > 4);
+
+	local_irq_save(flags);
+
+	/* loop thru all sets of TLB */
+	for (set = 0; set < mmu->sets; set++) {
+
+		int is_valid, way;
+		unsigned int pd0[4];
+
+		/* read out all the ways of current set */
+		for (way = 0, is_valid = 0; way < n_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);
+			is_valid |= pd0[way] & _PAGE_PRESENT;
+			pd0[way] &= PAGE_MASK;
+		}
+
+		/* 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 < n_ways - 1; way++) {
+
+			int n;
+
+			if (!pd0[way])
+				continue;
+
+			for (n = way + 1; n < n_ways; n++) {
+				if (pd0[way] != pd0[n])
+					continue;
+
+				if (!dup_pd_silent)
+					pr_info("Dup TLB PD0 %08x @ set %d ways %d,%d\n",
+						pd0[way], set, way, n);
+
+				/*
+				 * clear entry @way and not @n.
+				 * This is critical to our optimised loop
+				 */
+				pd0[way] = 0;
+				write_aux_reg(ARC_REG_TLBINDEX,
+						SET_WAY_TO_IDX(mmu, set, way));
+				__tlb_entry_erase();
+			}
+		}
+	}
+
+	local_irq_restore(flags);
+}
diff --git a/arch/arc/mm/tlbex.S b/arch/arc/mm/tlbex.S
new file mode 100644
index 000000000..dc65e87a5
--- /dev/null
+++ b/arch/arc/mm/tlbex.S
@@ -0,0 +1,378 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * TLB Exception Handling for ARC
+ *
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * Vineetg: April 2011 :
+ *  -MMU v1: moved out legacy code into a separate 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 committing a D-TLB
+ *   entry, so that it doesn't knock out its 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 apiece 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
+ */
+
+#include <linux/linkage.h>
+#include <linux/pgtable.h>
+#include <asm/entry.h>
+#include <asm/mmu.h>
+#include <asm/arcregs.h>
+#include <asm/cache.h>
+#include <asm/processor.h>
+
+#ifdef CONFIG_ISA_ARCOMPACT
+;-----------------------------------------------------------------
+; 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....
+;--------------------------------------------------------------------------
+
+; scratch memory to save [r0-r3] used to code TLB refill Handler
+ARCFP_DATA ex_saved_reg1
+	.align 1 << L1_CACHE_SHIFT
+	.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
+
+.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,
+	asl 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]
+.endm
+
+.macro TLBMISS_RESTORE_REGS
+#ifdef CONFIG_SMP
+	GET_CPU_ID  r0			; get to per cpu scratch mem
+	asl 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
+
+#else	/* ARCv2 */
+
+.macro TLBMISS_FREEUP_REGS
+#ifdef CONFIG_ARC_HAS_LL64
+	std   r0, [sp, -16]
+	std   r2, [sp, -8]
+#else
+	PUSH  r0
+	PUSH  r1
+	PUSH  r2
+	PUSH  r3
+#endif
+.endm
+
+.macro TLBMISS_RESTORE_REGS
+#ifdef CONFIG_ARC_HAS_LL64
+	ldd   r0, [sp, -16]
+	ldd   r2, [sp, -8]
+#else
+	POP   r3
+	POP   r2
+	POP   r1
+	POP   r0
+#endif
+.endm
+
+#endif
+
+;============================================================================
+;TLB Miss handling Code
+;============================================================================
+
+#ifndef PMD_SHIFT
+#define PMD_SHIFT PUD_SHIFT
+#endif
+
+#ifndef PUD_SHIFT
+#define PUD_SHIFT PGDIR_SHIFT
+#endif
+
+;-----------------------------------------------------------------------------
+; 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]
+
+#ifdef CONFIG_ISA_ARCV2
+	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   r3, [r1, r0]            ; PGD entry corresp to faulting addr
+	tst	r3, r3
+	bz	do_slow_path_pf         ; if no Page Table, do page fault
+
+#if CONFIG_PGTABLE_LEVELS > 3
+	lsr     r0, r2, PUD_SHIFT	; Bits for indexing into PUD
+	and	r0, r0, (PTRS_PER_PUD - 1)
+	ld.as	r1, [r3, r0]		; PMD entry
+	tst	r1, r1
+	bz	do_slow_path_pf
+	mov	r3, r1
+#endif
+
+#if CONFIG_PGTABLE_LEVELS > 2
+	lsr     r0, r2, PMD_SHIFT	; Bits for indexing into PMD
+	and	r0, r0, (PTRS_PER_PMD - 1)
+	ld.as	r1, [r3, r0]		; PMD entry
+	tst	r1, r1
+	bz	do_slow_path_pf
+	mov	r3, r1
+#endif
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	and.f	0, r3, _PAGE_HW_SZ	; Is this Huge PMD (thp)
+	add2.nz	r1, r1, r0
+	bnz.d	2f		; YES: PGD == PMD has THP PTE: stop pgd walk
+	mov.nz	r0, r3
+
+#endif
+	and	r1, r3, PAGE_MASK
+
+	; 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 * 4)
+
+#ifdef CONFIG_ARC_HAS_PAE40
+#define PTE_SIZE_LOG	3	/* 8 == 2 ^ 3 */
+#else
+#define PTE_SIZE_LOG	2	/* 4 == 2 ^ 2 */
+#endif
+
+	; multiply in step (3) above avoided by shifting lesser in step (1)
+	lsr     r0, r2, ( PAGE_SHIFT - PTE_SIZE_LOG )
+	and     r0, r0, ( (PTRS_PER_PTE - 1) << PTE_SIZE_LOG )
+	ld.aw   r0, [r1, r0]            ; r0: PTE (lower word only for PAE40)
+					; r1: PTE ptr
+
+2:
+
+.endm
+
+;-----------------------------------------------------------------
+; Convert Linux PTE entry into TLB entry
+; A one-word PTE entry is programmed as two-word TLB Entry [PD0:PD1] in mmu
+;    (for PAE40, two-words PTE, while three-word TLB Entry [PD0:PD1:PD1HI])
+; IN: r0 = PTE, r1 = ptr to PTE
+
+.macro CONV_PTE_TO_TLB
+	and    r3, r0, PTE_BITS_RWX	;          r  w  x
+	asl    r2, r3, 3		; Kr Kw Kx 0  0  0 (GLOBAL, kernel only)
+	and.f  0,  r0, _PAGE_GLOBAL
+	or.z   r2, r2, r3		; Kr Kw Kx Ur Uw Ux (!GLOBAL, user page)
+
+	and r3, r0, PTE_BITS_NON_RWX_IN_PD1 ; Extract PFN+cache bits from PTE
+	or  r3, r3, r2
+
+	sr  r3, [ARC_REG_TLBPD1]    	; paddr[31..13] | Kr Kw Kx Ur Uw Ux | C
+#ifdef	CONFIG_ARC_HAS_PAE40
+	ld	r3, [r1, 4]		; paddr[39..32]
+	sr	r3, [ARC_REG_TLBPD1HI]
+#endif
+
+	and r2, r0, PTE_BITS_IN_PD0 ; Extract other PTE flags: (V)alid, (G)lb
+
+	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
+#ifdef CONFIG_ARC_MMU_V3
+
+	/* Get free TLB slot: Set = computed from vaddr, way = random */
+	sr  TLBGetIndex, [ARC_REG_TLBCOMMAND]
+
+	/* Commit the Write */
+	sr TLBWriteNI, [ARC_REG_TLBCOMMAND]
+
+#else
+	sr TLBInsertEntry, [ARC_REG_TLBCOMMAND]
+#endif
+
+88:
+.endm
+
+
+ARCFP_CODE	;Fast Path Code, candidate for ICCM
+
+;-----------------------------------------------------------------------------
+; I-TLB Miss Exception Handler
+;-----------------------------------------------------------------------------
+
+ENTRY(EV_TLBMissI)
+
+	TLBMISS_FREEUP_REGS
+
+	;----------------------------------------------------------------
+	; Get the PTE corresponding to V-addr accessed, r2 is setup with EFA
+	LOAD_FAULT_PTE
+
+	;----------------------------------------------------------------
+	; VERIFY_PTE: Check if PTE permissions approp for executing code
+	cmp_s   r2, VMALLOC_START
+	mov_s   r2, (_PAGE_PRESENT | _PAGE_EXECUTE)
+	or.hs   r2, r2, _PAGE_GLOBAL
+
+	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_ACCESSED  ; set Accessed Bit
+	st_s    r0, [r1]                ; Write back PTE
+
+	CONV_PTE_TO_TLB
+	COMMIT_ENTRY_TO_MMU
+	TLBMISS_RESTORE_REGS
+EV_TLBMissI_fast_ret:	; additional label for VDK OS-kit instrumentation
+	rtie
+
+END(EV_TLBMissI)
+
+;-----------------------------------------------------------------------------
+; D-TLB Miss Exception Handler
+;-----------------------------------------------------------------------------
+
+ENTRY(EV_TLBMissD)
+
+	TLBMISS_FREEUP_REGS
+
+	;----------------------------------------------------------------
+	; Get the PTE corresponding to V-addr accessed
+	; If PTE exists, it will setup, r0 = PTE, r1 = Ptr to PTE, r2 = EFA
+	LOAD_FAULT_PTE
+
+	;----------------------------------------------------------------
+	; VERIFY_PTE: Chk if PTE permissions approp for data access (R/W/R+W)
+
+	cmp_s	r2, VMALLOC_START
+	mov_s   r2, _PAGE_PRESENT	; common bit for K/U PTE
+	or.hs	r2, r2, _PAGE_GLOBAL	; kernel PTE only
+
+	; Linux PTE [RWX] bits are semantically overloaded:
+	; -If PAGE_GLOBAL set, they refer to kernel-only flags (vmalloc)
+	; -Otherwise they are user-mode permissions, and those are exactly
+	;  same for kernel mode as well (e.g. copy_(to|from)_user)
+
+	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 (both R and W)
+
+	; 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
+	or      r0, r0, _PAGE_ACCESSED        ; Accessed bit always
+	or.nz   r0, r0, _PAGE_DIRTY           ; if Write, set Dirty bit as well
+	st_s    r0, [r1]                      ; Write back PTE
+
+	CONV_PTE_TO_TLB
+
+	COMMIT_ENTRY_TO_MMU
+	TLBMISS_RESTORE_REGS
+EV_TLBMissD_fast_ret:	; additional label for VDK OS-kit instrumentation
+	rtie
+
+;-------- Common routine to call Linux Page Fault Handler -----------
+do_slow_path_pf:
+
+#ifdef CONFIG_ISA_ARCV2
+	; Set Z flag if exception in U mode. Hardware micro-ops do this on any
+	; taken interrupt/exception, and thus is already the case at the entry
+	; above, but ensuing code would have already clobbered.
+	; EXCEPTION_PROLOGUE called in slow path, relies on correct Z flag set
+
+	lr	r2, [erstatus]
+	and	r2, r2, STATUS_U_MASK
+	bxor.f	0, r2, STATUS_U_BIT
+#endif
+
+	; 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).
+	b  call_do_page_fault
+END(EV_TLBMissD)
diff --git a/arch/arc/net/Makefile b/arch/arc/net/Makefile
new file mode 100644
index 000000000..ea5790952
--- /dev/null
+++ b/arch/arc/net/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+ifeq ($(CONFIG_ISA_ARCV2),y)
+	obj-$(CONFIG_BPF_JIT) += bpf_jit_core.o
+	obj-$(CONFIG_BPF_JIT) += bpf_jit_arcv2.o
+endif
diff --git a/arch/arc/net/bpf_jit.h b/arch/arc/net/bpf_jit.h
new file mode 100644
index 000000000..495f3023e
--- /dev/null
+++ b/arch/arc/net/bpf_jit.h
@@ -0,0 +1,164 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * The interface that a back-end should provide to bpf_jit_core.c.
+ *
+ * Copyright (c) 2024 Synopsys Inc.
+ * Author: Shahab Vahedi <shahab@synopsys.com>
+ */
+
+#ifndef _ARC_BPF_JIT_H
+#define _ARC_BPF_JIT_H
+
+#include <linux/bpf.h>
+#include <linux/filter.h>
+
+/* Print debug info and assert. */
+//#define ARC_BPF_JIT_DEBUG
+
+/* Determine the address type of the target. */
+#ifdef CONFIG_ISA_ARCV2
+#define ARC_ADDR u32
+#endif
+
+/*
+ * For the translation of some BPF instructions, a temporary register
+ * might be needed for some interim data.
+ */
+#define JIT_REG_TMP MAX_BPF_JIT_REG
+
+/*
+ * Buffer access: If buffer "b" is not NULL, advance by "n" bytes.
+ *
+ * This macro must be used in any place that potentially requires a
+ * "buf + len". This way, we make sure that the "buf" argument for
+ * the underlying "arc_*(buf, ...)" ends up as NULL instead of something
+ * like "0+4" or "0+8", etc. Those "arc_*()" functions check their "buf"
+ * value to decide if instructions should be emitted or not.
+ */
+#define BUF(b, n) (((b) != NULL) ? ((b) + (n)) : (b))
+
+/************** Functions that the back-end must provide **************/
+/* Extension for 32-bit operations. */
+u8 zext(u8 *buf, u8 rd);
+/***** Moves *****/
+u8 mov_r32(u8 *buf, u8 rd, u8 rs, u8 sign_ext);
+u8 mov_r32_i32(u8 *buf, u8 reg, s32 imm);
+u8 mov_r64(u8 *buf, u8 rd, u8 rs, u8 sign_ext);
+u8 mov_r64_i32(u8 *buf, u8 reg, s32 imm);
+u8 mov_r64_i64(u8 *buf, u8 reg, u32 lo, u32 hi);
+/***** Loads and stores *****/
+u8 load_r(u8 *buf, u8 rd, u8 rs, s16 off, u8 size, bool sign_ext);
+u8 store_r(u8 *buf, u8 rd, u8 rs, s16 off, u8 size);
+u8 store_i(u8 *buf, s32 imm, u8 rd, s16 off, u8 size);
+/***** Addition *****/
+u8 add_r32(u8 *buf, u8 rd, u8 rs);
+u8 add_r32_i32(u8 *buf, u8 rd, s32 imm);
+u8 add_r64(u8 *buf, u8 rd, u8 rs);
+u8 add_r64_i32(u8 *buf, u8 rd, s32 imm);
+/***** Subtraction *****/
+u8 sub_r32(u8 *buf, u8 rd, u8 rs);
+u8 sub_r32_i32(u8 *buf, u8 rd, s32 imm);
+u8 sub_r64(u8 *buf, u8 rd, u8 rs);
+u8 sub_r64_i32(u8 *buf, u8 rd, s32 imm);
+/***** Multiplication *****/
+u8 mul_r32(u8 *buf, u8 rd, u8 rs);
+u8 mul_r32_i32(u8 *buf, u8 rd, s32 imm);
+u8 mul_r64(u8 *buf, u8 rd, u8 rs);
+u8 mul_r64_i32(u8 *buf, u8 rd, s32 imm);
+/***** Division *****/
+u8 div_r32(u8 *buf, u8 rd, u8 rs, bool sign_ext);
+u8 div_r32_i32(u8 *buf, u8 rd, s32 imm, bool sign_ext);
+/***** Remainder *****/
+u8 mod_r32(u8 *buf, u8 rd, u8 rs, bool sign_ext);
+u8 mod_r32_i32(u8 *buf, u8 rd, s32 imm, bool sign_ext);
+/***** Bitwise AND *****/
+u8 and_r32(u8 *buf, u8 rd, u8 rs);
+u8 and_r32_i32(u8 *buf, u8 rd, s32 imm);
+u8 and_r64(u8 *buf, u8 rd, u8 rs);
+u8 and_r64_i32(u8 *buf, u8 rd, s32 imm);
+/***** Bitwise OR *****/
+u8 or_r32(u8 *buf, u8 rd, u8 rs);
+u8 or_r32_i32(u8 *buf, u8 rd, s32 imm);
+u8 or_r64(u8 *buf, u8 rd, u8 rs);
+u8 or_r64_i32(u8 *buf, u8 rd, s32 imm);
+/***** Bitwise XOR *****/
+u8 xor_r32(u8 *buf, u8 rd, u8 rs);
+u8 xor_r32_i32(u8 *buf, u8 rd, s32 imm);
+u8 xor_r64(u8 *buf, u8 rd, u8 rs);
+u8 xor_r64_i32(u8 *buf, u8 rd, s32 imm);
+/***** Bitwise Negate *****/
+u8 neg_r32(u8 *buf, u8 r);
+u8 neg_r64(u8 *buf, u8 r);
+/***** Bitwise left shift *****/
+u8 lsh_r32(u8 *buf, u8 rd, u8 rs);
+u8 lsh_r32_i32(u8 *buf, u8 rd, u8 imm);
+u8 lsh_r64(u8 *buf, u8 rd, u8 rs);
+u8 lsh_r64_i32(u8 *buf, u8 rd, s32 imm);
+/***** Bitwise right shift (logical) *****/
+u8 rsh_r32(u8 *buf, u8 rd, u8 rs);
+u8 rsh_r32_i32(u8 *buf, u8 rd, u8 imm);
+u8 rsh_r64(u8 *buf, u8 rd, u8 rs);
+u8 rsh_r64_i32(u8 *buf, u8 rd, s32 imm);
+/***** Bitwise right shift (arithmetic) *****/
+u8 arsh_r32(u8 *buf, u8 rd, u8 rs);
+u8 arsh_r32_i32(u8 *buf, u8 rd, u8 imm);
+u8 arsh_r64(u8 *buf, u8 rd, u8 rs);
+u8 arsh_r64_i32(u8 *buf, u8 rd, s32 imm);
+/***** Frame related *****/
+u32 mask_for_used_regs(u8 bpf_reg, bool is_call);
+u8 arc_prologue(u8 *buf, u32 usage, u16 frame_size);
+u8 arc_epilogue(u8 *buf, u32 usage, u16 frame_size);
+/***** Jumps *****/
+/*
+ * Different sorts of conditions (ARC enum as opposed to BPF_*).
+ *
+ * Do not change the order of enums here. ARC_CC_SLE+1 is used
+ * to determine the number of JCCs.
+ */
+enum ARC_CC {
+	ARC_CC_UGT = 0,		/* unsigned >  */
+	ARC_CC_UGE,		/* unsigned >= */
+	ARC_CC_ULT,		/* unsigned <  */
+	ARC_CC_ULE,		/* unsigned <= */
+	ARC_CC_SGT,		/*   signed >  */
+	ARC_CC_SGE,		/*   signed >= */
+	ARC_CC_SLT,		/*   signed <  */
+	ARC_CC_SLE,		/*   signed <= */
+	ARC_CC_AL,		/* always      */
+	ARC_CC_EQ,		/*          == */
+	ARC_CC_NE,		/*          != */
+	ARC_CC_SET,		/* test        */
+	ARC_CC_LAST
+};
+
+/*
+ * A few notes:
+ *
+ * - check_jmp_*() are prerequisites before calling the gen_jmp_*().
+ *   They return "true" if the jump is possible and "false" otherwise.
+ *
+ * - The notion of "*_off" is to emphasize that these parameters are
+ *   merely offsets in the JIT stream and not absolute addresses. One
+ *   can look at them as addresses if the JIT code would start from
+ *   address 0x0000_0000. Nonetheless, since the buffer address for the
+ *   JIT is on a word-aligned address, this works and actually makes
+ *   things simpler (offsets are in the range of u32 which is more than
+ *   enough).
+ */
+bool check_jmp_32(u32 curr_off, u32 targ_off, u8 cond);
+bool check_jmp_64(u32 curr_off, u32 targ_off, u8 cond);
+u8 gen_jmp_32(u8 *buf, u8 rd, u8 rs, u8 cond, u32 c_off, u32 t_off);
+u8 gen_jmp_64(u8 *buf, u8 rd, u8 rs, u8 cond, u32 c_off, u32 t_off);
+/***** Miscellaneous *****/
+u8 gen_func_call(u8 *buf, ARC_ADDR func_addr, bool external_func);
+u8 arc_to_bpf_return(u8 *buf);
+/*
+ * - Perform byte swaps on "rd" based on the "size".
+ * - If "force" is set, do it unconditionally. Otherwise, consider the
+ *   desired "endian"ness and the host endianness.
+ * - For data "size"s up to 32 bits, perform a zero-extension if asked
+ *   by the "do_zext" boolean.
+ */
+u8 gen_swap(u8 *buf, u8 rd, u8 size, u8 endian, bool force, bool do_zext);
+
+#endif /* _ARC_BPF_JIT_H */
diff --git a/arch/arc/net/bpf_jit_arcv2.c b/arch/arc/net/bpf_jit_arcv2.c
new file mode 100644
index 000000000..7ee50aeae
--- /dev/null
+++ b/arch/arc/net/bpf_jit_arcv2.c
@@ -0,0 +1,3007 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * The ARCv2 backend of Just-In-Time compiler for eBPF bytecode.
+ *
+ * Copyright (c) 2024 Synopsys Inc.
+ * Author: Shahab Vahedi <shahab@synopsys.com>
+ */
+#include <linux/bug.h>
+#include "bpf_jit.h"
+
+/* ARC core registers. */
+enum {
+	ARC_R_0,  ARC_R_1,  ARC_R_2,  ARC_R_3,  ARC_R_4,  ARC_R_5,
+	ARC_R_6,  ARC_R_7,  ARC_R_8,  ARC_R_9,  ARC_R_10, ARC_R_11,
+	ARC_R_12, ARC_R_13, ARC_R_14, ARC_R_15, ARC_R_16, ARC_R_17,
+	ARC_R_18, ARC_R_19, ARC_R_20, ARC_R_21, ARC_R_22, ARC_R_23,
+	ARC_R_24, ARC_R_25, ARC_R_26, ARC_R_FP, ARC_R_SP, ARC_R_ILINK,
+	ARC_R_30, ARC_R_BLINK,
+	/*
+	 * Having ARC_R_IMM encoded as source register means there is an
+	 * immediate that must be interpreted from the next 4 bytes. If
+	 * encoded as the destination register though, it implies that the
+	 * output of the operation is not assigned to any register. The
+	 * latter is helpful if we only care about updating the CPU status
+	 * flags.
+	 */
+	ARC_R_IMM = 62
+};
+
+/*
+ * Remarks about the rationale behind the chosen mapping:
+ *
+ * - BPF_REG_{1,2,3,4} are the argument registers and must be mapped to
+ *   argument registers in ARCv2 ABI: r0-r7. The r7 registers is the last
+ *   argument register in the ABI. Therefore BPF_REG_5, as the fifth
+ *   argument, must be pushed onto the stack. This is a must for calling
+ *   in-kernel functions.
+ *
+ * - In ARCv2 ABI, the return value is in r0 for 32-bit results and (r1,r0)
+ *   for 64-bit results. However, because they're already used for BPF_REG_1,
+ *   the next available scratch registers, r8 and r9, are the best candidates
+ *   for BPF_REG_0. After a "call" to a(n) (in-kernel) function, the result
+ *   is "mov"ed to these registers. At a BPF_EXIT, their value is "mov"ed to
+ *   (r1,r0).
+ *   It is worth mentioning that scratch registers are the best choice for
+ *   BPF_REG_0, because it is very popular in BPF instruction encoding.
+ *
+ * - JIT_REG_TMP is an artifact needed to translate some BPF instructions.
+ *   Its life span is one single BPF instruction. Since during the
+ *   analyze_reg_usage(), it is not known if temporary registers are used,
+ *   it is mapped to ARC's scratch registers: r10 and r11. Therefore, they
+ *   don't matter in analysing phase and don't need saving. This temporary
+ *   register is added as yet another index in the bpf2arc array, so it will
+ *   unfold like the rest of registers during the code generation process.
+ *
+ * - Mapping of callee-saved BPF registers, BPF_REG_{6,7,8,9}, starts from
+ *   (r15,r14) register pair. The (r13,r12) is not a good choice, because
+ *   in ARCv2 ABI, r12 is not a callee-saved register and this can cause
+ *   problem when calling an in-kernel function. Theoretically, the mapping
+ *   could start from (r14,r13), but it is not a conventional ARCv2 register
+ *   pair. To have a future proof design, I opted for this arrangement.
+ *   If/when we decide to add ARCv2 instructions that do use register pairs,
+ *   the mapping, hopefully, doesn't need to be revisited.
+ */
+static const u8 bpf2arc[][2] = {
+	/* Return value from in-kernel function, and exit value from eBPF */
+	[BPF_REG_0] = {ARC_R_8, ARC_R_9},
+	/* Arguments from eBPF program to in-kernel function */
+	[BPF_REG_1] = {ARC_R_0, ARC_R_1},
+	[BPF_REG_2] = {ARC_R_2, ARC_R_3},
+	[BPF_REG_3] = {ARC_R_4, ARC_R_5},
+	[BPF_REG_4] = {ARC_R_6, ARC_R_7},
+	/* Remaining arguments, to be passed on the stack per 32-bit ABI */
+	[BPF_REG_5] = {ARC_R_22, ARC_R_23},
+	/* Callee-saved registers that in-kernel function will preserve */
+	[BPF_REG_6] = {ARC_R_14, ARC_R_15},
+	[BPF_REG_7] = {ARC_R_16, ARC_R_17},
+	[BPF_REG_8] = {ARC_R_18, ARC_R_19},
+	[BPF_REG_9] = {ARC_R_20, ARC_R_21},
+	/* Read-only frame pointer to access the eBPF stack. 32-bit only. */
+	[BPF_REG_FP] = {ARC_R_FP, },
+	/* Register for blinding constants */
+	[BPF_REG_AX] = {ARC_R_24, ARC_R_25},
+	/* Temporary registers for internal use */
+	[JIT_REG_TMP] = {ARC_R_10, ARC_R_11}
+};
+
+#define ARC_CALLEE_SAVED_REG_FIRST ARC_R_13
+#define ARC_CALLEE_SAVED_REG_LAST  ARC_R_25
+
+#define REG_LO(r) (bpf2arc[(r)][0])
+#define REG_HI(r) (bpf2arc[(r)][1])
+
+/*
+ * To comply with ARCv2 ABI, BPF's arg5 must be put on stack. After which,
+ * the stack needs to be restored by ARG5_SIZE.
+ */
+#define ARG5_SIZE 8
+
+/* Instruction lengths in bytes. */
+enum {
+	INSN_len_normal = 4,	/* Normal instructions length. */
+	INSN_len_imm = 4	/* Length of an extra 32-bit immediate. */
+};
+
+/* ZZ defines the size of operation in encodings that it is used. */
+enum {
+	ZZ_1_byte = 1,
+	ZZ_2_byte = 2,
+	ZZ_4_byte = 0,
+	ZZ_8_byte = 3
+};
+
+/*
+ * AA is mostly about address write back mode. It determines if the
+ * address in question should be updated before usage or after:
+ *   addr += offset; data = *addr;
+ *   data = *addr; addr += offset;
+ *
+ * In "scaling" mode, the effective address will become the sum
+ * of "address" + "index"*"size". The "size" is specified by the
+ * "ZZ" field. There is no write back when AA is set for scaling:
+ *   data = *(addr + offset<<zz)
+ */
+enum {
+	AA_none  = 0,
+	AA_pre   = 1,	/* in assembly known as "a/aw". */
+	AA_post  = 2,	/* in assembly known as "ab". */
+	AA_scale = 3	/* in assembly known as "as". */
+};
+
+/* X flag determines the mode of extension. */
+enum {
+	X_zero = 0,
+	X_sign = 1
+};
+
+/* Condition codes. */
+enum {
+	CC_always     = 0,	/* condition is true all the time */
+	CC_equal      = 1,	/* if status32.z flag is set */
+	CC_unequal    = 2,	/* if status32.z flag is clear */
+	CC_positive   = 3,	/* if status32.n flag is clear */
+	CC_negative   = 4,	/* if status32.n flag is set */
+	CC_less_u     = 5,	/* less than (unsigned) */
+	CC_less_eq_u  = 14,	/* less than or equal (unsigned) */
+	CC_great_eq_u = 6,	/* greater than or equal (unsigned) */
+	CC_great_u    = 13,	/* greater than (unsigned) */
+	CC_less_s     = 11,	/* less than (signed) */
+	CC_less_eq_s  = 12,	/* less than or equal (signed) */
+	CC_great_eq_s = 10,	/* greater than or equal (signed) */
+	CC_great_s    = 9	/* greater than (signed) */
+};
+
+#define IN_U6_RANGE(x)	((x) <= (0x40      - 1) && (x) >= 0)
+#define IN_S9_RANGE(x)	((x) <= (0x100     - 1) && (x) >= -0x100)
+#define IN_S12_RANGE(x)	((x) <= (0x800     - 1) && (x) >= -0x800)
+#define IN_S21_RANGE(x)	((x) <= (0x100000  - 1) && (x) >= -0x100000)
+#define IN_S25_RANGE(x)	((x) <= (0x1000000 - 1) && (x) >= -0x1000000)
+
+/* Operands in most of the encodings. */
+#define OP_A(x)	((x) & 0x03f)
+#define OP_B(x)	((((x) & 0x07) << 24) | (((x) & 0x38) <<  9))
+#define OP_C(x)	(((x) & 0x03f) << 6)
+#define OP_IMM	(OP_C(ARC_R_IMM))
+#define COND(x)	(OP_A((x) & 31))
+#define FLAG(x)	(((x) & 1) << 15)
+
+/*
+ * The 4-byte encoding of "mov b,c":
+ *
+ * 0010_0bbb 0000_1010 0BBB_cccc cc00_0000
+ *
+ * b:  BBBbbb		destination register
+ * c:  cccccc		source register
+ */
+#define OPC_MOV		0x200a0000
+
+/*
+ * The 4-byte encoding of "mov b,s12" (used for moving small immediates):
+ *
+ * 0010_0bbb 1000_1010 0BBB_ssss ssSS_SSSS
+ *
+ * b:  BBBbbb		destination register
+ * s:  SSSSSSssssss	source immediate (signed)
+ */
+#define OPC_MOVI	0x208a0000
+#define MOVI_S12(x)	((((x) & 0xfc0) >> 6) | (((x) & 0x3f) << 6))
+
+/*
+ * The 4-byte encoding of "mov[.qq] b,u6", used for conditional
+ * moving of even smaller immediates:
+ *
+ * 0010_0bbb 1100_1010 0BBB_cccc cciq_qqqq
+ *
+ * qq: qqqqq		condition code
+ * i:			If set, c is considered a 6-bit immediate, else a reg.
+ *
+ * b:  BBBbbb		destination register
+ * c:  cccccc		source
+ */
+#define OPC_MOV_CC	0x20ca0000
+#define MOV_CC_I	BIT(5)
+#define OPC_MOVU_CC	(OPC_MOV_CC | MOV_CC_I)
+
+/*
+ * The 4-byte encoding of "sexb b,c" (8-bit sign extension):
+ *
+ * 0010_0bbb 0010_1111 0BBB_cccc cc00_0101
+ *
+ * b:  BBBbbb		destination register
+ * c:  cccccc		source register
+ */
+#define OPC_SEXB	0x202f0005
+
+/*
+ * The 4-byte encoding of "sexh b,c" (16-bit sign extension):
+ *
+ * 0010_0bbb 0010_1111 0BBB_cccc cc00_0110
+ *
+ * b:  BBBbbb		destination register
+ * c:  cccccc		source register
+ */
+#define OPC_SEXH	0x202f0006
+
+/*
+ * The 4-byte encoding of "ld[zz][.x][.aa] c,[b,s9]":
+ *
+ * 0001_0bbb ssss_ssss SBBB_0aaz zxcc_cccc
+ *
+ * zz:			size mode
+ * aa:			address write back mode
+ * x:			extension mode
+ *
+ * s9: S_ssss_ssss	9-bit signed number
+ * b:  BBBbbb		source reg for address
+ * c:  cccccc		destination register
+ */
+#define OPC_LOAD	0x10000000
+#define LOAD_X(x)	((x) << 6)
+#define LOAD_ZZ(x)	((x) << 7)
+#define LOAD_AA(x)	((x) << 9)
+#define LOAD_S9(x)	((((x) & 0x0ff) << 16) | (((x) & 0x100) <<  7))
+#define LOAD_C(x)	((x) & 0x03f)
+/* Unsigned and signed loads. */
+#define OPC_LDU		(OPC_LOAD | LOAD_X(X_zero))
+#define OPC_LDS		(OPC_LOAD | LOAD_X(X_sign))
+/* 32-bit load. */
+#define OPC_LD32	(OPC_LDU | LOAD_ZZ(ZZ_4_byte))
+/* "pop reg" is merely a "ld.ab reg,[sp,4]". */
+#define OPC_POP		\
+	(OPC_LD32 | LOAD_AA(AA_post) | LOAD_S9(4) | OP_B(ARC_R_SP))
+
+/*
+ * The 4-byte encoding of "st[zz][.aa] c,[b,s9]":
+ *
+ * 0001_1bbb ssss_ssss SBBB_cccc cc0a_azz0
+ *
+ * zz: zz		size mode
+ * aa: aa		address write back mode
+ *
+ * s9: S_ssss_ssss	9-bit signed number
+ * b:  BBBbbb		source reg for address
+ * c:  cccccc		source reg to be stored
+ */
+#define OPC_STORE	0x18000000
+#define STORE_ZZ(x)	((x) << 1)
+#define STORE_AA(x)	((x) << 3)
+#define STORE_S9(x)	((((x) & 0x0ff) << 16) | (((x) & 0x100) <<  7))
+/* 32-bit store. */
+#define OPC_ST32	(OPC_STORE | STORE_ZZ(ZZ_4_byte))
+/* "push reg" is merely a "st.aw reg,[sp,-4]". */
+#define OPC_PUSH	\
+	(OPC_ST32 | STORE_AA(AA_pre) | STORE_S9(-4) | OP_B(ARC_R_SP))
+
+/*
+ * The 4-byte encoding of "add a,b,c":
+ *
+ * 0010_0bbb 0i00_0000 fBBB_cccc ccaa_aaaa
+ *
+ * f:                   indicates if flags (carry, etc.) should be updated
+ * i:			If set, c is considered a 6-bit immediate, else a reg.
+ *
+ * a:  aaaaaa		result
+ * b:  BBBbbb		the 1st input operand
+ * c:  cccccc		the 2nd input operand
+ */
+#define OPC_ADD		0x20000000
+/* Addition with updating the pertinent flags in "status32" register. */
+#define OPC_ADDF	(OPC_ADD | FLAG(1))
+#define ADDI		BIT(22)
+#define ADDI_U6(x)	OP_C(x)
+#define OPC_ADDI	(OPC_ADD | ADDI)
+#define OPC_ADDIF	(OPC_ADDI | FLAG(1))
+#define OPC_ADD_I	(OPC_ADD | OP_IMM)
+
+/*
+ * The 4-byte encoding of "adc a,b,c" (addition with carry):
+ *
+ * 0010_0bbb 0i00_0001 0BBB_cccc ccaa_aaaa
+ *
+ * i:			if set, c is considered a 6-bit immediate, else a reg.
+ *
+ * a:  aaaaaa		result
+ * b:  BBBbbb		the 1st input operand
+ * c:  cccccc		the 2nd input operand
+ */
+#define OPC_ADC		0x20010000
+#define ADCI		BIT(22)
+#define ADCI_U6(x)	OP_C(x)
+#define OPC_ADCI	(OPC_ADC | ADCI)
+
+/*
+ * The 4-byte encoding of "sub a,b,c":
+ *
+ * 0010_0bbb 0i00_0010 fBBB_cccc ccaa_aaaa
+ *
+ * f:                   indicates if flags (carry, etc.) should be updated
+ * i:			if set, c is considered a 6-bit immediate, else a reg.
+ *
+ * a:  aaaaaa		result
+ * b:  BBBbbb		the 1st input operand
+ * c:  cccccc		the 2nd input operand
+ */
+#define OPC_SUB		0x20020000
+/* Subtraction with updating the pertinent flags in "status32" register. */
+#define OPC_SUBF	(OPC_SUB | FLAG(1))
+#define SUBI		BIT(22)
+#define SUBI_U6(x)	OP_C(x)
+#define OPC_SUBI	(OPC_SUB | SUBI)
+#define OPC_SUB_I	(OPC_SUB | OP_IMM)
+
+/*
+ * The 4-byte encoding of "sbc a,b,c" (subtraction with carry):
+ *
+ * 0010_0bbb 0000_0011 fBBB_cccc ccaa_aaaa
+ *
+ * f:                   indicates if flags (carry, etc.) should be updated
+ *
+ * a:  aaaaaa		result
+ * b:  BBBbbb		the 1st input operand
+ * c:  cccccc		the 2nd input operand
+ */
+#define OPC_SBC		0x20030000
+
+/*
+ * The 4-byte encoding of "cmp[.qq] b,c":
+ *
+ * 0010_0bbb 1100_1100 1BBB_cccc cc0q_qqqq
+ *
+ * qq:	qqqqq		condition code
+ *
+ * b:  BBBbbb		the 1st operand
+ * c:  cccccc		the 2nd operand
+ */
+#define OPC_CMP		0x20cc8000
+
+/*
+ * The 4-byte encoding of "neg a,b":
+ *
+ * 0010_0bbb 0100_1110 0BBB_0000 00aa_aaaa
+ *
+ * a:  aaaaaa		result
+ * b:  BBBbbb		input
+ */
+#define OPC_NEG		0x204e0000
+
+/*
+ * The 4-byte encoding of "mpy a,b,c".
+ * mpy is the signed 32-bit multiplication with the lower 32-bit
+ * of the product as the result.
+ *
+ * 0010_0bbb 0001_1010 0BBB_cccc ccaa_aaaa
+ *
+ * a:  aaaaaa		result
+ * b:  BBBbbb		the 1st input operand
+ * c:  cccccc		the 2nd input operand
+ */
+#define OPC_MPY		0x201a0000
+#define OPC_MPYI	(OPC_MPY | OP_IMM)
+
+/*
+ * The 4-byte encoding of "mpydu a,b,c".
+ * mpydu is the unsigned 32-bit multiplication with the lower 32-bit of
+ * the product in register "a" and the higher 32-bit in register "a+1".
+ *
+ * 0010_1bbb 0001_1001 0BBB_cccc ccaa_aaaa
+ *
+ * a:  aaaaaa		64-bit result in registers (R_a+1,R_a)
+ * b:  BBBbbb		the 1st input operand
+ * c:  cccccc		the 2nd input operand
+ */
+#define OPC_MPYDU	0x28190000
+#define OPC_MPYDUI	(OPC_MPYDU | OP_IMM)
+
+/*
+ * The 4-byte encoding of "divu a,b,c" (unsigned division):
+ *
+ * 0010_1bbb 0000_0101 0BBB_cccc ccaa_aaaa
+ *
+ * a:  aaaaaa		result (quotient)
+ * b:  BBBbbb		the 1st input operand
+ * c:  cccccc		the 2nd input operand (divisor)
+ */
+#define OPC_DIVU	0x28050000
+#define OPC_DIVUI	(OPC_DIVU | OP_IMM)
+
+/*
+ * The 4-byte encoding of "div a,b,c" (signed division):
+ *
+ * 0010_1bbb 0000_0100 0BBB_cccc ccaa_aaaa
+ *
+ * a:  aaaaaa		result (quotient)
+ * b:  BBBbbb		the 1st input operand
+ * c:  cccccc		the 2nd input operand (divisor)
+ */
+#define OPC_DIVS	0x28040000
+#define OPC_DIVSI	(OPC_DIVS | OP_IMM)
+
+/*
+ * The 4-byte encoding of "remu a,b,c" (unsigned remainder):
+ *
+ * 0010_1bbb 0000_1001 0BBB_cccc ccaa_aaaa
+ *
+ * a:  aaaaaa		result (remainder)
+ * b:  BBBbbb		the 1st input operand
+ * c:  cccccc		the 2nd input operand (divisor)
+ */
+#define OPC_REMU	0x28090000
+#define OPC_REMUI	(OPC_REMU | OP_IMM)
+
+/*
+ * The 4-byte encoding of "rem a,b,c" (signed remainder):
+ *
+ * 0010_1bbb 0000_1000 0BBB_cccc ccaa_aaaa
+ *
+ * a:  aaaaaa		result (remainder)
+ * b:  BBBbbb		the 1st input operand
+ * c:  cccccc		the 2nd input operand (divisor)
+ */
+#define OPC_REMS	0x28080000
+#define OPC_REMSI	(OPC_REMS | OP_IMM)
+
+/*
+ * The 4-byte encoding of "and a,b,c":
+ *
+ * 0010_0bbb 0000_0100 fBBB_cccc ccaa_aaaa
+ *
+ * f:                   indicates if zero and negative flags should be updated
+ *
+ * a:  aaaaaa		result
+ * b:  BBBbbb		the 1st input operand
+ * c:  cccccc		the 2nd input operand
+ */
+#define OPC_AND		0x20040000
+#define OPC_ANDI	(OPC_AND | OP_IMM)
+
+/*
+ * The 4-byte encoding of "tst[.qq] b,c".
+ * Checks if the two input operands have any bit set at the same
+ * position.
+ *
+ * 0010_0bbb 1100_1011 1BBB_cccc cc0q_qqqq
+ *
+ * qq:	qqqqq		condition code
+ *
+ * b:  BBBbbb		the 1st input operand
+ * c:  cccccc		the 2nd input operand
+ */
+#define OPC_TST		0x20cb8000
+
+/*
+ * The 4-byte encoding of "or a,b,c":
+ *
+ * 0010_0bbb 0000_0101 0BBB_cccc ccaa_aaaa
+ *
+ * a:  aaaaaa		result
+ * b:  BBBbbb		the 1st input operand
+ * c:  cccccc		the 2nd input operand
+ */
+#define OPC_OR		0x20050000
+#define OPC_ORI		(OPC_OR | OP_IMM)
+
+/*
+ * The 4-byte encoding of "xor a,b,c":
+ *
+ * 0010_0bbb 0000_0111 0BBB_cccc ccaa_aaaa
+ *
+ * a:  aaaaaa		result
+ * b:  BBBbbb		the 1st input operand
+ * c:  cccccc		the 2nd input operand
+ */
+#define OPC_XOR		0x20070000
+#define OPC_XORI	(OPC_XOR | OP_IMM)
+
+/*
+ * The 4-byte encoding of "not b,c":
+ *
+ * 0010_0bbb 0010_1111 0BBB_cccc cc00_1010
+ *
+ * b:  BBBbbb		result
+ * c:  cccccc		input
+ */
+#define OPC_NOT		0x202f000a
+
+/*
+ * The 4-byte encoding of "btst b,u6":
+ *
+ * 0010_0bbb 0101_0001 1BBB_uuuu uu00_0000
+ *
+ * b:  BBBbbb		input number to check
+ * u6: uuuuuu		6-bit unsigned number specifying bit position to check
+ */
+#define OPC_BTSTU6	0x20518000
+#define BTST_U6(x)	(OP_C((x) & 63))
+
+/*
+ * The 4-byte encoding of "asl[.qq] b,b,c" (arithmetic shift left):
+ *
+ * 0010_1bbb 0i00_0000 0BBB_cccc ccaa_aaaa
+ *
+ * i:			if set, c is considered a 5-bit immediate, else a reg.
+ *
+ * b:  BBBbbb		result and the first operand (number to be shifted)
+ * c:  cccccc		amount to be shifted
+ */
+#define OPC_ASL		0x28000000
+#define ASL_I		BIT(22)
+#define ASLI_U6(x)	OP_C((x) & 31)
+#define OPC_ASLI	(OPC_ASL | ASL_I)
+
+/*
+ * The 4-byte encoding of "asr a,b,c" (arithmetic shift right):
+ *
+ * 0010_1bbb 0i00_0010 0BBB_cccc ccaa_aaaa
+ *
+ * i:			if set, c is considered a 6-bit immediate, else a reg.
+ *
+ * a:  aaaaaa		result
+ * b:  BBBbbb		first input:  number to be shifted
+ * c:  cccccc		second input: amount to be shifted
+ */
+#define OPC_ASR		0x28020000
+#define ASR_I		ASL_I
+#define ASRI_U6(x)	ASLI_U6(x)
+#define OPC_ASRI	(OPC_ASR | ASR_I)
+
+/*
+ * The 4-byte encoding of "lsr a,b,c" (logical shift right):
+ *
+ * 0010_1bbb 0i00_0001 0BBB_cccc ccaa_aaaa
+ *
+ * i:			if set, c is considered a 6-bit immediate, else a reg.
+ *
+ * a:  aaaaaa		result
+ * b:  BBBbbb		first input:  number to be shifted
+ * c:  cccccc		second input: amount to be shifted
+ */
+#define OPC_LSR		0x28010000
+#define LSR_I		ASL_I
+#define LSRI_U6(x)	ASLI_U6(x)
+#define OPC_LSRI	(OPC_LSR | LSR_I)
+
+/*
+ * The 4-byte encoding of "swape b,c":
+ *
+ * 0010_1bbb 0010_1111 0bbb_cccc cc00_1001
+ *
+ * b:  BBBbbb		destination register
+ * c:  cccccc		source register
+ */
+#define OPC_SWAPE	0x282f0009
+
+/*
+ * Encoding for jump to an address in register:
+ * j reg_c
+ *
+ * 0010_0000 1110_0000 0000_cccc cc00_0000
+ *
+ * c:  cccccc		register holding the destination address
+ */
+#define OPC_JMP		0x20e00000
+/* Jump to "branch-and-link" register, which effectively is a "return". */
+#define OPC_J_BLINK	(OPC_JMP | OP_C(ARC_R_BLINK))
+
+/*
+ * Encoding for jump-and-link to an address in register:
+ * jl reg_c
+ *
+ * 0010_0000 0010_0010 0000_cccc cc00_0000
+ *
+ * c:  cccccc		register holding the destination address
+ */
+#define OPC_JL		0x20220000
+
+/*
+ * Encoding for (conditional) branch to an offset from the current location
+ * that is word aligned: (PC & 0xffff_fffc) + s21
+ * B[qq] s21
+ *
+ * 0000_0sss ssss_sss0 SSSS_SSSS SS0q_qqqq
+ *
+ * qq:	qqqqq				condition code
+ * s21:	SSSS SSSS_SSss ssss_ssss	The displacement (21-bit signed)
+ *
+ * The displacement is supposed to be 16-bit (2-byte) aligned. Therefore,
+ * it should be a multiple of 2. Hence, there is an implied '0' bit at its
+ * LSB: S_SSSS SSSS_Ssss ssss_sss0
+ */
+#define OPC_BCC		0x00000000
+#define BCC_S21(d)	((((d) & 0x7fe) << 16) | (((d) & 0x1ff800) >> 5))
+
+/*
+ * Encoding for unconditional branch to an offset from the current location
+ * that is word aligned: (PC & 0xffff_fffc) + s25
+ * B s25
+ *
+ * 0000_0sss ssss_sss1 SSSS_SSSS SS00_TTTT
+ *
+ * s25:	TTTT SSSS SSSS_SSss ssss_ssss	The displacement (25-bit signed)
+ *
+ * The displacement is supposed to be 16-bit (2-byte) aligned. Therefore,
+ * it should be a multiple of 2. Hence, there is an implied '0' bit at its
+ * LSB: T TTTS_SSSS SSSS_Ssss ssss_sss0
+ */
+#define OPC_B		0x00010000
+#define B_S25(d)	((((d) & 0x1e00000) >> 21) | BCC_S21(d))
+
+static inline void emit_2_bytes(u8 *buf, u16 bytes)
+{
+	*((u16 *)buf) = bytes;
+}
+
+static inline void emit_4_bytes(u8 *buf, u32 bytes)
+{
+	emit_2_bytes(buf, bytes >> 16);
+	emit_2_bytes(buf + 2, bytes & 0xffff);
+}
+
+static inline u8 bpf_to_arc_size(u8 size)
+{
+	switch (size) {
+	case BPF_B:
+		return ZZ_1_byte;
+	case BPF_H:
+		return ZZ_2_byte;
+	case BPF_W:
+		return ZZ_4_byte;
+	case BPF_DW:
+		return ZZ_8_byte;
+	default:
+		return ZZ_4_byte;
+	}
+}
+
+/************** Encoders (Deal with ARC regs) ************/
+
+/* Move an immediate to register with a 4-byte instruction. */
+static u8 arc_movi_r(u8 *buf, u8 reg, s16 imm)
+{
+	const u32 insn = OPC_MOVI | OP_B(reg) | MOVI_S12(imm);
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+/* rd <- rs */
+static u8 arc_mov_r(u8 *buf, u8 rd, u8 rs)
+{
+	const u32 insn = OPC_MOV | OP_B(rd) | OP_C(rs);
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+/* The emitted code may have different sizes based on "imm". */
+static u8 arc_mov_i(u8 *buf, u8 rd, s32 imm)
+{
+	const u32 insn = OPC_MOV | OP_B(rd) | OP_IMM;
+
+	if (IN_S12_RANGE(imm))
+		return arc_movi_r(buf, rd, imm);
+
+	if (buf) {
+		emit_4_bytes(buf, insn);
+		emit_4_bytes(buf + INSN_len_normal, imm);
+	}
+	return INSN_len_normal + INSN_len_imm;
+}
+
+/* The emitted code will always have the same size (8). */
+static u8 arc_mov_i_fixed(u8 *buf, u8 rd, s32 imm)
+{
+	const u32 insn = OPC_MOV | OP_B(rd) | OP_IMM;
+
+	if (buf) {
+		emit_4_bytes(buf, insn);
+		emit_4_bytes(buf + INSN_len_normal, imm);
+	}
+	return INSN_len_normal + INSN_len_imm;
+}
+
+/* Conditional move. */
+static u8 arc_mov_cc_r(u8 *buf, u8 cc, u8 rd, u8 rs)
+{
+	const u32 insn = OPC_MOV_CC | OP_B(rd) | OP_C(rs) | COND(cc);
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+/* Conditional move of a small immediate to rd. */
+static u8 arc_movu_cc_r(u8 *buf, u8 cc, u8 rd, u8 imm)
+{
+	const u32 insn = OPC_MOVU_CC | OP_B(rd) | OP_C(imm) | COND(cc);
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+/* Sign extension from a byte. */
+static u8 arc_sexb_r(u8 *buf, u8 rd, u8 rs)
+{
+	const u32 insn = OPC_SEXB | OP_B(rd) | OP_C(rs);
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+/* Sign extension from two bytes. */
+static u8 arc_sexh_r(u8 *buf, u8 rd, u8 rs)
+{
+	const u32 insn = OPC_SEXH | OP_B(rd) | OP_C(rs);
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+/* st reg, [reg_mem, off] */
+static u8 arc_st_r(u8 *buf, u8 reg, u8 reg_mem, s16 off, u8 zz)
+{
+	const u32 insn = OPC_STORE | STORE_ZZ(zz) | OP_C(reg) |
+		OP_B(reg_mem) | STORE_S9(off);
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+/* st.aw reg, [sp, -4] */
+static u8 arc_push_r(u8 *buf, u8 reg)
+{
+	const u32 insn = OPC_PUSH | OP_C(reg);
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+/* ld reg, [reg_mem, off] (unsigned) */
+static u8 arc_ld_r(u8 *buf, u8 reg, u8 reg_mem, s16 off, u8 zz)
+{
+	const u32 insn = OPC_LDU | LOAD_ZZ(zz) | LOAD_C(reg) |
+		OP_B(reg_mem) | LOAD_S9(off);
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+/* ld.x reg, [reg_mem, off] (sign extend) */
+static u8 arc_ldx_r(u8 *buf, u8 reg, u8 reg_mem, s16 off, u8 zz)
+{
+	const u32 insn = OPC_LDS | LOAD_ZZ(zz) | LOAD_C(reg) |
+		OP_B(reg_mem) | LOAD_S9(off);
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+/* ld.ab reg,[sp,4] */
+static u8 arc_pop_r(u8 *buf, u8 reg)
+{
+	const u32 insn = OPC_POP | LOAD_C(reg);
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+/* add Ra,Ra,Rc */
+static u8 arc_add_r(u8 *buf, u8 ra, u8 rc)
+{
+	const u32 insn = OPC_ADD | OP_A(ra) | OP_B(ra) | OP_C(rc);
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+/* add.f Ra,Ra,Rc */
+static u8 arc_addf_r(u8 *buf, u8 ra, u8 rc)
+{
+	const u32 insn = OPC_ADDF | OP_A(ra) | OP_B(ra) | OP_C(rc);
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+/* add.f Ra,Ra,u6 */
+static u8 arc_addif_r(u8 *buf, u8 ra, u8 u6)
+{
+	const u32 insn = OPC_ADDIF | OP_A(ra) | OP_B(ra) | ADDI_U6(u6);
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+/* add Ra,Ra,u6 */
+static u8 arc_addi_r(u8 *buf, u8 ra, u8 u6)
+{
+	const u32 insn = OPC_ADDI | OP_A(ra) | OP_B(ra) | ADDI_U6(u6);
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+/* add Ra,Rb,imm */
+static u8 arc_add_i(u8 *buf, u8 ra, u8 rb, s32 imm)
+{
+	const u32 insn = OPC_ADD_I | OP_A(ra) | OP_B(rb);
+
+	if (buf) {
+		emit_4_bytes(buf, insn);
+		emit_4_bytes(buf + INSN_len_normal, imm);
+	}
+	return INSN_len_normal + INSN_len_imm;
+}
+
+/* adc Ra,Ra,Rc */
+static u8 arc_adc_r(u8 *buf, u8 ra, u8 rc)
+{
+	const u32 insn = OPC_ADC | OP_A(ra) | OP_B(ra) | OP_C(rc);
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+/* adc Ra,Ra,u6 */
+static u8 arc_adci_r(u8 *buf, u8 ra, u8 u6)
+{
+	const u32 insn = OPC_ADCI | OP_A(ra) | OP_B(ra) | ADCI_U6(u6);
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+/* sub Ra,Ra,Rc */
+static u8 arc_sub_r(u8 *buf, u8 ra, u8 rc)
+{
+	const u32 insn = OPC_SUB | OP_A(ra) | OP_B(ra) | OP_C(rc);
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+/* sub.f Ra,Ra,Rc */
+static u8 arc_subf_r(u8 *buf, u8 ra, u8 rc)
+{
+	const u32 insn = OPC_SUBF | OP_A(ra) | OP_B(ra) | OP_C(rc);
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+/* sub Ra,Ra,u6 */
+static u8 arc_subi_r(u8 *buf, u8 ra, u8 u6)
+{
+	const u32 insn = OPC_SUBI | OP_A(ra) | OP_B(ra) | SUBI_U6(u6);
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+/* sub Ra,Ra,imm */
+static u8 arc_sub_i(u8 *buf, u8 ra, s32 imm)
+{
+	const u32 insn = OPC_SUB_I | OP_A(ra) | OP_B(ra);
+
+	if (buf) {
+		emit_4_bytes(buf, insn);
+		emit_4_bytes(buf + INSN_len_normal, imm);
+	}
+	return INSN_len_normal + INSN_len_imm;
+}
+
+/* sbc Ra,Ra,Rc */
+static u8 arc_sbc_r(u8 *buf, u8 ra, u8 rc)
+{
+	const u32 insn = OPC_SBC | OP_A(ra) | OP_B(ra) | OP_C(rc);
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+/* cmp Rb,Rc */
+static u8 arc_cmp_r(u8 *buf, u8 rb, u8 rc)
+{
+	const u32 insn = OPC_CMP | OP_B(rb) | OP_C(rc);
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+/*
+ * cmp.z Rb,Rc
+ *
+ * This "cmp.z" variant of compare instruction is used on lower
+ * 32-bits of register pairs after "cmp"ing their upper parts. If the
+ * upper parts are equal (z), then this one will proceed to check the
+ * rest.
+ */
+static u8 arc_cmpz_r(u8 *buf, u8 rb, u8 rc)
+{
+	const u32 insn = OPC_CMP | OP_B(rb) | OP_C(rc) | CC_equal;
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+/* neg Ra,Rb */
+static u8 arc_neg_r(u8 *buf, u8 ra, u8 rb)
+{
+	const u32 insn = OPC_NEG | OP_A(ra) | OP_B(rb);
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+/* mpy Ra,Rb,Rc */
+static u8 arc_mpy_r(u8 *buf, u8 ra, u8 rb, u8 rc)
+{
+	const u32 insn = OPC_MPY | OP_A(ra) | OP_B(rb) | OP_C(rc);
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+/* mpy Ra,Rb,imm */
+static u8 arc_mpy_i(u8 *buf, u8 ra, u8 rb, s32 imm)
+{
+	const u32 insn = OPC_MPYI | OP_A(ra) | OP_B(rb);
+
+	if (buf) {
+		emit_4_bytes(buf, insn);
+		emit_4_bytes(buf + INSN_len_normal, imm);
+	}
+	return INSN_len_normal + INSN_len_imm;
+}
+
+/* mpydu Ra,Ra,Rc */
+static u8 arc_mpydu_r(u8 *buf, u8 ra, u8 rc)
+{
+	const u32 insn = OPC_MPYDU | OP_A(ra) | OP_B(ra) | OP_C(rc);
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+/* mpydu Ra,Ra,imm */
+static u8 arc_mpydu_i(u8 *buf, u8 ra, s32 imm)
+{
+	const u32 insn = OPC_MPYDUI | OP_A(ra) | OP_B(ra);
+
+	if (buf) {
+		emit_4_bytes(buf, insn);
+		emit_4_bytes(buf + INSN_len_normal, imm);
+	}
+	return INSN_len_normal + INSN_len_imm;
+}
+
+/* divu Rd,Rd,Rs */
+static u8 arc_divu_r(u8 *buf, u8 rd, u8 rs)
+{
+	const u32 insn = OPC_DIVU | OP_A(rd) | OP_B(rd) | OP_C(rs);
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+/* divu Rd,Rd,imm */
+static u8 arc_divu_i(u8 *buf, u8 rd, s32 imm)
+{
+	const u32 insn = OPC_DIVUI | OP_A(rd) | OP_B(rd);
+
+	if (buf) {
+		emit_4_bytes(buf, insn);
+		emit_4_bytes(buf + INSN_len_normal, imm);
+	}
+	return INSN_len_normal + INSN_len_imm;
+}
+
+/* div Rd,Rd,Rs */
+static u8 arc_divs_r(u8 *buf, u8 rd, u8 rs)
+{
+	const u32 insn = OPC_DIVS | OP_A(rd) | OP_B(rd) | OP_C(rs);
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+/* div Rd,Rd,imm */
+static u8 arc_divs_i(u8 *buf, u8 rd, s32 imm)
+{
+	const u32 insn = OPC_DIVSI | OP_A(rd) | OP_B(rd);
+
+	if (buf) {
+		emit_4_bytes(buf, insn);
+		emit_4_bytes(buf + INSN_len_normal, imm);
+	}
+	return INSN_len_normal + INSN_len_imm;
+}
+
+/* remu Rd,Rd,Rs */
+static u8 arc_remu_r(u8 *buf, u8 rd, u8 rs)
+{
+	const u32 insn = OPC_REMU | OP_A(rd) | OP_B(rd) | OP_C(rs);
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+/* remu Rd,Rd,imm */
+static u8 arc_remu_i(u8 *buf, u8 rd, s32 imm)
+{
+	const u32 insn = OPC_REMUI | OP_A(rd) | OP_B(rd);
+
+	if (buf) {
+		emit_4_bytes(buf, insn);
+		emit_4_bytes(buf + INSN_len_normal, imm);
+	}
+	return INSN_len_normal + INSN_len_imm;
+}
+
+/* rem Rd,Rd,Rs */
+static u8 arc_rems_r(u8 *buf, u8 rd, u8 rs)
+{
+	const u32 insn = OPC_REMS | OP_A(rd) | OP_B(rd) | OP_C(rs);
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+/* rem Rd,Rd,imm */
+static u8 arc_rems_i(u8 *buf, u8 rd, s32 imm)
+{
+	const u32 insn = OPC_REMSI | OP_A(rd) | OP_B(rd);
+
+	if (buf) {
+		emit_4_bytes(buf, insn);
+		emit_4_bytes(buf + INSN_len_normal, imm);
+	}
+	return INSN_len_normal + INSN_len_imm;
+}
+
+/* and Rd,Rd,Rs */
+static u8 arc_and_r(u8 *buf, u8 rd, u8 rs)
+{
+	const u32 insn = OPC_AND | OP_A(rd) | OP_B(rd) | OP_C(rs);
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+/* and Rd,Rd,limm */
+static u8 arc_and_i(u8 *buf, u8 rd, s32 imm)
+{
+	const u32 insn = OPC_ANDI | OP_A(rd) | OP_B(rd);
+
+	if (buf) {
+		emit_4_bytes(buf, insn);
+		emit_4_bytes(buf + INSN_len_normal, imm);
+	}
+	return INSN_len_normal + INSN_len_imm;
+}
+
+/* tst Rd,Rs */
+static u8 arc_tst_r(u8 *buf, u8 rd, u8 rs)
+{
+	const u32 insn = OPC_TST | OP_B(rd) | OP_C(rs);
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+/*
+ * This particular version, "tst.z ...", is meant to be used after a
+ * "tst" on the low 32-bit of register pairs. If that "tst" is not
+ * zero, then we don't need to test the upper 32-bits lest it sets
+ * the zero flag.
+ */
+static u8 arc_tstz_r(u8 *buf, u8 rd, u8 rs)
+{
+	const u32 insn = OPC_TST | OP_B(rd) | OP_C(rs) | CC_equal;
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+static u8 arc_or_r(u8 *buf, u8 rd, u8 rs1, u8 rs2)
+{
+	const u32 insn = OPC_OR | OP_A(rd) | OP_B(rs1) | OP_C(rs2);
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+static u8 arc_or_i(u8 *buf, u8 rd, s32 imm)
+{
+	const u32 insn = OPC_ORI | OP_A(rd) | OP_B(rd);
+
+	if (buf) {
+		emit_4_bytes(buf, insn);
+		emit_4_bytes(buf + INSN_len_normal, imm);
+	}
+	return INSN_len_normal + INSN_len_imm;
+}
+
+static u8 arc_xor_r(u8 *buf, u8 rd, u8 rs)
+{
+	const u32 insn = OPC_XOR | OP_A(rd) | OP_B(rd) | OP_C(rs);
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+static u8 arc_xor_i(u8 *buf, u8 rd, s32 imm)
+{
+	const u32 insn = OPC_XORI | OP_A(rd) | OP_B(rd);
+
+	if (buf) {
+		emit_4_bytes(buf, insn);
+		emit_4_bytes(buf + INSN_len_normal, imm);
+	}
+	return INSN_len_normal + INSN_len_imm;
+}
+
+static u8 arc_not_r(u8 *buf, u8 rd, u8 rs)
+{
+	const u32 insn = OPC_NOT | OP_B(rd) | OP_C(rs);
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+static u8 arc_btst_i(u8 *buf, u8 rs, u8 imm)
+{
+	const u32 insn = OPC_BTSTU6 | OP_B(rs) | BTST_U6(imm);
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+static u8 arc_asl_r(u8 *buf, u8 rd, u8 rs1, u8 rs2)
+{
+	const u32 insn = OPC_ASL | OP_A(rd) | OP_B(rs1) | OP_C(rs2);
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+static u8 arc_asli_r(u8 *buf, u8 rd, u8 rs, u8 imm)
+{
+	const u32 insn = OPC_ASLI | OP_A(rd) | OP_B(rs) | ASLI_U6(imm);
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+static u8 arc_asr_r(u8 *buf, u8 rd, u8 rs1, u8 rs2)
+{
+	const u32 insn = OPC_ASR | OP_A(rd) | OP_B(rs1) | OP_C(rs2);
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+static u8 arc_asri_r(u8 *buf, u8 rd, u8 rs, u8 imm)
+{
+	const u32 insn = OPC_ASRI | OP_A(rd) | OP_B(rs) | ASRI_U6(imm);
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+static u8 arc_lsr_r(u8 *buf, u8 rd, u8 rs1, u8 rs2)
+{
+	const u32 insn = OPC_LSR | OP_A(rd) | OP_B(rs1) | OP_C(rs2);
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+static u8 arc_lsri_r(u8 *buf, u8 rd, u8 rs, u8 imm)
+{
+	const u32 insn = OPC_LSRI | OP_A(rd) | OP_B(rs) | LSRI_U6(imm);
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+static u8 arc_swape_r(u8 *buf, u8 r)
+{
+	const u32 insn = OPC_SWAPE | OP_B(r) | OP_C(r);
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+static u8 arc_jmp_return(u8 *buf)
+{
+	if (buf)
+		emit_4_bytes(buf, OPC_J_BLINK);
+	return INSN_len_normal;
+}
+
+static u8 arc_jl(u8 *buf, u8 reg)
+{
+	const u32 insn = OPC_JL | OP_C(reg);
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+/*
+ * Conditional jump to an address that is max 21 bits away (signed).
+ *
+ * b<cc> s21
+ */
+static u8 arc_bcc(u8 *buf, u8 cc, int offset)
+{
+	const u32 insn = OPC_BCC | BCC_S21(offset) | COND(cc);
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+/*
+ * Unconditional jump to an address that is max 25 bits away (signed).
+ *
+ * b     s25
+ */
+static u8 arc_b(u8 *buf, s32 offset)
+{
+	const u32 insn = OPC_B | B_S25(offset);
+
+	if (buf)
+		emit_4_bytes(buf, insn);
+	return INSN_len_normal;
+}
+
+/************* Packers (Deal with BPF_REGs) **************/
+
+u8 zext(u8 *buf, u8 rd)
+{
+	if (rd != BPF_REG_FP)
+		return arc_movi_r(buf, REG_HI(rd), 0);
+	else
+		return 0;
+}
+
+u8 mov_r32(u8 *buf, u8 rd, u8 rs, u8 sign_ext)
+{
+	u8 len = 0;
+
+	if (sign_ext) {
+		if (sign_ext == 8)
+			len = arc_sexb_r(buf, REG_LO(rd), REG_LO(rs));
+		else if (sign_ext == 16)
+			len = arc_sexh_r(buf, REG_LO(rd), REG_LO(rs));
+		else if (sign_ext == 32 && rd != rs)
+			len = arc_mov_r(buf, REG_LO(rd), REG_LO(rs));
+
+		return len;
+	}
+
+	/* Unsigned move. */
+
+	if (rd != rs)
+		len = arc_mov_r(buf, REG_LO(rd), REG_LO(rs));
+
+	return len;
+}
+
+u8 mov_r32_i32(u8 *buf, u8 reg, s32 imm)
+{
+	return arc_mov_i(buf, REG_LO(reg), imm);
+}
+
+u8 mov_r64(u8 *buf, u8 rd, u8 rs, u8 sign_ext)
+{
+	u8 len = 0;
+
+	if (sign_ext) {
+		/* First handle the low 32-bit part. */
+		len = mov_r32(buf, rd, rs, sign_ext);
+
+		/* Now propagate the sign bit of LO to HI. */
+		if (sign_ext == 8 || sign_ext == 16 || sign_ext == 32) {
+			len += arc_asri_r(BUF(buf, len),
+					  REG_HI(rd), REG_LO(rd), 31);
+		}
+
+		return len;
+	}
+
+	/* Unsigned move. */
+
+	if (rd == rs)
+		return 0;
+
+	len = arc_mov_r(buf, REG_LO(rd), REG_LO(rs));
+
+	if (rs != BPF_REG_FP)
+		len += arc_mov_r(BUF(buf, len), REG_HI(rd), REG_HI(rs));
+	/* BPF_REG_FP is mapped to 32-bit "fp" register. */
+	else
+		len += arc_movi_r(BUF(buf, len), REG_HI(rd), 0);
+
+	return len;
+}
+
+/* Sign extend the 32-bit immediate into 64-bit register pair. */
+u8 mov_r64_i32(u8 *buf, u8 reg, s32 imm)
+{
+	u8 len = 0;
+
+	len = arc_mov_i(buf, REG_LO(reg), imm);
+
+	/* BPF_REG_FP is mapped to 32-bit "fp" register. */
+	if (reg != BPF_REG_FP) {
+		if (imm >= 0)
+			len += arc_movi_r(BUF(buf, len), REG_HI(reg), 0);
+		else
+			len += arc_movi_r(BUF(buf, len), REG_HI(reg), -1);
+	}
+
+	return len;
+}
+
+/*
+ * This is merely used for translation of "LD R, IMM64" instructions
+ * of the BPF. These sort of instructions are sometimes used for
+ * relocations. If during the normal pass, the relocation value is
+ * not known, the BPF instruction may look something like:
+ *
+ * LD R <- 0x0000_0001_0000_0001
+ *
+ * Which will nicely translate to two 4-byte ARC instructions:
+ *
+ * mov R_lo, 1               # imm is small enough to be s12
+ * mov R_hi, 1               # same
+ *
+ * However, during the extra pass, the IMM64 will have changed
+ * to the resolved address and looks something like:
+ *
+ * LD R <- 0x0000_0000_1234_5678
+ *
+ * Now, the translated code will require 12 bytes:
+ *
+ * mov R_lo, 0x12345678      # this is an 8-byte instruction
+ * mov R_hi, 0               # still 4 bytes
+ *
+ * Which in practice will result in overwriting the following
+ * instruction. To avoid such cases, we will always emit codes
+ * with fixed sizes.
+ */
+u8 mov_r64_i64(u8 *buf, u8 reg, u32 lo, u32 hi)
+{
+	u8 len;
+
+	len  = arc_mov_i_fixed(buf, REG_LO(reg), lo);
+	len += arc_mov_i_fixed(BUF(buf, len), REG_HI(reg), hi);
+
+	return len;
+}
+
+/*
+ * If the "off"set is too big (doesn't encode as S9) for:
+ *
+ *   {ld,st}  r, [rm, off]
+ *
+ * Then emit:
+ *
+ *   add r10, REG_LO(rm), off
+ *
+ * and make sure that r10 becomes the effective address:
+ *
+ *   {ld,st}  r, [r10, 0]
+ */
+static u8 adjust_mem_access(u8 *buf, s16 *off, u8 size,
+			    u8 rm, u8 *arc_reg_mem)
+{
+	u8 len = 0;
+	*arc_reg_mem = REG_LO(rm);
+
+	if (!IN_S9_RANGE(*off) ||
+	    (size == BPF_DW && !IN_S9_RANGE(*off + 4))) {
+		len += arc_add_i(BUF(buf, len),
+				 REG_LO(JIT_REG_TMP), REG_LO(rm), (u32)(*off));
+		*arc_reg_mem = REG_LO(JIT_REG_TMP);
+		*off = 0;
+	}
+
+	return len;
+}
+
+/* store rs, [rd, off] */
+u8 store_r(u8 *buf, u8 rs, u8 rd, s16 off, u8 size)
+{
+	u8 len, arc_reg_mem;
+
+	len = adjust_mem_access(buf, &off, size, rd, &arc_reg_mem);
+
+	if (size == BPF_DW) {
+		len += arc_st_r(BUF(buf, len), REG_LO(rs), arc_reg_mem,
+				off, ZZ_4_byte);
+		len += arc_st_r(BUF(buf, len), REG_HI(rs), arc_reg_mem,
+				off + 4, ZZ_4_byte);
+	} else {
+		u8 zz = bpf_to_arc_size(size);
+
+		len += arc_st_r(BUF(buf, len), REG_LO(rs), arc_reg_mem,
+				off, zz);
+	}
+
+	return len;
+}
+
+/*
+ * For {8,16,32}-bit stores:
+ *   mov r21, imm
+ *   st  r21, [...]
+ * For 64-bit stores:
+ *   mov r21, imm
+ *   st  r21, [...]
+ *   mov r21, {0,-1}
+ *   st  r21, [...+4]
+ */
+u8 store_i(u8 *buf, s32 imm, u8 rd, s16 off, u8 size)
+{
+	u8 len, arc_reg_mem;
+	/* REG_LO(JIT_REG_TMP) might be used by "adjust_mem_access()". */
+	const u8 arc_rs = REG_HI(JIT_REG_TMP);
+
+	len = adjust_mem_access(buf, &off, size, rd, &arc_reg_mem);
+
+	if (size == BPF_DW) {
+		len += arc_mov_i(BUF(buf, len), arc_rs, imm);
+		len += arc_st_r(BUF(buf, len), arc_rs, arc_reg_mem,
+				off, ZZ_4_byte);
+		imm = (imm >= 0 ? 0 : -1);
+		len += arc_mov_i(BUF(buf, len), arc_rs, imm);
+		len += arc_st_r(BUF(buf, len), arc_rs, arc_reg_mem,
+				off + 4, ZZ_4_byte);
+	} else {
+		u8 zz = bpf_to_arc_size(size);
+
+		len += arc_mov_i(BUF(buf, len), arc_rs, imm);
+		len += arc_st_r(BUF(buf, len), arc_rs, arc_reg_mem, off, zz);
+	}
+
+	return len;
+}
+
+/*
+ * For the calling convention of a little endian machine, the LO part
+ * must be on top of the stack.
+ */
+static u8 push_r64(u8 *buf, u8 reg)
+{
+	u8 len = 0;
+
+#ifdef __LITTLE_ENDIAN
+	/* BPF_REG_FP is mapped to 32-bit "fp" register. */
+	if (reg != BPF_REG_FP)
+		len += arc_push_r(BUF(buf, len), REG_HI(reg));
+	len += arc_push_r(BUF(buf, len), REG_LO(reg));
+#else
+	len += arc_push_r(BUF(buf, len), REG_LO(reg));
+	if (reg != BPF_REG_FP)
+		len += arc_push_r(BUF(buf, len), REG_HI(reg));
+#endif
+
+	return len;
+}
+
+/* load rd, [rs, off] */
+u8 load_r(u8 *buf, u8 rd, u8 rs, s16 off, u8 size, bool sign_ext)
+{
+	u8 len, arc_reg_mem;
+
+	len = adjust_mem_access(buf, &off, size, rs, &arc_reg_mem);
+
+	if (size == BPF_B || size == BPF_H || size == BPF_W) {
+		const u8 zz = bpf_to_arc_size(size);
+
+		/* Use LD.X only if the data size is less than 32-bit. */
+		if (sign_ext && (zz == ZZ_1_byte || zz == ZZ_2_byte)) {
+			len += arc_ldx_r(BUF(buf, len), REG_LO(rd),
+					 arc_reg_mem, off, zz);
+		} else {
+			len += arc_ld_r(BUF(buf, len), REG_LO(rd),
+					arc_reg_mem, off, zz);
+		}
+
+		if (sign_ext) {
+			/* Propagate the sign bit to the higher reg. */
+			len += arc_asri_r(BUF(buf, len),
+					  REG_HI(rd), REG_LO(rd), 31);
+		} else {
+			len += arc_movi_r(BUF(buf, len), REG_HI(rd), 0);
+		}
+	} else if (size == BPF_DW) {
+		/*
+		 * We are about to issue 2 consecutive loads:
+		 *
+		 *   ld rx, [rb, off+0]
+		 *   ld ry, [rb, off+4]
+		 *
+		 * If "rx" and "rb" are the same registers, then the order
+		 * should change to guarantee that "rb" remains intact
+		 * during these 2 operations:
+		 *
+		 *   ld ry, [rb, off+4]
+		 *   ld rx, [rb, off+0]
+		 */
+		if (REG_LO(rd) != arc_reg_mem) {
+			len += arc_ld_r(BUF(buf, len), REG_LO(rd), arc_reg_mem,
+					off, ZZ_4_byte);
+			len += arc_ld_r(BUF(buf, len), REG_HI(rd), arc_reg_mem,
+					off + 4, ZZ_4_byte);
+		} else {
+			len += arc_ld_r(BUF(buf, len), REG_HI(rd), arc_reg_mem,
+					off + 4, ZZ_4_byte);
+			len += arc_ld_r(BUF(buf, len), REG_LO(rd), arc_reg_mem,
+					off, ZZ_4_byte);
+		}
+	}
+
+	return len;
+}
+
+u8 add_r32(u8 *buf, u8 rd, u8 rs)
+{
+	return arc_add_r(buf, REG_LO(rd), REG_LO(rs));
+}
+
+u8 add_r32_i32(u8 *buf, u8 rd, s32 imm)
+{
+	if (IN_U6_RANGE(imm))
+		return arc_addi_r(buf, REG_LO(rd), imm);
+	else
+		return arc_add_i(buf, REG_LO(rd), REG_LO(rd), imm);
+}
+
+u8 add_r64(u8 *buf, u8 rd, u8 rs)
+{
+	u8 len;
+
+	len  = arc_addf_r(buf, REG_LO(rd), REG_LO(rs));
+	len += arc_adc_r(BUF(buf, len), REG_HI(rd), REG_HI(rs));
+	return len;
+}
+
+u8 add_r64_i32(u8 *buf, u8 rd, s32 imm)
+{
+	u8 len;
+
+	if (IN_U6_RANGE(imm)) {
+		len  = arc_addif_r(buf, REG_LO(rd), imm);
+		len += arc_adci_r(BUF(buf, len), REG_HI(rd), 0);
+	} else {
+		len  = mov_r64_i32(buf, JIT_REG_TMP, imm);
+		len += add_r64(BUF(buf, len), rd, JIT_REG_TMP);
+	}
+	return len;
+}
+
+u8 sub_r32(u8 *buf, u8 rd, u8 rs)
+{
+	return arc_sub_r(buf, REG_LO(rd), REG_LO(rs));
+}
+
+u8 sub_r32_i32(u8 *buf, u8 rd, s32 imm)
+{
+	if (IN_U6_RANGE(imm))
+		return arc_subi_r(buf, REG_LO(rd), imm);
+	else
+		return arc_sub_i(buf, REG_LO(rd), imm);
+}
+
+u8 sub_r64(u8 *buf, u8 rd, u8 rs)
+{
+	u8 len;
+
+	len  = arc_subf_r(buf, REG_LO(rd), REG_LO(rs));
+	len += arc_sbc_r(BUF(buf, len), REG_HI(rd), REG_HI(rs));
+	return len;
+}
+
+u8 sub_r64_i32(u8 *buf, u8 rd, s32 imm)
+{
+	u8 len;
+
+	len  = mov_r64_i32(buf, JIT_REG_TMP, imm);
+	len += sub_r64(BUF(buf, len), rd, JIT_REG_TMP);
+	return len;
+}
+
+static u8 cmp_r32(u8 *buf, u8 rd, u8 rs)
+{
+	return arc_cmp_r(buf, REG_LO(rd), REG_LO(rs));
+}
+
+u8 neg_r32(u8 *buf, u8 r)
+{
+	return arc_neg_r(buf, REG_LO(r), REG_LO(r));
+}
+
+/* In a two's complement system, -r is (~r + 1). */
+u8 neg_r64(u8 *buf, u8 r)
+{
+	u8 len;
+
+	len  = arc_not_r(buf, REG_LO(r), REG_LO(r));
+	len += arc_not_r(BUF(buf, len), REG_HI(r), REG_HI(r));
+	len += add_r64_i32(BUF(buf, len), r, 1);
+	return len;
+}
+
+u8 mul_r32(u8 *buf, u8 rd, u8 rs)
+{
+	return arc_mpy_r(buf, REG_LO(rd), REG_LO(rd), REG_LO(rs));
+}
+
+u8 mul_r32_i32(u8 *buf, u8 rd, s32 imm)
+{
+	return arc_mpy_i(buf, REG_LO(rd), REG_LO(rd), imm);
+}
+
+/*
+ * MUL B, C
+ * --------
+ * mpy       t0, B_hi, C_lo
+ * mpy       t1, B_lo, C_hi
+ * mpydu   B_lo, B_lo, C_lo
+ * add     B_hi, B_hi,   t0
+ * add     B_hi, B_hi,   t1
+ */
+u8 mul_r64(u8 *buf, u8 rd, u8 rs)
+{
+	const u8 t0   = REG_LO(JIT_REG_TMP);
+	const u8 t1   = REG_HI(JIT_REG_TMP);
+	const u8 C_lo = REG_LO(rs);
+	const u8 C_hi = REG_HI(rs);
+	const u8 B_lo = REG_LO(rd);
+	const u8 B_hi = REG_HI(rd);
+	u8 len;
+
+	len  = arc_mpy_r(buf, t0, B_hi, C_lo);
+	len += arc_mpy_r(BUF(buf, len), t1, B_lo, C_hi);
+	len += arc_mpydu_r(BUF(buf, len), B_lo, C_lo);
+	len += arc_add_r(BUF(buf, len), B_hi, t0);
+	len += arc_add_r(BUF(buf, len), B_hi, t1);
+
+	return len;
+}
+
+/*
+ * MUL B, imm
+ * ----------
+ *
+ *  To get a 64-bit result from a signed 64x32 multiplication:
+ *
+ *         B_hi             B_lo   *
+ *         sign             imm
+ *  -----------------------------
+ *  HI(B_lo*imm)     LO(B_lo*imm)  +
+ *     B_hi*imm                    +
+ *     B_lo*sign
+ *  -----------------------------
+ *        res_hi           res_lo
+ *
+ * mpy     t1, B_lo, sign(imm)
+ * mpy     t0, B_hi, imm
+ * mpydu B_lo, B_lo, imm
+ * add   B_hi, B_hi,  t0
+ * add   B_hi, B_hi,  t1
+ *
+ * Note: We can't use signed double multiplication, "mpyd", instead of an
+ * unsigned version, "mpydu", and then get rid of the sign adjustments
+ * calculated in "t1". The signed multiplication, "mpyd", will consider
+ * both operands, "B_lo" and "imm", as signed inputs. However, for this
+ * 64x32 multiplication, "B_lo" must be treated as an unsigned number.
+ */
+u8 mul_r64_i32(u8 *buf, u8 rd, s32 imm)
+{
+	const u8 t0   = REG_LO(JIT_REG_TMP);
+	const u8 t1   = REG_HI(JIT_REG_TMP);
+	const u8 B_lo = REG_LO(rd);
+	const u8 B_hi = REG_HI(rd);
+	u8 len = 0;
+
+	if (imm == 1)
+		return 0;
+
+	/* Is the sign-extension of the immediate "-1"? */
+	if (imm < 0)
+		len += arc_neg_r(BUF(buf, len), t1, B_lo);
+
+	len += arc_mpy_i(BUF(buf, len), t0, B_hi, imm);
+	len += arc_mpydu_i(BUF(buf, len), B_lo, imm);
+	len += arc_add_r(BUF(buf, len), B_hi, t0);
+
+	/* Add the "sign*B_lo" part, if necessary. */
+	if (imm < 0)
+		len += arc_add_r(BUF(buf, len), B_hi, t1);
+
+	return len;
+}
+
+u8 div_r32(u8 *buf, u8 rd, u8 rs, bool sign_ext)
+{
+	if (sign_ext)
+		return arc_divs_r(buf, REG_LO(rd), REG_LO(rs));
+	else
+		return arc_divu_r(buf, REG_LO(rd), REG_LO(rs));
+}
+
+u8 div_r32_i32(u8 *buf, u8 rd, s32 imm, bool sign_ext)
+{
+	if (imm == 0)
+		return 0;
+
+	if (sign_ext)
+		return arc_divs_i(buf, REG_LO(rd), imm);
+	else
+		return arc_divu_i(buf, REG_LO(rd), imm);
+}
+
+u8 mod_r32(u8 *buf, u8 rd, u8 rs, bool sign_ext)
+{
+	if (sign_ext)
+		return arc_rems_r(buf, REG_LO(rd), REG_LO(rs));
+	else
+		return arc_remu_r(buf, REG_LO(rd), REG_LO(rs));
+}
+
+u8 mod_r32_i32(u8 *buf, u8 rd, s32 imm, bool sign_ext)
+{
+	if (imm == 0)
+		return 0;
+
+	if (sign_ext)
+		return arc_rems_i(buf, REG_LO(rd), imm);
+	else
+		return arc_remu_i(buf, REG_LO(rd), imm);
+}
+
+u8 and_r32(u8 *buf, u8 rd, u8 rs)
+{
+	return arc_and_r(buf, REG_LO(rd), REG_LO(rs));
+}
+
+u8 and_r32_i32(u8 *buf, u8 rd, s32 imm)
+{
+	return arc_and_i(buf, REG_LO(rd), imm);
+}
+
+u8 and_r64(u8 *buf, u8 rd, u8 rs)
+{
+	u8 len;
+
+	len  = arc_and_r(buf, REG_LO(rd), REG_LO(rs));
+	len += arc_and_r(BUF(buf, len), REG_HI(rd), REG_HI(rs));
+	return len;
+}
+
+u8 and_r64_i32(u8 *buf, u8 rd, s32 imm)
+{
+	u8 len;
+
+	len  = mov_r64_i32(buf, JIT_REG_TMP, imm);
+	len += and_r64(BUF(buf, len), rd, JIT_REG_TMP);
+	return len;
+}
+
+static u8 tst_r32(u8 *buf, u8 rd, u8 rs)
+{
+	return arc_tst_r(buf, REG_LO(rd), REG_LO(rs));
+}
+
+u8 or_r32(u8 *buf, u8 rd, u8 rs)
+{
+	return arc_or_r(buf, REG_LO(rd), REG_LO(rd), REG_LO(rs));
+}
+
+u8 or_r32_i32(u8 *buf, u8 rd, s32 imm)
+{
+	return arc_or_i(buf, REG_LO(rd), imm);
+}
+
+u8 or_r64(u8 *buf, u8 rd, u8 rs)
+{
+	u8 len;
+
+	len  = arc_or_r(buf, REG_LO(rd), REG_LO(rd), REG_LO(rs));
+	len += arc_or_r(BUF(buf, len), REG_HI(rd), REG_HI(rd), REG_HI(rs));
+	return len;
+}
+
+u8 or_r64_i32(u8 *buf, u8 rd, s32 imm)
+{
+	u8 len;
+
+	len  = mov_r64_i32(buf, JIT_REG_TMP, imm);
+	len += or_r64(BUF(buf, len), rd, JIT_REG_TMP);
+	return len;
+}
+
+u8 xor_r32(u8 *buf, u8 rd, u8 rs)
+{
+	return arc_xor_r(buf, REG_LO(rd), REG_LO(rs));
+}
+
+u8 xor_r32_i32(u8 *buf, u8 rd, s32 imm)
+{
+	return arc_xor_i(buf, REG_LO(rd), imm);
+}
+
+u8 xor_r64(u8 *buf, u8 rd, u8 rs)
+{
+	u8 len;
+
+	len  = arc_xor_r(buf, REG_LO(rd), REG_LO(rs));
+	len += arc_xor_r(BUF(buf, len), REG_HI(rd), REG_HI(rs));
+	return len;
+}
+
+u8 xor_r64_i32(u8 *buf, u8 rd, s32 imm)
+{
+	u8 len;
+
+	len  = mov_r64_i32(buf, JIT_REG_TMP, imm);
+	len += xor_r64(BUF(buf, len), rd, JIT_REG_TMP);
+	return len;
+}
+
+/* "asl a,b,c" --> "a = (b << (c & 31))". */
+u8 lsh_r32(u8 *buf, u8 rd, u8 rs)
+{
+	return arc_asl_r(buf, REG_LO(rd), REG_LO(rd), REG_LO(rs));
+}
+
+u8 lsh_r32_i32(u8 *buf, u8 rd, u8 imm)
+{
+	return arc_asli_r(buf, REG_LO(rd), REG_LO(rd), imm);
+}
+
+/*
+ * algorithm
+ * ---------
+ * if (n <= 32)
+ *   to_hi = lo >> (32-n)   # (32-n) is the negate of "n" in a 5-bit width.
+ *   lo <<= n
+ *   hi <<= n
+ *   hi |= to_hi
+ * else
+ *   hi = lo << (n-32)
+ *   lo = 0
+ *
+ * assembly translation for "LSH B, C"
+ * (heavily influenced by ARC gcc)
+ * -----------------------------------
+ * not    t0, C_lo            # The first 3 lines are almost the same as:
+ * lsr    t1, B_lo, 1         #   neg   t0, C_lo
+ * lsr    t1, t1, t0          #   lsr   t1, B_lo, t0   --> t1 is "to_hi"
+ * mov    t0, C_lo*           # with one important difference. In "neg"
+ * asl    B_lo, B_lo, t0      # version, when C_lo=0, t1 becomes B_lo while
+ * asl    B_hi, B_hi, t0      # it should be 0. The "not" approach instead,
+ * or     B_hi, B_hi, t1      # "shift"s t1 once and 31 times, practically
+ * btst   t0, 5               # setting it to 0 when C_lo=0.
+ * mov.ne B_hi, B_lo**
+ * mov.ne B_lo, 0
+ *
+ * *The "mov t0, C_lo" is necessary to cover the cases that C is the same
+ * register as B.
+ *
+ * **ARC performs a shift in this manner: B <<= (C & 31)
+ * For 32<=n<64, "n-32" and "n&31" are the same. Therefore, "B << n" and
+ * "B << (n-32)" yield the same results. e.g. the results of "B << 35" and
+ * "B << 3" are the same.
+ *
+ * The behaviour is undefined for n >= 64.
+ */
+u8 lsh_r64(u8 *buf, u8 rd, u8 rs)
+{
+	const u8 t0   = REG_LO(JIT_REG_TMP);
+	const u8 t1   = REG_HI(JIT_REG_TMP);
+	const u8 C_lo = REG_LO(rs);
+	const u8 B_lo = REG_LO(rd);
+	const u8 B_hi = REG_HI(rd);
+	u8 len;
+
+	len  = arc_not_r(buf, t0, C_lo);
+	len += arc_lsri_r(BUF(buf, len), t1, B_lo, 1);
+	len += arc_lsr_r(BUF(buf, len), t1, t1, t0);
+	len += arc_mov_r(BUF(buf, len), t0, C_lo);
+	len += arc_asl_r(BUF(buf, len), B_lo, B_lo, t0);
+	len += arc_asl_r(BUF(buf, len), B_hi, B_hi, t0);
+	len += arc_or_r(BUF(buf, len), B_hi, B_hi, t1);
+	len += arc_btst_i(BUF(buf, len), t0, 5);
+	len += arc_mov_cc_r(BUF(buf, len), CC_unequal, B_hi, B_lo);
+	len += arc_movu_cc_r(BUF(buf, len), CC_unequal, B_lo, 0);
+
+	return len;
+}
+
+/*
+ * if (n < 32)
+ *   to_hi = B_lo >> 32-n          # extract upper n bits
+ *   lo <<= n
+ *   hi <<=n
+ *   hi |= to_hi
+ * else if (n < 64)
+ *   hi = lo << n-32
+ *   lo = 0
+ */
+u8 lsh_r64_i32(u8 *buf, u8 rd, s32 imm)
+{
+	const u8 t0   = REG_LO(JIT_REG_TMP);
+	const u8 B_lo = REG_LO(rd);
+	const u8 B_hi = REG_HI(rd);
+	const u8 n    = (u8)imm;
+	u8 len = 0;
+
+	if (n == 0) {
+		return 0;
+	} else if (n <= 31) {
+		len  = arc_lsri_r(buf, t0, B_lo, 32 - n);
+		len += arc_asli_r(BUF(buf, len), B_lo, B_lo, n);
+		len += arc_asli_r(BUF(buf, len), B_hi, B_hi, n);
+		len += arc_or_r(BUF(buf, len), B_hi, B_hi, t0);
+	} else if (n <= 63) {
+		len  = arc_asli_r(buf, B_hi, B_lo, n - 32);
+		len += arc_movi_r(BUF(buf, len), B_lo, 0);
+	}
+	/* n >= 64 is undefined behaviour. */
+
+	return len;
+}
+
+/* "lsr a,b,c" --> "a = (b >> (c & 31))". */
+u8 rsh_r32(u8 *buf, u8 rd, u8 rs)
+{
+	return arc_lsr_r(buf, REG_LO(rd), REG_LO(rd), REG_LO(rs));
+}
+
+u8 rsh_r32_i32(u8 *buf, u8 rd, u8 imm)
+{
+	return arc_lsri_r(buf, REG_LO(rd), REG_LO(rd), imm);
+}
+
+/*
+ * For better commentary, see lsh_r64().
+ *
+ * algorithm
+ * ---------
+ * if (n <= 32)
+ *   to_lo = hi << (32-n)
+ *   hi >>= n
+ *   lo >>= n
+ *   lo |= to_lo
+ * else
+ *   lo = hi >> (n-32)
+ *   hi = 0
+ *
+ * RSH    B,C
+ * ----------
+ * not    t0, C_lo
+ * asl    t1, B_hi, 1
+ * asl    t1, t1, t0
+ * mov    t0, C_lo
+ * lsr    B_hi, B_hi, t0
+ * lsr    B_lo, B_lo, t0
+ * or     B_lo, B_lo, t1
+ * btst   t0, 5
+ * mov.ne B_lo, B_hi
+ * mov.ne B_hi, 0
+ */
+u8 rsh_r64(u8 *buf, u8 rd, u8 rs)
+{
+	const u8 t0   = REG_LO(JIT_REG_TMP);
+	const u8 t1   = REG_HI(JIT_REG_TMP);
+	const u8 C_lo = REG_LO(rs);
+	const u8 B_lo = REG_LO(rd);
+	const u8 B_hi = REG_HI(rd);
+	u8 len;
+
+	len  = arc_not_r(buf, t0, C_lo);
+	len += arc_asli_r(BUF(buf, len), t1, B_hi, 1);
+	len += arc_asl_r(BUF(buf, len), t1, t1, t0);
+	len += arc_mov_r(BUF(buf, len), t0, C_lo);
+	len += arc_lsr_r(BUF(buf, len), B_hi, B_hi, t0);
+	len += arc_lsr_r(BUF(buf, len), B_lo, B_lo, t0);
+	len += arc_or_r(BUF(buf, len), B_lo, B_lo, t1);
+	len += arc_btst_i(BUF(buf, len), t0, 5);
+	len += arc_mov_cc_r(BUF(buf, len), CC_unequal, B_lo, B_hi);
+	len += arc_movu_cc_r(BUF(buf, len), CC_unequal, B_hi, 0);
+
+	return len;
+}
+
+/*
+ * if (n < 32)
+ *   to_lo = B_lo << 32-n     # extract lower n bits, right-padded with 32-n 0s
+ *   lo >>=n
+ *   hi >>=n
+ *   hi |= to_lo
+ * else if (n < 64)
+ *   lo = hi >> n-32
+ *   hi = 0
+ */
+u8 rsh_r64_i32(u8 *buf, u8 rd, s32 imm)
+{
+	const u8 t0   = REG_LO(JIT_REG_TMP);
+	const u8 B_lo = REG_LO(rd);
+	const u8 B_hi = REG_HI(rd);
+	const u8 n    = (u8)imm;
+	u8 len = 0;
+
+	if (n == 0) {
+		return 0;
+	} else if (n <= 31) {
+		len  = arc_asli_r(buf, t0, B_hi, 32 - n);
+		len += arc_lsri_r(BUF(buf, len), B_lo, B_lo, n);
+		len += arc_lsri_r(BUF(buf, len), B_hi, B_hi, n);
+		len += arc_or_r(BUF(buf, len), B_lo, B_lo, t0);
+	} else if (n <= 63) {
+		len  = arc_lsri_r(buf, B_lo, B_hi, n - 32);
+		len += arc_movi_r(BUF(buf, len), B_hi, 0);
+	}
+	/* n >= 64 is undefined behaviour. */
+
+	return len;
+}
+
+/* "asr a,b,c" --> "a = (b s>> (c & 31))". */
+u8 arsh_r32(u8 *buf, u8 rd, u8 rs)
+{
+	return arc_asr_r(buf, REG_LO(rd), REG_LO(rd), REG_LO(rs));
+}
+
+u8 arsh_r32_i32(u8 *buf, u8 rd, u8 imm)
+{
+	return arc_asri_r(buf, REG_LO(rd), REG_LO(rd), imm);
+}
+
+/*
+ * For comparison, see rsh_r64().
+ *
+ * algorithm
+ * ---------
+ * if (n <= 32)
+ *   to_lo = hi << (32-n)
+ *   hi s>>= n
+ *   lo  >>= n
+ *   lo |= to_lo
+ * else
+ *   hi_sign = hi s>>31
+ *   lo = hi s>> (n-32)
+ *   hi = hi_sign
+ *
+ * ARSH   B,C
+ * ----------
+ * not    t0, C_lo
+ * asl    t1, B_hi, 1
+ * asl    t1, t1, t0
+ * mov    t0, C_lo
+ * asr    B_hi, B_hi, t0
+ * lsr    B_lo, B_lo, t0
+ * or     B_lo, B_lo, t1
+ * btst   t0, 5
+ * asr    t0, B_hi, 31        # now, t0 = 0 or -1 based on B_hi's sign
+ * mov.ne B_lo, B_hi
+ * mov.ne B_hi, t0
+ */
+u8 arsh_r64(u8 *buf, u8 rd, u8 rs)
+{
+	const u8 t0   = REG_LO(JIT_REG_TMP);
+	const u8 t1   = REG_HI(JIT_REG_TMP);
+	const u8 C_lo = REG_LO(rs);
+	const u8 B_lo = REG_LO(rd);
+	const u8 B_hi = REG_HI(rd);
+	u8 len;
+
+	len  = arc_not_r(buf, t0, C_lo);
+	len += arc_asli_r(BUF(buf, len), t1, B_hi, 1);
+	len += arc_asl_r(BUF(buf, len), t1, t1, t0);
+	len += arc_mov_r(BUF(buf, len), t0, C_lo);
+	len += arc_asr_r(BUF(buf, len), B_hi, B_hi, t0);
+	len += arc_lsr_r(BUF(buf, len), B_lo, B_lo, t0);
+	len += arc_or_r(BUF(buf, len), B_lo, B_lo, t1);
+	len += arc_btst_i(BUF(buf, len), t0, 5);
+	len += arc_asri_r(BUF(buf, len), t0, B_hi, 31);
+	len += arc_mov_cc_r(BUF(buf, len), CC_unequal, B_lo, B_hi);
+	len += arc_mov_cc_r(BUF(buf, len), CC_unequal, B_hi, t0);
+
+	return len;
+}
+
+/*
+ * if (n < 32)
+ *   to_lo = lo << 32-n     # extract lower n bits, right-padded with 32-n 0s
+ *   lo >>=n
+ *   hi s>>=n
+ *   hi |= to_lo
+ * else if (n < 64)
+ *   lo = hi s>> n-32
+ *   hi = (lo[msb] ? -1 : 0)
+ */
+u8 arsh_r64_i32(u8 *buf, u8 rd, s32 imm)
+{
+	const u8 t0   = REG_LO(JIT_REG_TMP);
+	const u8 B_lo = REG_LO(rd);
+	const u8 B_hi = REG_HI(rd);
+	const u8 n    = (u8)imm;
+	u8 len = 0;
+
+	if (n == 0) {
+		return 0;
+	} else if (n <= 31) {
+		len  = arc_asli_r(buf, t0, B_hi, 32 - n);
+		len += arc_lsri_r(BUF(buf, len), B_lo, B_lo, n);
+		len += arc_asri_r(BUF(buf, len), B_hi, B_hi, n);
+		len += arc_or_r(BUF(buf, len), B_lo, B_lo, t0);
+	} else if (n <= 63) {
+		len  = arc_asri_r(buf, B_lo, B_hi, n - 32);
+		len += arc_movi_r(BUF(buf, len), B_hi, -1);
+		len += arc_btst_i(BUF(buf, len), B_lo, 31);
+		len += arc_movu_cc_r(BUF(buf, len), CC_equal, B_hi, 0);
+	}
+	/* n >= 64 is undefined behaviour. */
+
+	return len;
+}
+
+u8 gen_swap(u8 *buf, u8 rd, u8 size, u8 endian, bool force, bool do_zext)
+{
+	u8 len = 0;
+#ifdef __BIG_ENDIAN
+	const u8 host_endian = BPF_FROM_BE;
+#else
+	const u8 host_endian = BPF_FROM_LE;
+#endif
+	if (host_endian != endian || force) {
+		switch (size) {
+		case 16:
+			/*
+			 * r = B4B3_B2B1 << 16 --> r = B2B1_0000
+			 * then, swape(r) would become the desired 0000_B1B2
+			 */
+			len = arc_asli_r(buf, REG_LO(rd), REG_LO(rd), 16);
+			fallthrough;
+		case 32:
+			len += arc_swape_r(BUF(buf, len), REG_LO(rd));
+			if (do_zext)
+				len += zext(BUF(buf, len), rd);
+			break;
+		case 64:
+			/*
+			 * swap "hi" and "lo":
+			 *   hi ^= lo;
+			 *   lo ^= hi;
+			 *   hi ^= lo;
+			 * and then swap the bytes in "hi" and "lo".
+			 */
+			len  = arc_xor_r(buf, REG_HI(rd), REG_LO(rd));
+			len += arc_xor_r(BUF(buf, len), REG_LO(rd), REG_HI(rd));
+			len += arc_xor_r(BUF(buf, len), REG_HI(rd), REG_LO(rd));
+			len += arc_swape_r(BUF(buf, len), REG_LO(rd));
+			len += arc_swape_r(BUF(buf, len), REG_HI(rd));
+			break;
+		default:
+			/* The caller must have handled this. */
+			break;
+		}
+	} else {
+		/*
+		 * If the same endianness, there's not much to do other
+		 * than zeroing out the upper bytes based on the "size".
+		 */
+		switch (size) {
+		case 16:
+			len = arc_and_i(buf, REG_LO(rd), 0xffff);
+			fallthrough;
+		case 32:
+			if (do_zext)
+				len += zext(BUF(buf, len), rd);
+			break;
+		case 64:
+			break;
+		default:
+			/* The caller must have handled this. */
+			break;
+		}
+	}
+
+	return len;
+}
+
+/*
+ * To create a frame, all that is needed is:
+ *
+ *  push fp
+ *  mov  fp, sp
+ *  sub  sp, <frame_size>
+ *
+ * "push fp" is taken care of separately while saving the clobbered registers.
+ * All that remains is copying SP value to FP and shrinking SP's address space
+ * for any possible function call to come.
+ */
+static inline u8 frame_create(u8 *buf, u16 size)
+{
+	u8 len;
+
+	len = arc_mov_r(buf, ARC_R_FP, ARC_R_SP);
+	if (IN_U6_RANGE(size))
+		len += arc_subi_r(BUF(buf, len), ARC_R_SP, size);
+	else
+		len += arc_sub_i(BUF(buf, len), ARC_R_SP, size);
+	return len;
+}
+
+/*
+ * mov sp, fp
+ *
+ * The value of SP upon entering was copied to FP.
+ */
+static inline u8 frame_restore(u8 *buf)
+{
+	return arc_mov_r(buf, ARC_R_SP, ARC_R_FP);
+}
+
+/*
+ * Going from a JITed code to the native caller:
+ *
+ * mov ARC_ABI_RET_lo, BPF_REG_0_lo     # r0 <- r8
+ * mov ARC_ABI_RET_hi, BPF_REG_0_hi     # r1 <- r9
+ */
+static u8 bpf_to_arc_return(u8 *buf)
+{
+	u8 len;
+
+	len  = arc_mov_r(buf, ARC_R_0, REG_LO(BPF_REG_0));
+	len += arc_mov_r(BUF(buf, len), ARC_R_1, REG_HI(BPF_REG_0));
+	return len;
+}
+
+/*
+ * Coming back from an external (in-kernel) function to the JITed code:
+ *
+ * mov ARC_ABI_RET_lo, BPF_REG_0_lo     # r8 <- r0
+ * mov ARC_ABI_RET_hi, BPF_REG_0_hi     # r9 <- r1
+ */
+u8 arc_to_bpf_return(u8 *buf)
+{
+	u8 len;
+
+	len  = arc_mov_r(buf, REG_LO(BPF_REG_0), ARC_R_0);
+	len += arc_mov_r(BUF(buf, len), REG_HI(BPF_REG_0), ARC_R_1);
+	return len;
+}
+
+/*
+ * This translation leads to:
+ *
+ *   mov r10, addr                # always an 8-byte instruction
+ *   jl  [r10]
+ *
+ * The length of the "mov" must be fixed (8), otherwise it may diverge
+ * during the normal and extra passes:
+ *
+ *          normal pass                  extra pass
+ *
+ *   180:  mov     r10,0        |   180:  mov     r10,0x700578d8
+ *   184:  jl      [r10]        |   188:  jl      [r10]
+ *   188:  add.f   r16,r16,0x1  |   18c:  adc     r17,r17,0
+ *   18c:  adc     r17,r17,0    |
+ *
+ * In the above example, the change from "r10 <- 0" to "r10 <- 0x700578d8"
+ * has led to an increase in the length of the "mov" instruction.
+ * Inadvertently, that caused the loss of the "add.f" instruction.
+ */
+static u8 jump_and_link(u8 *buf, u32 addr)
+{
+	u8 len;
+
+	len  = arc_mov_i_fixed(buf, REG_LO(JIT_REG_TMP), addr);
+	len += arc_jl(BUF(buf, len), REG_LO(JIT_REG_TMP));
+	return len;
+}
+
+/*
+ * This function determines which ARC registers must be saved and restored.
+ * It does so by looking into:
+ *
+ * "bpf_reg": The clobbered (destination) BPF register
+ * "is_call": Indicator if the current instruction is a call
+ *
+ * When a register of interest is clobbered, its corresponding bit position
+ * in return value, "usage", is set to true.
+ */
+u32 mask_for_used_regs(u8 bpf_reg, bool is_call)
+{
+	u32 usage = 0;
+
+	/* BPF registers that must be saved. */
+	if (bpf_reg >= BPF_REG_6 && bpf_reg <= BPF_REG_9) {
+		usage |= BIT(REG_LO(bpf_reg));
+		usage |= BIT(REG_HI(bpf_reg));
+	/*
+	 * Using the frame pointer register implies that it should
+	 * be saved and reinitialised with the current frame data.
+	 */
+	} else if (bpf_reg == BPF_REG_FP) {
+		usage |= BIT(REG_LO(BPF_REG_FP));
+	/* Could there be some ARC registers that must to be saved? */
+	} else {
+		if (REG_LO(bpf_reg) >= ARC_CALLEE_SAVED_REG_FIRST &&
+		    REG_LO(bpf_reg) <= ARC_CALLEE_SAVED_REG_LAST)
+			usage |= BIT(REG_LO(bpf_reg));
+
+		if (REG_HI(bpf_reg) >= ARC_CALLEE_SAVED_REG_FIRST &&
+		    REG_HI(bpf_reg) <= ARC_CALLEE_SAVED_REG_LAST)
+			usage |= BIT(REG_HI(bpf_reg));
+	}
+
+	/* A "call" indicates that ARC's "blink" reg must be saved. */
+	usage |= is_call ? BIT(ARC_R_BLINK) : 0;
+
+	return usage;
+}
+
+/*
+ * push blink             # if blink is marked as clobbered
+ * push r[0-n]            # if r[i] is marked as clobbered
+ * push fp                # if fp is marked as clobbered
+ * mov  fp, sp            # if frame_size > 0 (clobbers fp)
+ * sub  sp, <frame_size>  # same as above
+ */
+u8 arc_prologue(u8 *buf, u32 usage, u16 frame_size)
+{
+	u8 len = 0;
+	u32 gp_regs = 0;
+
+	/* Deal with blink first. */
+	if (usage & BIT(ARC_R_BLINK))
+		len += arc_push_r(BUF(buf, len), ARC_R_BLINK);
+
+	gp_regs = usage & ~(BIT(ARC_R_BLINK) | BIT(ARC_R_FP));
+	while (gp_regs) {
+		u8 reg = __builtin_ffs(gp_regs) - 1;
+
+		len += arc_push_r(BUF(buf, len), reg);
+		gp_regs &= ~BIT(reg);
+	}
+
+	/* Deal with fp last. */
+	if ((usage & BIT(ARC_R_FP)) || frame_size > 0)
+		len += arc_push_r(BUF(buf, len), ARC_R_FP);
+
+	if (frame_size > 0)
+		len += frame_create(BUF(buf, len), frame_size);
+
+#ifdef ARC_BPF_JIT_DEBUG
+	if ((usage & BIT(ARC_R_FP)) && frame_size == 0) {
+		pr_err("FP is being saved while there is no frame.\n");
+		BUG();
+	}
+#endif
+
+	return len;
+}
+
+/*
+ * mov  sp, fp            # if frame_size > 0
+ * pop  fp                # if fp is marked as clobbered
+ * pop  r[n-0]            # if r[i] is marked as clobbered
+ * pop  blink             # if blink is marked as clobbered
+ * mov  r0, r8            # always: ABI_return <- BPF_return
+ * mov  r1, r9            # continuation of above
+ * j    [blink]           # always
+ *
+ * "fp being marked as clobbered" and "frame_size > 0" are the two sides of
+ * the same coin.
+ */
+u8 arc_epilogue(u8 *buf, u32 usage, u16 frame_size)
+{
+	u32 len = 0;
+	u32 gp_regs = 0;
+
+#ifdef ARC_BPF_JIT_DEBUG
+	if ((usage & BIT(ARC_R_FP)) && frame_size == 0) {
+		pr_err("FP is being saved while there is no frame.\n");
+		BUG();
+	}
+#endif
+
+	if (frame_size > 0)
+		len += frame_restore(BUF(buf, len));
+
+	/* Deal with fp first. */
+	if ((usage & BIT(ARC_R_FP)) || frame_size > 0)
+		len += arc_pop_r(BUF(buf, len), ARC_R_FP);
+
+	gp_regs = usage & ~(BIT(ARC_R_BLINK) | BIT(ARC_R_FP));
+	while (gp_regs) {
+		/* "usage" is 32-bit, each bit indicating an ARC register. */
+		u8 reg = 31 - __builtin_clz(gp_regs);
+
+		len += arc_pop_r(BUF(buf, len), reg);
+		gp_regs &= ~BIT(reg);
+	}
+
+	/* Deal with blink last. */
+	if (usage & BIT(ARC_R_BLINK))
+		len += arc_pop_r(BUF(buf, len), ARC_R_BLINK);
+
+	/* Wrap up the return value and jump back to the caller. */
+	len += bpf_to_arc_return(BUF(buf, len));
+	len += arc_jmp_return(BUF(buf, len));
+
+	return len;
+}
+
+/*
+ * For details on the algorithm, see the comments of "gen_jcc_64()".
+ *
+ * This data structure is holding information for jump translations.
+ *
+ * jit_off: How many bytes into the current JIT address, "b"ranch insn. occurs
+ * cond: The condition that the ARC branch instruction must use
+ *
+ * e.g.:
+ *
+ * BPF_JGE  R1, R0, @target
+ * ------------------------
+ *            |
+ *            v
+ * 0x1000: cmp  r3, r1     # 0x1000 is the JIT address for "BPF_JGE ..." insn
+ * 0x1004: bhi  @target    # first jump (branch higher)
+ * 0x1008: blo  @end       # second jump acting as a skip (end is 0x1014)
+ * 0x100C: cmp  r2, r0     # the lower 32 bits are evaluated
+ * 0x1010: bhs  @target    # third jump (branch higher or same)
+ * 0x1014: ...
+ *
+ * The jit_off(set) of the "bhi" is 4 bytes.
+ * The cond(ition) for the "bhi" is "CC_great_u".
+ *
+ * The jit_off(set) is necessary for calculating the exact displacement
+ * to the "target" address:
+ *
+ * jit_address + jit_off(set) - @target
+ * 0x1000      + 4            - @target
+ */
+#define JCC64_NR_OF_JMPS 3	/* Number of jumps in jcc64 template. */
+#define JCC64_INSNS_TO_END 3	/* Number of insn. inclusive the 2nd jmp to end. */
+#define JCC64_SKIP_JMP 1	/* Index of the "skip" jump to "end". */
+static const struct {
+	/*
+	 * "jit_off" is common between all "jmp[]" and is coupled with
+	 * "cond" of each "jmp[]" instance. e.g.:
+	 *
+	 * arcv2_64_jccs.jit_off[1]
+	 * arcv2_64_jccs.jmp[ARC_CC_UGT].cond[1]
+	 *
+	 * Are indicating that the second jump in JITed code of "UGT"
+	 * is at offset "jit_off[1]" while its condition is "cond[1]".
+	 */
+	u8 jit_off[JCC64_NR_OF_JMPS];
+
+	struct {
+		u8 cond[JCC64_NR_OF_JMPS];
+	} jmp[ARC_CC_SLE + 1];
+} arcv2_64_jccs = {
+	.jit_off = {
+		INSN_len_normal * 1,
+		INSN_len_normal * 2,
+		INSN_len_normal * 4
+	},
+	/*
+	 *   cmp  rd_hi, rs_hi
+	 *   bhi  @target         # 1: u>
+	 *   blo  @end            # 2: u<
+	 *   cmp  rd_lo, rs_lo
+	 *   bhi  @target         # 3: u>
+	 * end:
+	 */
+	.jmp[ARC_CC_UGT] = {
+		.cond = {CC_great_u, CC_less_u, CC_great_u}
+	},
+	/*
+	 *   cmp  rd_hi, rs_hi
+	 *   bhi  @target         # 1: u>
+	 *   blo  @end            # 2: u<
+	 *   cmp  rd_lo, rs_lo
+	 *   bhs  @target         # 3: u>=
+	 * end:
+	 */
+	.jmp[ARC_CC_UGE] = {
+		.cond = {CC_great_u, CC_less_u, CC_great_eq_u}
+	},
+	/*
+	 *   cmp  rd_hi, rs_hi
+	 *   blo  @target         # 1: u<
+	 *   bhi  @end            # 2: u>
+	 *   cmp  rd_lo, rs_lo
+	 *   blo  @target         # 3: u<
+	 * end:
+	 */
+	.jmp[ARC_CC_ULT] = {
+		.cond = {CC_less_u, CC_great_u, CC_less_u}
+	},
+	/*
+	 *   cmp  rd_hi, rs_hi
+	 *   blo  @target         # 1: u<
+	 *   bhi  @end            # 2: u>
+	 *   cmp  rd_lo, rs_lo
+	 *   bls  @target         # 3: u<=
+	 * end:
+	 */
+	.jmp[ARC_CC_ULE] = {
+		.cond = {CC_less_u, CC_great_u, CC_less_eq_u}
+	},
+	/*
+	 *   cmp  rd_hi, rs_hi
+	 *   bgt  @target         # 1: s>
+	 *   blt  @end            # 2: s<
+	 *   cmp  rd_lo, rs_lo
+	 *   bhi  @target         # 3: u>
+	 * end:
+	 */
+	.jmp[ARC_CC_SGT] = {
+		.cond = {CC_great_s, CC_less_s, CC_great_u}
+	},
+	/*
+	 *   cmp  rd_hi, rs_hi
+	 *   bgt  @target         # 1: s>
+	 *   blt  @end            # 2: s<
+	 *   cmp  rd_lo, rs_lo
+	 *   bhs  @target         # 3: u>=
+	 * end:
+	 */
+	.jmp[ARC_CC_SGE] = {
+		.cond = {CC_great_s, CC_less_s, CC_great_eq_u}
+	},
+	/*
+	 *   cmp  rd_hi, rs_hi
+	 *   blt  @target         # 1: s<
+	 *   bgt  @end            # 2: s>
+	 *   cmp  rd_lo, rs_lo
+	 *   blo  @target         # 3: u<
+	 * end:
+	 */
+	.jmp[ARC_CC_SLT] = {
+		.cond = {CC_less_s, CC_great_s, CC_less_u}
+	},
+	/*
+	 *   cmp  rd_hi, rs_hi
+	 *   blt  @target         # 1: s<
+	 *   bgt  @end            # 2: s>
+	 *   cmp  rd_lo, rs_lo
+	 *   bls  @target         # 3: u<=
+	 * end:
+	 */
+	.jmp[ARC_CC_SLE] = {
+		.cond = {CC_less_s, CC_great_s, CC_less_eq_u}
+	}
+};
+
+/*
+ * The displacement (offset) for ARC's "b"ranch instruction is the distance
+ * from the aligned version of _current_ instruction (PCL) to the target
+ * instruction:
+ *
+ * DISP = TARGET - PCL          # PCL is the word aligned PC
+ */
+static inline s32 get_displacement(u32 curr_off, u32 targ_off)
+{
+	return (s32)(targ_off - (curr_off & ~3L));
+}
+
+/*
+ * "disp"lacement should be:
+ *
+ * 1. 16-bit aligned.
+ * 2. fit in S25, because no "condition code" is supposed to be encoded.
+ */
+static inline bool is_valid_far_disp(s32 disp)
+{
+	return (!(disp & 1) && IN_S25_RANGE(disp));
+}
+
+/*
+ * "disp"lacement should be:
+ *
+ * 1. 16-bit aligned.
+ * 2. fit in S21, because "condition code" is supposed to be encoded too.
+ */
+static inline bool is_valid_near_disp(s32 disp)
+{
+	return (!(disp & 1) && IN_S21_RANGE(disp));
+}
+
+/*
+ * cmp        rd_hi, rs_hi
+ * cmp.z      rd_lo, rs_lo
+ * b{eq,ne}   @target
+ *   |  |
+ *   |  `-->  "eq" param is false (JNE)
+ *   `----->  "eq" param is true  (JEQ)
+ */
+static int gen_j_eq_64(u8 *buf, u8 rd, u8 rs, bool eq,
+		       u32 curr_off, u32 targ_off)
+{
+	s32 disp;
+	u8 len = 0;
+
+	len += arc_cmp_r(BUF(buf, len), REG_HI(rd), REG_HI(rs));
+	len += arc_cmpz_r(BUF(buf, len), REG_LO(rd), REG_LO(rs));
+	disp = get_displacement(curr_off + len, targ_off);
+	len += arc_bcc(BUF(buf, len), eq ? CC_equal : CC_unequal, disp);
+
+	return len;
+}
+
+/*
+ * tst   rd_hi, rs_hi
+ * tst.z rd_lo, rs_lo
+ * bne   @target
+ */
+static u8 gen_jset_64(u8 *buf, u8 rd, u8 rs, u32 curr_off, u32 targ_off)
+{
+	u8 len = 0;
+	s32 disp;
+
+	len += arc_tst_r(BUF(buf, len), REG_HI(rd), REG_HI(rs));
+	len += arc_tstz_r(BUF(buf, len), REG_LO(rd), REG_LO(rs));
+	disp = get_displacement(curr_off + len, targ_off);
+	len += arc_bcc(BUF(buf, len), CC_unequal, disp);
+
+	return len;
+}
+
+/*
+ * Verify if all the jumps for a JITed jcc64 operation are valid,
+ * by consulting the data stored at "arcv2_64_jccs".
+ */
+static bool check_jcc_64(u32 curr_off, u32 targ_off, u8 cond)
+{
+	size_t i;
+
+	if (cond >= ARC_CC_LAST)
+		return false;
+
+	for (i = 0; i < JCC64_NR_OF_JMPS; i++) {
+		u32 from, to;
+
+		from = curr_off + arcv2_64_jccs.jit_off[i];
+		/* for the 2nd jump, we jump to the end of block. */
+		if (i != JCC64_SKIP_JMP)
+			to = targ_off;
+		else
+			to = from + (JCC64_INSNS_TO_END * INSN_len_normal);
+		/* There is a "cc" in the instruction, so a "near" jump. */
+		if (!is_valid_near_disp(get_displacement(from, to)))
+			return false;
+	}
+
+	return true;
+}
+
+/* Can the jump from "curr_off" to "targ_off" actually happen? */
+bool check_jmp_64(u32 curr_off, u32 targ_off, u8 cond)
+{
+	s32 disp;
+
+	switch (cond) {
+	case ARC_CC_UGT:
+	case ARC_CC_UGE:
+	case ARC_CC_ULT:
+	case ARC_CC_ULE:
+	case ARC_CC_SGT:
+	case ARC_CC_SGE:
+	case ARC_CC_SLT:
+	case ARC_CC_SLE:
+		return check_jcc_64(curr_off, targ_off, cond);
+	case ARC_CC_EQ:
+	case ARC_CC_NE:
+	case ARC_CC_SET:
+		/*
+		 * The "jump" for the JITed BPF_J{SET,EQ,NE} is actually the
+		 * 3rd instruction. See comments of "gen_j{set,_eq}_64()".
+		 */
+		curr_off += 2 * INSN_len_normal;
+		disp = get_displacement(curr_off, targ_off);
+		/* There is a "cc" field in the issued instruction. */
+		return is_valid_near_disp(disp);
+	case ARC_CC_AL:
+		disp = get_displacement(curr_off, targ_off);
+		return is_valid_far_disp(disp);
+	default:
+		return false;
+	}
+}
+
+/*
+ * The template for the 64-bit jumps with the following BPF conditions
+ *
+ * u< u<= u> u>= s< s<= s> s>=
+ *
+ * Looks like below:
+ *
+ *   cmp   rd_hi, rs_hi
+ *   b<c1> @target
+ *   b<c2> @end
+ *   cmp   rd_lo, rs_lo   # if execution reaches here, r{d,s}_hi are equal
+ *   b<c3> @target
+ * end:
+ *
+ * "c1" is the condition that JIT is handling minus the equality part.
+ * For instance if we have to translate an "unsigned greater or equal",
+ * then "c1" will be "unsigned greater". We won't know about equality
+ * until all 64-bits of data (higeher and lower registers) are processed.
+ *
+ * "c2" is the counter logic of "c1". For instance, if "c1" is originated
+ * from "s>", then "c2" would be "s<". Notice that equality doesn't play
+ * a role here either, because the lower 32 bits are not processed yet.
+ *
+ * "c3" is the unsigned version of "c1", no matter if the BPF condition
+ * was signed or unsigned. An unsigned version is necessary, because the
+ * MSB of the lower 32 bits does not reflect a sign in the whole 64-bit
+ * scheme. Otherwise, 64-bit comparisons like
+ * (0x0000_0000,0x8000_0000) s>= (0x0000_0000,0x0000_0000)
+ * would yield an incorrect result. Finally, if there is an equality
+ * check in the BPF condition, it will be reflected in "c3".
+ *
+ * You can find all the instances of this template where the
+ * "arcv2_64_jccs" is getting initialised.
+ */
+static u8 gen_jcc_64(u8 *buf, u8 rd, u8 rs, u8 cond,
+		     u32 curr_off, u32 targ_off)
+{
+	s32 disp;
+	u32 end_off;
+	const u8 *cc = arcv2_64_jccs.jmp[cond].cond;
+	u8 len = 0;
+
+	/* cmp rd_hi, rs_hi */
+	len += arc_cmp_r(buf, REG_HI(rd), REG_HI(rs));
+
+	/* b<c1> @target */
+	disp = get_displacement(curr_off + len, targ_off);
+	len += arc_bcc(BUF(buf, len), cc[0], disp);
+
+	/* b<c2> @end */
+	end_off = curr_off + len + (JCC64_INSNS_TO_END * INSN_len_normal);
+	disp = get_displacement(curr_off + len, end_off);
+	len += arc_bcc(BUF(buf, len), cc[1], disp);
+
+	/* cmp rd_lo, rs_lo */
+	len += arc_cmp_r(BUF(buf, len), REG_LO(rd), REG_LO(rs));
+
+	/* b<c3> @target */
+	disp = get_displacement(curr_off + len, targ_off);
+	len += arc_bcc(BUF(buf, len), cc[2], disp);
+
+	return len;
+}
+
+/*
+ * This function only applies the necessary logic to make the proper
+ * translations. All the sanity checks must have already been done
+ * by calling the check_jmp_64().
+ */
+u8 gen_jmp_64(u8 *buf, u8 rd, u8 rs, u8 cond, u32 curr_off, u32 targ_off)
+{
+	u8 len = 0;
+	bool eq = false;
+	s32 disp;
+
+	switch (cond) {
+	case ARC_CC_AL:
+		disp = get_displacement(curr_off, targ_off);
+		len = arc_b(buf, disp);
+		break;
+	case ARC_CC_UGT:
+	case ARC_CC_UGE:
+	case ARC_CC_ULT:
+	case ARC_CC_ULE:
+	case ARC_CC_SGT:
+	case ARC_CC_SGE:
+	case ARC_CC_SLT:
+	case ARC_CC_SLE:
+		len = gen_jcc_64(buf, rd, rs, cond, curr_off, targ_off);
+		break;
+	case ARC_CC_EQ:
+		eq = true;
+		fallthrough;
+	case ARC_CC_NE:
+		len = gen_j_eq_64(buf, rd, rs, eq, curr_off, targ_off);
+		break;
+	case ARC_CC_SET:
+		len = gen_jset_64(buf, rd, rs, curr_off, targ_off);
+		break;
+	default:
+#ifdef ARC_BPF_JIT_DEBUG
+		pr_err("64-bit jump condition is not known.\n");
+		BUG();
+#endif
+	}
+	return len;
+}
+
+/*
+ * The condition codes to use when generating JIT instructions
+ * for 32-bit jumps.
+ *
+ * The "ARC_CC_AL" index is not really used by the code, but it
+ * is here for the sake of completeness.
+ *
+ * The "ARC_CC_SET" becomes "CC_unequal" because of the "tst"
+ * instruction that precedes the conditional branch.
+ */
+static const u8 arcv2_32_jmps[ARC_CC_LAST] = {
+	[ARC_CC_UGT] = CC_great_u,
+	[ARC_CC_UGE] = CC_great_eq_u,
+	[ARC_CC_ULT] = CC_less_u,
+	[ARC_CC_ULE] = CC_less_eq_u,
+	[ARC_CC_SGT] = CC_great_s,
+	[ARC_CC_SGE] = CC_great_eq_s,
+	[ARC_CC_SLT] = CC_less_s,
+	[ARC_CC_SLE] = CC_less_eq_s,
+	[ARC_CC_AL]  = CC_always,
+	[ARC_CC_EQ]  = CC_equal,
+	[ARC_CC_NE]  = CC_unequal,
+	[ARC_CC_SET] = CC_unequal
+};
+
+/* Can the jump from "curr_off" to "targ_off" actually happen? */
+bool check_jmp_32(u32 curr_off, u32 targ_off, u8 cond)
+{
+	u8 addendum;
+	s32 disp;
+
+	if (cond >= ARC_CC_LAST)
+		return false;
+
+	/*
+	 * The unconditional jump happens immediately, while the rest
+	 * are either preceded by a "cmp" or "tst" instruction.
+	 */
+	addendum = (cond == ARC_CC_AL) ? 0 : INSN_len_normal;
+	disp = get_displacement(curr_off + addendum, targ_off);
+
+	if (cond == ARC_CC_AL)
+		return is_valid_far_disp(disp);
+	else
+		return is_valid_near_disp(disp);
+}
+
+/*
+ * The JITed code for 32-bit (conditional) branches:
+ *
+ * ARC_CC_AL  @target
+ *   b @jit_targ_addr
+ *
+ * ARC_CC_SET rd, rs, @target
+ *   tst rd, rs
+ *   bnz @jit_targ_addr
+ *
+ * ARC_CC_xx  rd, rs, @target
+ *   cmp rd, rs
+ *   b<cc> @jit_targ_addr            # cc = arcv2_32_jmps[xx]
+ */
+u8 gen_jmp_32(u8 *buf, u8 rd, u8 rs, u8 cond, u32 curr_off, u32 targ_off)
+{
+	s32 disp;
+	u8 len = 0;
+
+	/*
+	 * Although this must have already been checked by "check_jmp_32()",
+	 * we're not going to risk accessing "arcv2_32_jmps" array without
+	 * the boundary check.
+	 */
+	if (cond >= ARC_CC_LAST) {
+#ifdef ARC_BPF_JIT_DEBUG
+		pr_err("32-bit jump condition is not known.\n");
+		BUG();
+#endif
+		return 0;
+	}
+
+	/* If there is a "condition", issue the "cmp" or "tst" first. */
+	if (cond != ARC_CC_AL) {
+		if (cond == ARC_CC_SET)
+			len = tst_r32(buf, rd, rs);
+		else
+			len = cmp_r32(buf, rd, rs);
+		/*
+		 * The issued instruction affects the "disp"lacement as
+		 * it alters the "curr_off" by its "len"gth. The "curr_off"
+		 * should always point to the jump instruction.
+		 */
+		disp = get_displacement(curr_off + len, targ_off);
+		len += arc_bcc(BUF(buf, len), arcv2_32_jmps[cond], disp);
+	} else {
+		/* The straight forward unconditional jump. */
+		disp = get_displacement(curr_off, targ_off);
+		len = arc_b(buf, disp);
+	}
+
+	return len;
+}
+
+/*
+ * Generate code for functions calls. There can be two types of calls:
+ *
+ * - Calling another BPF function
+ * - Calling an in-kernel function which is compiled by ARC gcc
+ *
+ * In the later case, we must comply to ARCv2 ABI and handle arguments
+ * and return values accordingly.
+ */
+u8 gen_func_call(u8 *buf, ARC_ADDR func_addr, bool external_func)
+{
+	u8 len = 0;
+
+	/*
+	 * In case of an in-kernel function call, always push the 5th
+	 * argument onto the stack, because that's where the ABI dictates
+	 * it should be found. If the callee doesn't really use it, no harm
+	 * is done. The stack is readjusted either way after the call.
+	 */
+	if (external_func)
+		len += push_r64(BUF(buf, len), BPF_REG_5);
+
+	len += jump_and_link(BUF(buf, len), func_addr);
+
+	if (external_func)
+		len += arc_add_i(BUF(buf, len), ARC_R_SP, ARC_R_SP, ARG5_SIZE);
+
+	return len;
+}
diff --git a/arch/arc/net/bpf_jit_core.c b/arch/arc/net/bpf_jit_core.c
new file mode 100644
index 000000000..639a2736f
--- /dev/null
+++ b/arch/arc/net/bpf_jit_core.c
@@ -0,0 +1,1414 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * The back-end-agnostic part of Just-In-Time compiler for eBPF bytecode.
+ *
+ * Copyright (c) 2024 Synopsys Inc.
+ * Author: Shahab Vahedi <shahab@synopsys.com>
+ */
+#include <linux/bug.h>
+#include "bpf_jit.h"
+
+/*
+ * Check for the return value. A pattern used often in this file.
+ * There must be a "ret" variable of type "int" in the scope.
+ */
+#define CHECK_RET(cmd)			\
+	do {				\
+		ret = (cmd);		\
+		if (ret < 0)		\
+			return ret;	\
+	} while (0)
+
+#ifdef ARC_BPF_JIT_DEBUG
+/* Dumps bytes in /var/log/messages at KERN_INFO level (4). */
+static void dump_bytes(const u8 *buf, u32 len, const char *header)
+{
+	u8 line[64];
+	size_t i, j;
+
+	pr_info("-----------------[ %s ]-----------------\n", header);
+
+	for (i = 0, j = 0; i < len; i++) {
+		/* Last input byte? */
+		if (i == len - 1) {
+			j += scnprintf(line + j, 64 - j, "0x%02x", buf[i]);
+			pr_info("%s\n", line);
+			break;
+		}
+		/* End of line? */
+		else if (i % 8 == 7) {
+			j += scnprintf(line + j, 64 - j, "0x%02x", buf[i]);
+			pr_info("%s\n", line);
+			j = 0;
+		} else {
+			j += scnprintf(line + j, 64 - j, "0x%02x, ", buf[i]);
+		}
+	}
+}
+#endif /* ARC_BPF_JIT_DEBUG */
+
+/********************* JIT context ***********************/
+
+/*
+ * buf:		Translated instructions end up here.
+ * len:		The length of whole block in bytes.
+ * index:	The offset at which the _next_ instruction may be put.
+ */
+struct jit_buffer {
+	u8	*buf;
+	u32	len;
+	u32	index;
+};
+
+/*
+ * This is a subset of "struct jit_context" that its information is deemed
+ * necessary for the next extra pass to come.
+ *
+ * bpf_header:	Needed to finally lock the region.
+ * bpf2insn:	Used to find the translation for instructions of interest.
+ *
+ * Things like "jit.buf" and "jit.len" can be retrieved respectively from
+ * "prog->bpf_func" and "prog->jited_len".
+ */
+struct arc_jit_data {
+	struct bpf_binary_header *bpf_header;
+	u32                      *bpf2insn;
+};
+
+/*
+ * The JIT pertinent context that is used by different functions.
+ *
+ * prog:		The current eBPF program being handled.
+ * jit:			The JIT buffer and its length.
+ * bpf_header:		The JITed program header. "jit.buf" points inside it.
+ * emit:		If set, opcodes are written to memory; else, a dry-run.
+ * do_zext:		If true, 32-bit sub-regs must be zero extended.
+ * bpf2insn:		Maps BPF insn indices to their counterparts in jit.buf.
+ * bpf2insn_valid:	Indicates if "bpf2ins" is populated with the mappings.
+ * jit_data:		A piece of memory to transfer data to the next pass.
+ * arc_regs_clobbered:	Each bit status determines if that arc reg is clobbered.
+ * save_blink:		Whether ARC's "blink" register needs to be saved.
+ * frame_size:		Derived from "prog->aux->stack_depth".
+ * epilogue_offset:	Used by early "return"s in the code to jump here.
+ * need_extra_pass:	A forecast if an "extra_pass" will occur.
+ * is_extra_pass:	Indicates if the current pass is an extra pass.
+ * user_bpf_prog:	True, if VM opcodes come from a real program.
+ * success:		Indicates if the whole JIT went OK.
+ */
+struct jit_context {
+	struct bpf_prog			*prog;
+	struct jit_buffer		jit;
+	struct bpf_binary_header	*bpf_header;
+	bool				emit;
+	bool				do_zext;
+	u32				*bpf2insn;
+	bool				bpf2insn_valid;
+	struct arc_jit_data		*jit_data;
+	u32				arc_regs_clobbered;
+	bool				save_blink;
+	u16				frame_size;
+	u32				epilogue_offset;
+	bool				need_extra_pass;
+	bool				is_extra_pass;
+	bool				user_bpf_prog;
+	bool				success;
+};
+
+/*
+ * If we're in ARC_BPF_JIT_DEBUG mode and the debug level is right, dump the
+ * input BPF stream. "bpf_jit_dump()" is not fully suited for this purpose.
+ */
+static void vm_dump(const struct bpf_prog *prog)
+{
+#ifdef ARC_BPF_JIT_DEBUG
+	if (bpf_jit_enable > 1)
+		dump_bytes((u8 *)prog->insns, 8 * prog->len, " VM  ");
+#endif
+}
+
+/*
+ * If the right level of debug is set, dump the bytes. There are 2 variants
+ * of this function:
+ *
+ * 1. Use the standard bpf_jit_dump() which is meant only for JITed code.
+ * 2. Use the dump_bytes() to match its "vm_dump()" instance.
+ */
+static void jit_dump(const struct jit_context *ctx)
+{
+#ifdef ARC_BPF_JIT_DEBUG
+	u8 header[8];
+#endif
+	const int pass = ctx->is_extra_pass ? 2 : 1;
+
+	if (bpf_jit_enable <= 1 || !ctx->prog->jited)
+		return;
+
+#ifdef ARC_BPF_JIT_DEBUG
+	scnprintf(header, sizeof(header), "JIT:%d", pass);
+	dump_bytes(ctx->jit.buf, ctx->jit.len, header);
+	pr_info("\n");
+#else
+	bpf_jit_dump(ctx->prog->len, ctx->jit.len, pass, ctx->jit.buf);
+#endif
+}
+
+/* Initialise the context so there's no garbage. */
+static int jit_ctx_init(struct jit_context *ctx, struct bpf_prog *prog)
+{
+	memset(ctx, 0, sizeof(*ctx));
+
+	ctx->prog = prog;
+
+	/* If the verifier doesn't zero-extend, then we have to do it. */
+	ctx->do_zext = !ctx->prog->aux->verifier_zext;
+
+	ctx->is_extra_pass = ctx->prog->jited;
+	ctx->user_bpf_prog = ctx->prog->is_func;
+
+	return 0;
+}
+
+/*
+ * Only after the first iteration of normal pass (the dry-run),
+ * there are valid offsets in ctx->bpf2insn array.
+ */
+static inline bool offsets_available(const struct jit_context *ctx)
+{
+	return ctx->bpf2insn_valid;
+}
+
+/*
+ * "*mem" should be freed when there is no "extra pass" to come,
+ * or the compilation terminated abruptly. A few of such memory
+ * allocations are: ctx->jit_data and ctx->bpf2insn.
+ */
+static inline void maybe_free(struct jit_context *ctx, void **mem)
+{
+	if (*mem) {
+		if (!ctx->success || !ctx->need_extra_pass) {
+			kfree(*mem);
+			*mem = NULL;
+		}
+	}
+}
+
+/*
+ * Free memories based on the status of the context.
+ *
+ * A note about "bpf_header": On successful runs, "bpf_header" is
+ * not freed, because "jit.buf", a sub-array of it, is returned as
+ * the "bpf_func". However, "bpf_header" is lost and nothing points
+ * to it. This should not cause a leakage, because apparently
+ * "bpf_header" can be revived by "bpf_jit_binary_hdr()". This is
+ * how "bpf_jit_free()" in "kernel/bpf/core.c" releases the memory.
+ */
+static void jit_ctx_cleanup(struct jit_context *ctx)
+{
+	maybe_free(ctx, (void **)&ctx->bpf2insn);
+	maybe_free(ctx, (void **)&ctx->jit_data);
+
+	if (!ctx->bpf2insn)
+		ctx->bpf2insn_valid = false;
+
+	/* Freeing "bpf_header" is enough. "jit.buf" is a sub-array of it. */
+	if (!ctx->success) {
+		if (ctx->bpf_header) {
+			bpf_jit_binary_free(ctx->bpf_header);
+			ctx->bpf_header = NULL;
+			ctx->jit.buf    = NULL;
+			ctx->jit.index  = 0;
+			ctx->jit.len    = 0;
+		}
+		if (ctx->is_extra_pass) {
+			ctx->prog->bpf_func = NULL;
+			ctx->prog->jited = 0;
+			ctx->prog->jited_len = 0;
+		}
+	}
+
+	ctx->emit = false;
+	ctx->do_zext = false;
+}
+
+/*
+ * Analyse the register usage and record the frame size.
+ * The register usage is determined by consulting the back-end.
+ */
+static void analyze_reg_usage(struct jit_context *ctx)
+{
+	size_t i;
+	u32 usage = 0;
+	const struct bpf_insn *insn = ctx->prog->insnsi;
+
+	for (i = 0; i < ctx->prog->len; i++) {
+		u8 bpf_reg;
+		bool call;
+
+		bpf_reg = insn[i].dst_reg;
+		call = (insn[i].code == (BPF_JMP | BPF_CALL)) ? true : false;
+		usage |= mask_for_used_regs(bpf_reg, call);
+	}
+
+	ctx->arc_regs_clobbered = usage;
+	ctx->frame_size = ctx->prog->aux->stack_depth;
+}
+
+/* Verify that no instruction will be emitted when there is no buffer. */
+static inline int jit_buffer_check(const struct jit_context *ctx)
+{
+	if (ctx->emit) {
+		if (!ctx->jit.buf) {
+			pr_err("bpf-jit: inconsistence state; no "
+			       "buffer to emit instructions.\n");
+			return -EINVAL;
+		} else if (ctx->jit.index > ctx->jit.len) {
+			pr_err("bpf-jit: estimated JIT length is less "
+			       "than the emitted instructions.\n");
+			return -EFAULT;
+		}
+	}
+	return 0;
+}
+
+/* On a dry-run (emit=false), "jit.len" is growing gradually. */
+static inline void jit_buffer_update(struct jit_context *ctx, u32 n)
+{
+	if (!ctx->emit)
+		ctx->jit.len += n;
+	else
+		ctx->jit.index += n;
+}
+
+/* Based on "emit", determine the address where instructions are emitted. */
+static inline u8 *effective_jit_buf(const struct jit_context *ctx)
+{
+	return ctx->emit ? (ctx->jit.buf + ctx->jit.index) : NULL;
+}
+
+/* Prologue based on context variables set by "analyze_reg_usage()". */
+static int handle_prologue(struct jit_context *ctx)
+{
+	int ret;
+	u8 *buf = effective_jit_buf(ctx);
+	u32 len = 0;
+
+	CHECK_RET(jit_buffer_check(ctx));
+
+	len = arc_prologue(buf, ctx->arc_regs_clobbered, ctx->frame_size);
+	jit_buffer_update(ctx, len);
+
+	return 0;
+}
+
+/* The counter part for "handle_prologue()". */
+static int handle_epilogue(struct jit_context *ctx)
+{
+	int ret;
+	u8 *buf = effective_jit_buf(ctx);
+	u32 len = 0;
+
+	CHECK_RET(jit_buffer_check(ctx));
+
+	len = arc_epilogue(buf, ctx->arc_regs_clobbered, ctx->frame_size);
+	jit_buffer_update(ctx, len);
+
+	return 0;
+}
+
+/* Tell which number of the BPF instruction we are dealing with. */
+static inline s32 get_index_for_insn(const struct jit_context *ctx,
+				     const struct bpf_insn *insn)
+{
+	return (insn - ctx->prog->insnsi);
+}
+
+/*
+ * In most of the cases, the "offset" is read from "insn->off". However,
+ * if it is an unconditional BPF_JMP32, then it comes from "insn->imm".
+ *
+ * (Courtesy of "cpu=v4" support)
+ */
+static inline s32 get_offset(const struct bpf_insn *insn)
+{
+	if ((BPF_CLASS(insn->code) == BPF_JMP32) &&
+	    (BPF_OP(insn->code) == BPF_JA))
+		return insn->imm;
+	else
+		return insn->off;
+}
+
+/*
+ * Determine to which number of the BPF instruction we're jumping to.
+ *
+ * The "offset" is interpreted as the "number" of BPF instructions
+ * from the _next_ BPF instruction. e.g.:
+ *
+ *  4 means 4 instructions after  the next insn
+ *  0 means 0 instructions after  the next insn -> fallthrough.
+ * -1 means 1 instruction  before the next insn -> jmp to current insn.
+ *
+ *  Another way to look at this, "offset" is the number of instructions
+ *  that exist between the current instruction and the target instruction.
+ *
+ *  It is worth noting that a "mov r,i64", which is 16-byte long, is
+ *  treated as two instructions long, therefore "offset" needn't be
+ *  treated specially for those. Everything is uniform.
+ */
+static inline s32 get_target_index_for_insn(const struct jit_context *ctx,
+					    const struct bpf_insn *insn)
+{
+	return (get_index_for_insn(ctx, insn) + 1) + get_offset(insn);
+}
+
+/* Is there an immediate operand encoded in the "insn"? */
+static inline bool has_imm(const struct bpf_insn *insn)
+{
+	return BPF_SRC(insn->code) == BPF_K;
+}
+
+/* Is the last BPF instruction? */
+static inline bool is_last_insn(const struct bpf_prog *prog, u32 idx)
+{
+	return idx == (prog->len - 1);
+}
+
+/*
+ * Invocation of this function, conditionally signals the need for
+ * an extra pass. The conditions that must be met are:
+ *
+ * 1. The current pass itself shouldn't be an extra pass.
+ * 2. The stream of bytes being JITed must come from a user program.
+ */
+static inline void set_need_for_extra_pass(struct jit_context *ctx)
+{
+	if (!ctx->is_extra_pass)
+		ctx->need_extra_pass = ctx->user_bpf_prog;
+}
+
+/*
+ * Check if the "size" is valid and then transfer the control to
+ * the back-end for the swap.
+ */
+static int handle_swap(u8 *buf, u8 rd, u8 size, u8 endian,
+		       bool force, bool do_zext, u8 *len)
+{
+	/* Sanity check on the size. */
+	switch (size) {
+	case 16:
+	case 32:
+	case 64:
+		break;
+	default:
+		pr_err("bpf-jit: invalid size for swap.\n");
+		return -EINVAL;
+	}
+
+	*len = gen_swap(buf, rd, size, endian, force, do_zext);
+
+	return 0;
+}
+
+/* Checks if the (instruction) index is in valid range. */
+static inline bool check_insn_idx_valid(const struct jit_context *ctx,
+					const s32 idx)
+{
+	return (idx >= 0 && idx < ctx->prog->len);
+}
+
+/*
+ * Decouple the back-end from BPF by converting BPF conditions
+ * to internal enum. ARC_CC_* start from 0 and are used as index
+ * to an array. BPF_J* usage must end after this conversion.
+ */
+static int bpf_cond_to_arc(const u8 op, u8 *arc_cc)
+{
+	switch (op) {
+	case BPF_JA:
+		*arc_cc = ARC_CC_AL;
+		break;
+	case BPF_JEQ:
+		*arc_cc = ARC_CC_EQ;
+		break;
+	case BPF_JGT:
+		*arc_cc = ARC_CC_UGT;
+		break;
+	case BPF_JGE:
+		*arc_cc = ARC_CC_UGE;
+		break;
+	case BPF_JSET:
+		*arc_cc = ARC_CC_SET;
+		break;
+	case BPF_JNE:
+		*arc_cc = ARC_CC_NE;
+		break;
+	case BPF_JSGT:
+		*arc_cc = ARC_CC_SGT;
+		break;
+	case BPF_JSGE:
+		*arc_cc = ARC_CC_SGE;
+		break;
+	case BPF_JLT:
+		*arc_cc = ARC_CC_ULT;
+		break;
+	case BPF_JLE:
+		*arc_cc = ARC_CC_ULE;
+		break;
+	case BPF_JSLT:
+		*arc_cc = ARC_CC_SLT;
+		break;
+	case BPF_JSLE:
+		*arc_cc = ARC_CC_SLE;
+		break;
+	default:
+		pr_err("bpf-jit: can't handle condition 0x%02X\n", op);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+/*
+ * Check a few things for a supposedly "jump" instruction:
+ *
+ * 0. "insn" is a "jump" instruction, but not the "call/exit" variant.
+ * 1. The current "insn" index is in valid range.
+ * 2. The index of target instruction is in valid range.
+ */
+static int check_bpf_jump(const struct jit_context *ctx,
+			  const struct bpf_insn *insn)
+{
+	const u8 class = BPF_CLASS(insn->code);
+	const u8 op = BPF_OP(insn->code);
+
+	/* Must be a jmp(32) instruction that is not a "call/exit". */
+	if ((class != BPF_JMP && class != BPF_JMP32) ||
+	    (op == BPF_CALL || op == BPF_EXIT)) {
+		pr_err("bpf-jit: not a jump instruction.\n");
+		return -EINVAL;
+	}
+
+	if (!check_insn_idx_valid(ctx, get_index_for_insn(ctx, insn))) {
+		pr_err("bpf-jit: the bpf jump insn is not in prog.\n");
+		return -EINVAL;
+	}
+
+	if (!check_insn_idx_valid(ctx, get_target_index_for_insn(ctx, insn))) {
+		pr_err("bpf-jit: bpf jump label is out of range.\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/*
+ * Based on input "insn", consult "ctx->bpf2insn" to get the
+ * related index (offset) of the translation in JIT stream.
+ */
+static u32 get_curr_jit_off(const struct jit_context *ctx,
+			    const struct bpf_insn *insn)
+{
+	const s32 idx = get_index_for_insn(ctx, insn);
+#ifdef ARC_BPF_JIT_DEBUG
+	BUG_ON(!offsets_available(ctx) || !check_insn_idx_valid(ctx, idx));
+#endif
+	return ctx->bpf2insn[idx];
+}
+
+/*
+ * The input "insn" must be a jump instruction.
+ *
+ * Based on input "insn", consult "ctx->bpf2insn" to get the
+ * related JIT index (offset) of "target instruction" that
+ * "insn" would jump to.
+ */
+static u32 get_targ_jit_off(const struct jit_context *ctx,
+			    const struct bpf_insn *insn)
+{
+	const s32 tidx = get_target_index_for_insn(ctx, insn);
+#ifdef ARC_BPF_JIT_DEBUG
+	BUG_ON(!offsets_available(ctx) || !check_insn_idx_valid(ctx, tidx));
+#endif
+	return ctx->bpf2insn[tidx];
+}
+
+/*
+ * This function will return 0 for a feasible jump.
+ *
+ * Consult the back-end to check if it finds it feasible to emit
+ * the necessary instructions based on "cond" and the displacement
+ * between the "from_off" and the "to_off".
+ */
+static int feasible_jit_jump(u32 from_off, u32 to_off, u8 cond, bool j32)
+{
+	int ret = 0;
+
+	if (j32) {
+		if (!check_jmp_32(from_off, to_off, cond))
+			ret = -EFAULT;
+	} else {
+		if (!check_jmp_64(from_off, to_off, cond))
+			ret = -EFAULT;
+	}
+
+	if (ret != 0)
+		pr_err("bpf-jit: the JIT displacement is not OK.\n");
+
+	return ret;
+}
+
+/*
+ * This jump handler performs the following steps:
+ *
+ * 1. Compute ARC's internal condition code from BPF's
+ * 2. Determine the bitness of the operation (32 vs. 64)
+ * 3. Sanity check on BPF stream
+ * 4. Sanity check on what is supposed to be JIT's displacement
+ * 5. And finally, emit the necessary instructions
+ *
+ * The last two steps are performed through the back-end.
+ * The value of steps 1 and 2 are necessary inputs for the back-end.
+ */
+static int handle_jumps(const struct jit_context *ctx,
+			const struct bpf_insn *insn,
+			u8 *len)
+{
+	u8 cond;
+	int ret = 0;
+	u8 *buf = effective_jit_buf(ctx);
+	const bool j32 = (BPF_CLASS(insn->code) == BPF_JMP32) ? true : false;
+	const u8 rd = insn->dst_reg;
+	u8 rs = insn->src_reg;
+	u32 curr_off = 0, targ_off = 0;
+
+	*len = 0;
+
+	/* Map the BPF condition to internal enum. */
+	CHECK_RET(bpf_cond_to_arc(BPF_OP(insn->code), &cond));
+
+	/* Sanity check on the BPF byte stream. */
+	CHECK_RET(check_bpf_jump(ctx, insn));
+
+	/*
+	 * Move the immediate into a temporary register _now_ for 2 reasons:
+	 *
+	 * 1. "gen_jmp_{32,64}()" deal with operands in registers.
+	 *
+	 * 2. The "len" parameter will grow so that the current jit offset
+	 *    (curr_off) will have increased to a point where the necessary
+	 *    instructions can be inserted by "gen_jmp_{32,64}()".
+	 */
+	if (has_imm(insn) && cond != ARC_CC_AL) {
+		if (j32) {
+			*len += mov_r32_i32(BUF(buf, *len), JIT_REG_TMP,
+					    insn->imm);
+		} else {
+			*len += mov_r64_i32(BUF(buf, *len), JIT_REG_TMP,
+					    insn->imm);
+		}
+		rs = JIT_REG_TMP;
+	}
+
+	/* If the offsets are known, check if the branch can occur. */
+	if (offsets_available(ctx)) {
+		curr_off = get_curr_jit_off(ctx, insn) + *len;
+		targ_off = get_targ_jit_off(ctx, insn);
+
+		/* Sanity check on the back-end side. */
+		CHECK_RET(feasible_jit_jump(curr_off, targ_off, cond, j32));
+	}
+
+	if (j32) {
+		*len += gen_jmp_32(BUF(buf, *len), rd, rs, cond,
+				   curr_off, targ_off);
+	} else {
+		*len += gen_jmp_64(BUF(buf, *len), rd, rs, cond,
+				   curr_off, targ_off);
+	}
+
+	return ret;
+}
+
+/* Jump to translated epilogue address. */
+static int handle_jmp_epilogue(struct jit_context *ctx,
+			       const struct bpf_insn *insn, u8 *len)
+{
+	u8 *buf = effective_jit_buf(ctx);
+	u32 curr_off = 0, epi_off = 0;
+
+	/* Check the offset only if the data is available. */
+	if (offsets_available(ctx)) {
+		curr_off = get_curr_jit_off(ctx, insn);
+		epi_off = ctx->epilogue_offset;
+
+		if (!check_jmp_64(curr_off, epi_off, ARC_CC_AL)) {
+			pr_err("bpf-jit: epilogue offset is not valid.\n");
+			return -EINVAL;
+		}
+	}
+
+	/* Jump to "epilogue offset" (rd and rs don't matter). */
+	*len = gen_jmp_64(buf, 0, 0, ARC_CC_AL, curr_off, epi_off);
+
+	return 0;
+}
+
+/* Try to get the resolved address and generate the instructions. */
+static int handle_call(struct jit_context *ctx,
+		       const struct bpf_insn *insn,
+		       u8 *len)
+{
+	int  ret;
+	bool in_kernel_func, fixed = false;
+	u64  addr = 0;
+	u8  *buf = effective_jit_buf(ctx);
+
+	ret = bpf_jit_get_func_addr(ctx->prog, insn, ctx->is_extra_pass,
+				    &addr, &fixed);
+	if (ret < 0) {
+		pr_err("bpf-jit: can't get the address for call.\n");
+		return ret;
+	}
+	in_kernel_func = (fixed ? true : false);
+
+	/* No valuable address retrieved (yet). */
+	if (!fixed && !addr)
+		set_need_for_extra_pass(ctx);
+
+	*len = gen_func_call(buf, (ARC_ADDR)addr, in_kernel_func);
+
+	if (insn->src_reg != BPF_PSEUDO_CALL) {
+		/* Assigning ABI's return reg to JIT's return reg. */
+		*len += arc_to_bpf_return(BUF(buf, *len));
+	}
+
+	return 0;
+}
+
+/*
+ * Try to generate instructions for loading a 64-bit immediate.
+ * These sort of instructions are usually associated with the 64-bit
+ * relocations: R_BPF_64_64. Therefore, signal the need for an extra
+ * pass if the circumstances are right.
+ */
+static int handle_ld_imm64(struct jit_context *ctx,
+			   const struct bpf_insn *insn,
+			   u8 *len)
+{
+	const s32 idx = get_index_for_insn(ctx, insn);
+	u8 *buf = effective_jit_buf(ctx);
+
+	/* We're about to consume 2 VM instructions. */
+	if (is_last_insn(ctx->prog, idx)) {
+		pr_err("bpf-jit: need more data for 64-bit immediate.\n");
+		return -EINVAL;
+	}
+
+	*len = mov_r64_i64(buf, insn->dst_reg, insn->imm, (insn + 1)->imm);
+
+	if (bpf_pseudo_func(insn))
+		set_need_for_extra_pass(ctx);
+
+	return 0;
+}
+
+/*
+ * Handles one eBPF instruction at a time. To make this function faster,
+ * it does not call "jit_buffer_check()". Else, it would call it for every
+ * instruction. As a result, it should not be invoked directly. Only
+ * "handle_body()", that has already executed the "check", may call this
+ * function.
+ *
+ * If the "ret" value is negative, something has went wrong. Else,
+ * it mostly holds the value 0 and rarely 1. Number 1 signals
+ * the loop in "handle_body()" to skip the next instruction, because
+ * it has been consumed as part of a 64-bit immediate value.
+ */
+static int handle_insn(struct jit_context *ctx, u32 idx)
+{
+	const struct bpf_insn *insn = &ctx->prog->insnsi[idx];
+	const u8  code = insn->code;
+	const u8  dst  = insn->dst_reg;
+	const u8  src  = insn->src_reg;
+	const s16 off  = insn->off;
+	const s32 imm  = insn->imm;
+	u8 *buf = effective_jit_buf(ctx);
+	u8  len = 0;
+	int ret = 0;
+
+	switch (code) {
+	/* dst += src (32-bit) */
+	case BPF_ALU | BPF_ADD | BPF_X:
+		len = add_r32(buf, dst, src);
+		break;
+	/* dst += imm (32-bit) */
+	case BPF_ALU | BPF_ADD | BPF_K:
+		len = add_r32_i32(buf, dst, imm);
+		break;
+	/* dst -= src (32-bit) */
+	case BPF_ALU | BPF_SUB | BPF_X:
+		len = sub_r32(buf, dst, src);
+		break;
+	/* dst -= imm (32-bit) */
+	case BPF_ALU | BPF_SUB | BPF_K:
+		len = sub_r32_i32(buf, dst, imm);
+		break;
+	/* dst = -dst (32-bit) */
+	case BPF_ALU | BPF_NEG:
+		len = neg_r32(buf, dst);
+		break;
+	/* dst *= src (32-bit) */
+	case BPF_ALU | BPF_MUL | BPF_X:
+		len = mul_r32(buf, dst, src);
+		break;
+	/* dst *= imm (32-bit) */
+	case BPF_ALU | BPF_MUL | BPF_K:
+		len = mul_r32_i32(buf, dst, imm);
+		break;
+	/* dst /= src (32-bit) */
+	case BPF_ALU | BPF_DIV | BPF_X:
+		len = div_r32(buf, dst, src, off == 1);
+		break;
+	/* dst /= imm (32-bit) */
+	case BPF_ALU | BPF_DIV | BPF_K:
+		len = div_r32_i32(buf, dst, imm, off == 1);
+		break;
+	/* dst %= src (32-bit) */
+	case BPF_ALU | BPF_MOD | BPF_X:
+		len = mod_r32(buf, dst, src, off == 1);
+		break;
+	/* dst %= imm (32-bit) */
+	case BPF_ALU | BPF_MOD | BPF_K:
+		len = mod_r32_i32(buf, dst, imm, off == 1);
+		break;
+	/* dst &= src (32-bit) */
+	case BPF_ALU | BPF_AND | BPF_X:
+		len = and_r32(buf, dst, src);
+		break;
+	/* dst &= imm (32-bit) */
+	case BPF_ALU | BPF_AND | BPF_K:
+		len = and_r32_i32(buf, dst, imm);
+		break;
+	/* dst |= src (32-bit) */
+	case BPF_ALU | BPF_OR | BPF_X:
+		len = or_r32(buf, dst, src);
+		break;
+	/* dst |= imm (32-bit) */
+	case BPF_ALU | BPF_OR | BPF_K:
+		len = or_r32_i32(buf, dst, imm);
+		break;
+	/* dst ^= src (32-bit) */
+	case BPF_ALU | BPF_XOR | BPF_X:
+		len = xor_r32(buf, dst, src);
+		break;
+	/* dst ^= imm (32-bit) */
+	case BPF_ALU | BPF_XOR | BPF_K:
+		len = xor_r32_i32(buf, dst, imm);
+		break;
+	/* dst <<= src (32-bit) */
+	case BPF_ALU | BPF_LSH | BPF_X:
+		len = lsh_r32(buf, dst, src);
+		break;
+	/* dst <<= imm (32-bit) */
+	case BPF_ALU | BPF_LSH | BPF_K:
+		len = lsh_r32_i32(buf, dst, imm);
+		break;
+	/* dst >>= src (32-bit) [unsigned] */
+	case BPF_ALU | BPF_RSH | BPF_X:
+		len = rsh_r32(buf, dst, src);
+		break;
+	/* dst >>= imm (32-bit) [unsigned] */
+	case BPF_ALU | BPF_RSH | BPF_K:
+		len = rsh_r32_i32(buf, dst, imm);
+		break;
+	/* dst >>= src (32-bit) [signed] */
+	case BPF_ALU | BPF_ARSH | BPF_X:
+		len = arsh_r32(buf, dst, src);
+		break;
+	/* dst >>= imm (32-bit) [signed] */
+	case BPF_ALU | BPF_ARSH | BPF_K:
+		len = arsh_r32_i32(buf, dst, imm);
+		break;
+	/* dst = src (32-bit) */
+	case BPF_ALU | BPF_MOV | BPF_X:
+		len = mov_r32(buf, dst, src, (u8)off);
+		break;
+	/* dst = imm32 (32-bit) */
+	case BPF_ALU | BPF_MOV | BPF_K:
+		len = mov_r32_i32(buf, dst, imm);
+		break;
+	/* dst = swap(dst) */
+	case BPF_ALU   | BPF_END | BPF_FROM_LE:
+	case BPF_ALU   | BPF_END | BPF_FROM_BE:
+	case BPF_ALU64 | BPF_END | BPF_FROM_LE: {
+		CHECK_RET(handle_swap(buf, dst, imm, BPF_SRC(code),
+				      BPF_CLASS(code) == BPF_ALU64,
+				      ctx->do_zext, &len));
+		break;
+	}
+	/* dst += src (64-bit) */
+	case BPF_ALU64 | BPF_ADD | BPF_X:
+		len = add_r64(buf, dst, src);
+		break;
+	/* dst += imm32 (64-bit) */
+	case BPF_ALU64 | BPF_ADD | BPF_K:
+		len = add_r64_i32(buf, dst, imm);
+		break;
+	/* dst -= src (64-bit) */
+	case BPF_ALU64 | BPF_SUB | BPF_X:
+		len = sub_r64(buf, dst, src);
+		break;
+	/* dst -= imm32 (64-bit) */
+	case BPF_ALU64 | BPF_SUB | BPF_K:
+		len = sub_r64_i32(buf, dst, imm);
+		break;
+	/* dst = -dst (64-bit) */
+	case BPF_ALU64 | BPF_NEG:
+		len = neg_r64(buf, dst);
+		break;
+	/* dst *= src (64-bit) */
+	case BPF_ALU64 | BPF_MUL | BPF_X:
+		len = mul_r64(buf, dst, src);
+		break;
+	/* dst *= imm32 (64-bit) */
+	case BPF_ALU64 | BPF_MUL | BPF_K:
+		len = mul_r64_i32(buf, dst, imm);
+		break;
+	/* dst &= src (64-bit) */
+	case BPF_ALU64 | BPF_AND | BPF_X:
+		len = and_r64(buf, dst, src);
+		break;
+	/* dst &= imm32 (64-bit) */
+	case BPF_ALU64 | BPF_AND | BPF_K:
+		len = and_r64_i32(buf, dst, imm);
+		break;
+	/* dst |= src (64-bit) */
+	case BPF_ALU64 | BPF_OR | BPF_X:
+		len = or_r64(buf, dst, src);
+		break;
+	/* dst |= imm32 (64-bit) */
+	case BPF_ALU64 | BPF_OR | BPF_K:
+		len = or_r64_i32(buf, dst, imm);
+		break;
+	/* dst ^= src (64-bit) */
+	case BPF_ALU64 | BPF_XOR | BPF_X:
+		len = xor_r64(buf, dst, src);
+		break;
+	/* dst ^= imm32 (64-bit) */
+	case BPF_ALU64 | BPF_XOR | BPF_K:
+		len = xor_r64_i32(buf, dst, imm);
+		break;
+	/* dst <<= src (64-bit) */
+	case BPF_ALU64 | BPF_LSH | BPF_X:
+		len = lsh_r64(buf, dst, src);
+		break;
+	/* dst <<= imm32 (64-bit) */
+	case BPF_ALU64 | BPF_LSH | BPF_K:
+		len = lsh_r64_i32(buf, dst, imm);
+		break;
+	/* dst >>= src (64-bit) [unsigned] */
+	case BPF_ALU64 | BPF_RSH | BPF_X:
+		len = rsh_r64(buf, dst, src);
+		break;
+	/* dst >>= imm32 (64-bit) [unsigned] */
+	case BPF_ALU64 | BPF_RSH | BPF_K:
+		len = rsh_r64_i32(buf, dst, imm);
+		break;
+	/* dst >>= src (64-bit) [signed] */
+	case BPF_ALU64 | BPF_ARSH | BPF_X:
+		len = arsh_r64(buf, dst, src);
+		break;
+	/* dst >>= imm32 (64-bit) [signed] */
+	case BPF_ALU64 | BPF_ARSH | BPF_K:
+		len = arsh_r64_i32(buf, dst, imm);
+		break;
+	/* dst = src (64-bit) */
+	case BPF_ALU64 | BPF_MOV | BPF_X:
+		len = mov_r64(buf, dst, src, (u8)off);
+		break;
+	/* dst = imm32 (sign extend to 64-bit) */
+	case BPF_ALU64 | BPF_MOV | BPF_K:
+		len = mov_r64_i32(buf, dst, imm);
+		break;
+	/* dst = imm64 */
+	case BPF_LD | BPF_DW | BPF_IMM:
+		CHECK_RET(handle_ld_imm64(ctx, insn, &len));
+		/* Tell the loop to skip the next instruction. */
+		ret = 1;
+		break;
+	/* dst = *(size *)(src + off) */
+	case BPF_LDX | BPF_MEM | BPF_W:
+	case BPF_LDX | BPF_MEM | BPF_H:
+	case BPF_LDX | BPF_MEM | BPF_B:
+	case BPF_LDX | BPF_MEM | BPF_DW:
+		len = load_r(buf, dst, src, off, BPF_SIZE(code), false);
+		break;
+	case BPF_LDX | BPF_MEMSX | BPF_W:
+	case BPF_LDX | BPF_MEMSX | BPF_H:
+	case BPF_LDX | BPF_MEMSX | BPF_B:
+		len = load_r(buf, dst, src, off, BPF_SIZE(code), true);
+		break;
+	/* *(size *)(dst + off) = src */
+	case BPF_STX | BPF_MEM | BPF_W:
+	case BPF_STX | BPF_MEM | BPF_H:
+	case BPF_STX | BPF_MEM | BPF_B:
+	case BPF_STX | BPF_MEM | BPF_DW:
+		len = store_r(buf, src, dst, off, BPF_SIZE(code));
+		break;
+	case BPF_ST | BPF_MEM | BPF_W:
+	case BPF_ST | BPF_MEM | BPF_H:
+	case BPF_ST | BPF_MEM | BPF_B:
+	case BPF_ST | BPF_MEM | BPF_DW:
+		len = store_i(buf, imm, dst, off, BPF_SIZE(code));
+		break;
+	case BPF_JMP   | BPF_JA:
+	case BPF_JMP   | BPF_JEQ  | BPF_X:
+	case BPF_JMP   | BPF_JEQ  | BPF_K:
+	case BPF_JMP   | BPF_JNE  | BPF_X:
+	case BPF_JMP   | BPF_JNE  | BPF_K:
+	case BPF_JMP   | BPF_JSET | BPF_X:
+	case BPF_JMP   | BPF_JSET | BPF_K:
+	case BPF_JMP   | BPF_JGT  | BPF_X:
+	case BPF_JMP   | BPF_JGT  | BPF_K:
+	case BPF_JMP   | BPF_JGE  | BPF_X:
+	case BPF_JMP   | BPF_JGE  | BPF_K:
+	case BPF_JMP   | BPF_JSGT | BPF_X:
+	case BPF_JMP   | BPF_JSGT | BPF_K:
+	case BPF_JMP   | BPF_JSGE | BPF_X:
+	case BPF_JMP   | BPF_JSGE | BPF_K:
+	case BPF_JMP   | BPF_JLT  | BPF_X:
+	case BPF_JMP   | BPF_JLT  | BPF_K:
+	case BPF_JMP   | BPF_JLE  | BPF_X:
+	case BPF_JMP   | BPF_JLE  | BPF_K:
+	case BPF_JMP   | BPF_JSLT | BPF_X:
+	case BPF_JMP   | BPF_JSLT | BPF_K:
+	case BPF_JMP   | BPF_JSLE | BPF_X:
+	case BPF_JMP   | BPF_JSLE | BPF_K:
+	case BPF_JMP32 | BPF_JA:
+	case BPF_JMP32 | BPF_JEQ  | BPF_X:
+	case BPF_JMP32 | BPF_JEQ  | BPF_K:
+	case BPF_JMP32 | BPF_JNE  | BPF_X:
+	case BPF_JMP32 | BPF_JNE  | BPF_K:
+	case BPF_JMP32 | BPF_JSET | BPF_X:
+	case BPF_JMP32 | BPF_JSET | BPF_K:
+	case BPF_JMP32 | BPF_JGT  | BPF_X:
+	case BPF_JMP32 | BPF_JGT  | BPF_K:
+	case BPF_JMP32 | BPF_JGE  | BPF_X:
+	case BPF_JMP32 | BPF_JGE  | BPF_K:
+	case BPF_JMP32 | BPF_JSGT | BPF_X:
+	case BPF_JMP32 | BPF_JSGT | BPF_K:
+	case BPF_JMP32 | BPF_JSGE | BPF_X:
+	case BPF_JMP32 | BPF_JSGE | BPF_K:
+	case BPF_JMP32 | BPF_JLT  | BPF_X:
+	case BPF_JMP32 | BPF_JLT  | BPF_K:
+	case BPF_JMP32 | BPF_JLE  | BPF_X:
+	case BPF_JMP32 | BPF_JLE  | BPF_K:
+	case BPF_JMP32 | BPF_JSLT | BPF_X:
+	case BPF_JMP32 | BPF_JSLT | BPF_K:
+	case BPF_JMP32 | BPF_JSLE | BPF_X:
+	case BPF_JMP32 | BPF_JSLE | BPF_K:
+		CHECK_RET(handle_jumps(ctx, insn, &len));
+		break;
+	case BPF_JMP | BPF_CALL:
+		CHECK_RET(handle_call(ctx, insn, &len));
+		break;
+
+	case BPF_JMP | BPF_EXIT:
+		/* If this is the last instruction, epilogue will follow. */
+		if (is_last_insn(ctx->prog, idx))
+			break;
+		CHECK_RET(handle_jmp_epilogue(ctx, insn, &len));
+		break;
+	default:
+		pr_err("bpf-jit: can't handle instruction code 0x%02X\n", code);
+		return -EOPNOTSUPP;
+	}
+
+	if (BPF_CLASS(code) == BPF_ALU) {
+		/*
+		 * Skip the "swap" instructions. Even 64-bit swaps are of type
+		 * BPF_ALU (and not BPF_ALU64). Therefore, for the swaps, one
+		 * has to look at the "size" of the operations rather than the
+		 * ALU type. "gen_swap()" specifically takes care of that.
+		 */
+		if (BPF_OP(code) != BPF_END && ctx->do_zext)
+			len += zext(BUF(buf, len), dst);
+	}
+
+	jit_buffer_update(ctx, len);
+
+	return ret;
+}
+
+static int handle_body(struct jit_context *ctx)
+{
+	int ret;
+	bool populate_bpf2insn = false;
+	const struct bpf_prog *prog = ctx->prog;
+
+	CHECK_RET(jit_buffer_check(ctx));
+
+	/*
+	 * Record the mapping for the instructions during the dry-run.
+	 * Doing it this way allows us to have the mapping ready for
+	 * the jump instructions during the real compilation phase.
+	 */
+	if (!ctx->emit)
+		populate_bpf2insn = true;
+
+	for (u32 i = 0; i < prog->len; i++) {
+		/* During the dry-run, jit.len grows gradually per BPF insn. */
+		if (populate_bpf2insn)
+			ctx->bpf2insn[i] = ctx->jit.len;
+
+		CHECK_RET(handle_insn(ctx, i));
+		if (ret > 0) {
+			/* "ret" is 1 if two (64-bit) chunks were consumed. */
+			ctx->bpf2insn[i + 1] = ctx->bpf2insn[i];
+			i++;
+		}
+	}
+
+	/* If bpf2insn had to be populated, then it is done at this point. */
+	if (populate_bpf2insn)
+		ctx->bpf2insn_valid = true;
+
+	return 0;
+}
+
+/*
+ * Initialize the memory with "unimp_s" which is the mnemonic for
+ * "unimplemented" instruction and always raises an exception.
+ *
+ * The instruction is 2 bytes. If "size" is odd, there is not much
+ * that can be done about the last byte in "area". Because, the
+ * CPU always fetches instructions in two bytes. Therefore, the
+ * byte beyond the last one is going to accompany it during a
+ * possible fetch. In the most likely case of a little endian
+ * system, that beyond-byte will become the major opcode and
+ * we have no control over its initialisation.
+ */
+static void fill_ill_insn(void *area, unsigned int size)
+{
+	const u16 unimp_s = 0x79e0;
+
+	if (size & 1) {
+		*((u8 *)area + (size - 1)) = 0xff;
+		size -= 1;
+	}
+
+	memset16(area, unimp_s, size >> 1);
+}
+
+/* Piece of memory that can be allocated at the beginning of jit_prepare(). */
+static int jit_prepare_early_mem_alloc(struct jit_context *ctx)
+{
+	ctx->bpf2insn = kcalloc(ctx->prog->len, sizeof(ctx->jit.len),
+				GFP_KERNEL);
+
+	if (!ctx->bpf2insn) {
+		pr_err("bpf-jit: could not allocate memory for "
+		       "mapping of the instructions.\n");
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+/*
+ * Memory allocations that rely on parameters known at the end of
+ * jit_prepare().
+ */
+static int jit_prepare_final_mem_alloc(struct jit_context *ctx)
+{
+	const size_t alignment = sizeof(u32);
+
+	ctx->bpf_header = bpf_jit_binary_alloc(ctx->jit.len, &ctx->jit.buf,
+					       alignment, fill_ill_insn);
+	if (!ctx->bpf_header) {
+		pr_err("bpf-jit: could not allocate memory for translation.\n");
+		return -ENOMEM;
+	}
+
+	if (ctx->need_extra_pass) {
+		ctx->jit_data = kzalloc_obj(*ctx->jit_data);
+		if (!ctx->jit_data)
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
+/*
+ * The first phase of the translation without actually emitting any
+ * instruction. It helps in getting a forecast on some aspects, such
+ * as the length of the whole program or where the epilogue starts.
+ *
+ * Whenever the necessary parameters are known, memories are allocated.
+ */
+static int jit_prepare(struct jit_context *ctx)
+{
+	int ret;
+
+	/* Dry run. */
+	ctx->emit = false;
+
+	CHECK_RET(jit_prepare_early_mem_alloc(ctx));
+
+	/* Get the length of prologue section after some register analysis. */
+	analyze_reg_usage(ctx);
+	CHECK_RET(handle_prologue(ctx));
+
+	CHECK_RET(handle_body(ctx));
+
+	/* Record at which offset epilogue begins. */
+	ctx->epilogue_offset = ctx->jit.len;
+
+	/* Process the epilogue section now. */
+	CHECK_RET(handle_epilogue(ctx));
+
+	CHECK_RET(jit_prepare_final_mem_alloc(ctx));
+
+	return 0;
+}
+
+/*
+ * jit_compile() is the real compilation phase. jit_prepare() is
+ * invoked before jit_compile() as a dry-run to make sure everything
+ * will go OK and allocate the necessary memory.
+ *
+ * In the end, jit_compile() checks if it has produced the same number
+ * of instructions as jit_prepare() would.
+ */
+static int jit_compile(struct jit_context *ctx)
+{
+	int ret;
+
+	/* Let there be code. */
+	ctx->emit = true;
+
+	CHECK_RET(handle_prologue(ctx));
+
+	CHECK_RET(handle_body(ctx));
+
+	CHECK_RET(handle_epilogue(ctx));
+
+	if (ctx->jit.index != ctx->jit.len) {
+		pr_err("bpf-jit: divergence between the phases; "
+		       "%u vs. %u (bytes).\n",
+		       ctx->jit.len, ctx->jit.index);
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
+/*
+ * Calling this function implies a successful JIT. A successful
+ * translation is signaled by setting the right parameters:
+ *
+ * prog->jited=1, prog->jited_len=..., prog->bpf_func=...
+ */
+static int jit_finalize(struct jit_context *ctx)
+{
+	struct bpf_prog *prog = ctx->prog;
+
+	/* We're going to need this information for the "do_extra_pass()". */
+	if (ctx->need_extra_pass) {
+		ctx->jit_data->bpf_header = ctx->bpf_header;
+		ctx->jit_data->bpf2insn = ctx->bpf2insn;
+		prog->aux->jit_data = (void *)ctx->jit_data;
+	} else {
+		/*
+		 * If things seem finalised, then mark the JITed memory
+		 * as R-X and flush it.
+		 */
+		if (bpf_jit_binary_lock_ro(ctx->bpf_header)) {
+			pr_err("bpf-jit: Could not lock the JIT memory.\n");
+			return -EFAULT;
+		}
+		flush_icache_range((unsigned long)ctx->bpf_header,
+				   (unsigned long)
+				   BUF(ctx->jit.buf, ctx->jit.len));
+		prog->aux->jit_data = NULL;
+		bpf_prog_fill_jited_linfo(prog, ctx->bpf2insn);
+	}
+
+	ctx->success = true;
+	prog->bpf_func = (void *)ctx->jit.buf;
+	prog->jited_len = ctx->jit.len;
+	prog->jited = 1;
+
+	jit_ctx_cleanup(ctx);
+	jit_dump(ctx);
+
+	return 0;
+}
+
+/*
+ * A lenient verification for the existence of JIT context in "prog".
+ * Apparently the JIT internals, namely jit_subprogs() in bpf/verifier.c,
+ * may request for a second compilation although nothing needs to be done.
+ */
+static inline int check_jit_context(const struct bpf_prog *prog)
+{
+	if (!prog->aux->jit_data) {
+		pr_notice("bpf-jit: no jit data for the extra pass.\n");
+		return 1;
+	} else {
+		return 0;
+	}
+}
+
+/* Reuse the previous pass's data. */
+static int jit_resume_context(struct jit_context *ctx)
+{
+	struct arc_jit_data *jdata =
+		(struct arc_jit_data *)ctx->prog->aux->jit_data;
+
+	if (!jdata) {
+		pr_err("bpf-jit: no jit data for the extra pass.\n");
+		return -EINVAL;
+	}
+
+	ctx->jit.buf = (u8 *)ctx->prog->bpf_func;
+	ctx->jit.len = ctx->prog->jited_len;
+	ctx->bpf_header = jdata->bpf_header;
+	ctx->bpf2insn = (u32 *)jdata->bpf2insn;
+	ctx->bpf2insn_valid = ctx->bpf2insn ? true : false;
+	ctx->jit_data = jdata;
+
+	return 0;
+}
+
+/*
+ * Patch in the new addresses. The instructions of interest are:
+ *
+ * - call
+ * - ld r64, imm64
+ *
+ * For "call"s, it resolves the addresses one more time through the
+ * handle_call().
+ *
+ * For 64-bit immediate loads, it just retranslates them, because the BPF
+ * core in kernel might have changed the value since the normal pass.
+ */
+static int jit_patch_relocations(struct jit_context *ctx)
+{
+	const u8 bpf_opc_call = BPF_JMP | BPF_CALL;
+	const u8 bpf_opc_ldi64 = BPF_LD | BPF_DW | BPF_IMM;
+	const struct bpf_prog *prog = ctx->prog;
+	int ret;
+
+	ctx->emit = true;
+	for (u32 i = 0; i < prog->len; i++) {
+		const struct bpf_insn *insn = &prog->insnsi[i];
+		u8 dummy;
+		/*
+		 * Adjust "ctx.jit.index", so "gen_*()" functions below
+		 * can use it for their output addresses.
+		 */
+		ctx->jit.index = ctx->bpf2insn[i];
+
+		if (insn->code == bpf_opc_call) {
+			CHECK_RET(handle_call(ctx, insn, &dummy));
+		} else if (insn->code == bpf_opc_ldi64) {
+			CHECK_RET(handle_ld_imm64(ctx, insn, &dummy));
+			/* Skip the next instruction. */
+			++i;
+		}
+	}
+	return 0;
+}
+
+/*
+ * A normal pass that involves a "dry-run" phase, jit_prepare(),
+ * to get the necessary data for the real compilation phase,
+ * jit_compile().
+ */
+static struct bpf_prog *do_normal_pass(struct bpf_prog *prog)
+{
+	struct jit_context ctx;
+
+	/* Bail out if JIT is disabled. */
+	if (!prog->jit_requested)
+		return prog;
+
+	if (jit_ctx_init(&ctx, prog)) {
+		jit_ctx_cleanup(&ctx);
+		return prog;
+	}
+
+	/* Get the lengths and allocate buffer. */
+	if (jit_prepare(&ctx)) {
+		jit_ctx_cleanup(&ctx);
+		return prog;
+	}
+
+	if (jit_compile(&ctx)) {
+		jit_ctx_cleanup(&ctx);
+		return prog;
+	}
+
+	if (jit_finalize(&ctx)) {
+		jit_ctx_cleanup(&ctx);
+		return prog;
+	}
+
+	return ctx.prog;
+}
+
+/*
+ * If there are multi-function BPF programs that call each other,
+ * their translated addresses are not known all at once. Therefore,
+ * an extra pass is needed to consult the bpf_jit_get_func_addr()
+ * again to get the newly translated addresses in order to resolve
+ * the "call"s.
+ */
+static struct bpf_prog *do_extra_pass(struct bpf_prog *prog)
+{
+	struct jit_context ctx;
+
+	/* Skip if there's no context to resume from. */
+	if (check_jit_context(prog))
+		return prog;
+
+	if (jit_ctx_init(&ctx, prog)) {
+		jit_ctx_cleanup(&ctx);
+		return prog;
+	}
+
+	if (jit_resume_context(&ctx)) {
+		jit_ctx_cleanup(&ctx);
+		return prog;
+	}
+
+	if (jit_patch_relocations(&ctx)) {
+		jit_ctx_cleanup(&ctx);
+		return prog;
+	}
+
+	if (jit_finalize(&ctx)) {
+		jit_ctx_cleanup(&ctx);
+		return prog;
+	}
+
+	return ctx.prog;
+}
+
+/*
+ * This function may be invoked twice for the same stream of BPF
+ * instructions. The "extra pass" happens, when there are
+ * (re)locations involved that their addresses are not known
+ * during the first run.
+ */
+struct bpf_prog *bpf_int_jit_compile(struct bpf_verifier_env *env, struct bpf_prog *prog)
+{
+	vm_dump(prog);
+
+	/* Was this program already translated? */
+	if (!prog->jited)
+		return do_normal_pass(prog);
+	else
+		return do_extra_pass(prog);
+
+	return prog;
+}
diff --git a/arch/arc/plat-axs10x/Kconfig b/arch/arc/plat-axs10x/Kconfig
new file mode 100644
index 000000000..40f2a74d4
--- /dev/null
+++ b/arch/arc/plat-axs10x/Kconfig
@@ -0,0 +1,45 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Copyright (C) 2013-15 Synopsys, Inc. (www.synopsys.com)
+#
+
+menuconfig ARC_PLAT_AXS10X
+	bool "Synopsys ARC AXS10x Software Development Platforms"
+	select DW_APB_ICTL
+	select GPIO_DWAPB
+	select HAVE_PCI
+	select GENERIC_IRQ_CHIP
+	select GPIOLIB
+	select AXS101 if ISA_ARCOMPACT
+	select AXS103 if ISA_ARCV2
+	help
+	  Support for the ARC AXS10x Software Development Platforms.
+
+	  The AXS10x Platforms consist of a mainboard with peripherals,
+	  on which several daughter cards can be placed. The daughter cards
+	  typically contain a CPU and memory.
+
+if ARC_PLAT_AXS10X
+
+config AXS101
+	depends on ISA_ARCOMPACT
+	bool "AXS101 with AXC001 CPU Card (ARC 770D/EM6/AS221)"
+	help
+	  This adds support for the 770D/EM6/AS221 CPU Card. Only the ARC
+	  770D is supported in Linux.
+
+	  The AXS101 Platform consists of an AXS10x mainboard with
+	  this daughtercard. Please use the axs101.dts device tree
+	  with this configuration.
+
+config AXS103
+	bool "AXS103 with AXC003 CPU Card (ARC HS38x)"
+	depends on ISA_ARCV2
+	help
+	  This adds support for the HS38x CPU Card.
+
+	  The AXS103 Platform consists of an AXS10x mainboard with
+	  this daughtercard. Please use the axs103.dts device tree
+	  with this configuration.
+
+endif
diff --git a/arch/arc/plat-axs10x/Makefile b/arch/arc/plat-axs10x/Makefile
new file mode 100644
index 000000000..cebe5716e
--- /dev/null
+++ b/arch/arc/plat-axs10x/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Copyright (C) 2013-15 Synopsys, Inc. (www.synopsys.com)
+#
+
+obj-$(CONFIG_ARC_PLAT_AXS10X) += axs10x.o
diff --git a/arch/arc/plat-axs10x/axs10x.c b/arch/arc/plat-axs10x/axs10x.c
new file mode 100644
index 000000000..1feb990a5
--- /dev/null
+++ b/arch/arc/plat-axs10x/axs10x.c
@@ -0,0 +1,384 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AXS101/AXS103 Software Development Platform
+ *
+ * Copyright (C) 2013-15 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#include <linux/of_fdt.h>
+#include <linux/libfdt.h>
+
+#include <asm/asm-offsets.h>
+#include <asm/io.h>
+#include <asm/mach_desc.h>
+#include <soc/arc/mcip.h>
+
+#define AXS_MB_CGU		0xE0010000
+#define AXS_MB_CREG		0xE0011000
+
+#define CREG_MB_IRQ_MUX		(AXS_MB_CREG + 0x214)
+#define CREG_MB_SW_RESET	(AXS_MB_CREG + 0x220)
+#define CREG_MB_VER		(AXS_MB_CREG + 0x230)
+#define CREG_MB_CONFIG		(AXS_MB_CREG + 0x234)
+
+#define AXC001_CREG		0xF0001000
+#define AXC001_GPIO_INTC	0xF0003000
+
+static void __init axs10x_enable_gpio_intc_wire(void)
+{
+	/*
+	 * Peripherals on CPU Card and Mother Board are wired to cpu intc via
+	 * intermediate DW APB GPIO blocks (mainly for debouncing)
+	 *
+	 *         ---------------------
+	 *        |  snps,arc700-intc |
+	 *        ---------------------
+	 *          | #7          | #15
+	 * -------------------   -------------------
+	 * | snps,dw-apb-gpio |  | snps,dw-apb-gpio |
+	 * -------------------   -------------------
+	 *        | #12                     |
+	 *        |                 [ Debug UART on cpu card ]
+	 *        |
+	 * ------------------------
+	 * | snps,dw-apb-intc (MB)|
+	 * ------------------------
+	 *  |      |       |      |
+	 * [eth] [uart]        [... other perip on Main Board]
+	 *
+	 * Current implementation of "irq-dw-apb-ictl" driver doesn't work well
+	 * with stacked INTCs. In particular problem happens if its master INTC
+	 * not yet instantiated. See discussion here -
+	 * https://lore.kernel.org/lkml/54F6FE2C.7020309@synopsys.com
+	 *
+	 * So setup the first gpio block as a passive pass thru and hide it from
+	 * DT hardware topology - connect MB intc directly to cpu intc
+	 * The GPIO "wire" needs to be init nevertheless (here)
+	 *
+	 * One side adv is that peripheral interrupt handling avoids one nested
+	 * intc ISR hop
+	 */
+#define GPIO_INTEN		(AXC001_GPIO_INTC + 0x30)
+#define GPIO_INTMASK		(AXC001_GPIO_INTC + 0x34)
+#define GPIO_INTTYPE_LEVEL	(AXC001_GPIO_INTC + 0x38)
+#define GPIO_INT_POLARITY	(AXC001_GPIO_INTC + 0x3c)
+#define MB_TO_GPIO_IRQ		12
+
+	iowrite32(~(1 << MB_TO_GPIO_IRQ), (void __iomem *) GPIO_INTMASK);
+	iowrite32(0, (void __iomem *) GPIO_INTTYPE_LEVEL);
+	iowrite32(~0, (void __iomem *) GPIO_INT_POLARITY);
+	iowrite32(1 << MB_TO_GPIO_IRQ, (void __iomem *) GPIO_INTEN);
+}
+
+static void __init axs10x_print_board_ver(unsigned int creg, const char *str)
+{
+	union ver {
+		struct {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+			unsigned int pad:11, y:12, m:4, d:5;
+#else
+			unsigned int d:5, m:4, y:12, pad:11;
+#endif
+		};
+		unsigned int val;
+	} board;
+
+	board.val = ioread32((void __iomem *)creg);
+	pr_info("AXS: %s FPGA Date: %u-%u-%u\n", str, board.d, board.m,
+		board.y);
+}
+
+static void __init axs10x_early_init(void)
+{
+	int mb_rev;
+	char mb[32];
+
+	/* Determine motherboard version */
+	if (ioread32((void __iomem *) CREG_MB_CONFIG) & (1 << 28))
+		mb_rev = 3;	/* HT-3 (rev3.0) */
+	else
+		mb_rev = 2;	/* HT-2 (rev2.0) */
+
+	axs10x_enable_gpio_intc_wire();
+
+	scnprintf(mb, 32, "MainBoard v%d", mb_rev);
+	axs10x_print_board_ver(CREG_MB_VER, mb);
+}
+
+#ifdef CONFIG_AXS101
+
+#define CREG_CPU_ADDR_770	(AXC001_CREG + 0x20)
+#define CREG_CPU_ADDR_TUNN	(AXC001_CREG + 0x60)
+#define CREG_CPU_ADDR_770_UPD	(AXC001_CREG + 0x34)
+#define CREG_CPU_ADDR_TUNN_UPD	(AXC001_CREG + 0x74)
+
+#define CREG_CPU_ARC770_IRQ_MUX	(AXC001_CREG + 0x114)
+#define CREG_CPU_GPIO_UART_MUX	(AXC001_CREG + 0x120)
+
+/*
+ * Set up System Memory Map for ARC cpu / peripherals controllers
+ *
+ * Each AXI master has a 4GB memory map specified as 16 apertures of 256MB, each
+ * of which maps to a corresponding 256MB aperture in Target slave memory map.
+ *
+ * e.g. ARC cpu AXI Master's aperture 8 (0x8000_0000) is mapped to aperture 0
+ * (0x0000_0000) of DDR Port 0 (slave #1)
+ *
+ * Access from cpu to MB controllers such as GMAC is setup using AXI Tunnel:
+ * which has master/slaves on both ends.
+ * e.g. aperture 14 (0xE000_0000) of ARC cpu is mapped to aperture 14
+ * (0xE000_0000) of CPU Card AXI Tunnel slave (slave #3) which is mapped to
+ * MB AXI Tunnel Master, which also has a mem map setup
+ *
+ * In the reverse direction, MB AXI Masters (e.g. GMAC) mem map is setup
+ * to map to MB AXI Tunnel slave which connects to CPU Card AXI Tunnel Master
+ */
+struct aperture {
+	unsigned int slave_sel:4, slave_off:4, pad:24;
+};
+
+/* CPU Card target slaves */
+#define AXC001_SLV_NONE			0
+#define AXC001_SLV_DDR_PORT0		1
+#define AXC001_SLV_SRAM			2
+#define AXC001_SLV_AXI_TUNNEL		3
+#define AXC001_SLV_AXI2APB		6
+#define AXC001_SLV_DDR_PORT1		7
+
+/* MB AXI Target slaves */
+#define AXS_MB_SLV_NONE			0
+#define AXS_MB_SLV_AXI_TUNNEL_CPU	1
+#define AXS_MB_SLV_AXI_TUNNEL_HAPS	2
+#define AXS_MB_SLV_SRAM			3
+#define AXS_MB_SLV_CONTROL		4
+
+/* MB AXI masters */
+#define AXS_MB_MST_TUNNEL_CPU		0
+#define AXS_MB_MST_USB_OHCI		10
+
+/*
+ * memmap for ARC core on CPU Card
+ */
+static const struct aperture axc001_memmap[16] = {
+	{AXC001_SLV_AXI_TUNNEL,		0x0},
+	{AXC001_SLV_AXI_TUNNEL,		0x1},
+	{AXC001_SLV_SRAM,		0x0}, /* 0x2000_0000: Local SRAM */
+	{AXC001_SLV_NONE,		0x0},
+	{AXC001_SLV_NONE,		0x0},
+	{AXC001_SLV_NONE,		0x0},
+	{AXC001_SLV_NONE,		0x0},
+	{AXC001_SLV_NONE,		0x0},
+	{AXC001_SLV_DDR_PORT0,		0x0}, /* 0x8000_0000: DDR   0..256M */
+	{AXC001_SLV_DDR_PORT0,		0x1}, /* 0x9000_0000: DDR 256..512M */
+	{AXC001_SLV_DDR_PORT0,		0x2},
+	{AXC001_SLV_DDR_PORT0,		0x3},
+	{AXC001_SLV_NONE,		0x0},
+	{AXC001_SLV_AXI_TUNNEL,		0xD},
+	{AXC001_SLV_AXI_TUNNEL,		0xE}, /* MB: CREG, CGU... */
+	{AXC001_SLV_AXI2APB,		0x0}, /* CPU Card local CREG, CGU... */
+};
+
+/*
+ * memmap for CPU Card AXI Tunnel Master (for access by MB controllers)
+ * GMAC (MB) -> MB AXI Tunnel slave -> CPU Card AXI Tunnel Master -> DDR
+ */
+static const struct aperture axc001_axi_tunnel_memmap[16] = {
+	{AXC001_SLV_AXI_TUNNEL,		0x0},
+	{AXC001_SLV_AXI_TUNNEL,		0x1},
+	{AXC001_SLV_SRAM,		0x0},
+	{AXC001_SLV_NONE,		0x0},
+	{AXC001_SLV_NONE,		0x0},
+	{AXC001_SLV_NONE,		0x0},
+	{AXC001_SLV_NONE,		0x0},
+	{AXC001_SLV_NONE,		0x0},
+	{AXC001_SLV_DDR_PORT1,		0x0},
+	{AXC001_SLV_DDR_PORT1,		0x1},
+	{AXC001_SLV_DDR_PORT1,		0x2},
+	{AXC001_SLV_DDR_PORT1,		0x3},
+	{AXC001_SLV_NONE,		0x0},
+	{AXC001_SLV_AXI_TUNNEL,		0xD},
+	{AXC001_SLV_AXI_TUNNEL,		0xE},
+	{AXC001_SLV_AXI2APB,		0x0},
+};
+
+/*
+ * memmap for MB AXI Masters
+ * Same mem map for all perip controllers as well as MB AXI Tunnel Master
+ */
+static const struct aperture axs_mb_memmap[16] = {
+	{AXS_MB_SLV_SRAM,		0x0},
+	{AXS_MB_SLV_SRAM,		0x0},
+	{AXS_MB_SLV_NONE,		0x0},
+	{AXS_MB_SLV_NONE,		0x0},
+	{AXS_MB_SLV_NONE,		0x0},
+	{AXS_MB_SLV_NONE,		0x0},
+	{AXS_MB_SLV_NONE,		0x0},
+	{AXS_MB_SLV_NONE,		0x0},
+	{AXS_MB_SLV_AXI_TUNNEL_CPU,	0x8},	/* DDR on CPU Card */
+	{AXS_MB_SLV_AXI_TUNNEL_CPU,	0x9},	/* DDR on CPU Card */
+	{AXS_MB_SLV_AXI_TUNNEL_CPU,	0xA},
+	{AXS_MB_SLV_AXI_TUNNEL_CPU,	0xB},
+	{AXS_MB_SLV_NONE,		0x0},
+	{AXS_MB_SLV_AXI_TUNNEL_HAPS,	0xD},
+	{AXS_MB_SLV_CONTROL,		0x0},	/* MB Local CREG, CGU... */
+	{AXS_MB_SLV_AXI_TUNNEL_CPU,	0xF},
+};
+
+static noinline void __init
+axs101_set_memmap(void __iomem *base, const struct aperture map[16])
+{
+	unsigned int slave_select, slave_offset;
+	int i;
+
+	slave_select = slave_offset = 0;
+	for (i = 0; i < 8; i++) {
+		slave_select |= map[i].slave_sel << (i << 2);
+		slave_offset |= map[i].slave_off << (i << 2);
+	}
+
+	iowrite32(slave_select, base + 0x0);	/* SLV0 */
+	iowrite32(slave_offset, base + 0x8);	/* OFFSET0 */
+
+	slave_select = slave_offset = 0;
+	for (i = 0; i < 8; i++) {
+		slave_select |= map[i+8].slave_sel << (i << 2);
+		slave_offset |= map[i+8].slave_off << (i << 2);
+	}
+
+	iowrite32(slave_select, base + 0x4);	/* SLV1 */
+	iowrite32(slave_offset, base + 0xC);	/* OFFSET1 */
+}
+
+static void __init axs101_early_init(void)
+{
+	int i;
+
+	/* ARC 770D memory view */
+	axs101_set_memmap((void __iomem *) CREG_CPU_ADDR_770, axc001_memmap);
+	iowrite32(1, (void __iomem *) CREG_CPU_ADDR_770_UPD);
+
+	/* AXI tunnel memory map (incoming traffic from MB into CPU Card */
+	axs101_set_memmap((void __iomem *) CREG_CPU_ADDR_TUNN,
+			      axc001_axi_tunnel_memmap);
+	iowrite32(1, (void __iomem *) CREG_CPU_ADDR_TUNN_UPD);
+
+	/* MB peripherals memory map */
+	for (i = AXS_MB_MST_TUNNEL_CPU; i <= AXS_MB_MST_USB_OHCI; i++)
+		axs101_set_memmap((void __iomem *) AXS_MB_CREG + (i << 4),
+				      axs_mb_memmap);
+
+	iowrite32(0x3ff, (void __iomem *) AXS_MB_CREG + 0x100); /* Update */
+
+	/* GPIO pins 18 and 19 are used as UART rx and tx, respectively. */
+	iowrite32(0x01, (void __iomem *) CREG_CPU_GPIO_UART_MUX);
+
+	/* Set up the MB interrupt system: mux interrupts to GPIO7) */
+	iowrite32(0x01, (void __iomem *) CREG_MB_IRQ_MUX);
+
+	/* reset ethernet and ULPI interfaces */
+	iowrite32(0x18, (void __iomem *) CREG_MB_SW_RESET);
+
+	/* map GPIO 14:10 to ARC 9:5 (IRQ mux change for MB v2 onwards) */
+	iowrite32(0x52, (void __iomem *) CREG_CPU_ARC770_IRQ_MUX);
+
+	axs10x_early_init();
+}
+
+#endif	/* CONFIG_AXS101 */
+
+#ifdef CONFIG_AXS103
+
+#define AXC003_CREG	0xF0001000
+#define AXC003_MST_AXI_TUNNEL	0
+#define AXC003_MST_HS38		1
+
+#define CREG_CPU_AXI_M0_IRQ_MUX	(AXC003_CREG + 0x440)
+#define CREG_CPU_GPIO_UART_MUX	(AXC003_CREG + 0x480)
+#define CREG_CPU_TUN_IO_CTRL	(AXC003_CREG + 0x494)
+
+
+static void __init axs103_early_init(void)
+{
+#ifdef CONFIG_ARC_MCIP
+	/*
+	 * AXS103 configurations for SMP/QUAD configurations share device tree
+	 * which defaults to 100 MHz. However recent failures of Quad config
+	 * revealed P&R timing violations so clamp it down to safe 50 MHz
+	 * Instead of duplicating defconfig/DT for SMP/QUAD, add a small hack
+	 * of fudging the freq in DT
+	 */
+#define AXS103_QUAD_CORE_CPU_FREQ_HZ	50000000
+
+	unsigned int num_cores = (read_aux_reg(ARC_REG_MCIP_BCR) >> 16) & 0x3F;
+	if (num_cores > 2) {
+		u32 freq;
+		int off = fdt_path_offset(initial_boot_params, "/cpu_card/core_clk");
+		const struct fdt_property *prop;
+
+		prop = fdt_get_property(initial_boot_params, off,
+					"assigned-clock-rates", NULL);
+		freq = be32_to_cpu(*(u32 *)(prop->data));
+
+		/* Patching .dtb in-place with new core clock value */
+		if (freq != AXS103_QUAD_CORE_CPU_FREQ_HZ) {
+			freq = cpu_to_be32(AXS103_QUAD_CORE_CPU_FREQ_HZ);
+			fdt_setprop_inplace(initial_boot_params, off,
+					    "assigned-clock-rates", &freq, sizeof(freq));
+		}
+	}
+#endif
+
+	/* Memory maps already config in pre-bootloader */
+
+	/* set GPIO mux to UART */
+	iowrite32(0x01, (void __iomem *) CREG_CPU_GPIO_UART_MUX);
+
+	iowrite32((0x00100000U | 0x000C0000U | 0x00003322U),
+		  (void __iomem *) CREG_CPU_TUN_IO_CTRL);
+
+	/* Set up the AXS_MB interrupt system.*/
+	iowrite32(12, (void __iomem *) (CREG_CPU_AXI_M0_IRQ_MUX
+					 + (AXC003_MST_HS38 << 2)));
+
+	/* connect ICTL - Main Board with GPIO line */
+	iowrite32(0x01, (void __iomem *) CREG_MB_IRQ_MUX);
+
+	axs10x_print_board_ver(AXC003_CREG + 4088, "AXC003 CPU Card");
+
+	axs10x_early_init();
+}
+#endif
+
+#ifdef CONFIG_AXS101
+
+static const char *axs101_compat[] __initconst = {
+	"snps,axs101",
+	NULL,
+};
+
+MACHINE_START(AXS101, "axs101")
+	.dt_compat	= axs101_compat,
+	.init_early	= axs101_early_init,
+MACHINE_END
+
+#endif	/* CONFIG_AXS101 */
+
+#ifdef CONFIG_AXS103
+
+static const char *axs103_compat[] __initconst = {
+	"snps,axs103",
+	NULL,
+};
+
+MACHINE_START(AXS103, "axs103")
+	.dt_compat	= axs103_compat,
+	.init_early	= axs103_early_init,
+MACHINE_END
+
+/*
+ * For the VDK OS-kit, to get the offset to pid and command fields
+ */
+char coware_swa_pid_offset[TASK_PID];
+char coware_swa_comm_offset[TASK_COMM];
+
+#endif	/* CONFIG_AXS103 */
diff --git a/arch/arc/plat-hsdk/Kconfig b/arch/arc/plat-hsdk/Kconfig
new file mode 100644
index 000000000..a2d10c29f
--- /dev/null
+++ b/arch/arc/plat-hsdk/Kconfig
@@ -0,0 +1,14 @@
+# SPDX-License-Identifier: GPL-2.0-only
+# Copyright (C) 2017 Synopsys, Inc. (www.synopsys.com)
+#
+
+menuconfig ARC_SOC_HSDK
+	bool "ARC HS Development Kit SOC"
+	depends on ISA_ARCV2
+	select ARC_HAS_ACCL_REGS
+	select ARC_IRQ_NO_AUTOSAVE
+	select ARC_FPU_SAVE_RESTORE
+	select CLK_HSDK
+	select RESET_CONTROLLER
+	select RESET_HSDK
+	select HAVE_PCI
diff --git a/arch/arc/plat-hsdk/Makefile b/arch/arc/plat-hsdk/Makefile
new file mode 100644
index 000000000..bb2921e82
--- /dev/null
+++ b/arch/arc/plat-hsdk/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Copyright (C) 2017 Synopsys, Inc. (www.synopsys.com)
+#
+
+obj-y := platform.o
diff --git a/arch/arc/plat-hsdk/platform.c b/arch/arc/plat-hsdk/platform.c
new file mode 100644
index 000000000..c4a875b22
--- /dev/null
+++ b/arch/arc/plat-hsdk/platform.c
@@ -0,0 +1,326 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * ARC HSDK Platform support code
+ *
+ * Copyright (C) 2017 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#include <linux/init.h>
+#include <linux/of_fdt.h>
+#include <linux/libfdt.h>
+#include <linux/smp.h>
+#include <asm/arcregs.h>
+#include <asm/io.h>
+#include <asm/mach_desc.h>
+
+int arc_hsdk_axi_dmac_coherent __section(".data") = 0;
+
+#define ARC_CCM_UNUSED_ADDR	0x60000000
+
+
+#define ARC_PERIPHERAL_BASE	0xf0000000
+#define CREG_BASE		(ARC_PERIPHERAL_BASE + 0x1000)
+
+#define SDIO_BASE		(ARC_PERIPHERAL_BASE + 0xA000)
+#define SDIO_UHS_REG_EXT	(SDIO_BASE + 0x108)
+#define SDIO_UHS_REG_EXT_DIV_2	(2 << 30)
+
+#define HSDK_GPIO_INTC          (ARC_PERIPHERAL_BASE + 0x3000)
+
+static void __init hsdk_enable_gpio_intc_wire(void)
+{
+	/*
+	 * Peripherals on CPU Card are wired to cpu intc via intermediate
+	 * DW APB GPIO blocks (mainly for debouncing)
+	 *
+	 *         ---------------------
+	 *        |  snps,archs-intc  |
+	 *        ---------------------
+	 *                  |
+	 *        ----------------------
+	 *        | snps,archs-idu-intc |
+	 *        ----------------------
+	 *         |   |     |   |    |
+	 *         | [eth] [USB]    [... other peripherals]
+	 *         |
+	 * -------------------
+	 * | snps,dw-apb-intc |
+	 * -------------------
+	 *  |      |   |   |
+	 * [Bt] [HAPS]   [... other peripherals]
+	 *
+	 * Current implementation of "irq-dw-apb-ictl" driver doesn't work well
+	 * with stacked INTCs. In particular problem happens if its master INTC
+	 * not yet instantiated. See discussion here -
+	 * https://lore.kernel.org/lkml/54F6FE2C.7020309@synopsys.com
+	 *
+	 * So setup the first gpio block as a passive pass thru and hide it from
+	 * DT hardware topology - connect intc directly to cpu intc
+	 * The GPIO "wire" needs to be init nevertheless (here)
+	 *
+	 * One side adv is that peripheral interrupt handling avoids one nested
+	 * intc ISR hop
+	 *
+	 * According to HSDK User's Manual [1], "Table 2 Interrupt Mapping"
+	 * we have the following GPIO input lines used as sources of interrupt:
+	 * - GPIO[0] - Bluetooth interrupt of RS9113 module
+	 * - GPIO[2] - HAPS interrupt (on HapsTrak 3 connector)
+	 * - GPIO[3] - Audio codec (MAX9880A) interrupt
+	 * - GPIO[8-23] - Available on Arduino and PMOD_x headers
+	 * For now there's no use of Arduino and PMOD_x headers in Linux
+	 * use-case so we only enable lines 0, 2 and 3.
+	 *
+	 * [1] https://github.com/foss-for-synopsys-dwc-arc-processors/ARC-Development-Systems-Forum/wiki/docs/ARC_HSDK_User_Guide.pdf
+	 */
+#define GPIO_INTEN              (HSDK_GPIO_INTC + 0x30)
+#define GPIO_INTMASK            (HSDK_GPIO_INTC + 0x34)
+#define GPIO_INTTYPE_LEVEL      (HSDK_GPIO_INTC + 0x38)
+#define GPIO_INT_POLARITY       (HSDK_GPIO_INTC + 0x3c)
+#define GPIO_INT_CONNECTED_MASK	0x0d
+
+	iowrite32(0xffffffff, (void __iomem *) GPIO_INTMASK);
+	iowrite32(~GPIO_INT_CONNECTED_MASK, (void __iomem *) GPIO_INTMASK);
+	iowrite32(0x00000000, (void __iomem *) GPIO_INTTYPE_LEVEL);
+	iowrite32(0xffffffff, (void __iomem *) GPIO_INT_POLARITY);
+	iowrite32(GPIO_INT_CONNECTED_MASK, (void __iomem *) GPIO_INTEN);
+}
+
+static int __init hsdk_tweak_node_coherency(const char *path, bool coherent)
+{
+	void *fdt = initial_boot_params;
+	const void *prop;
+	int node, ret;
+	bool dt_coh_set;
+
+	node = fdt_path_offset(fdt, path);
+	if (node < 0)
+		goto tweak_fail;
+
+	prop = fdt_getprop(fdt, node, "dma-coherent", &ret);
+	if (!prop && ret != -FDT_ERR_NOTFOUND)
+		goto tweak_fail;
+
+	dt_coh_set = ret != -FDT_ERR_NOTFOUND;
+	ret = 0;
+
+	/* need to remove "dma-coherent" property */
+	if (dt_coh_set && !coherent)
+		ret = fdt_delprop(fdt, node, "dma-coherent");
+
+	/* need to set "dma-coherent" property */
+	if (!dt_coh_set && coherent)
+		ret = fdt_setprop(fdt, node, "dma-coherent", NULL, 0);
+
+	if (ret < 0)
+		goto tweak_fail;
+
+	return 0;
+
+tweak_fail:
+	pr_err("failed to tweak %s to %scoherent\n", path, coherent ? "" : "non");
+	return -EFAULT;
+}
+
+enum hsdk_axi_masters {
+	M_HS_CORE = 0,
+	M_HS_RTT,
+	M_AXI_TUN,
+	M_HDMI_VIDEO,
+	M_HDMI_AUDIO,
+	M_USB_HOST,
+	M_ETHERNET,
+	M_SDIO,
+	M_GPU,
+	M_DMAC_0,
+	M_DMAC_1,
+	M_DVFS
+};
+
+#define UPDATE_VAL	1
+
+/*
+ * This is modified configuration of AXI bridge. Default settings
+ * are specified in "Table 111 CREG Address Decoder register reset values".
+ *
+ * AXI_M_m_SLV{0|1} - Slave Select register for master 'm'.
+ * Possible slaves are:
+ *  - 0  => no slave selected
+ *  - 1  => DDR controller port #1
+ *  - 2  => SRAM controller
+ *  - 3  => AXI tunnel
+ *  - 4  => EBI controller
+ *  - 5  => ROM controller
+ *  - 6  => AXI2APB bridge
+ *  - 7  => DDR controller port #2
+ *  - 8  => DDR controller port #3
+ *  - 9  => HS38x4 IOC
+ *  - 10 => HS38x4 DMI
+ * AXI_M_m_OFFSET{0|1} - Addr Offset register for master 'm'
+ *
+ * Please read ARC HS Development IC Specification, section 17.2 for more
+ * information about apertures configuration.
+ *
+ * m	master		AXI_M_m_SLV0	AXI_M_m_SLV1	AXI_M_m_OFFSET0	AXI_M_m_OFFSET1
+ * 0	HS (CBU)	0x11111111	0x63111111	0xFEDCBA98	0x0E543210
+ * 1	HS (RTT)	0x77777777	0x77777777	0xFEDCBA98	0x76543210
+ * 2	AXI Tunnel	0x88888888	0x88888888	0xFEDCBA98	0x76543210
+ * 3	HDMI-VIDEO	0x77777777	0x77777777	0xFEDCBA98	0x76543210
+ * 4	HDMI-ADUIO	0x77777777	0x77777777	0xFEDCBA98	0x76543210
+ * 5	USB-HOST	0x77777777	0x77999999	0xFEDCBA98	0x76DCBA98
+ * 6	ETHERNET	0x77777777	0x77999999	0xFEDCBA98	0x76DCBA98
+ * 7	SDIO		0x77777777	0x77999999	0xFEDCBA98	0x76DCBA98
+ * 8	GPU		0x77777777	0x77777777	0xFEDCBA98	0x76543210
+ * 9	DMAC (port #1)	0x77777777	0x77777777	0xFEDCBA98	0x76543210
+ * 10	DMAC (port #2)	0x77777777	0x77777777	0xFEDCBA98	0x76543210
+ * 11	DVFS		0x00000000	0x60000000	0x00000000	0x00000000
+ */
+
+#define CREG_AXI_M_SLV0(m)  ((void __iomem *)(CREG_BASE + 0x20 * (m)))
+#define CREG_AXI_M_SLV1(m)  ((void __iomem *)(CREG_BASE + 0x20 * (m) + 0x04))
+#define CREG_AXI_M_OFT0(m)  ((void __iomem *)(CREG_BASE + 0x20 * (m) + 0x08))
+#define CREG_AXI_M_OFT1(m)  ((void __iomem *)(CREG_BASE + 0x20 * (m) + 0x0C))
+#define CREG_AXI_M_UPDT(m)  ((void __iomem *)(CREG_BASE + 0x20 * (m) + 0x14))
+
+#define CREG_AXI_M_HS_CORE_BOOT	((void __iomem *)(CREG_BASE + 0x010))
+
+#define CREG_PAE		((void __iomem *)(CREG_BASE + 0x180))
+#define CREG_PAE_UPDT		((void __iomem *)(CREG_BASE + 0x194))
+
+static void __init hsdk_init_memory_bridge_axi_dmac(void)
+{
+	bool coherent = !!arc_hsdk_axi_dmac_coherent;
+	u32 axi_m_slv1, axi_m_oft1;
+
+	/*
+	 * Don't tweak memory bridge configuration if we failed to tweak DTB
+	 * as we will end up in a inconsistent state.
+	 */
+	if (hsdk_tweak_node_coherency("/soc/dmac@80000", coherent))
+		return;
+
+	if (coherent) {
+		axi_m_slv1 = 0x77999999;
+		axi_m_oft1 = 0x76DCBA98;
+	} else {
+		axi_m_slv1 = 0x77777777;
+		axi_m_oft1 = 0x76543210;
+	}
+
+	writel(0x77777777, CREG_AXI_M_SLV0(M_DMAC_0));
+	writel(0xFEDCBA98, CREG_AXI_M_OFT0(M_DMAC_0));
+	writel(axi_m_slv1, CREG_AXI_M_SLV1(M_DMAC_0));
+	writel(axi_m_oft1, CREG_AXI_M_OFT1(M_DMAC_0));
+	writel(UPDATE_VAL, CREG_AXI_M_UPDT(M_DMAC_0));
+
+	writel(0x77777777, CREG_AXI_M_SLV0(M_DMAC_1));
+	writel(0xFEDCBA98, CREG_AXI_M_OFT0(M_DMAC_1));
+	writel(axi_m_slv1, CREG_AXI_M_SLV1(M_DMAC_1));
+	writel(axi_m_oft1, CREG_AXI_M_OFT1(M_DMAC_1));
+	writel(UPDATE_VAL, CREG_AXI_M_UPDT(M_DMAC_1));
+}
+
+static void __init hsdk_init_memory_bridge(void)
+{
+	u32 reg;
+
+	/*
+	 * M_HS_CORE has one unique register - BOOT.
+	 * We need to clean boot mirror (BOOT[1:0]) bits in them to avoid first
+	 * aperture to be masked by 'boot mirror'.
+	 */
+	reg = readl(CREG_AXI_M_HS_CORE_BOOT) & (~0x3);
+	writel(reg, CREG_AXI_M_HS_CORE_BOOT);
+	writel(0x11111111, CREG_AXI_M_SLV0(M_HS_CORE));
+	writel(0x63111111, CREG_AXI_M_SLV1(M_HS_CORE));
+	writel(0xFEDCBA98, CREG_AXI_M_OFT0(M_HS_CORE));
+	writel(0x0E543210, CREG_AXI_M_OFT1(M_HS_CORE));
+	writel(UPDATE_VAL, CREG_AXI_M_UPDT(M_HS_CORE));
+
+	writel(0x77777777, CREG_AXI_M_SLV0(M_HS_RTT));
+	writel(0x77777777, CREG_AXI_M_SLV1(M_HS_RTT));
+	writel(0xFEDCBA98, CREG_AXI_M_OFT0(M_HS_RTT));
+	writel(0x76543210, CREG_AXI_M_OFT1(M_HS_RTT));
+	writel(UPDATE_VAL, CREG_AXI_M_UPDT(M_HS_RTT));
+
+	writel(0x88888888, CREG_AXI_M_SLV0(M_AXI_TUN));
+	writel(0x88888888, CREG_AXI_M_SLV1(M_AXI_TUN));
+	writel(0xFEDCBA98, CREG_AXI_M_OFT0(M_AXI_TUN));
+	writel(0x76543210, CREG_AXI_M_OFT1(M_AXI_TUN));
+	writel(UPDATE_VAL, CREG_AXI_M_UPDT(M_AXI_TUN));
+
+	writel(0x77777777, CREG_AXI_M_SLV0(M_HDMI_VIDEO));
+	writel(0x77777777, CREG_AXI_M_SLV1(M_HDMI_VIDEO));
+	writel(0xFEDCBA98, CREG_AXI_M_OFT0(M_HDMI_VIDEO));
+	writel(0x76543210, CREG_AXI_M_OFT1(M_HDMI_VIDEO));
+	writel(UPDATE_VAL, CREG_AXI_M_UPDT(M_HDMI_VIDEO));
+
+	writel(0x77777777, CREG_AXI_M_SLV0(M_HDMI_AUDIO));
+	writel(0x77777777, CREG_AXI_M_SLV1(M_HDMI_AUDIO));
+	writel(0xFEDCBA98, CREG_AXI_M_OFT0(M_HDMI_AUDIO));
+	writel(0x76543210, CREG_AXI_M_OFT1(M_HDMI_AUDIO));
+	writel(UPDATE_VAL, CREG_AXI_M_UPDT(M_HDMI_AUDIO));
+
+	writel(0x77777777, CREG_AXI_M_SLV0(M_USB_HOST));
+	writel(0x77999999, CREG_AXI_M_SLV1(M_USB_HOST));
+	writel(0xFEDCBA98, CREG_AXI_M_OFT0(M_USB_HOST));
+	writel(0x76DCBA98, CREG_AXI_M_OFT1(M_USB_HOST));
+	writel(UPDATE_VAL, CREG_AXI_M_UPDT(M_USB_HOST));
+
+	writel(0x77777777, CREG_AXI_M_SLV0(M_ETHERNET));
+	writel(0x77999999, CREG_AXI_M_SLV1(M_ETHERNET));
+	writel(0xFEDCBA98, CREG_AXI_M_OFT0(M_ETHERNET));
+	writel(0x76DCBA98, CREG_AXI_M_OFT1(M_ETHERNET));
+	writel(UPDATE_VAL, CREG_AXI_M_UPDT(M_ETHERNET));
+
+	writel(0x77777777, CREG_AXI_M_SLV0(M_SDIO));
+	writel(0x77999999, CREG_AXI_M_SLV1(M_SDIO));
+	writel(0xFEDCBA98, CREG_AXI_M_OFT0(M_SDIO));
+	writel(0x76DCBA98, CREG_AXI_M_OFT1(M_SDIO));
+	writel(UPDATE_VAL, CREG_AXI_M_UPDT(M_SDIO));
+
+	writel(0x77777777, CREG_AXI_M_SLV0(M_GPU));
+	writel(0x77777777, CREG_AXI_M_SLV1(M_GPU));
+	writel(0xFEDCBA98, CREG_AXI_M_OFT0(M_GPU));
+	writel(0x76543210, CREG_AXI_M_OFT1(M_GPU));
+	writel(UPDATE_VAL, CREG_AXI_M_UPDT(M_GPU));
+
+	writel(0x00000000, CREG_AXI_M_SLV0(M_DVFS));
+	writel(0x60000000, CREG_AXI_M_SLV1(M_DVFS));
+	writel(0x00000000, CREG_AXI_M_OFT0(M_DVFS));
+	writel(0x00000000, CREG_AXI_M_OFT1(M_DVFS));
+	writel(UPDATE_VAL, CREG_AXI_M_UPDT(M_DVFS));
+
+	hsdk_init_memory_bridge_axi_dmac();
+
+	/*
+	 * PAE remapping for DMA clients does not work due to an RTL bug, so
+	 * CREG_PAE register must be programmed to all zeroes, otherwise it
+	 * will cause problems with DMA to/from peripherals even if PAE40 is
+	 * not used.
+	 */
+	writel(0x00000000, CREG_PAE);
+	writel(UPDATE_VAL, CREG_PAE_UPDT);
+}
+
+static void __init hsdk_init_early(void)
+{
+	hsdk_init_memory_bridge();
+
+	/*
+	 * Switch SDIO external ciu clock divider from default div-by-8 to
+	 * minimum possible div-by-2.
+	 */
+	iowrite32(SDIO_UHS_REG_EXT_DIV_2, (void __iomem *) SDIO_UHS_REG_EXT);
+
+	hsdk_enable_gpio_intc_wire();
+}
+
+static const char *hsdk_compat[] __initconst = {
+	"snps,hsdk",
+	NULL,
+};
+
+MACHINE_START(SIMULATION, "hsdk")
+	.dt_compat	= hsdk_compat,
+	.init_early     = hsdk_init_early,
+MACHINE_END
diff --git a/arch/arc/plat-sim/Makefile b/arch/arc/plat-sim/Makefile
new file mode 100644
index 000000000..ea9389bf8
--- /dev/null
+++ b/arch/arc/plat-sim/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Copyright (C) 2011-2012 Synopsys, Inc. (www.synopsys.com)
+#
+
+obj-y := platform.o
diff --git a/arch/arc/plat-sim/platform.c b/arch/arc/plat-sim/platform.c
new file mode 100644
index 000000000..2bde2a6e3
--- /dev/null
+++ b/arch/arc/plat-sim/platform.c
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * ARC simulation Platform support code
+ *
+ * Copyright (C) 2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#include <linux/init.h>
+#include <asm/mach_desc.h>
+
+/*----------------------- 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 *simulation_compat[] __initconst = {
+#ifdef CONFIG_ISA_ARCOMPACT
+	"snps,nsim",
+	"snps,nsimosci",
+#else
+	"snps,nsimosci_hs",
+	"snps,zebu_hs",
+#endif
+	NULL,
+};
+
+MACHINE_START(SIMULATION, "simulation")
+	.dt_compat	= simulation_compat,
+MACHINE_END
diff --git a/arch/arc/plat-tb10x/Kconfig b/arch/arc/plat-tb10x/Kconfig
new file mode 100644
index 000000000..158d53aad
--- /dev/null
+++ b/arch/arc/plat-tb10x/Kconfig
@@ -0,0 +1,20 @@
+# SPDX-License-Identifier: GPL-2.0-only
+# Abilis Systems TB10x platform kernel configuration file
+#
+# Author: Christian Ruppert <christian.ruppert@abilis.com>
+#
+
+
+menuconfig ARC_PLAT_TB10X
+	bool "Abilis TB10x"
+	select PINCTRL
+	select PINCTRL_TB10X
+	select PINMUX
+	select GPIOLIB
+	select GPIO_TB10X
+	select TB10X_IRQC
+	help
+	  Support for platforms based on the TB10x home media gateway SOC by
+	  Abilis Systems. TB10x is based on the ARC700 CPU architecture.
+	  Say Y if you are building a kernel for one of the SOCs in this
+	  series (e.g. TB100 or TB101). If in doubt say N.
diff --git a/arch/arc/plat-tb10x/Makefile b/arch/arc/plat-tb10x/Makefile
new file mode 100644
index 000000000..8e97d454e
--- /dev/null
+++ b/arch/arc/plat-tb10x/Makefile
@@ -0,0 +1,10 @@
+# SPDX-License-Identifier: GPL-2.0-only
+# Abilis Systems TB10x platform Makefile
+#
+# Author: Christian Ruppert <christian.ruppert@abilis.com>
+#
+
+
+KBUILD_CFLAGS   += -Iarch/arc/plat-tb10x/include
+
+obj-y += tb10x.o
diff --git a/arch/arc/plat-tb10x/tb10x.c b/arch/arc/plat-tb10x/tb10x.c
new file mode 100644
index 000000000..11d23420f
--- /dev/null
+++ b/arch/arc/plat-tb10x/tb10x.c
@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Abilis Systems TB10x platform initialisation
+ *
+ * Copyright (C) Abilis Systems 2012
+ *
+ * Author: Christian Ruppert <christian.ruppert@abilis.com>
+ */
+
+#include <linux/init.h>
+#include <asm/mach_desc.h>
+
+static const char *tb10x_compat[] __initdata = {
+	"abilis,arc-tb10x",
+	NULL,
+};
+
+MACHINE_START(TB10x, "tb10x")
+	.dt_compat	= tb10x_compat,
+MACHINE_END