Adding upstream version 6.1.76.upstream/6.1.76upstream

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

312 files changed, 42679 insertions, 0 deletions

diff --git a/arch/riscv/Kbuild b/arch/riscv/Kbuild
new file mode 100644
index 000000000..afa83e307
--- /dev/null
+++ b/arch/riscv/Kbuild
@@ -0,0 +1,11 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+obj-y += kernel/ mm/ net/
+obj-$(CONFIG_BUILTIN_DTB) += boot/dts/
+obj-y += errata/
+obj-$(CONFIG_KVM) += kvm/
+
+obj-$(CONFIG_ARCH_HAS_KEXEC_PURGATORY) += purgatory/
+
+# for cleaning
+subdir- += boot
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
new file mode 100644
index 000000000..d702359f8
--- /dev/null
+++ b/arch/riscv/Kconfig
@@ -0,0 +1,726 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# For a description of the syntax of this configuration file,
+# see Documentation/kbuild/kconfig-language.rst.
+#
+
+config 64BIT
+	bool
+
+config 32BIT
+	bool
+
+config RISCV
+	def_bool y
+	select ARCH_CLOCKSOURCE_INIT
+	select ARCH_ENABLE_HUGEPAGE_MIGRATION if HUGETLB_PAGE && MIGRATION
+	select ARCH_ENABLE_SPLIT_PMD_PTLOCK if PGTABLE_LEVELS > 2
+	select ARCH_HAS_BINFMT_FLAT
+	select ARCH_HAS_CURRENT_STACK_POINTER
+	select ARCH_HAS_DEBUG_VM_PGTABLE
+	select ARCH_HAS_DEBUG_VIRTUAL if MMU
+	select ARCH_HAS_DEBUG_WX
+	select ARCH_HAS_FORTIFY_SOURCE
+	select ARCH_HAS_GCOV_PROFILE_ALL
+	select ARCH_HAS_GIGANTIC_PAGE
+	select ARCH_HAS_KCOV
+	select ARCH_HAS_MMIOWB
+	select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
+	select ARCH_HAS_PTE_SPECIAL
+	select ARCH_HAS_SET_DIRECT_MAP if MMU
+	select ARCH_HAS_SET_MEMORY if MMU
+	select ARCH_HAS_STRICT_KERNEL_RWX if MMU && !XIP_KERNEL
+	select ARCH_HAS_STRICT_MODULE_RWX if MMU && !XIP_KERNEL
+	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
+	select ARCH_HAS_UBSAN_SANITIZE_ALL
+	select ARCH_OPTIONAL_KERNEL_RWX if ARCH_HAS_STRICT_KERNEL_RWX
+	select ARCH_OPTIONAL_KERNEL_RWX_DEFAULT
+	select ARCH_STACKWALK
+	select ARCH_SUPPORTS_ATOMIC_RMW
+	select ARCH_SUPPORTS_DEBUG_PAGEALLOC if MMU
+	select ARCH_SUPPORTS_HUGETLBFS if MMU
+	select ARCH_SUPPORTS_PAGE_TABLE_CHECK if MMU
+	select ARCH_USE_MEMTEST
+	select ARCH_USE_QUEUED_RWLOCKS
+	select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU
+	select ARCH_WANT_FRAME_POINTERS
+	select ARCH_WANT_GENERAL_HUGETLB
+	select ARCH_WANT_HUGE_PMD_SHARE if 64BIT
+	select ARCH_WANTS_THP_SWAP if HAVE_ARCH_TRANSPARENT_HUGEPAGE
+	select BINFMT_FLAT_NO_DATA_START_OFFSET if !MMU
+	select BUILDTIME_TABLE_SORT if MMU
+	select CLONE_BACKWARDS
+	select CLINT_TIMER if !MMU
+	select COMMON_CLK
+	select CPU_PM if CPU_IDLE
+	select EDAC_SUPPORT
+	select GENERIC_ARCH_TOPOLOGY
+	select GENERIC_ATOMIC64 if !64BIT
+	select GENERIC_CLOCKEVENTS_BROADCAST if SMP
+	select GENERIC_EARLY_IOREMAP
+	select GENERIC_GETTIMEOFDAY if HAVE_GENERIC_VDSO
+	select GENERIC_IDLE_POLL_SETUP
+	select GENERIC_IOREMAP if MMU
+	select GENERIC_IRQ_MULTI_HANDLER
+	select GENERIC_IRQ_SHOW
+	select GENERIC_IRQ_SHOW_LEVEL
+	select GENERIC_LIB_DEVMEM_IS_ALLOWED
+	select GENERIC_PCI_IOMAP
+	select GENERIC_PTDUMP if MMU
+	select GENERIC_SCHED_CLOCK
+	select GENERIC_SMP_IDLE_THREAD
+	select GENERIC_TIME_VSYSCALL if MMU && 64BIT
+	select GENERIC_VDSO_TIME_NS if HAVE_GENERIC_VDSO
+	select HARDIRQS_SW_RESEND
+	select HAVE_ARCH_AUDITSYSCALL
+	select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL
+	select HAVE_ARCH_JUMP_LABEL_RELATIVE if !XIP_KERNEL
+	select HAVE_ARCH_KASAN if MMU && 64BIT
+	select HAVE_ARCH_KASAN_VMALLOC if MMU && 64BIT
+	select HAVE_ARCH_KFENCE if MMU && 64BIT
+	select HAVE_ARCH_KGDB if !XIP_KERNEL
+	select HAVE_ARCH_KGDB_QXFER_PKT
+	select HAVE_ARCH_MMAP_RND_BITS if MMU
+	select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT
+	select HAVE_ARCH_SECCOMP_FILTER
+	select HAVE_ARCH_TRACEHOOK
+	select HAVE_ARCH_TRANSPARENT_HUGEPAGE if 64BIT && MMU
+	select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE
+	select HAVE_ARCH_THREAD_STRUCT_WHITELIST
+	select HAVE_ARCH_VMAP_STACK if MMU && 64BIT
+	select HAVE_ASM_MODVERSIONS
+	select HAVE_CONTEXT_TRACKING_USER
+	select HAVE_DEBUG_KMEMLEAK
+	select HAVE_DMA_CONTIGUOUS if MMU
+	select HAVE_EBPF_JIT if MMU
+	select HAVE_FUNCTION_ERROR_INJECTION
+	select HAVE_GCC_PLUGINS
+	select HAVE_GENERIC_VDSO if MMU && 64BIT
+	select HAVE_IRQ_TIME_ACCOUNTING
+	select HAVE_KPROBES if !XIP_KERNEL
+	select HAVE_KPROBES_ON_FTRACE if !XIP_KERNEL
+	select HAVE_KRETPROBES if !XIP_KERNEL
+	select HAVE_MOVE_PMD
+	select HAVE_MOVE_PUD
+	select HAVE_PCI
+	select HAVE_PERF_EVENTS
+	select HAVE_PERF_REGS
+	select HAVE_PERF_USER_STACK_DUMP
+	select HAVE_POSIX_CPU_TIMERS_TASK_WORK
+	select HAVE_REGS_AND_STACK_ACCESS_API
+	select HAVE_FUNCTION_ARG_ACCESS_API
+	select HAVE_STACKPROTECTOR
+	select HAVE_SYSCALL_TRACEPOINTS
+	select HAVE_RSEQ
+	select IRQ_DOMAIN
+	select IRQ_FORCED_THREADING
+	select LOCK_MM_AND_FIND_VMA
+	select MODULES_USE_ELF_RELA if MODULES
+	select MODULE_SECTIONS if MODULES
+	select OF
+	select OF_DMA_DEFAULT_COHERENT
+	select OF_EARLY_FLATTREE
+	select OF_IRQ
+	select PCI_DOMAINS_GENERIC if PCI
+	select PCI_MSI if PCI
+	select RISCV_INTC
+	select RISCV_TIMER if RISCV_SBI
+	select SPARSE_IRQ
+	select SYSCTL_EXCEPTION_TRACE
+	select THREAD_INFO_IN_TASK
+	select TRACE_IRQFLAGS_SUPPORT
+	select UACCESS_MEMCPY if !MMU
+	select ZONE_DMA32 if 64BIT
+
+config ARCH_MMAP_RND_BITS_MIN
+	default 18 if 64BIT
+	default 8
+
+config ARCH_MMAP_RND_COMPAT_BITS_MIN
+	default 8
+
+# max bits determined by the following formula:
+#  VA_BITS - PAGE_SHIFT - 3
+config ARCH_MMAP_RND_BITS_MAX
+	default 24 if 64BIT # SV39 based
+	default 17
+
+config ARCH_MMAP_RND_COMPAT_BITS_MAX
+	default 17
+
+# set if we run in machine mode, cleared if we run in supervisor mode
+config RISCV_M_MODE
+	bool
+	default !MMU
+
+# set if we are running in S-mode and can use SBI calls
+config RISCV_SBI
+	bool
+	depends on !RISCV_M_MODE
+	default y
+
+config MMU
+	bool "MMU-based Paged Memory Management Support"
+	default y
+	help
+	  Select if you want MMU-based virtualised addressing space
+	  support by paged memory management. If unsure, say 'Y'.
+
+config PAGE_OFFSET
+	hex
+	default 0xC0000000 if 32BIT
+	default 0x80000000 if 64BIT && !MMU
+	default 0xff60000000000000 if 64BIT
+
+config KASAN_SHADOW_OFFSET
+	hex
+	depends on KASAN_GENERIC
+	default 0xdfffffff00000000 if 64BIT
+	default 0xffffffff if 32BIT
+
+config ARCH_FLATMEM_ENABLE
+	def_bool !NUMA
+
+config ARCH_SPARSEMEM_ENABLE
+	def_bool y
+	depends on MMU
+	select SPARSEMEM_STATIC if 32BIT && SPARSEMEM
+	select SPARSEMEM_VMEMMAP_ENABLE if 64BIT
+
+config ARCH_SELECT_MEMORY_MODEL
+	def_bool ARCH_SPARSEMEM_ENABLE
+
+config ARCH_SUPPORTS_UPROBES
+	def_bool y
+
+config STACKTRACE_SUPPORT
+	def_bool y
+
+config GENERIC_BUG
+	def_bool y
+	depends on BUG
+	select GENERIC_BUG_RELATIVE_POINTERS if 64BIT
+
+config GENERIC_BUG_RELATIVE_POINTERS
+	bool
+
+config GENERIC_CALIBRATE_DELAY
+	def_bool y
+
+config GENERIC_CSUM
+	def_bool y
+
+config GENERIC_HWEIGHT
+	def_bool y
+
+config FIX_EARLYCON_MEM
+	def_bool MMU
+
+config PGTABLE_LEVELS
+	int
+	default 5 if 64BIT
+	default 2
+
+config LOCKDEP_SUPPORT
+	def_bool y
+
+config RISCV_DMA_NONCOHERENT
+	bool
+	select ARCH_HAS_DMA_PREP_COHERENT
+	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
+	select ARCH_HAS_SYNC_DMA_FOR_CPU
+	select ARCH_HAS_SETUP_DMA_OPS
+	select DMA_DIRECT_REMAP
+
+config AS_HAS_INSN
+	def_bool $(as-instr,.insn r 51$(comma) 0$(comma) 0$(comma) t0$(comma) t0$(comma) zero)
+
+source "arch/riscv/Kconfig.socs"
+source "arch/riscv/Kconfig.erratas"
+
+menu "Platform type"
+
+config NONPORTABLE
+	bool "Allow configurations that result in non-portable kernels"
+	help
+	  RISC-V kernel binaries are compatible between all known systems
+	  whenever possible, but there are some use cases that can only be
+	  satisfied by configurations that result in kernel binaries that are
+	  not portable between systems.
+
+	  Selecting N does not guarantee kernels will be portable to all known
+	  systems.  Selecting any of the options guarded by NONPORTABLE will
+	  result in kernel binaries that are unlikely to be portable between
+	  systems.
+
+	  If unsure, say N.
+
+choice
+	prompt "Base ISA"
+	default ARCH_RV64I
+	help
+	  This selects the base ISA that this kernel will target and must match
+	  the target platform.
+
+config ARCH_RV32I
+	bool "RV32I"
+	depends on NONPORTABLE
+	select 32BIT
+	select GENERIC_LIB_ASHLDI3
+	select GENERIC_LIB_ASHRDI3
+	select GENERIC_LIB_LSHRDI3
+	select GENERIC_LIB_UCMPDI2
+	select MMU
+
+config ARCH_RV64I
+	bool "RV64I"
+	select 64BIT
+	select ARCH_SUPPORTS_INT128 if CC_HAS_INT128
+	select HAVE_DYNAMIC_FTRACE if !XIP_KERNEL && MMU && $(cc-option,-fpatchable-function-entry=8)
+	select HAVE_DYNAMIC_FTRACE_WITH_REGS if HAVE_DYNAMIC_FTRACE
+	select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL
+	select HAVE_FUNCTION_GRAPH_TRACER
+	select HAVE_FUNCTION_TRACER if !XIP_KERNEL && !PREEMPTION
+	select SWIOTLB if MMU
+
+endchoice
+
+# We must be able to map all physical memory into the kernel, but the compiler
+# is still a bit more efficient when generating code if it's setup in a manner
+# such that it can only map 2GiB of memory.
+choice
+	prompt "Kernel Code Model"
+	default CMODEL_MEDLOW if 32BIT
+	default CMODEL_MEDANY if 64BIT
+
+	config CMODEL_MEDLOW
+		bool "medium low code model"
+	config CMODEL_MEDANY
+		bool "medium any code model"
+endchoice
+
+config MODULE_SECTIONS
+	bool
+	select HAVE_MOD_ARCH_SPECIFIC
+
+config SMP
+	bool "Symmetric Multi-Processing"
+	help
+	  This enables support for systems with more than one CPU.  If
+	  you say N here, the kernel will run on single and
+	  multiprocessor machines, but will use only one CPU of a
+	  multiprocessor machine. If you say Y here, the kernel will run
+	  on many, but not all, single processor machines. On a single
+	  processor machine, the kernel will run faster if you say N
+	  here.
+
+	  If you don't know what to do here, say N.
+
+config NR_CPUS
+	int "Maximum number of CPUs (2-512)"
+	depends on SMP
+	range 2 512 if !RISCV_SBI_V01
+	range 2 32 if RISCV_SBI_V01 && 32BIT
+	range 2 64 if RISCV_SBI_V01 && 64BIT
+	default "32" if 32BIT
+	default "64" if 64BIT
+
+config HOTPLUG_CPU
+	bool "Support for hot-pluggable CPUs"
+	depends on SMP
+	select GENERIC_IRQ_MIGRATION
+	help
+
+	  Say Y here to experiment with turning CPUs off and on.  CPUs
+	  can be controlled through /sys/devices/system/cpu.
+
+	  Say N if you want to disable CPU hotplug.
+
+choice
+	prompt "CPU Tuning"
+	default TUNE_GENERIC
+
+config TUNE_GENERIC
+	bool "generic"
+
+endchoice
+
+# Common NUMA Features
+config NUMA
+	bool "NUMA Memory Allocation and Scheduler Support"
+	depends on SMP && MMU
+	select GENERIC_ARCH_NUMA
+	select OF_NUMA
+	select ARCH_SUPPORTS_NUMA_BALANCING
+	select USE_PERCPU_NUMA_NODE_ID
+	select NEED_PER_CPU_EMBED_FIRST_CHUNK
+	help
+	  Enable NUMA (Non-Uniform Memory Access) support.
+
+	  The kernel will try to allocate memory used by a CPU on the
+	  local memory of the CPU and add some more NUMA awareness to the kernel.
+
+config NODES_SHIFT
+	int "Maximum NUMA Nodes (as a power of 2)"
+	range 1 10
+	default "2"
+	depends on NUMA
+	help
+	  Specify the maximum number of NUMA Nodes available on the target
+	  system.  Increases memory reserved to accommodate various tables.
+
+config RISCV_ALTERNATIVE
+	bool
+	depends on !XIP_KERNEL
+	help
+	  This Kconfig allows the kernel to automatically patch the
+	  errata required by the execution platform at run time. The
+	  code patching is performed once in the boot stages. It means
+	  that the overhead from this mechanism is just taken once.
+
+config RISCV_ALTERNATIVE_EARLY
+	bool
+	depends on RISCV_ALTERNATIVE
+	help
+	  Allows early patching of the kernel for special errata
+
+config RISCV_ISA_C
+	bool "Emit compressed instructions when building Linux"
+	default y
+	help
+	  Adds "C" to the ISA subsets that the toolchain is allowed to emit
+	  when building Linux, which results in compressed instructions in the
+	  Linux binary.
+
+	  If you don't know what to do here, say Y.
+
+config RISCV_ISA_SVPBMT
+	bool "SVPBMT extension support"
+	depends on 64BIT && MMU
+	depends on !XIP_KERNEL
+	select RISCV_ALTERNATIVE
+	default y
+	help
+	   Adds support to dynamically detect the presence of the SVPBMT
+	   ISA-extension (Supervisor-mode: page-based memory types) and
+	   enable its usage.
+
+	   The memory type for a page contains a combination of attributes
+	   that indicate the cacheability, idempotency, and ordering
+	   properties for access to that page.
+
+	   The SVPBMT extension is only available on 64Bit cpus.
+
+	   If you don't know what to do here, say Y.
+
+config TOOLCHAIN_HAS_ZICBOM
+	bool
+	default y
+	depends on !64BIT || $(cc-option,-mabi=lp64 -march=rv64ima_zicbom)
+	depends on !32BIT || $(cc-option,-mabi=ilp32 -march=rv32ima_zicbom)
+	depends on LLD_VERSION >= 150000 || LD_VERSION >= 23800
+
+config RISCV_ISA_ZICBOM
+	bool "Zicbom extension support for non-coherent DMA operation"
+	depends on TOOLCHAIN_HAS_ZICBOM
+	depends on !XIP_KERNEL && MMU
+	select RISCV_DMA_NONCOHERENT
+	select RISCV_ALTERNATIVE
+	default y
+	help
+	   Adds support to dynamically detect the presence of the ZICBOM
+	   extension (Cache Block Management Operations) and enable its
+	   usage.
+
+	   The Zicbom extension can be used to handle for example
+	   non-coherent DMA support on devices that need it.
+
+	   If you don't know what to do here, say Y.
+
+config TOOLCHAIN_HAS_ZIHINTPAUSE
+	bool
+	default y
+	depends on !64BIT || $(cc-option,-mabi=lp64 -march=rv64ima_zihintpause)
+	depends on !32BIT || $(cc-option,-mabi=ilp32 -march=rv32ima_zihintpause)
+	depends on LLD_VERSION >= 150000 || LD_VERSION >= 23600
+
+config TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI
+	def_bool y
+	# https://sourceware.org/git/?p=binutils-gdb.git;a=commit;h=aed44286efa8ae8717a77d94b51ac3614e2ca6dc
+	# https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=98416dbb0a62579d4a7a4a76bab51b5b52fec2cd
+	depends on AS_IS_GNU && AS_VERSION >= 23600
+	help
+	  Binutils-2.38 and GCC-12.1.0 bumped the default ISA spec to the newer
+	  20191213 version, which moves some instructions from the I extension to
+	  the Zicsr and Zifencei extensions. This requires explicitly specifying
+	  Zicsr and Zifencei when binutils >= 2.38 or GCC >= 12.1.0. Zicsr
+	  and Zifencei are supported in binutils from version 2.36 onwards.
+	  To make life easier, and avoid forcing toolchains that default to a
+	  newer ISA spec to version 2.2, relax the check to binutils >= 2.36.
+	  For clang < 17 or GCC < 11.3.0, for which this is not possible or need
+	  special treatment, this is dealt with in TOOLCHAIN_NEEDS_OLD_ISA_SPEC.
+
+config TOOLCHAIN_NEEDS_OLD_ISA_SPEC
+	def_bool y
+	depends on TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI
+	# https://github.com/llvm/llvm-project/commit/22e199e6afb1263c943c0c0d4498694e15bf8a16
+	# https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=d29f5d6ab513c52fd872f532c492e35ae9fd6671
+	depends on (CC_IS_CLANG && CLANG_VERSION < 170000) || (CC_IS_GCC && GCC_VERSION < 110300)
+	help
+	  Certain versions of clang and GCC do not support zicsr and zifencei via
+	  -march. This option causes an older ISA spec compatible with these older
+	  versions of clang and GCC to be passed to GAS, which has the same result
+	  as passing zicsr and zifencei to -march.
+
+config FPU
+	bool "FPU support"
+	default y
+	help
+	  Say N here if you want to disable all floating-point related procedure
+	  in the kernel.
+
+	  If you don't know what to do here, say Y.
+
+endmenu # "Platform type"
+
+menu "Kernel features"
+
+source "kernel/Kconfig.hz"
+
+config RISCV_SBI_V01
+	bool "SBI v0.1 support"
+	depends on RISCV_SBI
+	help
+	  This config allows kernel to use SBI v0.1 APIs. This will be
+	  deprecated in future once legacy M-mode software are no longer in use.
+
+config RISCV_BOOT_SPINWAIT
+	bool "Spinwait booting method"
+	depends on SMP
+	default y if RISCV_SBI_V01 || RISCV_M_MODE
+	help
+	  This enables support for booting Linux via spinwait method. In the
+	  spinwait method, all cores randomly jump to Linux. One of the cores
+	  gets chosen via lottery and all other keep spinning on a percpu
+	  variable. This method cannot support CPU hotplug and sparse hartid
+	  scheme. It should be only enabled for M-mode Linux or platforms relying
+	  on older firmware without SBI HSM extension. All other platforms should
+	  rely on ordered booting via SBI HSM extension which gets chosen
+	  dynamically at runtime if the firmware supports it.
+
+	  Since spinwait is incompatible with sparse hart IDs, it requires
+	  NR_CPUS be large enough to contain the physical hart ID of the first
+	  hart to enter Linux.
+
+	  If unsure what to do here, say N.
+
+config KEXEC
+	bool "Kexec system call"
+	select KEXEC_CORE
+	select HOTPLUG_CPU if SMP
+	depends on MMU
+	help
+	  kexec is a system call that implements the ability to shutdown your
+	  current kernel, and to start another kernel. It is like a reboot
+	  but it is independent of the system firmware. And like a reboot
+	  you can start any kernel with it, not just Linux.
+
+	  The name comes from the similarity to the exec system call.
+
+config KEXEC_FILE
+	bool "kexec file based systmem call"
+	select KEXEC_CORE
+	select KEXEC_ELF
+	select HAVE_IMA_KEXEC if IMA
+	depends on 64BIT && MMU
+	help
+	  This is new version of kexec system call. This system call is
+	  file based and takes file descriptors as system call argument
+	  for kernel and initramfs as opposed to list of segments as
+	  accepted by previous system call.
+
+	  If you don't know what to do here, say Y.
+
+config ARCH_HAS_KEXEC_PURGATORY
+	def_bool KEXEC_FILE
+	depends on CRYPTO=y
+	depends on CRYPTO_SHA256=y
+
+config CRASH_DUMP
+	bool "Build kdump crash kernel"
+	help
+	  Generate crash dump after being started by kexec. This should
+	  be normally only set in special crash dump kernels which are
+	  loaded in the main kernel with kexec-tools into a specially
+	  reserved region and then later executed after a crash by
+	  kdump/kexec.
+
+	  For more details see Documentation/admin-guide/kdump/kdump.rst
+
+config COMPAT
+	bool "Kernel support for 32-bit U-mode"
+	default 64BIT
+	depends on 64BIT && MMU
+	help
+	  This option enables support for a 32-bit U-mode running under a 64-bit
+	  kernel at S-mode. riscv32-specific components such as system calls,
+	  the user helper functions (vdso), signal rt_frame functions and the
+	  ptrace interface are handled appropriately by the kernel.
+
+	  If you want to execute 32-bit userspace applications, say Y.
+
+endmenu # "Kernel features"
+
+menu "Boot options"
+
+config CMDLINE
+	string "Built-in kernel command line"
+	help
+	  For most platforms, the arguments for the kernel's command line
+	  are provided at run-time, during boot. However, there are cases
+	  where either no arguments are being provided or the provided
+	  arguments are insufficient or even invalid.
+
+	  When that occurs, it is possible to define a built-in command
+	  line here and choose how the kernel should use it later on.
+
+choice
+	prompt "Built-in command line usage" if CMDLINE != ""
+	default CMDLINE_FALLBACK
+	help
+	  Choose how the kernel will handle the provided built-in command
+	  line.
+
+config CMDLINE_FALLBACK
+	bool "Use bootloader kernel arguments if available"
+	help
+	  Use the built-in command line as fallback in case we get nothing
+	  during boot. This is the default behaviour.
+
+config CMDLINE_EXTEND
+	bool "Extend bootloader kernel arguments"
+	help
+	  The command-line arguments provided during boot will be
+	  appended to the built-in command line. This is useful in
+	  cases where the provided arguments are insufficient and
+	  you don't want to or cannot modify them.
+
+config CMDLINE_FORCE
+	bool "Always use the default kernel command string"
+	help
+	  Always use the built-in command line, even if we get one during
+	  boot. This is useful in case you need to override the provided
+	  command line on systems where you don't have or want control
+	  over it.
+
+endchoice
+
+config EFI_STUB
+	bool
+
+config EFI
+	bool "UEFI runtime support"
+	depends on OF && !XIP_KERNEL
+	select LIBFDT
+	select UCS2_STRING
+	select EFI_PARAMS_FROM_FDT
+	select EFI_STUB
+	select EFI_GENERIC_STUB
+	select EFI_RUNTIME_WRAPPERS
+	select RISCV_ISA_C
+	depends on MMU
+	default y
+	help
+	  This option provides support for runtime services provided
+	  by UEFI firmware (such as non-volatile variables, realtime
+	  clock, and platform reset). A UEFI stub is also provided to
+	  allow the kernel to be booted as an EFI application. This
+	  is only useful on systems that have UEFI firmware.
+
+config CC_HAVE_STACKPROTECTOR_TLS
+	def_bool $(cc-option,-mstack-protector-guard=tls -mstack-protector-guard-reg=tp -mstack-protector-guard-offset=0)
+
+config STACKPROTECTOR_PER_TASK
+	def_bool y
+	depends on !RANDSTRUCT
+	depends on STACKPROTECTOR && CC_HAVE_STACKPROTECTOR_TLS
+
+config PHYS_RAM_BASE_FIXED
+	bool "Explicitly specified physical RAM address"
+	depends on NONPORTABLE
+	default n
+
+config PHYS_RAM_BASE
+	hex "Platform Physical RAM address"
+	depends on PHYS_RAM_BASE_FIXED
+	default "0x80000000"
+	help
+	  This is the physical address of RAM in the system. It has to be
+	  explicitly specified to run early relocations of read-write data
+	  from flash to RAM.
+
+config XIP_KERNEL
+	bool "Kernel Execute-In-Place from ROM"
+	depends on MMU && SPARSEMEM && NONPORTABLE
+	# This prevents XIP from being enabled by all{yes,mod}config, which
+	# fail to build since XIP doesn't support large kernels.
+	depends on !COMPILE_TEST
+	select PHYS_RAM_BASE_FIXED
+	help
+	  Execute-In-Place allows the kernel to run from non-volatile storage
+	  directly addressable by the CPU, such as NOR flash. This saves RAM
+	  space since the text section of the kernel is not loaded from flash
+	  to RAM.  Read-write sections, such as the data section and stack,
+	  are still copied to RAM.  The XIP kernel is not compressed since
+	  it has to run directly from flash, so it will take more space to
+	  store it.  The flash address used to link the kernel object files,
+	  and for storing it, is configuration dependent. Therefore, if you
+	  say Y here, you must know the proper physical address where to
+	  store the kernel image depending on your own flash memory usage.
+
+	  Also note that the make target becomes "make xipImage" rather than
+	  "make zImage" or "make Image".  The final kernel binary to put in
+	  ROM memory will be arch/riscv/boot/xipImage.
+
+	  SPARSEMEM is required because the kernel text and rodata that are
+	  flash resident are not backed by memmap, then any attempt to get
+	  a struct page on those regions will trigger a fault.
+
+	  If unsure, say N.
+
+config XIP_PHYS_ADDR
+	hex "XIP Kernel Physical Location"
+	depends on XIP_KERNEL
+	default "0x21000000"
+	help
+	  This is the physical address in your flash memory the kernel will
+	  be linked for and stored to.  This address is dependent on your
+	  own flash usage.
+
+endmenu # "Boot options"
+
+config BUILTIN_DTB
+	bool
+	depends on OF && NONPORTABLE
+	default y if XIP_KERNEL
+
+config PORTABLE
+	bool
+	default !NONPORTABLE
+	select EFI
+	select OF
+	select MMU
+
+menu "Power management options"
+
+source "kernel/power/Kconfig"
+
+endmenu # "Power management options"
+
+menu "CPU Power Management"
+
+source "drivers/cpuidle/Kconfig"
+
+endmenu # "CPU Power Management"
+
+source "arch/riscv/kvm/Kconfig"
diff --git a/arch/riscv/Kconfig.debug b/arch/riscv/Kconfig.debug
new file mode 100644
index 000000000..e69de29bb
--- /dev/null
+++ b/arch/riscv/Kconfig.debug
diff --git a/arch/riscv/Kconfig.erratas b/arch/riscv/Kconfig.erratas
new file mode 100644
index 000000000..f3623df23
--- /dev/null
+++ b/arch/riscv/Kconfig.erratas
@@ -0,0 +1,69 @@
+menu "CPU errata selection"
+
+config ERRATA_SIFIVE
+	bool "SiFive errata"
+	depends on !XIP_KERNEL
+	select RISCV_ALTERNATIVE
+	help
+	  All SiFive errata Kconfig depend on this Kconfig. Disabling
+	  this Kconfig will disable all SiFive errata. Please say "Y"
+	  here if your platform uses SiFive CPU cores.
+
+	  Otherwise, please say "N" here to avoid unnecessary overhead.
+
+config ERRATA_SIFIVE_CIP_453
+	bool "Apply SiFive errata CIP-453"
+	depends on ERRATA_SIFIVE && 64BIT
+	default y
+	help
+	  This will apply the SiFive CIP-453 errata to add sign extension
+	  to the $badaddr when exception type is instruction page fault
+	  and instruction access fault.
+
+	  If you don't know what to do here, say "Y".
+
+config ERRATA_SIFIVE_CIP_1200
+	bool "Apply SiFive errata CIP-1200"
+	depends on ERRATA_SIFIVE && 64BIT
+	default y
+	help
+	  This will apply the SiFive CIP-1200 errata to repalce all
+	  "sfence.vma addr" with "sfence.vma" to ensure that the addr
+	  has been flushed from TLB.
+
+	  If you don't know what to do here, say "Y".
+
+config ERRATA_THEAD
+	bool "T-HEAD errata"
+	depends on !XIP_KERNEL
+	select RISCV_ALTERNATIVE
+	help
+	  All T-HEAD errata Kconfig depend on this Kconfig. Disabling
+	  this Kconfig will disable all T-HEAD errata. Please say "Y"
+	  here if your platform uses T-HEAD CPU cores.
+
+	  Otherwise, please say "N" here to avoid unnecessary overhead.
+
+config ERRATA_THEAD_PBMT
+	bool "Apply T-Head memory type errata"
+	depends on ERRATA_THEAD && 64BIT && MMU
+	select RISCV_ALTERNATIVE_EARLY
+	default y
+	help
+	  This will apply the memory type errata to handle the non-standard
+	  memory type bits in page-table-entries on T-Head SoCs.
+
+	  If you don't know what to do here, say "Y".
+
+config ERRATA_THEAD_CMO
+	bool "Apply T-Head cache management errata"
+	depends on ERRATA_THEAD && MMU
+	select RISCV_DMA_NONCOHERENT
+	default y
+	help
+	  This will apply the cache management errata to handle the
+	  non-standard handling on non-coherent operations on T-Head SoCs.
+
+	  If you don't know what to do here, say "Y".
+
+endmenu # "CPU errata selection"
diff --git a/arch/riscv/Kconfig.socs b/arch/riscv/Kconfig.socs
new file mode 100644
index 000000000..29d78eefc
--- /dev/null
+++ b/arch/riscv/Kconfig.socs
@@ -0,0 +1,84 @@
+menu "SoC selection"
+
+config SOC_MICROCHIP_POLARFIRE
+	bool "Microchip PolarFire SoCs"
+	select MCHP_CLK_MPFS
+	select SIFIVE_PLIC
+	help
+	  This enables support for Microchip PolarFire SoC platforms.
+
+config SOC_SIFIVE
+	bool "SiFive SoCs"
+	select SERIAL_SIFIVE if TTY
+	select SERIAL_SIFIVE_CONSOLE if TTY
+	select CLK_SIFIVE
+	select CLK_SIFIVE_PRCI
+	select SIFIVE_PLIC
+	select ERRATA_SIFIVE if !XIP_KERNEL
+	help
+	  This enables support for SiFive SoC platform hardware.
+
+config SOC_STARFIVE
+	bool "StarFive SoCs"
+	select PINCTRL
+	select RESET_CONTROLLER
+	select SIFIVE_PLIC
+	select ARM_AMBA
+	help
+	  This enables support for StarFive SoC platform hardware.
+
+config SOC_VIRT
+	bool "QEMU Virt Machine"
+	select CLINT_TIMER if RISCV_M_MODE
+	select POWER_RESET
+	select POWER_RESET_SYSCON
+	select POWER_RESET_SYSCON_POWEROFF
+	select GOLDFISH
+	select RTC_DRV_GOLDFISH if RTC_CLASS
+	select SIFIVE_PLIC
+	select PM_GENERIC_DOMAINS if PM
+	select PM_GENERIC_DOMAINS_OF if PM && OF
+	select RISCV_SBI_CPUIDLE if CPU_IDLE && RISCV_SBI
+	help
+	  This enables support for QEMU Virt Machine.
+
+config SOC_CANAAN
+	bool "Canaan Kendryte K210 SoC"
+	depends on !MMU
+	select CLINT_TIMER if RISCV_M_MODE
+	select SERIAL_SIFIVE if TTY
+	select SERIAL_SIFIVE_CONSOLE if TTY
+	select SIFIVE_PLIC
+	select ARCH_HAS_RESET_CONTROLLER
+	select PINCTRL
+	select COMMON_CLK
+	select COMMON_CLK_K210
+	help
+	  This enables support for Canaan Kendryte K210 SoC platform hardware.
+
+if SOC_CANAAN
+
+config SOC_CANAAN_K210_DTB_BUILTIN
+	bool "Builtin device tree for the Canaan Kendryte K210"
+	depends on SOC_CANAAN
+	default y
+	select OF
+	select BUILTIN_DTB
+	help
+	  Build a device tree for the Kendryte K210 into the Linux image.
+	  This option should be selected if no bootloader is being used.
+	  If unsure, say Y.
+
+config SOC_CANAAN_K210_DTB_SOURCE
+	string "Source file for the Canaan Kendryte K210 builtin DTB"
+	depends on SOC_CANAAN
+	depends on SOC_CANAAN_K210_DTB_BUILTIN
+	default "k210_generic"
+	help
+	  Base name (without suffix, relative to arch/riscv/boot/dts/canaan)
+	  for the DTS file that will be used to produce the DTB linked into the
+	  kernel.
+
+endif # SOC_CANAAN
+
+endmenu # "SoC selection"
diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile
new file mode 100644
index 000000000..3cb876f83
--- /dev/null
+++ b/arch/riscv/Makefile
@@ -0,0 +1,188 @@
+# This file is included by the global makefile so that you can add your own
+# architecture-specific flags and dependencies.
+#
+# This file is subject to the terms and conditions of the GNU General Public
+# License.  See the file "COPYING" in the main directory of this archive
+# for more details.
+#
+
+OBJCOPYFLAGS    := -O binary
+LDFLAGS_vmlinux :=
+ifeq ($(CONFIG_DYNAMIC_FTRACE),y)
+	LDFLAGS_vmlinux := --no-relax
+	KBUILD_CPPFLAGS += -DCC_USING_PATCHABLE_FUNCTION_ENTRY
+ifeq ($(CONFIG_RISCV_ISA_C),y)
+	CC_FLAGS_FTRACE := -fpatchable-function-entry=4
+else
+	CC_FLAGS_FTRACE := -fpatchable-function-entry=2
+endif
+endif
+
+ifeq ($(CONFIG_CMODEL_MEDLOW),y)
+KBUILD_CFLAGS_MODULE += -mcmodel=medany
+endif
+
+export BITS
+ifeq ($(CONFIG_ARCH_RV64I),y)
+	BITS := 64
+	UTS_MACHINE := riscv64
+
+	KBUILD_CFLAGS += -mabi=lp64
+	KBUILD_AFLAGS += -mabi=lp64
+
+	KBUILD_LDFLAGS += -melf64lriscv
+else
+	BITS := 32
+	UTS_MACHINE := riscv32
+
+	KBUILD_CFLAGS += -mabi=ilp32
+	KBUILD_AFLAGS += -mabi=ilp32
+	KBUILD_LDFLAGS += -melf32lriscv
+endif
+
+ifeq ($(CONFIG_LD_IS_LLD),y)
+ifeq ($(shell test $(CONFIG_LLD_VERSION) -lt 150000; echo $$?),0)
+	KBUILD_CFLAGS += -mno-relax
+	KBUILD_AFLAGS += -mno-relax
+ifndef CONFIG_AS_IS_LLVM
+	KBUILD_CFLAGS += -Wa,-mno-relax
+	KBUILD_AFLAGS += -Wa,-mno-relax
+endif
+endif
+endif
+
+# ISA string setting
+riscv-march-$(CONFIG_ARCH_RV32I)	:= rv32ima
+riscv-march-$(CONFIG_ARCH_RV64I)	:= rv64ima
+riscv-march-$(CONFIG_FPU)		:= $(riscv-march-y)fd
+riscv-march-$(CONFIG_RISCV_ISA_C)	:= $(riscv-march-y)c
+
+ifdef CONFIG_TOOLCHAIN_NEEDS_OLD_ISA_SPEC
+KBUILD_CFLAGS += -Wa,-misa-spec=2.2
+KBUILD_AFLAGS += -Wa,-misa-spec=2.2
+else
+riscv-march-$(CONFIG_TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI) := $(riscv-march-y)_zicsr_zifencei
+endif
+
+# Check if the toolchain supports Zicbom extension
+riscv-march-$(CONFIG_TOOLCHAIN_HAS_ZICBOM) := $(riscv-march-y)_zicbom
+
+# Check if the toolchain supports Zihintpause extension
+riscv-march-$(CONFIG_TOOLCHAIN_HAS_ZIHINTPAUSE) := $(riscv-march-y)_zihintpause
+
+KBUILD_CFLAGS += -march=$(subst fd,,$(riscv-march-y))
+KBUILD_AFLAGS += -march=$(riscv-march-y)
+
+KBUILD_CFLAGS += -mno-save-restore
+KBUILD_CFLAGS += -DCONFIG_PAGE_OFFSET=$(CONFIG_PAGE_OFFSET)
+
+ifeq ($(CONFIG_CMODEL_MEDLOW),y)
+	KBUILD_CFLAGS += -mcmodel=medlow
+endif
+ifeq ($(CONFIG_CMODEL_MEDANY),y)
+	KBUILD_CFLAGS += -mcmodel=medany
+endif
+ifeq ($(CONFIG_PERF_EVENTS),y)
+        KBUILD_CFLAGS += -fno-omit-frame-pointer
+endif
+
+# Avoid generating .eh_frame sections.
+KBUILD_CFLAGS += -fno-asynchronous-unwind-tables -fno-unwind-tables
+
+# The RISC-V attributes frequently cause compatibility issues and provide no
+# information, so just turn them off.
+KBUILD_CFLAGS += $(call cc-option,-mno-riscv-attribute)
+KBUILD_AFLAGS += $(call cc-option,-mno-riscv-attribute)
+KBUILD_CFLAGS += $(call as-option,-Wa$(comma)-mno-arch-attr)
+KBUILD_AFLAGS += $(call as-option,-Wa$(comma)-mno-arch-attr)
+
+KBUILD_CFLAGS_MODULE += $(call cc-option,-mno-relax)
+KBUILD_AFLAGS_MODULE += $(call as-option,-Wa$(comma)-mno-relax)
+
+# GCC versions that support the "-mstrict-align" option default to allowing
+# unaligned accesses.  While unaligned accesses are explicitly allowed in the
+# RISC-V ISA, they're emulated by machine mode traps on all extant
+# architectures.  It's faster to have GCC emit only aligned accesses.
+KBUILD_CFLAGS += $(call cc-option,-mstrict-align)
+
+ifeq ($(CONFIG_STACKPROTECTOR_PER_TASK),y)
+prepare: stack_protector_prepare
+stack_protector_prepare: prepare0
+	$(eval KBUILD_CFLAGS += -mstack-protector-guard=tls		  \
+				-mstack-protector-guard-reg=tp		  \
+				-mstack-protector-guard-offset=$(shell	  \
+			awk '{if ($$2 == "TSK_STACK_CANARY") print $$3;}' \
+					include/generated/asm-offsets.h))
+endif
+
+# arch specific predefines for sparse
+CHECKFLAGS += -D__riscv -D__riscv_xlen=$(BITS)
+
+# Default target when executing plain make
+boot		:= arch/riscv/boot
+ifeq ($(CONFIG_XIP_KERNEL),y)
+KBUILD_IMAGE := $(boot)/xipImage
+else
+KBUILD_IMAGE	:= $(boot)/Image.gz
+endif
+
+libs-y += arch/riscv/lib/
+libs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a
+
+PHONY += vdso_install
+vdso_install:
+	$(Q)$(MAKE) $(build)=arch/riscv/kernel/vdso $@
+	$(if $(CONFIG_COMPAT),$(Q)$(MAKE) \
+		$(build)=arch/riscv/kernel/compat_vdso compat_$@)
+
+ifeq ($(KBUILD_EXTMOD),)
+ifeq ($(CONFIG_MMU),y)
+prepare: vdso_prepare
+vdso_prepare: prepare0
+	$(Q)$(MAKE) $(build)=arch/riscv/kernel/vdso include/generated/vdso-offsets.h
+	$(if $(CONFIG_COMPAT),$(Q)$(MAKE) \
+		$(build)=arch/riscv/kernel/compat_vdso include/generated/compat_vdso-offsets.h)
+
+endif
+endif
+
+ifneq ($(CONFIG_XIP_KERNEL),y)
+ifeq ($(CONFIG_RISCV_M_MODE)$(CONFIG_SOC_CANAAN),yy)
+KBUILD_IMAGE := $(boot)/loader.bin
+else
+ifeq ($(CONFIG_EFI_ZBOOT),)
+KBUILD_IMAGE := $(boot)/Image.gz
+else
+KBUILD_IMAGE := $(boot)/vmlinuz.efi
+endif
+endif
+endif
+BOOT_TARGETS := Image Image.gz loader loader.bin xipImage vmlinuz.efi
+
+all:	$(notdir $(KBUILD_IMAGE))
+
+$(BOOT_TARGETS): vmlinux
+	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
+	@$(kecho) '  Kernel: $(boot)/$@ is ready'
+
+Image.%: Image
+	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
+
+install: KBUILD_IMAGE := $(boot)/Image
+zinstall: KBUILD_IMAGE := $(boot)/Image.gz
+install zinstall:
+	$(call cmd,install)
+
+PHONY += rv32_randconfig
+rv32_randconfig:
+	$(Q)$(MAKE) KCONFIG_ALLCONFIG=$(srctree)/arch/riscv/configs/32-bit.config \
+		-f $(srctree)/Makefile randconfig
+
+PHONY += rv64_randconfig
+rv64_randconfig:
+	$(Q)$(MAKE) KCONFIG_ALLCONFIG=$(srctree)/arch/riscv/configs/64-bit.config \
+		-f $(srctree)/Makefile randconfig
+
+PHONY += rv32_defconfig
+rv32_defconfig:
+	$(Q)$(MAKE) -f $(srctree)/Makefile defconfig 32-bit.config
diff --git a/arch/riscv/boot/.gitignore b/arch/riscv/boot/.gitignore
new file mode 100644
index 000000000..e1bc507e8
--- /dev/null
+++ b/arch/riscv/boot/.gitignore
@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: GPL-2.0-only
+Image
+Image.*
+loader
+loader.lds
+loader.bin
+vmlinuz*
+xipImage
diff --git a/arch/riscv/boot/Makefile b/arch/riscv/boot/Makefile
new file mode 100644
index 000000000..d1a49adcb
--- /dev/null
+++ b/arch/riscv/boot/Makefile
@@ -0,0 +1,66 @@
+#
+# arch/riscv/boot/Makefile
+#
+# This file is included by the global makefile so that you can add your own
+# architecture-specific flags and dependencies.
+#
+# This file is subject to the terms and conditions of the GNU General Public
+# License.  See the file "COPYING" in the main directory of this archive
+# for more details.
+#
+# Copyright (C) 2018, Anup Patel.
+# Author: Anup Patel <anup@brainfault.org>
+#
+# Based on the ia64 and arm64 boot/Makefile.
+#
+
+KCOV_INSTRUMENT := n
+
+OBJCOPYFLAGS_Image :=-O binary -R .note -R .note.gnu.build-id -R .comment -S
+OBJCOPYFLAGS_xipImage :=-O binary -R .note -R .note.gnu.build-id -R .comment -S
+
+targets := Image Image.* loader loader.o loader.lds loader.bin
+targets := Image Image.* loader loader.o loader.lds loader.bin xipImage
+
+ifeq ($(CONFIG_XIP_KERNEL),y)
+
+quiet_cmd_mkxip = $(quiet_cmd_objcopy)
+cmd_mkxip = $(cmd_objcopy)
+
+$(obj)/xipImage: vmlinux FORCE
+	$(call if_changed,mkxip)
+	@$(kecho) '  Physical Address of xipImage: $(CONFIG_XIP_PHYS_ADDR)'
+
+endif
+
+$(obj)/Image: vmlinux FORCE
+	$(call if_changed,objcopy)
+
+$(obj)/Image.gz: $(obj)/Image FORCE
+	$(call if_changed,gzip)
+
+$(obj)/loader.o: $(src)/loader.S $(obj)/Image
+
+$(obj)/loader: $(obj)/loader.o $(obj)/Image $(obj)/loader.lds FORCE
+	$(Q)$(LD) -T $(obj)/loader.lds -o $@ $(obj)/loader.o
+
+$(obj)/Image.bz2: $(obj)/Image FORCE
+	$(call if_changed,bzip2)
+
+$(obj)/Image.lz4: $(obj)/Image FORCE
+	$(call if_changed,lz4)
+
+$(obj)/Image.lzma: $(obj)/Image FORCE
+	$(call if_changed,lzma)
+
+$(obj)/Image.lzo: $(obj)/Image FORCE
+	$(call if_changed,lzo)
+
+$(obj)/loader.bin: $(obj)/loader FORCE
+	$(call if_changed,objcopy)
+
+EFI_ZBOOT_PAYLOAD	:= Image
+EFI_ZBOOT_BFD_TARGET	:= elf$(BITS)-littleriscv
+EFI_ZBOOT_MACH_TYPE	:= RISCV$(BITS)
+
+include $(srctree)/drivers/firmware/efi/libstub/Makefile.zboot
diff --git a/arch/riscv/boot/dts/Makefile b/arch/riscv/boot/dts/Makefile
new file mode 100644
index 000000000..ff174996c
--- /dev/null
+++ b/arch/riscv/boot/dts/Makefile
@@ -0,0 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0
+subdir-y += sifive
+subdir-y += starfive
+subdir-$(CONFIG_SOC_CANAAN_K210_DTB_BUILTIN) += canaan
+subdir-y += microchip
+
+obj-$(CONFIG_BUILTIN_DTB) := $(addsuffix /, $(subdir-y))
diff --git a/arch/riscv/boot/dts/canaan/Makefile b/arch/riscv/boot/dts/canaan/Makefile
new file mode 100644
index 000000000..befe4eb75
--- /dev/null
+++ b/arch/riscv/boot/dts/canaan/Makefile
@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0
+dtb-$(CONFIG_SOC_CANAAN) += canaan_kd233.dtb
+dtb-$(CONFIG_SOC_CANAAN) += k210_generic.dtb
+dtb-$(CONFIG_SOC_CANAAN) += sipeed_maix_bit.dtb
+dtb-$(CONFIG_SOC_CANAAN) += sipeed_maix_dock.dtb
+dtb-$(CONFIG_SOC_CANAAN) += sipeed_maix_go.dtb
+dtb-$(CONFIG_SOC_CANAAN) += sipeed_maixduino.dtb
+
+obj-$(CONFIG_SOC_CANAAN_K210_DTB_BUILTIN) += $(addsuffix .dtb.o, $(CONFIG_SOC_CANAAN_K210_DTB_SOURCE))
diff --git a/arch/riscv/boot/dts/canaan/canaan_kd233.dts b/arch/riscv/boot/dts/canaan/canaan_kd233.dts
new file mode 100644
index 000000000..8df4cf365
--- /dev/null
+++ b/arch/riscv/boot/dts/canaan/canaan_kd233.dts
@@ -0,0 +1,152 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2019-20 Sean Anderson <seanga2@gmail.com>
+ * Copyright (C) 2020 Western Digital Corporation or its affiliates.
+ */
+
+/dts-v1/;
+
+#include "k210.dtsi"
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/input.h>
+
+/ {
+	model = "Kendryte KD233";
+	compatible = "canaan,kendryte-kd233", "canaan,kendryte-k210";
+
+	chosen {
+		bootargs = "earlycon console=ttySIF0";
+		stdout-path = "serial0:115200n8";
+	};
+
+	gpio-leds {
+		compatible = "gpio-leds";
+
+		led0 {
+			gpios = <&gpio0 8 GPIO_ACTIVE_LOW>;
+		};
+
+		led1 {
+			gpios = <&gpio0 9 GPIO_ACTIVE_LOW>;
+		};
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+
+		key {
+			label = "KEY0";
+			linux,code = <BTN_0>;
+			gpios = <&gpio0 10 GPIO_ACTIVE_LOW>;
+		};
+	};
+};
+
+&fpioa {
+	pinctrl-0 = <&jtag_pinctrl>;
+	pinctrl-names = "default";
+	status = "okay";
+
+	jtag_pinctrl: jtag-pinmux {
+		pinmux = <K210_FPIOA(0, K210_PCF_JTAG_TCLK)>,
+			 <K210_FPIOA(1, K210_PCF_JTAG_TDI)>,
+			 <K210_FPIOA(2, K210_PCF_JTAG_TMS)>,
+			 <K210_FPIOA(3, K210_PCF_JTAG_TDO)>;
+	};
+
+	uarths_pinctrl: uarths-pinmux {
+		pinmux = <K210_FPIOA(4, K210_PCF_UARTHS_RX)>,
+			 <K210_FPIOA(5, K210_PCF_UARTHS_TX)>;
+	};
+
+	spi0_pinctrl: spi0-pinmux {
+		pinmux = <K210_FPIOA(6, K210_PCF_GPIOHS20)>,  /* cs */
+			 <K210_FPIOA(7, K210_PCF_SPI0_SCLK)>, /* wr */
+			 <K210_FPIOA(8, K210_PCF_GPIOHS21)>;  /* dc */
+	};
+
+	dvp_pinctrl: dvp-pinmux {
+		pinmux = <K210_FPIOA(9, K210_PCF_SCCB_SCLK)>,
+			 <K210_FPIOA(10, K210_PCF_SCCB_SDA)>,
+			 <K210_FPIOA(11, K210_PCF_DVP_RST)>,
+			 <K210_FPIOA(12, K210_PCF_DVP_VSYNC)>,
+			 <K210_FPIOA(13, K210_PCF_DVP_PWDN)>,
+			 <K210_FPIOA(14, K210_PCF_DVP_XCLK)>,
+			 <K210_FPIOA(15, K210_PCF_DVP_PCLK)>,
+			 <K210_FPIOA(17, K210_PCF_DVP_HSYNC)>;
+	};
+
+	gpiohs_pinctrl: gpiohs-pinmux {
+		pinmux = <K210_FPIOA(16, K210_PCF_GPIOHS0)>,
+			 <K210_FPIOA(20, K210_PCF_GPIOHS4)>, /* Rot. dip sw line 8 */
+			 <K210_FPIOA(21, K210_PCF_GPIOHS5)>, /* Rot. dip sw line 4 */
+			 <K210_FPIOA(22, K210_PCF_GPIOHS6)>, /* Rot. dip sw line 2 */
+			 <K210_FPIOA(23, K210_PCF_GPIOHS7)>, /* Rot. dip sw line 1 */
+			 <K210_FPIOA(24, K210_PCF_GPIOHS8)>,
+			 <K210_FPIOA(25, K210_PCF_GPIOHS9)>,
+			 <K210_FPIOA(26, K210_PCF_GPIOHS10)>;
+	};
+
+	spi1_pinctrl: spi1-pinmux {
+		pinmux = <K210_FPIOA(29, K210_PCF_SPI1_SCLK)>,
+			 <K210_FPIOA(30, K210_PCF_SPI1_D0)>,
+			 <K210_FPIOA(31, K210_PCF_SPI1_D1)>,
+			 <K210_FPIOA(32, K210_PCF_GPIOHS16)>; /* cs */
+	};
+
+	i2s0_pinctrl: i2s0-pinmux {
+		pinmux = <K210_FPIOA(33, K210_PCF_I2S0_IN_D0)>,
+			 <K210_FPIOA(34, K210_PCF_I2S0_WS)>,
+			 <K210_FPIOA(35, K210_PCF_I2S0_SCLK)>;
+	};
+};
+
+&uarths0 {
+	pinctrl-0 = <&uarths_pinctrl>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&gpio0 {
+	pinctrl-0 = <&gpiohs_pinctrl>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&i2s0 {
+	#sound-dai-cells = <1>;
+	pinctrl-0 = <&i2s0_pinctrl>;
+	pinctrl-names = "default";
+};
+
+&spi0 {
+	pinctrl-0 = <&spi0_pinctrl>;
+	pinctrl-names = "default";
+	num-cs = <1>;
+	cs-gpios = <&gpio0 20 GPIO_ACTIVE_HIGH>;
+
+	panel@0 {
+		compatible = "canaan,kd233-tft", "ilitek,ili9341";
+		reg = <0>;
+		dc-gpios = <&gpio0 21 GPIO_ACTIVE_HIGH>;
+		spi-max-frequency = <10000000>;
+		status = "disabled";
+	};
+};
+
+&spi1 {
+	pinctrl-0 = <&spi1_pinctrl>;
+	pinctrl-names = "default";
+	num-cs = <1>;
+	cs-gpios = <&gpio0 16 GPIO_ACTIVE_LOW>;
+	status = "okay";
+
+	mmc@0 {
+		compatible = "mmc-spi-slot";
+		reg = <0>;
+		voltage-ranges = <3300 3300>;
+		spi-max-frequency = <25000000>;
+		broken-cd;
+	};
+};
diff --git a/arch/riscv/boot/dts/canaan/k210.dtsi b/arch/riscv/boot/dts/canaan/k210.dtsi
new file mode 100644
index 000000000..07e2e2649
--- /dev/null
+++ b/arch/riscv/boot/dts/canaan/k210.dtsi
@@ -0,0 +1,502 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2019-20 Sean Anderson <seanga2@gmail.com>
+ * Copyright (C) 2020 Western Digital Corporation or its affiliates.
+ */
+#include <dt-bindings/clock/k210-clk.h>
+#include <dt-bindings/pinctrl/k210-fpioa.h>
+#include <dt-bindings/reset/k210-rst.h>
+
+/ {
+	/*
+	 * Although the K210 is a 64-bit CPU, the address bus is only 32-bits
+	 * wide, and the upper half of all addresses is ignored.
+	 */
+	#address-cells = <1>;
+	#size-cells = <1>;
+	compatible = "canaan,kendryte-k210";
+
+	aliases {
+		serial0 = &uarths0;
+		serial1 = &uart1;
+		serial2 = &uart2;
+		serial3 = &uart3;
+	};
+
+	/*
+	 * The K210 has an sv39 MMU following the privileged specification v1.9.
+	 * Since this is a non-ratified draft specification, the kernel does not
+	 * support it and the K210 support enabled only for the !MMU case.
+	 * Be consistent with this by setting the CPUs MMU type to "none".
+	 */
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		timebase-frequency = <7800000>;
+		cpu0: cpu@0 {
+			device_type = "cpu";
+			compatible = "canaan,k210", "riscv";
+			reg = <0>;
+			riscv,isa = "rv64imafdc";
+			mmu-type = "riscv,none";
+			i-cache-block-size = <64>;
+			i-cache-size = <0x8000>;
+			d-cache-block-size = <64>;
+			d-cache-size = <0x8000>;
+			cpu0_intc: interrupt-controller {
+				#interrupt-cells = <1>;
+				interrupt-controller;
+				compatible = "riscv,cpu-intc";
+			};
+		};
+		cpu1: cpu@1 {
+			device_type = "cpu";
+			compatible = "canaan,k210", "riscv";
+			reg = <1>;
+			riscv,isa = "rv64imafdc";
+			mmu-type = "riscv,none";
+			i-cache-block-size = <64>;
+			i-cache-size = <0x8000>;
+			d-cache-block-size = <64>;
+			d-cache-size = <0x8000>;
+			cpu1_intc: interrupt-controller {
+				#interrupt-cells = <1>;
+				interrupt-controller;
+				compatible = "riscv,cpu-intc";
+			};
+		};
+
+		cpu-map {
+			cluster0 {
+				core0 {
+					cpu = <&cpu0>;
+				};
+
+				core1 {
+					cpu = <&cpu1>;
+				};
+			};
+		};
+	};
+
+	sram: memory@80000000 {
+		device_type = "memory";
+		reg = <0x80000000 0x400000>, /* sram0 4 MiB */
+		      <0x80400000 0x200000>, /* sram1 2 MiB */
+		      <0x80600000 0x200000>; /* aisram 2 MiB */
+	};
+
+	sram_controller: memory-controller {
+		compatible = "canaan,k210-sram";
+		clocks = <&sysclk K210_CLK_SRAM0>,
+			 <&sysclk K210_CLK_SRAM1>,
+			 <&sysclk K210_CLK_AI>;
+		clock-names = "sram0", "sram1", "aisram";
+	};
+
+	clocks {
+		in0: oscillator {
+			compatible = "fixed-clock";
+			#clock-cells = <0>;
+			clock-frequency = <26000000>;
+		};
+	};
+
+	soc {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		compatible = "simple-bus";
+		ranges;
+		interrupt-parent = <&plic0>;
+
+		rom0: nvmem@1000 {
+			reg = <0x1000 0x1000>;
+			read-only;
+		};
+
+		clint0: timer@2000000 {
+			compatible = "canaan,k210-clint", "sifive,clint0";
+			reg = <0x2000000 0xC000>;
+			interrupts-extended = <&cpu0_intc 3>, <&cpu0_intc 7>,
+					      <&cpu1_intc 3>, <&cpu1_intc 7>;
+		};
+
+		plic0: interrupt-controller@c000000 {
+			#interrupt-cells = <1>;
+			#address-cells = <0>;
+			compatible = "canaan,k210-plic", "sifive,plic-1.0.0";
+			reg = <0xC000000 0x4000000>;
+			interrupt-controller;
+			interrupts-extended = <&cpu0_intc 11>, <&cpu0_intc 9>,
+					      <&cpu1_intc 11>, <&cpu1_intc 9>;
+			riscv,ndev = <65>;
+		};
+
+		uarths0: serial@38000000 {
+			compatible = "canaan,k210-uarths", "sifive,uart0";
+			reg = <0x38000000 0x1000>;
+			interrupts = <33>;
+			clocks = <&sysclk K210_CLK_CPU>;
+		};
+
+		gpio0: gpio-controller@38001000 {
+			#interrupt-cells = <2>;
+			#gpio-cells = <2>;
+			compatible = "canaan,k210-gpiohs", "sifive,gpio0";
+			reg = <0x38001000 0x1000>;
+			interrupt-controller;
+			interrupts = <34>, <35>, <36>, <37>, <38>, <39>, <40>,
+				     <41>, <42>, <43>, <44>, <45>, <46>, <47>,
+				     <48>, <49>, <50>, <51>, <52>, <53>, <54>,
+				     <55>, <56>, <57>, <58>, <59>, <60>, <61>,
+				     <62>, <63>, <64>, <65>;
+			gpio-controller;
+			ngpios = <32>;
+		};
+
+		dmac0: dma-controller@50000000 {
+			compatible = "snps,axi-dma-1.01a";
+			reg = <0x50000000 0x1000>;
+			interrupts = <27>, <28>, <29>, <30>, <31>, <32>;
+			#dma-cells = <1>;
+			clocks = <&sysclk K210_CLK_DMA>, <&sysclk K210_CLK_DMA>;
+			clock-names = "core-clk", "cfgr-clk";
+			resets = <&sysrst K210_RST_DMA>;
+			dma-channels = <6>;
+			snps,dma-masters = <2>;
+			snps,priority = <0 1 2 3 4 5>;
+			snps,data-width = <5>;
+			snps,block-size = <0x200000 0x200000 0x200000
+					   0x200000 0x200000 0x200000>;
+			snps,axi-max-burst-len = <256>;
+		};
+
+		apb0: bus@50200000 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "simple-pm-bus";
+			ranges = <0x50200000 0x50200000 0x200000>;
+			clocks = <&sysclk K210_CLK_APB0>;
+
+			gpio1: gpio@50200000 {
+				#address-cells = <1>;
+				#size-cells = <0>;
+				compatible = "snps,dw-apb-gpio";
+				reg = <0x50200000 0x80>;
+				clocks = <&sysclk K210_CLK_APB0>,
+					 <&sysclk K210_CLK_GPIO>;
+				clock-names = "bus", "db";
+				resets = <&sysrst K210_RST_GPIO>;
+
+				gpio1_0: gpio-port@0 {
+					#gpio-cells = <2>;
+					#interrupt-cells = <2>;
+					compatible = "snps,dw-apb-gpio-port";
+					reg = <0>;
+					interrupt-controller;
+					interrupts = <23>;
+					gpio-controller;
+					ngpios = <8>;
+				};
+			};
+
+			uart1: serial@50210000 {
+				compatible = "snps,dw-apb-uart";
+				reg = <0x50210000 0x100>;
+				interrupts = <11>;
+				clocks = <&sysclk K210_CLK_UART1>,
+					 <&sysclk K210_CLK_APB0>;
+				clock-names = "baudclk", "apb_pclk";
+				resets = <&sysrst K210_RST_UART1>;
+				reg-io-width = <4>;
+				reg-shift = <2>;
+				dcd-override;
+				dsr-override;
+				cts-override;
+				ri-override;
+			};
+
+			uart2: serial@50220000 {
+				compatible = "snps,dw-apb-uart";
+				reg = <0x50220000 0x100>;
+				interrupts = <12>;
+				clocks = <&sysclk K210_CLK_UART2>,
+					 <&sysclk K210_CLK_APB0>;
+				clock-names = "baudclk", "apb_pclk";
+				resets = <&sysrst K210_RST_UART2>;
+				reg-io-width = <4>;
+				reg-shift = <2>;
+				dcd-override;
+				dsr-override;
+				cts-override;
+				ri-override;
+			};
+
+			uart3: serial@50230000 {
+				compatible = "snps,dw-apb-uart";
+				reg = <0x50230000 0x100>;
+				interrupts = <13>;
+				clocks = <&sysclk K210_CLK_UART3>,
+					 <&sysclk K210_CLK_APB0>;
+				clock-names = "baudclk", "apb_pclk";
+				resets = <&sysrst K210_RST_UART3>;
+				reg-io-width = <4>;
+				reg-shift = <2>;
+				dcd-override;
+				dsr-override;
+				cts-override;
+				ri-override;
+			};
+
+			spi2: spi@50240000 {
+				compatible = "canaan,k210-spi";
+				spi-slave;
+				reg = <0x50240000 0x100>;
+				#address-cells = <0>;
+				#size-cells = <0>;
+				interrupts = <3>;
+				clocks = <&sysclk K210_CLK_SPI2>,
+					 <&sysclk K210_CLK_APB0>;
+				clock-names = "ssi_clk", "pclk";
+				resets = <&sysrst K210_RST_SPI2>;
+				spi-max-frequency = <25000000>;
+			};
+
+			i2s0: i2s@50250000 {
+				compatible = "canaan,k210-i2s", "snps,designware-i2s";
+				reg = <0x50250000 0x200>;
+				interrupts = <5>;
+				clocks = <&sysclk K210_CLK_I2S0>;
+				clock-names = "i2sclk";
+				resets = <&sysrst K210_RST_I2S0>;
+			};
+
+			i2s1: i2s@50260000 {
+				compatible = "canaan,k210-i2s", "snps,designware-i2s";
+				reg = <0x50260000 0x200>;
+				interrupts = <6>;
+				clocks = <&sysclk K210_CLK_I2S1>;
+				clock-names = "i2sclk";
+				resets = <&sysrst K210_RST_I2S1>;
+			};
+
+			i2s2: i2s@50270000 {
+				compatible = "canaan,k210-i2s", "snps,designware-i2s";
+				reg = <0x50270000 0x200>;
+				interrupts = <7>;
+				clocks = <&sysclk K210_CLK_I2S2>;
+				clock-names = "i2sclk";
+				resets = <&sysrst K210_RST_I2S2>;
+			};
+
+			i2c0: i2c@50280000 {
+				compatible = "snps,designware-i2c";
+				reg = <0x50280000 0x100>;
+				interrupts = <8>;
+				clocks = <&sysclk K210_CLK_I2C0>,
+					 <&sysclk K210_CLK_APB0>;
+				clock-names = "ref", "pclk";
+				resets = <&sysrst K210_RST_I2C0>;
+			};
+
+			i2c1: i2c@50290000 {
+				compatible = "snps,designware-i2c";
+				reg = <0x50290000 0x100>;
+				interrupts = <9>;
+				clocks = <&sysclk K210_CLK_I2C1>,
+					 <&sysclk K210_CLK_APB0>;
+				clock-names = "ref", "pclk";
+				resets = <&sysrst K210_RST_I2C1>;
+			};
+
+			i2c2: i2c@502a0000 {
+				compatible = "snps,designware-i2c";
+				reg = <0x502A0000 0x100>;
+				interrupts = <10>;
+				clocks = <&sysclk K210_CLK_I2C2>,
+					 <&sysclk K210_CLK_APB0>;
+				clock-names = "ref", "pclk";
+				resets = <&sysrst K210_RST_I2C2>;
+			};
+
+			fpioa: pinmux@502b0000 {
+				compatible = "canaan,k210-fpioa";
+				reg = <0x502B0000 0x100>;
+				clocks = <&sysclk K210_CLK_FPIOA>,
+					 <&sysclk K210_CLK_APB0>;
+				clock-names = "ref", "pclk";
+				resets = <&sysrst K210_RST_FPIOA>;
+				canaan,k210-sysctl-power = <&sysctl 108>;
+			};
+
+			timer0: timer@502d0000 {
+				compatible = "snps,dw-apb-timer";
+				reg = <0x502D0000 0x14>;
+				interrupts = <14>;
+				clocks = <&sysclk K210_CLK_TIMER0>,
+					 <&sysclk K210_CLK_APB0>;
+				clock-names = "timer", "pclk";
+				resets = <&sysrst K210_RST_TIMER0>;
+			};
+
+			timer1: timer@502d0014 {
+				compatible = "snps,dw-apb-timer";
+				reg = <0x502D0014 0x14>;
+				interrupts = <15>;
+				clocks = <&sysclk K210_CLK_TIMER0>,
+					 <&sysclk K210_CLK_APB0>;
+				clock-names = "timer", "pclk";
+				resets = <&sysrst K210_RST_TIMER0>;
+			};
+
+			timer2: timer@502e0000 {
+				compatible = "snps,dw-apb-timer";
+				reg = <0x502E0000 0x14>;
+				interrupts = <16>;
+				clocks = <&sysclk K210_CLK_TIMER1>,
+					 <&sysclk K210_CLK_APB0>;
+				clock-names = "timer", "pclk";
+				resets = <&sysrst K210_RST_TIMER1>;
+			};
+
+			timer3: timer@502e0014 {
+				compatible = "snps,dw-apb-timer";
+				reg = <0x502E0014 0x114>;
+				interrupts = <17>;
+				clocks = <&sysclk K210_CLK_TIMER1>,
+					 <&sysclk K210_CLK_APB0>;
+				clock-names = "timer", "pclk";
+				resets = <&sysrst K210_RST_TIMER1>;
+			};
+
+			timer4: timer@502f0000 {
+				compatible = "snps,dw-apb-timer";
+				reg = <0x502F0000 0x14>;
+				interrupts = <18>;
+				clocks = <&sysclk K210_CLK_TIMER2>,
+					 <&sysclk K210_CLK_APB0>;
+				clock-names = "timer", "pclk";
+				resets = <&sysrst K210_RST_TIMER2>;
+			};
+
+			timer5: timer@502f0014 {
+				compatible = "snps,dw-apb-timer";
+				reg = <0x502F0014 0x14>;
+				interrupts = <19>;
+				clocks = <&sysclk K210_CLK_TIMER2>,
+					 <&sysclk K210_CLK_APB0>;
+				clock-names = "timer", "pclk";
+				resets = <&sysrst K210_RST_TIMER2>;
+			};
+		};
+
+		apb1: bus@50400000 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "simple-pm-bus";
+			ranges = <0x50400000 0x50400000 0x40100>;
+			clocks = <&sysclk K210_CLK_APB1>;
+
+			wdt0: watchdog@50400000 {
+				compatible = "snps,dw-wdt";
+				reg = <0x50400000 0x100>;
+				interrupts = <21>;
+				clocks = <&sysclk K210_CLK_WDT0>,
+					 <&sysclk K210_CLK_APB1>;
+				clock-names = "tclk", "pclk";
+				resets = <&sysrst K210_RST_WDT0>;
+			};
+
+			wdt1: watchdog@50410000 {
+				compatible = "snps,dw-wdt";
+				reg = <0x50410000 0x100>;
+				interrupts = <22>;
+				clocks = <&sysclk K210_CLK_WDT1>,
+					 <&sysclk K210_CLK_APB1>;
+				clock-names = "tclk", "pclk";
+				resets = <&sysrst K210_RST_WDT1>;
+			};
+
+			sysctl: syscon@50440000 {
+				compatible = "canaan,k210-sysctl",
+					     "syscon", "simple-mfd";
+				reg = <0x50440000 0x100>;
+				clocks = <&sysclk K210_CLK_APB1>;
+				clock-names = "pclk";
+
+				sysclk: clock-controller {
+					#clock-cells = <1>;
+					compatible = "canaan,k210-clk";
+					clocks = <&in0>;
+				};
+
+				sysrst: reset-controller {
+					compatible = "canaan,k210-rst";
+					#reset-cells = <1>;
+				};
+
+				reboot: syscon-reboot {
+					compatible = "syscon-reboot";
+					regmap = <&sysctl>;
+					offset = <48>;
+					mask = <1>;
+					value = <1>;
+				};
+			};
+		};
+
+		apb2: bus@52000000 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "simple-pm-bus";
+			ranges = <0x52000000 0x52000000 0x2000200>;
+			clocks = <&sysclk K210_CLK_APB2>;
+
+			spi0: spi@52000000 {
+				#address-cells = <1>;
+				#size-cells = <0>;
+				compatible = "canaan,k210-spi";
+				reg = <0x52000000 0x100>;
+				interrupts = <1>;
+				clocks = <&sysclk K210_CLK_SPI0>,
+					 <&sysclk K210_CLK_APB2>;
+				clock-names = "ssi_clk", "pclk";
+				resets = <&sysrst K210_RST_SPI0>;
+				reset-names = "spi";
+				num-cs = <4>;
+				reg-io-width = <4>;
+			};
+
+			spi1: spi@53000000 {
+				#address-cells = <1>;
+				#size-cells = <0>;
+				compatible = "canaan,k210-spi";
+				reg = <0x53000000 0x100>;
+				interrupts = <2>;
+				clocks = <&sysclk K210_CLK_SPI1>,
+					 <&sysclk K210_CLK_APB2>;
+				clock-names = "ssi_clk", "pclk";
+				resets = <&sysrst K210_RST_SPI1>;
+				reset-names = "spi";
+				num-cs = <4>;
+				reg-io-width = <4>;
+			};
+
+			spi3: spi@54000000 {
+				#address-cells = <1>;
+				#size-cells = <0>;
+				compatible = "snps,dwc-ssi-1.01a";
+				reg = <0x54000000 0x200>;
+				interrupts = <4>;
+				clocks = <&sysclk K210_CLK_SPI3>,
+					 <&sysclk K210_CLK_APB2>;
+				clock-names = "ssi_clk", "pclk";
+				resets = <&sysrst K210_RST_SPI3>;
+				reset-names = "spi";
+
+				num-cs = <4>;
+				reg-io-width = <4>;
+			};
+		};
+	};
+};
diff --git a/arch/riscv/boot/dts/canaan/k210_generic.dts b/arch/riscv/boot/dts/canaan/k210_generic.dts
new file mode 100644
index 000000000..396c8ca4d
--- /dev/null
+++ b/arch/riscv/boot/dts/canaan/k210_generic.dts
@@ -0,0 +1,46 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2019-20 Sean Anderson <seanga2@gmail.com>
+ * Copyright (C) 2020 Western Digital Corporation or its affiliates.
+ */
+
+/dts-v1/;
+
+#include "k210.dtsi"
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/input.h>
+
+/ {
+	model = "Kendryte K210 generic";
+	compatible = "canaan,kendryte-k210";
+
+	chosen {
+		bootargs = "earlycon console=ttySIF0";
+		stdout-path = "serial0:115200n8";
+	};
+};
+
+&fpioa {
+	pinctrl-0 = <&jtag_pins>;
+	pinctrl-names = "default";
+	status = "okay";
+
+	jtag_pins: jtag-pinmux {
+		pinmux = <K210_FPIOA(0, K210_PCF_JTAG_TCLK)>,
+			 <K210_FPIOA(1, K210_PCF_JTAG_TDI)>,
+			 <K210_FPIOA(2, K210_PCF_JTAG_TMS)>,
+			 <K210_FPIOA(3, K210_PCF_JTAG_TDO)>;
+	};
+
+	uarths_pins: uarths-pinmux {
+		pinmux = <K210_FPIOA(4, K210_PCF_UARTHS_RX)>,
+			 <K210_FPIOA(5, K210_PCF_UARTHS_TX)>;
+	};
+};
+
+&uarths0 {
+	pinctrl-0 = <&uarths_pins>;
+	pinctrl-names = "default";
+	status = "okay";
+};
diff --git a/arch/riscv/boot/dts/canaan/sipeed_maix_bit.dts b/arch/riscv/boot/dts/canaan/sipeed_maix_bit.dts
new file mode 100644
index 000000000..6d25bf074
--- /dev/null
+++ b/arch/riscv/boot/dts/canaan/sipeed_maix_bit.dts
@@ -0,0 +1,211 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2019-20 Sean Anderson <seanga2@gmail.com>
+ * Copyright (C) 2020 Western Digital Corporation or its affiliates.
+ */
+
+/dts-v1/;
+
+#include "k210.dtsi"
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/input.h>
+#include <dt-bindings/leds/common.h>
+
+/ {
+	model = "SiPeed MAIX BiT";
+	compatible = "sipeed,maix-bit", "sipeed,maix-bitm",
+		     "canaan,kendryte-k210";
+
+	chosen {
+		bootargs = "earlycon console=ttySIF0";
+		stdout-path = "serial0:115200n8";
+	};
+
+	gpio-leds {
+		compatible = "gpio-leds";
+
+		led0 {
+			color = <LED_COLOR_ID_GREEN>;
+			label = "green";
+			gpios = <&gpio1_0 4 GPIO_ACTIVE_LOW>;
+		};
+
+		led1 {
+			color = <LED_COLOR_ID_RED>;
+			label = "red";
+			gpios = <&gpio1_0 5 GPIO_ACTIVE_LOW>;
+		};
+
+		led2 {
+			color = <LED_COLOR_ID_BLUE>;
+			label = "blue";
+			gpios = <&gpio1_0 6 GPIO_ACTIVE_LOW>;
+		};
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+
+		key-boot {
+			label = "BOOT";
+			linux,code = <BTN_0>;
+			gpios = <&gpio0 0 GPIO_ACTIVE_LOW>;
+		};
+	};
+};
+
+&fpioa {
+	pinctrl-names = "default";
+	pinctrl-0 = <&jtag_pinctrl>;
+	status = "okay";
+
+	jtag_pinctrl: jtag-pinmux {
+		pinmux = <K210_FPIOA(0, K210_PCF_JTAG_TCLK)>,
+			 <K210_FPIOA(1, K210_PCF_JTAG_TDI)>,
+			 <K210_FPIOA(2, K210_PCF_JTAG_TMS)>,
+			 <K210_FPIOA(3, K210_PCF_JTAG_TDO)>;
+	};
+
+	uarths_pinctrl: uarths-pinmux {
+		pinmux = <K210_FPIOA(4, K210_PCF_UARTHS_RX)>,
+			 <K210_FPIOA(5, K210_PCF_UARTHS_TX)>;
+	};
+
+	gpio_pinctrl: gpio-pinmux {
+		pinmux = <K210_FPIOA(8, K210_PCF_GPIO0)>,
+			 <K210_FPIOA(9, K210_PCF_GPIO1)>,
+			 <K210_FPIOA(10, K210_PCF_GPIO2)>,
+			 <K210_FPIOA(11, K210_PCF_GPIO3)>,
+			 <K210_FPIOA(12, K210_PCF_GPIO4)>,
+			 <K210_FPIOA(13, K210_PCF_GPIO5)>,
+			 <K210_FPIOA(14, K210_PCF_GPIO6)>,
+			 <K210_FPIOA(15, K210_PCF_GPIO7)>;
+	};
+
+	gpiohs_pinctrl: gpiohs-pinmux {
+		pinmux = <K210_FPIOA(16, K210_PCF_GPIOHS0)>,
+			 <K210_FPIOA(17, K210_PCF_GPIOHS1)>,
+			 <K210_FPIOA(21, K210_PCF_GPIOHS5)>,
+			 <K210_FPIOA(22, K210_PCF_GPIOHS6)>,
+			 <K210_FPIOA(23, K210_PCF_GPIOHS7)>,
+			 <K210_FPIOA(24, K210_PCF_GPIOHS8)>,
+			 <K210_FPIOA(25, K210_PCF_GPIOHS9)>,
+			 <K210_FPIOA(32, K210_PCF_GPIOHS16)>,
+			 <K210_FPIOA(33, K210_PCF_GPIOHS17)>,
+			 <K210_FPIOA(34, K210_PCF_GPIOHS18)>,
+			 <K210_FPIOA(35, K210_PCF_GPIOHS19)>;
+	};
+
+	i2s0_pinctrl: i2s0-pinmux {
+		pinmux = <K210_FPIOA(18, K210_PCF_I2S0_SCLK)>,
+			 <K210_FPIOA(19, K210_PCF_I2S0_WS)>,
+			 <K210_FPIOA(20, K210_PCF_I2S0_IN_D0)>;
+	};
+
+	dvp_pinctrl: dvp-pinmux {
+		pinmux = <K210_FPIOA(40, K210_PCF_SCCB_SDA)>,
+			 <K210_FPIOA(41, K210_PCF_SCCB_SCLK)>,
+			 <K210_FPIOA(42, K210_PCF_DVP_RST)>,
+			 <K210_FPIOA(43, K210_PCF_DVP_VSYNC)>,
+			 <K210_FPIOA(44, K210_PCF_DVP_PWDN)>,
+			 <K210_FPIOA(45, K210_PCF_DVP_HSYNC)>,
+			 <K210_FPIOA(46, K210_PCF_DVP_XCLK)>,
+			 <K210_FPIOA(47, K210_PCF_DVP_PCLK)>;
+	};
+
+	spi0_pinctrl: spi0-pinmux {
+		pinmux = <K210_FPIOA(36, K210_PCF_GPIOHS20)>,  /* cs */
+			 <K210_FPIOA(37, K210_PCF_GPIOHS21)>,  /* rst */
+			 <K210_FPIOA(38, K210_PCF_GPIOHS22)>,  /* dc */
+			 <K210_FPIOA(39, K210_PCF_SPI0_SCLK)>; /* wr */
+	};
+
+	spi1_pinctrl: spi1-pinmux {
+		pinmux = <K210_FPIOA(26, K210_PCF_SPI1_D1)>,
+			 <K210_FPIOA(27, K210_PCF_SPI1_SCLK)>,
+			 <K210_FPIOA(28, K210_PCF_SPI1_D0)>,
+			 <K210_FPIOA(29, K210_PCF_GPIOHS13)>; /* cs */
+	};
+
+	i2c1_pinctrl: i2c1-pinmux {
+		pinmux = <K210_FPIOA(30, K210_PCF_I2C1_SCLK)>,
+			 <K210_FPIOA(31, K210_PCF_I2C1_SDA)>;
+	};
+};
+
+&uarths0 {
+	pinctrl-0 = <&uarths_pinctrl>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&gpio0 {
+	pinctrl-0 = <&gpiohs_pinctrl>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&gpio1 {
+	pinctrl-0 = <&gpio_pinctrl>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&i2s0 {
+	#sound-dai-cells = <1>;
+	pinctrl-0 = <&i2s0_pinctrl>;
+	pinctrl-names = "default";
+};
+
+&i2c1 {
+	pinctrl-0 = <&i2c1_pinctrl>;
+	pinctrl-names = "default";
+	clock-frequency = <400000>;
+	status = "okay";
+};
+
+&spi0 {
+	pinctrl-0 = <&spi0_pinctrl>;
+	pinctrl-names = "default";
+	num-cs = <1>;
+	cs-gpios = <&gpio0 20 GPIO_ACTIVE_HIGH>;
+
+	panel@0 {
+		compatible = "sitronix,st7789v";
+		reg = <0>;
+		reset-gpios = <&gpio0 21 GPIO_ACTIVE_LOW>;
+		dc-gpios = <&gpio0 22 GPIO_ACTIVE_HIGH>;
+		spi-max-frequency = <15000000>;
+		spi-cs-high;
+		status = "disabled";
+	};
+};
+
+&spi1 {
+	pinctrl-0 = <&spi1_pinctrl>;
+	pinctrl-names = "default";
+	num-cs = <1>;
+	cs-gpios = <&gpio0 13 GPIO_ACTIVE_LOW>;
+	status = "okay";
+
+	mmc@0 {
+		compatible = "mmc-spi-slot";
+		reg = <0>;
+		voltage-ranges = <3300 3300>;
+		spi-max-frequency = <25000000>;
+		broken-cd;
+	};
+};
+
+&spi3 {
+	flash@0 {
+		compatible = "jedec,spi-nor";
+		reg = <0>;
+		spi-max-frequency = <50000000>;
+		spi-tx-bus-width = <4>;
+		spi-rx-bus-width = <4>;
+		m25p,fast-read;
+		broken-flash-reset;
+	};
+};
diff --git a/arch/riscv/boot/dts/canaan/sipeed_maix_dock.dts b/arch/riscv/boot/dts/canaan/sipeed_maix_dock.dts
new file mode 100644
index 000000000..f4f4d8d5e
--- /dev/null
+++ b/arch/riscv/boot/dts/canaan/sipeed_maix_dock.dts
@@ -0,0 +1,213 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2019-20 Sean Anderson <seanga2@gmail.com>
+ * Copyright (C) 2020 Western Digital Corporation or its affiliates.
+ */
+
+/dts-v1/;
+
+#include "k210.dtsi"
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/input.h>
+#include <dt-bindings/leds/common.h>
+
+/ {
+	model = "SiPeed MAIX Dock";
+	compatible = "sipeed,maix-dock-m1", "sipeed,maix-dock-m1w",
+		     "canaan,kendryte-k210";
+
+	chosen {
+		bootargs = "earlycon console=ttySIF0";
+		stdout-path = "serial0:115200n8";
+	};
+
+	gpio-leds {
+		compatible = "gpio-leds";
+
+		/*
+		 * Note: the board wiring drawing documents green on
+		 * gpio #4, red on gpio #5 and blue on gpio #6. However,
+		 * the board is actually wired differently as defined here.
+		 */
+		led0 {
+			color = <LED_COLOR_ID_BLUE>;
+			label = "blue";
+			gpios = <&gpio1_0 4 GPIO_ACTIVE_LOW>;
+		};
+
+		led1 {
+			color = <LED_COLOR_ID_GREEN>;
+			label = "green";
+			gpios = <&gpio1_0 5 GPIO_ACTIVE_LOW>;
+		};
+
+		led2 {
+			color = <LED_COLOR_ID_RED>;
+			label = "red";
+			gpios = <&gpio1_0 6 GPIO_ACTIVE_LOW>;
+		};
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+
+		key-boot {
+			label = "BOOT";
+			linux,code = <BTN_0>;
+			gpios = <&gpio0 0 GPIO_ACTIVE_LOW>;
+		};
+	};
+};
+
+&fpioa {
+	pinctrl-0 = <&jtag_pinctrl>;
+	pinctrl-names = "default";
+	status = "okay";
+
+	jtag_pinctrl: jtag-pinmux {
+		pinmux = <K210_FPIOA(0, K210_PCF_JTAG_TCLK)>,
+			 <K210_FPIOA(1, K210_PCF_JTAG_TDI)>,
+			 <K210_FPIOA(2, K210_PCF_JTAG_TMS)>,
+			 <K210_FPIOA(3, K210_PCF_JTAG_TDO)>;
+	};
+
+	uarths_pinctrl: uarths-pinmux {
+		pinmux = <K210_FPIOA(4, K210_PCF_UARTHS_RX)>,
+			 <K210_FPIOA(5, K210_PCF_UARTHS_TX)>;
+	};
+
+	gpio_pinctrl: gpio-pinmux {
+		pinmux = <K210_FPIOA(8, K210_PCF_GPIO0)>,
+			 <K210_FPIOA(11, K210_PCF_GPIO3)>,
+			 <K210_FPIOA(12, K210_PCF_GPIO4)>,
+			 <K210_FPIOA(13, K210_PCF_GPIO5)>,
+			 <K210_FPIOA(14, K210_PCF_GPIO6)>,
+			 <K210_FPIOA(15, K210_PCF_GPIO7)>;
+	};
+
+	gpiohs_pinctrl: gpiohs-pinmux {
+		pinmux = <K210_FPIOA(16, K210_PCF_GPIOHS0)>,
+			 <K210_FPIOA(17, K210_PCF_GPIOHS1)>,
+			 <K210_FPIOA(21, K210_PCF_GPIOHS5)>,
+			 <K210_FPIOA(22, K210_PCF_GPIOHS6)>,
+			 <K210_FPIOA(23, K210_PCF_GPIOHS7)>,
+			 <K210_FPIOA(24, K210_PCF_GPIOHS8)>,
+			 <K210_FPIOA(25, K210_PCF_GPIOHS9)>,
+			 <K210_FPIOA(32, K210_PCF_GPIOHS16)>,
+			 <K210_FPIOA(33, K210_PCF_GPIOHS17)>,
+			 <K210_FPIOA(34, K210_PCF_GPIOHS18)>,
+			 <K210_FPIOA(35, K210_PCF_GPIOHS19)>;
+	};
+
+	i2s0_pinctrl: i2s0-pinmux {
+		pinmux = <K210_FPIOA(18, K210_PCF_I2S0_SCLK)>,
+			 <K210_FPIOA(19, K210_PCF_I2S0_WS)>,
+			 <K210_FPIOA(20, K210_PCF_I2S0_IN_D0)>;
+	};
+
+	dvp_pinctrl: dvp-pinmux {
+		pinmux = <K210_FPIOA(40, K210_PCF_SCCB_SDA)>,
+			 <K210_FPIOA(41, K210_PCF_SCCB_SCLK)>,
+			 <K210_FPIOA(42, K210_PCF_DVP_RST)>,
+			 <K210_FPIOA(43, K210_PCF_DVP_VSYNC)>,
+			 <K210_FPIOA(44, K210_PCF_DVP_PWDN)>,
+			 <K210_FPIOA(45, K210_PCF_DVP_HSYNC)>,
+			 <K210_FPIOA(46, K210_PCF_DVP_XCLK)>,
+			 <K210_FPIOA(47, K210_PCF_DVP_PCLK)>;
+	};
+
+	spi0_pinctrl: spi0-pinmux {
+		pinmux = <K210_FPIOA(36, K210_PCF_GPIOHS20)>,  /* cs */
+			 <K210_FPIOA(37, K210_PCF_GPIOHS21)>,  /* rst */
+			 <K210_FPIOA(38, K210_PCF_GPIOHS22)>,  /* dc */
+			 <K210_FPIOA(39, K210_PCF_SPI0_SCLK)>; /* wr */
+	};
+
+	spi1_pinctrl: spi1-pinmux {
+		pinmux = <K210_FPIOA(26, K210_PCF_SPI1_D1)>,
+			 <K210_FPIOA(27, K210_PCF_SPI1_SCLK)>,
+			 <K210_FPIOA(28, K210_PCF_SPI1_D0)>,
+			 <K210_FPIOA(29, K210_PCF_GPIOHS13)>; /* cs */
+	};
+
+	i2c1_pinctrl: i2c1-pinmux {
+		pinmux = <K210_FPIOA(9, K210_PCF_I2C1_SCLK)>,
+			 <K210_FPIOA(10, K210_PCF_I2C1_SDA)>;
+	};
+};
+
+&uarths0 {
+	pinctrl-0 = <&uarths_pinctrl>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&gpio0 {
+	pinctrl-0 = <&gpiohs_pinctrl>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&gpio1 {
+	pinctrl-0 = <&gpio_pinctrl>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&i2s0 {
+	#sound-dai-cells = <1>;
+	pinctrl-0 = <&i2s0_pinctrl>;
+	pinctrl-names = "default";
+};
+
+&i2c1 {
+	pinctrl-0 = <&i2c1_pinctrl>;
+	pinctrl-names = "default";
+	clock-frequency = <400000>;
+	status = "okay";
+};
+
+&spi0 {
+	pinctrl-0 = <&spi0_pinctrl>;
+	pinctrl-names = "default";
+	num-cs = <1>;
+	cs-gpios = <&gpio0 20 GPIO_ACTIVE_HIGH>;
+
+	panel@0 {
+		compatible = "sitronix,st7789v";
+		reg = <0>;
+		reset-gpios = <&gpio0 21 GPIO_ACTIVE_LOW>;
+		dc-gpios = <&gpio0 22 0>;
+		spi-max-frequency = <15000000>;
+		status = "disabled";
+	};
+};
+
+&spi1 {
+	pinctrl-0 = <&spi1_pinctrl>;
+	pinctrl-names = "default";
+	num-cs = <1>;
+	cs-gpios = <&gpio0 13 GPIO_ACTIVE_LOW>;
+	status = "okay";
+
+	mmc@0 {
+		compatible = "mmc-spi-slot";
+		reg = <0>;
+		voltage-ranges = <3300 3300>;
+		spi-max-frequency = <25000000>;
+		broken-cd;
+	};
+};
+
+&spi3 {
+	flash@0 {
+		compatible = "jedec,spi-nor";
+		reg = <0>;
+		spi-max-frequency = <50000000>;
+		spi-tx-bus-width = <4>;
+		spi-rx-bus-width = <4>;
+		m25p,fast-read;
+		broken-flash-reset;
+	};
+};
diff --git a/arch/riscv/boot/dts/canaan/sipeed_maix_go.dts b/arch/riscv/boot/dts/canaan/sipeed_maix_go.dts
new file mode 100644
index 000000000..0d86df47e
--- /dev/null
+++ b/arch/riscv/boot/dts/canaan/sipeed_maix_go.dts
@@ -0,0 +1,221 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2019-20 Sean Anderson <seanga2@gmail.com>
+ * Copyright (C) 2020 Western Digital Corporation or its affiliates.
+ */
+
+/dts-v1/;
+
+#include "k210.dtsi"
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/input.h>
+#include <dt-bindings/leds/common.h>
+
+/ {
+	model = "SiPeed MAIX GO";
+	compatible = "sipeed,maix-go", "canaan,kendryte-k210";
+
+	chosen {
+		bootargs = "earlycon console=ttySIF0";
+		stdout-path = "serial0:115200n8";
+	};
+
+	gpio-leds {
+		compatible = "gpio-leds";
+
+		led0 {
+			color = <LED_COLOR_ID_GREEN>;
+			label = "green";
+			gpios = <&gpio1_0 4 GPIO_ACTIVE_LOW>;
+		};
+
+		led1 {
+			color = <LED_COLOR_ID_RED>;
+			label = "red";
+			gpios = <&gpio1_0 5 GPIO_ACTIVE_LOW>;
+		};
+
+		led2 {
+			color = <LED_COLOR_ID_BLUE>;
+			label = "blue";
+			gpios = <&gpio1_0 6 GPIO_ACTIVE_LOW>;
+		};
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+
+		key-up {
+			label = "UP";
+			linux,code = <BTN_1>;
+			gpios = <&gpio1_0 7 GPIO_ACTIVE_LOW>;
+		};
+
+		key-press {
+			label = "PRESS";
+			linux,code = <BTN_0>;
+			gpios = <&gpio0 0 GPIO_ACTIVE_LOW>;
+		};
+
+		key-down {
+			label = "DOWN";
+			linux,code = <BTN_2>;
+			gpios = <&gpio0 1 GPIO_ACTIVE_LOW>;
+		};
+	};
+};
+
+&fpioa {
+	pinctrl-0 = <&jtag_pinctrl>;
+	pinctrl-names = "default";
+	status = "okay";
+
+	jtag_pinctrl: jtag-pinmux {
+		pinmux = <K210_FPIOA(0, K210_PCF_JTAG_TCLK)>,
+			 <K210_FPIOA(1, K210_PCF_JTAG_TDI)>,
+			 <K210_FPIOA(2, K210_PCF_JTAG_TMS)>,
+			 <K210_FPIOA(3, K210_PCF_JTAG_TDO)>;
+	};
+
+	uarths_pinctrl: uarths-pinmux {
+		pinmux = <K210_FPIOA(4, K210_PCF_UARTHS_RX)>,
+			 <K210_FPIOA(5, K210_PCF_UARTHS_TX)>;
+	};
+
+	gpio_pinctrl: gpio-pinmux {
+		pinmux = <K210_FPIOA(8, K210_PCF_GPIO0)>,
+			 <K210_FPIOA(9, K210_PCF_GPIO1)>,
+			 <K210_FPIOA(10, K210_PCF_GPIO2)>,
+			 <K210_FPIOA(11, K210_PCF_GPIO3)>,
+			 <K210_FPIOA(12, K210_PCF_GPIO4)>,
+			 <K210_FPIOA(13, K210_PCF_GPIO5)>,
+			 <K210_FPIOA(14, K210_PCF_GPIO6)>,
+			 <K210_FPIOA(15, K210_PCF_GPIO7)>;
+	};
+
+	gpiohs_pinctrl: gpiohs-pinmux {
+		pinmux = <K210_FPIOA(16, K210_PCF_GPIOHS0)>,
+			 <K210_FPIOA(17, K210_PCF_GPIOHS1)>,
+			 <K210_FPIOA(21, K210_PCF_GPIOHS5)>,
+			 <K210_FPIOA(22, K210_PCF_GPIOHS6)>,
+			 <K210_FPIOA(23, K210_PCF_GPIOHS7)>,
+			 <K210_FPIOA(24, K210_PCF_GPIOHS8)>,
+			 <K210_FPIOA(25, K210_PCF_GPIOHS9)>,
+			 <K210_FPIOA(32, K210_PCF_GPIOHS16)>,
+			 <K210_FPIOA(33, K210_PCF_GPIOHS17)>,
+			 <K210_FPIOA(34, K210_PCF_GPIOHS18)>,
+			 <K210_FPIOA(35, K210_PCF_GPIOHS19)>;
+	};
+
+	i2s0_pinctrl: i2s0-pinmux {
+		pinmux = <K210_FPIOA(18, K210_PCF_I2S0_SCLK)>,
+			 <K210_FPIOA(19, K210_PCF_I2S0_WS)>,
+			 <K210_FPIOA(20, K210_PCF_I2S0_IN_D0)>;
+	};
+
+	dvp_pinctrl: dvp-pinmux {
+		pinmux = <K210_FPIOA(40, K210_PCF_SCCB_SDA)>,
+			 <K210_FPIOA(41, K210_PCF_SCCB_SCLK)>,
+			 <K210_FPIOA(42, K210_PCF_DVP_RST)>,
+			 <K210_FPIOA(43, K210_PCF_DVP_VSYNC)>,
+			 <K210_FPIOA(44, K210_PCF_DVP_PWDN)>,
+			 <K210_FPIOA(45, K210_PCF_DVP_HSYNC)>,
+			 <K210_FPIOA(46, K210_PCF_DVP_XCLK)>,
+			 <K210_FPIOA(47, K210_PCF_DVP_PCLK)>;
+	};
+
+	spi0_pinctrl: spi0-pinmux {
+		pinmux = <K210_FPIOA(36, K210_PCF_GPIOHS20)>,  /* cs */
+			 <K210_FPIOA(37, K210_PCF_GPIOHS21)>,  /* rst */
+			 <K210_FPIOA(38, K210_PCF_GPIOHS22)>,  /* dc */
+			 <K210_FPIOA(39, K210_PCF_SPI0_SCLK)>; /* wr */
+	};
+
+	spi1_pinctrl: spi1-pinmux {
+		pinmux = <K210_FPIOA(26, K210_PCF_SPI1_D1)>,
+			 <K210_FPIOA(27, K210_PCF_SPI1_SCLK)>,
+			 <K210_FPIOA(28, K210_PCF_SPI1_D0)>,
+			 <K210_FPIOA(29, K210_PCF_GPIOHS13)>; /* cs */
+	};
+
+	i2c1_pinctrl: i2c1-pinmux {
+		pinmux = <K210_FPIOA(30, K210_PCF_I2C1_SCLK)>,
+			 <K210_FPIOA(31, K210_PCF_I2C1_SDA)>;
+	};
+};
+
+&uarths0 {
+	pinctrl-0 = <&uarths_pinctrl>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&gpio0 {
+	pinctrl-0 = <&gpiohs_pinctrl>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&gpio1 {
+	pinctrl-0 = <&gpio_pinctrl>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&i2s0 {
+	#sound-dai-cells = <1>;
+	pinctrl-0 = <&i2s0_pinctrl>;
+	pinctrl-names = "default";
+};
+
+&i2c1 {
+	pinctrl-0 = <&i2c1_pinctrl>;
+	pinctrl-names = "default";
+	clock-frequency = <400000>;
+	status = "okay";
+};
+
+&spi0 {
+	pinctrl-0 = <&spi0_pinctrl>;
+	pinctrl-names = "default";
+	num-cs = <1>;
+	cs-gpios = <&gpio0 20 GPIO_ACTIVE_HIGH>;
+
+	panel@0 {
+		compatible = "sitronix,st7789v";
+		reg = <0>;
+		reset-gpios = <&gpio0 21 GPIO_ACTIVE_LOW>;
+		dc-gpios = <&gpio0 22 GPIO_ACTIVE_HIGH>;
+		spi-max-frequency = <15000000>;
+		status = "disabled";
+	};
+};
+
+&spi1 {
+	pinctrl-0 = <&spi1_pinctrl>;
+	pinctrl-names = "default";
+	num-cs = <1>;
+	cs-gpios = <&gpio0 13 GPIO_ACTIVE_LOW>;
+	status = "okay";
+
+	mmc@0 {
+		compatible = "mmc-spi-slot";
+		reg = <0>;
+		voltage-ranges = <3300 3300>;
+		spi-max-frequency = <25000000>;
+		broken-cd;
+	};
+};
+
+&spi3 {
+	flash@0 {
+		compatible = "jedec,spi-nor";
+		reg = <0>;
+		spi-max-frequency = <50000000>;
+		spi-tx-bus-width = <4>;
+		spi-rx-bus-width = <4>;
+		m25p,fast-read;
+		broken-flash-reset;
+	};
+};
diff --git a/arch/riscv/boot/dts/canaan/sipeed_maixduino.dts b/arch/riscv/boot/dts/canaan/sipeed_maixduino.dts
new file mode 100644
index 000000000..5c05c498e
--- /dev/null
+++ b/arch/riscv/boot/dts/canaan/sipeed_maixduino.dts
@@ -0,0 +1,186 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2019-20 Sean Anderson <seanga2@gmail.com>
+ * Copyright (C) 2020 Western Digital Corporation or its affiliates.
+ */
+
+/dts-v1/;
+
+#include "k210.dtsi"
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/input.h>
+
+/ {
+	model = "SiPeed MAIXDUINO";
+	compatible = "sipeed,maixduino", "canaan,kendryte-k210";
+
+	chosen {
+		bootargs = "earlycon console=ttySIF0";
+		stdout-path = "serial0:115200n8";
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+
+		key-boot {
+			label = "BOOT";
+			linux,code = <BTN_0>;
+			gpios = <&gpio0 0 GPIO_ACTIVE_LOW>;
+		};
+	};
+
+	vcc_3v3: regulator-3v3 {
+		compatible = "regulator-fixed";
+		regulator-name = "3v3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+	};
+};
+
+&fpioa {
+	status = "okay";
+
+	uarths_pinctrl: uarths-pinmux {
+		pinmux = <K210_FPIOA(4, K210_PCF_UARTHS_RX)>, /* Header "0" */
+			 <K210_FPIOA(5, K210_PCF_UARTHS_TX)>; /* Header "1" */
+	};
+
+	gpio_pinctrl: gpio-pinmux {
+		pinmux = <K210_FPIOA(8, K210_PCF_GPIO0)>,
+			 <K210_FPIOA(9, K210_PCF_GPIO1)>;
+	};
+
+	gpiohs_pinctrl: gpiohs-pinmux {
+		pinmux = <K210_FPIOA(16, K210_PCF_GPIOHS0)>,  /* BOOT */
+			 <K210_FPIOA(21, K210_PCF_GPIOHS2)>,  /* Header "2" */
+			 <K210_FPIOA(22, K210_PCF_GPIOHS3)>,  /* Header "3" */
+			 <K210_FPIOA(23, K210_PCF_GPIOHS4)>,  /* Header "4" */
+			 <K210_FPIOA(24, K210_PCF_GPIOHS5)>,  /* Header "5" */
+			 <K210_FPIOA(32, K210_PCF_GPIOHS6)>,  /* Header "6" */
+			 <K210_FPIOA(15, K210_PCF_GPIOHS7)>,  /* Header "7" */
+			 <K210_FPIOA(14, K210_PCF_GPIOHS8)>,  /* Header "8" */
+			 <K210_FPIOA(13, K210_PCF_GPIOHS9)>,  /* Header "9" */
+			 <K210_FPIOA(12, K210_PCF_GPIOHS10)>, /* Header "10" */
+			 <K210_FPIOA(11, K210_PCF_GPIOHS11)>, /* Header "11" */
+			 <K210_FPIOA(10, K210_PCF_GPIOHS12)>, /* Header "12" */
+			 <K210_FPIOA(3,  K210_PCF_GPIOHS13)>; /* Header "13" */
+	};
+
+	i2s0_pinctrl: i2s0-pinmux {
+		pinmux = <K210_FPIOA(18, K210_PCF_I2S0_SCLK)>,
+			 <K210_FPIOA(19, K210_PCF_I2S0_WS)>,
+			 <K210_FPIOA(20, K210_PCF_I2S0_IN_D0)>;
+	};
+
+	spi1_pinctrl: spi1-pinmux {
+		pinmux = <K210_FPIOA(26, K210_PCF_SPI1_D1)>,
+			 <K210_FPIOA(27, K210_PCF_SPI1_SCLK)>,
+			 <K210_FPIOA(28, K210_PCF_SPI1_D0)>,
+			 <K210_FPIOA(29, K210_PCF_GPIO2)>; /* cs */
+	};
+
+	i2c1_pinctrl: i2c1-pinmux {
+		pinmux = <K210_FPIOA(30, K210_PCF_I2C1_SCLK)>, /* Header "scl" */
+			 <K210_FPIOA(31, K210_PCF_I2C1_SDA)>;  /* Header "sda" */
+	};
+
+	i2s1_pinctrl: i2s1-pinmux {
+		pinmux = <K210_FPIOA(33, K210_PCF_I2S1_WS)>,
+			 <K210_FPIOA(34, K210_PCF_I2S1_IN_D0)>,
+			 <K210_FPIOA(35, K210_PCF_I2S1_SCLK)>;
+	};
+
+	spi0_pinctrl: spi0-pinmux {
+		pinmux = <K210_FPIOA(36, K210_PCF_GPIOHS20)>,  /* cs */
+			 <K210_FPIOA(37, K210_PCF_GPIOHS21)>,  /* rst */
+			 <K210_FPIOA(38, K210_PCF_GPIOHS22)>,  /* dc */
+			 <K210_FPIOA(39, K210_PCF_SPI0_SCLK)>; /* wr */
+	};
+
+	dvp_pinctrl: dvp-pinmux {
+		pinmux = <K210_FPIOA(40, K210_PCF_SCCB_SDA)>,
+			 <K210_FPIOA(41, K210_PCF_SCCB_SCLK)>,
+			 <K210_FPIOA(42, K210_PCF_DVP_RST)>,
+			 <K210_FPIOA(43, K210_PCF_DVP_VSYNC)>,
+			 <K210_FPIOA(44, K210_PCF_DVP_PWDN)>,
+			 <K210_FPIOA(45, K210_PCF_DVP_HSYNC)>,
+			 <K210_FPIOA(46, K210_PCF_DVP_XCLK)>,
+			 <K210_FPIOA(47, K210_PCF_DVP_PCLK)>;
+	};
+};
+
+&uarths0 {
+	pinctrl-0 = <&uarths_pinctrl>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&gpio0 {
+	pinctrl-0 = <&gpiohs_pinctrl>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&gpio1 {
+	pinctrl-0 = <&gpio_pinctrl>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&i2s0 {
+	#sound-dai-cells = <1>;
+	pinctrl-0 = <&i2s0_pinctrl>;
+	pinctrl-names = "default";
+};
+
+&i2c1 {
+	pinctrl-0 = <&i2c1_pinctrl>;
+	pinctrl-names = "default";
+	clock-frequency = <400000>;
+	status = "okay";
+};
+
+&spi0 {
+	pinctrl-0 = <&spi0_pinctrl>;
+	pinctrl-names = "default";
+	num-cs = <1>;
+	cs-gpios = <&gpio0 20 GPIO_ACTIVE_HIGH>;
+
+	panel@0 {
+		compatible = "sitronix,st7789v";
+		reg = <0>;
+		reset-gpios = <&gpio0 21 GPIO_ACTIVE_LOW>;
+		dc-gpios = <&gpio0 22 0>;
+		spi-max-frequency = <15000000>;
+		power-supply = <&vcc_3v3>;
+	};
+};
+
+&spi1 {
+	pinctrl-0 = <&spi1_pinctrl>;
+	pinctrl-names = "default";
+	num-cs = <1>;
+	cs-gpios = <&gpio1_0 2 GPIO_ACTIVE_LOW>;
+	status = "okay";
+
+	mmc@0 {
+		compatible = "mmc-spi-slot";
+		reg = <0>;
+		voltage-ranges = <3300 3300>;
+		spi-max-frequency = <25000000>;
+		broken-cd;
+	};
+};
+
+&spi3 {
+	flash@0 {
+		compatible = "jedec,spi-nor";
+		reg = <0>;
+		spi-max-frequency = <50000000>;
+		spi-tx-bus-width = <4>;
+		spi-rx-bus-width = <4>;
+		m25p,fast-read;
+		broken-flash-reset;
+	};
+};
diff --git a/arch/riscv/boot/dts/microchip/Makefile b/arch/riscv/boot/dts/microchip/Makefile
new file mode 100644
index 000000000..7427a2093
--- /dev/null
+++ b/arch/riscv/boot/dts/microchip/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0
+dtb-$(CONFIG_SOC_MICROCHIP_POLARFIRE) += mpfs-icicle-kit.dtb
+dtb-$(CONFIG_SOC_MICROCHIP_POLARFIRE) += mpfs-m100pfsevp.dtb
+dtb-$(CONFIG_SOC_MICROCHIP_POLARFIRE) += mpfs-polarberry.dtb
+dtb-$(CONFIG_SOC_MICROCHIP_POLARFIRE) += mpfs-sev-kit.dtb
+obj-$(CONFIG_BUILTIN_DTB) += $(addsuffix .o, $(dtb-y))
diff --git a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi
new file mode 100644
index 000000000..5d3e5240e
--- /dev/null
+++ b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi
@@ -0,0 +1,70 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/* Copyright (c) 2020-2021 Microchip Technology Inc */
+
+/ {
+	compatible = "microchip,mpfs-icicle-reference-rtlv2210", "microchip,mpfs-icicle-kit",
+		     "microchip,mpfs";
+
+	core_pwm0: pwm@40000000 {
+		compatible = "microchip,corepwm-rtl-v4";
+		reg = <0x0 0x40000000 0x0 0xF0>;
+		microchip,sync-update-mask = /bits/ 32 <0>;
+		#pwm-cells = <3>;
+		clocks = <&fabric_clk3>;
+		status = "disabled";
+	};
+
+	i2c2: i2c@40000200 {
+		compatible = "microchip,corei2c-rtl-v7";
+		reg = <0x0 0x40000200 0x0 0x100>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		clocks = <&fabric_clk3>;
+		interrupt-parent = <&plic>;
+		interrupts = <122>;
+		clock-frequency = <100000>;
+		status = "disabled";
+	};
+
+	fabric_clk3: fabric-clk3 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <50000000>;
+	};
+
+	fabric_clk1: fabric-clk1 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <125000000>;
+	};
+
+	pcie: pcie@3000000000 {
+		compatible = "microchip,pcie-host-1.0";
+		#address-cells = <0x3>;
+		#interrupt-cells = <0x1>;
+		#size-cells = <0x2>;
+		device_type = "pci";
+		reg = <0x30 0x0 0x0 0x8000000>, <0x0 0x43000000 0x0 0x10000>;
+		reg-names = "cfg", "apb";
+		bus-range = <0x0 0x7f>;
+		interrupt-parent = <&plic>;
+		interrupts = <119>;
+		interrupt-map = <0 0 0 1 &pcie_intc 0>,
+				<0 0 0 2 &pcie_intc 1>,
+				<0 0 0 3 &pcie_intc 2>,
+				<0 0 0 4 &pcie_intc 3>;
+		interrupt-map-mask = <0 0 0 7>;
+		clocks = <&fabric_clk1>, <&fabric_clk3>;
+		clock-names = "fic1", "fic3";
+		ranges = <0x3000000 0x0 0x8000000 0x30 0x8000000 0x0 0x80000000>;
+		dma-ranges = <0x02000000 0x0 0x00000000 0x0 0x00000000 0x1 0x00000000>;
+		msi-parent = <&pcie>;
+		msi-controller;
+		status = "disabled";
+		pcie_intc: interrupt-controller {
+			#address-cells = <0>;
+			#interrupt-cells = <1>;
+			interrupt-controller;
+		};
+	};
+};
diff --git a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts
new file mode 100644
index 000000000..8ced67c3b
--- /dev/null
+++ b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts
@@ -0,0 +1,171 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/* Copyright (c) 2020-2021 Microchip Technology Inc */
+
+/dts-v1/;
+
+#include "mpfs.dtsi"
+#include "mpfs-icicle-kit-fabric.dtsi"
+
+/* Clock frequency (in Hz) of the rtcclk */
+#define RTCCLK_FREQ		1000000
+
+/ {
+	model = "Microchip PolarFire-SoC Icicle Kit";
+	compatible = "microchip,mpfs-icicle-reference-rtlv2210", "microchip,mpfs-icicle-kit",
+		     "microchip,mpfs";
+
+	aliases {
+		ethernet0 = &mac1;
+		serial0 = &mmuart0;
+		serial1 = &mmuart1;
+		serial2 = &mmuart2;
+		serial3 = &mmuart3;
+		serial4 = &mmuart4;
+	};
+
+	chosen {
+		stdout-path = "serial1:115200n8";
+	};
+
+	cpus {
+		timebase-frequency = <RTCCLK_FREQ>;
+	};
+
+	ddrc_cache_lo: memory@80000000 {
+		device_type = "memory";
+		reg = <0x0 0x80000000 0x0 0x40000000>;
+		status = "okay";
+	};
+
+	ddrc_cache_hi: memory@1040000000 {
+		device_type = "memory";
+		reg = <0x10 0x40000000 0x0 0x40000000>;
+		status = "okay";
+	};
+
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		hss_payload: region@BFC00000 {
+			reg = <0x0 0xBFC00000 0x0 0x400000>;
+			no-map;
+		};
+	};
+};
+
+&core_pwm0 {
+	status = "okay";
+};
+
+&gpio2 {
+	interrupts = <53>, <53>, <53>, <53>,
+		     <53>, <53>, <53>, <53>,
+		     <53>, <53>, <53>, <53>,
+		     <53>, <53>, <53>, <53>,
+		     <53>, <53>, <53>, <53>,
+		     <53>, <53>, <53>, <53>,
+		     <53>, <53>, <53>, <53>,
+		     <53>, <53>, <53>, <53>;
+	status = "okay";
+};
+
+&i2c0 {
+	status = "okay";
+};
+
+&i2c1 {
+	status = "okay";
+};
+
+&i2c2 {
+	status = "okay";
+};
+
+&mac0 {
+	phy-mode = "sgmii";
+	phy-handle = <&phy0>;
+	status = "okay";
+};
+
+&mac1 {
+	phy-mode = "sgmii";
+	phy-handle = <&phy1>;
+	status = "okay";
+
+	phy1: ethernet-phy@9 {
+		reg = <9>;
+	};
+
+	phy0: ethernet-phy@8 {
+		reg = <8>;
+	};
+};
+
+&mbox {
+	status = "okay";
+};
+
+&mmc {
+	bus-width = <4>;
+	disable-wp;
+	cap-sd-highspeed;
+	cap-mmc-highspeed;
+	mmc-ddr-1_8v;
+	mmc-hs200-1_8v;
+	sd-uhs-sdr12;
+	sd-uhs-sdr25;
+	sd-uhs-sdr50;
+	sd-uhs-sdr104;
+	status = "okay";
+};
+
+&mmuart1 {
+	status = "okay";
+};
+
+&mmuart2 {
+	status = "okay";
+};
+
+&mmuart3 {
+	status = "okay";
+};
+
+&mmuart4 {
+	status = "okay";
+};
+
+&pcie {
+	status = "okay";
+};
+
+&qspi {
+	status = "okay";
+};
+
+&refclk {
+	clock-frequency = <125000000>;
+};
+
+&rtc {
+	status = "okay";
+};
+
+&spi0 {
+	status = "okay";
+};
+
+&spi1 {
+	status = "okay";
+};
+
+&syscontroller {
+	status = "okay";
+};
+
+&usb {
+	status = "okay";
+	dr_mode = "host";
+};
diff --git a/arch/riscv/boot/dts/microchip/mpfs-m100pfs-fabric.dtsi b/arch/riscv/boot/dts/microchip/mpfs-m100pfs-fabric.dtsi
new file mode 100644
index 000000000..7b9ee13b6
--- /dev/null
+++ b/arch/riscv/boot/dts/microchip/mpfs-m100pfs-fabric.dtsi
@@ -0,0 +1,45 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/* Copyright (c) 2022 Microchip Technology Inc */
+
+/ {
+	fabric_clk3: fabric-clk3 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <62500000>;
+	};
+
+	fabric_clk1: fabric-clk1 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <125000000>;
+	};
+
+	pcie: pcie@2000000000 {
+		compatible = "microchip,pcie-host-1.0";
+		#address-cells = <0x3>;
+		#interrupt-cells = <0x1>;
+		#size-cells = <0x2>;
+		device_type = "pci";
+		reg = <0x20 0x0 0x0 0x8000000>, <0x0 0x43000000 0x0 0x10000>;
+		reg-names = "cfg", "apb";
+		bus-range = <0x0 0x7f>;
+		interrupt-parent = <&plic>;
+		interrupts = <119>;
+		interrupt-map = <0 0 0 1 &pcie_intc 0>,
+				<0 0 0 2 &pcie_intc 1>,
+				<0 0 0 3 &pcie_intc 2>,
+				<0 0 0 4 &pcie_intc 3>;
+		interrupt-map-mask = <0 0 0 7>;
+		clocks = <&fabric_clk1>, <&fabric_clk1>, <&fabric_clk3>;
+		clock-names = "fic0", "fic1", "fic3";
+		ranges = <0x3000000 0x0 0x8000000 0x20 0x8000000 0x0 0x80000000>;
+		msi-parent = <&pcie>;
+		msi-controller;
+		status = "disabled";
+		pcie_intc: interrupt-controller {
+			#address-cells = <0>;
+			#interrupt-cells = <1>;
+			interrupt-controller;
+		};
+	};
+};
diff --git a/arch/riscv/boot/dts/microchip/mpfs-m100pfsevp.dts b/arch/riscv/boot/dts/microchip/mpfs-m100pfsevp.dts
new file mode 100644
index 000000000..184cb36a1
--- /dev/null
+++ b/arch/riscv/boot/dts/microchip/mpfs-m100pfsevp.dts
@@ -0,0 +1,179 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Original all-in-one devicetree:
+ * Copyright (C) 2021-2022 - Wolfgang Grandegger <wg@aries-embedded.de>
+ * Rewritten to use includes:
+ * Copyright (C) 2022 - Conor Dooley <conor.dooley@microchip.com>
+ */
+/dts-v1/;
+
+#include "mpfs.dtsi"
+#include "mpfs-m100pfs-fabric.dtsi"
+
+/* Clock frequency (in Hz) of the rtcclk */
+#define MTIMER_FREQ	1000000
+
+/ {
+	model = "Aries Embedded M100PFEVPS";
+	compatible = "aries,m100pfsevp", "microchip,mpfs";
+
+	aliases {
+		ethernet0 = &mac0;
+		ethernet1 = &mac1;
+		serial0 = &mmuart0;
+		serial1 = &mmuart1;
+		serial2 = &mmuart2;
+		serial3 = &mmuart3;
+		serial4 = &mmuart4;
+		gpio0 = &gpio0;
+		gpio1 = &gpio2;
+	};
+
+	chosen {
+		stdout-path = "serial1:115200n8";
+	};
+
+	cpus {
+		timebase-frequency = <MTIMER_FREQ>;
+	};
+
+	ddrc_cache_lo: memory@80000000 {
+		device_type = "memory";
+		reg = <0x0 0x80000000 0x0 0x40000000>;
+	};
+	ddrc_cache_hi: memory@1040000000 {
+		device_type = "memory";
+		reg = <0x10 0x40000000 0x0 0x40000000>;
+	};
+};
+
+&can0 {
+	status = "okay";
+};
+
+&i2c0 {
+	status = "okay";
+};
+
+&i2c1 {
+	status = "okay";
+};
+
+&gpio0 {
+	interrupts = <13>, <14>, <15>, <16>,
+		     <17>, <18>, <19>, <20>,
+		     <21>, <22>, <23>, <24>,
+		     <25>, <26>;
+	ngpios = <14>;
+	status = "okay";
+
+	pmic-irq-hog {
+		gpio-hog;
+		gpios = <13 0>;
+		input;
+	};
+
+	/* Set to low for eMMC, high for SD-card */
+	mmc-sel-hog {
+		gpio-hog;
+		gpios = <12 0>;
+		output-high;
+	};
+};
+
+&gpio2 {
+	interrupts = <13>, <14>, <15>, <16>,
+		     <17>, <18>, <19>, <20>,
+		     <21>, <22>, <23>, <24>,
+		     <25>, <26>, <27>, <28>,
+		     <29>, <30>, <31>, <32>,
+		     <33>, <34>, <35>, <36>,
+		     <37>, <38>, <39>, <40>,
+		     <41>, <42>, <43>, <44>;
+	status = "okay";
+};
+
+&mac0 {
+	status = "okay";
+	phy-mode = "gmii";
+	phy-handle = <&phy0>;
+	phy0: ethernet-phy@0 {
+		reg = <0>;
+	};
+};
+
+&mac1 {
+	status = "okay";
+	phy-mode = "gmii";
+	phy-handle = <&phy1>;
+	phy1: ethernet-phy@0 {
+		reg = <0>;
+	};
+};
+
+&mbox {
+	status = "okay";
+};
+
+&mmc {
+	max-frequency = <50000000>;
+	bus-width = <4>;
+	cap-mmc-highspeed;
+	cap-sd-highspeed;
+	no-1-8-v;
+	sd-uhs-sdr12;
+	sd-uhs-sdr25;
+	sd-uhs-sdr50;
+	sd-uhs-sdr104;
+	disable-wp;
+	status = "okay";
+};
+
+&mmuart1 {
+	status = "okay";
+};
+
+&mmuart2 {
+	status = "okay";
+};
+
+&mmuart3 {
+	status = "okay";
+};
+
+&mmuart4 {
+	status = "okay";
+};
+
+&pcie {
+	status = "okay";
+};
+
+&qspi {
+	status = "okay";
+};
+
+&refclk {
+	clock-frequency = <125000000>;
+};
+
+&rtc {
+	status = "okay";
+};
+
+&spi0 {
+	status = "okay";
+};
+
+&spi1 {
+	status = "okay";
+};
+
+&syscontroller {
+	status = "okay";
+};
+
+&usb {
+	status = "okay";
+	dr_mode = "host";
+};
diff --git a/arch/riscv/boot/dts/microchip/mpfs-polarberry-fabric.dtsi b/arch/riscv/boot/dts/microchip/mpfs-polarberry-fabric.dtsi
new file mode 100644
index 000000000..67303bc0e
--- /dev/null
+++ b/arch/riscv/boot/dts/microchip/mpfs-polarberry-fabric.dtsi
@@ -0,0 +1,45 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/* Copyright (c) 2020-2022 Microchip Technology Inc */
+
+/ {
+	fabric_clk3: fabric-clk3 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <62500000>;
+	};
+
+	fabric_clk1: fabric-clk1 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <125000000>;
+	};
+
+	pcie: pcie@2000000000 {
+		compatible = "microchip,pcie-host-1.0";
+		#address-cells = <0x3>;
+		#interrupt-cells = <0x1>;
+		#size-cells = <0x2>;
+		device_type = "pci";
+		reg = <0x20 0x0 0x0 0x8000000>, <0x0 0x43000000 0x0 0x10000>;
+		reg-names = "cfg", "apb";
+		bus-range = <0x0 0x7f>;
+		interrupt-parent = <&plic>;
+		interrupts = <119>;
+		interrupt-map = <0 0 0 1 &pcie_intc 0>,
+				<0 0 0 2 &pcie_intc 1>,
+				<0 0 0 3 &pcie_intc 2>,
+				<0 0 0 4 &pcie_intc 3>;
+		interrupt-map-mask = <0 0 0 7>;
+		clocks = <&fabric_clk1>, <&fabric_clk1>, <&fabric_clk3>;
+		clock-names = "fic0", "fic1", "fic3";
+		ranges = <0x3000000 0x0 0x8000000 0x20 0x8000000 0x0 0x80000000>;
+		msi-parent = <&pcie>;
+		msi-controller;
+		status = "disabled";
+		pcie_intc: interrupt-controller {
+			#address-cells = <0>;
+			#interrupt-cells = <1>;
+			interrupt-controller;
+		};
+	};
+};
diff --git a/arch/riscv/boot/dts/microchip/mpfs-polarberry.dts b/arch/riscv/boot/dts/microchip/mpfs-polarberry.dts
new file mode 100644
index 000000000..c87cc2d8f
--- /dev/null
+++ b/arch/riscv/boot/dts/microchip/mpfs-polarberry.dts
@@ -0,0 +1,96 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/* Copyright (c) 2020-2022 Microchip Technology Inc */
+
+/dts-v1/;
+
+#include "mpfs.dtsi"
+#include "mpfs-polarberry-fabric.dtsi"
+
+/* Clock frequency (in Hz) of the rtcclk */
+#define MTIMER_FREQ	1000000
+
+/ {
+	model = "Sundance PolarBerry";
+	compatible = "sundance,polarberry", "microchip,mpfs";
+
+	aliases {
+		ethernet0 = &mac1;
+		serial0 = &mmuart0;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	cpus {
+		timebase-frequency = <MTIMER_FREQ>;
+	};
+
+	ddrc_cache_lo: memory@80000000 {
+		device_type = "memory";
+		reg = <0x0 0x80000000 0x0 0x2e000000>;
+	};
+
+	ddrc_cache_hi: memory@1000000000 {
+		device_type = "memory";
+		reg = <0x10 0x00000000 0x0 0xC0000000>;
+	};
+};
+
+/*
+ * phy0 is connected to mac0, but the port itself is on the (optional) carrier
+ * board.
+ */
+&mac0 {
+	phy-mode = "sgmii";
+	phy-handle = <&phy0>;
+	status = "disabled";
+};
+
+&mac1 {
+	phy-mode = "sgmii";
+	phy-handle = <&phy1>;
+	status = "okay";
+
+	phy1: ethernet-phy@5 {
+		reg = <5>;
+	};
+
+	phy0: ethernet-phy@4 {
+		reg = <4>;
+	};
+};
+
+&mbox {
+	status = "okay";
+};
+
+&mmc {
+	bus-width = <4>;
+	disable-wp;
+	cap-sd-highspeed;
+	cap-mmc-highspeed;
+	mmc-ddr-1_8v;
+	mmc-hs200-1_8v;
+	sd-uhs-sdr12;
+	sd-uhs-sdr25;
+	sd-uhs-sdr50;
+	sd-uhs-sdr104;
+	status = "okay";
+};
+
+&mmuart0 {
+	status = "okay";
+};
+
+&refclk {
+	clock-frequency = <125000000>;
+};
+
+&rtc {
+	status = "okay";
+};
+
+&syscontroller {
+	status = "okay";
+};
diff --git a/arch/riscv/boot/dts/microchip/mpfs-sev-kit-fabric.dtsi b/arch/riscv/boot/dts/microchip/mpfs-sev-kit-fabric.dtsi
new file mode 100644
index 000000000..39a77df48
--- /dev/null
+++ b/arch/riscv/boot/dts/microchip/mpfs-sev-kit-fabric.dtsi
@@ -0,0 +1,16 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/* Copyright (c) 2022 Microchip Technology Inc */
+
+/ {
+	fabric_clk3: fabric-clk3 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <0>;
+	};
+
+	fabric_clk1: fabric-clk1 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <125000000>;
+	};
+};
diff --git a/arch/riscv/boot/dts/microchip/mpfs-sev-kit.dts b/arch/riscv/boot/dts/microchip/mpfs-sev-kit.dts
new file mode 100644
index 000000000..013cb666c
--- /dev/null
+++ b/arch/riscv/boot/dts/microchip/mpfs-sev-kit.dts
@@ -0,0 +1,145 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/* Copyright (c) 2022 Microchip Technology Inc */
+
+/dts-v1/;
+
+#include "mpfs.dtsi"
+#include "mpfs-sev-kit-fabric.dtsi"
+
+/* Clock frequency (in Hz) of the rtcclk */
+#define MTIMER_FREQ		1000000
+
+/ {
+	#address-cells = <2>;
+	#size-cells = <2>;
+	model = "Microchip PolarFire-SoC SEV Kit";
+	compatible = "microchip,mpfs-sev-kit", "microchip,mpfs";
+
+	aliases {
+		ethernet0 = &mac1;
+		serial0 = &mmuart0;
+		serial1 = &mmuart1;
+		serial2 = &mmuart2;
+		serial3 = &mmuart3;
+		serial4 = &mmuart4;
+	};
+
+	chosen {
+		stdout-path = "serial1:115200n8";
+	};
+
+	cpus {
+		timebase-frequency = <MTIMER_FREQ>;
+	};
+
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		fabricbuf0ddrc: buffer@80000000 {
+			compatible = "shared-dma-pool";
+			reg = <0x0 0x80000000 0x0 0x2000000>;
+		};
+
+		fabricbuf1ddrnc: buffer@c4000000 {
+			compatible = "shared-dma-pool";
+			reg = <0x0 0xc4000000 0x0 0x4000000>;
+		};
+
+		fabricbuf2ddrncwcb: buffer@d4000000 {
+			compatible = "shared-dma-pool";
+			reg = <0x0 0xd4000000 0x0 0x4000000>;
+		};
+	};
+
+	ddrc_cache: memory@1000000000 {
+		device_type = "memory";
+		reg = <0x10 0x0 0x0 0x76000000>;
+	};
+};
+
+&i2c0 {
+	status = "okay";
+};
+
+&gpio2 {
+	interrupts = <53>, <53>, <53>, <53>,
+		     <53>, <53>, <53>, <53>,
+		     <53>, <53>, <53>, <53>,
+		     <53>, <53>, <53>, <53>,
+		     <53>, <53>, <53>, <53>,
+		     <53>, <53>, <53>, <53>,
+		     <53>, <53>, <53>, <53>,
+		     <53>, <53>, <53>, <53>;
+	status = "okay";
+};
+
+&mac0 {
+	status = "okay";
+	phy-mode = "sgmii";
+	phy-handle = <&phy0>;
+	phy1: ethernet-phy@9 {
+		reg = <9>;
+	};
+	phy0: ethernet-phy@8 {
+		reg = <8>;
+	};
+};
+
+&mac1 {
+	status = "okay";
+	phy-mode = "sgmii";
+	phy-handle = <&phy1>;
+};
+
+&mbox {
+	status = "okay";
+};
+
+&mmc {
+	status = "okay";
+	bus-width = <4>;
+	disable-wp;
+	cap-sd-highspeed;
+	cap-mmc-highspeed;
+	mmc-ddr-1_8v;
+	mmc-hs200-1_8v;
+	sd-uhs-sdr12;
+	sd-uhs-sdr25;
+	sd-uhs-sdr50;
+	sd-uhs-sdr104;
+};
+
+&mmuart1 {
+	status = "okay";
+};
+
+&mmuart2 {
+	status = "okay";
+};
+
+&mmuart3 {
+	status = "okay";
+};
+
+&mmuart4 {
+	status = "okay";
+};
+
+&refclk {
+	clock-frequency = <125000000>;
+};
+
+&rtc {
+	status = "okay";
+};
+
+&syscontroller {
+	status = "okay";
+};
+
+&usb {
+	status = "okay";
+	dr_mode = "otg";
+};
diff --git a/arch/riscv/boot/dts/microchip/mpfs.dtsi b/arch/riscv/boot/dts/microchip/mpfs.dtsi
new file mode 100644
index 000000000..8f463399a
--- /dev/null
+++ b/arch/riscv/boot/dts/microchip/mpfs.dtsi
@@ -0,0 +1,476 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/* Copyright (c) 2020-2021 Microchip Technology Inc */
+
+/dts-v1/;
+#include "dt-bindings/clock/microchip,mpfs-clock.h"
+
+/ {
+	#address-cells = <2>;
+	#size-cells = <2>;
+	model = "Microchip PolarFire SoC";
+	compatible = "microchip,mpfs";
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu0: cpu@0 {
+			compatible = "sifive,e51", "sifive,rocket0", "riscv";
+			device_type = "cpu";
+			i-cache-block-size = <64>;
+			i-cache-sets = <128>;
+			i-cache-size = <16384>;
+			reg = <0>;
+			riscv,isa = "rv64imac";
+			clocks = <&clkcfg CLK_CPU>;
+			status = "disabled";
+
+			cpu0_intc: interrupt-controller {
+				#interrupt-cells = <1>;
+				compatible = "riscv,cpu-intc";
+				interrupt-controller;
+			};
+		};
+
+		cpu1: cpu@1 {
+			compatible = "sifive,u54-mc", "sifive,rocket0", "riscv";
+			d-cache-block-size = <64>;
+			d-cache-sets = <64>;
+			d-cache-size = <32768>;
+			d-tlb-sets = <1>;
+			d-tlb-size = <32>;
+			device_type = "cpu";
+			i-cache-block-size = <64>;
+			i-cache-sets = <64>;
+			i-cache-size = <32768>;
+			i-tlb-sets = <1>;
+			i-tlb-size = <32>;
+			mmu-type = "riscv,sv39";
+			reg = <1>;
+			riscv,isa = "rv64imafdc";
+			clocks = <&clkcfg CLK_CPU>;
+			tlb-split;
+			next-level-cache = <&cctrllr>;
+			status = "okay";
+
+			cpu1_intc: interrupt-controller {
+				#interrupt-cells = <1>;
+				compatible = "riscv,cpu-intc";
+				interrupt-controller;
+			};
+		};
+
+		cpu2: cpu@2 {
+			compatible = "sifive,u54-mc", "sifive,rocket0", "riscv";
+			d-cache-block-size = <64>;
+			d-cache-sets = <64>;
+			d-cache-size = <32768>;
+			d-tlb-sets = <1>;
+			d-tlb-size = <32>;
+			device_type = "cpu";
+			i-cache-block-size = <64>;
+			i-cache-sets = <64>;
+			i-cache-size = <32768>;
+			i-tlb-sets = <1>;
+			i-tlb-size = <32>;
+			mmu-type = "riscv,sv39";
+			reg = <2>;
+			riscv,isa = "rv64imafdc";
+			clocks = <&clkcfg CLK_CPU>;
+			tlb-split;
+			next-level-cache = <&cctrllr>;
+			status = "okay";
+
+			cpu2_intc: interrupt-controller {
+				#interrupt-cells = <1>;
+				compatible = "riscv,cpu-intc";
+				interrupt-controller;
+			};
+		};
+
+		cpu3: cpu@3 {
+			compatible = "sifive,u54-mc", "sifive,rocket0", "riscv";
+			d-cache-block-size = <64>;
+			d-cache-sets = <64>;
+			d-cache-size = <32768>;
+			d-tlb-sets = <1>;
+			d-tlb-size = <32>;
+			device_type = "cpu";
+			i-cache-block-size = <64>;
+			i-cache-sets = <64>;
+			i-cache-size = <32768>;
+			i-tlb-sets = <1>;
+			i-tlb-size = <32>;
+			mmu-type = "riscv,sv39";
+			reg = <3>;
+			riscv,isa = "rv64imafdc";
+			clocks = <&clkcfg CLK_CPU>;
+			tlb-split;
+			next-level-cache = <&cctrllr>;
+			status = "okay";
+
+			cpu3_intc: interrupt-controller {
+				#interrupt-cells = <1>;
+				compatible = "riscv,cpu-intc";
+				interrupt-controller;
+			};
+		};
+
+		cpu4: cpu@4 {
+			compatible = "sifive,u54-mc", "sifive,rocket0", "riscv";
+			d-cache-block-size = <64>;
+			d-cache-sets = <64>;
+			d-cache-size = <32768>;
+			d-tlb-sets = <1>;
+			d-tlb-size = <32>;
+			device_type = "cpu";
+			i-cache-block-size = <64>;
+			i-cache-sets = <64>;
+			i-cache-size = <32768>;
+			i-tlb-sets = <1>;
+			i-tlb-size = <32>;
+			mmu-type = "riscv,sv39";
+			reg = <4>;
+			riscv,isa = "rv64imafdc";
+			clocks = <&clkcfg CLK_CPU>;
+			tlb-split;
+			next-level-cache = <&cctrllr>;
+			status = "okay";
+			cpu4_intc: interrupt-controller {
+				#interrupt-cells = <1>;
+				compatible = "riscv,cpu-intc";
+				interrupt-controller;
+			};
+		};
+
+		cpu-map {
+			cluster0 {
+				core0 {
+					cpu = <&cpu0>;
+				};
+
+				core1 {
+					cpu = <&cpu1>;
+				};
+
+				core2 {
+					cpu = <&cpu2>;
+				};
+
+				core3 {
+					cpu = <&cpu3>;
+				};
+
+				core4 {
+					cpu = <&cpu4>;
+				};
+			};
+		};
+	};
+
+	refclk: mssrefclk {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+	};
+
+	syscontroller: syscontroller {
+		compatible = "microchip,mpfs-sys-controller";
+		mboxes = <&mbox 0>;
+	};
+
+	soc {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		compatible = "simple-bus";
+		ranges;
+
+		cctrllr: cache-controller@2010000 {
+			compatible = "microchip,mpfs-ccache", "sifive,fu540-c000-ccache", "cache";
+			reg = <0x0 0x2010000 0x0 0x1000>;
+			cache-block-size = <64>;
+			cache-level = <2>;
+			cache-sets = <1024>;
+			cache-size = <2097152>;
+			cache-unified;
+			interrupt-parent = <&plic>;
+			interrupts = <1>, <3>, <4>, <2>;
+		};
+
+		clint: clint@2000000 {
+			compatible = "sifive,fu540-c000-clint", "sifive,clint0";
+			reg = <0x0 0x2000000 0x0 0xC000>;
+			interrupts-extended = <&cpu0_intc 3>, <&cpu0_intc 7>,
+					      <&cpu1_intc 3>, <&cpu1_intc 7>,
+					      <&cpu2_intc 3>, <&cpu2_intc 7>,
+					      <&cpu3_intc 3>, <&cpu3_intc 7>,
+					      <&cpu4_intc 3>, <&cpu4_intc 7>;
+		};
+
+		plic: interrupt-controller@c000000 {
+			compatible = "sifive,fu540-c000-plic", "sifive,plic-1.0.0";
+			reg = <0x0 0xc000000 0x0 0x4000000>;
+			#address-cells = <0>;
+			#interrupt-cells = <1>;
+			interrupt-controller;
+			interrupts-extended = <&cpu0_intc 11>,
+					      <&cpu1_intc 11>, <&cpu1_intc 9>,
+					      <&cpu2_intc 11>, <&cpu2_intc 9>,
+					      <&cpu3_intc 11>, <&cpu3_intc 9>,
+					      <&cpu4_intc 11>, <&cpu4_intc 9>;
+			riscv,ndev = <186>;
+		};
+
+		pdma: dma-controller@3000000 {
+			compatible = "sifive,fu540-c000-pdma", "sifive,pdma0";
+			reg = <0x0 0x3000000 0x0 0x8000>;
+			interrupt-parent = <&plic>;
+			interrupts = <5 6>, <7 8>, <9 10>, <11 12>;
+			dma-channels = <4>;
+			#dma-cells = <1>;
+		};
+
+		clkcfg: clkcfg@20002000 {
+			compatible = "microchip,mpfs-clkcfg";
+			reg = <0x0 0x20002000 0x0 0x1000>, <0x0 0x3E001000 0x0 0x1000>;
+			clocks = <&refclk>;
+			#clock-cells = <1>;
+		};
+
+		mmuart0: serial@20000000 {
+			compatible = "ns16550a";
+			reg = <0x0 0x20000000 0x0 0x400>;
+			reg-io-width = <4>;
+			reg-shift = <2>;
+			interrupt-parent = <&plic>;
+			interrupts = <90>;
+			current-speed = <115200>;
+			clocks = <&clkcfg CLK_MMUART0>;
+			status = "disabled"; /* Reserved for the HSS */
+		};
+
+		mmuart1: serial@20100000 {
+			compatible = "ns16550a";
+			reg = <0x0 0x20100000 0x0 0x400>;
+			reg-io-width = <4>;
+			reg-shift = <2>;
+			interrupt-parent = <&plic>;
+			interrupts = <91>;
+			current-speed = <115200>;
+			clocks = <&clkcfg CLK_MMUART1>;
+			status = "disabled";
+		};
+
+		mmuart2: serial@20102000 {
+			compatible = "ns16550a";
+			reg = <0x0 0x20102000 0x0 0x400>;
+			reg-io-width = <4>;
+			reg-shift = <2>;
+			interrupt-parent = <&plic>;
+			interrupts = <92>;
+			current-speed = <115200>;
+			clocks = <&clkcfg CLK_MMUART2>;
+			status = "disabled";
+		};
+
+		mmuart3: serial@20104000 {
+			compatible = "ns16550a";
+			reg = <0x0 0x20104000 0x0 0x400>;
+			reg-io-width = <4>;
+			reg-shift = <2>;
+			interrupt-parent = <&plic>;
+			interrupts = <93>;
+			current-speed = <115200>;
+			clocks = <&clkcfg CLK_MMUART3>;
+			status = "disabled";
+		};
+
+		mmuart4: serial@20106000 {
+			compatible = "ns16550a";
+			reg = <0x0 0x20106000 0x0 0x400>;
+			reg-io-width = <4>;
+			reg-shift = <2>;
+			interrupt-parent = <&plic>;
+			interrupts = <94>;
+			clocks = <&clkcfg CLK_MMUART4>;
+			current-speed = <115200>;
+			status = "disabled";
+		};
+
+		/* Common node entry for emmc/sd */
+		mmc: mmc@20008000 {
+			compatible = "microchip,mpfs-sd4hc", "cdns,sd4hc";
+			reg = <0x0 0x20008000 0x0 0x1000>;
+			interrupt-parent = <&plic>;
+			interrupts = <88>;
+			clocks = <&clkcfg CLK_MMC>;
+			max-frequency = <200000000>;
+			status = "disabled";
+		};
+
+		spi0: spi@20108000 {
+			compatible = "microchip,mpfs-spi";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x0 0x20108000 0x0 0x1000>;
+			interrupt-parent = <&plic>;
+			interrupts = <54>;
+			clocks = <&clkcfg CLK_SPI0>;
+			status = "disabled";
+		};
+
+		spi1: spi@20109000 {
+			compatible = "microchip,mpfs-spi";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x0 0x20109000 0x0 0x1000>;
+			interrupt-parent = <&plic>;
+			interrupts = <55>;
+			clocks = <&clkcfg CLK_SPI1>;
+			status = "disabled";
+		};
+
+		qspi: spi@21000000 {
+			compatible = "microchip,mpfs-qspi", "microchip,coreqspi-rtl-v2";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x0 0x21000000 0x0 0x1000>;
+			interrupt-parent = <&plic>;
+			interrupts = <85>;
+			clocks = <&clkcfg CLK_QSPI>;
+			status = "disabled";
+		};
+
+		i2c0: i2c@2010a000 {
+			compatible = "microchip,mpfs-i2c", "microchip,corei2c-rtl-v7";
+			reg = <0x0 0x2010a000 0x0 0x1000>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			interrupt-parent = <&plic>;
+			interrupts = <58>;
+			clocks = <&clkcfg CLK_I2C0>;
+			clock-frequency = <100000>;
+			status = "disabled";
+		};
+
+		i2c1: i2c@2010b000 {
+			compatible = "microchip,mpfs-i2c", "microchip,corei2c-rtl-v7";
+			reg = <0x0 0x2010b000 0x0 0x1000>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			interrupt-parent = <&plic>;
+			interrupts = <61>;
+			clocks = <&clkcfg CLK_I2C1>;
+			clock-frequency = <100000>;
+			status = "disabled";
+		};
+
+		can0: can@2010c000 {
+			compatible = "microchip,mpfs-can";
+			reg = <0x0 0x2010c000 0x0 0x1000>;
+			clocks = <&clkcfg CLK_CAN0>;
+			interrupt-parent = <&plic>;
+			interrupts = <56>;
+			status = "disabled";
+		};
+
+		can1: can@2010d000 {
+			compatible = "microchip,mpfs-can";
+			reg = <0x0 0x2010d000 0x0 0x1000>;
+			clocks = <&clkcfg CLK_CAN1>;
+			interrupt-parent = <&plic>;
+			interrupts = <57>;
+			status = "disabled";
+		};
+
+		mac0: ethernet@20110000 {
+			compatible = "cdns,macb";
+			reg = <0x0 0x20110000 0x0 0x2000>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			interrupt-parent = <&plic>;
+			interrupts = <64>, <65>, <66>, <67>, <68>, <69>;
+			local-mac-address = [00 00 00 00 00 00];
+			clocks = <&clkcfg CLK_MAC0>, <&clkcfg CLK_AHB>;
+			clock-names = "pclk", "hclk";
+			status = "disabled";
+		};
+
+		mac1: ethernet@20112000 {
+			compatible = "cdns,macb";
+			reg = <0x0 0x20112000 0x0 0x2000>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			interrupt-parent = <&plic>;
+			interrupts = <70>, <71>, <72>, <73>, <74>, <75>;
+			local-mac-address = [00 00 00 00 00 00];
+			clocks = <&clkcfg CLK_MAC1>, <&clkcfg CLK_AHB>;
+			clock-names = "pclk", "hclk";
+			status = "disabled";
+		};
+
+		gpio0: gpio@20120000 {
+			compatible = "microchip,mpfs-gpio";
+			reg = <0x0 0x20120000 0x0 0x1000>;
+			interrupt-parent = <&plic>;
+			interrupt-controller;
+			#interrupt-cells = <1>;
+			clocks = <&clkcfg CLK_GPIO0>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			status = "disabled";
+		};
+
+		gpio1: gpio@20121000 {
+			compatible = "microchip,mpfs-gpio";
+			reg = <0x0 0x20121000 0x0 0x1000>;
+			interrupt-parent = <&plic>;
+			interrupt-controller;
+			#interrupt-cells = <1>;
+			clocks = <&clkcfg CLK_GPIO1>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			status = "disabled";
+		};
+
+		gpio2: gpio@20122000 {
+			compatible = "microchip,mpfs-gpio";
+			reg = <0x0 0x20122000 0x0 0x1000>;
+			interrupt-parent = <&plic>;
+			interrupt-controller;
+			#interrupt-cells = <1>;
+			clocks = <&clkcfg CLK_GPIO2>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			status = "disabled";
+		};
+
+		rtc: rtc@20124000 {
+			compatible = "microchip,mpfs-rtc";
+			reg = <0x0 0x20124000 0x0 0x1000>;
+			interrupt-parent = <&plic>;
+			interrupts = <80>, <81>;
+			clocks = <&clkcfg CLK_RTC>, <&clkcfg CLK_RTCREF>;
+			clock-names = "rtc", "rtcref";
+			status = "disabled";
+		};
+
+		usb: usb@20201000 {
+			compatible = "microchip,mpfs-musb";
+			reg = <0x0 0x20201000 0x0 0x1000>;
+			interrupt-parent = <&plic>;
+			interrupts = <86>, <87>;
+			clocks = <&clkcfg CLK_USB>;
+			interrupt-names = "dma","mc";
+			status = "disabled";
+		};
+
+		mbox: mailbox@37020000 {
+			compatible = "microchip,mpfs-mailbox";
+			reg = <0x0 0x37020000 0x0 0x1000>, <0x0 0x2000318C 0x0 0x40>;
+			interrupt-parent = <&plic>;
+			interrupts = <96>;
+			#mbox-cells = <1>;
+			status = "disabled";
+		};
+	};
+};
diff --git a/arch/riscv/boot/dts/sifive/Makefile b/arch/riscv/boot/dts/sifive/Makefile
new file mode 100644
index 000000000..d90e4eb0a
--- /dev/null
+++ b/arch/riscv/boot/dts/sifive/Makefile
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
+dtb-$(CONFIG_SOC_SIFIVE) += hifive-unleashed-a00.dtb \
+			    hifive-unmatched-a00.dtb
+obj-$(CONFIG_BUILTIN_DTB) += $(addsuffix .o, $(dtb-y))
diff --git a/arch/riscv/boot/dts/sifive/fu540-c000.dtsi b/arch/riscv/boot/dts/sifive/fu540-c000.dtsi
new file mode 100644
index 000000000..24bba83be
--- /dev/null
+++ b/arch/riscv/boot/dts/sifive/fu540-c000.dtsi
@@ -0,0 +1,313 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/* Copyright (c) 2018-2019 SiFive, Inc */
+
+/dts-v1/;
+
+#include <dt-bindings/clock/sifive-fu540-prci.h>
+
+/ {
+	#address-cells = <2>;
+	#size-cells = <2>;
+	compatible = "sifive,fu540-c000", "sifive,fu540";
+
+	aliases {
+		serial0 = &uart0;
+		serial1 = &uart1;
+		ethernet0 = &eth0;
+	};
+
+	chosen {
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		cpu0: cpu@0 {
+			compatible = "sifive,e51", "sifive,rocket0", "riscv";
+			device_type = "cpu";
+			i-cache-block-size = <64>;
+			i-cache-sets = <128>;
+			i-cache-size = <16384>;
+			reg = <0>;
+			riscv,isa = "rv64imac";
+			status = "disabled";
+			cpu0_intc: interrupt-controller {
+				#interrupt-cells = <1>;
+				compatible = "riscv,cpu-intc";
+				interrupt-controller;
+			};
+		};
+		cpu1: cpu@1 {
+			compatible = "sifive,u54-mc", "sifive,rocket0", "riscv";
+			d-cache-block-size = <64>;
+			d-cache-sets = <64>;
+			d-cache-size = <32768>;
+			d-tlb-sets = <1>;
+			d-tlb-size = <32>;
+			device_type = "cpu";
+			i-cache-block-size = <64>;
+			i-cache-sets = <64>;
+			i-cache-size = <32768>;
+			i-tlb-sets = <1>;
+			i-tlb-size = <32>;
+			mmu-type = "riscv,sv39";
+			reg = <1>;
+			riscv,isa = "rv64imafdc";
+			tlb-split;
+			next-level-cache = <&l2cache>;
+			cpu1_intc: interrupt-controller {
+				#interrupt-cells = <1>;
+				compatible = "riscv,cpu-intc";
+				interrupt-controller;
+			};
+		};
+		cpu2: cpu@2 {
+			compatible = "sifive,u54-mc", "sifive,rocket0", "riscv";
+			d-cache-block-size = <64>;
+			d-cache-sets = <64>;
+			d-cache-size = <32768>;
+			d-tlb-sets = <1>;
+			d-tlb-size = <32>;
+			device_type = "cpu";
+			i-cache-block-size = <64>;
+			i-cache-sets = <64>;
+			i-cache-size = <32768>;
+			i-tlb-sets = <1>;
+			i-tlb-size = <32>;
+			mmu-type = "riscv,sv39";
+			reg = <2>;
+			riscv,isa = "rv64imafdc";
+			tlb-split;
+			next-level-cache = <&l2cache>;
+			cpu2_intc: interrupt-controller {
+				#interrupt-cells = <1>;
+				compatible = "riscv,cpu-intc";
+				interrupt-controller;
+			};
+		};
+		cpu3: cpu@3 {
+			compatible = "sifive,u54-mc", "sifive,rocket0", "riscv";
+			d-cache-block-size = <64>;
+			d-cache-sets = <64>;
+			d-cache-size = <32768>;
+			d-tlb-sets = <1>;
+			d-tlb-size = <32>;
+			device_type = "cpu";
+			i-cache-block-size = <64>;
+			i-cache-sets = <64>;
+			i-cache-size = <32768>;
+			i-tlb-sets = <1>;
+			i-tlb-size = <32>;
+			mmu-type = "riscv,sv39";
+			reg = <3>;
+			riscv,isa = "rv64imafdc";
+			tlb-split;
+			next-level-cache = <&l2cache>;
+			cpu3_intc: interrupt-controller {
+				#interrupt-cells = <1>;
+				compatible = "riscv,cpu-intc";
+				interrupt-controller;
+			};
+		};
+		cpu4: cpu@4 {
+			compatible = "sifive,u54-mc", "sifive,rocket0", "riscv";
+			d-cache-block-size = <64>;
+			d-cache-sets = <64>;
+			d-cache-size = <32768>;
+			d-tlb-sets = <1>;
+			d-tlb-size = <32>;
+			device_type = "cpu";
+			i-cache-block-size = <64>;
+			i-cache-sets = <64>;
+			i-cache-size = <32768>;
+			i-tlb-sets = <1>;
+			i-tlb-size = <32>;
+			mmu-type = "riscv,sv39";
+			reg = <4>;
+			riscv,isa = "rv64imafdc";
+			tlb-split;
+			next-level-cache = <&l2cache>;
+			cpu4_intc: interrupt-controller {
+				#interrupt-cells = <1>;
+				compatible = "riscv,cpu-intc";
+				interrupt-controller;
+			};
+		};
+
+		cpu-map {
+			cluster0 {
+				core0 {
+					cpu = <&cpu0>;
+				};
+
+				core1 {
+					cpu = <&cpu1>;
+				};
+
+				core2 {
+					cpu = <&cpu2>;
+				};
+
+				core3 {
+					cpu = <&cpu3>;
+				};
+
+				core4 {
+					cpu = <&cpu4>;
+				};
+			};
+		};
+	};
+	soc {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		compatible = "simple-bus";
+		ranges;
+		plic0: interrupt-controller@c000000 {
+			compatible = "sifive,fu540-c000-plic", "sifive,plic-1.0.0";
+			reg = <0x0 0xc000000 0x0 0x4000000>;
+			#address-cells = <0>;
+			#interrupt-cells = <1>;
+			interrupt-controller;
+			interrupts-extended =
+				<&cpu0_intc 0xffffffff>,
+				<&cpu1_intc 0xffffffff>, <&cpu1_intc 9>,
+				<&cpu2_intc 0xffffffff>, <&cpu2_intc 9>,
+				<&cpu3_intc 0xffffffff>, <&cpu3_intc 9>,
+				<&cpu4_intc 0xffffffff>, <&cpu4_intc 9>;
+			riscv,ndev = <53>;
+		};
+		prci: clock-controller@10000000 {
+			compatible = "sifive,fu540-c000-prci";
+			reg = <0x0 0x10000000 0x0 0x1000>;
+			clocks = <&hfclk>, <&rtcclk>;
+			#clock-cells = <1>;
+		};
+		uart0: serial@10010000 {
+			compatible = "sifive,fu540-c000-uart", "sifive,uart0";
+			reg = <0x0 0x10010000 0x0 0x1000>;
+			interrupt-parent = <&plic0>;
+			interrupts = <4>;
+			clocks = <&prci FU540_PRCI_CLK_TLCLK>;
+			status = "disabled";
+		};
+		dma: dma-controller@3000000 {
+			compatible = "sifive,fu540-c000-pdma", "sifive,pdma0";
+			reg = <0x0 0x3000000 0x0 0x8000>;
+			interrupt-parent = <&plic0>;
+			interrupts = <23>, <24>, <25>, <26>, <27>, <28>, <29>,
+				     <30>;
+			dma-channels = <4>;
+			#dma-cells = <1>;
+		};
+		uart1: serial@10011000 {
+			compatible = "sifive,fu540-c000-uart", "sifive,uart0";
+			reg = <0x0 0x10011000 0x0 0x1000>;
+			interrupt-parent = <&plic0>;
+			interrupts = <5>;
+			clocks = <&prci FU540_PRCI_CLK_TLCLK>;
+			status = "disabled";
+		};
+		i2c0: i2c@10030000 {
+			compatible = "sifive,fu540-c000-i2c", "sifive,i2c0";
+			reg = <0x0 0x10030000 0x0 0x1000>;
+			interrupt-parent = <&plic0>;
+			interrupts = <50>;
+			clocks = <&prci FU540_PRCI_CLK_TLCLK>;
+			reg-shift = <2>;
+			reg-io-width = <1>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+		qspi0: spi@10040000 {
+			compatible = "sifive,fu540-c000-spi", "sifive,spi0";
+			reg = <0x0 0x10040000 0x0 0x1000>,
+			      <0x0 0x20000000 0x0 0x10000000>;
+			interrupt-parent = <&plic0>;
+			interrupts = <51>;
+			clocks = <&prci FU540_PRCI_CLK_TLCLK>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+		qspi1: spi@10041000 {
+			compatible = "sifive,fu540-c000-spi", "sifive,spi0";
+			reg = <0x0 0x10041000 0x0 0x1000>,
+			      <0x0 0x30000000 0x0 0x10000000>;
+			interrupt-parent = <&plic0>;
+			interrupts = <52>;
+			clocks = <&prci FU540_PRCI_CLK_TLCLK>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+		qspi2: spi@10050000 {
+			compatible = "sifive,fu540-c000-spi", "sifive,spi0";
+			reg = <0x0 0x10050000 0x0 0x1000>;
+			interrupt-parent = <&plic0>;
+			interrupts = <6>;
+			clocks = <&prci FU540_PRCI_CLK_TLCLK>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+		eth0: ethernet@10090000 {
+			compatible = "sifive,fu540-c000-gem";
+			interrupt-parent = <&plic0>;
+			interrupts = <53>;
+			reg = <0x0 0x10090000 0x0 0x2000>,
+			      <0x0 0x100a0000 0x0 0x1000>;
+			local-mac-address = [00 00 00 00 00 00];
+			clock-names = "pclk", "hclk";
+			clocks = <&prci FU540_PRCI_CLK_GEMGXLPLL>,
+				 <&prci FU540_PRCI_CLK_GEMGXLPLL>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+		pwm0: pwm@10020000 {
+			compatible = "sifive,fu540-c000-pwm", "sifive,pwm0";
+			reg = <0x0 0x10020000 0x0 0x1000>;
+			interrupt-parent = <&plic0>;
+			interrupts = <42>, <43>, <44>, <45>;
+			clocks = <&prci FU540_PRCI_CLK_TLCLK>;
+			#pwm-cells = <3>;
+			status = "disabled";
+		};
+		pwm1: pwm@10021000 {
+			compatible = "sifive,fu540-c000-pwm", "sifive,pwm0";
+			reg = <0x0 0x10021000 0x0 0x1000>;
+			interrupt-parent = <&plic0>;
+			interrupts = <46>, <47>, <48>, <49>;
+			clocks = <&prci FU540_PRCI_CLK_TLCLK>;
+			#pwm-cells = <3>;
+			status = "disabled";
+		};
+		l2cache: cache-controller@2010000 {
+			compatible = "sifive,fu540-c000-ccache", "cache";
+			cache-block-size = <64>;
+			cache-level = <2>;
+			cache-sets = <1024>;
+			cache-size = <2097152>;
+			cache-unified;
+			interrupt-parent = <&plic0>;
+			interrupts = <1>, <2>, <3>;
+			reg = <0x0 0x2010000 0x0 0x1000>;
+		};
+		gpio: gpio@10060000 {
+			compatible = "sifive,fu540-c000-gpio", "sifive,gpio0";
+			interrupt-parent = <&plic0>;
+			interrupts = <7>, <8>, <9>, <10>, <11>, <12>, <13>,
+				     <14>, <15>, <16>, <17>, <18>, <19>, <20>,
+				     <21>, <22>;
+			reg = <0x0 0x10060000 0x0 0x1000>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			interrupt-controller;
+			#interrupt-cells = <2>;
+			clocks = <&prci FU540_PRCI_CLK_TLCLK>;
+			status = "disabled";
+		};
+	};
+};
diff --git a/arch/riscv/boot/dts/sifive/fu740-c000.dtsi b/arch/riscv/boot/dts/sifive/fu740-c000.dtsi
new file mode 100644
index 000000000..5235fd1c9
--- /dev/null
+++ b/arch/riscv/boot/dts/sifive/fu740-c000.dtsi
@@ -0,0 +1,350 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/* Copyright (c) 2020 SiFive, Inc */
+
+/dts-v1/;
+
+#include <dt-bindings/clock/sifive-fu740-prci.h>
+
+/ {
+	#address-cells = <2>;
+	#size-cells = <2>;
+	compatible = "sifive,fu740-c000", "sifive,fu740";
+
+	aliases {
+		serial0 = &uart0;
+		serial1 = &uart1;
+		ethernet0 = &eth0;
+	};
+
+	chosen {
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		cpu0: cpu@0 {
+			compatible = "sifive,bullet0", "riscv";
+			device_type = "cpu";
+			i-cache-block-size = <64>;
+			i-cache-sets = <128>;
+			i-cache-size = <16384>;
+			next-level-cache = <&ccache>;
+			reg = <0x0>;
+			riscv,isa = "rv64imac";
+			status = "disabled";
+			cpu0_intc: interrupt-controller {
+				#interrupt-cells = <1>;
+				compatible = "riscv,cpu-intc";
+				interrupt-controller;
+			};
+		};
+		cpu1: cpu@1 {
+			compatible = "sifive,bullet0", "riscv";
+			d-cache-block-size = <64>;
+			d-cache-sets = <64>;
+			d-cache-size = <32768>;
+			d-tlb-sets = <1>;
+			d-tlb-size = <40>;
+			device_type = "cpu";
+			i-cache-block-size = <64>;
+			i-cache-sets = <128>;
+			i-cache-size = <32768>;
+			i-tlb-sets = <1>;
+			i-tlb-size = <40>;
+			mmu-type = "riscv,sv39";
+			next-level-cache = <&ccache>;
+			reg = <0x1>;
+			riscv,isa = "rv64imafdc";
+			tlb-split;
+			cpu1_intc: interrupt-controller {
+				#interrupt-cells = <1>;
+				compatible = "riscv,cpu-intc";
+				interrupt-controller;
+			};
+		};
+		cpu2: cpu@2 {
+			compatible = "sifive,bullet0", "riscv";
+			d-cache-block-size = <64>;
+			d-cache-sets = <64>;
+			d-cache-size = <32768>;
+			d-tlb-sets = <1>;
+			d-tlb-size = <40>;
+			device_type = "cpu";
+			i-cache-block-size = <64>;
+			i-cache-sets = <128>;
+			i-cache-size = <32768>;
+			i-tlb-sets = <1>;
+			i-tlb-size = <40>;
+			mmu-type = "riscv,sv39";
+			next-level-cache = <&ccache>;
+			reg = <0x2>;
+			riscv,isa = "rv64imafdc";
+			tlb-split;
+			cpu2_intc: interrupt-controller {
+				#interrupt-cells = <1>;
+				compatible = "riscv,cpu-intc";
+				interrupt-controller;
+			};
+		};
+		cpu3: cpu@3 {
+			compatible = "sifive,bullet0", "riscv";
+			d-cache-block-size = <64>;
+			d-cache-sets = <64>;
+			d-cache-size = <32768>;
+			d-tlb-sets = <1>;
+			d-tlb-size = <40>;
+			device_type = "cpu";
+			i-cache-block-size = <64>;
+			i-cache-sets = <128>;
+			i-cache-size = <32768>;
+			i-tlb-sets = <1>;
+			i-tlb-size = <40>;
+			mmu-type = "riscv,sv39";
+			next-level-cache = <&ccache>;
+			reg = <0x3>;
+			riscv,isa = "rv64imafdc";
+			tlb-split;
+			cpu3_intc: interrupt-controller {
+				#interrupt-cells = <1>;
+				compatible = "riscv,cpu-intc";
+				interrupt-controller;
+			};
+		};
+		cpu4: cpu@4 {
+			compatible = "sifive,bullet0", "riscv";
+			d-cache-block-size = <64>;
+			d-cache-sets = <64>;
+			d-cache-size = <32768>;
+			d-tlb-sets = <1>;
+			d-tlb-size = <40>;
+			device_type = "cpu";
+			i-cache-block-size = <64>;
+			i-cache-sets = <128>;
+			i-cache-size = <32768>;
+			i-tlb-sets = <1>;
+			i-tlb-size = <40>;
+			mmu-type = "riscv,sv39";
+			next-level-cache = <&ccache>;
+			reg = <0x4>;
+			riscv,isa = "rv64imafdc";
+			tlb-split;
+			cpu4_intc: interrupt-controller {
+				#interrupt-cells = <1>;
+				compatible = "riscv,cpu-intc";
+				interrupt-controller;
+			};
+		};
+
+		cpu-map {
+			cluster0 {
+				core0 {
+					cpu = <&cpu0>;
+				};
+
+				core1 {
+					cpu = <&cpu1>;
+				};
+
+				core2 {
+					cpu = <&cpu2>;
+				};
+
+				core3 {
+					cpu = <&cpu3>;
+				};
+
+				core4 {
+					cpu = <&cpu4>;
+				};
+			};
+		};
+	};
+	soc {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		compatible = "simple-bus";
+		ranges;
+		plic0: interrupt-controller@c000000 {
+			#interrupt-cells = <1>;
+			#address-cells = <0>;
+			compatible = "sifive,fu540-c000-plic", "sifive,plic-1.0.0";
+			reg = <0x0 0xc000000 0x0 0x4000000>;
+			riscv,ndev = <69>;
+			interrupt-controller;
+			interrupts-extended =
+				<&cpu0_intc 0xffffffff>,
+				<&cpu1_intc 0xffffffff>, <&cpu1_intc 9>,
+				<&cpu2_intc 0xffffffff>, <&cpu2_intc 9>,
+				<&cpu3_intc 0xffffffff>, <&cpu3_intc 9>,
+				<&cpu4_intc 0xffffffff>, <&cpu4_intc 9>;
+		};
+		prci: clock-controller@10000000 {
+			compatible = "sifive,fu740-c000-prci";
+			reg = <0x0 0x10000000 0x0 0x1000>;
+			clocks = <&hfclk>, <&rtcclk>;
+			#clock-cells = <1>;
+			#reset-cells = <1>;
+		};
+		uart0: serial@10010000 {
+			compatible = "sifive,fu740-c000-uart", "sifive,uart0";
+			reg = <0x0 0x10010000 0x0 0x1000>;
+			interrupt-parent = <&plic0>;
+			interrupts = <39>;
+			clocks = <&prci FU740_PRCI_CLK_PCLK>;
+			status = "disabled";
+		};
+		uart1: serial@10011000 {
+			compatible = "sifive,fu740-c000-uart", "sifive,uart0";
+			reg = <0x0 0x10011000 0x0 0x1000>;
+			interrupt-parent = <&plic0>;
+			interrupts = <40>;
+			clocks = <&prci FU740_PRCI_CLK_PCLK>;
+			status = "disabled";
+		};
+		i2c0: i2c@10030000 {
+			compatible = "sifive,fu740-c000-i2c", "sifive,i2c0";
+			reg = <0x0 0x10030000 0x0 0x1000>;
+			interrupt-parent = <&plic0>;
+			interrupts = <52>;
+			clocks = <&prci FU740_PRCI_CLK_PCLK>;
+			reg-shift = <2>;
+			reg-io-width = <1>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+		i2c1: i2c@10031000 {
+			compatible = "sifive,fu740-c000-i2c", "sifive,i2c0";
+			reg = <0x0 0x10031000 0x0 0x1000>;
+			interrupt-parent = <&plic0>;
+			interrupts = <53>;
+			clocks = <&prci FU740_PRCI_CLK_PCLK>;
+			reg-shift = <2>;
+			reg-io-width = <1>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+		qspi0: spi@10040000 {
+			compatible = "sifive,fu740-c000-spi", "sifive,spi0";
+			reg = <0x0 0x10040000 0x0 0x1000>,
+			      <0x0 0x20000000 0x0 0x10000000>;
+			interrupt-parent = <&plic0>;
+			interrupts = <41>;
+			clocks = <&prci FU740_PRCI_CLK_PCLK>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+		qspi1: spi@10041000 {
+			compatible = "sifive,fu740-c000-spi", "sifive,spi0";
+			reg = <0x0 0x10041000 0x0 0x1000>,
+			      <0x0 0x30000000 0x0 0x10000000>;
+			interrupt-parent = <&plic0>;
+			interrupts = <42>;
+			clocks = <&prci FU740_PRCI_CLK_PCLK>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+		spi0: spi@10050000 {
+			compatible = "sifive,fu740-c000-spi", "sifive,spi0";
+			reg = <0x0 0x10050000 0x0 0x1000>;
+			interrupt-parent = <&plic0>;
+			interrupts = <43>;
+			clocks = <&prci FU740_PRCI_CLK_PCLK>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+		eth0: ethernet@10090000 {
+			compatible = "sifive,fu540-c000-gem";
+			interrupt-parent = <&plic0>;
+			interrupts = <55>;
+			reg = <0x0 0x10090000 0x0 0x2000>,
+			      <0x0 0x100a0000 0x0 0x1000>;
+			local-mac-address = [00 00 00 00 00 00];
+			clock-names = "pclk", "hclk";
+			clocks = <&prci FU740_PRCI_CLK_GEMGXLPLL>,
+				 <&prci FU740_PRCI_CLK_GEMGXLPLL>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+		pwm0: pwm@10020000 {
+			compatible = "sifive,fu740-c000-pwm", "sifive,pwm0";
+			reg = <0x0 0x10020000 0x0 0x1000>;
+			interrupt-parent = <&plic0>;
+			interrupts = <44>, <45>, <46>, <47>;
+			clocks = <&prci FU740_PRCI_CLK_PCLK>;
+			#pwm-cells = <3>;
+			status = "disabled";
+		};
+		pwm1: pwm@10021000 {
+			compatible = "sifive,fu740-c000-pwm", "sifive,pwm0";
+			reg = <0x0 0x10021000 0x0 0x1000>;
+			interrupt-parent = <&plic0>;
+			interrupts = <48>, <49>, <50>, <51>;
+			clocks = <&prci FU740_PRCI_CLK_PCLK>;
+			#pwm-cells = <3>;
+			status = "disabled";
+		};
+		ccache: cache-controller@2010000 {
+			compatible = "sifive,fu740-c000-ccache", "cache";
+			cache-block-size = <64>;
+			cache-level = <2>;
+			cache-sets = <2048>;
+			cache-size = <2097152>;
+			cache-unified;
+			interrupt-parent = <&plic0>;
+			interrupts = <19>, <21>, <22>, <20>;
+			reg = <0x0 0x2010000 0x0 0x1000>;
+		};
+		gpio: gpio@10060000 {
+			compatible = "sifive,fu740-c000-gpio", "sifive,gpio0";
+			interrupt-parent = <&plic0>;
+			interrupts = <23>, <24>, <25>, <26>, <27>, <28>, <29>,
+				     <30>, <31>, <32>, <33>, <34>, <35>, <36>,
+				     <37>, <38>;
+			reg = <0x0 0x10060000 0x0 0x1000>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			interrupt-controller;
+			#interrupt-cells = <2>;
+			clocks = <&prci FU740_PRCI_CLK_PCLK>;
+			status = "disabled";
+		};
+		pcie@e00000000 {
+			compatible = "sifive,fu740-pcie";
+			#address-cells = <3>;
+			#size-cells = <2>;
+			#interrupt-cells = <1>;
+			reg = <0xe 0x00000000 0x0 0x80000000>,
+			      <0xd 0xf0000000 0x0 0x10000000>,
+			      <0x0 0x100d0000 0x0 0x1000>;
+			reg-names = "dbi", "config", "mgmt";
+			device_type = "pci";
+			dma-coherent;
+			bus-range = <0x0 0xff>;
+			ranges = <0x81000000  0x0 0x60080000  0x0 0x60080000 0x0 0x10000>,      /* I/O */
+				 <0x82000000  0x0 0x60090000  0x0 0x60090000 0x0 0xff70000>,    /* mem */
+				 <0x82000000  0x0 0x70000000  0x0 0x70000000 0x0 0x10000000>,    /* mem */
+				 <0xc3000000 0x20 0x00000000 0x20 0x00000000 0x20 0x00000000>;  /* mem prefetchable */
+			num-lanes = <0x8>;
+			interrupts = <56>, <57>, <58>, <59>, <60>, <61>, <62>, <63>, <64>;
+			interrupt-names = "msi", "inta", "intb", "intc", "intd";
+			interrupt-parent = <&plic0>;
+			interrupt-map-mask = <0x0 0x0 0x0 0x7>;
+			interrupt-map = <0x0 0x0 0x0 0x1 &plic0 57>,
+					<0x0 0x0 0x0 0x2 &plic0 58>,
+					<0x0 0x0 0x0 0x3 &plic0 59>,
+					<0x0 0x0 0x0 0x4 &plic0 60>;
+			clock-names = "pcie_aux";
+			clocks = <&prci FU740_PRCI_CLK_PCIE_AUX>;
+			pwren-gpios = <&gpio 5 0>;
+			reset-gpios = <&gpio 8 0>;
+			resets = <&prci 4>;
+			status = "okay";
+		};
+	};
+};
diff --git a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts
new file mode 100644
index 000000000..900a50526
--- /dev/null
+++ b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts
@@ -0,0 +1,141 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/* Copyright (c) 2018-2019 SiFive, Inc */
+
+#include "fu540-c000.dtsi"
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/leds/common.h>
+#include <dt-bindings/pwm/pwm.h>
+
+/* Clock frequency (in Hz) of the PCB crystal for rtcclk */
+#define RTCCLK_FREQ		1000000
+
+/ {
+	model = "SiFive HiFive Unleashed A00";
+	compatible = "sifive,hifive-unleashed-a00", "sifive,fu540-c000",
+		     "sifive,fu540";
+
+	chosen {
+		stdout-path = "serial0";
+	};
+
+	cpus {
+		timebase-frequency = <RTCCLK_FREQ>;
+	};
+
+	memory@80000000 {
+		device_type = "memory";
+		reg = <0x0 0x80000000 0x2 0x00000000>;
+	};
+
+	hfclk: hfclk {
+		#clock-cells = <0>;
+		compatible = "fixed-clock";
+		clock-frequency = <33333333>;
+		clock-output-names = "hfclk";
+	};
+
+	rtcclk: rtcclk {
+		#clock-cells = <0>;
+		compatible = "fixed-clock";
+		clock-frequency = <RTCCLK_FREQ>;
+		clock-output-names = "rtcclk";
+	};
+	gpio-restart {
+		compatible = "gpio-restart";
+		gpios = <&gpio 10 GPIO_ACTIVE_LOW>;
+	};
+
+	led-controller {
+		compatible = "pwm-leds";
+
+		led-d1 {
+			pwms = <&pwm0 0 7812500 PWM_POLARITY_INVERTED>;
+			active-low;
+			color = <LED_COLOR_ID_GREEN>;
+			max-brightness = <255>;
+			label = "d1";
+		};
+
+		led-d2 {
+			pwms = <&pwm0 1 7812500 PWM_POLARITY_INVERTED>;
+			active-low;
+			color = <LED_COLOR_ID_GREEN>;
+			max-brightness = <255>;
+			label = "d2";
+		};
+
+		led-d3 {
+			pwms = <&pwm0 2 7812500 PWM_POLARITY_INVERTED>;
+			active-low;
+			color = <LED_COLOR_ID_GREEN>;
+			max-brightness = <255>;
+			label = "d3";
+		};
+
+		led-d4 {
+			pwms = <&pwm0 3 7812500 PWM_POLARITY_INVERTED>;
+			active-low;
+			color = <LED_COLOR_ID_GREEN>;
+			max-brightness = <255>;
+			label = "d4";
+		};
+	};
+};
+
+&uart0 {
+	status = "okay";
+};
+
+&uart1 {
+	status = "okay";
+};
+
+&i2c0 {
+	status = "okay";
+};
+
+&qspi0 {
+	status = "okay";
+	flash@0 {
+		compatible = "jedec,spi-nor";
+		reg = <0>;
+		spi-max-frequency = <50000000>;
+		m25p,fast-read;
+		spi-tx-bus-width = <4>;
+		spi-rx-bus-width = <4>;
+	};
+};
+
+&qspi2 {
+	status = "okay";
+	mmc@0 {
+		compatible = "mmc-spi-slot";
+		reg = <0>;
+		spi-max-frequency = <20000000>;
+		voltage-ranges = <3300 3300>;
+		disable-wp;
+		gpios = <&gpio 11 GPIO_ACTIVE_LOW>;
+	};
+};
+
+&eth0 {
+	status = "okay";
+	phy-mode = "gmii";
+	phy-handle = <&phy0>;
+	phy0: ethernet-phy@0 {
+		compatible = "ethernet-phy-id0007.0771";
+		reg = <0>;
+	};
+};
+
+&pwm0 {
+	status = "okay";
+};
+
+&pwm1 {
+	status = "okay";
+};
+
+&gpio {
+	status = "okay";
+};
diff --git a/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts
new file mode 100644
index 000000000..07387f9c1
--- /dev/null
+++ b/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts
@@ -0,0 +1,288 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/* Copyright (c) 2020 SiFive, Inc */
+
+#include "fu740-c000.dtsi"
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/interrupt-controller/irq.h>
+#include <dt-bindings/leds/common.h>
+#include <dt-bindings/pwm/pwm.h>
+
+/* Clock frequency (in Hz) of the PCB crystal for rtcclk */
+#define RTCCLK_FREQ		1000000
+
+/ {
+	model = "SiFive HiFive Unmatched A00";
+	compatible = "sifive,hifive-unmatched-a00", "sifive,fu740-c000",
+		     "sifive,fu740";
+
+	chosen {
+		stdout-path = "serial0";
+	};
+
+	cpus {
+		timebase-frequency = <RTCCLK_FREQ>;
+	};
+
+	memory@80000000 {
+		device_type = "memory";
+		reg = <0x0 0x80000000 0x4 0x00000000>;
+	};
+
+	hfclk: hfclk {
+		#clock-cells = <0>;
+		compatible = "fixed-clock";
+		clock-frequency = <26000000>;
+		clock-output-names = "hfclk";
+	};
+
+	rtcclk: rtcclk {
+		#clock-cells = <0>;
+		compatible = "fixed-clock";
+		clock-frequency = <RTCCLK_FREQ>;
+		clock-output-names = "rtcclk";
+	};
+
+	gpio-poweroff {
+		compatible = "gpio-poweroff";
+		gpios = <&gpio 2 GPIO_ACTIVE_LOW>;
+	};
+
+	led-controller-1 {
+		compatible = "pwm-leds";
+
+		led-d12 {
+			pwms = <&pwm0 0 7812500 PWM_POLARITY_INVERTED>;
+			active-low;
+			color = <LED_COLOR_ID_GREEN>;
+			max-brightness = <255>;
+			label = "d12";
+		};
+	};
+
+	led-controller-2 {
+		compatible = "pwm-leds-multicolor";
+
+		multi-led {
+			color = <LED_COLOR_ID_RGB>;
+			max-brightness = <255>;
+			label = "d2";
+
+			led-red {
+				pwms = <&pwm0 2 7812500 PWM_POLARITY_INVERTED>;
+				active-low;
+				color = <LED_COLOR_ID_RED>;
+			};
+
+			led-green {
+				pwms = <&pwm0 1 7812500 PWM_POLARITY_INVERTED>;
+				active-low;
+				color = <LED_COLOR_ID_GREEN>;
+			};
+
+			led-blue {
+				pwms = <&pwm0 3 7812500 PWM_POLARITY_INVERTED>;
+				active-low;
+				color = <LED_COLOR_ID_BLUE>;
+			};
+		};
+	};
+};
+
+&uart0 {
+	status = "okay";
+};
+
+&uart1 {
+	status = "okay";
+};
+
+&i2c0 {
+	status = "okay";
+
+	temperature-sensor@4c {
+		compatible = "ti,tmp451";
+		reg = <0x4c>;
+		vcc-supply = <&vdd_bpro>;
+		interrupt-parent = <&gpio>;
+		interrupts = <6 IRQ_TYPE_LEVEL_LOW>;
+	};
+
+	eeprom@54 {
+		compatible = "microchip,24c02", "atmel,24c02";
+		reg = <0x54>;
+		vcc-supply = <&vdd_bpro>;
+		label = "board-id";
+		pagesize = <16>;
+		read-only;
+		size = <256>;
+	};
+
+	pmic@58 {
+		compatible = "dlg,da9063";
+		reg = <0x58>;
+		interrupt-parent = <&gpio>;
+		interrupts = <1 IRQ_TYPE_LEVEL_LOW>;
+		interrupt-controller;
+
+		onkey {
+			compatible = "dlg,da9063-onkey";
+		};
+
+		rtc {
+			compatible = "dlg,da9063-rtc";
+		};
+
+		watchdog {
+			compatible = "dlg,da9063-watchdog";
+		};
+
+		regulators {
+			vdd_bcore: bcores-merged {
+				regulator-min-microvolt = <1050000>;
+				regulator-max-microvolt = <1050000>;
+				regulator-min-microamp = <4800000>;
+				regulator-max-microamp = <4800000>;
+				regulator-always-on;
+			};
+
+			vdd_bpro: bpro {
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-min-microamp = <2400000>;
+				regulator-max-microamp = <2400000>;
+				regulator-always-on;
+			};
+
+			vdd_bperi: bperi {
+				regulator-min-microvolt = <1060000>;
+				regulator-max-microvolt = <1060000>;
+				regulator-min-microamp = <1500000>;
+				regulator-max-microamp = <1500000>;
+				regulator-always-on;
+			};
+
+			vdd_bmem_bio: bmem-bio-merged {
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <1200000>;
+				regulator-min-microamp = <3000000>;
+				regulator-max-microamp = <3000000>;
+				regulator-always-on;
+			};
+
+			vdd_ldo1: ldo1 {
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-always-on;
+			};
+
+			vdd_ldo2: ldo2 {
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-always-on;
+			};
+
+			vdd_ldo3: ldo3 {
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+
+			vdd_ldo4: ldo4 {
+				regulator-min-microvolt = <2500000>;
+				regulator-max-microvolt = <2500000>;
+				regulator-always-on;
+			};
+
+			vdd_ldo5: ldo5 {
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+
+			vdd_ldo6: ldo6 {
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-always-on;
+			};
+
+			vdd_ldo7: ldo7 {
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+
+			vdd_ldo8: ldo8 {
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+
+			vdd_ld09: ldo9 {
+				regulator-min-microvolt = <1050000>;
+				regulator-max-microvolt = <1050000>;
+				regulator-always-on;
+			};
+
+			vdd_ldo10: ldo10 {
+				regulator-min-microvolt = <1000000>;
+				regulator-max-microvolt = <1000000>;
+				regulator-always-on;
+			};
+
+			vdd_ldo11: ldo11 {
+				regulator-min-microvolt = <2500000>;
+				regulator-max-microvolt = <2500000>;
+				regulator-always-on;
+			};
+		};
+	};
+};
+
+&qspi0 {
+	status = "okay";
+	flash@0 {
+		compatible = "jedec,spi-nor";
+		reg = <0>;
+		spi-max-frequency = <50000000>;
+		m25p,fast-read;
+		spi-tx-bus-width = <4>;
+		spi-rx-bus-width = <4>;
+	};
+};
+
+&spi0 {
+	status = "okay";
+	mmc@0 {
+		compatible = "mmc-spi-slot";
+		reg = <0>;
+		spi-max-frequency = <20000000>;
+		voltage-ranges = <3300 3300>;
+		disable-wp;
+		gpios = <&gpio 15 GPIO_ACTIVE_LOW>;
+	};
+};
+
+&eth0 {
+	status = "okay";
+	phy-mode = "gmii";
+	phy-handle = <&phy0>;
+	phy0: ethernet-phy@0 {
+		reg = <0>;
+	};
+};
+
+&pwm0 {
+	status = "okay";
+};
+
+&pwm1 {
+	status = "okay";
+};
+
+&gpio {
+	status = "okay";
+	gpio-line-names = "J29.1", "PMICNTB", "PMICSHDN", "J8.1", "J8.3",
+		"PCIe_PWREN", "THERM", "UBRDG_RSTN", "PCIe_PERSTN",
+		"ULPI_RSTN", "J8.2", "UHUB_RSTN", "GEMGXL_RST", "J8.4",
+		"EN_VDD_SD", "SD_CD";
+};
diff --git a/arch/riscv/boot/dts/starfive/Makefile b/arch/riscv/boot/dts/starfive/Makefile
new file mode 100644
index 000000000..0ea1bc15a
--- /dev/null
+++ b/arch/riscv/boot/dts/starfive/Makefile
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0
+dtb-$(CONFIG_SOC_STARFIVE) += jh7100-beaglev-starlight.dtb
diff --git a/arch/riscv/boot/dts/starfive/jh7100-beaglev-starlight.dts b/arch/riscv/boot/dts/starfive/jh7100-beaglev-starlight.dts
new file mode 100644
index 000000000..f7a230110
--- /dev/null
+++ b/arch/riscv/boot/dts/starfive/jh7100-beaglev-starlight.dts
@@ -0,0 +1,164 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/*
+ * Copyright (C) 2021 StarFive Technology Co., Ltd.
+ * Copyright (C) 2021 Emil Renner Berthing <kernel@esmil.dk>
+ */
+
+/dts-v1/;
+#include "jh7100.dtsi"
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/leds/common.h>
+#include <dt-bindings/pinctrl/pinctrl-starfive-jh7100.h>
+
+/ {
+	model = "BeagleV Starlight Beta";
+	compatible = "beagle,beaglev-starlight-jh7100-r0", "starfive,jh7100";
+
+	aliases {
+		serial0 = &uart3;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	cpus {
+		timebase-frequency = <6250000>;
+	};
+
+	memory@80000000 {
+		device_type = "memory";
+		reg = <0x0 0x80000000 0x2 0x0>;
+	};
+
+	leds {
+		compatible = "gpio-leds";
+
+		led-ack {
+			gpios = <&gpio 43 GPIO_ACTIVE_HIGH>;
+			color = <LED_COLOR_ID_GREEN>;
+			function = LED_FUNCTION_HEARTBEAT;
+			linux,default-trigger = "heartbeat";
+			label = "ack";
+		};
+	};
+};
+
+&gpio {
+	i2c0_pins: i2c0-0 {
+		i2c-pins {
+			pinmux = <GPIOMUX(62, GPO_LOW,
+				  GPO_I2C0_PAD_SCK_OEN,
+				  GPI_I2C0_PAD_SCK_IN)>,
+				 <GPIOMUX(61, GPO_LOW,
+				  GPO_I2C0_PAD_SDA_OEN,
+				  GPI_I2C0_PAD_SDA_IN)>;
+			bias-disable; /* external pull-up */
+			input-enable;
+			input-schmitt-enable;
+		};
+	};
+
+	i2c1_pins: i2c1-0 {
+		i2c-pins {
+			pinmux = <GPIOMUX(47, GPO_LOW,
+				  GPO_I2C1_PAD_SCK_OEN,
+				  GPI_I2C1_PAD_SCK_IN)>,
+				 <GPIOMUX(48, GPO_LOW,
+				  GPO_I2C1_PAD_SDA_OEN,
+				  GPI_I2C1_PAD_SDA_IN)>;
+			bias-pull-up;
+			input-enable;
+			input-schmitt-enable;
+		};
+	};
+
+	i2c2_pins: i2c2-0 {
+		i2c-pins {
+			pinmux = <GPIOMUX(60, GPO_LOW,
+				  GPO_I2C2_PAD_SCK_OEN,
+				  GPI_I2C2_PAD_SCK_IN)>,
+				 <GPIOMUX(59, GPO_LOW,
+				  GPO_I2C2_PAD_SDA_OEN,
+				  GPI_I2C2_PAD_SDA_IN)>;
+			bias-disable; /* external pull-up */
+			input-enable;
+			input-schmitt-enable;
+		};
+	};
+
+	uart3_pins: uart3-0 {
+		rx-pins {
+			pinmux = <GPIOMUX(13, GPO_LOW, GPO_DISABLE,
+				  GPI_UART3_PAD_SIN)>;
+			bias-pull-up;
+			drive-strength = <14>;
+			input-enable;
+			input-schmitt-enable;
+			slew-rate = <0>;
+		};
+		tx-pins {
+			pinmux = <GPIOMUX(14, GPO_UART3_PAD_SOUT,
+				  GPO_ENABLE, GPI_NONE)>;
+			bias-disable;
+			drive-strength = <35>;
+			input-disable;
+			input-schmitt-disable;
+			slew-rate = <0>;
+		};
+	};
+};
+
+&i2c0 {
+	clock-frequency = <100000>;
+	i2c-sda-hold-time-ns = <300>;
+	i2c-sda-falling-time-ns = <500>;
+	i2c-scl-falling-time-ns = <500>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c0_pins>;
+	status = "okay";
+
+	pmic@5e {
+		compatible = "ti,tps65086";
+		reg = <0x5e>;
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		regulators {
+		};
+	};
+};
+
+&i2c1 {
+	clock-frequency = <400000>;
+	i2c-sda-hold-time-ns = <300>;
+	i2c-sda-falling-time-ns = <100>;
+	i2c-scl-falling-time-ns = <100>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c1_pins>;
+	status = "okay";
+};
+
+&i2c2 {
+	clock-frequency = <100000>;
+	i2c-sda-hold-time-ns = <300>;
+	i2c-sda-falling-time-ns = <500>;
+	i2c-scl-falling-time-ns = <500>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c2_pins>;
+	status = "okay";
+};
+
+&osc_sys {
+	clock-frequency = <25000000>;
+};
+
+&osc_aud {
+	clock-frequency = <27000000>;
+};
+
+&uart3 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart3_pins>;
+	status = "okay";
+};
diff --git a/arch/riscv/boot/dts/starfive/jh7100.dtsi b/arch/riscv/boot/dts/starfive/jh7100.dtsi
new file mode 100644
index 000000000..000447482
--- /dev/null
+++ b/arch/riscv/boot/dts/starfive/jh7100.dtsi
@@ -0,0 +1,242 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/*
+ * Copyright (C) 2021 StarFive Technology Co., Ltd.
+ * Copyright (C) 2021 Emil Renner Berthing <kernel@esmil.dk>
+ */
+
+/dts-v1/;
+#include <dt-bindings/clock/starfive-jh7100.h>
+#include <dt-bindings/reset/starfive-jh7100.h>
+
+/ {
+	compatible = "starfive,jh7100";
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		U74_0: cpu@0 {
+			compatible = "sifive,u74-mc", "riscv";
+			reg = <0>;
+			d-cache-block-size = <64>;
+			d-cache-sets = <64>;
+			d-cache-size = <32768>;
+			d-tlb-sets = <1>;
+			d-tlb-size = <32>;
+			device_type = "cpu";
+			i-cache-block-size = <64>;
+			i-cache-sets = <64>;
+			i-cache-size = <32768>;
+			i-tlb-sets = <1>;
+			i-tlb-size = <32>;
+			mmu-type = "riscv,sv39";
+			riscv,isa = "rv64imafdc";
+			tlb-split;
+
+			cpu0_intc: interrupt-controller {
+				compatible = "riscv,cpu-intc";
+				interrupt-controller;
+				#interrupt-cells = <1>;
+			};
+		};
+
+		U74_1: cpu@1 {
+			compatible = "sifive,u74-mc", "riscv";
+			reg = <1>;
+			d-cache-block-size = <64>;
+			d-cache-sets = <64>;
+			d-cache-size = <32768>;
+			d-tlb-sets = <1>;
+			d-tlb-size = <32>;
+			device_type = "cpu";
+			i-cache-block-size = <64>;
+			i-cache-sets = <64>;
+			i-cache-size = <32768>;
+			i-tlb-sets = <1>;
+			i-tlb-size = <32>;
+			mmu-type = "riscv,sv39";
+			riscv,isa = "rv64imafdc";
+			tlb-split;
+
+			cpu1_intc: interrupt-controller {
+				compatible = "riscv,cpu-intc";
+				interrupt-controller;
+				#interrupt-cells = <1>;
+			};
+		};
+
+		cpu-map {
+			cluster0 {
+				core0 {
+					cpu = <&U74_0>;
+				};
+
+				core1 {
+					cpu = <&U74_1>;
+				};
+			};
+		};
+	};
+
+	osc_sys: osc_sys {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		/* This value must be overridden by the board */
+		clock-frequency = <0>;
+	};
+
+	osc_aud: osc_aud {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		/* This value must be overridden by the board */
+		clock-frequency = <0>;
+	};
+
+	gmac_rmii_ref: gmac_rmii_ref {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		/* Should be overridden by the board when needed */
+		clock-frequency = <0>;
+	};
+
+	gmac_gr_mii_rxclk: gmac_gr_mii_rxclk {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		/* Should be overridden by the board when needed */
+		clock-frequency = <0>;
+	};
+
+	soc {
+		compatible = "simple-bus";
+		interrupt-parent = <&plic>;
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		clint: clint@2000000 {
+			compatible = "starfive,jh7100-clint", "sifive,clint0";
+			reg = <0x0 0x2000000 0x0 0x10000>;
+			interrupts-extended = <&cpu0_intc 3 &cpu0_intc 7
+					       &cpu1_intc 3 &cpu1_intc 7>;
+		};
+
+		plic: interrupt-controller@c000000 {
+			compatible = "starfive,jh7100-plic", "sifive,plic-1.0.0";
+			reg = <0x0 0xc000000 0x0 0x4000000>;
+			interrupts-extended = <&cpu0_intc 11 &cpu0_intc 9
+					       &cpu1_intc 11 &cpu1_intc 9>;
+			interrupt-controller;
+			#address-cells = <0>;
+			#interrupt-cells = <1>;
+			riscv,ndev = <133>;
+		};
+
+		clkgen: clock-controller@11800000 {
+			compatible = "starfive,jh7100-clkgen";
+			reg = <0x0 0x11800000 0x0 0x10000>;
+			clocks = <&osc_sys>, <&osc_aud>, <&gmac_rmii_ref>, <&gmac_gr_mii_rxclk>;
+			clock-names = "osc_sys", "osc_aud", "gmac_rmii_ref", "gmac_gr_mii_rxclk";
+			#clock-cells = <1>;
+		};
+
+		rstgen: reset-controller@11840000 {
+			compatible = "starfive,jh7100-reset";
+			reg = <0x0 0x11840000 0x0 0x10000>;
+			#reset-cells = <1>;
+		};
+
+		i2c0: i2c@118b0000 {
+			compatible = "snps,designware-i2c";
+			reg = <0x0 0x118b0000 0x0 0x10000>;
+			clocks = <&clkgen JH7100_CLK_I2C0_CORE>,
+				 <&clkgen JH7100_CLK_I2C0_APB>;
+			clock-names = "ref", "pclk";
+			resets = <&rstgen JH7100_RSTN_I2C0_APB>;
+			interrupts = <96>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
+		i2c1: i2c@118c0000 {
+			compatible = "snps,designware-i2c";
+			reg = <0x0 0x118c0000 0x0 0x10000>;
+			clocks = <&clkgen JH7100_CLK_I2C1_CORE>,
+				 <&clkgen JH7100_CLK_I2C1_APB>;
+			clock-names = "ref", "pclk";
+			resets = <&rstgen JH7100_RSTN_I2C1_APB>;
+			interrupts = <97>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
+		gpio: pinctrl@11910000 {
+			compatible = "starfive,jh7100-pinctrl";
+			reg = <0x0 0x11910000 0x0 0x10000>,
+			      <0x0 0x11858000 0x0 0x1000>;
+			reg-names = "gpio", "padctl";
+			clocks = <&clkgen JH7100_CLK_GPIO_APB>;
+			resets = <&rstgen JH7100_RSTN_GPIO_APB>;
+			interrupts = <32>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			interrupt-controller;
+			#interrupt-cells = <2>;
+		};
+
+		uart2: serial@12430000 {
+			compatible = "starfive,jh7100-uart", "snps,dw-apb-uart";
+			reg = <0x0 0x12430000 0x0 0x10000>;
+			clocks = <&clkgen JH7100_CLK_UART2_CORE>,
+				 <&clkgen JH7100_CLK_UART2_APB>;
+			clock-names = "baudclk", "apb_pclk";
+			resets = <&rstgen JH7100_RSTN_UART2_APB>;
+			interrupts = <72>;
+			reg-io-width = <4>;
+			reg-shift = <2>;
+			status = "disabled";
+		};
+
+		uart3: serial@12440000 {
+			compatible = "starfive,jh7100-uart", "snps,dw-apb-uart";
+			reg = <0x0 0x12440000 0x0 0x10000>;
+			clocks = <&clkgen JH7100_CLK_UART3_CORE>,
+				 <&clkgen JH7100_CLK_UART3_APB>;
+			clock-names = "baudclk", "apb_pclk";
+			resets = <&rstgen JH7100_RSTN_UART3_APB>;
+			interrupts = <73>;
+			reg-io-width = <4>;
+			reg-shift = <2>;
+			status = "disabled";
+		};
+
+		i2c2: i2c@12450000 {
+			compatible = "snps,designware-i2c";
+			reg = <0x0 0x12450000 0x0 0x10000>;
+			clocks = <&clkgen JH7100_CLK_I2C2_CORE>,
+				 <&clkgen JH7100_CLK_I2C2_APB>;
+			clock-names = "ref", "pclk";
+			resets = <&rstgen JH7100_RSTN_I2C2_APB>;
+			interrupts = <74>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
+		i2c3: i2c@12460000 {
+			compatible = "snps,designware-i2c";
+			reg = <0x0 0x12460000 0x0 0x10000>;
+			clocks = <&clkgen JH7100_CLK_I2C3_CORE>,
+				 <&clkgen JH7100_CLK_I2C3_APB>;
+			clock-names = "ref", "pclk";
+			resets = <&rstgen JH7100_RSTN_I2C3_APB>;
+			interrupts = <75>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+	};
+};
diff --git a/arch/riscv/boot/install.sh b/arch/riscv/boot/install.sh
new file mode 100755
index 000000000..4c63f3f06
--- /dev/null
+++ b/arch/riscv/boot/install.sh
@@ -0,0 +1,39 @@
+#!/bin/sh
+#
+# This file is subject to the terms and conditions of the GNU General Public
+# License.  See the file "COPYING" in the main directory of this archive
+# for more details.
+#
+# Copyright (C) 1995 by Linus Torvalds
+#
+# Adapted from code in arch/i386/boot/Makefile by H. Peter Anvin
+# Adapted from code in arch/i386/boot/install.sh by Russell King
+#
+# "make install" script for the RISC-V Linux port
+#
+# Arguments:
+#   $1 - kernel version
+#   $2 - kernel image file
+#   $3 - kernel map file
+#   $4 - default install path (blank if root directory)
+
+if [ "$(basename $2)" = "Image.gz" ]; then
+# Compressed install
+  echo "Installing compressed kernel"
+  base=vmlinuz
+else
+# Normal install
+  echo "Installing normal kernel"
+  base=vmlinux
+fi
+
+if [ -f $4/$base-$1 ]; then
+  mv $4/$base-$1 $4/$base-$1.old
+fi
+cat $2 > $4/$base-$1
+
+# Install system map file
+if [ -f $4/System.map-$1 ]; then
+  mv $4/System.map-$1 $4/System.map-$1.old
+fi
+cp $3 $4/System.map-$1
diff --git a/arch/riscv/boot/loader.S b/arch/riscv/boot/loader.S
new file mode 100644
index 000000000..dcf88cf44
--- /dev/null
+++ b/arch/riscv/boot/loader.S
@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+	.align 4
+	.section .payload, "ax", %progbits
+	.globl _start
+_start:
+	.incbin "arch/riscv/boot/Image"
+
diff --git a/arch/riscv/boot/loader.lds.S b/arch/riscv/boot/loader.lds.S
new file mode 100644
index 000000000..62d94696a
--- /dev/null
+++ b/arch/riscv/boot/loader.lds.S
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <asm/page.h>
+#include <asm/pgtable.h>
+
+OUTPUT_ARCH(riscv)
+ENTRY(_start)
+
+SECTIONS
+{
+	. = KERNEL_LINK_ADDR;
+
+	.payload : {
+		*(.payload)
+		. = ALIGN(8);
+	}
+}
diff --git a/arch/riscv/configs/32-bit.config b/arch/riscv/configs/32-bit.config
new file mode 100644
index 000000000..f6af0f708
--- /dev/null
+++ b/arch/riscv/configs/32-bit.config
@@ -0,0 +1,4 @@
+CONFIG_ARCH_RV32I=y
+CONFIG_32BIT=y
+# CONFIG_PORTABLE is not set
+CONFIG_NONPORTABLE=y
diff --git a/arch/riscv/configs/64-bit.config b/arch/riscv/configs/64-bit.config
new file mode 100644
index 000000000..313edc554
--- /dev/null
+++ b/arch/riscv/configs/64-bit.config
@@ -0,0 +1,2 @@
+CONFIG_ARCH_RV64I=y
+CONFIG_64BIT=y
diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig
new file mode 100644
index 000000000..05fd5fcf2
--- /dev/null
+++ b/arch/riscv/configs/defconfig
@@ -0,0 +1,214 @@
+CONFIG_SYSVIPC=y
+CONFIG_POSIX_MQUEUE=y
+CONFIG_NO_HZ_IDLE=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_BPF_SYSCALL=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_CGROUPS=y
+CONFIG_MEMCG=y
+CONFIG_CGROUP_SCHED=y
+CONFIG_CFS_BANDWIDTH=y
+CONFIG_RT_GROUP_SCHED=y
+CONFIG_CGROUP_PIDS=y
+CONFIG_CGROUP_FREEZER=y
+CONFIG_CGROUP_HUGETLB=y
+CONFIG_CPUSETS=y
+CONFIG_CGROUP_DEVICE=y
+CONFIG_CGROUP_CPUACCT=y
+CONFIG_CGROUP_PERF=y
+CONFIG_CGROUP_BPF=y
+CONFIG_NAMESPACES=y
+CONFIG_USER_NS=y
+CONFIG_CHECKPOINT_RESTORE=y
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_EXPERT=y
+# CONFIG_SYSFS_SYSCALL is not set
+CONFIG_PROFILING=y
+CONFIG_SOC_MICROCHIP_POLARFIRE=y
+CONFIG_SOC_SIFIVE=y
+CONFIG_SOC_STARFIVE=y
+CONFIG_SOC_VIRT=y
+CONFIG_SMP=y
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PM=y
+CONFIG_CPU_IDLE=y
+CONFIG_VIRTUALIZATION=y
+CONFIG_KVM=m
+CONFIG_JUMP_LABEL=y
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_BLK_DEV_THROTTLING=y
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_XFRM_USER=m
+CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+CONFIG_IP_PNP_RARP=y
+CONFIG_INET_ESP=m
+CONFIG_NETFILTER=y
+CONFIG_BRIDGE_NETFILTER=m
+CONFIG_NF_CONNTRACK=m
+CONFIG_NF_CONNTRACK_FTP=m
+CONFIG_NF_CONNTRACK_TFTP=m
+CONFIG_NETFILTER_XT_MARK=m
+CONFIG_NETFILTER_XT_MATCH_ADDRTYPE=m
+CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m
+CONFIG_NETFILTER_XT_MATCH_IPVS=m
+CONFIG_IP_VS=m
+CONFIG_IP_VS_PROTO_TCP=y
+CONFIG_IP_VS_PROTO_UDP=y
+CONFIG_IP_VS_RR=m
+CONFIG_IP_VS_NFCT=y
+CONFIG_NF_LOG_ARP=m
+CONFIG_NF_LOG_IPV4=m
+CONFIG_IP_NF_IPTABLES=m
+CONFIG_IP_NF_FILTER=m
+CONFIG_IP_NF_TARGET_REJECT=m
+CONFIG_IP_NF_NAT=m
+CONFIG_IP_NF_TARGET_MASQUERADE=m
+CONFIG_IP_NF_TARGET_REDIRECT=m
+CONFIG_IP_NF_MANGLE=m
+CONFIG_NF_LOG_IPV6=m
+CONFIG_IP6_NF_IPTABLES=m
+CONFIG_IP6_NF_MATCH_IPV6HEADER=m
+CONFIG_IP6_NF_FILTER=m
+CONFIG_IP6_NF_TARGET_REJECT=m
+CONFIG_IP6_NF_MANGLE=m
+CONFIG_BRIDGE=m
+CONFIG_BRIDGE_VLAN_FILTERING=y
+CONFIG_VLAN_8021Q=m
+CONFIG_NET_SCHED=y
+CONFIG_NET_CLS_CGROUP=m
+CONFIG_NETLINK_DIAG=y
+CONFIG_CGROUP_NET_PRIO=y
+CONFIG_NET_9P=y
+CONFIG_NET_9P_VIRTIO=y
+CONFIG_PCI=y
+CONFIG_PCIEPORTBUS=y
+CONFIG_PCI_HOST_GENERIC=y
+CONFIG_PCIE_XILINX=y
+CONFIG_PCIE_FU740=y
+CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_VIRTIO_BLK=y
+CONFIG_BLK_DEV_NVME=m
+CONFIG_BLK_DEV_SD=y
+CONFIG_BLK_DEV_SR=y
+CONFIG_SCSI_VIRTIO=y
+CONFIG_ATA=y
+CONFIG_SATA_AHCI=y
+CONFIG_SATA_AHCI_PLATFORM=y
+CONFIG_MD=y
+CONFIG_BLK_DEV_DM=m
+CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_NETDEVICES=y
+CONFIG_DUMMY=m
+CONFIG_MACVLAN=m
+CONFIG_IPVLAN=m
+CONFIG_VXLAN=m
+CONFIG_VETH=m
+CONFIG_VIRTIO_NET=y
+CONFIG_MACB=y
+CONFIG_E1000E=y
+CONFIG_R8169=y
+CONFIG_MICROSEMI_PHY=y
+CONFIG_INPUT_MOUSEDEV=y
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_OF_PLATFORM=y
+CONFIG_VIRTIO_CONSOLE=y
+CONFIG_HW_RANDOM=y
+CONFIG_HW_RANDOM_VIRTIO=y
+CONFIG_SPI=y
+CONFIG_SPI_SIFIVE=y
+# CONFIG_PTP_1588_CLOCK is not set
+CONFIG_GPIOLIB=y
+CONFIG_GPIO_SIFIVE=y
+CONFIG_DRM=m
+CONFIG_DRM_RADEON=m
+CONFIG_DRM_NOUVEAU=m
+CONFIG_DRM_VIRTIO_GPU=m
+CONFIG_FB=y
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_USB=y
+CONFIG_USB_XHCI_HCD=y
+CONFIG_USB_XHCI_PLATFORM=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_USB_UAS=y
+CONFIG_MMC=y
+CONFIG_MMC_SDHCI=y
+CONFIG_MMC_SDHCI_PLTFM=y
+CONFIG_MMC_SDHCI_CADENCE=y
+CONFIG_MMC_SPI=y
+CONFIG_RTC_CLASS=y
+CONFIG_VIRTIO_PCI=y
+CONFIG_VIRTIO_BALLOON=y
+CONFIG_VIRTIO_INPUT=y
+CONFIG_VIRTIO_MMIO=y
+CONFIG_RPMSG_CHAR=y
+CONFIG_RPMSG_CTRL=y
+CONFIG_RPMSG_VIRTIO=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
+CONFIG_BTRFS_FS=m
+CONFIG_BTRFS_FS_POSIX_ACL=y
+CONFIG_AUTOFS4_FS=y
+CONFIG_OVERLAY_FS=m
+CONFIG_ISO9660_FS=y
+CONFIG_JOLIET=y
+CONFIG_ZISOFS=y
+CONFIG_MSDOS_FS=y
+CONFIG_VFAT_FS=y
+CONFIG_TMPFS=y
+CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_HUGETLBFS=y
+CONFIG_NFS_FS=y
+CONFIG_NFS_V4=y
+CONFIG_NFS_V4_1=y
+CONFIG_NFS_V4_2=y
+CONFIG_ROOT_NFS=y
+CONFIG_9P_FS=y
+CONFIG_NLS_CODEPAGE_437=y
+CONFIG_NLS_ISO8859_1=m
+CONFIG_SECURITY=y
+CONFIG_SECURITY_SELINUX=y
+CONFIG_SECURITY_APPARMOR=y
+CONFIG_DEFAULT_SECURITY_DAC=y
+CONFIG_CRYPTO_USER_API_HASH=y
+CONFIG_CRYPTO_DEV_VIRTIO=y
+CONFIG_PRINTK_TIME=y
+CONFIG_DEBUG_FS=y
+CONFIG_DEBUG_PAGEALLOC=y
+CONFIG_SCHED_STACK_END_CHECK=y
+CONFIG_DEBUG_VM=y
+CONFIG_DEBUG_VM_PGFLAGS=y
+CONFIG_DEBUG_MEMORY_INIT=y
+CONFIG_DEBUG_PER_CPU_MAPS=y
+CONFIG_SOFTLOCKUP_DETECTOR=y
+CONFIG_WQ_WATCHDOG=y
+CONFIG_DEBUG_TIMEKEEPING=y
+CONFIG_DEBUG_RT_MUTEXES=y
+CONFIG_DEBUG_SPINLOCK=y
+CONFIG_DEBUG_MUTEXES=y
+CONFIG_DEBUG_RWSEMS=y
+CONFIG_DEBUG_ATOMIC_SLEEP=y
+CONFIG_DEBUG_LIST=y
+CONFIG_DEBUG_PLIST=y
+CONFIG_DEBUG_SG=y
+# CONFIG_RCU_TRACE is not set
+CONFIG_RCU_EQS_DEBUG=y
+# CONFIG_FTRACE is not set
+# CONFIG_RUNTIME_TESTING_MENU is not set
+CONFIG_MEMTEST=y
diff --git a/arch/riscv/configs/nommu_k210_defconfig b/arch/riscv/configs/nommu_k210_defconfig
new file mode 100644
index 000000000..96fe8def6
--- /dev/null
+++ b/arch/riscv/configs/nommu_k210_defconfig
@@ -0,0 +1,91 @@
+# CONFIG_CPU_ISOLATION is not set
+CONFIG_LOG_BUF_SHIFT=13
+CONFIG_PRINTK_SAFE_LOG_BUF_SHIFT=12
+CONFIG_BLK_DEV_INITRD=y
+# CONFIG_RD_GZIP is not set
+# CONFIG_RD_BZIP2 is not set
+# CONFIG_RD_LZMA is not set
+# CONFIG_RD_XZ is not set
+# CONFIG_RD_LZO is not set
+# CONFIG_RD_LZ4 is not set
+# CONFIG_RD_ZSTD is not set
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
+# CONFIG_SYSFS_SYSCALL is not set
+# CONFIG_FHANDLE is not set
+# CONFIG_BASE_FULL is not set
+# CONFIG_FUTEX is not set
+# CONFIG_EPOLL is not set
+# CONFIG_SIGNALFD is not set
+# CONFIG_TIMERFD is not set
+# CONFIG_EVENTFD is not set
+# CONFIG_AIO is not set
+# CONFIG_IO_URING is not set
+# CONFIG_ADVISE_SYSCALLS is not set
+# CONFIG_KALLSYMS is not set
+CONFIG_EMBEDDED=y
+# CONFIG_VM_EVENT_COUNTERS is not set
+# CONFIG_COMPAT_BRK is not set
+CONFIG_SLOB=y
+# CONFIG_MMU is not set
+CONFIG_SOC_CANAAN=y
+CONFIG_NONPORTABLE=y
+CONFIG_SMP=y
+CONFIG_NR_CPUS=2
+CONFIG_CMDLINE="earlycon console=ttySIF0"
+CONFIG_CMDLINE_FORCE=y
+# CONFIG_SECCOMP is not set
+# CONFIG_STACKPROTECTOR is not set
+# CONFIG_GCC_PLUGINS is not set
+# CONFIG_BLOCK is not set
+CONFIG_BINFMT_FLAT=y
+# CONFIG_COREDUMP is not set
+CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
+# CONFIG_FW_LOADER is not set
+# CONFIG_ALLOW_DEV_COREDUMP is not set
+# CONFIG_INPUT is not set
+# CONFIG_SERIO is not set
+# CONFIG_VT is not set
+# CONFIG_UNIX98_PTYS is not set
+# CONFIG_LEGACY_PTYS is not set
+# CONFIG_LDISC_AUTOLOAD is not set
+# CONFIG_HW_RANDOM is not set
+# CONFIG_DEVMEM is not set
+CONFIG_I2C=y
+# CONFIG_I2C_COMPAT is not set
+CONFIG_I2C_CHARDEV=y
+# CONFIG_I2C_HELPER_AUTO is not set
+CONFIG_I2C_DESIGNWARE_PLATFORM=y
+CONFIG_SPI=y
+# CONFIG_SPI_MEM is not set
+CONFIG_SPI_DESIGNWARE=y
+CONFIG_SPI_DW_MMIO=y
+# CONFIG_GPIO_CDEV_V1 is not set
+CONFIG_GPIO_DWAPB=y
+CONFIG_GPIO_SIFIVE=y
+CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_SYSCON=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_USER=y
+# CONFIG_VIRTIO_MENU is not set
+# CONFIG_VHOST_MENU is not set
+# CONFIG_FILE_LOCKING is not set
+# CONFIG_DNOTIFY is not set
+# CONFIG_INOTIFY_USER is not set
+# CONFIG_MISC_FILESYSTEMS is not set
+CONFIG_LSM="[]"
+CONFIG_PRINTK_TIME=y
+# CONFIG_SYMBOLIC_ERRNAME is not set
+# CONFIG_DEBUG_BUGVERBOSE is not set
+# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
+# CONFIG_FRAME_POINTER is not set
+# CONFIG_DEBUG_MISC is not set
+CONFIG_PANIC_ON_OOPS=y
+# CONFIG_SCHED_DEBUG is not set
+# CONFIG_RCU_TRACE is not set
+# CONFIG_FTRACE is not set
+# CONFIG_RUNTIME_TESTING_MENU is not set
diff --git a/arch/riscv/configs/nommu_k210_sdcard_defconfig b/arch/riscv/configs/nommu_k210_sdcard_defconfig
new file mode 100644
index 000000000..379740654
--- /dev/null
+++ b/arch/riscv/configs/nommu_k210_sdcard_defconfig
@@ -0,0 +1,88 @@
+# CONFIG_CPU_ISOLATION is not set
+CONFIG_LOG_BUF_SHIFT=13
+CONFIG_PRINTK_SAFE_LOG_BUF_SHIFT=12
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
+# CONFIG_SYSFS_SYSCALL is not set
+# CONFIG_FHANDLE is not set
+# CONFIG_BASE_FULL is not set
+# CONFIG_FUTEX is not set
+# CONFIG_EPOLL is not set
+# CONFIG_SIGNALFD is not set
+# CONFIG_TIMERFD is not set
+# CONFIG_EVENTFD is not set
+# CONFIG_AIO is not set
+# CONFIG_IO_URING is not set
+# CONFIG_ADVISE_SYSCALLS is not set
+# CONFIG_KALLSYMS is not set
+CONFIG_EMBEDDED=y
+# CONFIG_VM_EVENT_COUNTERS is not set
+# CONFIG_COMPAT_BRK is not set
+CONFIG_SLOB=y
+# CONFIG_MMU is not set
+CONFIG_SOC_CANAAN=y
+CONFIG_NONPORTABLE=y
+CONFIG_SMP=y
+CONFIG_NR_CPUS=2
+CONFIG_CMDLINE="earlycon console=ttySIF0 root=/dev/mmcblk0p1 rootwait ro"
+CONFIG_CMDLINE_FORCE=y
+# CONFIG_SECCOMP is not set
+# CONFIG_STACKPROTECTOR is not set
+# CONFIG_GCC_PLUGINS is not set
+# CONFIG_MQ_IOSCHED_DEADLINE is not set
+# CONFIG_MQ_IOSCHED_KYBER is not set
+CONFIG_BINFMT_FLAT=y
+# CONFIG_COREDUMP is not set
+CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
+# CONFIG_FW_LOADER is not set
+# CONFIG_ALLOW_DEV_COREDUMP is not set
+# CONFIG_BLK_DEV 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_LDISC_AUTOLOAD is not set
+# CONFIG_HW_RANDOM is not set
+# CONFIG_DEVMEM is not set
+CONFIG_I2C=y
+CONFIG_I2C_CHARDEV=y
+# CONFIG_I2C_HELPER_AUTO is not set
+CONFIG_I2C_DESIGNWARE_PLATFORM=y
+CONFIG_SPI=y
+# CONFIG_SPI_MEM is not set
+CONFIG_SPI_DESIGNWARE=y
+CONFIG_SPI_DW_MMIO=y
+# CONFIG_GPIO_CDEV_V1 is not set
+CONFIG_GPIO_DWAPB=y
+CONFIG_GPIO_SIFIVE=y
+CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_SYSCON=y
+# CONFIG_HWMON is not set
+# CONFIG_USB_SUPPORT is not set
+CONFIG_MMC=y
+# CONFIG_PWRSEQ_EMMC is not set
+# CONFIG_PWRSEQ_SIMPLE is not set
+CONFIG_MMC_SPI=y
+CONFIG_NEW_LEDS=y
+CONFIG_LEDS_CLASS=y
+CONFIG_LEDS_GPIO=y
+CONFIG_LEDS_USER=y
+# CONFIG_VIRTIO_MENU is not set
+# CONFIG_VHOST_MENU is not set
+CONFIG_EXT2_FS=y
+# CONFIG_FILE_LOCKING is not set
+# CONFIG_DNOTIFY is not set
+# CONFIG_INOTIFY_USER is not set
+# CONFIG_MISC_FILESYSTEMS is not set
+CONFIG_LSM="[]"
+CONFIG_PRINTK_TIME=y
+# CONFIG_SYMBOLIC_ERRNAME is not set
+# CONFIG_DEBUG_BUGVERBOSE is not set
+# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
+# CONFIG_FRAME_POINTER is not set
+# CONFIG_DEBUG_MISC is not set
+CONFIG_PANIC_ON_OOPS=y
+# CONFIG_SCHED_DEBUG is not set
+# CONFIG_RCU_TRACE is not set
+# CONFIG_FTRACE is not set
+# CONFIG_RUNTIME_TESTING_MENU is not set
diff --git a/arch/riscv/configs/nommu_virt_defconfig b/arch/riscv/configs/nommu_virt_defconfig
new file mode 100644
index 000000000..1a56eda5c
--- /dev/null
+++ b/arch/riscv/configs/nommu_virt_defconfig
@@ -0,0 +1,73 @@
+# CONFIG_CPU_ISOLATION is not set
+CONFIG_LOG_BUF_SHIFT=16
+CONFIG_PRINTK_SAFE_LOG_BUF_SHIFT=12
+CONFIG_BLK_DEV_INITRD=y
+# CONFIG_RD_BZIP2 is not set
+# CONFIG_RD_LZMA is not set
+# CONFIG_RD_XZ is not set
+# CONFIG_RD_LZO is not set
+# CONFIG_RD_LZ4 is not set
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
+CONFIG_EXPERT=y
+# CONFIG_SYSFS_SYSCALL is not set
+# CONFIG_FHANDLE is not set
+# CONFIG_BASE_FULL is not set
+# CONFIG_EPOLL is not set
+# CONFIG_SIGNALFD is not set
+# CONFIG_TIMERFD is not set
+# CONFIG_EVENTFD is not set
+# CONFIG_AIO is not set
+# CONFIG_IO_URING is not set
+# CONFIG_ADVISE_SYSCALLS is not set
+# CONFIG_KALLSYMS is not set
+# CONFIG_VM_EVENT_COUNTERS is not set
+# CONFIG_COMPAT_BRK is not set
+CONFIG_SLOB=y
+# CONFIG_MMU is not set
+CONFIG_SOC_VIRT=y
+CONFIG_NONPORTABLE=y
+CONFIG_SMP=y
+CONFIG_CMDLINE="root=/dev/vda rw earlycon=uart8250,mmio,0x10000000,115200n8 console=ttyS0"
+CONFIG_CMDLINE_FORCE=y
+CONFIG_JUMP_LABEL=y
+CONFIG_PARTITION_ADVANCED=y
+# CONFIG_MSDOS_PARTITION is not set
+# CONFIG_EFI_PARTITION is not set
+# CONFIG_MQ_IOSCHED_DEADLINE is not set
+# CONFIG_MQ_IOSCHED_KYBER is not set
+CONFIG_BINFMT_FLAT=y
+# CONFIG_COREDUMP is not set
+CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
+# CONFIG_FW_LOADER is not set
+# CONFIG_ALLOW_DEV_COREDUMP is not set
+CONFIG_VIRTIO_BLK=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_LDISC_AUTOLOAD is not set
+CONFIG_SERIAL_8250=y
+# CONFIG_SERIAL_8250_DEPRECATED_OPTIONS is not set
+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_DEVMEM is not set
+# CONFIG_HWMON is not set
+# CONFIG_VGA_CONSOLE is not set
+# CONFIG_HID is not set
+# CONFIG_USB_SUPPORT is not set
+CONFIG_VIRTIO_MMIO=y
+CONFIG_VIRTIO_MMIO_CMDLINE_DEVICES=y
+CONFIG_EXT2_FS=y
+# CONFIG_DNOTIFY is not set
+# CONFIG_INOTIFY_USER is not set
+# CONFIG_MISC_FILESYSTEMS is not set
+CONFIG_LSM="[]"
+CONFIG_PRINTK_TIME=y
+# CONFIG_SCHED_DEBUG is not set
+# CONFIG_RCU_TRACE is not set
+# CONFIG_FTRACE is not set
+# CONFIG_RUNTIME_TESTING_MENU is not set
diff --git a/arch/riscv/configs/rv32_defconfig b/arch/riscv/configs/rv32_defconfig
new file mode 100644
index 000000000..38760e429
--- /dev/null
+++ b/arch/riscv/configs/rv32_defconfig
@@ -0,0 +1,139 @@
+CONFIG_SYSVIPC=y
+CONFIG_POSIX_MQUEUE=y
+CONFIG_NO_HZ_IDLE=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_BPF_SYSCALL=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_CGROUPS=y
+CONFIG_CGROUP_SCHED=y
+CONFIG_CFS_BANDWIDTH=y
+CONFIG_CGROUP_BPF=y
+CONFIG_NAMESPACES=y
+CONFIG_USER_NS=y
+CONFIG_CHECKPOINT_RESTORE=y
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_EXPERT=y
+# CONFIG_SYSFS_SYSCALL is not set
+CONFIG_PROFILING=y
+CONFIG_SOC_SIFIVE=y
+CONFIG_SOC_VIRT=y
+CONFIG_NONPORTABLE=y
+CONFIG_ARCH_RV32I=y
+CONFIG_SMP=y
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PM=y
+CONFIG_CPU_IDLE=y
+CONFIG_VIRTUALIZATION=y
+CONFIG_KVM=m
+CONFIG_JUMP_LABEL=y
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+CONFIG_IP_PNP_RARP=y
+CONFIG_NETLINK_DIAG=y
+CONFIG_NET_9P=y
+CONFIG_NET_9P_VIRTIO=y
+CONFIG_PCI=y
+CONFIG_PCIEPORTBUS=y
+CONFIG_PCI_HOST_GENERIC=y
+CONFIG_PCIE_XILINX=y
+CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_VIRTIO_BLK=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_BLK_DEV_SR=y
+CONFIG_SCSI_VIRTIO=y
+CONFIG_ATA=y
+CONFIG_SATA_AHCI=y
+CONFIG_SATA_AHCI_PLATFORM=y
+CONFIG_NETDEVICES=y
+CONFIG_VIRTIO_NET=y
+CONFIG_MACB=y
+CONFIG_E1000E=y
+CONFIG_R8169=y
+CONFIG_MICROSEMI_PHY=y
+CONFIG_INPUT_MOUSEDEV=y
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_OF_PLATFORM=y
+CONFIG_VIRTIO_CONSOLE=y
+CONFIG_HW_RANDOM=y
+CONFIG_HW_RANDOM_VIRTIO=y
+CONFIG_SPI=y
+CONFIG_SPI_SIFIVE=y
+# CONFIG_PTP_1588_CLOCK is not set
+CONFIG_DRM=y
+CONFIG_DRM_RADEON=y
+CONFIG_DRM_VIRTIO_GPU=y
+CONFIG_FB=y
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_USB=y
+CONFIG_USB_XHCI_HCD=y
+CONFIG_USB_XHCI_PLATFORM=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_USB_UAS=y
+CONFIG_MMC=y
+CONFIG_MMC_SPI=y
+CONFIG_RTC_CLASS=y
+CONFIG_VIRTIO_PCI=y
+CONFIG_VIRTIO_BALLOON=y
+CONFIG_VIRTIO_INPUT=y
+CONFIG_VIRTIO_MMIO=y
+CONFIG_RPMSG_CHAR=y
+CONFIG_RPMSG_CTRL=y
+CONFIG_RPMSG_VIRTIO=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_AUTOFS4_FS=y
+CONFIG_MSDOS_FS=y
+CONFIG_VFAT_FS=y
+CONFIG_TMPFS=y
+CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_HUGETLBFS=y
+CONFIG_NFS_FS=y
+CONFIG_NFS_V4=y
+CONFIG_NFS_V4_1=y
+CONFIG_NFS_V4_2=y
+CONFIG_ROOT_NFS=y
+CONFIG_9P_FS=y
+CONFIG_CRYPTO_USER_API_HASH=y
+CONFIG_CRYPTO_DEV_VIRTIO=y
+CONFIG_PRINTK_TIME=y
+CONFIG_DEBUG_FS=y
+CONFIG_DEBUG_PAGEALLOC=y
+CONFIG_SCHED_STACK_END_CHECK=y
+CONFIG_DEBUG_VM=y
+CONFIG_DEBUG_VM_PGFLAGS=y
+CONFIG_DEBUG_MEMORY_INIT=y
+CONFIG_DEBUG_PER_CPU_MAPS=y
+CONFIG_SOFTLOCKUP_DETECTOR=y
+CONFIG_WQ_WATCHDOG=y
+CONFIG_DEBUG_TIMEKEEPING=y
+CONFIG_DEBUG_RT_MUTEXES=y
+CONFIG_DEBUG_SPINLOCK=y
+CONFIG_DEBUG_MUTEXES=y
+CONFIG_DEBUG_RWSEMS=y
+CONFIG_DEBUG_ATOMIC_SLEEP=y
+CONFIG_STACKTRACE=y
+CONFIG_DEBUG_LIST=y
+CONFIG_DEBUG_PLIST=y
+CONFIG_DEBUG_SG=y
+# CONFIG_RCU_TRACE is not set
+CONFIG_RCU_EQS_DEBUG=y
+# CONFIG_FTRACE is not set
+# CONFIG_RUNTIME_TESTING_MENU is not set
+CONFIG_MEMTEST=y
diff --git a/arch/riscv/errata/Makefile b/arch/riscv/errata/Makefile
new file mode 100644
index 000000000..a1055965f
--- /dev/null
+++ b/arch/riscv/errata/Makefile
@@ -0,0 +1,2 @@
+obj-$(CONFIG_ERRATA_SIFIVE) += sifive/
+obj-$(CONFIG_ERRATA_THEAD) += thead/
diff --git a/arch/riscv/errata/sifive/Makefile b/arch/riscv/errata/sifive/Makefile
new file mode 100644
index 000000000..2fde48db0
--- /dev/null
+++ b/arch/riscv/errata/sifive/Makefile
@@ -0,0 +1,2 @@
+obj-$(CONFIG_ERRATA_SIFIVE_CIP_453) += errata_cip_453.o
+obj-y += errata.o
diff --git a/arch/riscv/errata/sifive/errata.c b/arch/riscv/errata/sifive/errata.c
new file mode 100644
index 000000000..c24a349dd
--- /dev/null
+++ b/arch/riscv/errata/sifive/errata.c
@@ -0,0 +1,120 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2021 Sifive.
+ */
+
+#include <linux/kernel.h>
+#include <linux/memory.h>
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/bug.h>
+#include <asm/patch.h>
+#include <asm/alternative.h>
+#include <asm/vendorid_list.h>
+#include <asm/errata_list.h>
+
+struct errata_info_t {
+	char name[ERRATA_STRING_LENGTH_MAX];
+	bool (*check_func)(unsigned long  arch_id, unsigned long impid);
+};
+
+static bool errata_cip_453_check_func(unsigned long  arch_id, unsigned long impid)
+{
+	/*
+	 * Affected cores:
+	 * Architecture ID: 0x8000000000000007
+	 * Implement ID: 0x20181004 <= impid <= 0x20191105
+	 */
+	if (arch_id != 0x8000000000000007 ||
+	    (impid < 0x20181004 || impid > 0x20191105))
+		return false;
+	return true;
+}
+
+static bool errata_cip_1200_check_func(unsigned long  arch_id, unsigned long impid)
+{
+	/*
+	 * Affected cores:
+	 * Architecture ID: 0x8000000000000007 or 0x1
+	 * Implement ID: mimpid[23:0] <= 0x200630 and mimpid != 0x01200626
+	 */
+	if (arch_id != 0x8000000000000007 && arch_id != 0x1)
+		return false;
+	if ((impid & 0xffffff) > 0x200630 || impid == 0x1200626)
+		return false;
+	return true;
+}
+
+static struct errata_info_t errata_list[ERRATA_SIFIVE_NUMBER] = {
+	{
+		.name = "cip-453",
+		.check_func = errata_cip_453_check_func
+	},
+	{
+		.name = "cip-1200",
+		.check_func = errata_cip_1200_check_func
+	},
+};
+
+static u32 __init_or_module sifive_errata_probe(unsigned long archid,
+						unsigned long impid)
+{
+	int idx;
+	u32 cpu_req_errata = 0;
+
+	for (idx = 0; idx < ERRATA_SIFIVE_NUMBER; idx++)
+		if (errata_list[idx].check_func(archid, impid))
+			cpu_req_errata |= (1U << idx);
+
+	return cpu_req_errata;
+}
+
+static void __init_or_module warn_miss_errata(u32 miss_errata)
+{
+	int i;
+
+	pr_warn("----------------------------------------------------------------\n");
+	pr_warn("WARNING: Missing the following errata may cause potential issues\n");
+	for (i = 0; i < ERRATA_SIFIVE_NUMBER; i++)
+		if (miss_errata & 0x1 << i)
+			pr_warn("\tSiFive Errata[%d]:%s\n", i, errata_list[i].name);
+	pr_warn("Please enable the corresponding Kconfig to apply them\n");
+	pr_warn("----------------------------------------------------------------\n");
+}
+
+void __init_or_module sifive_errata_patch_func(struct alt_entry *begin,
+					       struct alt_entry *end,
+					       unsigned long archid,
+					       unsigned long impid,
+					       unsigned int stage)
+{
+	struct alt_entry *alt;
+	u32 cpu_req_errata;
+	u32 cpu_apply_errata = 0;
+	u32 tmp;
+
+	if (stage == RISCV_ALTERNATIVES_EARLY_BOOT)
+		return;
+
+	cpu_req_errata = sifive_errata_probe(archid, impid);
+
+	for (alt = begin; alt < end; alt++) {
+		if (alt->vendor_id != SIFIVE_VENDOR_ID)
+			continue;
+		if (alt->errata_id >= ERRATA_SIFIVE_NUMBER) {
+			WARN(1, "This errata id:%d is not in kernel errata list", alt->errata_id);
+			continue;
+		}
+
+		tmp = (1U << alt->errata_id);
+		if (cpu_req_errata & tmp) {
+			mutex_lock(&text_mutex);
+			patch_text_nosync(alt->old_ptr, alt->alt_ptr, alt->alt_len);
+			mutex_unlock(&text_mutex);
+			cpu_apply_errata |= tmp;
+		}
+	}
+	if (stage != RISCV_ALTERNATIVES_MODULE &&
+	    cpu_apply_errata != cpu_req_errata)
+		warn_miss_errata(cpu_req_errata - cpu_apply_errata);
+}
diff --git a/arch/riscv/errata/sifive/errata_cip_453.S b/arch/riscv/errata/sifive/errata_cip_453.S
new file mode 100644
index 000000000..f1b9623fe
--- /dev/null
+++ b/arch/riscv/errata/sifive/errata_cip_453.S
@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2021 SiFive
+ */
+
+#include <linux/linkage.h>
+#include <asm/asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/alternative.h>
+
+.macro ADD_SIGN_EXT pt_reg badaddr tmp_reg
+	REG_L \badaddr, PT_BADADDR(\pt_reg)
+	li \tmp_reg,1
+	slli \tmp_reg,\tmp_reg,0x26
+	and \tmp_reg,\tmp_reg,\badaddr
+	beqz \tmp_reg, 1f
+	li \tmp_reg,-1
+	slli \tmp_reg,\tmp_reg,0x27
+	or \badaddr,\tmp_reg,\badaddr
+	REG_S \badaddr, PT_BADADDR(\pt_reg)
+1:
+.endm
+
+ENTRY(sifive_cip_453_page_fault_trp)
+	ADD_SIGN_EXT a0, t0, t1
+#ifdef CONFIG_MMU
+	la t0, do_page_fault
+#else
+	la t0, do_trap_unknown
+#endif
+	jr t0
+END(sifive_cip_453_page_fault_trp)
+
+ENTRY(sifive_cip_453_insn_fault_trp)
+	ADD_SIGN_EXT a0, t0, t1
+	la t0, do_trap_insn_fault
+	jr t0
+END(sifive_cip_453_insn_fault_trp)
diff --git a/arch/riscv/errata/thead/Makefile b/arch/riscv/errata/thead/Makefile
new file mode 100644
index 000000000..137e700d9
--- /dev/null
+++ b/arch/riscv/errata/thead/Makefile
@@ -0,0 +1,11 @@
+ifdef CONFIG_RISCV_ALTERNATIVE_EARLY
+CFLAGS_errata.o := -mcmodel=medany
+ifdef CONFIG_FTRACE
+CFLAGS_REMOVE_errata.o = $(CC_FLAGS_FTRACE)
+endif
+ifdef CONFIG_KASAN
+KASAN_SANITIZE_errata.o := n
+endif
+endif
+
+obj-y += errata.o
diff --git a/arch/riscv/errata/thead/errata.c b/arch/riscv/errata/thead/errata.c
new file mode 100644
index 000000000..32a34ed73
--- /dev/null
+++ b/arch/riscv/errata/thead/errata.c
@@ -0,0 +1,95 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2021 Heiko Stuebner <heiko@sntech.de>
+ */
+
+#include <linux/bug.h>
+#include <linux/kernel.h>
+#include <linux/memory.h>
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/uaccess.h>
+#include <asm/alternative.h>
+#include <asm/cacheflush.h>
+#include <asm/errata_list.h>
+#include <asm/patch.h>
+#include <asm/vendorid_list.h>
+
+static bool errata_probe_pbmt(unsigned int stage,
+			      unsigned long arch_id, unsigned long impid)
+{
+	if (!IS_ENABLED(CONFIG_ERRATA_THEAD_PBMT))
+		return false;
+
+	if (arch_id != 0 || impid != 0)
+		return false;
+
+	if (stage == RISCV_ALTERNATIVES_EARLY_BOOT ||
+	    stage == RISCV_ALTERNATIVES_MODULE)
+		return true;
+
+	return false;
+}
+
+static bool errata_probe_cmo(unsigned int stage,
+			     unsigned long arch_id, unsigned long impid)
+{
+	if (!IS_ENABLED(CONFIG_ERRATA_THEAD_CMO))
+		return false;
+
+	if (arch_id != 0 || impid != 0)
+		return false;
+
+	if (stage == RISCV_ALTERNATIVES_EARLY_BOOT)
+		return false;
+
+	riscv_cbom_block_size = L1_CACHE_BYTES;
+	riscv_noncoherent_supported();
+	return true;
+}
+
+static u32 thead_errata_probe(unsigned int stage,
+			      unsigned long archid, unsigned long impid)
+{
+	u32 cpu_req_errata = 0;
+
+	if (errata_probe_pbmt(stage, archid, impid))
+		cpu_req_errata |= BIT(ERRATA_THEAD_PBMT);
+
+	if (errata_probe_cmo(stage, archid, impid))
+		cpu_req_errata |= BIT(ERRATA_THEAD_CMO);
+
+	return cpu_req_errata;
+}
+
+void __init_or_module thead_errata_patch_func(struct alt_entry *begin, struct alt_entry *end,
+					      unsigned long archid, unsigned long impid,
+					      unsigned int stage)
+{
+	struct alt_entry *alt;
+	u32 cpu_req_errata = thead_errata_probe(stage, archid, impid);
+	u32 tmp;
+
+	for (alt = begin; alt < end; alt++) {
+		if (alt->vendor_id != THEAD_VENDOR_ID)
+			continue;
+		if (alt->errata_id >= ERRATA_THEAD_NUMBER)
+			continue;
+
+		tmp = (1U << alt->errata_id);
+		if (cpu_req_errata & tmp) {
+			/* On vm-alternatives, the mmu isn't running yet */
+			if (stage == RISCV_ALTERNATIVES_EARLY_BOOT) {
+				memcpy((void *)__pa_symbol(alt->old_ptr),
+				       (void *)__pa_symbol(alt->alt_ptr), alt->alt_len);
+			} else {
+				mutex_lock(&text_mutex);
+				patch_text_nosync(alt->old_ptr, alt->alt_ptr, alt->alt_len);
+				mutex_unlock(&text_mutex);
+			}
+		}
+	}
+
+	if (stage == RISCV_ALTERNATIVES_EARLY_BOOT)
+		local_flush_icache_all();
+}
diff --git a/arch/riscv/include/asm/Kbuild b/arch/riscv/include/asm/Kbuild
new file mode 100644
index 000000000..504f8b7e7
--- /dev/null
+++ b/arch/riscv/include/asm/Kbuild
@@ -0,0 +1,11 @@
+# SPDX-License-Identifier: GPL-2.0
+generic-y += early_ioremap.h
+generic-y += flat.h
+generic-y += kvm_para.h
+generic-y += parport.h
+generic-y += spinlock.h
+generic-y += spinlock_types.h
+generic-y += qrwlock.h
+generic-y += qrwlock_types.h
+generic-y += user.h
+generic-y += vmlinux.lds.h
diff --git a/arch/riscv/include/asm/alternative-macros.h b/arch/riscv/include/asm/alternative-macros.h
new file mode 100644
index 000000000..ec2f3f1b8
--- /dev/null
+++ b/arch/riscv/include/asm/alternative-macros.h
@@ -0,0 +1,205 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_ALTERNATIVE_MACROS_H
+#define __ASM_ALTERNATIVE_MACROS_H
+
+#ifdef CONFIG_RISCV_ALTERNATIVE
+
+#ifdef __ASSEMBLY__
+
+.macro ALT_ENTRY oldptr newptr vendor_id errata_id new_len
+	RISCV_PTR \oldptr
+	RISCV_PTR \newptr
+	REG_ASM \vendor_id
+	REG_ASM \new_len
+	.word	\errata_id
+.endm
+
+.macro ALT_NEW_CONTENT vendor_id, errata_id, enable = 1, new_c : vararg
+	.if \enable
+	.pushsection .alternative, "a"
+	ALT_ENTRY 886b, 888f, \vendor_id, \errata_id, 889f - 888f
+	.popsection
+	.subsection 1
+888 :
+	.option push
+	.option norvc
+	.option norelax
+	\new_c
+	.option pop
+889 :
+	.org    . - (889b - 888b) + (887b - 886b)
+	.org    . - (887b - 886b) + (889b - 888b)
+	.previous
+	.endif
+.endm
+
+.macro __ALTERNATIVE_CFG old_c, new_c, vendor_id, errata_id, enable
+886 :
+	.option push
+	.option norvc
+	.option norelax
+	\old_c
+	.option pop
+887 :
+	ALT_NEW_CONTENT \vendor_id, \errata_id, \enable, \new_c
+.endm
+
+#define _ALTERNATIVE_CFG(old_c, new_c, vendor_id, errata_id, CONFIG_k) \
+	__ALTERNATIVE_CFG old_c, new_c, vendor_id, errata_id, IS_ENABLED(CONFIG_k)
+
+.macro __ALTERNATIVE_CFG_2 old_c, new_c_1, vendor_id_1, errata_id_1, enable_1, \
+				  new_c_2, vendor_id_2, errata_id_2, enable_2
+886 :
+	.option push
+	.option norvc
+	.option norelax
+	\old_c
+	.option pop
+887 :
+	ALT_NEW_CONTENT \vendor_id_1, \errata_id_1, \enable_1, \new_c_1
+	ALT_NEW_CONTENT \vendor_id_2, \errata_id_2, \enable_2, \new_c_2
+.endm
+
+#define _ALTERNATIVE_CFG_2(old_c, new_c_1, vendor_id_1, errata_id_1,	\
+					CONFIG_k_1,			\
+				  new_c_2, vendor_id_2, errata_id_2,	\
+					CONFIG_k_2)			\
+	__ALTERNATIVE_CFG_2 old_c, new_c_1, vendor_id_1, errata_id_1,	\
+					IS_ENABLED(CONFIG_k_1),		\
+				   new_c_2, vendor_id_2, errata_id_2,	\
+					IS_ENABLED(CONFIG_k_2)
+
+#else /* !__ASSEMBLY__ */
+
+#include <asm/asm.h>
+#include <linux/stringify.h>
+
+#define ALT_ENTRY(oldptr, newptr, vendor_id, errata_id, newlen)		\
+	RISCV_PTR " " oldptr "\n"					\
+	RISCV_PTR " " newptr "\n"					\
+	REG_ASM " " vendor_id "\n"					\
+	REG_ASM " " newlen "\n"						\
+	".word " errata_id "\n"
+
+#define ALT_NEW_CONTENT(vendor_id, errata_id, enable, new_c)		\
+	".if " __stringify(enable) " == 1\n"				\
+	".pushsection .alternative, \"a\"\n"				\
+	ALT_ENTRY("886b", "888f", __stringify(vendor_id), __stringify(errata_id), "889f - 888f") \
+	".popsection\n"							\
+	".subsection 1\n"						\
+	"888 :\n"							\
+	".option push\n"						\
+	".option norvc\n"						\
+	".option norelax\n"						\
+	new_c "\n"							\
+	".option pop\n"							\
+	"889 :\n"							\
+	".org	. - (887b - 886b) + (889b - 888b)\n"			\
+	".org	. - (889b - 888b) + (887b - 886b)\n"			\
+	".previous\n"							\
+	".endif\n"
+
+#define __ALTERNATIVE_CFG(old_c, new_c, vendor_id, errata_id, enable)	\
+	"886 :\n"							\
+	".option push\n"						\
+	".option norvc\n"						\
+	".option norelax\n"						\
+	old_c "\n"							\
+	".option pop\n"							\
+	"887 :\n"							\
+	ALT_NEW_CONTENT(vendor_id, errata_id, enable, new_c)
+
+#define _ALTERNATIVE_CFG(old_c, new_c, vendor_id, errata_id, CONFIG_k)	\
+	__ALTERNATIVE_CFG(old_c, new_c, vendor_id, errata_id, IS_ENABLED(CONFIG_k))
+
+#define __ALTERNATIVE_CFG_2(old_c, new_c_1, vendor_id_1, errata_id_1,	\
+					enable_1,			\
+				   new_c_2, vendor_id_2, errata_id_2,	\
+					enable_2)			\
+	"886 :\n"							\
+	".option push\n"						\
+	".option norvc\n"						\
+	".option norelax\n"						\
+	old_c "\n"							\
+	".option pop\n"							\
+	"887 :\n"							\
+	ALT_NEW_CONTENT(vendor_id_1, errata_id_1, enable_1, new_c_1)	\
+	ALT_NEW_CONTENT(vendor_id_2, errata_id_2, enable_2, new_c_2)
+
+#define _ALTERNATIVE_CFG_2(old_c, new_c_1, vendor_id_1, errata_id_1,	\
+					CONFIG_k_1,			\
+				  new_c_2, vendor_id_2, errata_id_2,	\
+					CONFIG_k_2)			\
+	__ALTERNATIVE_CFG_2(old_c, new_c_1, vendor_id_1, errata_id_1,	\
+					IS_ENABLED(CONFIG_k_1),		\
+				   new_c_2, vendor_id_2, errata_id_2,	\
+					IS_ENABLED(CONFIG_k_2))
+
+#endif /* __ASSEMBLY__ */
+
+#else /* CONFIG_RISCV_ALTERNATIVE */
+#ifdef __ASSEMBLY__
+
+.macro __ALTERNATIVE_CFG old_c
+	\old_c
+.endm
+
+#define _ALTERNATIVE_CFG(old_c, new_c, vendor_id, errata_id, CONFIG_k) \
+	__ALTERNATIVE_CFG old_c
+
+#define _ALTERNATIVE_CFG_2(old_c, new_c_1, vendor_id_1, errata_id_1,	\
+					CONFIG_k_1,			\
+				  new_c_2, vendor_id_2, errata_id_2,	\
+					CONFIG_k_2)			\
+       __ALTERNATIVE_CFG old_c
+
+#else /* !__ASSEMBLY__ */
+
+#define __ALTERNATIVE_CFG(old_c)  \
+	old_c "\n"
+
+#define _ALTERNATIVE_CFG(old_c, new_c, vendor_id, errata_id, CONFIG_k) \
+	__ALTERNATIVE_CFG(old_c)
+
+#define _ALTERNATIVE_CFG_2(old_c, new_c_1, vendor_id_1, errata_id_1,	\
+					CONFIG_k_1,			\
+				  new_c_2, vendor_id_2, errata_id_2,	\
+					CONFIG_k_2) \
+       __ALTERNATIVE_CFG(old_c)
+
+#endif /* __ASSEMBLY__ */
+#endif /* CONFIG_RISCV_ALTERNATIVE */
+
+/*
+ * Usage:
+ *   ALTERNATIVE(old_content, new_content, vendor_id, errata_id, CONFIG_k)
+ * in the assembly code. Otherwise,
+ *   asm(ALTERNATIVE(old_content, new_content, vendor_id, errata_id, CONFIG_k));
+ *
+ * old_content: The old content which is probably replaced with new content.
+ * new_content: The new content.
+ * vendor_id: The CPU vendor ID.
+ * errata_id: The errata ID.
+ * CONFIG_k: The Kconfig of this errata. When Kconfig is disabled, the old
+ *	     content will alwyas be executed.
+ */
+#define ALTERNATIVE(old_content, new_content, vendor_id, errata_id, CONFIG_k) \
+	_ALTERNATIVE_CFG(old_content, new_content, vendor_id, errata_id, CONFIG_k)
+
+/*
+ * A vendor wants to replace an old_content, but another vendor has used
+ * ALTERNATIVE() to patch its customized content at the same location. In
+ * this case, this vendor can create a new macro ALTERNATIVE_2() based
+ * on the following sample code and then replace ALTERNATIVE() with
+ * ALTERNATIVE_2() to append its customized content.
+ */
+#define ALTERNATIVE_2(old_content, new_content_1, vendor_id_1,		\
+					errata_id_1, CONFIG_k_1,	\
+				   new_content_2, vendor_id_2,		\
+					errata_id_2, CONFIG_k_2)	\
+	_ALTERNATIVE_CFG_2(old_content, new_content_1, vendor_id_1,	\
+					    errata_id_1, CONFIG_k_1,	\
+					new_content_2, vendor_id_2,	\
+					    errata_id_2, CONFIG_k_2)
+
+#endif
diff --git a/arch/riscv/include/asm/alternative.h b/arch/riscv/include/asm/alternative.h
new file mode 100644
index 000000000..6511dd73e
--- /dev/null
+++ b/arch/riscv/include/asm/alternative.h
@@ -0,0 +1,62 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2021 Sifive.
+ */
+
+#ifndef __ASM_ALTERNATIVE_H
+#define __ASM_ALTERNATIVE_H
+
+#define ERRATA_STRING_LENGTH_MAX 32
+
+#include <asm/alternative-macros.h>
+
+#ifndef __ASSEMBLY__
+
+#ifdef CONFIG_RISCV_ALTERNATIVE
+
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/stddef.h>
+#include <asm/hwcap.h>
+
+#define RISCV_ALTERNATIVES_BOOT		0 /* alternatives applied during regular boot */
+#define RISCV_ALTERNATIVES_MODULE	1 /* alternatives applied during module-init */
+#define RISCV_ALTERNATIVES_EARLY_BOOT	2 /* alternatives applied before mmu start */
+
+void __init apply_boot_alternatives(void);
+void __init apply_early_boot_alternatives(void);
+void apply_module_alternatives(void *start, size_t length);
+
+struct alt_entry {
+	void *old_ptr;		 /* address of original instruciton or data  */
+	void *alt_ptr;		 /* address of replacement instruction or data */
+	unsigned long vendor_id; /* cpu vendor id */
+	unsigned long alt_len;   /* The replacement size */
+	unsigned int errata_id;  /* The errata id */
+} __packed;
+
+struct errata_checkfunc_id {
+	unsigned long vendor_id;
+	bool (*func)(struct alt_entry *alt);
+};
+
+void sifive_errata_patch_func(struct alt_entry *begin, struct alt_entry *end,
+			      unsigned long archid, unsigned long impid,
+			      unsigned int stage);
+void thead_errata_patch_func(struct alt_entry *begin, struct alt_entry *end,
+			     unsigned long archid, unsigned long impid,
+			     unsigned int stage);
+
+void riscv_cpufeature_patch_func(struct alt_entry *begin, struct alt_entry *end,
+				 unsigned int stage);
+
+#else /* CONFIG_RISCV_ALTERNATIVE */
+
+static inline void apply_boot_alternatives(void) { }
+static inline void apply_early_boot_alternatives(void) { }
+static inline void apply_module_alternatives(void *start, size_t length) { }
+
+#endif /* CONFIG_RISCV_ALTERNATIVE */
+
+#endif
+#endif
diff --git a/arch/riscv/include/asm/asm-extable.h b/arch/riscv/include/asm/asm-extable.h
new file mode 100644
index 000000000..14be0673f
--- /dev/null
+++ b/arch/riscv/include/asm/asm-extable.h
@@ -0,0 +1,65 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef __ASM_ASM_EXTABLE_H
+#define __ASM_ASM_EXTABLE_H
+
+#define EX_TYPE_NONE			0
+#define EX_TYPE_FIXUP			1
+#define EX_TYPE_BPF			2
+#define EX_TYPE_UACCESS_ERR_ZERO	3
+
+#ifdef __ASSEMBLY__
+
+#define __ASM_EXTABLE_RAW(insn, fixup, type, data)	\
+	.pushsection	__ex_table, "a";		\
+	.balign		4;				\
+	.long		((insn) - .);			\
+	.long		((fixup) - .);			\
+	.short		(type);				\
+	.short		(data);				\
+	.popsection;
+
+	.macro		_asm_extable, insn, fixup
+	__ASM_EXTABLE_RAW(\insn, \fixup, EX_TYPE_FIXUP, 0)
+	.endm
+
+#else /* __ASSEMBLY__ */
+
+#include <linux/bits.h>
+#include <linux/stringify.h>
+#include <asm/gpr-num.h>
+
+#define __ASM_EXTABLE_RAW(insn, fixup, type, data)	\
+	".pushsection	__ex_table, \"a\"\n"		\
+	".balign	4\n"				\
+	".long		((" insn ") - .)\n"		\
+	".long		((" fixup ") - .)\n"		\
+	".short		(" type ")\n"			\
+	".short		(" data ")\n"			\
+	".popsection\n"
+
+#define _ASM_EXTABLE(insn, fixup)	\
+	__ASM_EXTABLE_RAW(#insn, #fixup, __stringify(EX_TYPE_FIXUP), "0")
+
+#define EX_DATA_REG_ERR_SHIFT	0
+#define EX_DATA_REG_ERR		GENMASK(4, 0)
+#define EX_DATA_REG_ZERO_SHIFT	5
+#define EX_DATA_REG_ZERO	GENMASK(9, 5)
+
+#define EX_DATA_REG(reg, gpr)						\
+	"((.L__gpr_num_" #gpr ") << " __stringify(EX_DATA_REG_##reg##_SHIFT) ")"
+
+#define _ASM_EXTABLE_UACCESS_ERR_ZERO(insn, fixup, err, zero)		\
+	__DEFINE_ASM_GPR_NUMS						\
+	__ASM_EXTABLE_RAW(#insn, #fixup, 				\
+			  __stringify(EX_TYPE_UACCESS_ERR_ZERO),	\
+			  "("						\
+			    EX_DATA_REG(ERR, err) " | "			\
+			    EX_DATA_REG(ZERO, zero)			\
+			  ")")
+
+#define _ASM_EXTABLE_UACCESS_ERR(insn, fixup, err)			\
+	_ASM_EXTABLE_UACCESS_ERR_ZERO(insn, fixup, err, zero)
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __ASM_ASM_EXTABLE_H */
diff --git a/arch/riscv/include/asm/asm-offsets.h b/arch/riscv/include/asm/asm-offsets.h
new file mode 100644
index 000000000..d370ee36a
--- /dev/null
+++ b/arch/riscv/include/asm/asm-offsets.h
@@ -0,0 +1 @@
+#include <generated/asm-offsets.h>
diff --git a/arch/riscv/include/asm/asm-prototypes.h b/arch/riscv/include/asm/asm-prototypes.h
new file mode 100644
index 000000000..ef386fcf3
--- /dev/null
+++ b/arch/riscv/include/asm/asm-prototypes.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_RISCV_PROTOTYPES_H
+#define _ASM_RISCV_PROTOTYPES_H
+
+#include <linux/ftrace.h>
+#include <asm-generic/asm-prototypes.h>
+
+long long __lshrti3(long long a, int b);
+long long __ashrti3(long long a, int b);
+long long __ashlti3(long long a, int b);
+
+
+#define DECLARE_DO_ERROR_INFO(name)	asmlinkage void name(struct pt_regs *regs)
+
+DECLARE_DO_ERROR_INFO(do_trap_unknown);
+DECLARE_DO_ERROR_INFO(do_trap_insn_misaligned);
+DECLARE_DO_ERROR_INFO(do_trap_insn_fault);
+DECLARE_DO_ERROR_INFO(do_trap_insn_illegal);
+DECLARE_DO_ERROR_INFO(do_trap_load_fault);
+DECLARE_DO_ERROR_INFO(do_trap_load_misaligned);
+DECLARE_DO_ERROR_INFO(do_trap_store_misaligned);
+DECLARE_DO_ERROR_INFO(do_trap_store_fault);
+DECLARE_DO_ERROR_INFO(do_trap_ecall_u);
+DECLARE_DO_ERROR_INFO(do_trap_ecall_s);
+DECLARE_DO_ERROR_INFO(do_trap_ecall_m);
+DECLARE_DO_ERROR_INFO(do_trap_break);
+
+asmlinkage unsigned long get_overflow_stack(void);
+asmlinkage void handle_bad_stack(struct pt_regs *regs);
+
+#endif /* _ASM_RISCV_PROTOTYPES_H */
diff --git a/arch/riscv/include/asm/asm.h b/arch/riscv/include/asm/asm.h
new file mode 100644
index 000000000..816e753de
--- /dev/null
+++ b/arch/riscv/include/asm/asm.h
@@ -0,0 +1,86 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2015 Regents of the University of California
+ */
+
+#ifndef _ASM_RISCV_ASM_H
+#define _ASM_RISCV_ASM_H
+
+#ifdef __ASSEMBLY__
+#define __ASM_STR(x)	x
+#else
+#define __ASM_STR(x)	#x
+#endif
+
+#if __riscv_xlen == 64
+#define __REG_SEL(a, b)	__ASM_STR(a)
+#elif __riscv_xlen == 32
+#define __REG_SEL(a, b)	__ASM_STR(b)
+#else
+#error "Unexpected __riscv_xlen"
+#endif
+
+#define REG_L		__REG_SEL(ld, lw)
+#define REG_S		__REG_SEL(sd, sw)
+#define REG_SC		__REG_SEL(sc.d, sc.w)
+#define REG_AMOSWAP_AQ	__REG_SEL(amoswap.d.aq, amoswap.w.aq)
+#define REG_ASM		__REG_SEL(.dword, .word)
+#define SZREG		__REG_SEL(8, 4)
+#define LGREG		__REG_SEL(3, 2)
+
+#if __SIZEOF_POINTER__ == 8
+#ifdef __ASSEMBLY__
+#define RISCV_PTR		.dword
+#define RISCV_SZPTR		8
+#define RISCV_LGPTR		3
+#else
+#define RISCV_PTR		".dword"
+#define RISCV_SZPTR		"8"
+#define RISCV_LGPTR		"3"
+#endif
+#elif __SIZEOF_POINTER__ == 4
+#ifdef __ASSEMBLY__
+#define RISCV_PTR		.word
+#define RISCV_SZPTR		4
+#define RISCV_LGPTR		2
+#else
+#define RISCV_PTR		".word"
+#define RISCV_SZPTR		"4"
+#define RISCV_LGPTR		"2"
+#endif
+#else
+#error "Unexpected __SIZEOF_POINTER__"
+#endif
+
+#if (__SIZEOF_INT__ == 4)
+#define RISCV_INT		__ASM_STR(.word)
+#define RISCV_SZINT		__ASM_STR(4)
+#define RISCV_LGINT		__ASM_STR(2)
+#else
+#error "Unexpected __SIZEOF_INT__"
+#endif
+
+#if (__SIZEOF_SHORT__ == 2)
+#define RISCV_SHORT		__ASM_STR(.half)
+#define RISCV_SZSHORT		__ASM_STR(2)
+#define RISCV_LGSHORT		__ASM_STR(1)
+#else
+#error "Unexpected __SIZEOF_SHORT__"
+#endif
+
+#ifdef __ASSEMBLY__
+
+/* Common assembly source macros */
+
+/*
+ * NOP sequence
+ */
+.macro	nops, num
+	.rept	\num
+	nop
+	.endr
+.endm
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_RISCV_ASM_H */
diff --git a/arch/riscv/include/asm/atomic.h b/arch/riscv/include/asm/atomic.h
new file mode 100644
index 000000000..0dfe9d857
--- /dev/null
+++ b/arch/riscv/include/asm/atomic.h
@@ -0,0 +1,438 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Copyright (C) 2012 Regents of the University of California
+ * Copyright (C) 2017 SiFive
+ */
+
+#ifndef _ASM_RISCV_ATOMIC_H
+#define _ASM_RISCV_ATOMIC_H
+
+#ifdef CONFIG_GENERIC_ATOMIC64
+# include <asm-generic/atomic64.h>
+#else
+# if (__riscv_xlen < 64)
+#  error "64-bit atomics require XLEN to be at least 64"
+# endif
+#endif
+
+#include <asm/cmpxchg.h>
+#include <asm/barrier.h>
+
+#define __atomic_acquire_fence()					\
+	__asm__ __volatile__(RISCV_ACQUIRE_BARRIER "" ::: "memory")
+
+#define __atomic_release_fence()					\
+	__asm__ __volatile__(RISCV_RELEASE_BARRIER "" ::: "memory");
+
+static __always_inline int arch_atomic_read(const atomic_t *v)
+{
+	return READ_ONCE(v->counter);
+}
+static __always_inline void arch_atomic_set(atomic_t *v, int i)
+{
+	WRITE_ONCE(v->counter, i);
+}
+
+#ifndef CONFIG_GENERIC_ATOMIC64
+#define ATOMIC64_INIT(i) { (i) }
+static __always_inline s64 arch_atomic64_read(const atomic64_t *v)
+{
+	return READ_ONCE(v->counter);
+}
+static __always_inline void arch_atomic64_set(atomic64_t *v, s64 i)
+{
+	WRITE_ONCE(v->counter, i);
+}
+#endif
+
+/*
+ * First, the atomic ops that have no ordering constraints and therefor don't
+ * have the AQ or RL bits set.  These don't return anything, so there's only
+ * one version to worry about.
+ */
+#define ATOMIC_OP(op, asm_op, I, asm_type, c_type, prefix)		\
+static __always_inline							\
+void arch_atomic##prefix##_##op(c_type i, atomic##prefix##_t *v)	\
+{									\
+	__asm__ __volatile__ (						\
+		"	amo" #asm_op "." #asm_type " zero, %1, %0"	\
+		: "+A" (v->counter)					\
+		: "r" (I)						\
+		: "memory");						\
+}									\
+
+#ifdef CONFIG_GENERIC_ATOMIC64
+#define ATOMIC_OPS(op, asm_op, I)					\
+        ATOMIC_OP (op, asm_op, I, w, int,   )
+#else
+#define ATOMIC_OPS(op, asm_op, I)					\
+        ATOMIC_OP (op, asm_op, I, w, int,   )				\
+        ATOMIC_OP (op, asm_op, I, d, s64, 64)
+#endif
+
+ATOMIC_OPS(add, add,  i)
+ATOMIC_OPS(sub, add, -i)
+ATOMIC_OPS(and, and,  i)
+ATOMIC_OPS( or,  or,  i)
+ATOMIC_OPS(xor, xor,  i)
+
+#undef ATOMIC_OP
+#undef ATOMIC_OPS
+
+/*
+ * Atomic ops that have ordered, relaxed, acquire, and release variants.
+ * There's two flavors of these: the arithmatic ops have both fetch and return
+ * versions, while the logical ops only have fetch versions.
+ */
+#define ATOMIC_FETCH_OP(op, asm_op, I, asm_type, c_type, prefix)	\
+static __always_inline							\
+c_type arch_atomic##prefix##_fetch_##op##_relaxed(c_type i,		\
+					     atomic##prefix##_t *v)	\
+{									\
+	register c_type ret;						\
+	__asm__ __volatile__ (						\
+		"	amo" #asm_op "." #asm_type " %1, %2, %0"	\
+		: "+A" (v->counter), "=r" (ret)				\
+		: "r" (I)						\
+		: "memory");						\
+	return ret;							\
+}									\
+static __always_inline							\
+c_type arch_atomic##prefix##_fetch_##op(c_type i, atomic##prefix##_t *v)	\
+{									\
+	register c_type ret;						\
+	__asm__ __volatile__ (						\
+		"	amo" #asm_op "." #asm_type ".aqrl  %1, %2, %0"	\
+		: "+A" (v->counter), "=r" (ret)				\
+		: "r" (I)						\
+		: "memory");						\
+	return ret;							\
+}
+
+#define ATOMIC_OP_RETURN(op, asm_op, c_op, I, asm_type, c_type, prefix)	\
+static __always_inline							\
+c_type arch_atomic##prefix##_##op##_return_relaxed(c_type i,		\
+					      atomic##prefix##_t *v)	\
+{									\
+        return arch_atomic##prefix##_fetch_##op##_relaxed(i, v) c_op I;	\
+}									\
+static __always_inline							\
+c_type arch_atomic##prefix##_##op##_return(c_type i, atomic##prefix##_t *v)	\
+{									\
+        return arch_atomic##prefix##_fetch_##op(i, v) c_op I;		\
+}
+
+#ifdef CONFIG_GENERIC_ATOMIC64
+#define ATOMIC_OPS(op, asm_op, c_op, I)					\
+        ATOMIC_FETCH_OP( op, asm_op,       I, w, int,   )		\
+        ATOMIC_OP_RETURN(op, asm_op, c_op, I, w, int,   )
+#else
+#define ATOMIC_OPS(op, asm_op, c_op, I)					\
+        ATOMIC_FETCH_OP( op, asm_op,       I, w, int,   )		\
+        ATOMIC_OP_RETURN(op, asm_op, c_op, I, w, int,   )		\
+        ATOMIC_FETCH_OP( op, asm_op,       I, d, s64, 64)		\
+        ATOMIC_OP_RETURN(op, asm_op, c_op, I, d, s64, 64)
+#endif
+
+ATOMIC_OPS(add, add, +,  i)
+ATOMIC_OPS(sub, add, +, -i)
+
+#define arch_atomic_add_return_relaxed	arch_atomic_add_return_relaxed
+#define arch_atomic_sub_return_relaxed	arch_atomic_sub_return_relaxed
+#define arch_atomic_add_return		arch_atomic_add_return
+#define arch_atomic_sub_return		arch_atomic_sub_return
+
+#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_add		arch_atomic_fetch_add
+#define arch_atomic_fetch_sub		arch_atomic_fetch_sub
+
+#ifndef CONFIG_GENERIC_ATOMIC64
+#define arch_atomic64_add_return_relaxed	arch_atomic64_add_return_relaxed
+#define arch_atomic64_sub_return_relaxed	arch_atomic64_sub_return_relaxed
+#define arch_atomic64_add_return		arch_atomic64_add_return
+#define arch_atomic64_sub_return		arch_atomic64_sub_return
+
+#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_add		arch_atomic64_fetch_add
+#define arch_atomic64_fetch_sub		arch_atomic64_fetch_sub
+#endif
+
+#undef ATOMIC_OPS
+
+#ifdef CONFIG_GENERIC_ATOMIC64
+#define ATOMIC_OPS(op, asm_op, I)					\
+        ATOMIC_FETCH_OP(op, asm_op, I, w, int,   )
+#else
+#define ATOMIC_OPS(op, asm_op, I)					\
+        ATOMIC_FETCH_OP(op, asm_op, I, w, int,   )			\
+        ATOMIC_FETCH_OP(op, asm_op, I, d, s64, 64)
+#endif
+
+ATOMIC_OPS(and, and, i)
+ATOMIC_OPS( or,  or, i)
+ATOMIC_OPS(xor, xor, i)
+
+#define arch_atomic_fetch_and_relaxed	arch_atomic_fetch_and_relaxed
+#define arch_atomic_fetch_or_relaxed	arch_atomic_fetch_or_relaxed
+#define arch_atomic_fetch_xor_relaxed	arch_atomic_fetch_xor_relaxed
+#define arch_atomic_fetch_and		arch_atomic_fetch_and
+#define arch_atomic_fetch_or		arch_atomic_fetch_or
+#define arch_atomic_fetch_xor		arch_atomic_fetch_xor
+
+#ifndef CONFIG_GENERIC_ATOMIC64
+#define arch_atomic64_fetch_and_relaxed	arch_atomic64_fetch_and_relaxed
+#define arch_atomic64_fetch_or_relaxed	arch_atomic64_fetch_or_relaxed
+#define arch_atomic64_fetch_xor_relaxed	arch_atomic64_fetch_xor_relaxed
+#define arch_atomic64_fetch_and		arch_atomic64_fetch_and
+#define arch_atomic64_fetch_or		arch_atomic64_fetch_or
+#define arch_atomic64_fetch_xor		arch_atomic64_fetch_xor
+#endif
+
+#undef ATOMIC_OPS
+
+#undef ATOMIC_FETCH_OP
+#undef ATOMIC_OP_RETURN
+
+/* This is required to provide a full barrier on success. */
+static __always_inline int arch_atomic_fetch_add_unless(atomic_t *v, int a, int u)
+{
+       int prev, rc;
+
+	__asm__ __volatile__ (
+		"0:	lr.w     %[p],  %[c]\n"
+		"	beq      %[p],  %[u], 1f\n"
+		"	add      %[rc], %[p], %[a]\n"
+		"	sc.w.rl  %[rc], %[rc], %[c]\n"
+		"	bnez     %[rc], 0b\n"
+		"	fence    rw, rw\n"
+		"1:\n"
+		: [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
+		: [a]"r" (a), [u]"r" (u)
+		: "memory");
+	return prev;
+}
+#define arch_atomic_fetch_add_unless arch_atomic_fetch_add_unless
+
+#ifndef CONFIG_GENERIC_ATOMIC64
+static __always_inline s64 arch_atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u)
+{
+       s64 prev;
+       long rc;
+
+	__asm__ __volatile__ (
+		"0:	lr.d     %[p],  %[c]\n"
+		"	beq      %[p],  %[u], 1f\n"
+		"	add      %[rc], %[p], %[a]\n"
+		"	sc.d.rl  %[rc], %[rc], %[c]\n"
+		"	bnez     %[rc], 0b\n"
+		"	fence    rw, rw\n"
+		"1:\n"
+		: [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
+		: [a]"r" (a), [u]"r" (u)
+		: "memory");
+	return prev;
+}
+#define arch_atomic64_fetch_add_unless arch_atomic64_fetch_add_unless
+#endif
+
+/*
+ * atomic_{cmp,}xchg is required to have exactly the same ordering semantics as
+ * {cmp,}xchg and the operations that return, so they need a full barrier.
+ */
+#define ATOMIC_OP(c_t, prefix, size)					\
+static __always_inline							\
+c_t arch_atomic##prefix##_xchg_relaxed(atomic##prefix##_t *v, c_t n)	\
+{									\
+	return __xchg_relaxed(&(v->counter), n, size);			\
+}									\
+static __always_inline							\
+c_t arch_atomic##prefix##_xchg_acquire(atomic##prefix##_t *v, c_t n)	\
+{									\
+	return __xchg_acquire(&(v->counter), n, size);			\
+}									\
+static __always_inline							\
+c_t arch_atomic##prefix##_xchg_release(atomic##prefix##_t *v, c_t n)	\
+{									\
+	return __xchg_release(&(v->counter), n, size);			\
+}									\
+static __always_inline							\
+c_t arch_atomic##prefix##_xchg(atomic##prefix##_t *v, c_t n)		\
+{									\
+	return __xchg(&(v->counter), n, size);				\
+}									\
+static __always_inline							\
+c_t arch_atomic##prefix##_cmpxchg_relaxed(atomic##prefix##_t *v,	\
+				     c_t o, c_t n)			\
+{									\
+	return __cmpxchg_relaxed(&(v->counter), o, n, size);		\
+}									\
+static __always_inline							\
+c_t arch_atomic##prefix##_cmpxchg_acquire(atomic##prefix##_t *v,	\
+				     c_t o, c_t n)			\
+{									\
+	return __cmpxchg_acquire(&(v->counter), o, n, size);		\
+}									\
+static __always_inline							\
+c_t arch_atomic##prefix##_cmpxchg_release(atomic##prefix##_t *v,	\
+				     c_t o, c_t n)			\
+{									\
+	return __cmpxchg_release(&(v->counter), o, n, size);		\
+}									\
+static __always_inline							\
+c_t arch_atomic##prefix##_cmpxchg(atomic##prefix##_t *v, c_t o, c_t n)	\
+{									\
+	return __cmpxchg(&(v->counter), o, n, size);			\
+}
+
+#ifdef CONFIG_GENERIC_ATOMIC64
+#define ATOMIC_OPS()							\
+	ATOMIC_OP(int,   , 4)
+#else
+#define ATOMIC_OPS()							\
+	ATOMIC_OP(int,   , 4)						\
+	ATOMIC_OP(s64, 64, 8)
+#endif
+
+ATOMIC_OPS()
+
+#define arch_atomic_xchg_relaxed	arch_atomic_xchg_relaxed
+#define arch_atomic_xchg_acquire	arch_atomic_xchg_acquire
+#define arch_atomic_xchg_release	arch_atomic_xchg_release
+#define arch_atomic_xchg		arch_atomic_xchg
+#define arch_atomic_cmpxchg_relaxed	arch_atomic_cmpxchg_relaxed
+#define arch_atomic_cmpxchg_acquire	arch_atomic_cmpxchg_acquire
+#define arch_atomic_cmpxchg_release	arch_atomic_cmpxchg_release
+#define arch_atomic_cmpxchg		arch_atomic_cmpxchg
+
+#undef ATOMIC_OPS
+#undef ATOMIC_OP
+
+static __always_inline bool arch_atomic_inc_unless_negative(atomic_t *v)
+{
+	int prev, rc;
+
+	__asm__ __volatile__ (
+		"0:	lr.w      %[p],  %[c]\n"
+		"	bltz      %[p],  1f\n"
+		"	addi      %[rc], %[p], 1\n"
+		"	sc.w.rl   %[rc], %[rc], %[c]\n"
+		"	bnez      %[rc], 0b\n"
+		"	fence     rw, rw\n"
+		"1:\n"
+		: [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
+		:
+		: "memory");
+	return !(prev < 0);
+}
+
+#define arch_atomic_inc_unless_negative arch_atomic_inc_unless_negative
+
+static __always_inline bool arch_atomic_dec_unless_positive(atomic_t *v)
+{
+	int prev, rc;
+
+	__asm__ __volatile__ (
+		"0:	lr.w      %[p],  %[c]\n"
+		"	bgtz      %[p],  1f\n"
+		"	addi      %[rc], %[p], -1\n"
+		"	sc.w.rl   %[rc], %[rc], %[c]\n"
+		"	bnez      %[rc], 0b\n"
+		"	fence     rw, rw\n"
+		"1:\n"
+		: [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
+		:
+		: "memory");
+	return !(prev > 0);
+}
+
+#define arch_atomic_dec_unless_positive arch_atomic_dec_unless_positive
+
+static __always_inline int arch_atomic_dec_if_positive(atomic_t *v)
+{
+       int prev, rc;
+
+	__asm__ __volatile__ (
+		"0:	lr.w     %[p],  %[c]\n"
+		"	addi     %[rc], %[p], -1\n"
+		"	bltz     %[rc], 1f\n"
+		"	sc.w.rl  %[rc], %[rc], %[c]\n"
+		"	bnez     %[rc], 0b\n"
+		"	fence    rw, rw\n"
+		"1:\n"
+		: [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
+		:
+		: "memory");
+	return prev - 1;
+}
+
+#define arch_atomic_dec_if_positive arch_atomic_dec_if_positive
+
+#ifndef CONFIG_GENERIC_ATOMIC64
+static __always_inline bool arch_atomic64_inc_unless_negative(atomic64_t *v)
+{
+	s64 prev;
+	long rc;
+
+	__asm__ __volatile__ (
+		"0:	lr.d      %[p],  %[c]\n"
+		"	bltz      %[p],  1f\n"
+		"	addi      %[rc], %[p], 1\n"
+		"	sc.d.rl   %[rc], %[rc], %[c]\n"
+		"	bnez      %[rc], 0b\n"
+		"	fence     rw, rw\n"
+		"1:\n"
+		: [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
+		:
+		: "memory");
+	return !(prev < 0);
+}
+
+#define arch_atomic64_inc_unless_negative arch_atomic64_inc_unless_negative
+
+static __always_inline bool arch_atomic64_dec_unless_positive(atomic64_t *v)
+{
+	s64 prev;
+	long rc;
+
+	__asm__ __volatile__ (
+		"0:	lr.d      %[p],  %[c]\n"
+		"	bgtz      %[p],  1f\n"
+		"	addi      %[rc], %[p], -1\n"
+		"	sc.d.rl   %[rc], %[rc], %[c]\n"
+		"	bnez      %[rc], 0b\n"
+		"	fence     rw, rw\n"
+		"1:\n"
+		: [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
+		:
+		: "memory");
+	return !(prev > 0);
+}
+
+#define arch_atomic64_dec_unless_positive arch_atomic64_dec_unless_positive
+
+static __always_inline s64 arch_atomic64_dec_if_positive(atomic64_t *v)
+{
+       s64 prev;
+       long rc;
+
+	__asm__ __volatile__ (
+		"0:	lr.d     %[p],  %[c]\n"
+		"	addi      %[rc], %[p], -1\n"
+		"	bltz     %[rc], 1f\n"
+		"	sc.d.rl  %[rc], %[rc], %[c]\n"
+		"	bnez     %[rc], 0b\n"
+		"	fence    rw, rw\n"
+		"1:\n"
+		: [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
+		:
+		: "memory");
+	return prev - 1;
+}
+
+#define arch_atomic64_dec_if_positive	arch_atomic64_dec_if_positive
+#endif
+
+#endif /* _ASM_RISCV_ATOMIC_H */
diff --git a/arch/riscv/include/asm/barrier.h b/arch/riscv/include/asm/barrier.h
new file mode 100644
index 000000000..110752594
--- /dev/null
+++ b/arch/riscv/include/asm/barrier.h
@@ -0,0 +1,78 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Based on arch/arm/include/asm/barrier.h
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2013 Regents of the University of California
+ * Copyright (C) 2017 SiFive
+ */
+
+#ifndef _ASM_RISCV_BARRIER_H
+#define _ASM_RISCV_BARRIER_H
+
+#ifndef __ASSEMBLY__
+
+#define nop()		__asm__ __volatile__ ("nop")
+#define __nops(n)	".rept	" #n "\nnop\n.endr\n"
+#define nops(n)		__asm__ __volatile__ (__nops(n))
+
+#define RISCV_FENCE(p, s) \
+	__asm__ __volatile__ ("fence " #p "," #s : : : "memory")
+
+/* These barriers need to enforce ordering on both devices or memory. */
+#define mb()		RISCV_FENCE(iorw,iorw)
+#define rmb()		RISCV_FENCE(ir,ir)
+#define wmb()		RISCV_FENCE(ow,ow)
+
+/* These barriers do not need to enforce ordering on devices, just memory. */
+#define __smp_mb()	RISCV_FENCE(rw,rw)
+#define __smp_rmb()	RISCV_FENCE(r,r)
+#define __smp_wmb()	RISCV_FENCE(w,w)
+
+#define __smp_store_release(p, v)					\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	RISCV_FENCE(rw,w);						\
+	WRITE_ONCE(*p, v);						\
+} while (0)
+
+#define __smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = READ_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	RISCV_FENCE(r,rw);						\
+	___p1;								\
+})
+
+/*
+ * This is a very specific barrier: it's currently only used in two places in
+ * the kernel, both in the scheduler.  See include/linux/spinlock.h for the two
+ * orderings it guarantees, but the "critical section is RCsc" guarantee
+ * mandates a barrier on RISC-V.  The sequence looks like:
+ *
+ *    lr.aq lock
+ *    sc    lock <= LOCKED
+ *    smp_mb__after_spinlock()
+ *    // critical section
+ *    lr    lock
+ *    sc.rl lock <= UNLOCKED
+ *
+ * The AQ/RL pair provides a RCpc critical section, but there's not really any
+ * way we can take advantage of that here because the ordering is only enforced
+ * on that one lock.  Thus, we're just doing a full fence.
+ *
+ * Since we allow writeX to be called from preemptive regions we need at least
+ * an "o" in the predecessor set to ensure device writes are visible before the
+ * task is marked as available for scheduling on a new hart.  While I don't see
+ * any concrete reason we need a full IO fence, it seems safer to just upgrade
+ * this in order to avoid any IO crossing a scheduling boundary.  In both
+ * instances the scheduler pairs this with an mb(), so nothing is necessary on
+ * the new hart.
+ */
+#define smp_mb__after_spinlock()	RISCV_FENCE(iorw,iorw)
+
+#include <asm-generic/barrier.h>
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_RISCV_BARRIER_H */
diff --git a/arch/riscv/include/asm/bitops.h b/arch/riscv/include/asm/bitops.h
new file mode 100644
index 000000000..3540b6909
--- /dev/null
+++ b/arch/riscv/include/asm/bitops.h
@@ -0,0 +1,204 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ */
+
+#ifndef _ASM_RISCV_BITOPS_H
+#define _ASM_RISCV_BITOPS_H
+
+#ifndef _LINUX_BITOPS_H
+#error "Only <linux/bitops.h> can be included directly"
+#endif /* _LINUX_BITOPS_H */
+
+#include <linux/compiler.h>
+#include <linux/irqflags.h>
+#include <asm/barrier.h>
+#include <asm/bitsperlong.h>
+
+#include <asm-generic/bitops/__ffs.h>
+#include <asm-generic/bitops/ffz.h>
+#include <asm-generic/bitops/fls.h>
+#include <asm-generic/bitops/__fls.h>
+#include <asm-generic/bitops/fls64.h>
+#include <asm-generic/bitops/sched.h>
+#include <asm-generic/bitops/ffs.h>
+
+#include <asm-generic/bitops/hweight.h>
+
+#if (BITS_PER_LONG == 64)
+#define __AMO(op)	"amo" #op ".d"
+#elif (BITS_PER_LONG == 32)
+#define __AMO(op)	"amo" #op ".w"
+#else
+#error "Unexpected BITS_PER_LONG"
+#endif
+
+#define __test_and_op_bit_ord(op, mod, nr, addr, ord)		\
+({								\
+	unsigned long __res, __mask;				\
+	__mask = BIT_MASK(nr);					\
+	__asm__ __volatile__ (					\
+		__AMO(op) #ord " %0, %2, %1"			\
+		: "=r" (__res), "+A" (addr[BIT_WORD(nr)])	\
+		: "r" (mod(__mask))				\
+		: "memory");					\
+	((__res & __mask) != 0);				\
+})
+
+#define __op_bit_ord(op, mod, nr, addr, ord)			\
+	__asm__ __volatile__ (					\
+		__AMO(op) #ord " zero, %1, %0"			\
+		: "+A" (addr[BIT_WORD(nr)])			\
+		: "r" (mod(BIT_MASK(nr)))			\
+		: "memory");
+
+#define __test_and_op_bit(op, mod, nr, addr) 			\
+	__test_and_op_bit_ord(op, mod, nr, addr, .aqrl)
+#define __op_bit(op, mod, nr, addr)				\
+	__op_bit_ord(op, mod, nr, addr, )
+
+/* Bitmask modifiers */
+#define __NOP(x)	(x)
+#define __NOT(x)	(~(x))
+
+/**
+ * test_and_set_bit - Set a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation may be reordered on other architectures than x86.
+ */
+static inline int test_and_set_bit(int nr, volatile unsigned long *addr)
+{
+	return __test_and_op_bit(or, __NOP, nr, addr);
+}
+
+/**
+ * test_and_clear_bit - Clear a bit and return its old value
+ * @nr: Bit to clear
+ * @addr: Address to count from
+ *
+ * This operation can be reordered on other architectures other than x86.
+ */
+static inline int test_and_clear_bit(int nr, volatile unsigned long *addr)
+{
+	return __test_and_op_bit(and, __NOT, nr, addr);
+}
+
+/**
+ * test_and_change_bit - Change a bit and return its old value
+ * @nr: Bit to change
+ * @addr: Address to count from
+ *
+ * This operation is atomic and cannot be reordered.
+ * It also implies a memory barrier.
+ */
+static inline int test_and_change_bit(int nr, volatile unsigned long *addr)
+{
+	return __test_and_op_bit(xor, __NOP, nr, addr);
+}
+
+/**
+ * set_bit - Atomically set a bit in memory
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * Note: there are no guarantees that this function will not be reordered
+ * on non x86 architectures, so if you are writing portable code,
+ * make sure not to rely on its reordering guarantees.
+ *
+ * Note that @nr may be almost arbitrarily large; this function is not
+ * restricted to acting on a single-word quantity.
+ */
+static inline void set_bit(int nr, volatile unsigned long *addr)
+{
+	__op_bit(or, __NOP, nr, addr);
+}
+
+/**
+ * clear_bit - Clears a bit in memory
+ * @nr: Bit to clear
+ * @addr: Address to start counting from
+ *
+ * Note: there are no guarantees that this function will not be reordered
+ * on non x86 architectures, so if you are writing portable code,
+ * make sure not to rely on its reordering guarantees.
+ */
+static inline void clear_bit(int nr, volatile unsigned long *addr)
+{
+	__op_bit(and, __NOT, nr, addr);
+}
+
+/**
+ * change_bit - Toggle a bit in memory
+ * @nr: Bit to change
+ * @addr: Address to start counting from
+ *
+ * change_bit()  may be reordered on other architectures than x86.
+ * Note that @nr may be almost arbitrarily large; this function is not
+ * restricted to acting on a single-word quantity.
+ */
+static inline void change_bit(int nr, volatile unsigned long *addr)
+{
+	__op_bit(xor, __NOP, nr, addr);
+}
+
+/**
+ * test_and_set_bit_lock - Set a bit and return its old value, for lock
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is atomic and provides acquire barrier semantics.
+ * It can be used to implement bit locks.
+ */
+static inline int test_and_set_bit_lock(
+	unsigned long nr, volatile unsigned long *addr)
+{
+	return __test_and_op_bit_ord(or, __NOP, nr, addr, .aq);
+}
+
+/**
+ * clear_bit_unlock - Clear a bit in memory, for unlock
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * This operation is atomic and provides release barrier semantics.
+ */
+static inline void clear_bit_unlock(
+	unsigned long nr, volatile unsigned long *addr)
+{
+	__op_bit_ord(and, __NOT, nr, addr, .rl);
+}
+
+/**
+ * __clear_bit_unlock - Clear a bit in memory, for unlock
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * This operation is like clear_bit_unlock, however it is not atomic.
+ * It does provide release barrier semantics so it can be used to unlock
+ * a bit lock, however it would only be used if no other CPU can modify
+ * any bits in the memory until the lock is released (a good example is
+ * if the bit lock itself protects access to the other bits in the word).
+ *
+ * On RISC-V systems there seems to be no benefit to taking advantage of the
+ * non-atomic property here: it's a lot more instructions and we still have to
+ * provide release semantics anyway.
+ */
+static inline void __clear_bit_unlock(
+	unsigned long nr, volatile unsigned long *addr)
+{
+	clear_bit_unlock(nr, addr);
+}
+
+#undef __test_and_op_bit
+#undef __op_bit
+#undef __NOP
+#undef __NOT
+#undef __AMO
+
+#include <asm-generic/bitops/non-atomic.h>
+#include <asm-generic/bitops/le.h>
+#include <asm-generic/bitops/ext2-atomic.h>
+
+#endif /* _ASM_RISCV_BITOPS_H */
diff --git a/arch/riscv/include/asm/bug.h b/arch/riscv/include/asm/bug.h
new file mode 100644
index 000000000..1aaea81fb
--- /dev/null
+++ b/arch/riscv/include/asm/bug.h
@@ -0,0 +1,92 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ */
+
+#ifndef _ASM_RISCV_BUG_H
+#define _ASM_RISCV_BUG_H
+
+#include <linux/compiler.h>
+#include <linux/const.h>
+#include <linux/types.h>
+
+#include <asm/asm.h>
+
+#define __INSN_LENGTH_MASK  _UL(0x3)
+#define __INSN_LENGTH_32    _UL(0x3)
+#define __COMPRESSED_INSN_MASK	_UL(0xffff)
+
+#define __BUG_INSN_32	_UL(0x00100073) /* ebreak */
+#define __BUG_INSN_16	_UL(0x9002) /* c.ebreak */
+
+#define GET_INSN_LENGTH(insn)						\
+({									\
+	unsigned long __len;						\
+	__len = ((insn & __INSN_LENGTH_MASK) == __INSN_LENGTH_32) ?	\
+		4UL : 2UL;						\
+	__len;								\
+})
+
+typedef u32 bug_insn_t;
+
+#ifdef CONFIG_GENERIC_BUG_RELATIVE_POINTERS
+#define __BUG_ENTRY_ADDR	RISCV_INT " 1b - ."
+#define __BUG_ENTRY_FILE	RISCV_INT " %0 - ."
+#else
+#define __BUG_ENTRY_ADDR	RISCV_PTR " 1b"
+#define __BUG_ENTRY_FILE	RISCV_PTR " %0"
+#endif
+
+#ifdef CONFIG_DEBUG_BUGVERBOSE
+#define __BUG_ENTRY			\
+	__BUG_ENTRY_ADDR "\n\t"		\
+	__BUG_ENTRY_FILE "\n\t"		\
+	RISCV_SHORT " %1\n\t"		\
+	RISCV_SHORT " %2"
+#else
+#define __BUG_ENTRY			\
+	__BUG_ENTRY_ADDR "\n\t"		\
+	RISCV_SHORT " %2"
+#endif
+
+#ifdef CONFIG_GENERIC_BUG
+#define __BUG_FLAGS(flags)					\
+do {								\
+	__asm__ __volatile__ (					\
+		"1:\n\t"					\
+			"ebreak\n"				\
+			".pushsection __bug_table,\"aw\"\n\t"	\
+		"2:\n\t"					\
+			__BUG_ENTRY "\n\t"			\
+			".org 2b + %3\n\t"                      \
+			".popsection"				\
+		:						\
+		: "i" (__FILE__), "i" (__LINE__),		\
+		  "i" (flags),					\
+		  "i" (sizeof(struct bug_entry)));              \
+} while (0)
+#else /* CONFIG_GENERIC_BUG */
+#define __BUG_FLAGS(flags) do {					\
+	__asm__ __volatile__ ("ebreak\n");			\
+} while (0)
+#endif /* CONFIG_GENERIC_BUG */
+
+#define BUG() do {						\
+	__BUG_FLAGS(0);						\
+	unreachable();						\
+} while (0)
+
+#define __WARN_FLAGS(flags) __BUG_FLAGS(BUGFLAG_WARNING|(flags))
+
+#define HAVE_ARCH_BUG
+
+#include <asm-generic/bug.h>
+
+struct pt_regs;
+struct task_struct;
+
+void __show_regs(struct pt_regs *regs);
+void die(struct pt_regs *regs, const char *str);
+void do_trap(struct pt_regs *regs, int signo, int code, unsigned long addr);
+
+#endif /* _ASM_RISCV_BUG_H */
diff --git a/arch/riscv/include/asm/cache.h b/arch/riscv/include/asm/cache.h
new file mode 100644
index 000000000..d3036df23
--- /dev/null
+++ b/arch/riscv/include/asm/cache.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2017 Chen Liqin <liqin.chen@sunplusct.com>
+ * Copyright (C) 2012 Regents of the University of California
+ */
+
+#ifndef _ASM_RISCV_CACHE_H
+#define _ASM_RISCV_CACHE_H
+
+#define L1_CACHE_SHIFT		6
+
+#define L1_CACHE_BYTES		(1 << L1_CACHE_SHIFT)
+
+#ifdef CONFIG_RISCV_DMA_NONCOHERENT
+#define ARCH_DMA_MINALIGN L1_CACHE_BYTES
+#endif
+
+/*
+ * RISC-V requires the stack pointer to be 16-byte aligned, so ensure that
+ * the flat loader aligns it accordingly.
+ */
+#ifndef CONFIG_MMU
+#define ARCH_SLAB_MINALIGN	16
+#endif
+
+#endif /* _ASM_RISCV_CACHE_H */
diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h
new file mode 100644
index 000000000..f6fbe7042
--- /dev/null
+++ b/arch/riscv/include/asm/cacheflush.h
@@ -0,0 +1,62 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2015 Regents of the University of California
+ */
+
+#ifndef _ASM_RISCV_CACHEFLUSH_H
+#define _ASM_RISCV_CACHEFLUSH_H
+
+#include <linux/mm.h>
+
+static inline void local_flush_icache_all(void)
+{
+	asm volatile ("fence.i" ::: "memory");
+}
+
+#define PG_dcache_clean PG_arch_1
+
+static inline void flush_dcache_page(struct page *page)
+{
+	if (test_bit(PG_dcache_clean, &page->flags))
+		clear_bit(PG_dcache_clean, &page->flags);
+}
+#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
+
+/*
+ * RISC-V doesn't have an instruction to flush parts of the instruction cache,
+ * so instead we just flush the whole thing.
+ */
+#define flush_icache_range(start, end) flush_icache_all()
+#define flush_icache_user_page(vma, pg, addr, len) \
+	flush_icache_mm(vma->vm_mm, 0)
+
+#ifndef CONFIG_SMP
+
+#define flush_icache_all() local_flush_icache_all()
+#define flush_icache_mm(mm, local) flush_icache_all()
+
+#else /* CONFIG_SMP */
+
+void flush_icache_all(void);
+void flush_icache_mm(struct mm_struct *mm, bool local);
+
+#endif /* CONFIG_SMP */
+
+extern unsigned int riscv_cbom_block_size;
+void riscv_init_cbom_blocksize(void);
+
+#ifdef CONFIG_RISCV_DMA_NONCOHERENT
+void riscv_noncoherent_supported(void);
+#else
+static inline void riscv_noncoherent_supported(void) {}
+#endif
+
+/*
+ * Bits in sys_riscv_flush_icache()'s flags argument.
+ */
+#define SYS_RISCV_FLUSH_ICACHE_LOCAL 1UL
+#define SYS_RISCV_FLUSH_ICACHE_ALL   (SYS_RISCV_FLUSH_ICACHE_LOCAL)
+
+#include <asm-generic/cacheflush.h>
+
+#endif /* _ASM_RISCV_CACHEFLUSH_H */
diff --git a/arch/riscv/include/asm/cacheinfo.h b/arch/riscv/include/asm/cacheinfo.h
new file mode 100644
index 000000000..d1a365215
--- /dev/null
+++ b/arch/riscv/include/asm/cacheinfo.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020 SiFive
+ */
+
+#ifndef _ASM_RISCV_CACHEINFO_H
+#define _ASM_RISCV_CACHEINFO_H
+
+#include <linux/cacheinfo.h>
+
+struct riscv_cacheinfo_ops {
+	const struct attribute_group * (*get_priv_group)(struct cacheinfo
+							*this_leaf);
+};
+
+void riscv_set_cacheinfo_ops(struct riscv_cacheinfo_ops *ops);
+uintptr_t get_cache_size(u32 level, enum cache_type type);
+uintptr_t get_cache_geometry(u32 level, enum cache_type type);
+
+#endif /* _ASM_RISCV_CACHEINFO_H */
diff --git a/arch/riscv/include/asm/clint.h b/arch/riscv/include/asm/clint.h
new file mode 100644
index 000000000..0789fd37b
--- /dev/null
+++ b/arch/riscv/include/asm/clint.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2020 Google, Inc
+ */
+
+#ifndef _ASM_RISCV_CLINT_H
+#define _ASM_RISCV_CLINT_H
+
+#include <linux/types.h>
+#include <asm/mmio.h>
+
+#ifdef CONFIG_RISCV_M_MODE
+/*
+ * This lives in the CLINT driver, but is accessed directly by timex.h to avoid
+ * any overhead when accessing the MMIO timer.
+ *
+ * The ISA defines mtime as a 64-bit memory-mapped register that increments at
+ * a constant frequency, but it doesn't define some other constraints we depend
+ * on (most notably ordering constraints, but also some simpler stuff like the
+ * memory layout).  Thus, this is called "clint_time_val" instead of something
+ * like "riscv_mtime", to signify that these non-ISA assumptions must hold.
+ */
+extern u64 __iomem *clint_time_val;
+#endif
+
+#endif
diff --git a/arch/riscv/include/asm/clocksource.h b/arch/riscv/include/asm/clocksource.h
new file mode 100644
index 000000000..482185566
--- /dev/null
+++ b/arch/riscv/include/asm/clocksource.h
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_CLOCKSOURCE_H
+#define _ASM_CLOCKSOURCE_H
+
+#include <asm/vdso/clocksource.h>
+
+#endif
diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h
new file mode 100644
index 000000000..12debce23
--- /dev/null
+++ b/arch/riscv/include/asm/cmpxchg.h
@@ -0,0 +1,363 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2014 Regents of the University of California
+ */
+
+#ifndef _ASM_RISCV_CMPXCHG_H
+#define _ASM_RISCV_CMPXCHG_H
+
+#include <linux/bug.h>
+
+#include <asm/barrier.h>
+#include <asm/fence.h>
+
+#define __xchg_relaxed(ptr, new, size)					\
+({									\
+	__typeof__(ptr) __ptr = (ptr);					\
+	__typeof__(new) __new = (new);					\
+	__typeof__(*(ptr)) __ret;					\
+	switch (size) {							\
+	case 4:								\
+		__asm__ __volatile__ (					\
+			"	amoswap.w %0, %2, %1\n"			\
+			: "=r" (__ret), "+A" (*__ptr)			\
+			: "r" (__new)					\
+			: "memory");					\
+		break;							\
+	case 8:								\
+		__asm__ __volatile__ (					\
+			"	amoswap.d %0, %2, %1\n"			\
+			: "=r" (__ret), "+A" (*__ptr)			\
+			: "r" (__new)					\
+			: "memory");					\
+		break;							\
+	default:							\
+		BUILD_BUG();						\
+	}								\
+	__ret;								\
+})
+
+#define arch_xchg_relaxed(ptr, x)					\
+({									\
+	__typeof__(*(ptr)) _x_ = (x);					\
+	(__typeof__(*(ptr))) __xchg_relaxed((ptr),			\
+					    _x_, sizeof(*(ptr)));	\
+})
+
+#define __xchg_acquire(ptr, new, size)					\
+({									\
+	__typeof__(ptr) __ptr = (ptr);					\
+	__typeof__(new) __new = (new);					\
+	__typeof__(*(ptr)) __ret;					\
+	switch (size) {							\
+	case 4:								\
+		__asm__ __volatile__ (					\
+			"	amoswap.w %0, %2, %1\n"			\
+			RISCV_ACQUIRE_BARRIER				\
+			: "=r" (__ret), "+A" (*__ptr)			\
+			: "r" (__new)					\
+			: "memory");					\
+		break;							\
+	case 8:								\
+		__asm__ __volatile__ (					\
+			"	amoswap.d %0, %2, %1\n"			\
+			RISCV_ACQUIRE_BARRIER				\
+			: "=r" (__ret), "+A" (*__ptr)			\
+			: "r" (__new)					\
+			: "memory");					\
+		break;							\
+	default:							\
+		BUILD_BUG();						\
+	}								\
+	__ret;								\
+})
+
+#define arch_xchg_acquire(ptr, x)					\
+({									\
+	__typeof__(*(ptr)) _x_ = (x);					\
+	(__typeof__(*(ptr))) __xchg_acquire((ptr),			\
+					    _x_, sizeof(*(ptr)));	\
+})
+
+#define __xchg_release(ptr, new, size)					\
+({									\
+	__typeof__(ptr) __ptr = (ptr);					\
+	__typeof__(new) __new = (new);					\
+	__typeof__(*(ptr)) __ret;					\
+	switch (size) {							\
+	case 4:								\
+		__asm__ __volatile__ (					\
+			RISCV_RELEASE_BARRIER				\
+			"	amoswap.w %0, %2, %1\n"			\
+			: "=r" (__ret), "+A" (*__ptr)			\
+			: "r" (__new)					\
+			: "memory");					\
+		break;							\
+	case 8:								\
+		__asm__ __volatile__ (					\
+			RISCV_RELEASE_BARRIER				\
+			"	amoswap.d %0, %2, %1\n"			\
+			: "=r" (__ret), "+A" (*__ptr)			\
+			: "r" (__new)					\
+			: "memory");					\
+		break;							\
+	default:							\
+		BUILD_BUG();						\
+	}								\
+	__ret;								\
+})
+
+#define arch_xchg_release(ptr, x)					\
+({									\
+	__typeof__(*(ptr)) _x_ = (x);					\
+	(__typeof__(*(ptr))) __xchg_release((ptr),			\
+					    _x_, sizeof(*(ptr)));	\
+})
+
+#define __xchg(ptr, new, size)						\
+({									\
+	__typeof__(ptr) __ptr = (ptr);					\
+	__typeof__(new) __new = (new);					\
+	__typeof__(*(ptr)) __ret;					\
+	switch (size) {							\
+	case 4:								\
+		__asm__ __volatile__ (					\
+			"	amoswap.w.aqrl %0, %2, %1\n"		\
+			: "=r" (__ret), "+A" (*__ptr)			\
+			: "r" (__new)					\
+			: "memory");					\
+		break;							\
+	case 8:								\
+		__asm__ __volatile__ (					\
+			"	amoswap.d.aqrl %0, %2, %1\n"		\
+			: "=r" (__ret), "+A" (*__ptr)			\
+			: "r" (__new)					\
+			: "memory");					\
+		break;							\
+	default:							\
+		BUILD_BUG();						\
+	}								\
+	__ret;								\
+})
+
+#define arch_xchg(ptr, x)						\
+({									\
+	__typeof__(*(ptr)) _x_ = (x);					\
+	(__typeof__(*(ptr))) __xchg((ptr), _x_, sizeof(*(ptr)));	\
+})
+
+#define xchg32(ptr, x)							\
+({									\
+	BUILD_BUG_ON(sizeof(*(ptr)) != 4);				\
+	arch_xchg((ptr), (x));						\
+})
+
+#define xchg64(ptr, x)							\
+({									\
+	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
+	arch_xchg((ptr), (x));						\
+})
+
+/*
+ * Atomic compare and exchange.  Compare OLD with MEM, if identical,
+ * store NEW in MEM.  Return the initial value in MEM.  Success is
+ * indicated by comparing RETURN with OLD.
+ */
+#define __cmpxchg_relaxed(ptr, old, new, size)				\
+({									\
+	__typeof__(ptr) __ptr = (ptr);					\
+	__typeof__(*(ptr)) __old = (old);				\
+	__typeof__(*(ptr)) __new = (new);				\
+	__typeof__(*(ptr)) __ret;					\
+	register unsigned int __rc;					\
+	switch (size) {							\
+	case 4:								\
+		__asm__ __volatile__ (					\
+			"0:	lr.w %0, %2\n"				\
+			"	bne  %0, %z3, 1f\n"			\
+			"	sc.w %1, %z4, %2\n"			\
+			"	bnez %1, 0b\n"				\
+			"1:\n"						\
+			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
+			: "rJ" ((long)__old), "rJ" (__new)		\
+			: "memory");					\
+		break;							\
+	case 8:								\
+		__asm__ __volatile__ (					\
+			"0:	lr.d %0, %2\n"				\
+			"	bne %0, %z3, 1f\n"			\
+			"	sc.d %1, %z4, %2\n"			\
+			"	bnez %1, 0b\n"				\
+			"1:\n"						\
+			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
+			: "rJ" (__old), "rJ" (__new)			\
+			: "memory");					\
+		break;							\
+	default:							\
+		BUILD_BUG();						\
+	}								\
+	__ret;								\
+})
+
+#define arch_cmpxchg_relaxed(ptr, o, n)					\
+({									\
+	__typeof__(*(ptr)) _o_ = (o);					\
+	__typeof__(*(ptr)) _n_ = (n);					\
+	(__typeof__(*(ptr))) __cmpxchg_relaxed((ptr),			\
+					_o_, _n_, sizeof(*(ptr)));	\
+})
+
+#define __cmpxchg_acquire(ptr, old, new, size)				\
+({									\
+	__typeof__(ptr) __ptr = (ptr);					\
+	__typeof__(*(ptr)) __old = (old);				\
+	__typeof__(*(ptr)) __new = (new);				\
+	__typeof__(*(ptr)) __ret;					\
+	register unsigned int __rc;					\
+	switch (size) {							\
+	case 4:								\
+		__asm__ __volatile__ (					\
+			"0:	lr.w %0, %2\n"				\
+			"	bne  %0, %z3, 1f\n"			\
+			"	sc.w %1, %z4, %2\n"			\
+			"	bnez %1, 0b\n"				\
+			RISCV_ACQUIRE_BARRIER				\
+			"1:\n"						\
+			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
+			: "rJ" ((long)__old), "rJ" (__new)		\
+			: "memory");					\
+		break;							\
+	case 8:								\
+		__asm__ __volatile__ (					\
+			"0:	lr.d %0, %2\n"				\
+			"	bne %0, %z3, 1f\n"			\
+			"	sc.d %1, %z4, %2\n"			\
+			"	bnez %1, 0b\n"				\
+			RISCV_ACQUIRE_BARRIER				\
+			"1:\n"						\
+			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
+			: "rJ" (__old), "rJ" (__new)			\
+			: "memory");					\
+		break;							\
+	default:							\
+		BUILD_BUG();						\
+	}								\
+	__ret;								\
+})
+
+#define arch_cmpxchg_acquire(ptr, o, n)					\
+({									\
+	__typeof__(*(ptr)) _o_ = (o);					\
+	__typeof__(*(ptr)) _n_ = (n);					\
+	(__typeof__(*(ptr))) __cmpxchg_acquire((ptr),			\
+					_o_, _n_, sizeof(*(ptr)));	\
+})
+
+#define __cmpxchg_release(ptr, old, new, size)				\
+({									\
+	__typeof__(ptr) __ptr = (ptr);					\
+	__typeof__(*(ptr)) __old = (old);				\
+	__typeof__(*(ptr)) __new = (new);				\
+	__typeof__(*(ptr)) __ret;					\
+	register unsigned int __rc;					\
+	switch (size) {							\
+	case 4:								\
+		__asm__ __volatile__ (					\
+			RISCV_RELEASE_BARRIER				\
+			"0:	lr.w %0, %2\n"				\
+			"	bne  %0, %z3, 1f\n"			\
+			"	sc.w %1, %z4, %2\n"			\
+			"	bnez %1, 0b\n"				\
+			"1:\n"						\
+			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
+			: "rJ" ((long)__old), "rJ" (__new)		\
+			: "memory");					\
+		break;							\
+	case 8:								\
+		__asm__ __volatile__ (					\
+			RISCV_RELEASE_BARRIER				\
+			"0:	lr.d %0, %2\n"				\
+			"	bne %0, %z3, 1f\n"			\
+			"	sc.d %1, %z4, %2\n"			\
+			"	bnez %1, 0b\n"				\
+			"1:\n"						\
+			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
+			: "rJ" (__old), "rJ" (__new)			\
+			: "memory");					\
+		break;							\
+	default:							\
+		BUILD_BUG();						\
+	}								\
+	__ret;								\
+})
+
+#define arch_cmpxchg_release(ptr, o, n)					\
+({									\
+	__typeof__(*(ptr)) _o_ = (o);					\
+	__typeof__(*(ptr)) _n_ = (n);					\
+	(__typeof__(*(ptr))) __cmpxchg_release((ptr),			\
+					_o_, _n_, sizeof(*(ptr)));	\
+})
+
+#define __cmpxchg(ptr, old, new, size)					\
+({									\
+	__typeof__(ptr) __ptr = (ptr);					\
+	__typeof__(*(ptr)) __old = (old);				\
+	__typeof__(*(ptr)) __new = (new);				\
+	__typeof__(*(ptr)) __ret;					\
+	register unsigned int __rc;					\
+	switch (size) {							\
+	case 4:								\
+		__asm__ __volatile__ (					\
+			"0:	lr.w %0, %2\n"				\
+			"	bne  %0, %z3, 1f\n"			\
+			"	sc.w.rl %1, %z4, %2\n"			\
+			"	bnez %1, 0b\n"				\
+			"	fence rw, rw\n"				\
+			"1:\n"						\
+			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
+			: "rJ" ((long)__old), "rJ" (__new)		\
+			: "memory");					\
+		break;							\
+	case 8:								\
+		__asm__ __volatile__ (					\
+			"0:	lr.d %0, %2\n"				\
+			"	bne %0, %z3, 1f\n"			\
+			"	sc.d.rl %1, %z4, %2\n"			\
+			"	bnez %1, 0b\n"				\
+			"	fence rw, rw\n"				\
+			"1:\n"						\
+			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
+			: "rJ" (__old), "rJ" (__new)			\
+			: "memory");					\
+		break;							\
+	default:							\
+		BUILD_BUG();						\
+	}								\
+	__ret;								\
+})
+
+#define arch_cmpxchg(ptr, o, n)						\
+({									\
+	__typeof__(*(ptr)) _o_ = (o);					\
+	__typeof__(*(ptr)) _n_ = (n);					\
+	(__typeof__(*(ptr))) __cmpxchg((ptr),				\
+				       _o_, _n_, sizeof(*(ptr)));	\
+})
+
+#define arch_cmpxchg_local(ptr, o, n)					\
+	(__cmpxchg_relaxed((ptr), (o), (n), sizeof(*(ptr))))
+
+#define arch_cmpxchg64(ptr, o, n)					\
+({									\
+	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
+	arch_cmpxchg((ptr), (o), (n));					\
+})
+
+#define arch_cmpxchg64_local(ptr, o, n)					\
+({									\
+	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
+	arch_cmpxchg_relaxed((ptr), (o), (n));				\
+})
+
+#endif /* _ASM_RISCV_CMPXCHG_H */
diff --git a/arch/riscv/include/asm/compat.h b/arch/riscv/include/asm/compat.h
new file mode 100644
index 000000000..2ac955b51
--- /dev/null
+++ b/arch/riscv/include/asm/compat.h
@@ -0,0 +1,129 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef __ASM_COMPAT_H
+#define __ASM_COMPAT_H
+
+#define COMPAT_UTS_MACHINE	"riscv\0\0"
+
+/*
+ * Architecture specific compatibility types
+ */
+#include <linux/types.h>
+#include <linux/sched.h>
+#include <linux/sched/task_stack.h>
+#include <asm-generic/compat.h>
+
+static inline int is_compat_task(void)
+{
+	return test_thread_flag(TIF_32BIT);
+}
+
+struct compat_user_regs_struct {
+	compat_ulong_t pc;
+	compat_ulong_t ra;
+	compat_ulong_t sp;
+	compat_ulong_t gp;
+	compat_ulong_t tp;
+	compat_ulong_t t0;
+	compat_ulong_t t1;
+	compat_ulong_t t2;
+	compat_ulong_t s0;
+	compat_ulong_t s1;
+	compat_ulong_t a0;
+	compat_ulong_t a1;
+	compat_ulong_t a2;
+	compat_ulong_t a3;
+	compat_ulong_t a4;
+	compat_ulong_t a5;
+	compat_ulong_t a6;
+	compat_ulong_t a7;
+	compat_ulong_t s2;
+	compat_ulong_t s3;
+	compat_ulong_t s4;
+	compat_ulong_t s5;
+	compat_ulong_t s6;
+	compat_ulong_t s7;
+	compat_ulong_t s8;
+	compat_ulong_t s9;
+	compat_ulong_t s10;
+	compat_ulong_t s11;
+	compat_ulong_t t3;
+	compat_ulong_t t4;
+	compat_ulong_t t5;
+	compat_ulong_t t6;
+};
+
+static inline void regs_to_cregs(struct compat_user_regs_struct *cregs,
+				 struct pt_regs *regs)
+{
+	cregs->pc	= (compat_ulong_t) regs->epc;
+	cregs->ra	= (compat_ulong_t) regs->ra;
+	cregs->sp	= (compat_ulong_t) regs->sp;
+	cregs->gp	= (compat_ulong_t) regs->gp;
+	cregs->tp	= (compat_ulong_t) regs->tp;
+	cregs->t0	= (compat_ulong_t) regs->t0;
+	cregs->t1	= (compat_ulong_t) regs->t1;
+	cregs->t2	= (compat_ulong_t) regs->t2;
+	cregs->s0	= (compat_ulong_t) regs->s0;
+	cregs->s1	= (compat_ulong_t) regs->s1;
+	cregs->a0	= (compat_ulong_t) regs->a0;
+	cregs->a1	= (compat_ulong_t) regs->a1;
+	cregs->a2	= (compat_ulong_t) regs->a2;
+	cregs->a3	= (compat_ulong_t) regs->a3;
+	cregs->a4	= (compat_ulong_t) regs->a4;
+	cregs->a5	= (compat_ulong_t) regs->a5;
+	cregs->a6	= (compat_ulong_t) regs->a6;
+	cregs->a7	= (compat_ulong_t) regs->a7;
+	cregs->s2	= (compat_ulong_t) regs->s2;
+	cregs->s3	= (compat_ulong_t) regs->s3;
+	cregs->s4	= (compat_ulong_t) regs->s4;
+	cregs->s5	= (compat_ulong_t) regs->s5;
+	cregs->s6	= (compat_ulong_t) regs->s6;
+	cregs->s7	= (compat_ulong_t) regs->s7;
+	cregs->s8	= (compat_ulong_t) regs->s8;
+	cregs->s9	= (compat_ulong_t) regs->s9;
+	cregs->s10	= (compat_ulong_t) regs->s10;
+	cregs->s11	= (compat_ulong_t) regs->s11;
+	cregs->t3	= (compat_ulong_t) regs->t3;
+	cregs->t4	= (compat_ulong_t) regs->t4;
+	cregs->t5	= (compat_ulong_t) regs->t5;
+	cregs->t6	= (compat_ulong_t) regs->t6;
+};
+
+static inline void cregs_to_regs(struct compat_user_regs_struct *cregs,
+				 struct pt_regs *regs)
+{
+	regs->epc	= (unsigned long) cregs->pc;
+	regs->ra	= (unsigned long) cregs->ra;
+	regs->sp	= (unsigned long) cregs->sp;
+	regs->gp	= (unsigned long) cregs->gp;
+	regs->tp	= (unsigned long) cregs->tp;
+	regs->t0	= (unsigned long) cregs->t0;
+	regs->t1	= (unsigned long) cregs->t1;
+	regs->t2	= (unsigned long) cregs->t2;
+	regs->s0	= (unsigned long) cregs->s0;
+	regs->s1	= (unsigned long) cregs->s1;
+	regs->a0	= (unsigned long) cregs->a0;
+	regs->a1	= (unsigned long) cregs->a1;
+	regs->a2	= (unsigned long) cregs->a2;
+	regs->a3	= (unsigned long) cregs->a3;
+	regs->a4	= (unsigned long) cregs->a4;
+	regs->a5	= (unsigned long) cregs->a5;
+	regs->a6	= (unsigned long) cregs->a6;
+	regs->a7	= (unsigned long) cregs->a7;
+	regs->s2	= (unsigned long) cregs->s2;
+	regs->s3	= (unsigned long) cregs->s3;
+	regs->s4	= (unsigned long) cregs->s4;
+	regs->s5	= (unsigned long) cregs->s5;
+	regs->s6	= (unsigned long) cregs->s6;
+	regs->s7	= (unsigned long) cregs->s7;
+	regs->s8	= (unsigned long) cregs->s8;
+	regs->s9	= (unsigned long) cregs->s9;
+	regs->s10	= (unsigned long) cregs->s10;
+	regs->s11	= (unsigned long) cregs->s11;
+	regs->t3	= (unsigned long) cregs->t3;
+	regs->t4	= (unsigned long) cregs->t4;
+	regs->t5	= (unsigned long) cregs->t5;
+	regs->t6	= (unsigned long) cregs->t6;
+};
+
+#endif /* __ASM_COMPAT_H */
diff --git a/arch/riscv/include/asm/cpu_ops.h b/arch/riscv/include/asm/cpu_ops.h
new file mode 100644
index 000000000..aa128466c
--- /dev/null
+++ b/arch/riscv/include/asm/cpu_ops.h
@@ -0,0 +1,45 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2020 Western Digital Corporation or its affiliates.
+ * Based on arch/arm64/include/asm/cpu_ops.h
+ */
+#ifndef __ASM_CPU_OPS_H
+#define __ASM_CPU_OPS_H
+
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/threads.h>
+
+/**
+ * struct cpu_operations - Callback operations for hotplugging CPUs.
+ *
+ * @name:		Name of the boot protocol.
+ * @cpu_prepare:	Early one-time preparation step for a cpu. If there
+ *			is a mechanism for doing so, tests whether it is
+ *			possible to boot the given HART.
+ * @cpu_start:		Boots a cpu into the kernel.
+ * @cpu_disable:	Prepares a cpu to die. May fail for some
+ *			mechanism-specific reason, which will cause the hot
+ *			unplug to be aborted. Called from the cpu to be killed.
+ * @cpu_stop:		Makes a cpu leave the kernel. Must not fail. Called from
+ *			the cpu being stopped.
+ * @cpu_is_stopped:	Ensures a cpu has left the kernel. Called from another
+ *			cpu.
+ */
+struct cpu_operations {
+	const char	*name;
+	int		(*cpu_prepare)(unsigned int cpu);
+	int		(*cpu_start)(unsigned int cpu,
+				     struct task_struct *tidle);
+#ifdef CONFIG_HOTPLUG_CPU
+	int		(*cpu_disable)(unsigned int cpu);
+	void		(*cpu_stop)(void);
+	int		(*cpu_is_stopped)(unsigned int cpu);
+#endif
+};
+
+extern const struct cpu_operations cpu_ops_spinwait;
+extern const struct cpu_operations *cpu_ops[NR_CPUS];
+void __init cpu_set_ops(int cpu);
+
+#endif /* ifndef __ASM_CPU_OPS_H */
diff --git a/arch/riscv/include/asm/cpu_ops_sbi.h b/arch/riscv/include/asm/cpu_ops_sbi.h
new file mode 100644
index 000000000..d6e4665b3
--- /dev/null
+++ b/arch/riscv/include/asm/cpu_ops_sbi.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2021 by Rivos Inc.
+ */
+#ifndef __ASM_CPU_OPS_SBI_H
+#define __ASM_CPU_OPS_SBI_H
+
+#ifndef __ASSEMBLY__
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/threads.h>
+
+extern const struct cpu_operations cpu_ops_sbi;
+
+/**
+ * struct sbi_hart_boot_data - Hart specific boot used during booting and
+ *			       cpu hotplug.
+ * @task_ptr: A pointer to the hart specific tp
+ * @stack_ptr: A pointer to the hart specific sp
+ */
+struct sbi_hart_boot_data {
+	void *task_ptr;
+	void *stack_ptr;
+};
+#endif
+
+#endif /* ifndef __ASM_CPU_OPS_SBI_H */
diff --git a/arch/riscv/include/asm/cpuidle.h b/arch/riscv/include/asm/cpuidle.h
new file mode 100644
index 000000000..71fdc607d
--- /dev/null
+++ b/arch/riscv/include/asm/cpuidle.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2021 Allwinner Ltd
+ * Copyright (C) 2021 Western Digital Corporation or its affiliates.
+ */
+
+#ifndef _ASM_RISCV_CPUIDLE_H
+#define _ASM_RISCV_CPUIDLE_H
+
+#include <asm/barrier.h>
+#include <asm/processor.h>
+
+static inline void cpu_do_idle(void)
+{
+	/*
+	 * Add mb() here to ensure that all
+	 * IO/MEM accesses are completed prior
+	 * to entering WFI.
+	 */
+	mb();
+	wait_for_interrupt();
+}
+
+#endif
diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h
new file mode 100644
index 000000000..0e571f648
--- /dev/null
+++ b/arch/riscv/include/asm/csr.h
@@ -0,0 +1,408 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2015 Regents of the University of California
+ */
+
+#ifndef _ASM_RISCV_CSR_H
+#define _ASM_RISCV_CSR_H
+
+#include <asm/asm.h>
+#include <linux/const.h>
+
+/* Status register flags */
+#define SR_SIE		_AC(0x00000002, UL) /* Supervisor Interrupt Enable */
+#define SR_MIE		_AC(0x00000008, UL) /* Machine Interrupt Enable */
+#define SR_SPIE		_AC(0x00000020, UL) /* Previous Supervisor IE */
+#define SR_MPIE		_AC(0x00000080, UL) /* Previous Machine IE */
+#define SR_SPP		_AC(0x00000100, UL) /* Previously Supervisor */
+#define SR_MPP		_AC(0x00001800, UL) /* Previously Machine */
+#define SR_SUM		_AC(0x00040000, UL) /* Supervisor User Memory Access */
+
+#define SR_FS		_AC(0x00006000, UL) /* Floating-point Status */
+#define SR_FS_OFF	_AC(0x00000000, UL)
+#define SR_FS_INITIAL	_AC(0x00002000, UL)
+#define SR_FS_CLEAN	_AC(0x00004000, UL)
+#define SR_FS_DIRTY	_AC(0x00006000, UL)
+
+#define SR_XS		_AC(0x00018000, UL) /* Extension Status */
+#define SR_XS_OFF	_AC(0x00000000, UL)
+#define SR_XS_INITIAL	_AC(0x00008000, UL)
+#define SR_XS_CLEAN	_AC(0x00010000, UL)
+#define SR_XS_DIRTY	_AC(0x00018000, UL)
+
+#ifndef CONFIG_64BIT
+#define SR_SD		_AC(0x80000000, UL) /* FS/XS dirty */
+#else
+#define SR_SD		_AC(0x8000000000000000, UL) /* FS/XS dirty */
+#endif
+
+#ifdef CONFIG_64BIT
+#define SR_UXL		_AC(0x300000000, UL) /* XLEN mask for U-mode */
+#define SR_UXL_32	_AC(0x100000000, UL) /* XLEN = 32 for U-mode */
+#define SR_UXL_64	_AC(0x200000000, UL) /* XLEN = 64 for U-mode */
+#define SR_UXL_SHIFT	32
+#endif
+
+/* SATP flags */
+#ifndef CONFIG_64BIT
+#define SATP_PPN	_AC(0x003FFFFF, UL)
+#define SATP_MODE_32	_AC(0x80000000, UL)
+#define SATP_ASID_BITS	9
+#define SATP_ASID_SHIFT	22
+#define SATP_ASID_MASK	_AC(0x1FF, UL)
+#else
+#define SATP_PPN	_AC(0x00000FFFFFFFFFFF, UL)
+#define SATP_MODE_39	_AC(0x8000000000000000, UL)
+#define SATP_MODE_48	_AC(0x9000000000000000, UL)
+#define SATP_MODE_57	_AC(0xa000000000000000, UL)
+#define SATP_ASID_BITS	16
+#define SATP_ASID_SHIFT	44
+#define SATP_ASID_MASK	_AC(0xFFFF, UL)
+#endif
+
+/* Exception cause high bit - is an interrupt if set */
+#define CAUSE_IRQ_FLAG		(_AC(1, UL) << (__riscv_xlen - 1))
+
+/* Interrupt causes (minus the high bit) */
+#define IRQ_S_SOFT		1
+#define IRQ_VS_SOFT		2
+#define IRQ_M_SOFT		3
+#define IRQ_S_TIMER		5
+#define IRQ_VS_TIMER		6
+#define IRQ_M_TIMER		7
+#define IRQ_S_EXT		9
+#define IRQ_VS_EXT		10
+#define IRQ_M_EXT		11
+#define IRQ_PMU_OVF		13
+
+/* Exception causes */
+#define EXC_INST_MISALIGNED	0
+#define EXC_INST_ACCESS		1
+#define EXC_INST_ILLEGAL	2
+#define EXC_BREAKPOINT		3
+#define EXC_LOAD_ACCESS		5
+#define EXC_STORE_ACCESS	7
+#define EXC_SYSCALL		8
+#define EXC_HYPERVISOR_SYSCALL	9
+#define EXC_SUPERVISOR_SYSCALL	10
+#define EXC_INST_PAGE_FAULT	12
+#define EXC_LOAD_PAGE_FAULT	13
+#define EXC_STORE_PAGE_FAULT	15
+#define EXC_INST_GUEST_PAGE_FAULT	20
+#define EXC_LOAD_GUEST_PAGE_FAULT	21
+#define EXC_VIRTUAL_INST_FAULT		22
+#define EXC_STORE_GUEST_PAGE_FAULT	23
+
+/* PMP configuration */
+#define PMP_R			0x01
+#define PMP_W			0x02
+#define PMP_X			0x04
+#define PMP_A			0x18
+#define PMP_A_TOR		0x08
+#define PMP_A_NA4		0x10
+#define PMP_A_NAPOT		0x18
+#define PMP_L			0x80
+
+/* HSTATUS flags */
+#ifdef CONFIG_64BIT
+#define HSTATUS_VSXL		_AC(0x300000000, UL)
+#define HSTATUS_VSXL_SHIFT	32
+#endif
+#define HSTATUS_VTSR		_AC(0x00400000, UL)
+#define HSTATUS_VTW		_AC(0x00200000, UL)
+#define HSTATUS_VTVM		_AC(0x00100000, UL)
+#define HSTATUS_VGEIN		_AC(0x0003f000, UL)
+#define HSTATUS_VGEIN_SHIFT	12
+#define HSTATUS_HU		_AC(0x00000200, UL)
+#define HSTATUS_SPVP		_AC(0x00000100, UL)
+#define HSTATUS_SPV		_AC(0x00000080, UL)
+#define HSTATUS_GVA		_AC(0x00000040, UL)
+#define HSTATUS_VSBE		_AC(0x00000020, UL)
+
+/* HGATP flags */
+#define HGATP_MODE_OFF		_AC(0, UL)
+#define HGATP_MODE_SV32X4	_AC(1, UL)
+#define HGATP_MODE_SV39X4	_AC(8, UL)
+#define HGATP_MODE_SV48X4	_AC(9, UL)
+#define HGATP_MODE_SV57X4	_AC(10, UL)
+
+#define HGATP32_MODE_SHIFT	31
+#define HGATP32_VMID_SHIFT	22
+#define HGATP32_VMID_MASK	_AC(0x1FC00000, UL)
+#define HGATP32_PPN		_AC(0x003FFFFF, UL)
+
+#define HGATP64_MODE_SHIFT	60
+#define HGATP64_VMID_SHIFT	44
+#define HGATP64_VMID_MASK	_AC(0x03FFF00000000000, UL)
+#define HGATP64_PPN		_AC(0x00000FFFFFFFFFFF, UL)
+
+#define HGATP_PAGE_SHIFT	12
+
+#ifdef CONFIG_64BIT
+#define HGATP_PPN		HGATP64_PPN
+#define HGATP_VMID_SHIFT	HGATP64_VMID_SHIFT
+#define HGATP_VMID_MASK		HGATP64_VMID_MASK
+#define HGATP_MODE_SHIFT	HGATP64_MODE_SHIFT
+#else
+#define HGATP_PPN		HGATP32_PPN
+#define HGATP_VMID_SHIFT	HGATP32_VMID_SHIFT
+#define HGATP_VMID_MASK		HGATP32_VMID_MASK
+#define HGATP_MODE_SHIFT	HGATP32_MODE_SHIFT
+#endif
+
+/* VSIP & HVIP relation */
+#define VSIP_TO_HVIP_SHIFT	(IRQ_VS_SOFT - IRQ_S_SOFT)
+#define VSIP_VALID_MASK		((_AC(1, UL) << IRQ_S_SOFT) | \
+				 (_AC(1, UL) << IRQ_S_TIMER) | \
+				 (_AC(1, UL) << IRQ_S_EXT))
+
+/* xENVCFG flags */
+#define ENVCFG_STCE			(_AC(1, ULL) << 63)
+#define ENVCFG_PBMTE			(_AC(1, ULL) << 62)
+#define ENVCFG_CBZE			(_AC(1, UL) << 7)
+#define ENVCFG_CBCFE			(_AC(1, UL) << 6)
+#define ENVCFG_CBIE_SHIFT		4
+#define ENVCFG_CBIE			(_AC(0x3, UL) << ENVCFG_CBIE_SHIFT)
+#define ENVCFG_CBIE_ILL			_AC(0x0, UL)
+#define ENVCFG_CBIE_FLUSH		_AC(0x1, UL)
+#define ENVCFG_CBIE_INV			_AC(0x3, UL)
+#define ENVCFG_FIOM			_AC(0x1, UL)
+
+/* symbolic CSR names: */
+#define CSR_CYCLE		0xc00
+#define CSR_TIME		0xc01
+#define CSR_INSTRET		0xc02
+#define CSR_HPMCOUNTER3		0xc03
+#define CSR_HPMCOUNTER4		0xc04
+#define CSR_HPMCOUNTER5		0xc05
+#define CSR_HPMCOUNTER6		0xc06
+#define CSR_HPMCOUNTER7		0xc07
+#define CSR_HPMCOUNTER8		0xc08
+#define CSR_HPMCOUNTER9		0xc09
+#define CSR_HPMCOUNTER10	0xc0a
+#define CSR_HPMCOUNTER11	0xc0b
+#define CSR_HPMCOUNTER12	0xc0c
+#define CSR_HPMCOUNTER13	0xc0d
+#define CSR_HPMCOUNTER14	0xc0e
+#define CSR_HPMCOUNTER15	0xc0f
+#define CSR_HPMCOUNTER16	0xc10
+#define CSR_HPMCOUNTER17	0xc11
+#define CSR_HPMCOUNTER18	0xc12
+#define CSR_HPMCOUNTER19	0xc13
+#define CSR_HPMCOUNTER20	0xc14
+#define CSR_HPMCOUNTER21	0xc15
+#define CSR_HPMCOUNTER22	0xc16
+#define CSR_HPMCOUNTER23	0xc17
+#define CSR_HPMCOUNTER24	0xc18
+#define CSR_HPMCOUNTER25	0xc19
+#define CSR_HPMCOUNTER26	0xc1a
+#define CSR_HPMCOUNTER27	0xc1b
+#define CSR_HPMCOUNTER28	0xc1c
+#define CSR_HPMCOUNTER29	0xc1d
+#define CSR_HPMCOUNTER30	0xc1e
+#define CSR_HPMCOUNTER31	0xc1f
+#define CSR_CYCLEH		0xc80
+#define CSR_TIMEH		0xc81
+#define CSR_INSTRETH		0xc82
+#define CSR_HPMCOUNTER3H	0xc83
+#define CSR_HPMCOUNTER4H	0xc84
+#define CSR_HPMCOUNTER5H	0xc85
+#define CSR_HPMCOUNTER6H	0xc86
+#define CSR_HPMCOUNTER7H	0xc87
+#define CSR_HPMCOUNTER8H	0xc88
+#define CSR_HPMCOUNTER9H	0xc89
+#define CSR_HPMCOUNTER10H	0xc8a
+#define CSR_HPMCOUNTER11H	0xc8b
+#define CSR_HPMCOUNTER12H	0xc8c
+#define CSR_HPMCOUNTER13H	0xc8d
+#define CSR_HPMCOUNTER14H	0xc8e
+#define CSR_HPMCOUNTER15H	0xc8f
+#define CSR_HPMCOUNTER16H	0xc90
+#define CSR_HPMCOUNTER17H	0xc91
+#define CSR_HPMCOUNTER18H	0xc92
+#define CSR_HPMCOUNTER19H	0xc93
+#define CSR_HPMCOUNTER20H	0xc94
+#define CSR_HPMCOUNTER21H	0xc95
+#define CSR_HPMCOUNTER22H	0xc96
+#define CSR_HPMCOUNTER23H	0xc97
+#define CSR_HPMCOUNTER24H	0xc98
+#define CSR_HPMCOUNTER25H	0xc99
+#define CSR_HPMCOUNTER26H	0xc9a
+#define CSR_HPMCOUNTER27H	0xc9b
+#define CSR_HPMCOUNTER28H	0xc9c
+#define CSR_HPMCOUNTER29H	0xc9d
+#define CSR_HPMCOUNTER30H	0xc9e
+#define CSR_HPMCOUNTER31H	0xc9f
+
+#define CSR_SSCOUNTOVF		0xda0
+
+#define CSR_SSTATUS		0x100
+#define CSR_SIE			0x104
+#define CSR_STVEC		0x105
+#define CSR_SCOUNTEREN		0x106
+#define CSR_SSCRATCH		0x140
+#define CSR_SEPC		0x141
+#define CSR_SCAUSE		0x142
+#define CSR_STVAL		0x143
+#define CSR_SIP			0x144
+#define CSR_SATP		0x180
+
+#define CSR_STIMECMP		0x14D
+#define CSR_STIMECMPH		0x15D
+
+#define CSR_VSSTATUS		0x200
+#define CSR_VSIE		0x204
+#define CSR_VSTVEC		0x205
+#define CSR_VSSCRATCH		0x240
+#define CSR_VSEPC		0x241
+#define CSR_VSCAUSE		0x242
+#define CSR_VSTVAL		0x243
+#define CSR_VSIP		0x244
+#define CSR_VSATP		0x280
+#define CSR_VSTIMECMP		0x24D
+#define CSR_VSTIMECMPH		0x25D
+
+#define CSR_HSTATUS		0x600
+#define CSR_HEDELEG		0x602
+#define CSR_HIDELEG		0x603
+#define CSR_HIE			0x604
+#define CSR_HTIMEDELTA		0x605
+#define CSR_HCOUNTEREN		0x606
+#define CSR_HGEIE		0x607
+#define CSR_HENVCFG		0x60a
+#define CSR_HTIMEDELTAH		0x615
+#define CSR_HENVCFGH		0x61a
+#define CSR_HTVAL		0x643
+#define CSR_HIP			0x644
+#define CSR_HVIP		0x645
+#define CSR_HTINST		0x64a
+#define CSR_HGATP		0x680
+#define CSR_HGEIP		0xe12
+
+#define CSR_MSTATUS		0x300
+#define CSR_MISA		0x301
+#define CSR_MIE			0x304
+#define CSR_MTVEC		0x305
+#define CSR_MENVCFG		0x30a
+#define CSR_MENVCFGH		0x31a
+#define CSR_MSCRATCH		0x340
+#define CSR_MEPC		0x341
+#define CSR_MCAUSE		0x342
+#define CSR_MTVAL		0x343
+#define CSR_MIP			0x344
+#define CSR_PMPCFG0		0x3a0
+#define CSR_PMPADDR0		0x3b0
+#define CSR_MVENDORID		0xf11
+#define CSR_MARCHID		0xf12
+#define CSR_MIMPID		0xf13
+#define CSR_MHARTID		0xf14
+
+#ifdef CONFIG_RISCV_M_MODE
+# define CSR_STATUS	CSR_MSTATUS
+# define CSR_IE		CSR_MIE
+# define CSR_TVEC	CSR_MTVEC
+# define CSR_SCRATCH	CSR_MSCRATCH
+# define CSR_EPC	CSR_MEPC
+# define CSR_CAUSE	CSR_MCAUSE
+# define CSR_TVAL	CSR_MTVAL
+# define CSR_IP		CSR_MIP
+
+# define SR_IE		SR_MIE
+# define SR_PIE		SR_MPIE
+# define SR_PP		SR_MPP
+
+# define RV_IRQ_SOFT		IRQ_M_SOFT
+# define RV_IRQ_TIMER	IRQ_M_TIMER
+# define RV_IRQ_EXT		IRQ_M_EXT
+#else /* CONFIG_RISCV_M_MODE */
+# define CSR_STATUS	CSR_SSTATUS
+# define CSR_IE		CSR_SIE
+# define CSR_TVEC	CSR_STVEC
+# define CSR_SCRATCH	CSR_SSCRATCH
+# define CSR_EPC	CSR_SEPC
+# define CSR_CAUSE	CSR_SCAUSE
+# define CSR_TVAL	CSR_STVAL
+# define CSR_IP		CSR_SIP
+
+# define SR_IE		SR_SIE
+# define SR_PIE		SR_SPIE
+# define SR_PP		SR_SPP
+
+# define RV_IRQ_SOFT		IRQ_S_SOFT
+# define RV_IRQ_TIMER	IRQ_S_TIMER
+# define RV_IRQ_EXT		IRQ_S_EXT
+# define RV_IRQ_PMU	IRQ_PMU_OVF
+# define SIP_LCOFIP     (_AC(0x1, UL) << IRQ_PMU_OVF)
+
+#endif /* !CONFIG_RISCV_M_MODE */
+
+/* IE/IP (Supervisor/Machine Interrupt Enable/Pending) flags */
+#define IE_SIE		(_AC(0x1, UL) << RV_IRQ_SOFT)
+#define IE_TIE		(_AC(0x1, UL) << RV_IRQ_TIMER)
+#define IE_EIE		(_AC(0x1, UL) << RV_IRQ_EXT)
+
+#ifndef __ASSEMBLY__
+
+#define csr_swap(csr, val)					\
+({								\
+	unsigned long __v = (unsigned long)(val);		\
+	__asm__ __volatile__ ("csrrw %0, " __ASM_STR(csr) ", %1"\
+			      : "=r" (__v) : "rK" (__v)		\
+			      : "memory");			\
+	__v;							\
+})
+
+#define csr_read(csr)						\
+({								\
+	register unsigned long __v;				\
+	__asm__ __volatile__ ("csrr %0, " __ASM_STR(csr)	\
+			      : "=r" (__v) :			\
+			      : "memory");			\
+	__v;							\
+})
+
+#define csr_write(csr, val)					\
+({								\
+	unsigned long __v = (unsigned long)(val);		\
+	__asm__ __volatile__ ("csrw " __ASM_STR(csr) ", %0"	\
+			      : : "rK" (__v)			\
+			      : "memory");			\
+})
+
+#define csr_read_set(csr, val)					\
+({								\
+	unsigned long __v = (unsigned long)(val);		\
+	__asm__ __volatile__ ("csrrs %0, " __ASM_STR(csr) ", %1"\
+			      : "=r" (__v) : "rK" (__v)		\
+			      : "memory");			\
+	__v;							\
+})
+
+#define csr_set(csr, val)					\
+({								\
+	unsigned long __v = (unsigned long)(val);		\
+	__asm__ __volatile__ ("csrs " __ASM_STR(csr) ", %0"	\
+			      : : "rK" (__v)			\
+			      : "memory");			\
+})
+
+#define csr_read_clear(csr, val)				\
+({								\
+	unsigned long __v = (unsigned long)(val);		\
+	__asm__ __volatile__ ("csrrc %0, " __ASM_STR(csr) ", %1"\
+			      : "=r" (__v) : "rK" (__v)		\
+			      : "memory");			\
+	__v;							\
+})
+
+#define csr_clear(csr, val)					\
+({								\
+	unsigned long __v = (unsigned long)(val);		\
+	__asm__ __volatile__ ("csrc " __ASM_STR(csr) ", %0"	\
+			      : : "rK" (__v)			\
+			      : "memory");			\
+})
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_RISCV_CSR_H */
diff --git a/arch/riscv/include/asm/current.h b/arch/riscv/include/asm/current.h
new file mode 100644
index 000000000..21774d868
--- /dev/null
+++ b/arch/riscv/include/asm/current.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Based on arm/arm64/include/asm/current.h
+ *
+ * Copyright (C) 2016 ARM
+ * Copyright (C) 2017 SiFive
+ */
+
+
+#ifndef _ASM_RISCV_CURRENT_H
+#define _ASM_RISCV_CURRENT_H
+
+#include <linux/bug.h>
+#include <linux/compiler.h>
+
+#ifndef __ASSEMBLY__
+
+struct task_struct;
+
+register struct task_struct *riscv_current_is_tp __asm__("tp");
+
+/*
+ * This only works because "struct thread_info" is at offset 0 from "struct
+ * task_struct".  This constraint seems to be necessary on other architectures
+ * as well, but __switch_to enforces it.  We can't check TASK_TI here because
+ * <asm/asm-offsets.h> includes this, and I can't get the definition of "struct
+ * task_struct" here due to some header ordering problems.
+ */
+static __always_inline struct task_struct *get_current(void)
+{
+	return riscv_current_is_tp;
+}
+
+#define current get_current()
+
+register unsigned long current_stack_pointer __asm__("sp");
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_RISCV_CURRENT_H */
diff --git a/arch/riscv/include/asm/delay.h b/arch/riscv/include/asm/delay.h
new file mode 100644
index 000000000..524f8ef7c
--- /dev/null
+++ b/arch/riscv/include/asm/delay.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2009 Chen Liqin <liqin.chen@sunplusct.com>
+ * Copyright (C) 2016 Regents of the University of California
+ */
+
+#ifndef _ASM_RISCV_DELAY_H
+#define _ASM_RISCV_DELAY_H
+
+extern unsigned long riscv_timebase;
+
+#define udelay udelay
+extern void udelay(unsigned long usecs);
+
+#define ndelay ndelay
+extern void ndelay(unsigned long nsecs);
+
+extern void __delay(unsigned long cycles);
+
+#endif /* _ASM_RISCV_DELAY_H */
diff --git a/arch/riscv/include/asm/efi.h b/arch/riscv/include/asm/efi.h
new file mode 100644
index 000000000..e229d7be4
--- /dev/null
+++ b/arch/riscv/include/asm/efi.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020 Western Digital Corporation or its affiliates.
+ */
+#ifndef _ASM_EFI_H
+#define _ASM_EFI_H
+
+#include <asm/csr.h>
+#include <asm/io.h>
+#include <asm/mmu_context.h>
+#include <asm/ptrace.h>
+#include <asm/tlbflush.h>
+#include <asm/pgalloc.h>
+
+#ifdef CONFIG_EFI
+extern void efi_init(void);
+#else
+#define efi_init()
+#endif
+
+int efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md);
+int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md);
+
+#define arch_efi_call_virt_setup()      ({		\
+		sync_kernel_mappings(efi_mm.pgd);	\
+		efi_virtmap_load();			\
+	})
+#define arch_efi_call_virt_teardown()   efi_virtmap_unload()
+
+#define ARCH_EFI_IRQ_FLAGS_MASK (SR_IE | SR_SPIE)
+
+/* Load initrd anywhere in system RAM */
+static inline unsigned long efi_get_max_initrd_addr(unsigned long image_addr)
+{
+	return ULONG_MAX;
+}
+
+#define alloc_screen_info(x...)		(&screen_info)
+
+static inline void free_screen_info(struct screen_info *si)
+{
+}
+
+void efi_virtmap_load(void);
+void efi_virtmap_unload(void);
+
+#endif /* _ASM_EFI_H */
diff --git a/arch/riscv/include/asm/elf.h b/arch/riscv/include/asm/elf.h
new file mode 100644
index 000000000..e7acffdf2
--- /dev/null
+++ b/arch/riscv/include/asm/elf.h
@@ -0,0 +1,143 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2003 Matjaz Breskvar <phoenix@bsemi.com>
+ * Copyright (C) 2010-2011 Jonas Bonn <jonas@southpole.se>
+ * Copyright (C) 2012 Regents of the University of California
+ */
+
+#ifndef _ASM_RISCV_ELF_H
+#define _ASM_RISCV_ELF_H
+
+#include <uapi/linux/elf.h>
+#include <linux/compat.h>
+#include <uapi/asm/elf.h>
+#include <asm/auxvec.h>
+#include <asm/byteorder.h>
+#include <asm/cacheinfo.h>
+
+/*
+ * These are used to set parameters in the core dumps.
+ */
+#define ELF_ARCH	EM_RISCV
+
+#ifndef ELF_CLASS
+#ifdef CONFIG_64BIT
+#define ELF_CLASS	ELFCLASS64
+#else
+#define ELF_CLASS	ELFCLASS32
+#endif
+#endif
+
+#define ELF_DATA	ELFDATA2LSB
+
+/*
+ * This is used to ensure we don't load something for the wrong architecture.
+ */
+#define elf_check_arch(x) (((x)->e_machine == EM_RISCV) && \
+			   ((x)->e_ident[EI_CLASS] == ELF_CLASS))
+
+extern bool compat_elf_check_arch(Elf32_Ehdr *hdr);
+#define compat_elf_check_arch	compat_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		((TASK_SIZE / 3) * 2)
+
+#ifdef CONFIG_64BIT
+#ifdef CONFIG_COMPAT
+#define STACK_RND_MASK		(test_thread_flag(TIF_32BIT) ? \
+				 0x7ff >> (PAGE_SHIFT - 12) : \
+				 0x3ffff >> (PAGE_SHIFT - 12))
+#else
+#define STACK_RND_MASK		(0x3ffff >> (PAGE_SHIFT - 12))
+#endif
+#endif
+/*
+ * This yields a mask that user programs can use to figure out what
+ * instruction set this CPU supports.  This could be done in user space,
+ * but it's not easy, and we've already done it here.
+ */
+#define ELF_HWCAP	(elf_hwcap)
+extern unsigned long elf_hwcap;
+
+/*
+ * This yields a string that ld.so will use to load implementation
+ * specific libraries for optimization.  This is more specific in
+ * intent than poking at uname or /proc/cpuinfo.
+ */
+#define ELF_PLATFORM	(NULL)
+
+#define COMPAT_ELF_PLATFORM	(NULL)
+
+#ifdef CONFIG_MMU
+#define ARCH_DLINFO						\
+do {								\
+	/*							\
+	 * Note that we add ulong after elf_addr_t because	\
+	 * casting current->mm->context.vdso triggers a cast	\
+	 * warning of cast from pointer to integer for		\
+	 * COMPAT ELFCLASS32.					\
+	 */							\
+	NEW_AUX_ENT(AT_SYSINFO_EHDR,				\
+		(elf_addr_t)(ulong)current->mm->context.vdso);	\
+	NEW_AUX_ENT(AT_L1I_CACHESIZE,				\
+		get_cache_size(1, CACHE_TYPE_INST));		\
+	NEW_AUX_ENT(AT_L1I_CACHEGEOMETRY,			\
+		get_cache_geometry(1, CACHE_TYPE_INST));	\
+	NEW_AUX_ENT(AT_L1D_CACHESIZE,				\
+		get_cache_size(1, CACHE_TYPE_DATA));		\
+	NEW_AUX_ENT(AT_L1D_CACHEGEOMETRY,			\
+		get_cache_geometry(1, CACHE_TYPE_DATA));	\
+	NEW_AUX_ENT(AT_L2_CACHESIZE,				\
+		get_cache_size(2, CACHE_TYPE_UNIFIED));		\
+	NEW_AUX_ENT(AT_L2_CACHEGEOMETRY,			\
+		get_cache_geometry(2, CACHE_TYPE_UNIFIED));	\
+	NEW_AUX_ENT(AT_L3_CACHESIZE,				\
+		get_cache_size(3, CACHE_TYPE_UNIFIED));		\
+	NEW_AUX_ENT(AT_L3_CACHEGEOMETRY,			\
+		get_cache_geometry(3, CACHE_TYPE_UNIFIED));	\
+} while (0)
+#define ARCH_HAS_SETUP_ADDITIONAL_PAGES
+struct linux_binprm;
+extern int arch_setup_additional_pages(struct linux_binprm *bprm,
+	int uses_interp);
+#endif /* CONFIG_MMU */
+
+#define ELF_CORE_COPY_REGS(dest, regs)			\
+do {							\
+	*(struct user_regs_struct *)&(dest) =		\
+		*(struct user_regs_struct *)regs;	\
+} while (0);
+
+#ifdef CONFIG_COMPAT
+
+#define SET_PERSONALITY(ex)					\
+do {    if ((ex).e_ident[EI_CLASS] == ELFCLASS32)		\
+		set_thread_flag(TIF_32BIT);			\
+	else							\
+		clear_thread_flag(TIF_32BIT);			\
+	if (personality(current->personality) != PER_LINUX32)	\
+		set_personality(PER_LINUX |			\
+			(current->personality & (~PER_MASK)));	\
+} while (0)
+
+#define COMPAT_ELF_ET_DYN_BASE		((TASK_SIZE_32 / 3) * 2)
+
+/* rv32 registers */
+typedef compat_ulong_t			compat_elf_greg_t;
+typedef compat_elf_greg_t		compat_elf_gregset_t[ELF_NGREG];
+
+extern int compat_arch_setup_additional_pages(struct linux_binprm *bprm,
+					      int uses_interp);
+#define compat_arch_setup_additional_pages \
+				compat_arch_setup_additional_pages
+
+#endif /* CONFIG_COMPAT */
+#endif /* _ASM_RISCV_ELF_H */
diff --git a/arch/riscv/include/asm/errata_list.h b/arch/riscv/include/asm/errata_list.h
new file mode 100644
index 000000000..7d2675bb7
--- /dev/null
+++ b/arch/riscv/include/asm/errata_list.h
@@ -0,0 +1,147 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2021 Sifive.
+ */
+#ifndef ASM_ERRATA_LIST_H
+#define ASM_ERRATA_LIST_H
+
+#include <asm/alternative.h>
+#include <asm/vendorid_list.h>
+
+#ifdef CONFIG_ERRATA_SIFIVE
+#define	ERRATA_SIFIVE_CIP_453 0
+#define	ERRATA_SIFIVE_CIP_1200 1
+#define	ERRATA_SIFIVE_NUMBER 2
+#endif
+
+#ifdef CONFIG_ERRATA_THEAD
+#define	ERRATA_THEAD_PBMT 0
+#define	ERRATA_THEAD_CMO 1
+#define	ERRATA_THEAD_NUMBER 2
+#endif
+
+#define	CPUFEATURE_SVPBMT 0
+#define	CPUFEATURE_ZICBOM 1
+#define	CPUFEATURE_NUMBER 2
+
+#ifdef __ASSEMBLY__
+
+#define ALT_INSN_FAULT(x)						\
+ALTERNATIVE(__stringify(RISCV_PTR do_trap_insn_fault),			\
+	    __stringify(RISCV_PTR sifive_cip_453_insn_fault_trp),	\
+	    SIFIVE_VENDOR_ID, ERRATA_SIFIVE_CIP_453,			\
+	    CONFIG_ERRATA_SIFIVE_CIP_453)
+
+#define ALT_PAGE_FAULT(x)						\
+ALTERNATIVE(__stringify(RISCV_PTR do_page_fault),			\
+	    __stringify(RISCV_PTR sifive_cip_453_page_fault_trp),	\
+	    SIFIVE_VENDOR_ID, ERRATA_SIFIVE_CIP_453,			\
+	    CONFIG_ERRATA_SIFIVE_CIP_453)
+#else /* !__ASSEMBLY__ */
+
+#define ALT_FLUSH_TLB_PAGE(x)						\
+asm(ALTERNATIVE("sfence.vma %0", "sfence.vma", SIFIVE_VENDOR_ID,	\
+		ERRATA_SIFIVE_CIP_1200, CONFIG_ERRATA_SIFIVE_CIP_1200)	\
+		: : "r" (addr) : "memory")
+
+/*
+ * _val is marked as "will be overwritten", so need to set it to 0
+ * in the default case.
+ */
+#define ALT_SVPBMT_SHIFT 61
+#define ALT_THEAD_PBMT_SHIFT 59
+#define ALT_SVPBMT(_val, prot)						\
+asm(ALTERNATIVE_2("li %0, 0\t\nnop",					\
+		  "li %0, %1\t\nslli %0,%0,%3", 0,			\
+			CPUFEATURE_SVPBMT, CONFIG_RISCV_ISA_SVPBMT,	\
+		  "li %0, %2\t\nslli %0,%0,%4", THEAD_VENDOR_ID,	\
+			ERRATA_THEAD_PBMT, CONFIG_ERRATA_THEAD_PBMT)	\
+		: "=r"(_val)						\
+		: "I"(prot##_SVPBMT >> ALT_SVPBMT_SHIFT),		\
+		  "I"(prot##_THEAD >> ALT_THEAD_PBMT_SHIFT),		\
+		  "I"(ALT_SVPBMT_SHIFT),				\
+		  "I"(ALT_THEAD_PBMT_SHIFT))
+
+#ifdef CONFIG_ERRATA_THEAD_PBMT
+/*
+ * IO/NOCACHE memory types are handled together with svpbmt,
+ * so on T-Head chips, check if no other memory type is set,
+ * and set the non-0 PMA type if applicable.
+ */
+#define ALT_THEAD_PMA(_val)						\
+asm volatile(ALTERNATIVE(						\
+	__nops(7),							\
+	"li      t3, %1\n\t"						\
+	"slli    t3, t3, %3\n\t"					\
+	"and     t3, %0, t3\n\t"					\
+	"bne     t3, zero, 2f\n\t"					\
+	"li      t3, %2\n\t"						\
+	"slli    t3, t3, %3\n\t"					\
+	"or      %0, %0, t3\n\t"					\
+	"2:",  THEAD_VENDOR_ID,						\
+		ERRATA_THEAD_PBMT, CONFIG_ERRATA_THEAD_PBMT)		\
+	: "+r"(_val)							\
+	: "I"(_PAGE_MTMASK_THEAD >> ALT_THEAD_PBMT_SHIFT),		\
+	  "I"(_PAGE_PMA_THEAD >> ALT_THEAD_PBMT_SHIFT),			\
+	  "I"(ALT_THEAD_PBMT_SHIFT)					\
+	: "t3")
+#else
+#define ALT_THEAD_PMA(_val)
+#endif
+
+/*
+ * dcache.ipa rs1 (invalidate, physical address)
+ * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
+ *   0000001    01010      rs1       000      00000  0001011
+ * dache.iva rs1 (invalida, virtual address)
+ *   0000001    00110      rs1       000      00000  0001011
+ *
+ * dcache.cpa rs1 (clean, physical address)
+ * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
+ *   0000001    01001      rs1       000      00000  0001011
+ * dcache.cva rs1 (clean, virtual address)
+ *   0000001    00101      rs1       000      00000  0001011
+ *
+ * dcache.cipa rs1 (clean then invalidate, physical address)
+ * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
+ *   0000001    01011      rs1       000      00000  0001011
+ * dcache.civa rs1 (... virtual address)
+ *   0000001    00111      rs1       000      00000  0001011
+ *
+ * sync.s (make sure all cache operations finished)
+ * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
+ *   0000000    11001     00000      000      00000  0001011
+ */
+#define THEAD_inval_A0	".long 0x0265000b"
+#define THEAD_clean_A0	".long 0x0255000b"
+#define THEAD_flush_A0	".long 0x0275000b"
+#define THEAD_SYNC_S	".long 0x0190000b"
+
+#define ALT_CMO_OP(_op, _start, _size, _cachesize)			\
+asm volatile(ALTERNATIVE_2(						\
+	__nops(6),							\
+	"mv a0, %1\n\t"							\
+	"j 2f\n\t"							\
+	"3:\n\t"							\
+	"cbo." __stringify(_op) " (a0)\n\t"				\
+	"add a0, a0, %0\n\t"						\
+	"2:\n\t"							\
+	"bltu a0, %2, 3b\n\t"						\
+	"nop", 0, CPUFEATURE_ZICBOM, CONFIG_RISCV_ISA_ZICBOM,		\
+	"mv a0, %1\n\t"							\
+	"j 2f\n\t"							\
+	"3:\n\t"							\
+	THEAD_##_op##_A0 "\n\t"						\
+	"add a0, a0, %0\n\t"						\
+	"2:\n\t"							\
+	"bltu a0, %2, 3b\n\t"						\
+	THEAD_SYNC_S, THEAD_VENDOR_ID,					\
+			ERRATA_THEAD_CMO, CONFIG_ERRATA_THEAD_CMO)	\
+	: : "r"(_cachesize),						\
+	    "r"((unsigned long)(_start) & ~((_cachesize) - 1UL)),	\
+	    "r"((unsigned long)(_start) + (_size))			\
+	: "a0")
+
+#endif /* __ASSEMBLY__ */
+
+#endif
diff --git a/arch/riscv/include/asm/extable.h b/arch/riscv/include/asm/extable.h
new file mode 100644
index 000000000..512012d19
--- /dev/null
+++ b/arch/riscv/include/asm/extable.h
@@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_RISCV_EXTABLE_H
+#define _ASM_RISCV_EXTABLE_H
+
+/*
+ * The exception table consists of pairs of relative offsets: the first
+ * is the relative offset to an instruction that is allowed to fault,
+ * and the second is the relative offset at which the program should
+ * continue. No registers are modified, so it is entirely up to the
+ * continuation code to figure out what to do.
+ *
+ * All the routines below use bits of fixup code that are out of line
+ * with the main instruction path.  This means when everything is well,
+ * we don't even have to jump over them.  Further, they do not intrude
+ * on our cache or tlb entries.
+ */
+
+struct exception_table_entry {
+	int insn, fixup;
+	short type, data;
+};
+
+#define ARCH_HAS_RELATIVE_EXTABLE
+
+#define swap_ex_entry_fixup(a, b, tmp, delta)		\
+do {							\
+	(a)->fixup = (b)->fixup + (delta);		\
+	(b)->fixup = (tmp).fixup - (delta);		\
+	(a)->type = (b)->type;				\
+	(b)->type = (tmp).type;				\
+	(a)->data = (b)->data;				\
+	(b)->data = (tmp).data;				\
+} while (0)
+
+bool fixup_exception(struct pt_regs *regs);
+
+#if defined(CONFIG_BPF_JIT) && defined(CONFIG_ARCH_RV64I)
+bool ex_handler_bpf(const struct exception_table_entry *ex, struct pt_regs *regs);
+#else
+static inline bool
+ex_handler_bpf(const struct exception_table_entry *ex,
+	       struct pt_regs *regs)
+{
+	return false;
+}
+#endif
+
+#endif
diff --git a/arch/riscv/include/asm/fence.h b/arch/riscv/include/asm/fence.h
new file mode 100644
index 000000000..2b443a3a4
--- /dev/null
+++ b/arch/riscv/include/asm/fence.h
@@ -0,0 +1,12 @@
+#ifndef _ASM_RISCV_FENCE_H
+#define _ASM_RISCV_FENCE_H
+
+#ifdef CONFIG_SMP
+#define RISCV_ACQUIRE_BARRIER		"\tfence r , rw\n"
+#define RISCV_RELEASE_BARRIER		"\tfence rw,  w\n"
+#else
+#define RISCV_ACQUIRE_BARRIER
+#define RISCV_RELEASE_BARRIER
+#endif
+
+#endif	/* _ASM_RISCV_FENCE_H */
diff --git a/arch/riscv/include/asm/fixmap.h b/arch/riscv/include/asm/fixmap.h
new file mode 100644
index 000000000..0a55099bb
--- /dev/null
+++ b/arch/riscv/include/asm/fixmap.h
@@ -0,0 +1,67 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2019 Western Digital Corporation or its affiliates.
+ */
+
+#ifndef _ASM_RISCV_FIXMAP_H
+#define _ASM_RISCV_FIXMAP_H
+
+#include <linux/kernel.h>
+#include <linux/sizes.h>
+#include <linux/pgtable.h>
+#include <asm/page.h>
+
+#ifdef CONFIG_MMU
+/*
+ * Here we define all the compile-time 'special' virtual addresses.
+ * The point is to have a constant address at compile time, but to
+ * set the physical address only in the boot process.
+ *
+ * These 'compile-time allocated' memory buffers are page-sized. Use
+ * set_fixmap(idx,phys) to associate physical memory with fixmap indices.
+ */
+enum fixed_addresses {
+	FIX_HOLE,
+	/*
+	 * The fdt fixmap mapping must be PMD aligned and will be mapped
+	 * using PMD entries in fixmap_pmd in 64-bit and a PGD entry in 32-bit.
+	 */
+	FIX_FDT_END,
+	FIX_FDT = FIX_FDT_END + FIX_FDT_SIZE / PAGE_SIZE - 1,
+
+	/* Below fixmaps will be mapped using fixmap_pte */
+	FIX_PTE,
+	FIX_PMD,
+	FIX_PUD,
+	FIX_P4D,
+	FIX_TEXT_POKE1,
+	FIX_TEXT_POKE0,
+	FIX_EARLYCON_MEM_BASE,
+
+	__end_of_permanent_fixed_addresses,
+	/*
+	 * Temporary boot-time mappings, used by early_ioremap(),
+	 * before ioremap() is functional.
+	 */
+#define NR_FIX_BTMAPS		(SZ_256K / PAGE_SIZE)
+#define FIX_BTMAPS_SLOTS	7
+#define TOTAL_FIX_BTMAPS	(NR_FIX_BTMAPS * FIX_BTMAPS_SLOTS)
+
+	FIX_BTMAP_END = __end_of_permanent_fixed_addresses,
+	FIX_BTMAP_BEGIN = FIX_BTMAP_END + TOTAL_FIX_BTMAPS - 1,
+
+	__end_of_fixed_addresses
+};
+
+#define __early_set_fixmap	__set_fixmap
+
+#define __late_set_fixmap	__set_fixmap
+#define __late_clear_fixmap(idx) __set_fixmap((idx), 0, FIXMAP_PAGE_CLEAR)
+
+extern void __set_fixmap(enum fixed_addresses idx,
+			 phys_addr_t phys, pgprot_t prot);
+
+#include <asm-generic/fixmap.h>
+
+#endif /* CONFIG_MMU */
+#endif /* _ASM_RISCV_FIXMAP_H */
diff --git a/arch/riscv/include/asm/ftrace.h b/arch/riscv/include/asm/ftrace.h
new file mode 100644
index 000000000..d47d87c2d
--- /dev/null
+++ b/arch/riscv/include/asm/ftrace.h
@@ -0,0 +1,114 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2017 Andes Technology Corporation */
+
+#ifndef _ASM_RISCV_FTRACE_H
+#define _ASM_RISCV_FTRACE_H
+
+/*
+ * The graph frame test is not possible if CONFIG_FRAME_POINTER is not enabled.
+ * Check arch/riscv/kernel/mcount.S for detail.
+ */
+#if defined(CONFIG_FUNCTION_GRAPH_TRACER) && defined(CONFIG_FRAME_POINTER)
+#define HAVE_FUNCTION_GRAPH_FP_TEST
+#endif
+#define HAVE_FUNCTION_GRAPH_RET_ADDR_PTR
+
+/*
+ * Clang prior to 13 had "mcount" instead of "_mcount":
+ * https://reviews.llvm.org/D98881
+ */
+#if defined(CONFIG_CC_IS_GCC) || CONFIG_CLANG_VERSION >= 130000
+#define MCOUNT_NAME _mcount
+#else
+#define MCOUNT_NAME mcount
+#endif
+
+#define ARCH_SUPPORTS_FTRACE_OPS 1
+#ifndef __ASSEMBLY__
+void MCOUNT_NAME(void);
+static inline unsigned long ftrace_call_adjust(unsigned long addr)
+{
+	return addr;
+}
+
+struct dyn_arch_ftrace {
+};
+#endif
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+/*
+ * A general call in RISC-V is a pair of insts:
+ * 1) auipc: setting high-20 pc-related bits to ra register
+ * 2) jalr: setting low-12 offset to ra, jump to ra, and set ra to
+ *          return address (original pc + 4)
+ *
+ *<ftrace enable>:
+ * 0: auipc  t0/ra, 0x?
+ * 4: jalr   t0/ra, ?(t0/ra)
+ *
+ *<ftrace disable>:
+ * 0: nop
+ * 4: nop
+ *
+ * Dynamic ftrace generates probes to call sites, so we must deal with
+ * both auipc and jalr at the same time.
+ */
+
+#define MCOUNT_ADDR		((unsigned long)MCOUNT_NAME)
+#define JALR_SIGN_MASK		(0x00000800)
+#define JALR_OFFSET_MASK	(0x00000fff)
+#define AUIPC_OFFSET_MASK	(0xfffff000)
+#define AUIPC_PAD		(0x00001000)
+#define JALR_SHIFT		20
+#define JALR_RA			(0x000080e7)
+#define AUIPC_RA		(0x00000097)
+#define JALR_T0			(0x000282e7)
+#define AUIPC_T0		(0x00000297)
+#define NOP4			(0x00000013)
+
+#define to_jalr_t0(offset)						\
+	(((offset & JALR_OFFSET_MASK) << JALR_SHIFT) | JALR_T0)
+
+#define to_auipc_t0(offset)						\
+	((offset & JALR_SIGN_MASK) ?					\
+	(((offset & AUIPC_OFFSET_MASK) + AUIPC_PAD) | AUIPC_T0) :	\
+	((offset & AUIPC_OFFSET_MASK) | AUIPC_T0))
+
+#define make_call_t0(caller, callee, call)				\
+do {									\
+	unsigned int offset =						\
+		(unsigned long) callee - (unsigned long) caller;	\
+	call[0] = to_auipc_t0(offset);					\
+	call[1] = to_jalr_t0(offset);					\
+} while (0)
+
+#define to_jalr_ra(offset)						\
+	(((offset & JALR_OFFSET_MASK) << JALR_SHIFT) | JALR_RA)
+
+#define to_auipc_ra(offset)						\
+	((offset & JALR_SIGN_MASK) ?					\
+	(((offset & AUIPC_OFFSET_MASK) + AUIPC_PAD) | AUIPC_RA) :	\
+	((offset & AUIPC_OFFSET_MASK) | AUIPC_RA))
+
+#define make_call_ra(caller, callee, call)				\
+do {									\
+	unsigned int offset =						\
+		(unsigned long) callee - (unsigned long) caller;	\
+	call[0] = to_auipc_ra(offset);					\
+	call[1] = to_jalr_ra(offset);					\
+} while (0)
+
+/*
+ * Let auipc+jalr be the basic *mcount unit*, so we make it 8 bytes here.
+ */
+#define MCOUNT_INSN_SIZE 8
+
+#ifndef __ASSEMBLY__
+struct dyn_ftrace;
+int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec);
+#define ftrace_init_nop ftrace_init_nop
+#endif
+
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+#endif /* _ASM_RISCV_FTRACE_H */
diff --git a/arch/riscv/include/asm/futex.h b/arch/riscv/include/asm/futex.h
new file mode 100644
index 000000000..fc8130f99
--- /dev/null
+++ b/arch/riscv/include/asm/futex.h
@@ -0,0 +1,104 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2006  Ralf Baechle (ralf@linux-mips.org)
+ * Copyright (c) 2018  Jim Wilson (jimw@sifive.com)
+ */
+
+#ifndef _ASM_RISCV_FUTEX_H
+#define _ASM_RISCV_FUTEX_H
+
+#include <linux/futex.h>
+#include <linux/uaccess.h>
+#include <linux/errno.h>
+#include <asm/asm.h>
+#include <asm/asm-extable.h>
+
+/* We don't even really need the extable code, but for now keep it simple */
+#ifndef CONFIG_MMU
+#define __enable_user_access()		do { } while (0)
+#define __disable_user_access()		do { } while (0)
+#endif
+
+#define __futex_atomic_op(insn, ret, oldval, uaddr, oparg)	\
+{								\
+	__enable_user_access();					\
+	__asm__ __volatile__ (					\
+	"1:	" insn "				\n"	\
+	"2:						\n"	\
+	_ASM_EXTABLE_UACCESS_ERR(1b, 2b, %[r])			\
+	: [r] "+r" (ret), [ov] "=&r" (oldval),			\
+	  [u] "+m" (*uaddr)					\
+	: [op] "Jr" (oparg)					\
+	: "memory");						\
+	__disable_user_access();				\
+}
+
+static inline int
+arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr)
+{
+	int oldval = 0, ret = 0;
+
+	if (!access_ok(uaddr, sizeof(u32)))
+		return -EFAULT;
+
+	switch (op) {
+	case FUTEX_OP_SET:
+		__futex_atomic_op("amoswap.w.aqrl %[ov],%z[op],%[u]",
+				  ret, oldval, uaddr, oparg);
+		break;
+	case FUTEX_OP_ADD:
+		__futex_atomic_op("amoadd.w.aqrl %[ov],%z[op],%[u]",
+				  ret, oldval, uaddr, oparg);
+		break;
+	case FUTEX_OP_OR:
+		__futex_atomic_op("amoor.w.aqrl %[ov],%z[op],%[u]",
+				  ret, oldval, uaddr, oparg);
+		break;
+	case FUTEX_OP_ANDN:
+		__futex_atomic_op("amoand.w.aqrl %[ov],%z[op],%[u]",
+				  ret, oldval, uaddr, ~oparg);
+		break;
+	case FUTEX_OP_XOR:
+		__futex_atomic_op("amoxor.w.aqrl %[ov],%z[op],%[u]",
+				  ret, oldval, uaddr, oparg);
+		break;
+	default:
+		ret = -ENOSYS;
+	}
+
+	if (!ret)
+		*oval = oldval;
+
+	return ret;
+}
+
+static inline int
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+			      u32 oldval, u32 newval)
+{
+	int ret = 0;
+	u32 val;
+	uintptr_t tmp;
+
+	if (!access_ok(uaddr, sizeof(u32)))
+		return -EFAULT;
+
+	__enable_user_access();
+	__asm__ __volatile__ (
+	"1:	lr.w.aqrl %[v],%[u]			\n"
+	"	bne %[v],%z[ov],3f			\n"
+	"2:	sc.w.aqrl %[t],%z[nv],%[u]		\n"
+	"	bnez %[t],1b				\n"
+	"3:						\n"
+		_ASM_EXTABLE_UACCESS_ERR(1b, 3b, %[r])	\
+		_ASM_EXTABLE_UACCESS_ERR(2b, 3b, %[r])	\
+	: [r] "+r" (ret), [v] "=&r" (val), [u] "+m" (*uaddr), [t] "=&r" (tmp)
+	: [ov] "Jr" (oldval), [nv] "Jr" (newval)
+	: "memory");
+	__disable_user_access();
+
+	*uval = val;
+	return ret;
+}
+
+#endif /* _ASM_RISCV_FUTEX_H */
diff --git a/arch/riscv/include/asm/gdb_xml.h b/arch/riscv/include/asm/gdb_xml.h
new file mode 100644
index 000000000..09342111f
--- /dev/null
+++ b/arch/riscv/include/asm/gdb_xml.h
@@ -0,0 +1,116 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __ASM_GDB_XML_H_
+#define __ASM_GDB_XML_H_
+
+const char riscv_gdb_stub_feature[64] =
+			"PacketSize=800;qXfer:features:read+;";
+
+static const char gdb_xfer_read_target[31] = "qXfer:features:read:target.xml:";
+
+#ifdef CONFIG_64BIT
+static const char gdb_xfer_read_cpuxml[39] =
+			"qXfer:features:read:riscv-64bit-cpu.xml";
+
+static const char riscv_gdb_stub_target_desc[256] =
+"l<?xml version=\"1.0\"?>"
+"<!DOCTYPE target SYSTEM \"gdb-target.dtd\">"
+"<target>"
+"<xi:include href=\"riscv-64bit-cpu.xml\"/>"
+"</target>";
+
+static const char riscv_gdb_stub_cpuxml[2048] =
+"l<?xml version=\"1.0\"?>"
+"<!DOCTYPE feature SYSTEM \"gdb-target.dtd\">"
+"<feature name=\"org.gnu.gdb.riscv.cpu\">"
+"<reg name=\""DBG_REG_ZERO"\" bitsize=\"64\" type=\"int\" regnum=\"0\"/>"
+"<reg name=\""DBG_REG_RA"\" bitsize=\"64\" type=\"code_ptr\"/>"
+"<reg name=\""DBG_REG_SP"\" bitsize=\"64\" type=\"data_ptr\"/>"
+"<reg name=\""DBG_REG_GP"\" bitsize=\"64\" type=\"data_ptr\"/>"
+"<reg name=\""DBG_REG_TP"\" bitsize=\"64\" type=\"data_ptr\"/>"
+"<reg name=\""DBG_REG_T0"\" bitsize=\"64\" type=\"int\"/>"
+"<reg name=\""DBG_REG_T1"\" bitsize=\"64\" type=\"int\"/>"
+"<reg name=\""DBG_REG_T2"\" bitsize=\"64\" type=\"int\"/>"
+"<reg name=\""DBG_REG_FP"\" bitsize=\"64\" type=\"data_ptr\"/>"
+"<reg name=\""DBG_REG_S1"\" bitsize=\"64\" type=\"int\"/>"
+"<reg name=\""DBG_REG_A0"\" bitsize=\"64\" type=\"int\"/>"
+"<reg name=\""DBG_REG_A1"\" bitsize=\"64\" type=\"int\"/>"
+"<reg name=\""DBG_REG_A2"\" bitsize=\"64\" type=\"int\"/>"
+"<reg name=\""DBG_REG_A3"\" bitsize=\"64\" type=\"int\"/>"
+"<reg name=\""DBG_REG_A4"\" bitsize=\"64\" type=\"int\"/>"
+"<reg name=\""DBG_REG_A5"\" bitsize=\"64\" type=\"int\"/>"
+"<reg name=\""DBG_REG_A6"\" bitsize=\"64\" type=\"int\"/>"
+"<reg name=\""DBG_REG_A7"\" bitsize=\"64\" type=\"int\"/>"
+"<reg name=\""DBG_REG_S2"\" bitsize=\"64\" type=\"int\"/>"
+"<reg name=\""DBG_REG_S3"\" bitsize=\"64\" type=\"int\"/>"
+"<reg name=\""DBG_REG_S4"\" bitsize=\"64\" type=\"int\"/>"
+"<reg name=\""DBG_REG_S5"\" bitsize=\"64\" type=\"int\"/>"
+"<reg name=\""DBG_REG_S6"\" bitsize=\"64\" type=\"int\"/>"
+"<reg name=\""DBG_REG_S7"\" bitsize=\"64\" type=\"int\"/>"
+"<reg name=\""DBG_REG_S8"\" bitsize=\"64\" type=\"int\"/>"
+"<reg name=\""DBG_REG_S9"\" bitsize=\"64\" type=\"int\"/>"
+"<reg name=\""DBG_REG_S10"\" bitsize=\"64\" type=\"int\"/>"
+"<reg name=\""DBG_REG_S11"\" bitsize=\"64\" type=\"int\"/>"
+"<reg name=\""DBG_REG_T3"\" bitsize=\"64\" type=\"int\"/>"
+"<reg name=\""DBG_REG_T4"\" bitsize=\"64\" type=\"int\"/>"
+"<reg name=\""DBG_REG_T5"\" bitsize=\"64\" type=\"int\"/>"
+"<reg name=\""DBG_REG_T6"\" bitsize=\"64\" type=\"int\"/>"
+"<reg name=\""DBG_REG_EPC"\" bitsize=\"64\" type=\"code_ptr\"/>"
+"<reg name=\""DBG_REG_STATUS"\" bitsize=\"64\" type=\"int\"/>"
+"<reg name=\""DBG_REG_BADADDR"\" bitsize=\"64\" type=\"int\"/>"
+"<reg name=\""DBG_REG_CAUSE"\" bitsize=\"64\" type=\"int\"/>"
+"</feature>";
+#else
+static const char gdb_xfer_read_cpuxml[39] =
+			"qXfer:features:read:riscv-32bit-cpu.xml";
+
+static const char riscv_gdb_stub_target_desc[256] =
+"l<?xml version=\"1.0\"?>"
+"<!DOCTYPE target SYSTEM \"gdb-target.dtd\">"
+"<target>"
+"<xi:include href=\"riscv-32bit-cpu.xml\"/>"
+"</target>";
+
+static const char riscv_gdb_stub_cpuxml[2048] =
+"l<?xml version=\"1.0\"?>"
+"<!DOCTYPE feature SYSTEM \"gdb-target.dtd\">"
+"<feature name=\"org.gnu.gdb.riscv.cpu\">"
+"<reg name=\""DBG_REG_ZERO"\" bitsize=\"32\" type=\"int\" regnum=\"0\"/>"
+"<reg name=\""DBG_REG_RA"\" bitsize=\"32\" type=\"code_ptr\"/>"
+"<reg name=\""DBG_REG_SP"\" bitsize=\"32\" type=\"data_ptr\"/>"
+"<reg name=\""DBG_REG_GP"\" bitsize=\"32\" type=\"data_ptr\"/>"
+"<reg name=\""DBG_REG_TP"\" bitsize=\"32\" type=\"data_ptr\"/>"
+"<reg name=\""DBG_REG_T0"\" bitsize=\"32\" type=\"int\"/>"
+"<reg name=\""DBG_REG_T1"\" bitsize=\"32\" type=\"int\"/>"
+"<reg name=\""DBG_REG_T2"\" bitsize=\"32\" type=\"int\"/>"
+"<reg name=\""DBG_REG_FP"\" bitsize=\"32\" type=\"data_ptr\"/>"
+"<reg name=\""DBG_REG_S1"\" bitsize=\"32\" type=\"int\"/>"
+"<reg name=\""DBG_REG_A0"\" bitsize=\"32\" type=\"int\"/>"
+"<reg name=\""DBG_REG_A1"\" bitsize=\"32\" type=\"int\"/>"
+"<reg name=\""DBG_REG_A2"\" bitsize=\"32\" type=\"int\"/>"
+"<reg name=\""DBG_REG_A3"\" bitsize=\"32\" type=\"int\"/>"
+"<reg name=\""DBG_REG_A4"\" bitsize=\"32\" type=\"int\"/>"
+"<reg name=\""DBG_REG_A5"\" bitsize=\"32\" type=\"int\"/>"
+"<reg name=\""DBG_REG_A6"\" bitsize=\"32\" type=\"int\"/>"
+"<reg name=\""DBG_REG_A7"\" bitsize=\"32\" type=\"int\"/>"
+"<reg name=\""DBG_REG_S2"\" bitsize=\"32\" type=\"int\"/>"
+"<reg name=\""DBG_REG_S3"\" bitsize=\"32\" type=\"int\"/>"
+"<reg name=\""DBG_REG_S4"\" bitsize=\"32\" type=\"int\"/>"
+"<reg name=\""DBG_REG_S5"\" bitsize=\"32\" type=\"int\"/>"
+"<reg name=\""DBG_REG_S6"\" bitsize=\"32\" type=\"int\"/>"
+"<reg name=\""DBG_REG_S7"\" bitsize=\"32\" type=\"int\"/>"
+"<reg name=\""DBG_REG_S8"\" bitsize=\"32\" type=\"int\"/>"
+"<reg name=\""DBG_REG_S9"\" bitsize=\"32\" type=\"int\"/>"
+"<reg name=\""DBG_REG_S10"\" bitsize=\"32\" type=\"int\"/>"
+"<reg name=\""DBG_REG_S11"\" bitsize=\"32\" type=\"int\"/>"
+"<reg name=\""DBG_REG_T3"\" bitsize=\"32\" type=\"int\"/>"
+"<reg name=\""DBG_REG_T4"\" bitsize=\"32\" type=\"int\"/>"
+"<reg name=\""DBG_REG_T5"\" bitsize=\"32\" type=\"int\"/>"
+"<reg name=\""DBG_REG_T6"\" bitsize=\"32\" type=\"int\"/>"
+"<reg name=\""DBG_REG_EPC"\" bitsize=\"32\" type=\"code_ptr\"/>"
+"<reg name=\""DBG_REG_STATUS"\" bitsize=\"32\" type=\"int\"/>"
+"<reg name=\""DBG_REG_BADADDR"\" bitsize=\"32\" type=\"int\"/>"
+"<reg name=\""DBG_REG_CAUSE"\" bitsize=\"32\" type=\"int\"/>"
+"</feature>";
+#endif
+#endif
diff --git a/arch/riscv/include/asm/gpr-num.h b/arch/riscv/include/asm/gpr-num.h
new file mode 100644
index 000000000..efeb5edf8
--- /dev/null
+++ b/arch/riscv/include/asm/gpr-num.h
@@ -0,0 +1,85 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef __ASM_GPR_NUM_H
+#define __ASM_GPR_NUM_H
+
+#ifdef __ASSEMBLY__
+
+	.irp	num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31
+	.equ	.L__gpr_num_x\num, \num
+	.endr
+
+	.equ	.L__gpr_num_zero,	0
+	.equ	.L__gpr_num_ra,		1
+	.equ	.L__gpr_num_sp,		2
+	.equ	.L__gpr_num_gp,		3
+	.equ	.L__gpr_num_tp,		4
+	.equ	.L__gpr_num_t0,		5
+	.equ	.L__gpr_num_t1,		6
+	.equ	.L__gpr_num_t2,		7
+	.equ	.L__gpr_num_s0,		8
+	.equ	.L__gpr_num_s1,		9
+	.equ	.L__gpr_num_a0,		10
+	.equ	.L__gpr_num_a1,		11
+	.equ	.L__gpr_num_a2,		12
+	.equ	.L__gpr_num_a3,		13
+	.equ	.L__gpr_num_a4,		14
+	.equ	.L__gpr_num_a5,		15
+	.equ	.L__gpr_num_a6,		16
+	.equ	.L__gpr_num_a7,		17
+	.equ	.L__gpr_num_s2,		18
+	.equ	.L__gpr_num_s3,		19
+	.equ	.L__gpr_num_s4,		20
+	.equ	.L__gpr_num_s5,		21
+	.equ	.L__gpr_num_s6,		22
+	.equ	.L__gpr_num_s7,		23
+	.equ	.L__gpr_num_s8,		24
+	.equ	.L__gpr_num_s9,		25
+	.equ	.L__gpr_num_s10,	26
+	.equ	.L__gpr_num_s11,	27
+	.equ	.L__gpr_num_t3,		28
+	.equ	.L__gpr_num_t4,		29
+	.equ	.L__gpr_num_t5,		30
+	.equ	.L__gpr_num_t6,		31
+
+#else /* __ASSEMBLY__ */
+
+#define __DEFINE_ASM_GPR_NUMS					\
+"	.irp	num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31\n" \
+"	.equ	.L__gpr_num_x\\num, \\num\n"			\
+"	.endr\n"						\
+"	.equ	.L__gpr_num_zero,	0\n"			\
+"	.equ	.L__gpr_num_ra,		1\n"			\
+"	.equ	.L__gpr_num_sp,		2\n"			\
+"	.equ	.L__gpr_num_gp,		3\n"			\
+"	.equ	.L__gpr_num_tp,		4\n"			\
+"	.equ	.L__gpr_num_t0,		5\n"			\
+"	.equ	.L__gpr_num_t1,		6\n"			\
+"	.equ	.L__gpr_num_t2,		7\n"			\
+"	.equ	.L__gpr_num_s0,		8\n"			\
+"	.equ	.L__gpr_num_s1,		9\n"			\
+"	.equ	.L__gpr_num_a0,		10\n"			\
+"	.equ	.L__gpr_num_a1,		11\n"			\
+"	.equ	.L__gpr_num_a2,		12\n"			\
+"	.equ	.L__gpr_num_a3,		13\n"			\
+"	.equ	.L__gpr_num_a4,		14\n"			\
+"	.equ	.L__gpr_num_a5,		15\n"			\
+"	.equ	.L__gpr_num_a6,		16\n"			\
+"	.equ	.L__gpr_num_a7,		17\n"			\
+"	.equ	.L__gpr_num_s2,		18\n"			\
+"	.equ	.L__gpr_num_s3,		19\n"			\
+"	.equ	.L__gpr_num_s4,		20\n"			\
+"	.equ	.L__gpr_num_s5,		21\n"			\
+"	.equ	.L__gpr_num_s6,		22\n"			\
+"	.equ	.L__gpr_num_s7,		23\n"			\
+"	.equ	.L__gpr_num_s8,		24\n"			\
+"	.equ	.L__gpr_num_s9,		25\n"			\
+"	.equ	.L__gpr_num_s10,	26\n"			\
+"	.equ	.L__gpr_num_s11,	27\n"			\
+"	.equ	.L__gpr_num_t3,		28\n"			\
+"	.equ	.L__gpr_num_t4,		29\n"			\
+"	.equ	.L__gpr_num_t5,		30\n"			\
+"	.equ	.L__gpr_num_t6,		31\n"
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __ASM_GPR_NUM_H */
diff --git a/arch/riscv/include/asm/hugetlb.h b/arch/riscv/include/asm/hugetlb.h
new file mode 100644
index 000000000..ec19d6afc
--- /dev/null
+++ b/arch/riscv/include/asm/hugetlb.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_RISCV_HUGETLB_H
+#define _ASM_RISCV_HUGETLB_H
+
+#include <asm-generic/hugetlb.h>
+#include <asm/page.h>
+
+static inline void arch_clear_hugepage_flags(struct page *page)
+{
+	clear_bit(PG_dcache_clean, &page->flags);
+}
+#define arch_clear_hugepage_flags arch_clear_hugepage_flags
+
+#endif /* _ASM_RISCV_HUGETLB_H */
diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
new file mode 100644
index 000000000..b22525290
--- /dev/null
+++ b/arch/riscv/include/asm/hwcap.h
@@ -0,0 +1,112 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copied from arch/arm64/include/asm/hwcap.h
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2017 SiFive
+ */
+#ifndef _ASM_RISCV_HWCAP_H
+#define _ASM_RISCV_HWCAP_H
+
+#include <asm/errno.h>
+#include <linux/bits.h>
+#include <uapi/asm/hwcap.h>
+
+#ifndef __ASSEMBLY__
+#include <linux/jump_label.h>
+/*
+ * This yields a mask that user programs can use to figure out what
+ * instruction set this cpu supports.
+ */
+#define ELF_HWCAP		(elf_hwcap)
+
+enum {
+	CAP_HWCAP = 1,
+};
+
+extern unsigned long elf_hwcap;
+
+#define RISCV_ISA_EXT_a		('a' - 'a')
+#define RISCV_ISA_EXT_c		('c' - 'a')
+#define RISCV_ISA_EXT_d		('d' - 'a')
+#define RISCV_ISA_EXT_f		('f' - 'a')
+#define RISCV_ISA_EXT_h		('h' - 'a')
+#define RISCV_ISA_EXT_i		('i' - 'a')
+#define RISCV_ISA_EXT_m		('m' - 'a')
+#define RISCV_ISA_EXT_s		('s' - 'a')
+#define RISCV_ISA_EXT_u		('u' - 'a')
+
+/*
+ * Increse this to higher value as kernel support more ISA extensions.
+ */
+#define RISCV_ISA_EXT_MAX	64
+#define RISCV_ISA_EXT_NAME_LEN_MAX 32
+
+/* The base ID for multi-letter ISA extensions */
+#define RISCV_ISA_EXT_BASE 26
+
+/*
+ * This enum represent the logical ID for each multi-letter RISC-V ISA extension.
+ * The logical ID should start from RISCV_ISA_EXT_BASE and must not exceed
+ * RISCV_ISA_EXT_MAX. 0-25 range is reserved for single letter
+ * extensions while all the multi-letter extensions should define the next
+ * available logical extension id.
+ */
+enum riscv_isa_ext_id {
+	RISCV_ISA_EXT_SSCOFPMF = RISCV_ISA_EXT_BASE,
+	RISCV_ISA_EXT_SVPBMT,
+	RISCV_ISA_EXT_ZICBOM,
+	RISCV_ISA_EXT_ZIHINTPAUSE,
+	RISCV_ISA_EXT_SSTC,
+	RISCV_ISA_EXT_SVINVAL,
+	RISCV_ISA_EXT_ID_MAX = RISCV_ISA_EXT_MAX,
+};
+
+/*
+ * This enum represents the logical ID for each RISC-V ISA extension static
+ * keys. We can use static key to optimize code path if some ISA extensions
+ * are available.
+ */
+enum riscv_isa_ext_key {
+	RISCV_ISA_EXT_KEY_FPU,		/* For 'F' and 'D' */
+	RISCV_ISA_EXT_KEY_ZIHINTPAUSE,
+	RISCV_ISA_EXT_KEY_SVINVAL,
+	RISCV_ISA_EXT_KEY_MAX,
+};
+
+struct riscv_isa_ext_data {
+	/* Name of the extension displayed to userspace via /proc/cpuinfo */
+	char uprop[RISCV_ISA_EXT_NAME_LEN_MAX];
+	/* The logical ISA extension ID */
+	unsigned int isa_ext_id;
+};
+
+extern struct static_key_false riscv_isa_ext_keys[RISCV_ISA_EXT_KEY_MAX];
+
+static __always_inline int riscv_isa_ext2key(int num)
+{
+	switch (num) {
+	case RISCV_ISA_EXT_f:
+		return RISCV_ISA_EXT_KEY_FPU;
+	case RISCV_ISA_EXT_d:
+		return RISCV_ISA_EXT_KEY_FPU;
+	case RISCV_ISA_EXT_ZIHINTPAUSE:
+		return RISCV_ISA_EXT_KEY_ZIHINTPAUSE;
+	case RISCV_ISA_EXT_SVINVAL:
+		return RISCV_ISA_EXT_KEY_SVINVAL;
+	default:
+		return -EINVAL;
+	}
+}
+
+unsigned long riscv_isa_extension_base(const unsigned long *isa_bitmap);
+
+#define riscv_isa_extension_mask(ext) BIT_MASK(RISCV_ISA_EXT_##ext)
+
+bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, int bit);
+#define riscv_isa_extension_available(isa_bitmap, ext)	\
+	__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_##ext)
+
+#endif
+
+#endif /* _ASM_RISCV_HWCAP_H */
diff --git a/arch/riscv/include/asm/image.h b/arch/riscv/include/asm/image.h
new file mode 100644
index 000000000..e0b319af3
--- /dev/null
+++ b/arch/riscv/include/asm/image.h
@@ -0,0 +1,65 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _ASM_RISCV_IMAGE_H
+#define _ASM_RISCV_IMAGE_H
+
+#define RISCV_IMAGE_MAGIC	"RISCV\0\0\0"
+#define RISCV_IMAGE_MAGIC2	"RSC\x05"
+
+#define RISCV_IMAGE_FLAG_BE_SHIFT	0
+#define RISCV_IMAGE_FLAG_BE_MASK	0x1
+
+#define RISCV_IMAGE_FLAG_LE		0
+#define RISCV_IMAGE_FLAG_BE		1
+
+#ifdef CONFIG_CPU_BIG_ENDIAN
+#error conversion of header fields to LE not yet implemented
+#else
+#define __HEAD_FLAG_BE		RISCV_IMAGE_FLAG_LE
+#endif
+
+#define __HEAD_FLAG(field)	(__HEAD_FLAG_##field << \
+				RISCV_IMAGE_FLAG_##field##_SHIFT)
+
+#define __HEAD_FLAGS		(__HEAD_FLAG(BE))
+
+#define RISCV_HEADER_VERSION_MAJOR 0
+#define RISCV_HEADER_VERSION_MINOR 2
+
+#define RISCV_HEADER_VERSION (RISCV_HEADER_VERSION_MAJOR << 16 | \
+			      RISCV_HEADER_VERSION_MINOR)
+
+#ifndef __ASSEMBLY__
+/**
+ * struct riscv_image_header - riscv kernel image header
+ * @code0:		Executable code
+ * @code1:		Executable code
+ * @text_offset:	Image load offset (little endian)
+ * @image_size:		Effective Image size (little endian)
+ * @flags:		kernel flags (little endian)
+ * @version:		version
+ * @res1:		reserved
+ * @res2:		reserved
+ * @magic:		Magic number (RISC-V specific; deprecated)
+ * @magic2:		Magic number 2 (to match the ARM64 'magic' field pos)
+ * @res3:		reserved (will be used for PE COFF offset)
+ *
+ * The intention is for this header format to be shared between multiple
+ * architectures to avoid a proliferation of image header formats.
+ */
+
+struct riscv_image_header {
+	u32 code0;
+	u32 code1;
+	u64 text_offset;
+	u64 image_size;
+	u64 flags;
+	u32 version;
+	u32 res1;
+	u64 res2;
+	u64 magic;
+	u32 magic2;
+	u32 res3;
+};
+#endif /* __ASSEMBLY__ */
+#endif /* _ASM_RISCV_IMAGE_H */
diff --git a/arch/riscv/include/asm/insn-def.h b/arch/riscv/include/asm/insn-def.h
new file mode 100644
index 000000000..16044affa
--- /dev/null
+++ b/arch/riscv/include/asm/insn-def.h
@@ -0,0 +1,137 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __ASM_INSN_DEF_H
+#define __ASM_INSN_DEF_H
+
+#include <asm/asm.h>
+
+#define INSN_R_FUNC7_SHIFT		25
+#define INSN_R_RS2_SHIFT		20
+#define INSN_R_RS1_SHIFT		15
+#define INSN_R_FUNC3_SHIFT		12
+#define INSN_R_RD_SHIFT			 7
+#define INSN_R_OPCODE_SHIFT		 0
+
+#ifdef __ASSEMBLY__
+
+#ifdef CONFIG_AS_HAS_INSN
+
+	.macro insn_r, opcode, func3, func7, rd, rs1, rs2
+	.insn	r \opcode, \func3, \func7, \rd, \rs1, \rs2
+	.endm
+
+#else
+
+#include <asm/gpr-num.h>
+
+	.macro insn_r, opcode, func3, func7, rd, rs1, rs2
+	.4byte	((\opcode << INSN_R_OPCODE_SHIFT) |		\
+		 (\func3 << INSN_R_FUNC3_SHIFT) |		\
+		 (\func7 << INSN_R_FUNC7_SHIFT) |		\
+		 (.L__gpr_num_\rd << INSN_R_RD_SHIFT) |		\
+		 (.L__gpr_num_\rs1 << INSN_R_RS1_SHIFT) |	\
+		 (.L__gpr_num_\rs2 << INSN_R_RS2_SHIFT))
+	.endm
+
+#endif
+
+#define __INSN_R(...)	insn_r __VA_ARGS__
+
+#else /* ! __ASSEMBLY__ */
+
+#ifdef CONFIG_AS_HAS_INSN
+
+#define __INSN_R(opcode, func3, func7, rd, rs1, rs2)	\
+	".insn	r " opcode ", " func3 ", " func7 ", " rd ", " rs1 ", " rs2 "\n"
+
+#else
+
+#include <linux/stringify.h>
+#include <asm/gpr-num.h>
+
+#define DEFINE_INSN_R							\
+	__DEFINE_ASM_GPR_NUMS						\
+"	.macro insn_r, opcode, func3, func7, rd, rs1, rs2\n"		\
+"	.4byte	((\\opcode << " __stringify(INSN_R_OPCODE_SHIFT) ") |"	\
+"		 (\\func3 << " __stringify(INSN_R_FUNC3_SHIFT) ") |"	\
+"		 (\\func7 << " __stringify(INSN_R_FUNC7_SHIFT) ") |"	\
+"		 (.L__gpr_num_\\rd << " __stringify(INSN_R_RD_SHIFT) ") |"    \
+"		 (.L__gpr_num_\\rs1 << " __stringify(INSN_R_RS1_SHIFT) ") |"  \
+"		 (.L__gpr_num_\\rs2 << " __stringify(INSN_R_RS2_SHIFT) "))\n" \
+"	.endm\n"
+
+#define UNDEFINE_INSN_R							\
+"	.purgem insn_r\n"
+
+#define __INSN_R(opcode, func3, func7, rd, rs1, rs2)			\
+	DEFINE_INSN_R							\
+	"insn_r " opcode ", " func3 ", " func7 ", " rd ", " rs1 ", " rs2 "\n" \
+	UNDEFINE_INSN_R
+
+#endif
+
+#endif /* ! __ASSEMBLY__ */
+
+#define INSN_R(opcode, func3, func7, rd, rs1, rs2)		\
+	__INSN_R(RV_##opcode, RV_##func3, RV_##func7,		\
+		 RV_##rd, RV_##rs1, RV_##rs2)
+
+#define RV_OPCODE(v)		__ASM_STR(v)
+#define RV_FUNC3(v)		__ASM_STR(v)
+#define RV_FUNC7(v)		__ASM_STR(v)
+#define RV_RD(v)		__ASM_STR(v)
+#define RV_RS1(v)		__ASM_STR(v)
+#define RV_RS2(v)		__ASM_STR(v)
+#define __RV_REG(v)		__ASM_STR(x ## v)
+#define RV___RD(v)		__RV_REG(v)
+#define RV___RS1(v)		__RV_REG(v)
+#define RV___RS2(v)		__RV_REG(v)
+
+#define RV_OPCODE_SYSTEM	RV_OPCODE(115)
+
+#define HFENCE_VVMA(vaddr, asid)				\
+	INSN_R(OPCODE_SYSTEM, FUNC3(0), FUNC7(17),		\
+	       __RD(0), RS1(vaddr), RS2(asid))
+
+#define HFENCE_GVMA(gaddr, vmid)				\
+	INSN_R(OPCODE_SYSTEM, FUNC3(0), FUNC7(49),		\
+	       __RD(0), RS1(gaddr), RS2(vmid))
+
+#define HLVX_HU(dest, addr)					\
+	INSN_R(OPCODE_SYSTEM, FUNC3(4), FUNC7(50),		\
+	       RD(dest), RS1(addr), __RS2(3))
+
+#define HLV_W(dest, addr)					\
+	INSN_R(OPCODE_SYSTEM, FUNC3(4), FUNC7(52),		\
+	       RD(dest), RS1(addr), __RS2(0))
+
+#ifdef CONFIG_64BIT
+#define HLV_D(dest, addr)					\
+	INSN_R(OPCODE_SYSTEM, FUNC3(4), FUNC7(54),		\
+	       RD(dest), RS1(addr), __RS2(0))
+#else
+#define HLV_D(dest, addr)					\
+	__ASM_STR(.error "hlv.d requires 64-bit support")
+#endif
+
+#define SINVAL_VMA(vaddr, asid)					\
+	INSN_R(OPCODE_SYSTEM, FUNC3(0), FUNC7(11),		\
+	       __RD(0), RS1(vaddr), RS2(asid))
+
+#define SFENCE_W_INVAL()					\
+	INSN_R(OPCODE_SYSTEM, FUNC3(0), FUNC7(12),		\
+	       __RD(0), __RS1(0), __RS2(0))
+
+#define SFENCE_INVAL_IR()					\
+	INSN_R(OPCODE_SYSTEM, FUNC3(0), FUNC7(12),		\
+	       __RD(0), __RS1(0), __RS2(1))
+
+#define HINVAL_VVMA(vaddr, asid)				\
+	INSN_R(OPCODE_SYSTEM, FUNC3(0), FUNC7(19),		\
+	       __RD(0), RS1(vaddr), RS2(asid))
+
+#define HINVAL_GVMA(gaddr, vmid)				\
+	INSN_R(OPCODE_SYSTEM, FUNC3(0), FUNC7(51),		\
+	       __RD(0), RS1(gaddr), RS2(vmid))
+
+#endif /* __ASM_INSN_DEF_H */
diff --git a/arch/riscv/include/asm/io.h b/arch/riscv/include/asm/io.h
new file mode 100644
index 000000000..42497d487
--- /dev/null
+++ b/arch/riscv/include/asm/io.h
@@ -0,0 +1,143 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * {read,write}{b,w,l,q} based on arch/arm64/include/asm/io.h
+ *   which was based on arch/arm/include/io.h
+ *
+ * Copyright (C) 1996-2000 Russell King
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2014 Regents of the University of California
+ */
+
+#ifndef _ASM_RISCV_IO_H
+#define _ASM_RISCV_IO_H
+
+#include <linux/types.h>
+#include <linux/pgtable.h>
+#include <asm/mmiowb.h>
+#include <asm/early_ioremap.h>
+
+/*
+ * MMIO access functions are separated out to break dependency cycles
+ * when using {read,write}* fns in low-level headers
+ */
+#include <asm/mmio.h>
+
+/*
+ *  I/O port access constants.
+ */
+#ifdef CONFIG_MMU
+#define IO_SPACE_LIMIT		(PCI_IO_SIZE - 1)
+#define PCI_IOBASE		((void __iomem *)PCI_IO_START)
+#endif /* CONFIG_MMU */
+
+/*
+ * Emulation routines for the port-mapped IO space used by some PCI drivers.
+ * These are defined as being "fully synchronous", but also "not guaranteed to
+ * be fully ordered with respect to other memory and I/O operations".  We're
+ * going to be on the safe side here and just make them:
+ *  - Fully ordered WRT each other, by bracketing them with two fences.  The
+ *    outer set contains both I/O so inX is ordered with outX, while the inner just
+ *    needs the type of the access (I for inX and O for outX).
+ *  - Ordered in the same manner as readX/writeX WRT memory by subsuming their
+ *    fences.
+ *  - Ordered WRT timer reads, so udelay and friends don't get elided by the
+ *    implementation.
+ * Note that there is no way to actually enforce that outX is a non-posted
+ * operation on RISC-V, but hopefully the timer ordering constraint is
+ * sufficient to ensure this works sanely on controllers that support I/O
+ * writes.
+ */
+#define __io_pbr()	__asm__ __volatile__ ("fence io,i"  : : : "memory");
+#define __io_par(v)	__asm__ __volatile__ ("fence i,ior" : : : "memory");
+#define __io_pbw()	__asm__ __volatile__ ("fence iow,o" : : : "memory");
+#define __io_paw()	__asm__ __volatile__ ("fence o,io"  : : : "memory");
+
+/*
+ * Accesses from a single hart to a single I/O address must be ordered.  This
+ * allows us to use the raw read macros, but we still need to fence before and
+ * after the block to ensure ordering WRT other macros.  These are defined to
+ * perform host-endian accesses so we use __raw instead of __cpu.
+ */
+#define __io_reads_ins(port, ctype, len, bfence, afence)			\
+	static inline void __ ## port ## len(const volatile void __iomem *addr,	\
+					     void *buffer,			\
+					     unsigned int count)		\
+	{									\
+		bfence;								\
+		if (count) {							\
+			ctype *buf = buffer;					\
+										\
+			do {							\
+				ctype x = __raw_read ## len(addr);		\
+				*buf++ = x;					\
+			} while (--count);					\
+		}								\
+		afence;								\
+	}
+
+#define __io_writes_outs(port, ctype, len, bfence, afence)			\
+	static inline void __ ## port ## len(volatile void __iomem *addr,	\
+					     const void *buffer,		\
+					     unsigned int count)		\
+	{									\
+		bfence;								\
+		if (count) {							\
+			const ctype *buf = buffer;				\
+										\
+			do {							\
+				__raw_write ## len(*buf++, addr);		\
+			} while (--count);					\
+		}								\
+		afence;								\
+	}
+
+__io_reads_ins(reads,  u8, b, __io_br(), __io_ar(addr))
+__io_reads_ins(reads, u16, w, __io_br(), __io_ar(addr))
+__io_reads_ins(reads, u32, l, __io_br(), __io_ar(addr))
+#define readsb(addr, buffer, count) __readsb(addr, buffer, count)
+#define readsw(addr, buffer, count) __readsw(addr, buffer, count)
+#define readsl(addr, buffer, count) __readsl(addr, buffer, count)
+
+__io_reads_ins(ins,  u8, b, __io_pbr(), __io_par(addr))
+__io_reads_ins(ins, u16, w, __io_pbr(), __io_par(addr))
+__io_reads_ins(ins, u32, l, __io_pbr(), __io_par(addr))
+#define insb(addr, buffer, count) __insb(PCI_IOBASE + (addr), buffer, count)
+#define insw(addr, buffer, count) __insw(PCI_IOBASE + (addr), buffer, count)
+#define insl(addr, buffer, count) __insl(PCI_IOBASE + (addr), buffer, count)
+
+__io_writes_outs(writes,  u8, b, __io_bw(), __io_aw())
+__io_writes_outs(writes, u16, w, __io_bw(), __io_aw())
+__io_writes_outs(writes, u32, l, __io_bw(), __io_aw())
+#define writesb(addr, buffer, count) __writesb(addr, buffer, count)
+#define writesw(addr, buffer, count) __writesw(addr, buffer, count)
+#define writesl(addr, buffer, count) __writesl(addr, buffer, count)
+
+__io_writes_outs(outs,  u8, b, __io_pbw(), __io_paw())
+__io_writes_outs(outs, u16, w, __io_pbw(), __io_paw())
+__io_writes_outs(outs, u32, l, __io_pbw(), __io_paw())
+#define outsb(addr, buffer, count) __outsb(PCI_IOBASE + (addr), buffer, count)
+#define outsw(addr, buffer, count) __outsw(PCI_IOBASE + (addr), buffer, count)
+#define outsl(addr, buffer, count) __outsl(PCI_IOBASE + (addr), buffer, count)
+
+#ifdef CONFIG_64BIT
+__io_reads_ins(reads, u64, q, __io_br(), __io_ar(addr))
+#define readsq(addr, buffer, count) __readsq(addr, buffer, count)
+
+__io_reads_ins(ins, u64, q, __io_pbr(), __io_par(addr))
+#define insq(addr, buffer, count) __insq(PCI_IOBASE + (addr), buffer, count)
+
+__io_writes_outs(writes, u64, q, __io_bw(), __io_aw())
+#define writesq(addr, buffer, count) __writesq(addr, buffer, count)
+
+__io_writes_outs(outs, u64, q, __io_pbr(), __io_paw())
+#define outsq(addr, buffer, count) __outsq(PCI_IOBASE + (addr), buffer, count)
+#endif
+
+#include <asm-generic/io.h>
+
+#ifdef CONFIG_MMU
+#define arch_memremap_wb(addr, size)	\
+	((__force void *)ioremap_prot((addr), (size), _PAGE_KERNEL))
+#endif
+
+#endif /* _ASM_RISCV_IO_H */
diff --git a/arch/riscv/include/asm/irq.h b/arch/riscv/include/asm/irq.h
new file mode 100644
index 000000000..e4c435509
--- /dev/null
+++ b/arch/riscv/include/asm/irq.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ * Copyright (C) 2017 SiFive
+ */
+
+#ifndef _ASM_RISCV_IRQ_H
+#define _ASM_RISCV_IRQ_H
+
+#include <linux/interrupt.h>
+#include <linux/linkage.h>
+
+#include <asm-generic/irq.h>
+
+extern void __init init_IRQ(void);
+
+#endif /* _ASM_RISCV_IRQ_H */
diff --git a/arch/riscv/include/asm/irq_work.h b/arch/riscv/include/asm/irq_work.h
new file mode 100644
index 000000000..b53891964
--- /dev/null
+++ b/arch/riscv/include/asm/irq_work.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_RISCV_IRQ_WORK_H
+#define _ASM_RISCV_IRQ_WORK_H
+
+static inline bool arch_irq_work_has_interrupt(void)
+{
+	return IS_ENABLED(CONFIG_SMP);
+}
+extern void arch_irq_work_raise(void);
+#endif /* _ASM_RISCV_IRQ_WORK_H */
diff --git a/arch/riscv/include/asm/irqflags.h b/arch/riscv/include/asm/irqflags.h
new file mode 100644
index 000000000..08d4d6a5b
--- /dev/null
+++ b/arch/riscv/include/asm/irqflags.h
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ */
+
+
+#ifndef _ASM_RISCV_IRQFLAGS_H
+#define _ASM_RISCV_IRQFLAGS_H
+
+#include <asm/processor.h>
+#include <asm/csr.h>
+
+/* read interrupt enabled status */
+static inline unsigned long arch_local_save_flags(void)
+{
+	return csr_read(CSR_STATUS);
+}
+
+/* unconditionally enable interrupts */
+static inline void arch_local_irq_enable(void)
+{
+	csr_set(CSR_STATUS, SR_IE);
+}
+
+/* unconditionally disable interrupts */
+static inline void arch_local_irq_disable(void)
+{
+	csr_clear(CSR_STATUS, SR_IE);
+}
+
+/* get status and disable interrupts */
+static inline unsigned long arch_local_irq_save(void)
+{
+	return csr_read_clear(CSR_STATUS, SR_IE);
+}
+
+/* test flags */
+static inline int arch_irqs_disabled_flags(unsigned long flags)
+{
+	return !(flags & SR_IE);
+}
+
+/* test hardware interrupt enable bit */
+static inline int arch_irqs_disabled(void)
+{
+	return arch_irqs_disabled_flags(arch_local_save_flags());
+}
+
+/* set interrupt enabled status */
+static inline void arch_local_irq_restore(unsigned long flags)
+{
+	csr_set(CSR_STATUS, flags & SR_IE);
+}
+
+#endif /* _ASM_RISCV_IRQFLAGS_H */
diff --git a/arch/riscv/include/asm/jump_label.h b/arch/riscv/include/asm/jump_label.h
new file mode 100644
index 000000000..14a5ea8d8
--- /dev/null
+++ b/arch/riscv/include/asm/jump_label.h
@@ -0,0 +1,62 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2020 Emil Renner Berthing
+ *
+ * Based on arch/arm64/include/asm/jump_label.h
+ */
+#ifndef __ASM_JUMP_LABEL_H
+#define __ASM_JUMP_LABEL_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+#include <asm/asm.h>
+
+#define JUMP_LABEL_NOP_SIZE 4
+
+static __always_inline bool arch_static_branch(struct static_key * const key,
+					       const bool branch)
+{
+	asm_volatile_goto(
+		"	.align		2			\n\t"
+		"	.option push				\n\t"
+		"	.option norelax				\n\t"
+		"	.option norvc				\n\t"
+		"1:	nop					\n\t"
+		"	.option pop				\n\t"
+		"	.pushsection	__jump_table, \"aw\"	\n\t"
+		"	.align		" RISCV_LGPTR "		\n\t"
+		"	.long		1b - ., %l[label] - .	\n\t"
+		"	" RISCV_PTR "	%0 - .			\n\t"
+		"	.popsection				\n\t"
+		:  :  "i"(&((char *)key)[branch]) :  : label);
+
+	return false;
+label:
+	return true;
+}
+
+static __always_inline bool arch_static_branch_jump(struct static_key * const key,
+						    const bool branch)
+{
+	asm_volatile_goto(
+		"	.align		2			\n\t"
+		"	.option push				\n\t"
+		"	.option norelax				\n\t"
+		"	.option norvc				\n\t"
+		"1:	jal		zero, %l[label]		\n\t"
+		"	.option pop				\n\t"
+		"	.pushsection	__jump_table, \"aw\"	\n\t"
+		"	.align		" RISCV_LGPTR "		\n\t"
+		"	.long		1b - ., %l[label] - .	\n\t"
+		"	" RISCV_PTR "	%0 - .			\n\t"
+		"	.popsection				\n\t"
+		:  :  "i"(&((char *)key)[branch]) :  : label);
+
+	return false;
+label:
+	return true;
+}
+
+#endif  /* __ASSEMBLY__ */
+#endif	/* __ASM_JUMP_LABEL_H */
diff --git a/arch/riscv/include/asm/kasan.h b/arch/riscv/include/asm/kasan.h
new file mode 100644
index 000000000..0b85e363e
--- /dev/null
+++ b/arch/riscv/include/asm/kasan.h
@@ -0,0 +1,45 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2019 Andes Technology Corporation */
+
+#ifndef __ASM_KASAN_H
+#define __ASM_KASAN_H
+
+#ifndef __ASSEMBLY__
+
+#ifdef CONFIG_KASAN
+
+/*
+ * The following comment was copied from arm64:
+ * KASAN_SHADOW_START: beginning of the kernel virtual addresses.
+ * KASAN_SHADOW_END: KASAN_SHADOW_START + 1/N of kernel virtual addresses,
+ * where N = (1 << KASAN_SHADOW_SCALE_SHIFT).
+ *
+ * KASAN_SHADOW_OFFSET:
+ * This value is used to map an address to the corresponding shadow
+ * address by the following formula:
+ *     shadow_addr = (address >> KASAN_SHADOW_SCALE_SHIFT) + KASAN_SHADOW_OFFSET
+ *
+ * (1 << (64 - KASAN_SHADOW_SCALE_SHIFT)) shadow addresses that lie in range
+ * [KASAN_SHADOW_OFFSET, KASAN_SHADOW_END) cover all 64-bits of virtual
+ * addresses. So KASAN_SHADOW_OFFSET should satisfy the following equation:
+ *      KASAN_SHADOW_OFFSET = KASAN_SHADOW_END -
+ *                              (1ULL << (64 - KASAN_SHADOW_SCALE_SHIFT))
+ */
+#define KASAN_SHADOW_SCALE_SHIFT	3
+
+#define KASAN_SHADOW_SIZE	(UL(1) << ((VA_BITS - 1) - KASAN_SHADOW_SCALE_SHIFT))
+/*
+ * Depending on the size of the virtual address space, the region may not be
+ * aligned on PGDIR_SIZE, so force its alignment to ease its population.
+ */
+#define KASAN_SHADOW_START	((KASAN_SHADOW_END - KASAN_SHADOW_SIZE) & PGDIR_MASK)
+#define KASAN_SHADOW_END	MODULES_LOWEST_VADDR
+#define KASAN_SHADOW_OFFSET	_AC(CONFIG_KASAN_SHADOW_OFFSET, UL)
+
+void kasan_init(void);
+asmlinkage void kasan_early_init(void);
+void kasan_swapper_init(void);
+
+#endif
+#endif
+#endif /* __ASM_KASAN_H */
diff --git a/arch/riscv/include/asm/kdebug.h b/arch/riscv/include/asm/kdebug.h
new file mode 100644
index 000000000..85ac00411
--- /dev/null
+++ b/arch/riscv/include/asm/kdebug.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef _ASM_ARC_KDEBUG_H
+#define _ASM_ARC_KDEBUG_H
+
+enum die_val {
+	DIE_UNUSED,
+	DIE_TRAP,
+	DIE_OOPS
+};
+
+#endif
diff --git a/arch/riscv/include/asm/kexec.h b/arch/riscv/include/asm/kexec.h
new file mode 100644
index 000000000..2b56769cb
--- /dev/null
+++ b/arch/riscv/include/asm/kexec.h
@@ -0,0 +1,72 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2019 FORTH-ICS/CARV
+ *  Nick Kossifidis <mick@ics.forth.gr>
+ */
+
+#ifndef _RISCV_KEXEC_H
+#define _RISCV_KEXEC_H
+
+#include <asm/page.h>    /* For PAGE_SIZE */
+
+/* Maximum physical address we can use pages from */
+#define KEXEC_SOURCE_MEMORY_LIMIT (-1UL)
+
+/* Maximum address we can reach in physical address mode */
+#define KEXEC_DESTINATION_MEMORY_LIMIT (-1UL)
+
+/* Maximum address we can use for the control code buffer */
+#define KEXEC_CONTROL_MEMORY_LIMIT (-1UL)
+
+/* Reserve a page for the control code buffer */
+#define KEXEC_CONTROL_PAGE_SIZE PAGE_SIZE
+
+#define KEXEC_ARCH KEXEC_ARCH_RISCV
+
+extern void riscv_crash_save_regs(struct pt_regs *newregs);
+
+static inline void
+crash_setup_regs(struct pt_regs *newregs,
+		 struct pt_regs *oldregs)
+{
+	if (oldregs)
+		memcpy(newregs, oldregs, sizeof(struct pt_regs));
+	else
+		riscv_crash_save_regs(newregs);
+}
+
+
+#define ARCH_HAS_KIMAGE_ARCH
+
+struct kimage_arch {
+	void *fdt; /* For CONFIG_KEXEC_FILE */
+	unsigned long fdt_addr;
+};
+
+extern const unsigned char riscv_kexec_relocate[];
+extern const unsigned int riscv_kexec_relocate_size;
+
+typedef void (*riscv_kexec_method)(unsigned long first_ind_entry,
+				   unsigned long jump_addr,
+				   unsigned long fdt_addr,
+				   unsigned long hartid,
+				   unsigned long va_pa_off);
+
+extern riscv_kexec_method riscv_kexec_norelocate;
+
+#ifdef CONFIG_KEXEC_FILE
+extern const struct kexec_file_ops elf_kexec_ops;
+
+struct purgatory_info;
+int arch_kexec_apply_relocations_add(struct purgatory_info *pi,
+				     Elf_Shdr *section,
+				     const Elf_Shdr *relsec,
+				     const Elf_Shdr *symtab);
+#define arch_kexec_apply_relocations_add arch_kexec_apply_relocations_add
+
+struct kimage;
+int arch_kimage_file_post_load_cleanup(struct kimage *image);
+#define arch_kimage_file_post_load_cleanup arch_kimage_file_post_load_cleanup
+#endif
+
+#endif
diff --git a/arch/riscv/include/asm/kfence.h b/arch/riscv/include/asm/kfence.h
new file mode 100644
index 000000000..d887a5404
--- /dev/null
+++ b/arch/riscv/include/asm/kfence.h
@@ -0,0 +1,63 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _ASM_RISCV_KFENCE_H
+#define _ASM_RISCV_KFENCE_H
+
+#include <linux/kfence.h>
+#include <linux/pfn.h>
+#include <asm-generic/pgalloc.h>
+#include <asm/pgtable.h>
+
+static inline int split_pmd_page(unsigned long addr)
+{
+	int i;
+	unsigned long pfn = PFN_DOWN(__pa((addr & PMD_MASK)));
+	pmd_t *pmd = pmd_off_k(addr);
+	pte_t *pte = pte_alloc_one_kernel(&init_mm);
+
+	if (!pte)
+		return -ENOMEM;
+
+	for (i = 0; i < PTRS_PER_PTE; i++)
+		set_pte(pte + i, pfn_pte(pfn + i, PAGE_KERNEL));
+	set_pmd(pmd, pfn_pmd(PFN_DOWN(__pa(pte)), PAGE_TABLE));
+
+	flush_tlb_kernel_range(addr, addr + PMD_SIZE);
+	return 0;
+}
+
+static inline bool arch_kfence_init_pool(void)
+{
+	int ret;
+	unsigned long addr;
+	pmd_t *pmd;
+
+	for (addr = (unsigned long)__kfence_pool; is_kfence_address((void *)addr);
+	     addr += PAGE_SIZE) {
+		pmd = pmd_off_k(addr);
+
+		if (pmd_leaf(*pmd)) {
+			ret = split_pmd_page(addr);
+			if (ret)
+				return false;
+		}
+	}
+
+	return true;
+}
+
+static inline bool kfence_protect_page(unsigned long addr, bool protect)
+{
+	pte_t *pte = virt_to_kpte(addr);
+
+	if (protect)
+		set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_PRESENT));
+	else
+		set_pte(pte, __pte(pte_val(*pte) | _PAGE_PRESENT));
+
+	flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+
+	return true;
+}
+
+#endif /* _ASM_RISCV_KFENCE_H */
diff --git a/arch/riscv/include/asm/kgdb.h b/arch/riscv/include/asm/kgdb.h
new file mode 100644
index 000000000..46677daf7
--- /dev/null
+++ b/arch/riscv/include/asm/kgdb.h
@@ -0,0 +1,113 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __ASM_KGDB_H_
+#define __ASM_KGDB_H_
+
+#ifdef __KERNEL__
+
+#define GDB_SIZEOF_REG sizeof(unsigned long)
+
+#define DBG_MAX_REG_NUM (36)
+#define NUMREGBYTES ((DBG_MAX_REG_NUM) * GDB_SIZEOF_REG)
+#define CACHE_FLUSH_IS_SAFE     1
+#define BUFMAX                  2048
+#ifdef CONFIG_RISCV_ISA_C
+#define BREAK_INSTR_SIZE	2
+#else
+#define BREAK_INSTR_SIZE	4
+#endif
+
+#ifndef	__ASSEMBLY__
+
+extern unsigned long kgdb_compiled_break;
+
+static inline void arch_kgdb_breakpoint(void)
+{
+	asm(".global kgdb_compiled_break\n"
+	    ".option norvc\n"
+	    "kgdb_compiled_break: ebreak\n"
+	    ".option rvc\n");
+}
+
+#endif /* !__ASSEMBLY__ */
+
+#define DBG_REG_ZERO "zero"
+#define DBG_REG_RA "ra"
+#define DBG_REG_SP "sp"
+#define DBG_REG_GP "gp"
+#define DBG_REG_TP "tp"
+#define DBG_REG_T0 "t0"
+#define DBG_REG_T1 "t1"
+#define DBG_REG_T2 "t2"
+#define DBG_REG_FP "fp"
+#define DBG_REG_S1 "s1"
+#define DBG_REG_A0 "a0"
+#define DBG_REG_A1 "a1"
+#define DBG_REG_A2 "a2"
+#define DBG_REG_A3 "a3"
+#define DBG_REG_A4 "a4"
+#define DBG_REG_A5 "a5"
+#define DBG_REG_A6 "a6"
+#define DBG_REG_A7 "a7"
+#define DBG_REG_S2 "s2"
+#define DBG_REG_S3 "s3"
+#define DBG_REG_S4 "s4"
+#define DBG_REG_S5 "s5"
+#define DBG_REG_S6 "s6"
+#define DBG_REG_S7 "s7"
+#define DBG_REG_S8 "s8"
+#define DBG_REG_S9 "s9"
+#define DBG_REG_S10 "s10"
+#define DBG_REG_S11 "s11"
+#define DBG_REG_T3 "t3"
+#define DBG_REG_T4 "t4"
+#define DBG_REG_T5 "t5"
+#define DBG_REG_T6 "t6"
+#define DBG_REG_EPC "pc"
+#define DBG_REG_STATUS "sstatus"
+#define DBG_REG_BADADDR "stval"
+#define DBG_REG_CAUSE "scause"
+
+#define DBG_REG_ZERO_OFF 0
+#define DBG_REG_RA_OFF 1
+#define DBG_REG_SP_OFF 2
+#define DBG_REG_GP_OFF 3
+#define DBG_REG_TP_OFF 4
+#define DBG_REG_T0_OFF 5
+#define DBG_REG_T1_OFF 6
+#define DBG_REG_T2_OFF 7
+#define DBG_REG_FP_OFF 8
+#define DBG_REG_S1_OFF 9
+#define DBG_REG_A0_OFF 10
+#define DBG_REG_A1_OFF 11
+#define DBG_REG_A2_OFF 12
+#define DBG_REG_A3_OFF 13
+#define DBG_REG_A4_OFF 14
+#define DBG_REG_A5_OFF 15
+#define DBG_REG_A6_OFF 16
+#define DBG_REG_A7_OFF 17
+#define DBG_REG_S2_OFF 18
+#define DBG_REG_S3_OFF 19
+#define DBG_REG_S4_OFF 20
+#define DBG_REG_S5_OFF 21
+#define DBG_REG_S6_OFF 22
+#define DBG_REG_S7_OFF 23
+#define DBG_REG_S8_OFF 24
+#define DBG_REG_S9_OFF 25
+#define DBG_REG_S10_OFF 26
+#define DBG_REG_S11_OFF 27
+#define DBG_REG_T3_OFF 28
+#define DBG_REG_T4_OFF 29
+#define DBG_REG_T5_OFF 30
+#define DBG_REG_T6_OFF 31
+#define DBG_REG_EPC_OFF 32
+#define DBG_REG_STATUS_OFF 33
+#define DBG_REG_BADADDR_OFF 34
+#define DBG_REG_CAUSE_OFF 35
+
+extern const char riscv_gdb_stub_feature[64];
+
+#define kgdb_arch_gdb_stub_feature riscv_gdb_stub_feature
+
+#endif
+#endif
diff --git a/arch/riscv/include/asm/kprobes.h b/arch/riscv/include/asm/kprobes.h
new file mode 100644
index 000000000..217ef89f2
--- /dev/null
+++ b/arch/riscv/include/asm/kprobes.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copied from arch/arm64/include/asm/kprobes.h
+ *
+ * Copyright (C) 2013 Linaro Limited
+ * Copyright (C) 2017 SiFive
+ */
+
+#ifndef _ASM_RISCV_KPROBES_H
+#define _ASM_RISCV_KPROBES_H
+
+#include <asm-generic/kprobes.h>
+
+#ifdef CONFIG_KPROBES
+#include <linux/types.h>
+#include <linux/ptrace.h>
+#include <linux/percpu.h>
+
+#define __ARCH_WANT_KPROBES_INSN_SLOT
+#define MAX_INSN_SIZE			2
+
+#define flush_insn_slot(p)		do { } while (0)
+#define kretprobe_blacklist_size	0
+
+#include <asm/probes.h>
+
+struct prev_kprobe {
+	struct kprobe *kp;
+	unsigned int status;
+};
+
+/* per-cpu kprobe control block */
+struct kprobe_ctlblk {
+	unsigned int kprobe_status;
+	unsigned long saved_status;
+	struct prev_kprobe prev_kprobe;
+};
+
+void arch_remove_kprobe(struct kprobe *p);
+int kprobe_fault_handler(struct pt_regs *regs, unsigned int trapnr);
+bool kprobe_breakpoint_handler(struct pt_regs *regs);
+bool kprobe_single_step_handler(struct pt_regs *regs);
+void __kretprobe_trampoline(void);
+void __kprobes *trampoline_probe_handler(struct pt_regs *regs);
+
+#endif /* CONFIG_KPROBES */
+#endif /* _ASM_RISCV_KPROBES_H */
diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h
new file mode 100644
index 000000000..dbbf43d52
--- /dev/null
+++ b/arch/riscv/include/asm/kvm_host.h
@@ -0,0 +1,333 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2019 Western Digital Corporation or its affiliates.
+ *
+ * Authors:
+ *     Anup Patel <anup.patel@wdc.com>
+ */
+
+#ifndef __RISCV_KVM_HOST_H__
+#define __RISCV_KVM_HOST_H__
+
+#include <linux/types.h>
+#include <linux/kvm.h>
+#include <linux/kvm_types.h>
+#include <linux/spinlock.h>
+#include <asm/csr.h>
+#include <asm/hwcap.h>
+#include <asm/kvm_vcpu_fp.h>
+#include <asm/kvm_vcpu_insn.h>
+#include <asm/kvm_vcpu_timer.h>
+
+#define KVM_MAX_VCPUS			1024
+
+#define KVM_HALT_POLL_NS_DEFAULT	500000
+
+#define KVM_VCPU_MAX_FEATURES		0
+
+#define KVM_REQ_SLEEP \
+	KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
+#define KVM_REQ_VCPU_RESET		KVM_ARCH_REQ(1)
+#define KVM_REQ_UPDATE_HGATP		KVM_ARCH_REQ(2)
+#define KVM_REQ_FENCE_I			\
+	KVM_ARCH_REQ_FLAGS(3, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
+#define KVM_REQ_HFENCE_GVMA_VMID_ALL	KVM_REQ_TLB_FLUSH
+#define KVM_REQ_HFENCE_VVMA_ALL		\
+	KVM_ARCH_REQ_FLAGS(4, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
+#define KVM_REQ_HFENCE			\
+	KVM_ARCH_REQ_FLAGS(5, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
+
+enum kvm_riscv_hfence_type {
+	KVM_RISCV_HFENCE_UNKNOWN = 0,
+	KVM_RISCV_HFENCE_GVMA_VMID_GPA,
+	KVM_RISCV_HFENCE_VVMA_ASID_GVA,
+	KVM_RISCV_HFENCE_VVMA_ASID_ALL,
+	KVM_RISCV_HFENCE_VVMA_GVA,
+};
+
+struct kvm_riscv_hfence {
+	enum kvm_riscv_hfence_type type;
+	unsigned long asid;
+	unsigned long order;
+	gpa_t addr;
+	gpa_t size;
+};
+
+#define KVM_RISCV_VCPU_MAX_HFENCE	64
+
+struct kvm_vm_stat {
+	struct kvm_vm_stat_generic generic;
+};
+
+struct kvm_vcpu_stat {
+	struct kvm_vcpu_stat_generic generic;
+	u64 ecall_exit_stat;
+	u64 wfi_exit_stat;
+	u64 mmio_exit_user;
+	u64 mmio_exit_kernel;
+	u64 csr_exit_user;
+	u64 csr_exit_kernel;
+	u64 signal_exits;
+	u64 exits;
+};
+
+struct kvm_arch_memory_slot {
+};
+
+struct kvm_vmid {
+	/*
+	 * Writes to vmid_version and vmid happen with vmid_lock held
+	 * whereas reads happen without any lock held.
+	 */
+	unsigned long vmid_version;
+	unsigned long vmid;
+};
+
+struct kvm_arch {
+	/* G-stage vmid */
+	struct kvm_vmid vmid;
+
+	/* G-stage page table */
+	pgd_t *pgd;
+	phys_addr_t pgd_phys;
+
+	/* Guest Timer */
+	struct kvm_guest_timer timer;
+};
+
+struct kvm_sbi_context {
+	int return_handled;
+};
+
+struct kvm_cpu_trap {
+	unsigned long sepc;
+	unsigned long scause;
+	unsigned long stval;
+	unsigned long htval;
+	unsigned long htinst;
+};
+
+struct kvm_cpu_context {
+	unsigned long zero;
+	unsigned long ra;
+	unsigned long sp;
+	unsigned long gp;
+	unsigned long tp;
+	unsigned long t0;
+	unsigned long t1;
+	unsigned long t2;
+	unsigned long s0;
+	unsigned long s1;
+	unsigned long a0;
+	unsigned long a1;
+	unsigned long a2;
+	unsigned long a3;
+	unsigned long a4;
+	unsigned long a5;
+	unsigned long a6;
+	unsigned long a7;
+	unsigned long s2;
+	unsigned long s3;
+	unsigned long s4;
+	unsigned long s5;
+	unsigned long s6;
+	unsigned long s7;
+	unsigned long s8;
+	unsigned long s9;
+	unsigned long s10;
+	unsigned long s11;
+	unsigned long t3;
+	unsigned long t4;
+	unsigned long t5;
+	unsigned long t6;
+	unsigned long sepc;
+	unsigned long sstatus;
+	unsigned long hstatus;
+	union __riscv_fp_state fp;
+};
+
+struct kvm_vcpu_csr {
+	unsigned long vsstatus;
+	unsigned long vsie;
+	unsigned long vstvec;
+	unsigned long vsscratch;
+	unsigned long vsepc;
+	unsigned long vscause;
+	unsigned long vstval;
+	unsigned long hvip;
+	unsigned long vsatp;
+	unsigned long scounteren;
+};
+
+struct kvm_vcpu_arch {
+	/* VCPU ran at least once */
+	bool ran_atleast_once;
+
+	/* Last Host CPU on which Guest VCPU exited */
+	int last_exit_cpu;
+
+	/* ISA feature bits (similar to MISA) */
+	DECLARE_BITMAP(isa, RISCV_ISA_EXT_MAX);
+
+	/* SSCRATCH, STVEC, and SCOUNTEREN of Host */
+	unsigned long host_sscratch;
+	unsigned long host_stvec;
+	unsigned long host_scounteren;
+
+	/* CPU context of Host */
+	struct kvm_cpu_context host_context;
+
+	/* CPU context of Guest VCPU */
+	struct kvm_cpu_context guest_context;
+
+	/* CPU CSR context of Guest VCPU */
+	struct kvm_vcpu_csr guest_csr;
+
+	/* CPU context upon Guest VCPU reset */
+	struct kvm_cpu_context guest_reset_context;
+
+	/* CPU CSR context upon Guest VCPU reset */
+	struct kvm_vcpu_csr guest_reset_csr;
+
+	/*
+	 * VCPU interrupts
+	 *
+	 * We have a lockless approach for tracking pending VCPU interrupts
+	 * implemented using atomic bitops. The irqs_pending bitmap represent
+	 * pending interrupts whereas irqs_pending_mask represent bits changed
+	 * in irqs_pending. Our approach is modeled around multiple producer
+	 * and single consumer problem where the consumer is the VCPU itself.
+	 */
+	unsigned long irqs_pending;
+	unsigned long irqs_pending_mask;
+
+	/* VCPU Timer */
+	struct kvm_vcpu_timer timer;
+
+	/* HFENCE request queue */
+	spinlock_t hfence_lock;
+	unsigned long hfence_head;
+	unsigned long hfence_tail;
+	struct kvm_riscv_hfence hfence_queue[KVM_RISCV_VCPU_MAX_HFENCE];
+
+	/* MMIO instruction details */
+	struct kvm_mmio_decode mmio_decode;
+
+	/* CSR instruction details */
+	struct kvm_csr_decode csr_decode;
+
+	/* SBI context */
+	struct kvm_sbi_context sbi_context;
+
+	/* Cache pages needed to program page tables with spinlock held */
+	struct kvm_mmu_memory_cache mmu_page_cache;
+
+	/* VCPU power-off state */
+	bool power_off;
+
+	/* Don't run the VCPU (blocked) */
+	bool pause;
+};
+
+static inline void kvm_arch_hardware_unsetup(void) {}
+static inline void kvm_arch_sync_events(struct kvm *kvm) {}
+static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
+
+#define KVM_ARCH_WANT_MMU_NOTIFIER
+
+#define KVM_RISCV_GSTAGE_TLB_MIN_ORDER		12
+
+void kvm_riscv_local_hfence_gvma_vmid_gpa(unsigned long vmid,
+					  gpa_t gpa, gpa_t gpsz,
+					  unsigned long order);
+void kvm_riscv_local_hfence_gvma_vmid_all(unsigned long vmid);
+void kvm_riscv_local_hfence_gvma_gpa(gpa_t gpa, gpa_t gpsz,
+				     unsigned long order);
+void kvm_riscv_local_hfence_gvma_all(void);
+void kvm_riscv_local_hfence_vvma_asid_gva(unsigned long vmid,
+					  unsigned long asid,
+					  unsigned long gva,
+					  unsigned long gvsz,
+					  unsigned long order);
+void kvm_riscv_local_hfence_vvma_asid_all(unsigned long vmid,
+					  unsigned long asid);
+void kvm_riscv_local_hfence_vvma_gva(unsigned long vmid,
+				     unsigned long gva, unsigned long gvsz,
+				     unsigned long order);
+void kvm_riscv_local_hfence_vvma_all(unsigned long vmid);
+
+void kvm_riscv_local_tlb_sanitize(struct kvm_vcpu *vcpu);
+
+void kvm_riscv_fence_i_process(struct kvm_vcpu *vcpu);
+void kvm_riscv_hfence_gvma_vmid_all_process(struct kvm_vcpu *vcpu);
+void kvm_riscv_hfence_vvma_all_process(struct kvm_vcpu *vcpu);
+void kvm_riscv_hfence_process(struct kvm_vcpu *vcpu);
+
+void kvm_riscv_fence_i(struct kvm *kvm,
+		       unsigned long hbase, unsigned long hmask);
+void kvm_riscv_hfence_gvma_vmid_gpa(struct kvm *kvm,
+				    unsigned long hbase, unsigned long hmask,
+				    gpa_t gpa, gpa_t gpsz,
+				    unsigned long order);
+void kvm_riscv_hfence_gvma_vmid_all(struct kvm *kvm,
+				    unsigned long hbase, unsigned long hmask);
+void kvm_riscv_hfence_vvma_asid_gva(struct kvm *kvm,
+				    unsigned long hbase, unsigned long hmask,
+				    unsigned long gva, unsigned long gvsz,
+				    unsigned long order, unsigned long asid);
+void kvm_riscv_hfence_vvma_asid_all(struct kvm *kvm,
+				    unsigned long hbase, unsigned long hmask,
+				    unsigned long asid);
+void kvm_riscv_hfence_vvma_gva(struct kvm *kvm,
+			       unsigned long hbase, unsigned long hmask,
+			       unsigned long gva, unsigned long gvsz,
+			       unsigned long order);
+void kvm_riscv_hfence_vvma_all(struct kvm *kvm,
+			       unsigned long hbase, unsigned long hmask);
+
+int kvm_riscv_gstage_ioremap(struct kvm *kvm, gpa_t gpa,
+			     phys_addr_t hpa, unsigned long size,
+			     bool writable, bool in_atomic);
+void kvm_riscv_gstage_iounmap(struct kvm *kvm, gpa_t gpa,
+			      unsigned long size);
+int kvm_riscv_gstage_map(struct kvm_vcpu *vcpu,
+			 struct kvm_memory_slot *memslot,
+			 gpa_t gpa, unsigned long hva, bool is_write);
+int kvm_riscv_gstage_alloc_pgd(struct kvm *kvm);
+void kvm_riscv_gstage_free_pgd(struct kvm *kvm);
+void kvm_riscv_gstage_update_hgatp(struct kvm_vcpu *vcpu);
+void kvm_riscv_gstage_mode_detect(void);
+unsigned long kvm_riscv_gstage_mode(void);
+int kvm_riscv_gstage_gpa_bits(void);
+
+void kvm_riscv_gstage_vmid_detect(void);
+unsigned long kvm_riscv_gstage_vmid_bits(void);
+int kvm_riscv_gstage_vmid_init(struct kvm *kvm);
+bool kvm_riscv_gstage_vmid_ver_changed(struct kvm_vmid *vmid);
+void kvm_riscv_gstage_vmid_update(struct kvm_vcpu *vcpu);
+
+void __kvm_riscv_unpriv_trap(void);
+
+unsigned long kvm_riscv_vcpu_unpriv_read(struct kvm_vcpu *vcpu,
+					 bool read_insn,
+					 unsigned long guest_addr,
+					 struct kvm_cpu_trap *trap);
+void kvm_riscv_vcpu_trap_redirect(struct kvm_vcpu *vcpu,
+				  struct kvm_cpu_trap *trap);
+int kvm_riscv_vcpu_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
+			struct kvm_cpu_trap *trap);
+
+void __kvm_riscv_switch_to(struct kvm_vcpu_arch *vcpu_arch);
+
+int kvm_riscv_vcpu_set_interrupt(struct kvm_vcpu *vcpu, unsigned int irq);
+int kvm_riscv_vcpu_unset_interrupt(struct kvm_vcpu *vcpu, unsigned int irq);
+void kvm_riscv_vcpu_flush_interrupts(struct kvm_vcpu *vcpu);
+void kvm_riscv_vcpu_sync_interrupts(struct kvm_vcpu *vcpu);
+bool kvm_riscv_vcpu_has_interrupts(struct kvm_vcpu *vcpu, unsigned long mask);
+void kvm_riscv_vcpu_power_off(struct kvm_vcpu *vcpu);
+void kvm_riscv_vcpu_power_on(struct kvm_vcpu *vcpu);
+
+int kvm_riscv_vcpu_sbi_return(struct kvm_vcpu *vcpu, struct kvm_run *run);
+int kvm_riscv_vcpu_sbi_ecall(struct kvm_vcpu *vcpu, struct kvm_run *run);
+
+#endif /* __RISCV_KVM_HOST_H__ */
diff --git a/arch/riscv/include/asm/kvm_types.h b/arch/riscv/include/asm/kvm_types.h
new file mode 100644
index 000000000..e15765f98
--- /dev/null
+++ b/arch/riscv/include/asm/kvm_types.h
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_RISCV_KVM_TYPES_H
+#define _ASM_RISCV_KVM_TYPES_H
+
+#define KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE 32
+
+#endif /* _ASM_RISCV_KVM_TYPES_H */
diff --git a/arch/riscv/include/asm/kvm_vcpu_fp.h b/arch/riscv/include/asm/kvm_vcpu_fp.h
new file mode 100644
index 000000000..b55401474
--- /dev/null
+++ b/arch/riscv/include/asm/kvm_vcpu_fp.h
@@ -0,0 +1,59 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2021 Western Digital Corporation or its affiliates.
+ *
+ * Authors:
+ *     Atish Patra <atish.patra@wdc.com>
+ *     Anup Patel <anup.patel@wdc.com>
+ */
+
+#ifndef __KVM_VCPU_RISCV_FP_H
+#define __KVM_VCPU_RISCV_FP_H
+
+#include <linux/types.h>
+
+struct kvm_cpu_context;
+
+#ifdef CONFIG_FPU
+void __kvm_riscv_fp_f_save(struct kvm_cpu_context *context);
+void __kvm_riscv_fp_f_restore(struct kvm_cpu_context *context);
+void __kvm_riscv_fp_d_save(struct kvm_cpu_context *context);
+void __kvm_riscv_fp_d_restore(struct kvm_cpu_context *context);
+
+void kvm_riscv_vcpu_fp_reset(struct kvm_vcpu *vcpu);
+void kvm_riscv_vcpu_guest_fp_save(struct kvm_cpu_context *cntx,
+				  const unsigned long *isa);
+void kvm_riscv_vcpu_guest_fp_restore(struct kvm_cpu_context *cntx,
+				     const unsigned long *isa);
+void kvm_riscv_vcpu_host_fp_save(struct kvm_cpu_context *cntx);
+void kvm_riscv_vcpu_host_fp_restore(struct kvm_cpu_context *cntx);
+#else
+static inline void kvm_riscv_vcpu_fp_reset(struct kvm_vcpu *vcpu)
+{
+}
+static inline void kvm_riscv_vcpu_guest_fp_save(struct kvm_cpu_context *cntx,
+						const unsigned long *isa)
+{
+}
+static inline void kvm_riscv_vcpu_guest_fp_restore(
+					struct kvm_cpu_context *cntx,
+					const unsigned long *isa)
+{
+}
+static inline void kvm_riscv_vcpu_host_fp_save(struct kvm_cpu_context *cntx)
+{
+}
+static inline void kvm_riscv_vcpu_host_fp_restore(
+					struct kvm_cpu_context *cntx)
+{
+}
+#endif
+
+int kvm_riscv_vcpu_get_reg_fp(struct kvm_vcpu *vcpu,
+			      const struct kvm_one_reg *reg,
+			      unsigned long rtype);
+int kvm_riscv_vcpu_set_reg_fp(struct kvm_vcpu *vcpu,
+			      const struct kvm_one_reg *reg,
+			      unsigned long rtype);
+
+#endif
diff --git a/arch/riscv/include/asm/kvm_vcpu_insn.h b/arch/riscv/include/asm/kvm_vcpu_insn.h
new file mode 100644
index 000000000..350011c83
--- /dev/null
+++ b/arch/riscv/include/asm/kvm_vcpu_insn.h
@@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2022 Ventana Micro Systems Inc.
+ */
+
+#ifndef __KVM_VCPU_RISCV_INSN_H
+#define __KVM_VCPU_RISCV_INSN_H
+
+struct kvm_vcpu;
+struct kvm_run;
+struct kvm_cpu_trap;
+
+struct kvm_mmio_decode {
+	unsigned long insn;
+	int insn_len;
+	int len;
+	int shift;
+	int return_handled;
+};
+
+struct kvm_csr_decode {
+	unsigned long insn;
+	int return_handled;
+};
+
+/* Return values used by function emulating a particular instruction */
+enum kvm_insn_return {
+	KVM_INSN_EXIT_TO_USER_SPACE = 0,
+	KVM_INSN_CONTINUE_NEXT_SEPC,
+	KVM_INSN_CONTINUE_SAME_SEPC,
+	KVM_INSN_ILLEGAL_TRAP,
+	KVM_INSN_VIRTUAL_TRAP
+};
+
+void kvm_riscv_vcpu_wfi(struct kvm_vcpu *vcpu);
+int kvm_riscv_vcpu_csr_return(struct kvm_vcpu *vcpu, struct kvm_run *run);
+int kvm_riscv_vcpu_virtual_insn(struct kvm_vcpu *vcpu, struct kvm_run *run,
+				struct kvm_cpu_trap *trap);
+
+int kvm_riscv_vcpu_mmio_load(struct kvm_vcpu *vcpu, struct kvm_run *run,
+			     unsigned long fault_addr,
+			     unsigned long htinst);
+int kvm_riscv_vcpu_mmio_store(struct kvm_vcpu *vcpu, struct kvm_run *run,
+			      unsigned long fault_addr,
+			      unsigned long htinst);
+int kvm_riscv_vcpu_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run);
+
+#endif
diff --git a/arch/riscv/include/asm/kvm_vcpu_sbi.h b/arch/riscv/include/asm/kvm_vcpu_sbi.h
new file mode 100644
index 000000000..d4e3e600b
--- /dev/null
+++ b/arch/riscv/include/asm/kvm_vcpu_sbi.h
@@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/**
+ * Copyright (c) 2021 Western Digital Corporation or its affiliates.
+ *
+ * Authors:
+ *     Atish Patra <atish.patra@wdc.com>
+ */
+
+#ifndef __RISCV_KVM_VCPU_SBI_H__
+#define __RISCV_KVM_VCPU_SBI_H__
+
+#define KVM_SBI_IMPID 3
+
+#define KVM_SBI_VERSION_MAJOR 1
+#define KVM_SBI_VERSION_MINOR 0
+
+struct kvm_vcpu_sbi_extension {
+	unsigned long extid_start;
+	unsigned long extid_end;
+	/**
+	 * SBI extension handler. It can be defined for a given extension or group of
+	 * extension. But it should always return linux error codes rather than SBI
+	 * specific error codes.
+	 */
+	int (*handler)(struct kvm_vcpu *vcpu, struct kvm_run *run,
+		       unsigned long *out_val, struct kvm_cpu_trap *utrap,
+		       bool *exit);
+};
+
+void kvm_riscv_vcpu_sbi_forward(struct kvm_vcpu *vcpu, struct kvm_run *run);
+void kvm_riscv_vcpu_sbi_system_reset(struct kvm_vcpu *vcpu,
+				     struct kvm_run *run,
+				     u32 type, u64 flags);
+const struct kvm_vcpu_sbi_extension *kvm_vcpu_sbi_find_ext(unsigned long extid);
+
+#ifdef CONFIG_RISCV_SBI_V01
+extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_v01;
+#endif
+extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_base;
+extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_time;
+extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_ipi;
+extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_rfence;
+extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_srst;
+extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_hsm;
+extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_experimental;
+extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_vendor;
+
+#endif /* __RISCV_KVM_VCPU_SBI_H__ */
diff --git a/arch/riscv/include/asm/kvm_vcpu_timer.h b/arch/riscv/include/asm/kvm_vcpu_timer.h
new file mode 100644
index 000000000..82f726030
--- /dev/null
+++ b/arch/riscv/include/asm/kvm_vcpu_timer.h
@@ -0,0 +1,52 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2019 Western Digital Corporation or its affiliates.
+ *
+ * Authors:
+ *	Atish Patra <atish.patra@wdc.com>
+ */
+
+#ifndef __KVM_VCPU_RISCV_TIMER_H
+#define __KVM_VCPU_RISCV_TIMER_H
+
+#include <linux/hrtimer.h>
+
+struct kvm_guest_timer {
+	/* Mult & Shift values to get nanoseconds from cycles */
+	u32 nsec_mult;
+	u32 nsec_shift;
+	/* Time delta value */
+	u64 time_delta;
+};
+
+struct kvm_vcpu_timer {
+	/* Flag for whether init is done */
+	bool init_done;
+	/* Flag for whether timer event is configured */
+	bool next_set;
+	/* Next timer event cycles */
+	u64 next_cycles;
+	/* Underlying hrtimer instance */
+	struct hrtimer hrt;
+
+	/* Flag to check if sstc is enabled or not */
+	bool sstc_enabled;
+	/* A function pointer to switch between stimecmp or hrtimer at runtime */
+	int (*timer_next_event)(struct kvm_vcpu *vcpu, u64 ncycles);
+};
+
+int kvm_riscv_vcpu_timer_next_event(struct kvm_vcpu *vcpu, u64 ncycles);
+int kvm_riscv_vcpu_get_reg_timer(struct kvm_vcpu *vcpu,
+				 const struct kvm_one_reg *reg);
+int kvm_riscv_vcpu_set_reg_timer(struct kvm_vcpu *vcpu,
+				 const struct kvm_one_reg *reg);
+int kvm_riscv_vcpu_timer_init(struct kvm_vcpu *vcpu);
+int kvm_riscv_vcpu_timer_deinit(struct kvm_vcpu *vcpu);
+int kvm_riscv_vcpu_timer_reset(struct kvm_vcpu *vcpu);
+void kvm_riscv_vcpu_timer_restore(struct kvm_vcpu *vcpu);
+void kvm_riscv_guest_timer_init(struct kvm *kvm);
+void kvm_riscv_vcpu_timer_sync(struct kvm_vcpu *vcpu);
+void kvm_riscv_vcpu_timer_save(struct kvm_vcpu *vcpu);
+bool kvm_riscv_vcpu_timer_pending(struct kvm_vcpu *vcpu);
+
+#endif
diff --git a/arch/riscv/include/asm/linkage.h b/arch/riscv/include/asm/linkage.h
new file mode 100644
index 000000000..9e88ba23c
--- /dev/null
+++ b/arch/riscv/include/asm/linkage.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2015 Regents of the University of California
+ */
+
+#ifndef _ASM_RISCV_LINKAGE_H
+#define _ASM_RISCV_LINKAGE_H
+
+#define __ALIGN		.balign 4
+#define __ALIGN_STR	".balign 4"
+
+#endif /* _ASM_RISCV_LINKAGE_H */
diff --git a/arch/riscv/include/asm/mmio.h b/arch/riscv/include/asm/mmio.h
new file mode 100644
index 000000000..4c58ee7f9
--- /dev/null
+++ b/arch/riscv/include/asm/mmio.h
@@ -0,0 +1,151 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * {read,write}{b,w,l,q} based on arch/arm64/include/asm/io.h
+ *   which was based on arch/arm/include/io.h
+ *
+ * Copyright (C) 1996-2000 Russell King
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2014 Regents of the University of California
+ */
+
+#ifndef _ASM_RISCV_MMIO_H
+#define _ASM_RISCV_MMIO_H
+
+#include <linux/types.h>
+#include <asm/mmiowb.h>
+
+/* Generic IO read/write.  These perform native-endian accesses. */
+#define __raw_writeb __raw_writeb
+static inline void __raw_writeb(u8 val, volatile void __iomem *addr)
+{
+	asm volatile("sb %0, 0(%1)" : : "r" (val), "r" (addr));
+}
+
+#define __raw_writew __raw_writew
+static inline void __raw_writew(u16 val, volatile void __iomem *addr)
+{
+	asm volatile("sh %0, 0(%1)" : : "r" (val), "r" (addr));
+}
+
+#define __raw_writel __raw_writel
+static inline void __raw_writel(u32 val, volatile void __iomem *addr)
+{
+	asm volatile("sw %0, 0(%1)" : : "r" (val), "r" (addr));
+}
+
+#ifdef CONFIG_64BIT
+#define __raw_writeq __raw_writeq
+static inline void __raw_writeq(u64 val, volatile void __iomem *addr)
+{
+	asm volatile("sd %0, 0(%1)" : : "r" (val), "r" (addr));
+}
+#endif
+
+#define __raw_readb __raw_readb
+static inline u8 __raw_readb(const volatile void __iomem *addr)
+{
+	u8 val;
+
+	asm volatile("lb %0, 0(%1)" : "=r" (val) : "r" (addr));
+	return val;
+}
+
+#define __raw_readw __raw_readw
+static inline u16 __raw_readw(const volatile void __iomem *addr)
+{
+	u16 val;
+
+	asm volatile("lh %0, 0(%1)" : "=r" (val) : "r" (addr));
+	return val;
+}
+
+#define __raw_readl __raw_readl
+static inline u32 __raw_readl(const volatile void __iomem *addr)
+{
+	u32 val;
+
+	asm volatile("lw %0, 0(%1)" : "=r" (val) : "r" (addr));
+	return val;
+}
+
+#ifdef CONFIG_64BIT
+#define __raw_readq __raw_readq
+static inline u64 __raw_readq(const volatile void __iomem *addr)
+{
+	u64 val;
+
+	asm volatile("ld %0, 0(%1)" : "=r" (val) : "r" (addr));
+	return val;
+}
+#endif
+
+/*
+ * Unordered I/O memory access primitives.  These are even more relaxed than
+ * the relaxed versions, as they don't even order accesses between successive
+ * operations to the I/O regions.
+ */
+#define readb_cpu(c)		({ u8  __r = __raw_readb(c); __r; })
+#define readw_cpu(c)		({ u16 __r = le16_to_cpu((__force __le16)__raw_readw(c)); __r; })
+#define readl_cpu(c)		({ u32 __r = le32_to_cpu((__force __le32)__raw_readl(c)); __r; })
+
+#define writeb_cpu(v, c)	((void)__raw_writeb((v), (c)))
+#define writew_cpu(v, c)	((void)__raw_writew((__force u16)cpu_to_le16(v), (c)))
+#define writel_cpu(v, c)	((void)__raw_writel((__force u32)cpu_to_le32(v), (c)))
+
+#ifdef CONFIG_64BIT
+#define readq_cpu(c)		({ u64 __r = le64_to_cpu((__force __le64)__raw_readq(c)); __r; })
+#define writeq_cpu(v, c)	((void)__raw_writeq((__force u64)cpu_to_le64(v), (c)))
+#endif
+
+/*
+ * Relaxed I/O memory access primitives. These follow the Device memory
+ * ordering rules but do not guarantee any ordering relative to Normal memory
+ * accesses.  These are defined to order the indicated access (either a read or
+ * write) with all other I/O memory accesses to the same peripheral. Since the
+ * platform specification defines that all I/O regions are strongly ordered on
+ * channel 0, no explicit fences are required to enforce this ordering.
+ */
+/* FIXME: These are now the same as asm-generic */
+#define __io_rbr()		do {} while (0)
+#define __io_rar()		do {} while (0)
+#define __io_rbw()		do {} while (0)
+#define __io_raw()		do {} while (0)
+
+#define readb_relaxed(c)	({ u8  __v; __io_rbr(); __v = readb_cpu(c); __io_rar(); __v; })
+#define readw_relaxed(c)	({ u16 __v; __io_rbr(); __v = readw_cpu(c); __io_rar(); __v; })
+#define readl_relaxed(c)	({ u32 __v; __io_rbr(); __v = readl_cpu(c); __io_rar(); __v; })
+
+#define writeb_relaxed(v, c)	({ __io_rbw(); writeb_cpu((v), (c)); __io_raw(); })
+#define writew_relaxed(v, c)	({ __io_rbw(); writew_cpu((v), (c)); __io_raw(); })
+#define writel_relaxed(v, c)	({ __io_rbw(); writel_cpu((v), (c)); __io_raw(); })
+
+#ifdef CONFIG_64BIT
+#define readq_relaxed(c)	({ u64 __v; __io_rbr(); __v = readq_cpu(c); __io_rar(); __v; })
+#define writeq_relaxed(v, c)	({ __io_rbw(); writeq_cpu((v), (c)); __io_raw(); })
+#endif
+
+/*
+ * I/O memory access primitives.  Reads are ordered relative to any following
+ * Normal memory read and delay() loop.  Writes are ordered relative to any
+ * prior Normal memory write.  The memory barriers here are necessary as RISC-V
+ * doesn't define any ordering between the memory space and the I/O space.
+ */
+#define __io_br()	do {} while (0)
+#define __io_ar(v)	({ __asm__ __volatile__ ("fence i,ir" : : : "memory"); })
+#define __io_bw()	({ __asm__ __volatile__ ("fence w,o" : : : "memory"); })
+#define __io_aw()	mmiowb_set_pending()
+
+#define readb(c)	({ u8  __v; __io_br(); __v = readb_cpu(c); __io_ar(__v); __v; })
+#define readw(c)	({ u16 __v; __io_br(); __v = readw_cpu(c); __io_ar(__v); __v; })
+#define readl(c)	({ u32 __v; __io_br(); __v = readl_cpu(c); __io_ar(__v); __v; })
+
+#define writeb(v, c)	({ __io_bw(); writeb_cpu((v), (c)); __io_aw(); })
+#define writew(v, c)	({ __io_bw(); writew_cpu((v), (c)); __io_aw(); })
+#define writel(v, c)	({ __io_bw(); writel_cpu((v), (c)); __io_aw(); })
+
+#ifdef CONFIG_64BIT
+#define readq(c)	({ u64 __v; __io_br(); __v = readq_cpu(c); __io_ar(__v); __v; })
+#define writeq(v, c)	({ __io_bw(); writeq_cpu((v), (c)); __io_aw(); })
+#endif
+
+#endif /* _ASM_RISCV_MMIO_H */
diff --git a/arch/riscv/include/asm/mmiowb.h b/arch/riscv/include/asm/mmiowb.h
new file mode 100644
index 000000000..0b2333e71
--- /dev/null
+++ b/arch/riscv/include/asm/mmiowb.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _ASM_RISCV_MMIOWB_H
+#define _ASM_RISCV_MMIOWB_H
+
+/*
+ * "o,w" is sufficient to ensure that all writes to the device have completed
+ * before the write to the spinlock is allowed to commit.
+ */
+#define mmiowb()	__asm__ __volatile__ ("fence o,w" : : : "memory");
+
+#include <linux/smp.h>
+#include <asm-generic/mmiowb.h>
+
+#endif	/* _ASM_RISCV_MMIOWB_H */
diff --git a/arch/riscv/include/asm/mmu.h b/arch/riscv/include/asm/mmu.h
new file mode 100644
index 000000000..0099dc116
--- /dev/null
+++ b/arch/riscv/include/asm/mmu.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ */
+
+
+#ifndef _ASM_RISCV_MMU_H
+#define _ASM_RISCV_MMU_H
+
+#ifndef __ASSEMBLY__
+
+typedef struct {
+#ifndef CONFIG_MMU
+	unsigned long	end_brk;
+#else
+	atomic_long_t id;
+#endif
+	void *vdso;
+#ifdef CONFIG_SMP
+	/* A local icache flush is needed before user execution can resume. */
+	cpumask_t icache_stale_mask;
+#endif
+} mm_context_t;
+
+void __init create_pgd_mapping(pgd_t *pgdp, uintptr_t va, phys_addr_t pa,
+			       phys_addr_t sz, pgprot_t prot);
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_RISCV_MMU_H */
diff --git a/arch/riscv/include/asm/mmu_context.h b/arch/riscv/include/asm/mmu_context.h
new file mode 100644
index 000000000..7030837ad
--- /dev/null
+++ b/arch/riscv/include/asm/mmu_context.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ * Copyright (C) 2017 SiFive
+ */
+
+#ifndef _ASM_RISCV_MMU_CONTEXT_H
+#define _ASM_RISCV_MMU_CONTEXT_H
+
+#include <linux/mm_types.h>
+#include <asm-generic/mm_hooks.h>
+
+#include <linux/mm.h>
+#include <linux/sched.h>
+
+void switch_mm(struct mm_struct *prev, struct mm_struct *next,
+	struct task_struct *task);
+
+#define activate_mm activate_mm
+static inline void activate_mm(struct mm_struct *prev,
+			       struct mm_struct *next)
+{
+	switch_mm(prev, next, NULL);
+}
+
+#define init_new_context init_new_context
+static inline int init_new_context(struct task_struct *tsk,
+			struct mm_struct *mm)
+{
+#ifdef CONFIG_MMU
+	atomic_long_set(&mm->context.id, 0);
+#endif
+	return 0;
+}
+
+DECLARE_STATIC_KEY_FALSE(use_asid_allocator);
+
+#include <asm-generic/mmu_context.h>
+
+#endif /* _ASM_RISCV_MMU_CONTEXT_H */
diff --git a/arch/riscv/include/asm/mmzone.h b/arch/riscv/include/asm/mmzone.h
new file mode 100644
index 000000000..fa17e01d9
--- /dev/null
+++ b/arch/riscv/include/asm/mmzone.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_MMZONE_H
+#define __ASM_MMZONE_H
+
+#ifdef CONFIG_NUMA
+
+#include <asm/numa.h>
+
+extern struct pglist_data *node_data[];
+#define NODE_DATA(nid)		(node_data[(nid)])
+
+#endif /* CONFIG_NUMA */
+#endif /* __ASM_MMZONE_H */
diff --git a/arch/riscv/include/asm/module.h b/arch/riscv/include/asm/module.h
new file mode 100644
index 000000000..76aa96a9f
--- /dev/null
+++ b/arch/riscv/include/asm/module.h
@@ -0,0 +1,114 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2017 Andes Technology Corporation */
+
+#ifndef _ASM_RISCV_MODULE_H
+#define _ASM_RISCV_MODULE_H
+
+#include <asm-generic/module.h>
+
+struct module;
+unsigned long module_emit_got_entry(struct module *mod, unsigned long val);
+unsigned long module_emit_plt_entry(struct module *mod, unsigned long val);
+
+#ifdef CONFIG_MODULE_SECTIONS
+struct mod_section {
+	Elf_Shdr *shdr;
+	int num_entries;
+	int max_entries;
+};
+
+struct mod_arch_specific {
+	struct mod_section got;
+	struct mod_section plt;
+	struct mod_section got_plt;
+};
+
+struct got_entry {
+	unsigned long symbol_addr;	/* the real variable address */
+};
+
+static inline struct got_entry emit_got_entry(unsigned long val)
+{
+	return (struct got_entry) {val};
+}
+
+static inline struct got_entry *get_got_entry(unsigned long val,
+					      const struct mod_section *sec)
+{
+	struct got_entry *got = (struct got_entry *)(sec->shdr->sh_addr);
+	int i;
+	for (i = 0; i < sec->num_entries; i++) {
+		if (got[i].symbol_addr == val)
+			return &got[i];
+	}
+	return NULL;
+}
+
+struct plt_entry {
+	/*
+	 * Trampoline code to real target address. The return address
+	 * should be the original (pc+4) before entring plt entry.
+	 */
+	u32 insn_auipc;		/* auipc t0, 0x0                       */
+	u32 insn_ld;		/* ld    t1, 0x10(t0)                  */
+	u32 insn_jr;		/* jr    t1                            */
+};
+
+#define OPC_AUIPC  0x0017
+#define OPC_LD     0x3003
+#define OPC_JALR   0x0067
+#define REG_T0     0x5
+#define REG_T1     0x6
+
+static inline struct plt_entry emit_plt_entry(unsigned long val,
+					      unsigned long plt,
+					      unsigned long got_plt)
+{
+	/*
+	 * U-Type encoding:
+	 * +------------+----------+----------+
+	 * | imm[31:12] | rd[11:7] | opc[6:0] |
+	 * +------------+----------+----------+
+	 *
+	 * I-Type encoding:
+	 * +------------+------------+--------+----------+----------+
+	 * | imm[31:20] | rs1[19:15] | funct3 | rd[11:7] | opc[6:0] |
+	 * +------------+------------+--------+----------+----------+
+	 *
+	 */
+	unsigned long offset = got_plt - plt;
+	u32 hi20 = (offset + 0x800) & 0xfffff000;
+	u32 lo12 = (offset - hi20);
+	return (struct plt_entry) {
+		OPC_AUIPC | (REG_T0 << 7) | hi20,
+		OPC_LD | (lo12 << 20) | (REG_T0 << 15) | (REG_T1 << 7),
+		OPC_JALR | (REG_T1 << 15)
+	};
+}
+
+static inline int get_got_plt_idx(unsigned long val, const struct mod_section *sec)
+{
+	struct got_entry *got_plt = (struct got_entry *)sec->shdr->sh_addr;
+	int i;
+	for (i = 0; i < sec->num_entries; i++) {
+		if (got_plt[i].symbol_addr == val)
+			return i;
+	}
+	return -1;
+}
+
+static inline struct plt_entry *get_plt_entry(unsigned long val,
+					      const struct mod_section *sec_plt,
+					      const struct mod_section *sec_got_plt)
+{
+	struct plt_entry *plt = (struct plt_entry *)sec_plt->shdr->sh_addr;
+	int got_plt_idx = get_got_plt_idx(val, sec_got_plt);
+	if (got_plt_idx >= 0)
+		return plt + got_plt_idx;
+	else
+		return NULL;
+}
+
+#endif /* CONFIG_MODULE_SECTIONS */
+
+#endif /* _ASM_RISCV_MODULE_H */
diff --git a/arch/riscv/include/asm/module.lds.h b/arch/riscv/include/asm/module.lds.h
new file mode 100644
index 000000000..1075beae1
--- /dev/null
+++ b/arch/riscv/include/asm/module.lds.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2017 Andes Technology Corporation */
+#ifdef CONFIG_MODULE_SECTIONS
+SECTIONS {
+	.plt : { BYTE(0) }
+	.got : { BYTE(0) }
+	.got.plt : { BYTE(0) }
+}
+#endif
diff --git a/arch/riscv/include/asm/numa.h b/arch/riscv/include/asm/numa.h
new file mode 100644
index 000000000..8c8cf4297
--- /dev/null
+++ b/arch/riscv/include/asm/numa.h
@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_NUMA_H
+#define __ASM_NUMA_H
+
+#include <asm/topology.h>
+#include <asm-generic/numa.h>
+
+#endif	/* __ASM_NUMA_H */
diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h
new file mode 100644
index 000000000..86048c60f
--- /dev/null
+++ b/arch/riscv/include/asm/page.h
@@ -0,0 +1,191 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2009 Chen Liqin <liqin.chen@sunplusct.com>
+ * Copyright (C) 2012 Regents of the University of California
+ * Copyright (C) 2017 SiFive
+ * Copyright (C) 2017 XiaojingZhu <zhuxiaoj@ict.ac.cn>
+ */
+
+#ifndef _ASM_RISCV_PAGE_H
+#define _ASM_RISCV_PAGE_H
+
+#include <linux/pfn.h>
+#include <linux/const.h>
+
+#define PAGE_SHIFT	(12)
+#define PAGE_SIZE	(_AC(1, UL) << PAGE_SHIFT)
+#define PAGE_MASK	(~(PAGE_SIZE - 1))
+
+#ifdef CONFIG_64BIT
+#define HUGE_MAX_HSTATE		2
+#else
+#define HUGE_MAX_HSTATE		1
+#endif
+#define HPAGE_SHIFT		PMD_SHIFT
+#define HPAGE_SIZE		(_AC(1, UL) << HPAGE_SHIFT)
+#define HPAGE_MASK              (~(HPAGE_SIZE - 1))
+#define HUGETLB_PAGE_ORDER      (HPAGE_SHIFT - PAGE_SHIFT)
+
+/*
+ * PAGE_OFFSET -- the first address of the first page of memory.
+ * When not using MMU this corresponds to the first free page in
+ * physical memory (aligned on a page boundary).
+ */
+#ifdef CONFIG_64BIT
+#ifdef CONFIG_MMU
+#define PAGE_OFFSET		kernel_map.page_offset
+#else
+#define PAGE_OFFSET		_AC(CONFIG_PAGE_OFFSET, UL)
+#endif
+/*
+ * By default, CONFIG_PAGE_OFFSET value corresponds to SV57 address space so
+ * define the PAGE_OFFSET value for SV48 and SV39.
+ */
+#define PAGE_OFFSET_L4		_AC(0xffffaf8000000000, UL)
+#define PAGE_OFFSET_L3		_AC(0xffffffd800000000, UL)
+#else
+#define PAGE_OFFSET		_AC(CONFIG_PAGE_OFFSET, UL)
+#endif /* CONFIG_64BIT */
+
+#ifndef __ASSEMBLY__
+
+#define clear_page(pgaddr)			memset((pgaddr), 0, PAGE_SIZE)
+#define copy_page(to, from)			memcpy((to), (from), PAGE_SIZE)
+
+#define clear_user_page(pgaddr, vaddr, page)	memset((pgaddr), 0, PAGE_SIZE)
+#define copy_user_page(vto, vfrom, vaddr, topg) \
+			memcpy((vto), (vfrom), PAGE_SIZE)
+
+/*
+ * Use struct definitions to apply C type checking
+ */
+
+/* Page Global Directory entry */
+typedef struct {
+	unsigned long pgd;
+} pgd_t;
+
+/* Page Table entry */
+typedef struct {
+	unsigned long pte;
+} pte_t;
+
+typedef struct {
+	unsigned long pgprot;
+} pgprot_t;
+
+typedef struct page *pgtable_t;
+
+#define pte_val(x)	((x).pte)
+#define pgd_val(x)	((x).pgd)
+#define pgprot_val(x)	((x).pgprot)
+
+#define __pte(x)	((pte_t) { (x) })
+#define __pgd(x)	((pgd_t) { (x) })
+#define __pgprot(x)	((pgprot_t) { (x) })
+
+#ifdef CONFIG_64BIT
+#define PTE_FMT "%016lx"
+#else
+#define PTE_FMT "%08lx"
+#endif
+
+#ifdef CONFIG_MMU
+extern unsigned long riscv_pfn_base;
+#define ARCH_PFN_OFFSET		(riscv_pfn_base)
+#else
+#define ARCH_PFN_OFFSET		(PAGE_OFFSET >> PAGE_SHIFT)
+#endif /* CONFIG_MMU */
+
+struct kernel_mapping {
+	unsigned long page_offset;
+	unsigned long virt_addr;
+	uintptr_t phys_addr;
+	uintptr_t size;
+	/* Offset between linear mapping virtual address and kernel load address */
+	unsigned long va_pa_offset;
+	/* Offset between kernel mapping virtual address and kernel load address */
+	unsigned long va_kernel_pa_offset;
+	unsigned long va_kernel_xip_pa_offset;
+#ifdef CONFIG_XIP_KERNEL
+	uintptr_t xiprom;
+	uintptr_t xiprom_sz;
+#endif
+};
+
+extern struct kernel_mapping kernel_map;
+extern phys_addr_t phys_ram_base;
+
+#define is_kernel_mapping(x)	\
+	((x) >= kernel_map.virt_addr && (x) < (kernel_map.virt_addr + kernel_map.size))
+
+#define is_linear_mapping(x)	\
+	((x) >= PAGE_OFFSET && (!IS_ENABLED(CONFIG_64BIT) || (x) < PAGE_OFFSET + KERN_VIRT_SIZE))
+
+#define linear_mapping_pa_to_va(x)	((void *)((unsigned long)(x) + kernel_map.va_pa_offset))
+#define kernel_mapping_pa_to_va(y)	({						\
+	unsigned long _y = y;								\
+	(IS_ENABLED(CONFIG_XIP_KERNEL) && _y < phys_ram_base) ?					\
+		(void *)((unsigned long)(_y) + kernel_map.va_kernel_xip_pa_offset) :		\
+		(void *)((unsigned long)(_y) + kernel_map.va_kernel_pa_offset + XIP_OFFSET);	\
+	})
+#define __pa_to_va_nodebug(x)		linear_mapping_pa_to_va(x)
+
+#define linear_mapping_va_to_pa(x)	((unsigned long)(x) - kernel_map.va_pa_offset)
+#define kernel_mapping_va_to_pa(y) ({						\
+	unsigned long _y = y;							\
+	(IS_ENABLED(CONFIG_XIP_KERNEL) && _y < kernel_map.virt_addr + XIP_OFFSET) ?	\
+		((unsigned long)(_y) - kernel_map.va_kernel_xip_pa_offset) :		\
+		((unsigned long)(_y) - kernel_map.va_kernel_pa_offset - XIP_OFFSET);	\
+	})
+
+#define __va_to_pa_nodebug(x)	({						\
+	unsigned long _x = x;							\
+	is_linear_mapping(_x) ?							\
+		linear_mapping_va_to_pa(_x) : kernel_mapping_va_to_pa(_x);	\
+	})
+
+#ifdef CONFIG_DEBUG_VIRTUAL
+extern phys_addr_t __virt_to_phys(unsigned long x);
+extern phys_addr_t __phys_addr_symbol(unsigned long x);
+#else
+#define __virt_to_phys(x)	__va_to_pa_nodebug(x)
+#define __phys_addr_symbol(x)	__va_to_pa_nodebug(x)
+#endif /* CONFIG_DEBUG_VIRTUAL */
+
+#define __pa_symbol(x)	__phys_addr_symbol(RELOC_HIDE((unsigned long)(x), 0))
+#define __pa(x)		__virt_to_phys((unsigned long)(x))
+#define __va(x)		((void *)__pa_to_va_nodebug((phys_addr_t)(x)))
+
+#define phys_to_pfn(phys)	(PFN_DOWN(phys))
+#define pfn_to_phys(pfn)	(PFN_PHYS(pfn))
+
+#define virt_to_pfn(vaddr)	(phys_to_pfn(__pa(vaddr)))
+#define pfn_to_virt(pfn)	(__va(pfn_to_phys(pfn)))
+
+#define virt_to_page(vaddr)	(pfn_to_page(virt_to_pfn(vaddr)))
+#define page_to_virt(page)	(pfn_to_virt(page_to_pfn(page)))
+
+#define page_to_phys(page)	(pfn_to_phys(page_to_pfn(page)))
+#define phys_to_page(paddr)	(pfn_to_page(phys_to_pfn(paddr)))
+
+#define sym_to_pfn(x)           __phys_to_pfn(__pa_symbol(x))
+
+#ifdef CONFIG_FLATMEM
+#define pfn_valid(pfn) \
+	(((pfn) >= ARCH_PFN_OFFSET) && (((pfn) - ARCH_PFN_OFFSET) < max_mapnr))
+#endif
+
+#endif /* __ASSEMBLY__ */
+
+#define virt_addr_valid(vaddr)	({						\
+	unsigned long _addr = (unsigned long)vaddr;				\
+	(unsigned long)(_addr) >= PAGE_OFFSET && pfn_valid(virt_to_pfn(_addr));	\
+})
+
+#define VM_DATA_DEFAULT_FLAGS	VM_DATA_FLAGS_NON_EXEC
+
+#include <asm-generic/memory_model.h>
+#include <asm-generic/getorder.h>
+
+#endif /* _ASM_RISCV_PAGE_H */
diff --git a/arch/riscv/include/asm/parse_asm.h b/arch/riscv/include/asm/parse_asm.h
new file mode 100644
index 000000000..3cd00332d
--- /dev/null
+++ b/arch/riscv/include/asm/parse_asm.h
@@ -0,0 +1,224 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2020 SiFive
+ */
+
+#ifndef _ASM_RISCV_INSN_H
+#define _ASM_RISCV_INSN_H
+
+#include <linux/bits.h>
+
+/* The bit field of immediate value in I-type instruction */
+#define I_IMM_SIGN_OPOFF	31
+#define I_IMM_11_0_OPOFF	20
+#define I_IMM_SIGN_OFF		12
+#define I_IMM_11_0_OFF		0
+#define I_IMM_11_0_MASK		GENMASK(11, 0)
+
+/* The bit field of immediate value in J-type instruction */
+#define J_IMM_SIGN_OPOFF	31
+#define J_IMM_10_1_OPOFF	21
+#define J_IMM_11_OPOFF		20
+#define J_IMM_19_12_OPOFF	12
+#define J_IMM_SIGN_OFF		20
+#define J_IMM_10_1_OFF		1
+#define J_IMM_11_OFF		11
+#define J_IMM_19_12_OFF		12
+#define J_IMM_10_1_MASK		GENMASK(9, 0)
+#define J_IMM_11_MASK		GENMASK(0, 0)
+#define J_IMM_19_12_MASK	GENMASK(7, 0)
+
+/* The bit field of immediate value in B-type instruction */
+#define B_IMM_SIGN_OPOFF	31
+#define B_IMM_10_5_OPOFF	25
+#define B_IMM_4_1_OPOFF		8
+#define B_IMM_11_OPOFF		7
+#define B_IMM_SIGN_OFF		12
+#define B_IMM_10_5_OFF		5
+#define B_IMM_4_1_OFF		1
+#define B_IMM_11_OFF		11
+#define B_IMM_10_5_MASK		GENMASK(5, 0)
+#define B_IMM_4_1_MASK		GENMASK(3, 0)
+#define B_IMM_11_MASK		GENMASK(0, 0)
+
+/* The register offset in RVG instruction */
+#define RVG_RS1_OPOFF		15
+#define RVG_RS2_OPOFF		20
+#define RVG_RD_OPOFF		7
+
+/* The bit field of immediate value in RVC J instruction */
+#define RVC_J_IMM_SIGN_OPOFF	12
+#define RVC_J_IMM_4_OPOFF	11
+#define RVC_J_IMM_9_8_OPOFF	9
+#define RVC_J_IMM_10_OPOFF	8
+#define RVC_J_IMM_6_OPOFF	7
+#define RVC_J_IMM_7_OPOFF	6
+#define RVC_J_IMM_3_1_OPOFF	3
+#define RVC_J_IMM_5_OPOFF	2
+#define RVC_J_IMM_SIGN_OFF	11
+#define RVC_J_IMM_4_OFF		4
+#define RVC_J_IMM_9_8_OFF	8
+#define RVC_J_IMM_10_OFF	10
+#define RVC_J_IMM_6_OFF		6
+#define RVC_J_IMM_7_OFF		7
+#define RVC_J_IMM_3_1_OFF	1
+#define RVC_J_IMM_5_OFF		5
+#define RVC_J_IMM_4_MASK	GENMASK(0, 0)
+#define RVC_J_IMM_9_8_MASK	GENMASK(1, 0)
+#define RVC_J_IMM_10_MASK	GENMASK(0, 0)
+#define RVC_J_IMM_6_MASK	GENMASK(0, 0)
+#define RVC_J_IMM_7_MASK	GENMASK(0, 0)
+#define RVC_J_IMM_3_1_MASK	GENMASK(2, 0)
+#define RVC_J_IMM_5_MASK	GENMASK(0, 0)
+
+/* The bit field of immediate value in RVC B instruction */
+#define RVC_B_IMM_SIGN_OPOFF	12
+#define RVC_B_IMM_4_3_OPOFF	10
+#define RVC_B_IMM_7_6_OPOFF	5
+#define RVC_B_IMM_2_1_OPOFF	3
+#define RVC_B_IMM_5_OPOFF	2
+#define RVC_B_IMM_SIGN_OFF	8
+#define RVC_B_IMM_4_3_OFF	3
+#define RVC_B_IMM_7_6_OFF	6
+#define RVC_B_IMM_2_1_OFF	1
+#define RVC_B_IMM_5_OFF		5
+#define RVC_B_IMM_4_3_MASK	GENMASK(1, 0)
+#define RVC_B_IMM_7_6_MASK	GENMASK(1, 0)
+#define RVC_B_IMM_2_1_MASK	GENMASK(1, 0)
+#define RVC_B_IMM_5_MASK	GENMASK(0, 0)
+
+/* The register offset in RVC op=C0 instruction */
+#define RVC_C0_RS1_OPOFF	7
+#define RVC_C0_RS2_OPOFF	2
+#define RVC_C0_RD_OPOFF		2
+
+/* The register offset in RVC op=C1 instruction */
+#define RVC_C1_RS1_OPOFF	7
+#define RVC_C1_RS2_OPOFF	2
+#define RVC_C1_RD_OPOFF		7
+
+/* The register offset in RVC op=C2 instruction */
+#define RVC_C2_RS1_OPOFF	7
+#define RVC_C2_RS2_OPOFF	2
+#define RVC_C2_RD_OPOFF		7
+
+/* parts of opcode for RVG*/
+#define OPCODE_BRANCH		0x63
+#define OPCODE_JALR		0x67
+#define OPCODE_JAL		0x6f
+#define OPCODE_SYSTEM		0x73
+
+/* parts of opcode for RVC*/
+#define OPCODE_C_0		0x0
+#define OPCODE_C_1		0x1
+#define OPCODE_C_2		0x2
+
+/* parts of funct3 code for I, M, A extension*/
+#define FUNCT3_JALR		0x0
+#define FUNCT3_BEQ		0x0
+#define FUNCT3_BNE		0x1000
+#define FUNCT3_BLT		0x4000
+#define FUNCT3_BGE		0x5000
+#define FUNCT3_BLTU		0x6000
+#define FUNCT3_BGEU		0x7000
+
+/* parts of funct3 code for C extension*/
+#define FUNCT3_C_BEQZ		0xc000
+#define FUNCT3_C_BNEZ		0xe000
+#define FUNCT3_C_J		0xa000
+#define FUNCT3_C_JAL		0x2000
+#define FUNCT4_C_JR		0x8000
+#define FUNCT4_C_JALR		0xf000
+
+#define FUNCT12_SRET		0x10200000
+
+#define MATCH_JALR		(FUNCT3_JALR | OPCODE_JALR)
+#define MATCH_JAL		(OPCODE_JAL)
+#define MATCH_BEQ		(FUNCT3_BEQ | OPCODE_BRANCH)
+#define MATCH_BNE		(FUNCT3_BNE | OPCODE_BRANCH)
+#define MATCH_BLT		(FUNCT3_BLT | OPCODE_BRANCH)
+#define MATCH_BGE		(FUNCT3_BGE | OPCODE_BRANCH)
+#define MATCH_BLTU		(FUNCT3_BLTU | OPCODE_BRANCH)
+#define MATCH_BGEU		(FUNCT3_BGEU | OPCODE_BRANCH)
+#define MATCH_SRET		(FUNCT12_SRET | OPCODE_SYSTEM)
+#define MATCH_C_BEQZ		(FUNCT3_C_BEQZ | OPCODE_C_1)
+#define MATCH_C_BNEZ		(FUNCT3_C_BNEZ | OPCODE_C_1)
+#define MATCH_C_J		(FUNCT3_C_J | OPCODE_C_1)
+#define MATCH_C_JAL		(FUNCT3_C_JAL | OPCODE_C_1)
+#define MATCH_C_JR		(FUNCT4_C_JR | OPCODE_C_2)
+#define MATCH_C_JALR		(FUNCT4_C_JALR | OPCODE_C_2)
+
+#define MASK_JALR		0x707f
+#define MASK_JAL		0x7f
+#define MASK_C_JALR		0xf07f
+#define MASK_C_JR		0xf07f
+#define MASK_C_JAL		0xe003
+#define MASK_C_J		0xe003
+#define MASK_BEQ		0x707f
+#define MASK_BNE		0x707f
+#define MASK_BLT		0x707f
+#define MASK_BGE		0x707f
+#define MASK_BLTU		0x707f
+#define MASK_BGEU		0x707f
+#define MASK_C_BEQZ		0xe003
+#define MASK_C_BNEZ		0xe003
+#define MASK_SRET		0xffffffff
+
+#define __INSN_LENGTH_MASK	_UL(0x3)
+#define __INSN_LENGTH_GE_32	_UL(0x3)
+#define __INSN_OPCODE_MASK	_UL(0x7F)
+#define __INSN_BRANCH_OPCODE	_UL(OPCODE_BRANCH)
+
+/* Define a series of is_XXX_insn functions to check if the value INSN
+ * is an instance of instruction XXX.
+ */
+#define DECLARE_INSN(INSN_NAME, INSN_MATCH, INSN_MASK) \
+static inline bool is_ ## INSN_NAME ## _insn(long insn) \
+{ \
+	return (insn & (INSN_MASK)) == (INSN_MATCH); \
+}
+
+#define RV_IMM_SIGN(x) (-(((x) >> 31) & 1))
+#define RVC_IMM_SIGN(x) (-(((x) >> 12) & 1))
+#define RV_X(X, s, mask)  (((X) >> (s)) & (mask))
+#define RVC_X(X, s, mask) RV_X(X, s, mask)
+
+#define EXTRACT_JTYPE_IMM(x) \
+	({typeof(x) x_ = (x); \
+	(RV_X(x_, J_IMM_10_1_OPOFF, J_IMM_10_1_MASK) << J_IMM_10_1_OFF) | \
+	(RV_X(x_, J_IMM_11_OPOFF, J_IMM_11_MASK) << J_IMM_11_OFF) | \
+	(RV_X(x_, J_IMM_19_12_OPOFF, J_IMM_19_12_MASK) << J_IMM_19_12_OFF) | \
+	(RV_IMM_SIGN(x_) << J_IMM_SIGN_OFF); })
+
+#define EXTRACT_ITYPE_IMM(x) \
+	({typeof(x) x_ = (x); \
+	(RV_X(x_, I_IMM_11_0_OPOFF, I_IMM_11_0_MASK)) | \
+	(RV_IMM_SIGN(x_) << I_IMM_SIGN_OFF); })
+
+#define EXTRACT_BTYPE_IMM(x) \
+	({typeof(x) x_ = (x); \
+	(RV_X(x_, B_IMM_4_1_OPOFF, B_IMM_4_1_MASK) << B_IMM_4_1_OFF) | \
+	(RV_X(x_, B_IMM_10_5_OPOFF, B_IMM_10_5_MASK) << B_IMM_10_5_OFF) | \
+	(RV_X(x_, B_IMM_11_OPOFF, B_IMM_11_MASK) << B_IMM_11_OFF) | \
+	(RV_IMM_SIGN(x_) << B_IMM_SIGN_OFF); })
+
+#define EXTRACT_RVC_J_IMM(x) \
+	({typeof(x) x_ = (x); \
+	(RVC_X(x_, RVC_J_IMM_3_1_OPOFF, RVC_J_IMM_3_1_MASK) << RVC_J_IMM_3_1_OFF) | \
+	(RVC_X(x_, RVC_J_IMM_4_OPOFF, RVC_J_IMM_4_MASK) << RVC_J_IMM_4_OFF) | \
+	(RVC_X(x_, RVC_J_IMM_5_OPOFF, RVC_J_IMM_5_MASK) << RVC_J_IMM_5_OFF) | \
+	(RVC_X(x_, RVC_J_IMM_6_OPOFF, RVC_J_IMM_6_MASK) << RVC_J_IMM_6_OFF) | \
+	(RVC_X(x_, RVC_J_IMM_7_OPOFF, RVC_J_IMM_7_MASK) << RVC_J_IMM_7_OFF) | \
+	(RVC_X(x_, RVC_J_IMM_9_8_OPOFF, RVC_J_IMM_9_8_MASK) << RVC_J_IMM_9_8_OFF) | \
+	(RVC_X(x_, RVC_J_IMM_10_OPOFF, RVC_J_IMM_10_MASK) << RVC_J_IMM_10_OFF) | \
+	(RVC_IMM_SIGN(x_) << RVC_J_IMM_SIGN_OFF); })
+
+#define EXTRACT_RVC_B_IMM(x) \
+	({typeof(x) x_ = (x); \
+	(RVC_X(x_, RVC_B_IMM_2_1_OPOFF, RVC_B_IMM_2_1_MASK) << RVC_B_IMM_2_1_OFF) | \
+	(RVC_X(x_, RVC_B_IMM_4_3_OPOFF, RVC_B_IMM_4_3_MASK) << RVC_B_IMM_4_3_OFF) | \
+	(RVC_X(x_, RVC_B_IMM_5_OPOFF, RVC_B_IMM_5_MASK) << RVC_B_IMM_5_OFF) | \
+	(RVC_X(x_, RVC_B_IMM_7_6_OPOFF, RVC_B_IMM_7_6_MASK) << RVC_B_IMM_7_6_OFF) | \
+	(RVC_IMM_SIGN(x_) << RVC_B_IMM_SIGN_OFF); })
+
+#endif /* _ASM_RISCV_INSN_H */
diff --git a/arch/riscv/include/asm/patch.h b/arch/riscv/include/asm/patch.h
new file mode 100644
index 000000000..98d9de07c
--- /dev/null
+++ b/arch/riscv/include/asm/patch.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2020 SiFive
+ */
+
+#ifndef _ASM_RISCV_PATCH_H
+#define _ASM_RISCV_PATCH_H
+
+int patch_text_nosync(void *addr, const void *insns, size_t len);
+int patch_text(void *addr, u32 insn);
+
+extern int riscv_patch_in_stop_machine;
+
+#endif /* _ASM_RISCV_PATCH_H */
diff --git a/arch/riscv/include/asm/pci.h b/arch/riscv/include/asm/pci.h
new file mode 100644
index 000000000..cc2a184cf
--- /dev/null
+++ b/arch/riscv/include/asm/pci.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2016 SiFive
+ */
+
+#ifndef _ASM_RISCV_PCI_H
+#define _ASM_RISCV_PCI_H
+
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/dma-mapping.h>
+
+#include <asm/io.h>
+
+#define PCIBIOS_MIN_IO		4
+#define PCIBIOS_MIN_MEM		16
+
+#if defined(CONFIG_PCI) && defined(CONFIG_NUMA)
+static inline int pcibus_to_node(struct pci_bus *bus)
+{
+	return dev_to_node(&bus->dev);
+}
+#ifndef cpumask_of_pcibus
+#define cpumask_of_pcibus(bus)	(pcibus_to_node(bus) == -1 ?		\
+				 cpu_all_mask :				\
+				 cpumask_of_node(pcibus_to_node(bus)))
+#endif
+#endif /* defined(CONFIG_PCI) && defined(CONFIG_NUMA) */
+
+/* Generic PCI */
+#include <asm-generic/pci.h>
+
+#endif  /* _ASM_RISCV_PCI_H */
diff --git a/arch/riscv/include/asm/perf_event.h b/arch/riscv/include/asm/perf_event.h
new file mode 100644
index 000000000..665bbc9b2
--- /dev/null
+++ b/arch/riscv/include/asm/perf_event.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2018 SiFive
+ * Copyright (C) 2018 Andes Technology Corporation
+ *
+ */
+
+#ifndef _ASM_RISCV_PERF_EVENT_H
+#define _ASM_RISCV_PERF_EVENT_H
+
+#include <linux/perf_event.h>
+#define perf_arch_bpf_user_pt_regs(regs) (struct user_regs_struct *)regs
+
+#define perf_arch_fetch_caller_regs(regs, __ip) { \
+	(regs)->epc = (__ip); \
+	(regs)->s0 = (unsigned long) __builtin_frame_address(0); \
+	(regs)->sp = current_stack_pointer; \
+	(regs)->status = SR_PP; \
+}
+#endif /* _ASM_RISCV_PERF_EVENT_H */
diff --git a/arch/riscv/include/asm/pgalloc.h b/arch/riscv/include/asm/pgalloc.h
new file mode 100644
index 000000000..59dc12b5b
--- /dev/null
+++ b/arch/riscv/include/asm/pgalloc.h
@@ -0,0 +1,163 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2009 Chen Liqin <liqin.chen@sunplusct.com>
+ * Copyright (C) 2012 Regents of the University of California
+ */
+
+#ifndef _ASM_RISCV_PGALLOC_H
+#define _ASM_RISCV_PGALLOC_H
+
+#include <linux/mm.h>
+#include <asm/tlb.h>
+
+#ifdef CONFIG_MMU
+#define __HAVE_ARCH_PUD_ALLOC_ONE
+#define __HAVE_ARCH_PUD_FREE
+#include <asm-generic/pgalloc.h>
+
+static inline void pmd_populate_kernel(struct mm_struct *mm,
+	pmd_t *pmd, pte_t *pte)
+{
+	unsigned long pfn = virt_to_pfn(pte);
+
+	set_pmd(pmd, __pmd((pfn << _PAGE_PFN_SHIFT) | _PAGE_TABLE));
+}
+
+static inline void pmd_populate(struct mm_struct *mm,
+	pmd_t *pmd, pgtable_t pte)
+{
+	unsigned long pfn = virt_to_pfn(page_address(pte));
+
+	set_pmd(pmd, __pmd((pfn << _PAGE_PFN_SHIFT) | _PAGE_TABLE));
+}
+
+#ifndef __PAGETABLE_PMD_FOLDED
+static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
+{
+	unsigned long pfn = virt_to_pfn(pmd);
+
+	set_pud(pud, __pud((pfn << _PAGE_PFN_SHIFT) | _PAGE_TABLE));
+}
+
+static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4d, pud_t *pud)
+{
+	if (pgtable_l4_enabled) {
+		unsigned long pfn = virt_to_pfn(pud);
+
+		set_p4d(p4d, __p4d((pfn << _PAGE_PFN_SHIFT) | _PAGE_TABLE));
+	}
+}
+
+static inline void p4d_populate_safe(struct mm_struct *mm, p4d_t *p4d,
+				     pud_t *pud)
+{
+	if (pgtable_l4_enabled) {
+		unsigned long pfn = virt_to_pfn(pud);
+
+		set_p4d_safe(p4d,
+			     __p4d((pfn << _PAGE_PFN_SHIFT) | _PAGE_TABLE));
+	}
+}
+
+static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, p4d_t *p4d)
+{
+	if (pgtable_l5_enabled) {
+		unsigned long pfn = virt_to_pfn(p4d);
+
+		set_pgd(pgd, __pgd((pfn << _PAGE_PFN_SHIFT) | _PAGE_TABLE));
+	}
+}
+
+static inline void pgd_populate_safe(struct mm_struct *mm, pgd_t *pgd,
+				     p4d_t *p4d)
+{
+	if (pgtable_l5_enabled) {
+		unsigned long pfn = virt_to_pfn(p4d);
+
+		set_pgd_safe(pgd,
+			     __pgd((pfn << _PAGE_PFN_SHIFT) | _PAGE_TABLE));
+	}
+}
+
+#define pud_alloc_one pud_alloc_one
+static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
+{
+	if (pgtable_l4_enabled)
+		return __pud_alloc_one(mm, addr);
+
+	return NULL;
+}
+
+#define pud_free pud_free
+static inline void pud_free(struct mm_struct *mm, pud_t *pud)
+{
+	if (pgtable_l4_enabled)
+		__pud_free(mm, pud);
+}
+
+#define __pud_free_tlb(tlb, pud, addr)  pud_free((tlb)->mm, pud)
+
+#define p4d_alloc_one p4d_alloc_one
+static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long addr)
+{
+	if (pgtable_l5_enabled) {
+		gfp_t gfp = GFP_PGTABLE_USER;
+
+		if (mm == &init_mm)
+			gfp = GFP_PGTABLE_KERNEL;
+		return (p4d_t *)get_zeroed_page(gfp);
+	}
+
+	return NULL;
+}
+
+static inline void __p4d_free(struct mm_struct *mm, p4d_t *p4d)
+{
+	BUG_ON((unsigned long)p4d & (PAGE_SIZE-1));
+	free_page((unsigned long)p4d);
+}
+
+#define p4d_free p4d_free
+static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d)
+{
+	if (pgtable_l5_enabled)
+		__p4d_free(mm, p4d);
+}
+
+#define __p4d_free_tlb(tlb, p4d, addr)  p4d_free((tlb)->mm, p4d)
+#endif /* __PAGETABLE_PMD_FOLDED */
+
+static inline void sync_kernel_mappings(pgd_t *pgd)
+{
+	memcpy(pgd + USER_PTRS_PER_PGD,
+	       init_mm.pgd + USER_PTRS_PER_PGD,
+	       (PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t));
+}
+
+static inline pgd_t *pgd_alloc(struct mm_struct *mm)
+{
+	pgd_t *pgd;
+
+	pgd = (pgd_t *)__get_free_page(GFP_KERNEL);
+	if (likely(pgd != NULL)) {
+		memset(pgd, 0, USER_PTRS_PER_PGD * sizeof(pgd_t));
+		/* Copy kernel mappings */
+		sync_kernel_mappings(pgd);
+	}
+	return pgd;
+}
+
+#ifndef __PAGETABLE_PMD_FOLDED
+
+#define __pmd_free_tlb(tlb, pmd, addr)  pmd_free((tlb)->mm, pmd)
+
+#endif /* __PAGETABLE_PMD_FOLDED */
+
+#define __pte_free_tlb(tlb, pte, buf)   \
+do {                                    \
+	pgtable_pte_page_dtor(pte);     \
+	tlb_remove_page((tlb), pte);    \
+} while (0)
+#endif /* CONFIG_MMU */
+
+#endif /* _ASM_RISCV_PGALLOC_H */
diff --git a/arch/riscv/include/asm/pgtable-32.h b/arch/riscv/include/asm/pgtable-32.h
new file mode 100644
index 000000000..59ba1fbaf
--- /dev/null
+++ b/arch/riscv/include/asm/pgtable-32.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ */
+
+#ifndef _ASM_RISCV_PGTABLE_32_H
+#define _ASM_RISCV_PGTABLE_32_H
+
+#include <asm-generic/pgtable-nopmd.h>
+#include <linux/bits.h>
+#include <linux/const.h>
+
+/* Size of region mapped by a page global directory */
+#define PGDIR_SHIFT     22
+#define PGDIR_SIZE      (_AC(1, UL) << PGDIR_SHIFT)
+#define PGDIR_MASK      (~(PGDIR_SIZE - 1))
+
+#define MAX_POSSIBLE_PHYSMEM_BITS 34
+
+/*
+ * rv32 PTE format:
+ * | XLEN-1  10 | 9             8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0
+ *       PFN      reserved for SW   D   A   G   U   X   W   R   V
+ */
+#define _PAGE_PFN_MASK  GENMASK(31, 10)
+
+#define _PAGE_NOCACHE		0
+#define _PAGE_IO		0
+#define _PAGE_MTMASK		0
+
+/* Set of bits to preserve across pte_modify() */
+#define _PAGE_CHG_MASK  (~(unsigned long)(_PAGE_PRESENT | _PAGE_READ |	\
+					  _PAGE_WRITE | _PAGE_EXEC |	\
+					  _PAGE_USER | _PAGE_GLOBAL))
+
+#endif /* _ASM_RISCV_PGTABLE_32_H */
diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h
new file mode 100644
index 000000000..42a042c0e
--- /dev/null
+++ b/arch/riscv/include/asm/pgtable-64.h
@@ -0,0 +1,377 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ */
+
+#ifndef _ASM_RISCV_PGTABLE_64_H
+#define _ASM_RISCV_PGTABLE_64_H
+
+#include <linux/bits.h>
+#include <linux/const.h>
+#include <asm/errata_list.h>
+
+extern bool pgtable_l4_enabled;
+extern bool pgtable_l5_enabled;
+
+#define PGDIR_SHIFT_L3  30
+#define PGDIR_SHIFT_L4  39
+#define PGDIR_SHIFT_L5  48
+#define PGDIR_SIZE_L3   (_AC(1, UL) << PGDIR_SHIFT_L3)
+
+#define PGDIR_SHIFT     (pgtable_l5_enabled ? PGDIR_SHIFT_L5 : \
+		(pgtable_l4_enabled ? PGDIR_SHIFT_L4 : PGDIR_SHIFT_L3))
+/* Size of region mapped by a page global directory */
+#define PGDIR_SIZE      (_AC(1, UL) << PGDIR_SHIFT)
+#define PGDIR_MASK      (~(PGDIR_SIZE - 1))
+
+/* p4d is folded into pgd in case of 4-level page table */
+#define P4D_SHIFT_L3   30
+#define P4D_SHIFT_L4   39
+#define P4D_SHIFT_L5   39
+#define P4D_SHIFT      (pgtable_l5_enabled ? P4D_SHIFT_L5 : \
+		(pgtable_l4_enabled ? P4D_SHIFT_L4 : P4D_SHIFT_L3))
+#define P4D_SIZE       (_AC(1, UL) << P4D_SHIFT)
+#define P4D_MASK       (~(P4D_SIZE - 1))
+
+/* pud is folded into pgd in case of 3-level page table */
+#define PUD_SHIFT      30
+#define PUD_SIZE       (_AC(1, UL) << PUD_SHIFT)
+#define PUD_MASK       (~(PUD_SIZE - 1))
+
+#define PMD_SHIFT       21
+/* Size of region mapped by a page middle directory */
+#define PMD_SIZE        (_AC(1, UL) << PMD_SHIFT)
+#define PMD_MASK        (~(PMD_SIZE - 1))
+
+/* Page 4th Directory entry */
+typedef struct {
+	unsigned long p4d;
+} p4d_t;
+
+#define p4d_val(x)	((x).p4d)
+#define __p4d(x)	((p4d_t) { (x) })
+#define PTRS_PER_P4D	(PAGE_SIZE / sizeof(p4d_t))
+
+/* Page Upper Directory entry */
+typedef struct {
+	unsigned long pud;
+} pud_t;
+
+#define pud_val(x)      ((x).pud)
+#define __pud(x)        ((pud_t) { (x) })
+#define PTRS_PER_PUD    (PAGE_SIZE / sizeof(pud_t))
+
+/* Page Middle Directory entry */
+typedef struct {
+	unsigned long pmd;
+} pmd_t;
+
+#define pmd_val(x)      ((x).pmd)
+#define __pmd(x)        ((pmd_t) { (x) })
+
+#define PTRS_PER_PMD    (PAGE_SIZE / sizeof(pmd_t))
+
+/*
+ * rv64 PTE format:
+ * | 63 | 62 61 | 60 54 | 53  10 | 9             8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0
+ *   N      MT     RSV    PFN      reserved for SW   D   A   G   U   X   W   R   V
+ */
+#define _PAGE_PFN_MASK  GENMASK(53, 10)
+
+/*
+ * [62:61] Svpbmt Memory Type definitions:
+ *
+ *  00 - PMA    Normal Cacheable, No change to implied PMA memory type
+ *  01 - NC     Non-cacheable, idempotent, weakly-ordered Main Memory
+ *  10 - IO     Non-cacheable, non-idempotent, strongly-ordered I/O memory
+ *  11 - Rsvd   Reserved for future standard use
+ */
+#define _PAGE_NOCACHE_SVPBMT	(1UL << 61)
+#define _PAGE_IO_SVPBMT		(1UL << 62)
+#define _PAGE_MTMASK_SVPBMT	(_PAGE_NOCACHE_SVPBMT | _PAGE_IO_SVPBMT)
+
+/*
+ * [63:59] T-Head Memory Type definitions:
+ *
+ * 00000 - NC   Weakly-ordered, Non-cacheable, Non-bufferable, Non-shareable, Non-trustable
+ * 01110 - PMA  Weakly-ordered, Cacheable, Bufferable, Shareable, Non-trustable
+ * 10000 - IO   Strongly-ordered, Non-cacheable, Non-bufferable, Non-shareable, Non-trustable
+ */
+#define _PAGE_PMA_THEAD		((1UL << 62) | (1UL << 61) | (1UL << 60))
+#define _PAGE_NOCACHE_THEAD	0UL
+#define _PAGE_IO_THEAD		(1UL << 63)
+#define _PAGE_MTMASK_THEAD	(_PAGE_PMA_THEAD | _PAGE_IO_THEAD | (1UL << 59))
+
+static inline u64 riscv_page_mtmask(void)
+{
+	u64 val;
+
+	ALT_SVPBMT(val, _PAGE_MTMASK);
+	return val;
+}
+
+static inline u64 riscv_page_nocache(void)
+{
+	u64 val;
+
+	ALT_SVPBMT(val, _PAGE_NOCACHE);
+	return val;
+}
+
+static inline u64 riscv_page_io(void)
+{
+	u64 val;
+
+	ALT_SVPBMT(val, _PAGE_IO);
+	return val;
+}
+
+#define _PAGE_NOCACHE		riscv_page_nocache()
+#define _PAGE_IO		riscv_page_io()
+#define _PAGE_MTMASK		riscv_page_mtmask()
+
+/* Set of bits to preserve across pte_modify() */
+#define _PAGE_CHG_MASK  (~(unsigned long)(_PAGE_PRESENT | _PAGE_READ |	\
+					  _PAGE_WRITE | _PAGE_EXEC |	\
+					  _PAGE_USER | _PAGE_GLOBAL |	\
+					  _PAGE_MTMASK))
+
+static inline int pud_present(pud_t pud)
+{
+	return (pud_val(pud) & _PAGE_PRESENT);
+}
+
+static inline int pud_none(pud_t pud)
+{
+	return (pud_val(pud) == 0);
+}
+
+static inline int pud_bad(pud_t pud)
+{
+	return !pud_present(pud);
+}
+
+#define pud_leaf	pud_leaf
+static inline int pud_leaf(pud_t pud)
+{
+	return pud_present(pud) && (pud_val(pud) & _PAGE_LEAF);
+}
+
+static inline int pud_user(pud_t pud)
+{
+	return pud_val(pud) & _PAGE_USER;
+}
+
+static inline void set_pud(pud_t *pudp, pud_t pud)
+{
+	*pudp = pud;
+}
+
+static inline void pud_clear(pud_t *pudp)
+{
+	set_pud(pudp, __pud(0));
+}
+
+static inline pud_t pfn_pud(unsigned long pfn, pgprot_t prot)
+{
+	return __pud((pfn << _PAGE_PFN_SHIFT) | pgprot_val(prot));
+}
+
+static inline unsigned long _pud_pfn(pud_t pud)
+{
+	return __page_val_to_pfn(pud_val(pud));
+}
+
+static inline pmd_t *pud_pgtable(pud_t pud)
+{
+	return (pmd_t *)pfn_to_virt(__page_val_to_pfn(pud_val(pud)));
+}
+
+static inline struct page *pud_page(pud_t pud)
+{
+	return pfn_to_page(__page_val_to_pfn(pud_val(pud)));
+}
+
+#define mm_p4d_folded  mm_p4d_folded
+static inline bool mm_p4d_folded(struct mm_struct *mm)
+{
+	if (pgtable_l5_enabled)
+		return false;
+
+	return true;
+}
+
+#define mm_pud_folded  mm_pud_folded
+static inline bool mm_pud_folded(struct mm_struct *mm)
+{
+	if (pgtable_l4_enabled)
+		return false;
+
+	return true;
+}
+
+#define pmd_index(addr) (((addr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1))
+
+static inline pmd_t pfn_pmd(unsigned long pfn, pgprot_t prot)
+{
+	unsigned long prot_val = pgprot_val(prot);
+
+	ALT_THEAD_PMA(prot_val);
+
+	return __pmd((pfn << _PAGE_PFN_SHIFT) | prot_val);
+}
+
+static inline unsigned long _pmd_pfn(pmd_t pmd)
+{
+	return __page_val_to_pfn(pmd_val(pmd));
+}
+
+#define mk_pmd(page, prot)    pfn_pmd(page_to_pfn(page), prot)
+
+#define pmd_ERROR(e) \
+	pr_err("%s:%d: bad pmd %016lx.\n", __FILE__, __LINE__, pmd_val(e))
+
+#define pud_ERROR(e)   \
+	pr_err("%s:%d: bad pud %016lx.\n", __FILE__, __LINE__, pud_val(e))
+
+#define p4d_ERROR(e)   \
+	pr_err("%s:%d: bad p4d %016lx.\n", __FILE__, __LINE__, p4d_val(e))
+
+static inline void set_p4d(p4d_t *p4dp, p4d_t p4d)
+{
+	if (pgtable_l4_enabled)
+		*p4dp = p4d;
+	else
+		set_pud((pud_t *)p4dp, (pud_t){ p4d_val(p4d) });
+}
+
+static inline int p4d_none(p4d_t p4d)
+{
+	if (pgtable_l4_enabled)
+		return (p4d_val(p4d) == 0);
+
+	return 0;
+}
+
+static inline int p4d_present(p4d_t p4d)
+{
+	if (pgtable_l4_enabled)
+		return (p4d_val(p4d) & _PAGE_PRESENT);
+
+	return 1;
+}
+
+static inline int p4d_bad(p4d_t p4d)
+{
+	if (pgtable_l4_enabled)
+		return !p4d_present(p4d);
+
+	return 0;
+}
+
+static inline void p4d_clear(p4d_t *p4d)
+{
+	if (pgtable_l4_enabled)
+		set_p4d(p4d, __p4d(0));
+}
+
+static inline p4d_t pfn_p4d(unsigned long pfn, pgprot_t prot)
+{
+	return __p4d((pfn << _PAGE_PFN_SHIFT) | pgprot_val(prot));
+}
+
+static inline unsigned long _p4d_pfn(p4d_t p4d)
+{
+	return __page_val_to_pfn(p4d_val(p4d));
+}
+
+static inline pud_t *p4d_pgtable(p4d_t p4d)
+{
+	if (pgtable_l4_enabled)
+		return (pud_t *)pfn_to_virt(__page_val_to_pfn(p4d_val(p4d)));
+
+	return (pud_t *)pud_pgtable((pud_t) { p4d_val(p4d) });
+}
+#define p4d_page_vaddr(p4d)	((unsigned long)p4d_pgtable(p4d))
+
+static inline struct page *p4d_page(p4d_t p4d)
+{
+	return pfn_to_page(__page_val_to_pfn(p4d_val(p4d)));
+}
+
+#define pud_index(addr) (((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1))
+
+#define pud_offset pud_offset
+static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
+{
+	if (pgtable_l4_enabled)
+		return p4d_pgtable(*p4d) + pud_index(address);
+
+	return (pud_t *)p4d;
+}
+
+static inline void set_pgd(pgd_t *pgdp, pgd_t pgd)
+{
+	if (pgtable_l5_enabled)
+		*pgdp = pgd;
+	else
+		set_p4d((p4d_t *)pgdp, (p4d_t){ pgd_val(pgd) });
+}
+
+static inline int pgd_none(pgd_t pgd)
+{
+	if (pgtable_l5_enabled)
+		return (pgd_val(pgd) == 0);
+
+	return 0;
+}
+
+static inline int pgd_present(pgd_t pgd)
+{
+	if (pgtable_l5_enabled)
+		return (pgd_val(pgd) & _PAGE_PRESENT);
+
+	return 1;
+}
+
+static inline int pgd_bad(pgd_t pgd)
+{
+	if (pgtable_l5_enabled)
+		return !pgd_present(pgd);
+
+	return 0;
+}
+
+static inline void pgd_clear(pgd_t *pgd)
+{
+	if (pgtable_l5_enabled)
+		set_pgd(pgd, __pgd(0));
+}
+
+static inline p4d_t *pgd_pgtable(pgd_t pgd)
+{
+	if (pgtable_l5_enabled)
+		return (p4d_t *)pfn_to_virt(__page_val_to_pfn(pgd_val(pgd)));
+
+	return (p4d_t *)p4d_pgtable((p4d_t) { pgd_val(pgd) });
+}
+#define pgd_page_vaddr(pgd)	((unsigned long)pgd_pgtable(pgd))
+
+static inline struct page *pgd_page(pgd_t pgd)
+{
+	return pfn_to_page(__page_val_to_pfn(pgd_val(pgd)));
+}
+#define pgd_page(pgd)	pgd_page(pgd)
+
+#define p4d_index(addr) (((addr) >> P4D_SHIFT) & (PTRS_PER_P4D - 1))
+
+#define p4d_offset p4d_offset
+static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
+{
+	if (pgtable_l5_enabled)
+		return pgd_pgtable(*pgd) + p4d_index(address);
+
+	return (p4d_t *)pgd;
+}
+
+#endif /* _ASM_RISCV_PGTABLE_64_H */
diff --git a/arch/riscv/include/asm/pgtable-bits.h b/arch/riscv/include/asm/pgtable-bits.h
new file mode 100644
index 000000000..b9e13a8fe
--- /dev/null
+++ b/arch/riscv/include/asm/pgtable-bits.h
@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ */
+
+#ifndef _ASM_RISCV_PGTABLE_BITS_H
+#define _ASM_RISCV_PGTABLE_BITS_H
+
+#define _PAGE_ACCESSED_OFFSET 6
+
+#define _PAGE_PRESENT   (1 << 0)
+#define _PAGE_READ      (1 << 1)    /* Readable */
+#define _PAGE_WRITE     (1 << 2)    /* Writable */
+#define _PAGE_EXEC      (1 << 3)    /* Executable */
+#define _PAGE_USER      (1 << 4)    /* User */
+#define _PAGE_GLOBAL    (1 << 5)    /* Global */
+#define _PAGE_ACCESSED  (1 << 6)    /* Set by hardware on any access */
+#define _PAGE_DIRTY     (1 << 7)    /* Set by hardware on any write */
+#define _PAGE_SOFT      (1 << 8)    /* Reserved for software */
+
+#define _PAGE_SPECIAL   _PAGE_SOFT
+#define _PAGE_TABLE     _PAGE_PRESENT
+
+/*
+ * _PAGE_PROT_NONE is set on not-present pages (and ignored by the hardware) to
+ * distinguish them from swapped out pages
+ */
+#define _PAGE_PROT_NONE _PAGE_GLOBAL
+
+#define _PAGE_PFN_SHIFT 10
+
+/*
+ * when all of R/W/X are zero, the PTE is a pointer to the next level
+ * of the page table; otherwise, it is a leaf PTE.
+ */
+#define _PAGE_LEAF (_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC)
+
+#endif /* _ASM_RISCV_PGTABLE_BITS_H */
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
new file mode 100644
index 000000000..59bb53da4
--- /dev/null
+++ b/arch/riscv/include/asm/pgtable.h
@@ -0,0 +1,835 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ */
+
+#ifndef _ASM_RISCV_PGTABLE_H
+#define _ASM_RISCV_PGTABLE_H
+
+#include <linux/mmzone.h>
+#include <linux/sizes.h>
+
+#include <asm/pgtable-bits.h>
+
+#ifndef CONFIG_MMU
+#define KERNEL_LINK_ADDR	PAGE_OFFSET
+#define KERN_VIRT_SIZE		(UL(-1))
+#else
+
+#define ADDRESS_SPACE_END	(UL(-1))
+
+#ifdef CONFIG_64BIT
+/* Leave 2GB for kernel and BPF at the end of the address space */
+#define KERNEL_LINK_ADDR	(ADDRESS_SPACE_END - SZ_2G + 1)
+#else
+#define KERNEL_LINK_ADDR	PAGE_OFFSET
+#endif
+
+/* Number of entries in the page global directory */
+#define PTRS_PER_PGD    (PAGE_SIZE / sizeof(pgd_t))
+/* Number of entries in the page table */
+#define PTRS_PER_PTE    (PAGE_SIZE / sizeof(pte_t))
+
+/*
+ * Half of the kernel address space (half of the entries of the page global
+ * directory) is for the direct mapping.
+ */
+#define KERN_VIRT_SIZE          ((PTRS_PER_PGD / 2 * PGDIR_SIZE) / 2)
+
+#define VMALLOC_SIZE     (KERN_VIRT_SIZE >> 1)
+#define VMALLOC_END      PAGE_OFFSET
+#define VMALLOC_START    (PAGE_OFFSET - VMALLOC_SIZE)
+
+#define BPF_JIT_REGION_SIZE	(SZ_128M)
+#ifdef CONFIG_64BIT
+#define BPF_JIT_REGION_START	(BPF_JIT_REGION_END - BPF_JIT_REGION_SIZE)
+#define BPF_JIT_REGION_END	(MODULES_END)
+#else
+#define BPF_JIT_REGION_START	(PAGE_OFFSET - BPF_JIT_REGION_SIZE)
+#define BPF_JIT_REGION_END	(VMALLOC_END)
+#endif
+
+/* Modules always live before the kernel */
+#ifdef CONFIG_64BIT
+/* This is used to define the end of the KASAN shadow region */
+#define MODULES_LOWEST_VADDR	(KERNEL_LINK_ADDR - SZ_2G)
+#define MODULES_VADDR		(PFN_ALIGN((unsigned long)&_end) - SZ_2G)
+#define MODULES_END		(PFN_ALIGN((unsigned long)&_start))
+#endif
+
+/*
+ * Roughly size the vmemmap space to be large enough to fit enough
+ * struct pages to map half the virtual address space. Then
+ * position vmemmap directly below the VMALLOC region.
+ */
+#ifdef CONFIG_64BIT
+#define VA_BITS		(pgtable_l5_enabled ? \
+				57 : (pgtable_l4_enabled ? 48 : 39))
+#else
+#define VA_BITS		32
+#endif
+
+#define VMEMMAP_SHIFT \
+	(VA_BITS - PAGE_SHIFT - 1 + STRUCT_PAGE_MAX_SHIFT)
+#define VMEMMAP_SIZE	BIT(VMEMMAP_SHIFT)
+#define VMEMMAP_END	VMALLOC_START
+#define VMEMMAP_START	(VMALLOC_START - VMEMMAP_SIZE)
+
+/*
+ * Define vmemmap for pfn_to_page & page_to_pfn calls. Needed if kernel
+ * is configured with CONFIG_SPARSEMEM_VMEMMAP enabled.
+ */
+#define vmemmap		((struct page *)VMEMMAP_START)
+
+#define PCI_IO_SIZE      SZ_16M
+#define PCI_IO_END       VMEMMAP_START
+#define PCI_IO_START     (PCI_IO_END - PCI_IO_SIZE)
+
+#define FIXADDR_TOP      PCI_IO_START
+#ifdef CONFIG_64BIT
+#define MAX_FDT_SIZE	 PMD_SIZE
+#define FIX_FDT_SIZE	 (MAX_FDT_SIZE + SZ_2M)
+#define FIXADDR_SIZE     (PMD_SIZE + FIX_FDT_SIZE)
+#else
+#define MAX_FDT_SIZE	 PGDIR_SIZE
+#define FIX_FDT_SIZE	 MAX_FDT_SIZE
+#define FIXADDR_SIZE     (PGDIR_SIZE + FIX_FDT_SIZE)
+#endif
+#define FIXADDR_START    (FIXADDR_TOP - FIXADDR_SIZE)
+
+#endif
+
+#ifdef CONFIG_XIP_KERNEL
+#define XIP_OFFSET		SZ_32M
+#define XIP_OFFSET_MASK		(SZ_32M - 1)
+#else
+#define XIP_OFFSET		0
+#endif
+
+#ifndef __ASSEMBLY__
+
+#include <asm/page.h>
+#include <asm/tlbflush.h>
+#include <linux/mm_types.h>
+
+#define __page_val_to_pfn(_val)  (((_val) & _PAGE_PFN_MASK) >> _PAGE_PFN_SHIFT)
+
+#ifdef CONFIG_64BIT
+#include <asm/pgtable-64.h>
+#else
+#include <asm/pgtable-32.h>
+#endif /* CONFIG_64BIT */
+
+#include <linux/page_table_check.h>
+
+#ifdef CONFIG_XIP_KERNEL
+#define XIP_FIXUP(addr) ({							\
+	uintptr_t __a = (uintptr_t)(addr);					\
+	(__a >= CONFIG_XIP_PHYS_ADDR && \
+	 __a < CONFIG_XIP_PHYS_ADDR + XIP_OFFSET * 2) ?	\
+		__a - CONFIG_XIP_PHYS_ADDR + CONFIG_PHYS_RAM_BASE - XIP_OFFSET :\
+		__a;								\
+	})
+#else
+#define XIP_FIXUP(addr)		(addr)
+#endif /* CONFIG_XIP_KERNEL */
+
+struct pt_alloc_ops {
+	pte_t *(*get_pte_virt)(phys_addr_t pa);
+	phys_addr_t (*alloc_pte)(uintptr_t va);
+#ifndef __PAGETABLE_PMD_FOLDED
+	pmd_t *(*get_pmd_virt)(phys_addr_t pa);
+	phys_addr_t (*alloc_pmd)(uintptr_t va);
+	pud_t *(*get_pud_virt)(phys_addr_t pa);
+	phys_addr_t (*alloc_pud)(uintptr_t va);
+	p4d_t *(*get_p4d_virt)(phys_addr_t pa);
+	phys_addr_t (*alloc_p4d)(uintptr_t va);
+#endif
+};
+
+extern struct pt_alloc_ops pt_ops __initdata;
+
+#ifdef CONFIG_MMU
+/* Number of PGD entries that a user-mode program can use */
+#define USER_PTRS_PER_PGD   (TASK_SIZE / PGDIR_SIZE)
+
+/* Page protection bits */
+#define _PAGE_BASE	(_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_USER)
+
+#define PAGE_NONE		__pgprot(_PAGE_PROT_NONE | _PAGE_READ)
+#define PAGE_READ		__pgprot(_PAGE_BASE | _PAGE_READ)
+#define PAGE_WRITE		__pgprot(_PAGE_BASE | _PAGE_READ | _PAGE_WRITE)
+#define PAGE_EXEC		__pgprot(_PAGE_BASE | _PAGE_EXEC)
+#define PAGE_READ_EXEC		__pgprot(_PAGE_BASE | _PAGE_READ | _PAGE_EXEC)
+#define PAGE_WRITE_EXEC		__pgprot(_PAGE_BASE | _PAGE_READ |	\
+					 _PAGE_EXEC | _PAGE_WRITE)
+
+#define PAGE_COPY		PAGE_READ
+#define PAGE_COPY_EXEC		PAGE_READ_EXEC
+#define PAGE_SHARED		PAGE_WRITE
+#define PAGE_SHARED_EXEC	PAGE_WRITE_EXEC
+
+#define _PAGE_KERNEL		(_PAGE_READ \
+				| _PAGE_WRITE \
+				| _PAGE_PRESENT \
+				| _PAGE_ACCESSED \
+				| _PAGE_DIRTY \
+				| _PAGE_GLOBAL)
+
+#define PAGE_KERNEL		__pgprot(_PAGE_KERNEL)
+#define PAGE_KERNEL_READ	__pgprot(_PAGE_KERNEL & ~_PAGE_WRITE)
+#define PAGE_KERNEL_EXEC	__pgprot(_PAGE_KERNEL | _PAGE_EXEC)
+#define PAGE_KERNEL_READ_EXEC	__pgprot((_PAGE_KERNEL & ~_PAGE_WRITE) \
+					 | _PAGE_EXEC)
+
+#define PAGE_TABLE		__pgprot(_PAGE_TABLE)
+
+#define _PAGE_IOREMAP	((_PAGE_KERNEL & ~_PAGE_MTMASK) | _PAGE_IO)
+#define PAGE_KERNEL_IO		__pgprot(_PAGE_IOREMAP)
+
+extern pgd_t swapper_pg_dir[];
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline int pmd_present(pmd_t pmd)
+{
+	/*
+	 * Checking for _PAGE_LEAF is needed too because:
+	 * When splitting a THP, split_huge_page() will temporarily clear
+	 * the present bit, in this situation, pmd_present() and
+	 * pmd_trans_huge() still needs to return true.
+	 */
+	return (pmd_val(pmd) & (_PAGE_PRESENT | _PAGE_PROT_NONE | _PAGE_LEAF));
+}
+#else
+static inline int pmd_present(pmd_t pmd)
+{
+	return (pmd_val(pmd) & (_PAGE_PRESENT | _PAGE_PROT_NONE));
+}
+#endif
+
+static inline int pmd_none(pmd_t pmd)
+{
+	return (pmd_val(pmd) == 0);
+}
+
+static inline int pmd_bad(pmd_t pmd)
+{
+	return !pmd_present(pmd) || (pmd_val(pmd) & _PAGE_LEAF);
+}
+
+#define pmd_leaf	pmd_leaf
+static inline int pmd_leaf(pmd_t pmd)
+{
+	return pmd_present(pmd) && (pmd_val(pmd) & _PAGE_LEAF);
+}
+
+static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
+{
+	*pmdp = pmd;
+}
+
+static inline void pmd_clear(pmd_t *pmdp)
+{
+	set_pmd(pmdp, __pmd(0));
+}
+
+static inline pgd_t pfn_pgd(unsigned long pfn, pgprot_t prot)
+{
+	unsigned long prot_val = pgprot_val(prot);
+
+	ALT_THEAD_PMA(prot_val);
+
+	return __pgd((pfn << _PAGE_PFN_SHIFT) | prot_val);
+}
+
+static inline unsigned long _pgd_pfn(pgd_t pgd)
+{
+	return __page_val_to_pfn(pgd_val(pgd));
+}
+
+static inline struct page *pmd_page(pmd_t pmd)
+{
+	return pfn_to_page(__page_val_to_pfn(pmd_val(pmd)));
+}
+
+static inline unsigned long pmd_page_vaddr(pmd_t pmd)
+{
+	return (unsigned long)pfn_to_virt(__page_val_to_pfn(pmd_val(pmd)));
+}
+
+static inline pte_t pmd_pte(pmd_t pmd)
+{
+	return __pte(pmd_val(pmd));
+}
+
+static inline pte_t pud_pte(pud_t pud)
+{
+	return __pte(pud_val(pud));
+}
+
+/* Yields the page frame number (PFN) of a page table entry */
+static inline unsigned long pte_pfn(pte_t pte)
+{
+	return __page_val_to_pfn(pte_val(pte));
+}
+
+#define pte_page(x)     pfn_to_page(pte_pfn(x))
+
+/* Constructs a page table entry */
+static inline pte_t pfn_pte(unsigned long pfn, pgprot_t prot)
+{
+	unsigned long prot_val = pgprot_val(prot);
+
+	ALT_THEAD_PMA(prot_val);
+
+	return __pte((pfn << _PAGE_PFN_SHIFT) | prot_val);
+}
+
+#define mk_pte(page, prot)       pfn_pte(page_to_pfn(page), prot)
+
+static inline int pte_present(pte_t pte)
+{
+	return (pte_val(pte) & (_PAGE_PRESENT | _PAGE_PROT_NONE));
+}
+
+static inline int pte_none(pte_t pte)
+{
+	return (pte_val(pte) == 0);
+}
+
+static inline int pte_write(pte_t pte)
+{
+	return pte_val(pte) & _PAGE_WRITE;
+}
+
+static inline int pte_exec(pte_t pte)
+{
+	return pte_val(pte) & _PAGE_EXEC;
+}
+
+static inline int pte_user(pte_t pte)
+{
+	return pte_val(pte) & _PAGE_USER;
+}
+
+static inline int pte_huge(pte_t pte)
+{
+	return pte_present(pte) && (pte_val(pte) & _PAGE_LEAF);
+}
+
+static inline int pte_dirty(pte_t pte)
+{
+	return pte_val(pte) & _PAGE_DIRTY;
+}
+
+static inline int pte_young(pte_t pte)
+{
+	return pte_val(pte) & _PAGE_ACCESSED;
+}
+
+static inline int pte_special(pte_t pte)
+{
+	return pte_val(pte) & _PAGE_SPECIAL;
+}
+
+/* static inline pte_t pte_rdprotect(pte_t pte) */
+
+static inline pte_t pte_wrprotect(pte_t pte)
+{
+	return __pte(pte_val(pte) & ~(_PAGE_WRITE));
+}
+
+/* static inline pte_t pte_mkread(pte_t pte) */
+
+static inline pte_t pte_mkwrite(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_WRITE);
+}
+
+/* static inline pte_t pte_mkexec(pte_t pte) */
+
+static inline pte_t pte_mkdirty(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_DIRTY);
+}
+
+static inline pte_t pte_mkclean(pte_t pte)
+{
+	return __pte(pte_val(pte) & ~(_PAGE_DIRTY));
+}
+
+static inline pte_t pte_mkyoung(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_ACCESSED);
+}
+
+static inline pte_t pte_mkold(pte_t pte)
+{
+	return __pte(pte_val(pte) & ~(_PAGE_ACCESSED));
+}
+
+static inline pte_t pte_mkspecial(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_SPECIAL);
+}
+
+static inline pte_t pte_mkhuge(pte_t pte)
+{
+	return pte;
+}
+
+#ifdef CONFIG_NUMA_BALANCING
+/*
+ * See the comment in include/asm-generic/pgtable.h
+ */
+static inline int pte_protnone(pte_t pte)
+{
+	return (pte_val(pte) & (_PAGE_PRESENT | _PAGE_PROT_NONE)) == _PAGE_PROT_NONE;
+}
+
+static inline int pmd_protnone(pmd_t pmd)
+{
+	return pte_protnone(pmd_pte(pmd));
+}
+#endif
+
+/* Modify page protection bits */
+static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
+{
+	unsigned long newprot_val = pgprot_val(newprot);
+
+	ALT_THEAD_PMA(newprot_val);
+
+	return __pte((pte_val(pte) & _PAGE_CHG_MASK) | newprot_val);
+}
+
+#define pgd_ERROR(e) \
+	pr_err("%s:%d: bad pgd " PTE_FMT ".\n", __FILE__, __LINE__, pgd_val(e))
+
+
+/* Commit new configuration to MMU hardware */
+static inline void update_mmu_cache(struct vm_area_struct *vma,
+	unsigned long address, pte_t *ptep)
+{
+	/*
+	 * The kernel assumes that TLBs don't cache invalid entries, but
+	 * in RISC-V, SFENCE.VMA specifies an ordering constraint, not a
+	 * cache flush; it is necessary even after writing invalid entries.
+	 * Relying on flush_tlb_fix_spurious_fault would suffice, but
+	 * the extra traps reduce performance.  So, eagerly SFENCE.VMA.
+	 */
+	local_flush_tlb_page(address);
+}
+
+static inline void update_mmu_cache_pmd(struct vm_area_struct *vma,
+		unsigned long address, pmd_t *pmdp)
+{
+	pte_t *ptep = (pte_t *)pmdp;
+
+	update_mmu_cache(vma, address, ptep);
+}
+
+#define __HAVE_ARCH_PTE_SAME
+static inline int pte_same(pte_t pte_a, pte_t pte_b)
+{
+	return pte_val(pte_a) == pte_val(pte_b);
+}
+
+/*
+ * Certain architectures need to do special things when PTEs within
+ * a page table are directly modified.  Thus, the following hook is
+ * made available.
+ */
+static inline void set_pte(pte_t *ptep, pte_t pteval)
+{
+	*ptep = pteval;
+}
+
+void flush_icache_pte(pte_t pte);
+
+static inline void __set_pte_at(struct mm_struct *mm,
+	unsigned long addr, pte_t *ptep, pte_t pteval)
+{
+	if (pte_present(pteval) && pte_exec(pteval))
+		flush_icache_pte(pteval);
+
+	set_pte(ptep, pteval);
+}
+
+static inline void set_pte_at(struct mm_struct *mm,
+	unsigned long addr, pte_t *ptep, pte_t pteval)
+{
+	page_table_check_pte_set(mm, addr, ptep, pteval);
+	__set_pte_at(mm, addr, ptep, pteval);
+}
+
+static inline void pte_clear(struct mm_struct *mm,
+	unsigned long addr, pte_t *ptep)
+{
+	__set_pte_at(mm, addr, ptep, __pte(0));
+}
+
+#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
+static inline int ptep_set_access_flags(struct vm_area_struct *vma,
+					unsigned long address, pte_t *ptep,
+					pte_t entry, int dirty)
+{
+	if (!pte_same(*ptep, entry))
+		set_pte_at(vma->vm_mm, address, ptep, entry);
+	/*
+	 * update_mmu_cache will unconditionally execute, handling both
+	 * the case that the PTE changed and the spurious fault case.
+	 */
+	return true;
+}
+
+#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
+static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
+				       unsigned long address, pte_t *ptep)
+{
+	pte_t pte = __pte(atomic_long_xchg((atomic_long_t *)ptep, 0));
+
+	page_table_check_pte_clear(mm, address, pte);
+
+	return pte;
+}
+
+#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
+static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
+					    unsigned long address,
+					    pte_t *ptep)
+{
+	if (!pte_young(*ptep))
+		return 0;
+	return test_and_clear_bit(_PAGE_ACCESSED_OFFSET, &pte_val(*ptep));
+}
+
+#define __HAVE_ARCH_PTEP_SET_WRPROTECT
+static inline void ptep_set_wrprotect(struct mm_struct *mm,
+				      unsigned long address, pte_t *ptep)
+{
+	atomic_long_and(~(unsigned long)_PAGE_WRITE, (atomic_long_t *)ptep);
+}
+
+#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
+static inline int ptep_clear_flush_young(struct vm_area_struct *vma,
+					 unsigned long address, pte_t *ptep)
+{
+	/*
+	 * This comment is borrowed from x86, but applies equally to RISC-V:
+	 *
+	 * Clearing the accessed bit without a TLB flush
+	 * doesn't cause data corruption. [ It could cause incorrect
+	 * page aging and the (mistaken) reclaim of hot pages, but the
+	 * chance of that should be relatively low. ]
+	 *
+	 * So as a performance optimization don't flush the TLB when
+	 * clearing the accessed bit, it will eventually be flushed by
+	 * a context switch or a VM operation anyway. [ In the rare
+	 * event of it not getting flushed for a long time the delay
+	 * shouldn't really matter because there's no real memory
+	 * pressure for swapout to react to. ]
+	 */
+	return ptep_test_and_clear_young(vma, address, ptep);
+}
+
+#define pgprot_noncached pgprot_noncached
+static inline pgprot_t pgprot_noncached(pgprot_t _prot)
+{
+	unsigned long prot = pgprot_val(_prot);
+
+	prot &= ~_PAGE_MTMASK;
+	prot |= _PAGE_IO;
+
+	return __pgprot(prot);
+}
+
+#define pgprot_writecombine pgprot_writecombine
+static inline pgprot_t pgprot_writecombine(pgprot_t _prot)
+{
+	unsigned long prot = pgprot_val(_prot);
+
+	prot &= ~_PAGE_MTMASK;
+	prot |= _PAGE_NOCACHE;
+
+	return __pgprot(prot);
+}
+
+/*
+ * THP functions
+ */
+static inline pmd_t pte_pmd(pte_t pte)
+{
+	return __pmd(pte_val(pte));
+}
+
+static inline pmd_t pmd_mkhuge(pmd_t pmd)
+{
+	return pmd;
+}
+
+static inline pmd_t pmd_mkinvalid(pmd_t pmd)
+{
+	return __pmd(pmd_val(pmd) & ~(_PAGE_PRESENT|_PAGE_PROT_NONE));
+}
+
+#define __pmd_to_phys(pmd)  (__page_val_to_pfn(pmd_val(pmd)) << PAGE_SHIFT)
+
+static inline unsigned long pmd_pfn(pmd_t pmd)
+{
+	return ((__pmd_to_phys(pmd) & PMD_MASK) >> PAGE_SHIFT);
+}
+
+#define __pud_to_phys(pud)  (__page_val_to_pfn(pud_val(pud)) << PAGE_SHIFT)
+
+static inline unsigned long pud_pfn(pud_t pud)
+{
+	return ((__pud_to_phys(pud) & PUD_MASK) >> PAGE_SHIFT);
+}
+
+static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
+{
+	return pte_pmd(pte_modify(pmd_pte(pmd), newprot));
+}
+
+#define pmd_write pmd_write
+static inline int pmd_write(pmd_t pmd)
+{
+	return pte_write(pmd_pte(pmd));
+}
+
+static inline int pmd_dirty(pmd_t pmd)
+{
+	return pte_dirty(pmd_pte(pmd));
+}
+
+#define pmd_young pmd_young
+static inline int pmd_young(pmd_t pmd)
+{
+	return pte_young(pmd_pte(pmd));
+}
+
+static inline int pmd_user(pmd_t pmd)
+{
+	return pte_user(pmd_pte(pmd));
+}
+
+static inline pmd_t pmd_mkold(pmd_t pmd)
+{
+	return pte_pmd(pte_mkold(pmd_pte(pmd)));
+}
+
+static inline pmd_t pmd_mkyoung(pmd_t pmd)
+{
+	return pte_pmd(pte_mkyoung(pmd_pte(pmd)));
+}
+
+static inline pmd_t pmd_mkwrite(pmd_t pmd)
+{
+	return pte_pmd(pte_mkwrite(pmd_pte(pmd)));
+}
+
+static inline pmd_t pmd_wrprotect(pmd_t pmd)
+{
+	return pte_pmd(pte_wrprotect(pmd_pte(pmd)));
+}
+
+static inline pmd_t pmd_mkclean(pmd_t pmd)
+{
+	return pte_pmd(pte_mkclean(pmd_pte(pmd)));
+}
+
+static inline pmd_t pmd_mkdirty(pmd_t pmd)
+{
+	return pte_pmd(pte_mkdirty(pmd_pte(pmd)));
+}
+
+static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
+				pmd_t *pmdp, pmd_t pmd)
+{
+	page_table_check_pmd_set(mm, addr, pmdp, pmd);
+	return __set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd));
+}
+
+static inline void set_pud_at(struct mm_struct *mm, unsigned long addr,
+				pud_t *pudp, pud_t pud)
+{
+	page_table_check_pud_set(mm, addr, pudp, pud);
+	return __set_pte_at(mm, addr, (pte_t *)pudp, pud_pte(pud));
+}
+
+#ifdef CONFIG_PAGE_TABLE_CHECK
+static inline bool pte_user_accessible_page(pte_t pte)
+{
+	return pte_present(pte) && pte_user(pte);
+}
+
+static inline bool pmd_user_accessible_page(pmd_t pmd)
+{
+	return pmd_leaf(pmd) && pmd_user(pmd);
+}
+
+static inline bool pud_user_accessible_page(pud_t pud)
+{
+	return pud_leaf(pud) && pud_user(pud);
+}
+#endif
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline int pmd_trans_huge(pmd_t pmd)
+{
+	return pmd_leaf(pmd);
+}
+
+#define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS
+static inline int pmdp_set_access_flags(struct vm_area_struct *vma,
+					unsigned long address, pmd_t *pmdp,
+					pmd_t entry, int dirty)
+{
+	return ptep_set_access_flags(vma, address, (pte_t *)pmdp, pmd_pte(entry), dirty);
+}
+
+#define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
+static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
+					unsigned long address, pmd_t *pmdp)
+{
+	return ptep_test_and_clear_young(vma, address, (pte_t *)pmdp);
+}
+
+#define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
+static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
+					unsigned long address, pmd_t *pmdp)
+{
+	pmd_t pmd = __pmd(atomic_long_xchg((atomic_long_t *)pmdp, 0));
+
+	page_table_check_pmd_clear(mm, address, pmd);
+
+	return pmd;
+}
+
+#define __HAVE_ARCH_PMDP_SET_WRPROTECT
+static inline void pmdp_set_wrprotect(struct mm_struct *mm,
+					unsigned long address, pmd_t *pmdp)
+{
+	ptep_set_wrprotect(mm, address, (pte_t *)pmdp);
+}
+
+#define pmdp_establish pmdp_establish
+static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
+				unsigned long address, pmd_t *pmdp, pmd_t pmd)
+{
+	page_table_check_pmd_set(vma->vm_mm, address, pmdp, pmd);
+	return __pmd(atomic_long_xchg((atomic_long_t *)pmdp, pmd_val(pmd)));
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
+/*
+ * Encode and decode a swap entry
+ *
+ * Format of swap PTE:
+ *	bit            0:	_PAGE_PRESENT (zero)
+ *	bit       1 to 3:       _PAGE_LEAF (zero)
+ *	bit            5:	_PAGE_PROT_NONE (zero)
+ *	bits      6 to 10:	swap type
+ *	bits 10 to XLEN-1:	swap offset
+ */
+#define __SWP_TYPE_SHIFT	6
+#define __SWP_TYPE_BITS		5
+#define __SWP_TYPE_MASK		((1UL << __SWP_TYPE_BITS) - 1)
+#define __SWP_OFFSET_SHIFT	(__SWP_TYPE_BITS + __SWP_TYPE_SHIFT)
+
+#define MAX_SWAPFILES_CHECK()	\
+	BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > __SWP_TYPE_BITS)
+
+#define __swp_type(x)	(((x).val >> __SWP_TYPE_SHIFT) & __SWP_TYPE_MASK)
+#define __swp_offset(x)	((x).val >> __SWP_OFFSET_SHIFT)
+#define __swp_entry(type, offset) ((swp_entry_t) \
+	{ ((type) << __SWP_TYPE_SHIFT) | ((offset) << __SWP_OFFSET_SHIFT) })
+
+#define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val(pte) })
+#define __swp_entry_to_pte(x)	((pte_t) { (x).val })
+
+#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
+#define __pmd_to_swp_entry(pmd) ((swp_entry_t) { pmd_val(pmd) })
+#define __swp_entry_to_pmd(swp) __pmd((swp).val)
+#endif /* CONFIG_ARCH_ENABLE_THP_MIGRATION */
+
+/*
+ * In the RV64 Linux scheme, we give the user half of the virtual-address space
+ * and give the kernel the other (upper) half.
+ */
+#ifdef CONFIG_64BIT
+#define KERN_VIRT_START	(-(BIT(VA_BITS)) + TASK_SIZE)
+#else
+#define KERN_VIRT_START	FIXADDR_START
+#endif
+
+/*
+ * Task size is 0x4000000000 for RV64 or 0x9fc00000 for RV32.
+ * Note that PGDIR_SIZE must evenly divide TASK_SIZE.
+ * Task size is:
+ * -     0x9fc00000 (~2.5GB) for RV32.
+ * -   0x4000000000 ( 256GB) for RV64 using SV39 mmu
+ * - 0x800000000000 ( 128TB) for RV64 using SV48 mmu
+ *
+ * Note that PGDIR_SIZE must evenly divide TASK_SIZE since "RISC-V
+ * Instruction Set Manual Volume II: Privileged Architecture" states that
+ * "load and store effective addresses, which are 64bits, must have bits
+ * 63–48 all equal to bit 47, or else a page-fault exception will occur."
+ */
+#ifdef CONFIG_64BIT
+#define TASK_SIZE_64	(PGDIR_SIZE * PTRS_PER_PGD / 2)
+#define TASK_SIZE_MIN	(PGDIR_SIZE_L3 * PTRS_PER_PGD / 2)
+
+#ifdef CONFIG_COMPAT
+#define TASK_SIZE_32	(_AC(0x80000000, UL) - PAGE_SIZE)
+#define TASK_SIZE	(test_thread_flag(TIF_32BIT) ? \
+			 TASK_SIZE_32 : TASK_SIZE_64)
+#else
+#define TASK_SIZE	TASK_SIZE_64
+#endif
+
+#else
+#define TASK_SIZE	FIXADDR_START
+#define TASK_SIZE_MIN	TASK_SIZE
+#endif
+
+#else /* CONFIG_MMU */
+
+#define PAGE_SHARED		__pgprot(0)
+#define PAGE_KERNEL		__pgprot(0)
+#define swapper_pg_dir		NULL
+#define TASK_SIZE		0xffffffffUL
+#define VMALLOC_START		0
+#define VMALLOC_END		TASK_SIZE
+
+#endif /* !CONFIG_MMU */
+
+#define kern_addr_valid(addr)   (1) /* FIXME */
+
+extern char _start[];
+extern void *_dtb_early_va;
+extern uintptr_t _dtb_early_pa;
+#if defined(CONFIG_XIP_KERNEL) && defined(CONFIG_MMU)
+#define dtb_early_va	(*(void **)XIP_FIXUP(&_dtb_early_va))
+#define dtb_early_pa	(*(uintptr_t *)XIP_FIXUP(&_dtb_early_pa))
+#else
+#define dtb_early_va	_dtb_early_va
+#define dtb_early_pa	_dtb_early_pa
+#endif /* CONFIG_XIP_KERNEL */
+extern u64 satp_mode;
+extern bool pgtable_l4_enabled;
+
+void paging_init(void);
+void misc_mem_init(void);
+
+/*
+ * ZERO_PAGE is a global shared page that is always zero,
+ * used for zero-mapped memory areas, etc.
+ */
+extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
+#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* _ASM_RISCV_PGTABLE_H */
diff --git a/arch/riscv/include/asm/probes.h b/arch/riscv/include/asm/probes.h
new file mode 100644
index 000000000..a787e6d53
--- /dev/null
+++ b/arch/riscv/include/asm/probes.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _ASM_RISCV_PROBES_H
+#define _ASM_RISCV_PROBES_H
+
+typedef u32 probe_opcode_t;
+typedef bool (probes_handler_t) (u32 opcode, unsigned long addr, struct pt_regs *);
+
+/* architecture specific copy of original instruction */
+struct arch_probe_insn {
+	probe_opcode_t *insn;
+	probes_handler_t *handler;
+	/* restore address after simulation */
+	unsigned long restore;
+};
+
+#ifdef CONFIG_KPROBES
+typedef u32 kprobe_opcode_t;
+struct arch_specific_insn {
+	struct arch_probe_insn api;
+};
+#endif
+
+#endif /* _ASM_RISCV_PROBES_H */
diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h
new file mode 100644
index 000000000..94a0590c6
--- /dev/null
+++ b/arch/riscv/include/asm/processor.h
@@ -0,0 +1,85 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ */
+
+#ifndef _ASM_RISCV_PROCESSOR_H
+#define _ASM_RISCV_PROCESSOR_H
+
+#include <linux/const.h>
+
+#include <vdso/processor.h>
+
+#include <asm/ptrace.h>
+
+/*
+ * This decides where the kernel will search for a free chunk of vm
+ * space during mmap's.
+ */
+#define TASK_UNMAPPED_BASE	PAGE_ALIGN(TASK_SIZE / 3)
+
+#define STACK_TOP		TASK_SIZE
+#ifdef CONFIG_64BIT
+#define STACK_TOP_MAX		TASK_SIZE_64
+#else
+#define STACK_TOP_MAX		TASK_SIZE
+#endif
+#define STACK_ALIGN		16
+
+#ifndef __ASSEMBLY__
+
+struct task_struct;
+struct pt_regs;
+
+/* CPU-specific state of a task */
+struct thread_struct {
+	/* Callee-saved registers */
+	unsigned long ra;
+	unsigned long sp;	/* Kernel mode stack */
+	unsigned long s[12];	/* s[0]: frame pointer */
+	struct __riscv_d_ext_state fstate;
+	unsigned long bad_cause;
+};
+
+/* Whitelist the fstate from the task_struct for hardened usercopy */
+static inline void arch_thread_struct_whitelist(unsigned long *offset,
+						unsigned long *size)
+{
+	*offset = offsetof(struct thread_struct, fstate);
+	*size = sizeof_field(struct thread_struct, fstate);
+}
+
+#define INIT_THREAD {					\
+	.sp = sizeof(init_stack) + (long)&init_stack,	\
+}
+
+#define task_pt_regs(tsk)						\
+	((struct pt_regs *)(task_stack_page(tsk) + THREAD_SIZE		\
+			    - ALIGN(sizeof(struct pt_regs), STACK_ALIGN)))
+
+#define KSTK_EIP(tsk)		(task_pt_regs(tsk)->epc)
+#define KSTK_ESP(tsk)		(task_pt_regs(tsk)->sp)
+
+
+/* Do necessary setup to start up a newly executed thread. */
+extern void start_thread(struct pt_regs *regs,
+			unsigned long pc, unsigned long sp);
+
+extern unsigned long __get_wchan(struct task_struct *p);
+
+
+static inline void wait_for_interrupt(void)
+{
+	__asm__ __volatile__ ("wfi");
+}
+
+struct device_node;
+int riscv_of_processor_hartid(struct device_node *node, unsigned long *hartid);
+int riscv_of_parent_hartid(struct device_node *node, unsigned long *hartid);
+
+extern void riscv_fill_hwcap(void);
+extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_RISCV_PROCESSOR_H */
diff --git a/arch/riscv/include/asm/ptdump.h b/arch/riscv/include/asm/ptdump.h
new file mode 100644
index 000000000..3c9ea6dd5
--- /dev/null
+++ b/arch/riscv/include/asm/ptdump.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2019 SiFive
+ */
+
+#ifndef _ASM_RISCV_PTDUMP_H
+#define _ASM_RISCV_PTDUMP_H
+
+void ptdump_check_wx(void);
+
+#ifdef CONFIG_DEBUG_WX
+static inline void debug_checkwx(void)
+{
+	ptdump_check_wx();
+}
+#else
+static inline void debug_checkwx(void)
+{
+}
+#endif
+
+#endif /* _ASM_RISCV_PTDUMP_H */
diff --git a/arch/riscv/include/asm/ptrace.h b/arch/riscv/include/asm/ptrace.h
new file mode 100644
index 000000000..6ecd46112
--- /dev/null
+++ b/arch/riscv/include/asm/ptrace.h
@@ -0,0 +1,177 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ */
+
+#ifndef _ASM_RISCV_PTRACE_H
+#define _ASM_RISCV_PTRACE_H
+
+#include <uapi/asm/ptrace.h>
+#include <asm/csr.h>
+#include <linux/compiler.h>
+
+#ifndef __ASSEMBLY__
+
+struct pt_regs {
+	unsigned long epc;
+	unsigned long ra;
+	unsigned long sp;
+	unsigned long gp;
+	unsigned long tp;
+	unsigned long t0;
+	unsigned long t1;
+	unsigned long t2;
+	unsigned long s0;
+	unsigned long s1;
+	unsigned long a0;
+	unsigned long a1;
+	unsigned long a2;
+	unsigned long a3;
+	unsigned long a4;
+	unsigned long a5;
+	unsigned long a6;
+	unsigned long a7;
+	unsigned long s2;
+	unsigned long s3;
+	unsigned long s4;
+	unsigned long s5;
+	unsigned long s6;
+	unsigned long s7;
+	unsigned long s8;
+	unsigned long s9;
+	unsigned long s10;
+	unsigned long s11;
+	unsigned long t3;
+	unsigned long t4;
+	unsigned long t5;
+	unsigned long t6;
+	/* Supervisor/Machine CSRs */
+	unsigned long status;
+	unsigned long badaddr;
+	unsigned long cause;
+	/* a0 value before the syscall */
+	unsigned long orig_a0;
+};
+
+#ifdef CONFIG_64BIT
+#define REG_FMT "%016lx"
+#else
+#define REG_FMT "%08lx"
+#endif
+
+#define user_mode(regs) (((regs)->status & SR_PP) == 0)
+
+#define MAX_REG_OFFSET offsetof(struct pt_regs, orig_a0)
+
+/* Helpers for working with the instruction pointer */
+static inline unsigned long instruction_pointer(struct pt_regs *regs)
+{
+	return regs->epc;
+}
+static inline void instruction_pointer_set(struct pt_regs *regs,
+					   unsigned long val)
+{
+	regs->epc = val;
+}
+
+#define profile_pc(regs) instruction_pointer(regs)
+
+/* Helpers for working with the user stack pointer */
+static inline unsigned long user_stack_pointer(struct pt_regs *regs)
+{
+	return regs->sp;
+}
+static inline void user_stack_pointer_set(struct pt_regs *regs,
+					  unsigned long val)
+{
+	regs->sp =  val;
+}
+
+/* Valid only for Kernel mode traps. */
+static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
+{
+	return regs->sp;
+}
+
+/* Helpers for working with the frame pointer */
+static inline unsigned long frame_pointer(struct pt_regs *regs)
+{
+	return regs->s0;
+}
+static inline void frame_pointer_set(struct pt_regs *regs,
+				     unsigned long val)
+{
+	regs->s0 = val;
+}
+
+static inline unsigned long regs_return_value(struct pt_regs *regs)
+{
+	return regs->a0;
+}
+
+static inline void regs_set_return_value(struct pt_regs *regs,
+					 unsigned long val)
+{
+	regs->a0 = val;
+}
+
+extern int regs_query_register_offset(const char *name);
+extern unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs,
+					       unsigned int n);
+
+void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
+			   unsigned long frame_pointer);
+int do_syscall_trace_enter(struct pt_regs *regs);
+void do_syscall_trace_exit(struct pt_regs *regs);
+
+/**
+ * regs_get_register() - get register value from its offset
+ * @regs:	pt_regs from which register value is gotten
+ * @offset:	offset of the register.
+ *
+ * regs_get_register returns the value of a register whose offset from @regs.
+ * The @offset is the offset of the register in struct pt_regs.
+ * If @offset is bigger than MAX_REG_OFFSET, this returns 0.
+ */
+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);
+}
+
+/**
+ * regs_get_kernel_argument() - get Nth function argument in kernel
+ * @regs:       pt_regs of that context
+ * @n:          function argument number (start from 0)
+ *
+ * regs_get_argument() returns @n th argument of the function call.
+ *
+ * Note you can get the parameter correctly if the function has no
+ * more than eight arguments.
+ */
+static inline unsigned long regs_get_kernel_argument(struct pt_regs *regs,
+						unsigned int n)
+{
+	static const int nr_reg_arguments = 8;
+	static const unsigned int argument_offs[] = {
+		offsetof(struct pt_regs, a0),
+		offsetof(struct pt_regs, a1),
+		offsetof(struct pt_regs, a2),
+		offsetof(struct pt_regs, a3),
+		offsetof(struct pt_regs, a4),
+		offsetof(struct pt_regs, a5),
+		offsetof(struct pt_regs, a6),
+		offsetof(struct pt_regs, a7),
+	};
+
+	if (n < nr_reg_arguments)
+		return regs_get_register(regs, argument_offs[n]);
+	return 0;
+}
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_RISCV_PTRACE_H */
diff --git a/arch/riscv/include/asm/sbi.h b/arch/riscv/include/asm/sbi.h
new file mode 100644
index 000000000..9baddaee5
--- /dev/null
+++ b/arch/riscv/include/asm/sbi.h
@@ -0,0 +1,330 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2015 Regents of the University of California
+ * Copyright (c) 2020 Western Digital Corporation or its affiliates.
+ */
+
+#ifndef _ASM_RISCV_SBI_H
+#define _ASM_RISCV_SBI_H
+
+#include <linux/types.h>
+#include <linux/cpumask.h>
+
+#ifdef CONFIG_RISCV_SBI
+enum sbi_ext_id {
+#ifdef CONFIG_RISCV_SBI_V01
+	SBI_EXT_0_1_SET_TIMER = 0x0,
+	SBI_EXT_0_1_CONSOLE_PUTCHAR = 0x1,
+	SBI_EXT_0_1_CONSOLE_GETCHAR = 0x2,
+	SBI_EXT_0_1_CLEAR_IPI = 0x3,
+	SBI_EXT_0_1_SEND_IPI = 0x4,
+	SBI_EXT_0_1_REMOTE_FENCE_I = 0x5,
+	SBI_EXT_0_1_REMOTE_SFENCE_VMA = 0x6,
+	SBI_EXT_0_1_REMOTE_SFENCE_VMA_ASID = 0x7,
+	SBI_EXT_0_1_SHUTDOWN = 0x8,
+#endif
+	SBI_EXT_BASE = 0x10,
+	SBI_EXT_TIME = 0x54494D45,
+	SBI_EXT_IPI = 0x735049,
+	SBI_EXT_RFENCE = 0x52464E43,
+	SBI_EXT_HSM = 0x48534D,
+	SBI_EXT_SRST = 0x53525354,
+	SBI_EXT_PMU = 0x504D55,
+
+	/* Experimentals extensions must lie within this range */
+	SBI_EXT_EXPERIMENTAL_START = 0x08000000,
+	SBI_EXT_EXPERIMENTAL_END = 0x08FFFFFF,
+
+	/* Vendor extensions must lie within this range */
+	SBI_EXT_VENDOR_START = 0x09000000,
+	SBI_EXT_VENDOR_END = 0x09FFFFFF,
+};
+
+enum sbi_ext_base_fid {
+	SBI_EXT_BASE_GET_SPEC_VERSION = 0,
+	SBI_EXT_BASE_GET_IMP_ID,
+	SBI_EXT_BASE_GET_IMP_VERSION,
+	SBI_EXT_BASE_PROBE_EXT,
+	SBI_EXT_BASE_GET_MVENDORID,
+	SBI_EXT_BASE_GET_MARCHID,
+	SBI_EXT_BASE_GET_MIMPID,
+};
+
+enum sbi_ext_time_fid {
+	SBI_EXT_TIME_SET_TIMER = 0,
+};
+
+enum sbi_ext_ipi_fid {
+	SBI_EXT_IPI_SEND_IPI = 0,
+};
+
+enum sbi_ext_rfence_fid {
+	SBI_EXT_RFENCE_REMOTE_FENCE_I = 0,
+	SBI_EXT_RFENCE_REMOTE_SFENCE_VMA,
+	SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID,
+	SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA_VMID,
+	SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA,
+	SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA_ASID,
+	SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA,
+};
+
+enum sbi_ext_hsm_fid {
+	SBI_EXT_HSM_HART_START = 0,
+	SBI_EXT_HSM_HART_STOP,
+	SBI_EXT_HSM_HART_STATUS,
+	SBI_EXT_HSM_HART_SUSPEND,
+};
+
+enum sbi_hsm_hart_state {
+	SBI_HSM_STATE_STARTED = 0,
+	SBI_HSM_STATE_STOPPED,
+	SBI_HSM_STATE_START_PENDING,
+	SBI_HSM_STATE_STOP_PENDING,
+	SBI_HSM_STATE_SUSPENDED,
+	SBI_HSM_STATE_SUSPEND_PENDING,
+	SBI_HSM_STATE_RESUME_PENDING,
+};
+
+#define SBI_HSM_SUSP_BASE_MASK			0x7fffffff
+#define SBI_HSM_SUSP_NON_RET_BIT		0x80000000
+#define SBI_HSM_SUSP_PLAT_BASE			0x10000000
+
+#define SBI_HSM_SUSPEND_RET_DEFAULT		0x00000000
+#define SBI_HSM_SUSPEND_RET_PLATFORM		SBI_HSM_SUSP_PLAT_BASE
+#define SBI_HSM_SUSPEND_RET_LAST		SBI_HSM_SUSP_BASE_MASK
+#define SBI_HSM_SUSPEND_NON_RET_DEFAULT		SBI_HSM_SUSP_NON_RET_BIT
+#define SBI_HSM_SUSPEND_NON_RET_PLATFORM	(SBI_HSM_SUSP_NON_RET_BIT | \
+						 SBI_HSM_SUSP_PLAT_BASE)
+#define SBI_HSM_SUSPEND_NON_RET_LAST		(SBI_HSM_SUSP_NON_RET_BIT | \
+						 SBI_HSM_SUSP_BASE_MASK)
+
+enum sbi_ext_srst_fid {
+	SBI_EXT_SRST_RESET = 0,
+};
+
+enum sbi_srst_reset_type {
+	SBI_SRST_RESET_TYPE_SHUTDOWN = 0,
+	SBI_SRST_RESET_TYPE_COLD_REBOOT,
+	SBI_SRST_RESET_TYPE_WARM_REBOOT,
+};
+
+enum sbi_srst_reset_reason {
+	SBI_SRST_RESET_REASON_NONE = 0,
+	SBI_SRST_RESET_REASON_SYS_FAILURE,
+};
+
+enum sbi_ext_pmu_fid {
+	SBI_EXT_PMU_NUM_COUNTERS = 0,
+	SBI_EXT_PMU_COUNTER_GET_INFO,
+	SBI_EXT_PMU_COUNTER_CFG_MATCH,
+	SBI_EXT_PMU_COUNTER_START,
+	SBI_EXT_PMU_COUNTER_STOP,
+	SBI_EXT_PMU_COUNTER_FW_READ,
+};
+
+union sbi_pmu_ctr_info {
+	unsigned long value;
+	struct {
+		unsigned long csr:12;
+		unsigned long width:6;
+#if __riscv_xlen == 32
+		unsigned long reserved:13;
+#else
+		unsigned long reserved:45;
+#endif
+		unsigned long type:1;
+	};
+};
+
+#define RISCV_PMU_RAW_EVENT_MASK GENMASK_ULL(47, 0)
+#define RISCV_PMU_RAW_EVENT_IDX 0x20000
+
+/** General pmu event codes specified in SBI PMU extension */
+enum sbi_pmu_hw_generic_events_t {
+	SBI_PMU_HW_NO_EVENT			= 0,
+	SBI_PMU_HW_CPU_CYCLES			= 1,
+	SBI_PMU_HW_INSTRUCTIONS			= 2,
+	SBI_PMU_HW_CACHE_REFERENCES		= 3,
+	SBI_PMU_HW_CACHE_MISSES			= 4,
+	SBI_PMU_HW_BRANCH_INSTRUCTIONS		= 5,
+	SBI_PMU_HW_BRANCH_MISSES		= 6,
+	SBI_PMU_HW_BUS_CYCLES			= 7,
+	SBI_PMU_HW_STALLED_CYCLES_FRONTEND	= 8,
+	SBI_PMU_HW_STALLED_CYCLES_BACKEND	= 9,
+	SBI_PMU_HW_REF_CPU_CYCLES		= 10,
+
+	SBI_PMU_HW_GENERAL_MAX,
+};
+
+/**
+ * Special "firmware" events provided by the firmware, even if the hardware
+ * does not support performance events. These events are encoded as a raw
+ * event type in Linux kernel perf framework.
+ */
+enum sbi_pmu_fw_generic_events_t {
+	SBI_PMU_FW_MISALIGNED_LOAD	= 0,
+	SBI_PMU_FW_MISALIGNED_STORE	= 1,
+	SBI_PMU_FW_ACCESS_LOAD		= 2,
+	SBI_PMU_FW_ACCESS_STORE		= 3,
+	SBI_PMU_FW_ILLEGAL_INSN		= 4,
+	SBI_PMU_FW_SET_TIMER		= 5,
+	SBI_PMU_FW_IPI_SENT		= 6,
+	SBI_PMU_FW_IPI_RECVD		= 7,
+	SBI_PMU_FW_FENCE_I_SENT		= 8,
+	SBI_PMU_FW_FENCE_I_RECVD	= 9,
+	SBI_PMU_FW_SFENCE_VMA_SENT	= 10,
+	SBI_PMU_FW_SFENCE_VMA_RCVD	= 11,
+	SBI_PMU_FW_SFENCE_VMA_ASID_SENT	= 12,
+	SBI_PMU_FW_SFENCE_VMA_ASID_RCVD	= 13,
+
+	SBI_PMU_FW_HFENCE_GVMA_SENT	= 14,
+	SBI_PMU_FW_HFENCE_GVMA_RCVD	= 15,
+	SBI_PMU_FW_HFENCE_GVMA_VMID_SENT = 16,
+	SBI_PMU_FW_HFENCE_GVMA_VMID_RCVD = 17,
+
+	SBI_PMU_FW_HFENCE_VVMA_SENT	= 18,
+	SBI_PMU_FW_HFENCE_VVMA_RCVD	= 19,
+	SBI_PMU_FW_HFENCE_VVMA_ASID_SENT = 20,
+	SBI_PMU_FW_HFENCE_VVMA_ASID_RCVD = 21,
+	SBI_PMU_FW_MAX,
+};
+
+/* SBI PMU event types */
+enum sbi_pmu_event_type {
+	SBI_PMU_EVENT_TYPE_HW = 0x0,
+	SBI_PMU_EVENT_TYPE_CACHE = 0x1,
+	SBI_PMU_EVENT_TYPE_RAW = 0x2,
+	SBI_PMU_EVENT_TYPE_FW = 0xf,
+};
+
+/* SBI PMU event types */
+enum sbi_pmu_ctr_type {
+	SBI_PMU_CTR_TYPE_HW = 0x0,
+	SBI_PMU_CTR_TYPE_FW,
+};
+
+/* Helper macros to decode event idx */
+#define SBI_PMU_EVENT_IDX_OFFSET 20
+#define SBI_PMU_EVENT_IDX_MASK 0xFFFFF
+#define SBI_PMU_EVENT_IDX_CODE_MASK 0xFFFF
+#define SBI_PMU_EVENT_IDX_TYPE_MASK 0xF0000
+#define SBI_PMU_EVENT_RAW_IDX 0x20000
+#define SBI_PMU_FIXED_CTR_MASK 0x07
+
+#define SBI_PMU_EVENT_CACHE_ID_CODE_MASK 0xFFF8
+#define SBI_PMU_EVENT_CACHE_OP_ID_CODE_MASK 0x06
+#define SBI_PMU_EVENT_CACHE_RESULT_ID_CODE_MASK 0x01
+
+#define SBI_PMU_EVENT_IDX_INVALID 0xFFFFFFFF
+
+/* Flags defined for config matching function */
+#define SBI_PMU_CFG_FLAG_SKIP_MATCH	(1 << 0)
+#define SBI_PMU_CFG_FLAG_CLEAR_VALUE	(1 << 1)
+#define SBI_PMU_CFG_FLAG_AUTO_START	(1 << 2)
+#define SBI_PMU_CFG_FLAG_SET_VUINH	(1 << 3)
+#define SBI_PMU_CFG_FLAG_SET_VSINH	(1 << 4)
+#define SBI_PMU_CFG_FLAG_SET_UINH	(1 << 5)
+#define SBI_PMU_CFG_FLAG_SET_SINH	(1 << 6)
+#define SBI_PMU_CFG_FLAG_SET_MINH	(1 << 7)
+
+/* Flags defined for counter start function */
+#define SBI_PMU_START_FLAG_SET_INIT_VALUE (1 << 0)
+
+/* Flags defined for counter stop function */
+#define SBI_PMU_STOP_FLAG_RESET (1 << 0)
+
+#define SBI_SPEC_VERSION_DEFAULT	0x1
+#define SBI_SPEC_VERSION_MAJOR_SHIFT	24
+#define SBI_SPEC_VERSION_MAJOR_MASK	0x7f
+#define SBI_SPEC_VERSION_MINOR_MASK	0xffffff
+
+/* SBI return error codes */
+#define SBI_SUCCESS		0
+#define SBI_ERR_FAILURE		-1
+#define SBI_ERR_NOT_SUPPORTED	-2
+#define SBI_ERR_INVALID_PARAM	-3
+#define SBI_ERR_DENIED		-4
+#define SBI_ERR_INVALID_ADDRESS	-5
+#define SBI_ERR_ALREADY_AVAILABLE -6
+#define SBI_ERR_ALREADY_STARTED -7
+#define SBI_ERR_ALREADY_STOPPED -8
+
+extern unsigned long sbi_spec_version;
+struct sbiret {
+	long error;
+	long value;
+};
+
+void sbi_init(void);
+struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0,
+			unsigned long arg1, unsigned long arg2,
+			unsigned long arg3, unsigned long arg4,
+			unsigned long arg5);
+
+void sbi_console_putchar(int ch);
+int sbi_console_getchar(void);
+long sbi_get_mvendorid(void);
+long sbi_get_marchid(void);
+long sbi_get_mimpid(void);
+void sbi_set_timer(uint64_t stime_value);
+void sbi_shutdown(void);
+void sbi_clear_ipi(void);
+int sbi_send_ipi(const struct cpumask *cpu_mask);
+int sbi_remote_fence_i(const struct cpumask *cpu_mask);
+int sbi_remote_sfence_vma(const struct cpumask *cpu_mask,
+			   unsigned long start,
+			   unsigned long size);
+
+int sbi_remote_sfence_vma_asid(const struct cpumask *cpu_mask,
+				unsigned long start,
+				unsigned long size,
+				unsigned long asid);
+int sbi_remote_hfence_gvma(const struct cpumask *cpu_mask,
+			   unsigned long start,
+			   unsigned long size);
+int sbi_remote_hfence_gvma_vmid(const struct cpumask *cpu_mask,
+				unsigned long start,
+				unsigned long size,
+				unsigned long vmid);
+int sbi_remote_hfence_vvma(const struct cpumask *cpu_mask,
+			   unsigned long start,
+			   unsigned long size);
+int sbi_remote_hfence_vvma_asid(const struct cpumask *cpu_mask,
+				unsigned long start,
+				unsigned long size,
+				unsigned long asid);
+long sbi_probe_extension(int ext);
+
+/* Check if current SBI specification version is 0.1 or not */
+static inline int sbi_spec_is_0_1(void)
+{
+	return (sbi_spec_version == SBI_SPEC_VERSION_DEFAULT) ? 1 : 0;
+}
+
+/* Get the major version of SBI */
+static inline unsigned long sbi_major_version(void)
+{
+	return (sbi_spec_version >> SBI_SPEC_VERSION_MAJOR_SHIFT) &
+		SBI_SPEC_VERSION_MAJOR_MASK;
+}
+
+/* Get the minor version of SBI */
+static inline unsigned long sbi_minor_version(void)
+{
+	return sbi_spec_version & SBI_SPEC_VERSION_MINOR_MASK;
+}
+
+/* Make SBI version */
+static inline unsigned long sbi_mk_version(unsigned long major,
+					    unsigned long minor)
+{
+	return ((major & SBI_SPEC_VERSION_MAJOR_MASK) <<
+		SBI_SPEC_VERSION_MAJOR_SHIFT) | minor;
+}
+
+int sbi_err_map_linux_errno(int err);
+#else /* CONFIG_RISCV_SBI */
+static inline int sbi_remote_fence_i(const struct cpumask *cpu_mask) { return -1; }
+static inline void sbi_init(void) {}
+#endif /* CONFIG_RISCV_SBI */
+#endif /* _ASM_RISCV_SBI_H */
diff --git a/arch/riscv/include/asm/seccomp.h b/arch/riscv/include/asm/seccomp.h
new file mode 100644
index 000000000..c7ee6a350
--- /dev/null
+++ b/arch/riscv/include/asm/seccomp.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _ASM_SECCOMP_H
+#define _ASM_SECCOMP_H
+
+#include <asm/unistd.h>
+
+#include <asm-generic/seccomp.h>
+
+#ifdef CONFIG_64BIT
+# define SECCOMP_ARCH_NATIVE		AUDIT_ARCH_RISCV64
+# define SECCOMP_ARCH_NATIVE_NR		NR_syscalls
+# define SECCOMP_ARCH_NATIVE_NAME	"riscv64"
+#else /* !CONFIG_64BIT */
+# define SECCOMP_ARCH_NATIVE		AUDIT_ARCH_RISCV32
+# define SECCOMP_ARCH_NATIVE_NR		NR_syscalls
+# define SECCOMP_ARCH_NATIVE_NAME	"riscv32"
+#endif
+
+#endif /* _ASM_SECCOMP_H */
diff --git a/arch/riscv/include/asm/sections.h b/arch/riscv/include/asm/sections.h
new file mode 100644
index 000000000..a393d5035
--- /dev/null
+++ b/arch/riscv/include/asm/sections.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2020 Western Digital Corporation or its affiliates.
+ */
+#ifndef __ASM_SECTIONS_H
+#define __ASM_SECTIONS_H
+
+#include <asm-generic/sections.h>
+#include <linux/mm.h>
+
+extern char _start[];
+extern char _start_kernel[];
+extern char __init_data_begin[], __init_data_end[];
+extern char __init_text_begin[], __init_text_end[];
+extern char __alt_start[], __alt_end[];
+extern char __exittext_begin[], __exittext_end[];
+
+static inline bool is_va_kernel_text(uintptr_t va)
+{
+	uintptr_t start = (uintptr_t)_start;
+	uintptr_t end = (uintptr_t)__init_data_begin;
+
+	return va >= start && va < end;
+}
+
+static inline bool is_va_kernel_lm_alias_text(uintptr_t va)
+{
+	uintptr_t start = (uintptr_t)lm_alias(_start);
+	uintptr_t end = (uintptr_t)lm_alias(__init_data_begin);
+
+	return va >= start && va < end;
+}
+
+#endif /* __ASM_SECTIONS_H */
diff --git a/arch/riscv/include/asm/set_memory.h b/arch/riscv/include/asm/set_memory.h
new file mode 100644
index 000000000..a2c14d4b3
--- /dev/null
+++ b/arch/riscv/include/asm/set_memory.h
@@ -0,0 +1,59 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2019 SiFive
+ */
+
+#ifndef _ASM_RISCV_SET_MEMORY_H
+#define _ASM_RISCV_SET_MEMORY_H
+
+#ifndef __ASSEMBLY__
+/*
+ * Functions to change memory attributes.
+ */
+#ifdef CONFIG_MMU
+int set_memory_ro(unsigned long addr, int numpages);
+int set_memory_rw(unsigned long addr, int numpages);
+int set_memory_x(unsigned long addr, int numpages);
+int set_memory_nx(unsigned long addr, int numpages);
+int set_memory_rw_nx(unsigned long addr, int numpages);
+static __always_inline int set_kernel_memory(char *startp, char *endp,
+					     int (*set_memory)(unsigned long start,
+							       int num_pages))
+{
+	unsigned long start = (unsigned long)startp;
+	unsigned long end = (unsigned long)endp;
+	int num_pages = PAGE_ALIGN(end - start) >> PAGE_SHIFT;
+
+	return set_memory(start, num_pages);
+}
+#else
+static inline int set_memory_ro(unsigned long addr, int numpages) { return 0; }
+static inline int set_memory_rw(unsigned long addr, int numpages) { return 0; }
+static inline int set_memory_x(unsigned long addr, int numpages) { return 0; }
+static inline int set_memory_nx(unsigned long addr, int numpages) { return 0; }
+static inline int set_memory_rw_nx(unsigned long addr, int numpages) { return 0; }
+static inline int set_kernel_memory(char *startp, char *endp,
+				    int (*set_memory)(unsigned long start,
+						      int num_pages))
+{
+	return 0;
+}
+#endif
+
+int set_direct_map_invalid_noflush(struct page *page);
+int set_direct_map_default_noflush(struct page *page);
+bool kernel_page_present(struct page *page);
+
+#endif /* __ASSEMBLY__ */
+
+#ifdef CONFIG_STRICT_KERNEL_RWX
+#ifdef CONFIG_64BIT
+#define SECTION_ALIGN (1 << 21)
+#else
+#define SECTION_ALIGN (1 << 22)
+#endif
+#else /* !CONFIG_STRICT_KERNEL_RWX */
+#define SECTION_ALIGN L1_CACHE_BYTES
+#endif /* CONFIG_STRICT_KERNEL_RWX */
+
+#endif /* _ASM_RISCV_SET_MEMORY_H */
diff --git a/arch/riscv/include/asm/signal.h b/arch/riscv/include/asm/signal.h
new file mode 100644
index 000000000..956ae0a01
--- /dev/null
+++ b/arch/riscv/include/asm/signal.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __ASM_SIGNAL_H
+#define __ASM_SIGNAL_H
+
+#include <uapi/asm/signal.h>
+#include <uapi/asm/ptrace.h>
+
+asmlinkage __visible
+void do_work_pending(struct pt_regs *regs, unsigned long thread_info_flags);
+
+#endif
diff --git a/arch/riscv/include/asm/signal32.h b/arch/riscv/include/asm/signal32.h
new file mode 100644
index 000000000..96dc56932
--- /dev/null
+++ b/arch/riscv/include/asm/signal32.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __ASM_SIGNAL32_H
+#define __ASM_SIGNAL32_H
+
+#if IS_ENABLED(CONFIG_COMPAT)
+int compat_setup_rt_frame(struct ksignal *ksig, sigset_t *set,
+			  struct pt_regs *regs);
+#else
+static inline
+int compat_setup_rt_frame(struct ksignal *ksig, sigset_t *set,
+			  struct pt_regs *regs)
+{
+	return -1;
+}
+#endif
+
+#endif
diff --git a/arch/riscv/include/asm/smp.h b/arch/riscv/include/asm/smp.h
new file mode 100644
index 000000000..3831b638e
--- /dev/null
+++ b/arch/riscv/include/asm/smp.h
@@ -0,0 +1,107 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ */
+
+#ifndef _ASM_RISCV_SMP_H
+#define _ASM_RISCV_SMP_H
+
+#include <linux/cpumask.h>
+#include <linux/irqreturn.h>
+#include <linux/thread_info.h>
+
+#define INVALID_HARTID ULONG_MAX
+
+struct seq_file;
+extern unsigned long boot_cpu_hartid;
+
+struct riscv_ipi_ops {
+	void (*ipi_inject)(const struct cpumask *target);
+	void (*ipi_clear)(void);
+};
+
+#ifdef CONFIG_SMP
+/*
+ * Mapping between linux logical cpu index and hartid.
+ */
+extern unsigned long __cpuid_to_hartid_map[NR_CPUS];
+#define cpuid_to_hartid_map(cpu)    __cpuid_to_hartid_map[cpu]
+
+/* print IPI stats */
+void show_ipi_stats(struct seq_file *p, int prec);
+
+/* SMP initialization hook for setup_arch */
+void __init setup_smp(void);
+
+/* Called from C code, this handles an IPI. */
+void handle_IPI(struct pt_regs *regs);
+
+/* Hook for the generic smp_call_function_many() routine. */
+void arch_send_call_function_ipi_mask(struct cpumask *mask);
+
+/* Hook for the generic smp_call_function_single() routine. */
+void arch_send_call_function_single_ipi(int cpu);
+
+int riscv_hartid_to_cpuid(unsigned long hartid);
+
+/* Set custom IPI operations */
+void riscv_set_ipi_ops(const struct riscv_ipi_ops *ops);
+
+/* Clear IPI for current CPU */
+void riscv_clear_ipi(void);
+
+/* Check other CPUs stop or not */
+bool smp_crash_stop_failed(void);
+
+/* Secondary hart entry */
+asmlinkage void smp_callin(void);
+
+/*
+ * Obtains the hart ID of the currently executing task.  This relies on
+ * THREAD_INFO_IN_TASK, but we define that unconditionally.
+ */
+#define raw_smp_processor_id() (current_thread_info()->cpu)
+
+#if defined CONFIG_HOTPLUG_CPU
+int __cpu_disable(void);
+void __cpu_die(unsigned int cpu);
+#endif /* CONFIG_HOTPLUG_CPU */
+
+#else
+
+static inline void show_ipi_stats(struct seq_file *p, int prec)
+{
+}
+
+static inline int riscv_hartid_to_cpuid(unsigned long hartid)
+{
+	if (hartid == boot_cpu_hartid)
+		return 0;
+
+	return -1;
+}
+static inline unsigned long cpuid_to_hartid_map(int cpu)
+{
+	return boot_cpu_hartid;
+}
+
+static inline void riscv_set_ipi_ops(const struct riscv_ipi_ops *ops)
+{
+}
+
+static inline void riscv_clear_ipi(void)
+{
+}
+
+#endif /* CONFIG_SMP */
+
+#if defined(CONFIG_HOTPLUG_CPU) && (CONFIG_SMP)
+bool cpu_has_hotplug(unsigned int cpu);
+#else
+static inline bool cpu_has_hotplug(unsigned int cpu)
+{
+	return false;
+}
+#endif
+
+#endif /* _ASM_RISCV_SMP_H */
diff --git a/arch/riscv/include/asm/soc.h b/arch/riscv/include/asm/soc.h
new file mode 100644
index 000000000..f49406605
--- /dev/null
+++ b/arch/riscv/include/asm/soc.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2020 Western Digital Corporation or its affiliates.
+ * Copyright (C) 2020 Google, Inc
+ */
+
+#ifndef _ASM_RISCV_SOC_H
+#define _ASM_RISCV_SOC_H
+
+#include <linux/of.h>
+#include <linux/linkage.h>
+#include <linux/types.h>
+
+#define SOC_EARLY_INIT_DECLARE(name, compat, fn)			\
+	static const struct of_device_id __soc_early_init__##name	\
+		__used __section("__soc_early_init_table")		\
+		 = { .compatible = compat, .data = fn  }
+
+void soc_early_init(void);
+
+extern unsigned long __soc_early_init_table_start;
+extern unsigned long __soc_early_init_table_end;
+
+#endif
diff --git a/arch/riscv/include/asm/sparsemem.h b/arch/riscv/include/asm/sparsemem.h
new file mode 100644
index 000000000..63acaecc3
--- /dev/null
+++ b/arch/riscv/include/asm/sparsemem.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _ASM_RISCV_SPARSEMEM_H
+#define _ASM_RISCV_SPARSEMEM_H
+
+#ifdef CONFIG_SPARSEMEM
+#ifdef CONFIG_64BIT
+#define MAX_PHYSMEM_BITS	56
+#else
+#define MAX_PHYSMEM_BITS	34
+#endif /* CONFIG_64BIT */
+#define SECTION_SIZE_BITS	27
+#endif /* CONFIG_SPARSEMEM */
+
+#endif /* _ASM_RISCV_SPARSEMEM_H */
diff --git a/arch/riscv/include/asm/stackprotector.h b/arch/riscv/include/asm/stackprotector.h
new file mode 100644
index 000000000..09093af46
--- /dev/null
+++ b/arch/riscv/include/asm/stackprotector.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _ASM_RISCV_STACKPROTECTOR_H
+#define _ASM_RISCV_STACKPROTECTOR_H
+
+#include <linux/random.h>
+#include <linux/version.h>
+
+extern unsigned long __stack_chk_guard;
+
+/*
+ * Initialize the stackprotector canary value.
+ *
+ * NOTE: this must only be called from functions that never return,
+ * and it must always be inlined.
+ */
+static __always_inline void boot_init_stack_canary(void)
+{
+	unsigned long canary;
+
+	/* Try to get a semi random initial value. */
+	get_random_bytes(&canary, sizeof(canary));
+	canary ^= LINUX_VERSION_CODE;
+	canary &= CANARY_MASK;
+
+	current->stack_canary = canary;
+	if (!IS_ENABLED(CONFIG_STACKPROTECTOR_PER_TASK))
+		__stack_chk_guard = current->stack_canary;
+}
+#endif /* _ASM_RISCV_STACKPROTECTOR_H */
diff --git a/arch/riscv/include/asm/stacktrace.h b/arch/riscv/include/asm/stacktrace.h
new file mode 100644
index 000000000..3450c1912
--- /dev/null
+++ b/arch/riscv/include/asm/stacktrace.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _ASM_RISCV_STACKTRACE_H
+#define _ASM_RISCV_STACKTRACE_H
+
+#include <linux/sched.h>
+#include <asm/ptrace.h>
+
+struct stackframe {
+	unsigned long fp;
+	unsigned long ra;
+};
+
+extern void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs,
+				    bool (*fn)(void *, unsigned long), void *arg);
+extern void dump_backtrace(struct pt_regs *regs, struct task_struct *task,
+			   const char *loglvl);
+
+#endif /* _ASM_RISCV_STACKTRACE_H */
diff --git a/arch/riscv/include/asm/string.h b/arch/riscv/include/asm/string.h
new file mode 100644
index 000000000..909049366
--- /dev/null
+++ b/arch/riscv/include/asm/string.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2013 Regents of the University of California
+ */
+
+#ifndef _ASM_RISCV_STRING_H
+#define _ASM_RISCV_STRING_H
+
+#include <linux/types.h>
+#include <linux/linkage.h>
+
+#define __HAVE_ARCH_MEMSET
+extern asmlinkage void *memset(void *, int, size_t);
+extern asmlinkage void *__memset(void *, int, size_t);
+#define __HAVE_ARCH_MEMCPY
+extern asmlinkage void *memcpy(void *, const void *, size_t);
+extern asmlinkage void *__memcpy(void *, const void *, size_t);
+#define __HAVE_ARCH_MEMMOVE
+extern asmlinkage void *memmove(void *, const void *, size_t);
+extern asmlinkage void *__memmove(void *, const void *, size_t);
+/* For those files which don't want to check by kasan. */
+#if defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__)
+#define memcpy(dst, src, len) __memcpy(dst, src, len)
+#define memset(s, c, n) __memset(s, c, n)
+#define memmove(dst, src, len) __memmove(dst, src, len)
+
+#ifndef __NO_FORTIFY
+#define __NO_FORTIFY /* FORTIFY_SOURCE uses __builtin_memcpy, etc. */
+#endif
+
+#endif
+#endif /* _ASM_RISCV_STRING_H */
diff --git a/arch/riscv/include/asm/suspend.h b/arch/riscv/include/asm/suspend.h
new file mode 100644
index 000000000..8be391c2a
--- /dev/null
+++ b/arch/riscv/include/asm/suspend.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2021 Western Digital Corporation or its affiliates.
+ * Copyright (c) 2022 Ventana Micro Systems Inc.
+ */
+
+#ifndef _ASM_RISCV_SUSPEND_H
+#define _ASM_RISCV_SUSPEND_H
+
+#include <asm/ptrace.h>
+
+struct suspend_context {
+	/* Saved and restored by low-level functions */
+	struct pt_regs regs;
+	/* Saved and restored by high-level functions */
+	unsigned long scratch;
+	unsigned long tvec;
+	unsigned long ie;
+#ifdef CONFIG_MMU
+	unsigned long satp;
+#endif
+};
+
+/* Low-level CPU suspend entry function */
+int __cpu_suspend_enter(struct suspend_context *context);
+
+/* High-level CPU suspend which will save context and call finish() */
+int cpu_suspend(unsigned long arg,
+		int (*finish)(unsigned long arg,
+			      unsigned long entry,
+			      unsigned long context));
+
+/* Low-level CPU resume entry function */
+int __cpu_resume_enter(unsigned long hartid, unsigned long context);
+
+#endif
diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/switch_to.h
new file mode 100644
index 000000000..11463489f
--- /dev/null
+++ b/arch/riscv/include/asm/switch_to.h
@@ -0,0 +1,83 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ */
+
+#ifndef _ASM_RISCV_SWITCH_TO_H
+#define _ASM_RISCV_SWITCH_TO_H
+
+#include <linux/jump_label.h>
+#include <linux/sched/task_stack.h>
+#include <asm/hwcap.h>
+#include <asm/processor.h>
+#include <asm/ptrace.h>
+#include <asm/csr.h>
+
+#ifdef CONFIG_FPU
+extern void __fstate_save(struct task_struct *save_to);
+extern void __fstate_restore(struct task_struct *restore_from);
+
+static inline void __fstate_clean(struct pt_regs *regs)
+{
+	regs->status = (regs->status & ~SR_FS) | SR_FS_CLEAN;
+}
+
+static inline void fstate_off(struct task_struct *task,
+			      struct pt_regs *regs)
+{
+	regs->status = (regs->status & ~SR_FS) | SR_FS_OFF;
+}
+
+static inline void fstate_save(struct task_struct *task,
+			       struct pt_regs *regs)
+{
+	if ((regs->status & SR_FS) == SR_FS_DIRTY) {
+		__fstate_save(task);
+		__fstate_clean(regs);
+	}
+}
+
+static inline void fstate_restore(struct task_struct *task,
+				  struct pt_regs *regs)
+{
+	if ((regs->status & SR_FS) != SR_FS_OFF) {
+		__fstate_restore(task);
+		__fstate_clean(regs);
+	}
+}
+
+static inline void __switch_to_aux(struct task_struct *prev,
+				   struct task_struct *next)
+{
+	struct pt_regs *regs;
+
+	regs = task_pt_regs(prev);
+	if (unlikely(regs->status & SR_SD))
+		fstate_save(prev, regs);
+	fstate_restore(next, task_pt_regs(next));
+}
+
+static __always_inline bool has_fpu(void)
+{
+	return static_branch_likely(&riscv_isa_ext_keys[RISCV_ISA_EXT_KEY_FPU]);
+}
+#else
+static __always_inline bool has_fpu(void) { return false; }
+#define fstate_save(task, regs) do { } while (0)
+#define fstate_restore(task, regs) do { } while (0)
+#define __switch_to_aux(__prev, __next) do { } while (0)
+#endif
+
+extern struct task_struct *__switch_to(struct task_struct *,
+				       struct task_struct *);
+
+#define switch_to(prev, next, last)			\
+do {							\
+	struct task_struct *__prev = (prev);		\
+	struct task_struct *__next = (next);		\
+	if (has_fpu())					\
+		__switch_to_aux(__prev, __next);	\
+	((last) = __switch_to(__prev, __next));		\
+} while (0)
+
+#endif /* _ASM_RISCV_SWITCH_TO_H */
diff --git a/arch/riscv/include/asm/syscall.h b/arch/riscv/include/asm/syscall.h
new file mode 100644
index 000000000..384a63b86
--- /dev/null
+++ b/arch/riscv/include/asm/syscall.h
@@ -0,0 +1,78 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2008-2009 Red Hat, Inc.  All rights reserved.
+ * Copyright 2010 Tilera Corporation. All Rights Reserved.
+ * Copyright 2015 Regents of the University of California, Berkeley
+ *
+ * See asm-generic/syscall.h for descriptions of what we must do here.
+ */
+
+#ifndef _ASM_RISCV_SYSCALL_H
+#define _ASM_RISCV_SYSCALL_H
+
+#include <uapi/linux/audit.h>
+#include <linux/sched.h>
+#include <linux/err.h>
+
+/* The array of function pointers for syscalls. */
+extern void * const sys_call_table[];
+extern void * const compat_sys_call_table[];
+
+/*
+ * Only the low 32 bits of orig_r0 are meaningful, so we return int.
+ * This importantly ignores the high bits on 64-bit, so comparisons
+ * sign-extend the low 32 bits.
+ */
+static inline int syscall_get_nr(struct task_struct *task,
+				 struct pt_regs *regs)
+{
+	return regs->a7;
+}
+
+static inline void syscall_rollback(struct task_struct *task,
+				    struct pt_regs *regs)
+{
+        regs->a0 = regs->orig_a0;
+}
+
+static inline long syscall_get_error(struct task_struct *task,
+				     struct pt_regs *regs)
+{
+	unsigned long error = regs->a0;
+
+	return IS_ERR_VALUE(error) ? error : 0;
+}
+
+static inline long syscall_get_return_value(struct task_struct *task,
+					    struct pt_regs *regs)
+{
+	return regs->a0;
+}
+
+static inline void syscall_set_return_value(struct task_struct *task,
+					    struct pt_regs *regs,
+					    int error, long val)
+{
+	regs->a0 = (long) error ?: val;
+}
+
+static inline void syscall_get_arguments(struct task_struct *task,
+					 struct pt_regs *regs,
+					 unsigned long *args)
+{
+	args[0] = regs->orig_a0;
+	args++;
+	memcpy(args, &regs->a1, 5 * sizeof(args[0]));
+}
+
+static inline int syscall_get_arch(struct task_struct *task)
+{
+#ifdef CONFIG_64BIT
+	return AUDIT_ARCH_RISCV64;
+#else
+	return AUDIT_ARCH_RISCV32;
+#endif
+}
+
+asmlinkage long sys_riscv_flush_icache(uintptr_t, uintptr_t, uintptr_t);
+#endif	/* _ASM_RISCV_SYSCALL_H */
diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h
new file mode 100644
index 000000000..f704c8dd5
--- /dev/null
+++ b/arch/riscv/include/asm/thread_info.h
@@ -0,0 +1,123 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2009 Chen Liqin <liqin.chen@sunplusct.com>
+ * Copyright (C) 2012 Regents of the University of California
+ * Copyright (C) 2017 SiFive
+ */
+
+#ifndef _ASM_RISCV_THREAD_INFO_H
+#define _ASM_RISCV_THREAD_INFO_H
+
+#include <asm/page.h>
+#include <linux/const.h>
+
+#ifdef CONFIG_KASAN
+#define KASAN_STACK_ORDER 1
+#else
+#define KASAN_STACK_ORDER 0
+#endif
+
+/* thread information allocation */
+#ifdef CONFIG_64BIT
+#define THREAD_SIZE_ORDER	(2 + KASAN_STACK_ORDER)
+#else
+#define THREAD_SIZE_ORDER	(1 + KASAN_STACK_ORDER)
+#endif
+#define THREAD_SIZE		(PAGE_SIZE << THREAD_SIZE_ORDER)
+
+/*
+ * By aligning VMAP'd stacks to 2 * THREAD_SIZE, we can detect overflow by
+ * checking sp & (1 << THREAD_SHIFT), which we can do cheaply in the entry
+ * assembly.
+ */
+#ifdef CONFIG_VMAP_STACK
+#define THREAD_ALIGN            (2 * THREAD_SIZE)
+#else
+#define THREAD_ALIGN            THREAD_SIZE
+#endif
+
+#define THREAD_SHIFT            (PAGE_SHIFT + THREAD_SIZE_ORDER)
+#define OVERFLOW_STACK_SIZE     SZ_4K
+#define SHADOW_OVERFLOW_STACK_SIZE (1024)
+
+#ifndef __ASSEMBLY__
+
+extern long shadow_stack[SHADOW_OVERFLOW_STACK_SIZE / sizeof(long)];
+extern unsigned long spin_shadow_stack;
+
+#include <asm/processor.h>
+#include <asm/csr.h>
+
+/*
+ * low level task data that entry.S needs immediate access to
+ * - this struct should fit entirely inside of one cache line
+ * - if the members of this struct changes, the assembly constants
+ *   in asm-offsets.c must be updated accordingly
+ * - thread_info is included in task_struct at an offset of 0.  This means that
+ *   tp points to both thread_info and task_struct.
+ */
+struct thread_info {
+	unsigned long		flags;		/* low level flags */
+	int                     preempt_count;  /* 0=>preemptible, <0=>BUG */
+	/*
+	 * These stack pointers are overwritten on every system call or
+	 * exception.  SP is also saved to the stack it can be recovered when
+	 * overwritten.
+	 */
+	long			kernel_sp;	/* Kernel stack pointer */
+	long			user_sp;	/* User stack pointer */
+	int			cpu;
+};
+
+/*
+ * macros/functions for gaining access to the thread information structure
+ *
+ * preempt_count needs to be 1 initially, until the scheduler is functional.
+ */
+#define INIT_THREAD_INFO(tsk)			\
+{						\
+	.flags		= 0,			\
+	.preempt_count	= INIT_PREEMPT_COUNT,	\
+}
+
+#endif /* !__ASSEMBLY__ */
+
+/*
+ * thread information flags
+ * - these are process state flags that various assembly files may need to
+ *   access
+ * - pending work-to-be-done flags are in lowest half-word
+ * - other flags in upper half-word(s)
+ */
+#define TIF_SYSCALL_TRACE	0	/* syscall trace active */
+#define TIF_NOTIFY_RESUME	1	/* callback before returning to user */
+#define TIF_SIGPENDING		2	/* signal pending */
+#define TIF_NEED_RESCHED	3	/* rescheduling necessary */
+#define TIF_RESTORE_SIGMASK	4	/* restore signal mask in do_signal() */
+#define TIF_MEMDIE		5	/* is terminating due to OOM killer */
+#define TIF_SYSCALL_TRACEPOINT  6       /* syscall tracepoint instrumentation */
+#define TIF_SYSCALL_AUDIT	7	/* syscall auditing */
+#define TIF_SECCOMP		8	/* syscall secure computing */
+#define TIF_NOTIFY_SIGNAL	9	/* signal notifications exist */
+#define TIF_UPROBE		10	/* uprobe breakpoint or singlestep */
+#define TIF_32BIT		11	/* compat-mode 32bit process */
+
+#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_TRACEPOINT	(1 << TIF_SYSCALL_TRACEPOINT)
+#define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
+#define _TIF_SECCOMP		(1 << TIF_SECCOMP)
+#define _TIF_NOTIFY_SIGNAL	(1 << TIF_NOTIFY_SIGNAL)
+#define _TIF_UPROBE		(1 << TIF_UPROBE)
+
+#define _TIF_WORK_MASK \
+	(_TIF_NOTIFY_RESUME | _TIF_SIGPENDING | _TIF_NEED_RESCHED | \
+	 _TIF_NOTIFY_SIGNAL | _TIF_UPROBE)
+
+#define _TIF_SYSCALL_WORK \
+	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_TRACEPOINT | _TIF_SYSCALL_AUDIT | \
+	 _TIF_SECCOMP)
+
+#endif /* _ASM_RISCV_THREAD_INFO_H */
diff --git a/arch/riscv/include/asm/timex.h b/arch/riscv/include/asm/timex.h
new file mode 100644
index 000000000..d6a7428f6
--- /dev/null
+++ b/arch/riscv/include/asm/timex.h
@@ -0,0 +1,93 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ */
+
+#ifndef _ASM_RISCV_TIMEX_H
+#define _ASM_RISCV_TIMEX_H
+
+#include <asm/csr.h>
+
+typedef unsigned long cycles_t;
+
+#ifdef CONFIG_RISCV_M_MODE
+
+#include <asm/clint.h>
+
+#ifdef CONFIG_64BIT
+static inline cycles_t get_cycles(void)
+{
+	return readq_relaxed(clint_time_val);
+}
+#else /* !CONFIG_64BIT */
+static inline u32 get_cycles(void)
+{
+	return readl_relaxed(((u32 *)clint_time_val));
+}
+#define get_cycles get_cycles
+
+static inline u32 get_cycles_hi(void)
+{
+	return readl_relaxed(((u32 *)clint_time_val) + 1);
+}
+#define get_cycles_hi get_cycles_hi
+#endif /* CONFIG_64BIT */
+
+/*
+ * Much like MIPS, we may not have a viable counter to use at an early point
+ * in the boot process. Unfortunately we don't have a fallback, so instead
+ * we just return 0.
+ */
+static inline unsigned long random_get_entropy(void)
+{
+	if (unlikely(clint_time_val == NULL))
+		return random_get_entropy_fallback();
+	return get_cycles();
+}
+#define random_get_entropy()	random_get_entropy()
+
+#else /* CONFIG_RISCV_M_MODE */
+
+static inline cycles_t get_cycles(void)
+{
+	return csr_read(CSR_TIME);
+}
+#define get_cycles get_cycles
+
+static inline u32 get_cycles_hi(void)
+{
+	return csr_read(CSR_TIMEH);
+}
+#define get_cycles_hi get_cycles_hi
+
+#endif /* !CONFIG_RISCV_M_MODE */
+
+#ifdef CONFIG_64BIT
+static inline u64 get_cycles64(void)
+{
+	return get_cycles();
+}
+#else /* CONFIG_64BIT */
+static inline u64 get_cycles64(void)
+{
+	u32 hi, lo;
+
+	do {
+		hi = get_cycles_hi();
+		lo = get_cycles();
+	} while (hi != get_cycles_hi());
+
+	return ((u64)hi << 32) | lo;
+}
+#endif /* CONFIG_64BIT */
+
+#define ARCH_HAS_READ_CURRENT_TIMER
+static inline int read_current_timer(unsigned long *timer_val)
+{
+	*timer_val = get_cycles();
+	return 0;
+}
+
+extern void time_init(void);
+
+#endif /* _ASM_RISCV_TIMEX_H */
diff --git a/arch/riscv/include/asm/tlb.h b/arch/riscv/include/asm/tlb.h
new file mode 100644
index 000000000..120bcf2ed
--- /dev/null
+++ b/arch/riscv/include/asm/tlb.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ */
+
+#ifndef _ASM_RISCV_TLB_H
+#define _ASM_RISCV_TLB_H
+
+struct mmu_gather;
+
+static void tlb_flush(struct mmu_gather *tlb);
+
+#define tlb_flush tlb_flush
+#include <asm-generic/tlb.h>
+
+static inline void tlb_flush(struct mmu_gather *tlb)
+{
+	flush_tlb_mm(tlb->mm);
+}
+
+#endif /* _ASM_RISCV_TLB_H */
diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h
new file mode 100644
index 000000000..a09196f8d
--- /dev/null
+++ b/arch/riscv/include/asm/tlbflush.h
@@ -0,0 +1,64 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2009 Chen Liqin <liqin.chen@sunplusct.com>
+ * Copyright (C) 2012 Regents of the University of California
+ */
+
+#ifndef _ASM_RISCV_TLBFLUSH_H
+#define _ASM_RISCV_TLBFLUSH_H
+
+#include <linux/mm_types.h>
+#include <asm/smp.h>
+#include <asm/errata_list.h>
+
+#ifdef CONFIG_MMU
+extern unsigned long asid_mask;
+
+static inline void local_flush_tlb_all(void)
+{
+	__asm__ __volatile__ ("sfence.vma" : : : "memory");
+}
+
+/* Flush one page from local TLB */
+static inline void local_flush_tlb_page(unsigned long addr)
+{
+	ALT_FLUSH_TLB_PAGE(__asm__ __volatile__ ("sfence.vma %0" : : "r" (addr) : "memory"));
+}
+#else /* CONFIG_MMU */
+#define local_flush_tlb_all()			do { } while (0)
+#define local_flush_tlb_page(addr)		do { } while (0)
+#endif /* CONFIG_MMU */
+
+#if defined(CONFIG_SMP) && defined(CONFIG_MMU)
+void flush_tlb_all(void);
+void flush_tlb_mm(struct mm_struct *mm);
+void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr);
+void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
+		     unsigned long end);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE
+void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
+			unsigned long end);
+#endif
+#else /* CONFIG_SMP && CONFIG_MMU */
+
+#define flush_tlb_all() local_flush_tlb_all()
+#define flush_tlb_page(vma, addr) local_flush_tlb_page(addr)
+
+static inline void flush_tlb_range(struct vm_area_struct *vma,
+		unsigned long start, unsigned long end)
+{
+	local_flush_tlb_all();
+}
+
+#define flush_tlb_mm(mm) flush_tlb_all()
+#endif /* !CONFIG_SMP || !CONFIG_MMU */
+
+/* Flush a range of kernel pages */
+static inline void flush_tlb_kernel_range(unsigned long start,
+	unsigned long end)
+{
+	flush_tlb_all();
+}
+
+#endif /* _ASM_RISCV_TLBFLUSH_H */
diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h
new file mode 100644
index 000000000..ec0cab9fb
--- /dev/null
+++ b/arch/riscv/include/asm/uaccess.h
@@ -0,0 +1,341 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * This file was copied from include/asm-generic/uaccess.h
+ */
+
+#ifndef _ASM_RISCV_UACCESS_H
+#define _ASM_RISCV_UACCESS_H
+
+#include <asm/asm-extable.h>
+#include <asm/pgtable.h>		/* for TASK_SIZE */
+
+/*
+ * User space memory access functions
+ */
+#ifdef CONFIG_MMU
+#include <linux/errno.h>
+#include <linux/compiler.h>
+#include <linux/thread_info.h>
+#include <asm/byteorder.h>
+#include <asm/extable.h>
+#include <asm/asm.h>
+#include <asm-generic/access_ok.h>
+
+#define __enable_user_access()							\
+	__asm__ __volatile__ ("csrs sstatus, %0" : : "r" (SR_SUM) : "memory")
+#define __disable_user_access()							\
+	__asm__ __volatile__ ("csrc sstatus, %0" : : "r" (SR_SUM) : "memory")
+
+/*
+ * The exception table consists of pairs of addresses: the first is the
+ * address of an instruction that is allowed to fault, and the second is
+ * the address at which the program should continue.  No registers are
+ * modified, so it is entirely up to the continuation code to figure out
+ * what to do.
+ *
+ * All the routines below use bits of fixup code that are out of line
+ * with the main instruction path.  This means when everything is well,
+ * we don't even have to jump over them.  Further, they do not intrude
+ * on our cache or tlb entries.
+ */
+
+#define __LSW	0
+#define __MSW	1
+
+/*
+ * The "__xxx" versions of the user access functions do not verify the address
+ * space - it must have been done previously with a separate "access_ok()"
+ * call.
+ */
+
+#define __get_user_asm(insn, x, ptr, err)			\
+do {								\
+	__typeof__(x) __x;					\
+	__asm__ __volatile__ (					\
+		"1:\n"						\
+		"	" insn " %1, %2\n"			\
+		"2:\n"						\
+		_ASM_EXTABLE_UACCESS_ERR_ZERO(1b, 2b, %0, %1)	\
+		: "+r" (err), "=&r" (__x)			\
+		: "m" (*(ptr)));				\
+	(x) = __x;						\
+} while (0)
+
+#ifdef CONFIG_64BIT
+#define __get_user_8(x, ptr, err) \
+	__get_user_asm("ld", x, ptr, err)
+#else /* !CONFIG_64BIT */
+#define __get_user_8(x, ptr, err)				\
+do {								\
+	u32 __user *__ptr = (u32 __user *)(ptr);		\
+	u32 __lo, __hi;						\
+	__asm__ __volatile__ (					\
+		"1:\n"						\
+		"	lw %1, %3\n"				\
+		"2:\n"						\
+		"	lw %2, %4\n"				\
+		"3:\n"						\
+		_ASM_EXTABLE_UACCESS_ERR_ZERO(1b, 3b, %0, %1)	\
+		_ASM_EXTABLE_UACCESS_ERR_ZERO(2b, 3b, %0, %1)	\
+		: "+r" (err), "=&r" (__lo), "=r" (__hi)		\
+		: "m" (__ptr[__LSW]), "m" (__ptr[__MSW]));	\
+	if (err)						\
+		__hi = 0;					\
+	(x) = (__typeof__(x))((__typeof__((x)-(x)))(		\
+		(((u64)__hi << 32) | __lo)));			\
+} while (0)
+#endif /* CONFIG_64BIT */
+
+#define __get_user_nocheck(x, __gu_ptr, __gu_err)		\
+do {								\
+	switch (sizeof(*__gu_ptr)) {				\
+	case 1:							\
+		__get_user_asm("lb", (x), __gu_ptr, __gu_err);	\
+		break;						\
+	case 2:							\
+		__get_user_asm("lh", (x), __gu_ptr, __gu_err);	\
+		break;						\
+	case 4:							\
+		__get_user_asm("lw", (x), __gu_ptr, __gu_err);	\
+		break;						\
+	case 8:							\
+		__get_user_8((x), __gu_ptr, __gu_err);	\
+		break;						\
+	default:						\
+		BUILD_BUG();					\
+	}							\
+} while (0)
+
+/**
+ * __get_user: - Get a simple variable from user space, with less checking.
+ * @x:   Variable to store result.
+ * @ptr: Source address, in user space.
+ *
+ * Context: User context only.  This function may sleep.
+ *
+ * This macro copies a single simple variable from user space to kernel
+ * space.  It supports simple types like char and int, but not larger
+ * data types like structures or arrays.
+ *
+ * @ptr must have pointer-to-simple-variable type, and the result of
+ * dereferencing @ptr must be assignable to @x without a cast.
+ *
+ * Caller must check the pointer with access_ok() before calling this
+ * function.
+ *
+ * Returns zero on success, or -EFAULT on error.
+ * On error, the variable @x is set to zero.
+ */
+#define __get_user(x, ptr)					\
+({								\
+	const __typeof__(*(ptr)) __user *__gu_ptr = (ptr);	\
+	long __gu_err = 0;					\
+								\
+	__chk_user_ptr(__gu_ptr);				\
+								\
+	__enable_user_access();					\
+	__get_user_nocheck(x, __gu_ptr, __gu_err);		\
+	__disable_user_access();				\
+								\
+	__gu_err;						\
+})
+
+/**
+ * get_user: - Get a simple variable from user space.
+ * @x:   Variable to store result.
+ * @ptr: Source address, in user space.
+ *
+ * Context: User context only.  This function may sleep.
+ *
+ * This macro copies a single simple variable from user space to kernel
+ * space.  It supports simple types like char and int, but not larger
+ * data types like structures or arrays.
+ *
+ * @ptr must have pointer-to-simple-variable type, and the result of
+ * dereferencing @ptr must be assignable to @x without a cast.
+ *
+ * Returns zero on success, or -EFAULT on error.
+ * On error, the variable @x is set to zero.
+ */
+#define get_user(x, ptr)					\
+({								\
+	const __typeof__(*(ptr)) __user *__p = (ptr);		\
+	might_fault();						\
+	access_ok(__p, sizeof(*__p)) ?		\
+		__get_user((x), __p) :				\
+		((x) = (__force __typeof__(x))0, -EFAULT);	\
+})
+
+#define __put_user_asm(insn, x, ptr, err)			\
+do {								\
+	__typeof__(*(ptr)) __x = x;				\
+	__asm__ __volatile__ (					\
+		"1:\n"						\
+		"	" insn " %z2, %1\n"			\
+		"2:\n"						\
+		_ASM_EXTABLE_UACCESS_ERR(1b, 2b, %0)		\
+		: "+r" (err), "=m" (*(ptr))			\
+		: "rJ" (__x));					\
+} while (0)
+
+#ifdef CONFIG_64BIT
+#define __put_user_8(x, ptr, err) \
+	__put_user_asm("sd", x, ptr, err)
+#else /* !CONFIG_64BIT */
+#define __put_user_8(x, ptr, err)				\
+do {								\
+	u32 __user *__ptr = (u32 __user *)(ptr);		\
+	u64 __x = (__typeof__((x)-(x)))(x);			\
+	__asm__ __volatile__ (					\
+		"1:\n"						\
+		"	sw %z3, %1\n"				\
+		"2:\n"						\
+		"	sw %z4, %2\n"				\
+		"3:\n"						\
+		_ASM_EXTABLE_UACCESS_ERR(1b, 3b, %0)		\
+		_ASM_EXTABLE_UACCESS_ERR(2b, 3b, %0)		\
+		: "+r" (err),					\
+			"=m" (__ptr[__LSW]),			\
+			"=m" (__ptr[__MSW])			\
+		: "rJ" (__x), "rJ" (__x >> 32));		\
+} while (0)
+#endif /* CONFIG_64BIT */
+
+#define __put_user_nocheck(x, __gu_ptr, __pu_err)					\
+do {								\
+	switch (sizeof(*__gu_ptr)) {				\
+	case 1:							\
+		__put_user_asm("sb", (x), __gu_ptr, __pu_err);	\
+		break;						\
+	case 2:							\
+		__put_user_asm("sh", (x), __gu_ptr, __pu_err);	\
+		break;						\
+	case 4:							\
+		__put_user_asm("sw", (x), __gu_ptr, __pu_err);	\
+		break;						\
+	case 8:							\
+		__put_user_8((x), __gu_ptr, __pu_err);	\
+		break;						\
+	default:						\
+		BUILD_BUG();					\
+	}							\
+} while (0)
+
+/**
+ * __put_user: - Write a simple value into user space, with less checking.
+ * @x:   Value to copy to user space.
+ * @ptr: Destination address, in user space.
+ *
+ * Context: User context only.  This function may sleep.
+ *
+ * This macro copies a single simple value from kernel space to user
+ * space.  It supports simple types like char and int, but not larger
+ * data types like structures or arrays.
+ *
+ * @ptr must have pointer-to-simple-variable type, and @x must be assignable
+ * to the result of dereferencing @ptr. The value of @x is copied to avoid
+ * re-ordering where @x is evaluated inside the block that enables user-space
+ * access (thus bypassing user space protection if @x is a function).
+ *
+ * Caller must check the pointer with access_ok() before calling this
+ * function.
+ *
+ * Returns zero on success, or -EFAULT on error.
+ */
+#define __put_user(x, ptr)					\
+({								\
+	__typeof__(*(ptr)) __user *__gu_ptr = (ptr);		\
+	__typeof__(*__gu_ptr) __val = (x);			\
+	long __pu_err = 0;					\
+								\
+	__chk_user_ptr(__gu_ptr);				\
+								\
+	__enable_user_access();					\
+	__put_user_nocheck(__val, __gu_ptr, __pu_err);		\
+	__disable_user_access();				\
+								\
+	__pu_err;						\
+})
+
+/**
+ * put_user: - Write a simple value into user space.
+ * @x:   Value to copy to user space.
+ * @ptr: Destination address, in user space.
+ *
+ * Context: User context only.  This function may sleep.
+ *
+ * This macro copies a single simple value from kernel space to user
+ * space.  It supports simple types like char and int, but not larger
+ * data types like structures or arrays.
+ *
+ * @ptr must have pointer-to-simple-variable type, and @x must be assignable
+ * to the result of dereferencing @ptr.
+ *
+ * Returns zero on success, or -EFAULT on error.
+ */
+#define put_user(x, ptr)					\
+({								\
+	__typeof__(*(ptr)) __user *__p = (ptr);			\
+	might_fault();						\
+	access_ok(__p, sizeof(*__p)) ?		\
+		__put_user((x), __p) :				\
+		-EFAULT;					\
+})
+
+
+unsigned long __must_check __asm_copy_to_user(void __user *to,
+	const void *from, unsigned long n);
+unsigned long __must_check __asm_copy_from_user(void *to,
+	const void __user *from, unsigned long n);
+
+static inline unsigned long
+raw_copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+	return __asm_copy_from_user(to, from, n);
+}
+
+static inline unsigned long
+raw_copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+	return __asm_copy_to_user(to, from, n);
+}
+
+extern long strncpy_from_user(char *dest, const char __user *src, long count);
+
+extern long __must_check strnlen_user(const char __user *str, long n);
+
+extern
+unsigned long __must_check __clear_user(void __user *addr, unsigned long n);
+
+static inline
+unsigned long __must_check clear_user(void __user *to, unsigned long n)
+{
+	might_fault();
+	return access_ok(to, n) ?
+		__clear_user(to, n) : n;
+}
+
+#define __get_kernel_nofault(dst, src, type, err_label)			\
+do {									\
+	long __kr_err;							\
+									\
+	__get_user_nocheck(*((type *)(dst)), (type *)(src), __kr_err);	\
+	if (unlikely(__kr_err))						\
+		goto err_label;						\
+} while (0)
+
+#define __put_kernel_nofault(dst, src, type, err_label)			\
+do {									\
+	long __kr_err;							\
+									\
+	__put_user_nocheck(*((type *)(src)), (type *)(dst), __kr_err);	\
+	if (unlikely(__kr_err))						\
+		goto err_label;						\
+} while (0)
+
+#else /* CONFIG_MMU */
+#include <asm-generic/uaccess.h>
+#endif /* CONFIG_MMU */
+#endif /* _ASM_RISCV_UACCESS_H */
diff --git a/arch/riscv/include/asm/unistd.h b/arch/riscv/include/asm/unistd.h
new file mode 100644
index 000000000..221630bdb
--- /dev/null
+++ b/arch/riscv/include/asm/unistd.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ */
+
+/*
+ * There is explicitly no include guard here because this file is expected to
+ * be included multiple times.
+ */
+
+#define __ARCH_WANT_SYS_CLONE
+
+#ifdef CONFIG_COMPAT
+#define __ARCH_WANT_COMPAT_TRUNCATE64
+#define __ARCH_WANT_COMPAT_FTRUNCATE64
+#define __ARCH_WANT_COMPAT_FALLOCATE
+#define __ARCH_WANT_COMPAT_PREAD64
+#define __ARCH_WANT_COMPAT_PWRITE64
+#define __ARCH_WANT_COMPAT_SYNC_FILE_RANGE
+#define __ARCH_WANT_COMPAT_READAHEAD
+#define __ARCH_WANT_COMPAT_FADVISE64_64
+#endif
+
+#include <uapi/asm/unistd.h>
+
+#define NR_syscalls (__NR_syscalls)
diff --git a/arch/riscv/include/asm/uprobes.h b/arch/riscv/include/asm/uprobes.h
new file mode 100644
index 000000000..f2183e00f
--- /dev/null
+++ b/arch/riscv/include/asm/uprobes.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef _ASM_RISCV_UPROBES_H
+#define _ASM_RISCV_UPROBES_H
+
+#include <asm/probes.h>
+#include <asm/patch.h>
+#include <asm/bug.h>
+
+#define MAX_UINSN_BYTES		8
+
+#ifdef CONFIG_RISCV_ISA_C
+#define UPROBE_SWBP_INSN	__BUG_INSN_16
+#define UPROBE_SWBP_INSN_SIZE	2
+#else
+#define UPROBE_SWBP_INSN	__BUG_INSN_32
+#define UPROBE_SWBP_INSN_SIZE	4
+#endif
+#define UPROBE_XOL_SLOT_BYTES	MAX_UINSN_BYTES
+
+typedef u32 uprobe_opcode_t;
+
+struct arch_uprobe_task {
+	unsigned long   saved_cause;
+};
+
+struct arch_uprobe {
+	union {
+		u8 insn[MAX_UINSN_BYTES];
+		u8 ixol[MAX_UINSN_BYTES];
+	};
+	struct arch_probe_insn api;
+	unsigned long insn_size;
+	bool simulate;
+};
+
+bool uprobe_breakpoint_handler(struct pt_regs *regs);
+bool uprobe_single_step_handler(struct pt_regs *regs);
+
+#endif /* _ASM_RISCV_UPROBES_H */
diff --git a/arch/riscv/include/asm/vdso.h b/arch/riscv/include/asm/vdso.h
new file mode 100644
index 000000000..af981426f
--- /dev/null
+++ b/arch/riscv/include/asm/vdso.h
@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 ARM Limited
+ * Copyright (C) 2014 Regents of the University of California
+ * Copyright (C) 2017 SiFive
+ */
+
+#ifndef _ASM_RISCV_VDSO_H
+#define _ASM_RISCV_VDSO_H
+
+/*
+ * All systems with an MMU have a VDSO, but systems without an MMU don't
+ * support shared libraries and therefor don't have one.
+ */
+#ifdef CONFIG_MMU
+
+#define __VVAR_PAGES    2
+
+#ifndef __ASSEMBLY__
+#include <generated/vdso-offsets.h>
+
+#define VDSO_SYMBOL(base, name)							\
+	(void __user *)((unsigned long)(base) + __vdso_##name##_offset)
+
+#ifdef CONFIG_COMPAT
+#include <generated/compat_vdso-offsets.h>
+
+#define COMPAT_VDSO_SYMBOL(base, name)						\
+	(void __user *)((unsigned long)(base) + compat__vdso_##name##_offset)
+
+#endif /* CONFIG_COMPAT */
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* CONFIG_MMU */
+
+#endif /* _ASM_RISCV_VDSO_H */
diff --git a/arch/riscv/include/asm/vdso/clocksource.h b/arch/riscv/include/asm/vdso/clocksource.h
new file mode 100644
index 000000000..df6ea65c1
--- /dev/null
+++ b/arch/riscv/include/asm/vdso/clocksource.h
@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_VDSOCLOCKSOURCE_H
+#define __ASM_VDSOCLOCKSOURCE_H
+
+#define VDSO_ARCH_CLOCKMODES	\
+	VDSO_CLOCKMODE_ARCHTIMER
+
+#endif
diff --git a/arch/riscv/include/asm/vdso/gettimeofday.h b/arch/riscv/include/asm/vdso/gettimeofday.h
new file mode 100644
index 000000000..77d9c2f72
--- /dev/null
+++ b/arch/riscv/include/asm/vdso/gettimeofday.h
@@ -0,0 +1,88 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_VDSO_GETTIMEOFDAY_H
+#define __ASM_VDSO_GETTIMEOFDAY_H
+
+#ifndef __ASSEMBLY__
+
+#include <asm/barrier.h>
+#include <asm/unistd.h>
+#include <asm/csr.h>
+#include <uapi/linux/time.h>
+
+#define VDSO_HAS_CLOCK_GETRES	1
+
+static __always_inline
+int gettimeofday_fallback(struct __kernel_old_timeval *_tv,
+			  struct timezone *_tz)
+{
+	register struct __kernel_old_timeval *tv asm("a0") = _tv;
+	register struct timezone *tz asm("a1") = _tz;
+	register long ret asm("a0");
+	register long nr asm("a7") = __NR_gettimeofday;
+
+	asm volatile ("ecall\n"
+		      : "=r" (ret)
+		      : "r"(tv), "r"(tz), "r"(nr)
+		      : "memory");
+
+	return ret;
+}
+
+static __always_inline
+long clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
+{
+	register clockid_t clkid asm("a0") = _clkid;
+	register struct __kernel_timespec *ts asm("a1") = _ts;
+	register long ret asm("a0");
+	register long nr asm("a7") = __NR_clock_gettime;
+
+	asm volatile ("ecall\n"
+		      : "=r" (ret)
+		      : "r"(clkid), "r"(ts), "r"(nr)
+		      : "memory");
+
+	return ret;
+}
+
+static __always_inline
+int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
+{
+	register clockid_t clkid asm("a0") = _clkid;
+	register struct __kernel_timespec *ts asm("a1") = _ts;
+	register long ret asm("a0");
+	register long nr asm("a7") = __NR_clock_getres;
+
+	asm volatile ("ecall\n"
+		      : "=r" (ret)
+		      : "r"(clkid), "r"(ts), "r"(nr)
+		      : "memory");
+
+	return ret;
+}
+
+static __always_inline u64 __arch_get_hw_counter(s32 clock_mode,
+						 const struct vdso_data *vd)
+{
+	/*
+	 * The purpose of csr_read(CSR_TIME) is to trap the system into
+	 * M-mode to obtain the value of CSR_TIME. Hence, unlike other
+	 * architecture, no fence instructions surround the csr_read()
+	 */
+	return csr_read(CSR_TIME);
+}
+
+static __always_inline const struct vdso_data *__arch_get_vdso_data(void)
+{
+	return _vdso_data;
+}
+
+#ifdef CONFIG_TIME_NS
+static __always_inline
+const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd)
+{
+	return _timens_data;
+}
+#endif
+#endif /* !__ASSEMBLY__ */
+
+#endif /* __ASM_VDSO_GETTIMEOFDAY_H */
diff --git a/arch/riscv/include/asm/vdso/processor.h b/arch/riscv/include/asm/vdso/processor.h
new file mode 100644
index 000000000..fa70cfe50
--- /dev/null
+++ b/arch/riscv/include/asm/vdso/processor.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef __ASM_VDSO_PROCESSOR_H
+#define __ASM_VDSO_PROCESSOR_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/jump_label.h>
+#include <asm/barrier.h>
+#include <asm/hwcap.h>
+
+static inline void cpu_relax(void)
+{
+	if (!static_branch_likely(&riscv_isa_ext_keys[RISCV_ISA_EXT_KEY_ZIHINTPAUSE])) {
+#ifdef __riscv_muldiv
+		int dummy;
+		/* In lieu of a halt instruction, induce a long-latency stall. */
+		__asm__ __volatile__ ("div %0, %0, zero" : "=r" (dummy));
+#endif
+	} else {
+		/*
+		 * Reduce instruction retirement.
+		 * This assumes the PC changes.
+		 */
+#ifdef CONFIG_TOOLCHAIN_HAS_ZIHINTPAUSE
+		__asm__ __volatile__ ("pause");
+#else
+		/* Encoding of the pause instruction */
+		__asm__ __volatile__ (".4byte 0x100000F");
+#endif
+	}
+	barrier();
+}
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __ASM_VDSO_PROCESSOR_H */
diff --git a/arch/riscv/include/asm/vdso/vsyscall.h b/arch/riscv/include/asm/vdso/vsyscall.h
new file mode 100644
index 000000000..82fd5d83b
--- /dev/null
+++ b/arch/riscv/include/asm/vdso/vsyscall.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_VDSO_VSYSCALL_H
+#define __ASM_VDSO_VSYSCALL_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/timekeeper_internal.h>
+#include <vdso/datapage.h>
+
+extern struct vdso_data *vdso_data;
+
+/*
+ * Update the vDSO data page to keep in sync with kernel timekeeping.
+ */
+static __always_inline struct vdso_data *__riscv_get_k_vdso_data(void)
+{
+	return vdso_data;
+}
+
+#define __arch_get_k_vdso_data __riscv_get_k_vdso_data
+
+/* The asm-generic header needs to be included after the definitions above */
+#include <asm-generic/vdso/vsyscall.h>
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* __ASM_VDSO_VSYSCALL_H */
diff --git a/arch/riscv/include/asm/vendorid_list.h b/arch/riscv/include/asm/vendorid_list.h
new file mode 100644
index 000000000..cb89af3f0
--- /dev/null
+++ b/arch/riscv/include/asm/vendorid_list.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2021 SiFive
+ */
+#ifndef ASM_VENDOR_LIST_H
+#define ASM_VENDOR_LIST_H
+
+#define SIFIVE_VENDOR_ID	0x489
+#define THEAD_VENDOR_ID		0x5b7
+
+#endif
diff --git a/arch/riscv/include/asm/vermagic.h b/arch/riscv/include/asm/vermagic.h
new file mode 100644
index 000000000..7b9441a57
--- /dev/null
+++ b/arch/riscv/include/asm/vermagic.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2017 Andes Technology Corporation */
+
+#ifndef _ASM_VERMAGIC_H
+#define _ASM_VERMAGIC_H
+
+#define MODULE_ARCH_VERMAGIC    "riscv"
+
+#endif /* _ASM_VERMAGIC_H */
diff --git a/arch/riscv/include/asm/vmalloc.h b/arch/riscv/include/asm/vmalloc.h
new file mode 100644
index 000000000..ff9abc00d
--- /dev/null
+++ b/arch/riscv/include/asm/vmalloc.h
@@ -0,0 +1,4 @@
+#ifndef _ASM_RISCV_VMALLOC_H
+#define _ASM_RISCV_VMALLOC_H
+
+#endif /* _ASM_RISCV_VMALLOC_H */
diff --git a/arch/riscv/include/asm/word-at-a-time.h b/arch/riscv/include/asm/word-at-a-time.h
new file mode 100644
index 000000000..7c086ac6e
--- /dev/null
+++ b/arch/riscv/include/asm/word-at-a-time.h
@@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * Derived from arch/x86/include/asm/word-at-a-time.h
+ */
+
+#ifndef _ASM_RISCV_WORD_AT_A_TIME_H
+#define _ASM_RISCV_WORD_AT_A_TIME_H
+
+
+#include <linux/kernel.h>
+
+struct word_at_a_time {
+	const unsigned long one_bits, high_bits;
+};
+
+#define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0x01), REPEAT_BYTE(0x80) }
+
+static inline unsigned long has_zero(unsigned long val,
+	unsigned long *bits, const struct word_at_a_time *c)
+{
+	unsigned long mask = ((val - c->one_bits) & ~val) & c->high_bits;
+	*bits = mask;
+	return mask;
+}
+
+static inline unsigned long prep_zero_mask(unsigned long val,
+	unsigned long bits, const struct word_at_a_time *c)
+{
+	return bits;
+}
+
+static inline unsigned long create_zero_mask(unsigned long bits)
+{
+	bits = (bits - 1) & ~bits;
+	return bits >> 7;
+}
+
+static inline unsigned long find_zero(unsigned long mask)
+{
+	return fls64(mask) >> 3;
+}
+
+/* The mask we created is directly usable as a bytemask */
+#define zero_bytemask(mask) (mask)
+
+#endif /* _ASM_RISCV_WORD_AT_A_TIME_H */
diff --git a/arch/riscv/include/asm/xip_fixup.h b/arch/riscv/include/asm/xip_fixup.h
new file mode 100644
index 000000000..b65bf6306
--- /dev/null
+++ b/arch/riscv/include/asm/xip_fixup.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * XIP fixup macros, only useful in assembly.
+ */
+#ifndef _ASM_RISCV_XIP_FIXUP_H
+#define _ASM_RISCV_XIP_FIXUP_H
+
+#include <linux/pgtable.h>
+
+#ifdef CONFIG_XIP_KERNEL
+.macro XIP_FIXUP_OFFSET reg
+        REG_L t0, _xip_fixup
+        add \reg, \reg, t0
+.endm
+.macro XIP_FIXUP_FLASH_OFFSET reg
+	la t0, __data_loc
+	REG_L t1, _xip_phys_offset
+	sub \reg, \reg, t1
+	add \reg, \reg, t0
+.endm
+
+_xip_fixup: .dword CONFIG_PHYS_RAM_BASE - CONFIG_XIP_PHYS_ADDR - XIP_OFFSET
+_xip_phys_offset: .dword CONFIG_XIP_PHYS_ADDR + XIP_OFFSET
+#else
+.macro XIP_FIXUP_OFFSET reg
+.endm
+.macro XIP_FIXUP_FLASH_OFFSET reg
+.endm
+#endif /* CONFIG_XIP_KERNEL */
+
+#endif
diff --git a/arch/riscv/include/uapi/asm/Kbuild b/arch/riscv/include/uapi/asm/Kbuild
new file mode 100644
index 000000000..f66554cd5
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/Kbuild
@@ -0,0 +1 @@
+# SPDX-License-Identifier: GPL-2.0
diff --git a/arch/riscv/include/uapi/asm/auxvec.h b/arch/riscv/include/uapi/asm/auxvec.h
new file mode 100644
index 000000000..fb187a33c
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/auxvec.h
@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2015 Regents of the University of California
+ */
+
+#ifndef _UAPI_ASM_RISCV_AUXVEC_H
+#define _UAPI_ASM_RISCV_AUXVEC_H
+
+/* vDSO location */
+#define AT_SYSINFO_EHDR 33
+
+/*
+ * The set of entries below represent more extensive information
+ * about the caches, in the form of two entry per cache type,
+ * one entry containing the cache size in bytes, and the other
+ * containing the cache line size in bytes in the bottom 16 bits
+ * and the cache associativity in the next 16 bits.
+ *
+ * The associativity is such that if N is the 16-bit value, the
+ * cache is N way set associative. A value if 0xffff means fully
+ * associative, a value of 1 means directly mapped.
+ *
+ * For all these fields, a value of 0 means that the information
+ * is not known.
+ */
+#define AT_L1I_CACHESIZE	40
+#define AT_L1I_CACHEGEOMETRY	41
+#define AT_L1D_CACHESIZE	42
+#define AT_L1D_CACHEGEOMETRY	43
+#define AT_L2_CACHESIZE		44
+#define AT_L2_CACHEGEOMETRY	45
+#define AT_L3_CACHESIZE		46
+#define AT_L3_CACHEGEOMETRY	47
+
+/* entries in ARCH_DLINFO */
+#define AT_VECTOR_SIZE_ARCH	9
+
+#endif /* _UAPI_ASM_RISCV_AUXVEC_H */
diff --git a/arch/riscv/include/uapi/asm/bitsperlong.h b/arch/riscv/include/uapi/asm/bitsperlong.h
new file mode 100644
index 000000000..7d0b32e3b
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/bitsperlong.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2015 Regents of the University of California
+ */
+
+#ifndef _UAPI_ASM_RISCV_BITSPERLONG_H
+#define _UAPI_ASM_RISCV_BITSPERLONG_H
+
+#define __BITS_PER_LONG (__SIZEOF_POINTER__ * 8)
+
+#include <asm-generic/bitsperlong.h>
+
+#endif /* _UAPI_ASM_RISCV_BITSPERLONG_H */
diff --git a/arch/riscv/include/uapi/asm/bpf_perf_event.h b/arch/riscv/include/uapi/asm/bpf_perf_event.h
new file mode 100644
index 000000000..6cb1c2823
--- /dev/null
+++ b/arch/riscv/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/riscv/include/uapi/asm/byteorder.h b/arch/riscv/include/uapi/asm/byteorder.h
new file mode 100644
index 000000000..f671e16bf
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/byteorder.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2015 Regents of the University of California
+ */
+
+#ifndef _UAPI_ASM_RISCV_BYTEORDER_H
+#define _UAPI_ASM_RISCV_BYTEORDER_H
+
+#include <linux/byteorder/little_endian.h>
+
+#endif /* _UAPI_ASM_RISCV_BYTEORDER_H */
diff --git a/arch/riscv/include/uapi/asm/elf.h b/arch/riscv/include/uapi/asm/elf.h
new file mode 100644
index 000000000..d696d6610
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/elf.h
@@ -0,0 +1,98 @@
+/*
+ * Copyright (C) 2003 Matjaz Breskvar <phoenix@bsemi.com>
+ * Copyright (C) 2010-2011 Jonas Bonn <jonas@southpole.se>
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef _UAPI_ASM_RISCV_ELF_H
+#define _UAPI_ASM_RISCV_ELF_H
+
+#include <asm/ptrace.h>
+
+/* ELF register definitions */
+typedef unsigned long elf_greg_t;
+typedef struct user_regs_struct elf_gregset_t;
+#define ELF_NGREG (sizeof(elf_gregset_t) / sizeof(elf_greg_t))
+
+/* We don't support f without d, or q.  */
+typedef __u64 elf_fpreg_t;
+typedef union __riscv_fp_state elf_fpregset_t;
+#define ELF_NFPREG (sizeof(struct __riscv_d_ext_state) / sizeof(elf_fpreg_t))
+
+#if __riscv_xlen == 64
+#define ELF_RISCV_R_SYM(r_info)		ELF64_R_SYM(r_info)
+#define ELF_RISCV_R_TYPE(r_info)	ELF64_R_TYPE(r_info)
+#else
+#define ELF_RISCV_R_SYM(r_info)		ELF32_R_SYM(r_info)
+#define ELF_RISCV_R_TYPE(r_info)	ELF32_R_TYPE(r_info)
+#endif
+
+/*
+ * RISC-V relocation types
+ */
+
+/* Relocation types used by the dynamic linker */
+#define R_RISCV_NONE		0
+#define R_RISCV_32		1
+#define R_RISCV_64		2
+#define R_RISCV_RELATIVE	3
+#define R_RISCV_COPY		4
+#define R_RISCV_JUMP_SLOT	5
+#define R_RISCV_TLS_DTPMOD32	6
+#define R_RISCV_TLS_DTPMOD64	7
+#define R_RISCV_TLS_DTPREL32	8
+#define R_RISCV_TLS_DTPREL64	9
+#define R_RISCV_TLS_TPREL32	10
+#define R_RISCV_TLS_TPREL64	11
+
+/* Relocation types not used by the dynamic linker */
+#define R_RISCV_BRANCH		16
+#define R_RISCV_JAL		17
+#define R_RISCV_CALL		18
+#define R_RISCV_CALL_PLT	19
+#define R_RISCV_GOT_HI20	20
+#define R_RISCV_TLS_GOT_HI20	21
+#define R_RISCV_TLS_GD_HI20	22
+#define R_RISCV_PCREL_HI20	23
+#define R_RISCV_PCREL_LO12_I	24
+#define R_RISCV_PCREL_LO12_S	25
+#define R_RISCV_HI20		26
+#define R_RISCV_LO12_I		27
+#define R_RISCV_LO12_S		28
+#define R_RISCV_TPREL_HI20	29
+#define R_RISCV_TPREL_LO12_I	30
+#define R_RISCV_TPREL_LO12_S	31
+#define R_RISCV_TPREL_ADD	32
+#define R_RISCV_ADD8		33
+#define R_RISCV_ADD16		34
+#define R_RISCV_ADD32		35
+#define R_RISCV_ADD64		36
+#define R_RISCV_SUB8		37
+#define R_RISCV_SUB16		38
+#define R_RISCV_SUB32		39
+#define R_RISCV_SUB64		40
+#define R_RISCV_GNU_VTINHERIT	41
+#define R_RISCV_GNU_VTENTRY	42
+#define R_RISCV_ALIGN		43
+#define R_RISCV_RVC_BRANCH	44
+#define R_RISCV_RVC_JUMP	45
+#define R_RISCV_LUI		46
+#define R_RISCV_GPREL_I		47
+#define R_RISCV_GPREL_S		48
+#define R_RISCV_TPREL_I		49
+#define R_RISCV_TPREL_S		50
+#define R_RISCV_RELAX		51
+#define R_RISCV_SUB6		52
+#define R_RISCV_SET6		53
+#define R_RISCV_SET8		54
+#define R_RISCV_SET16		55
+#define R_RISCV_SET32		56
+#define R_RISCV_32_PCREL	57
+
+
+#endif /* _UAPI_ASM_RISCV_ELF_H */
diff --git a/arch/riscv/include/uapi/asm/hwcap.h b/arch/riscv/include/uapi/asm/hwcap.h
new file mode 100644
index 000000000..46dc3f5ee
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/hwcap.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */
+/*
+ * Copied from arch/arm64/include/asm/hwcap.h
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2017 SiFive
+ */
+#ifndef _UAPI_ASM_RISCV_HWCAP_H
+#define _UAPI_ASM_RISCV_HWCAP_H
+
+/*
+ * Linux saves the floating-point registers according to the ISA Linux is
+ * executing on, as opposed to the ISA the user program is compiled for.  This
+ * is necessary for a handful of esoteric use cases: for example, userspace
+ * threading libraries must be able to examine the actual machine state in
+ * order to fully reconstruct the state of a thread.
+ */
+#define COMPAT_HWCAP_ISA_I	(1 << ('I' - 'A'))
+#define COMPAT_HWCAP_ISA_M	(1 << ('M' - 'A'))
+#define COMPAT_HWCAP_ISA_A	(1 << ('A' - 'A'))
+#define COMPAT_HWCAP_ISA_F	(1 << ('F' - 'A'))
+#define COMPAT_HWCAP_ISA_D	(1 << ('D' - 'A'))
+#define COMPAT_HWCAP_ISA_C	(1 << ('C' - 'A'))
+
+#endif /* _UAPI_ASM_RISCV_HWCAP_H */
diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h
new file mode 100644
index 000000000..8985ff234
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/kvm.h
@@ -0,0 +1,154 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2019 Western Digital Corporation or its affiliates.
+ *
+ * Authors:
+ *     Anup Patel <anup.patel@wdc.com>
+ */
+
+#ifndef __LINUX_KVM_RISCV_H
+#define __LINUX_KVM_RISCV_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+#include <asm/ptrace.h>
+
+#define __KVM_HAVE_READONLY_MEM
+
+#define KVM_COALESCED_MMIO_PAGE_OFFSET 1
+
+#define KVM_INTERRUPT_SET	-1U
+#define KVM_INTERRUPT_UNSET	-2U
+
+/* for KVM_GET_REGS and KVM_SET_REGS */
+struct kvm_regs {
+};
+
+/* for KVM_GET_FPU and KVM_SET_FPU */
+struct kvm_fpu {
+};
+
+/* KVM Debug exit structure */
+struct kvm_debug_exit_arch {
+};
+
+/* for KVM_SET_GUEST_DEBUG */
+struct kvm_guest_debug_arch {
+};
+
+/* definition of registers in kvm_run */
+struct kvm_sync_regs {
+};
+
+/* for KVM_GET_SREGS and KVM_SET_SREGS */
+struct kvm_sregs {
+};
+
+/* CONFIG registers for KVM_GET_ONE_REG and KVM_SET_ONE_REG */
+struct kvm_riscv_config {
+	unsigned long isa;
+	unsigned long zicbom_block_size;
+};
+
+/* CORE registers for KVM_GET_ONE_REG and KVM_SET_ONE_REG */
+struct kvm_riscv_core {
+	struct user_regs_struct regs;
+	unsigned long mode;
+};
+
+/* Possible privilege modes for kvm_riscv_core */
+#define KVM_RISCV_MODE_S	1
+#define KVM_RISCV_MODE_U	0
+
+/* CSR registers for KVM_GET_ONE_REG and KVM_SET_ONE_REG */
+struct kvm_riscv_csr {
+	unsigned long sstatus;
+	unsigned long sie;
+	unsigned long stvec;
+	unsigned long sscratch;
+	unsigned long sepc;
+	unsigned long scause;
+	unsigned long stval;
+	unsigned long sip;
+	unsigned long satp;
+	unsigned long scounteren;
+};
+
+/* TIMER registers for KVM_GET_ONE_REG and KVM_SET_ONE_REG */
+struct kvm_riscv_timer {
+	__u64 frequency;
+	__u64 time;
+	__u64 compare;
+	__u64 state;
+};
+
+/*
+ * ISA extension IDs specific to KVM. This is not the same as the host ISA
+ * extension IDs as that is internal to the host and should not be exposed
+ * to the guest. This should always be contiguous to keep the mapping simple
+ * in KVM implementation.
+ */
+enum KVM_RISCV_ISA_EXT_ID {
+	KVM_RISCV_ISA_EXT_A = 0,
+	KVM_RISCV_ISA_EXT_C,
+	KVM_RISCV_ISA_EXT_D,
+	KVM_RISCV_ISA_EXT_F,
+	KVM_RISCV_ISA_EXT_H,
+	KVM_RISCV_ISA_EXT_I,
+	KVM_RISCV_ISA_EXT_M,
+	KVM_RISCV_ISA_EXT_SVPBMT,
+	KVM_RISCV_ISA_EXT_SSTC,
+	KVM_RISCV_ISA_EXT_SVINVAL,
+	KVM_RISCV_ISA_EXT_ZIHINTPAUSE,
+	KVM_RISCV_ISA_EXT_ZICBOM,
+	KVM_RISCV_ISA_EXT_MAX,
+};
+
+/* Possible states for kvm_riscv_timer */
+#define KVM_RISCV_TIMER_STATE_OFF	0
+#define KVM_RISCV_TIMER_STATE_ON	1
+
+#define KVM_REG_SIZE(id)		\
+	(1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT))
+
+/* If you need to interpret the index values, here is the key: */
+#define KVM_REG_RISCV_TYPE_MASK		0x00000000FF000000
+#define KVM_REG_RISCV_TYPE_SHIFT	24
+
+/* Config registers are mapped as type 1 */
+#define KVM_REG_RISCV_CONFIG		(0x01 << KVM_REG_RISCV_TYPE_SHIFT)
+#define KVM_REG_RISCV_CONFIG_REG(name)	\
+	(offsetof(struct kvm_riscv_config, name) / sizeof(unsigned long))
+
+/* Core registers are mapped as type 2 */
+#define KVM_REG_RISCV_CORE		(0x02 << KVM_REG_RISCV_TYPE_SHIFT)
+#define KVM_REG_RISCV_CORE_REG(name)	\
+		(offsetof(struct kvm_riscv_core, name) / sizeof(unsigned long))
+
+/* Control and status registers are mapped as type 3 */
+#define KVM_REG_RISCV_CSR		(0x03 << KVM_REG_RISCV_TYPE_SHIFT)
+#define KVM_REG_RISCV_CSR_REG(name)	\
+		(offsetof(struct kvm_riscv_csr, name) / sizeof(unsigned long))
+
+/* Timer registers are mapped as type 4 */
+#define KVM_REG_RISCV_TIMER		(0x04 << KVM_REG_RISCV_TYPE_SHIFT)
+#define KVM_REG_RISCV_TIMER_REG(name)	\
+		(offsetof(struct kvm_riscv_timer, name) / sizeof(__u64))
+
+/* F extension registers are mapped as type 5 */
+#define KVM_REG_RISCV_FP_F		(0x05 << KVM_REG_RISCV_TYPE_SHIFT)
+#define KVM_REG_RISCV_FP_F_REG(name)	\
+		(offsetof(struct __riscv_f_ext_state, name) / sizeof(__u32))
+
+/* D extension registers are mapped as type 6 */
+#define KVM_REG_RISCV_FP_D		(0x06 << KVM_REG_RISCV_TYPE_SHIFT)
+#define KVM_REG_RISCV_FP_D_REG(name)	\
+		(offsetof(struct __riscv_d_ext_state, name) / sizeof(__u64))
+
+/* ISA Extension registers are mapped as type 7 */
+#define KVM_REG_RISCV_ISA_EXT		(0x07 << KVM_REG_RISCV_TYPE_SHIFT)
+
+#endif
+
+#endif /* __LINUX_KVM_RISCV_H */
diff --git a/arch/riscv/include/uapi/asm/perf_regs.h b/arch/riscv/include/uapi/asm/perf_regs.h
new file mode 100644
index 000000000..196f964bf
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/perf_regs.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd. */
+
+#ifndef _ASM_RISCV_PERF_REGS_H
+#define _ASM_RISCV_PERF_REGS_H
+
+enum perf_event_riscv_regs {
+	PERF_REG_RISCV_PC,
+	PERF_REG_RISCV_RA,
+	PERF_REG_RISCV_SP,
+	PERF_REG_RISCV_GP,
+	PERF_REG_RISCV_TP,
+	PERF_REG_RISCV_T0,
+	PERF_REG_RISCV_T1,
+	PERF_REG_RISCV_T2,
+	PERF_REG_RISCV_S0,
+	PERF_REG_RISCV_S1,
+	PERF_REG_RISCV_A0,
+	PERF_REG_RISCV_A1,
+	PERF_REG_RISCV_A2,
+	PERF_REG_RISCV_A3,
+	PERF_REG_RISCV_A4,
+	PERF_REG_RISCV_A5,
+	PERF_REG_RISCV_A6,
+	PERF_REG_RISCV_A7,
+	PERF_REG_RISCV_S2,
+	PERF_REG_RISCV_S3,
+	PERF_REG_RISCV_S4,
+	PERF_REG_RISCV_S5,
+	PERF_REG_RISCV_S6,
+	PERF_REG_RISCV_S7,
+	PERF_REG_RISCV_S8,
+	PERF_REG_RISCV_S9,
+	PERF_REG_RISCV_S10,
+	PERF_REG_RISCV_S11,
+	PERF_REG_RISCV_T3,
+	PERF_REG_RISCV_T4,
+	PERF_REG_RISCV_T5,
+	PERF_REG_RISCV_T6,
+	PERF_REG_RISCV_MAX,
+};
+#endif /* _ASM_RISCV_PERF_REGS_H */
diff --git a/arch/riscv/include/uapi/asm/ptrace.h b/arch/riscv/include/uapi/asm/ptrace.h
new file mode 100644
index 000000000..882547f6b
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/ptrace.h
@@ -0,0 +1,82 @@
+/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ */
+
+#ifndef _UAPI_ASM_RISCV_PTRACE_H
+#define _UAPI_ASM_RISCV_PTRACE_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+
+/*
+ * User-mode register state for core dumps, ptrace, sigcontext
+ *
+ * This decouples struct pt_regs from the userspace ABI.
+ * struct user_regs_struct must form a prefix of struct pt_regs.
+ */
+struct user_regs_struct {
+	unsigned long pc;
+	unsigned long ra;
+	unsigned long sp;
+	unsigned long gp;
+	unsigned long tp;
+	unsigned long t0;
+	unsigned long t1;
+	unsigned long t2;
+	unsigned long s0;
+	unsigned long s1;
+	unsigned long a0;
+	unsigned long a1;
+	unsigned long a2;
+	unsigned long a3;
+	unsigned long a4;
+	unsigned long a5;
+	unsigned long a6;
+	unsigned long a7;
+	unsigned long s2;
+	unsigned long s3;
+	unsigned long s4;
+	unsigned long s5;
+	unsigned long s6;
+	unsigned long s7;
+	unsigned long s8;
+	unsigned long s9;
+	unsigned long s10;
+	unsigned long s11;
+	unsigned long t3;
+	unsigned long t4;
+	unsigned long t5;
+	unsigned long t6;
+};
+
+struct __riscv_f_ext_state {
+	__u32 f[32];
+	__u32 fcsr;
+};
+
+struct __riscv_d_ext_state {
+	__u64 f[32];
+	__u32 fcsr;
+};
+
+struct __riscv_q_ext_state {
+	__u64 f[64] __attribute__((aligned(16)));
+	__u32 fcsr;
+	/*
+	 * Reserved for expansion of sigcontext structure.  Currently zeroed
+	 * upon signal, and must be zero upon sigreturn.
+	 */
+	__u32 reserved[3];
+};
+
+union __riscv_fp_state {
+	struct __riscv_f_ext_state f;
+	struct __riscv_d_ext_state d;
+	struct __riscv_q_ext_state q;
+};
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _UAPI_ASM_RISCV_PTRACE_H */
diff --git a/arch/riscv/include/uapi/asm/setup.h b/arch/riscv/include/uapi/asm/setup.h
new file mode 100644
index 000000000..66b13a522
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/setup.h
@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */
+
+#ifndef _UAPI_ASM_RISCV_SETUP_H
+#define _UAPI_ASM_RISCV_SETUP_H
+
+#define COMMAND_LINE_SIZE	1024
+
+#endif /* _UAPI_ASM_RISCV_SETUP_H */
diff --git a/arch/riscv/include/uapi/asm/sigcontext.h b/arch/riscv/include/uapi/asm/sigcontext.h
new file mode 100644
index 000000000..84f2dfcfd
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/sigcontext.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ */
+
+#ifndef _UAPI_ASM_RISCV_SIGCONTEXT_H
+#define _UAPI_ASM_RISCV_SIGCONTEXT_H
+
+#include <asm/ptrace.h>
+
+/*
+ * Signal context structure
+ *
+ * This contains the context saved before a signal handler is invoked;
+ * it is restored by sys_sigreturn / sys_rt_sigreturn.
+ */
+struct sigcontext {
+	struct user_regs_struct sc_regs;
+	union __riscv_fp_state sc_fpregs;
+};
+
+#endif /* _UAPI_ASM_RISCV_SIGCONTEXT_H */
diff --git a/arch/riscv/include/uapi/asm/ucontext.h b/arch/riscv/include/uapi/asm/ucontext.h
new file mode 100644
index 000000000..44eb99395
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/ucontext.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2017 SiFive, Inc.
+ *
+ * This file was copied from arch/arm64/include/uapi/asm/ucontext.h
+ */
+#ifndef _UAPI_ASM_RISCV_UCONTEXT_H
+#define _UAPI_ASM_RISCV_UCONTEXT_H
+
+#include <linux/types.h>
+
+struct ucontext {
+	unsigned long	  uc_flags;
+	struct ucontext	 *uc_link;
+	stack_t		  uc_stack;
+	sigset_t	  uc_sigmask;
+	/* There's some padding here to allow sigset_t to be expanded in the
+	 * future.  Though this is unlikely, other architectures put uc_sigmask
+	 * at the end of this structure and explicitly state it can be
+	 * expanded, so we didn't want to box ourselves in here. */
+	__u8		  __unused[1024 / 8 - sizeof(sigset_t)];
+	/* We can't put uc_sigmask at the end of this structure because we need
+	 * to be able to expand sigcontext in the future.  For example, the
+	 * vector ISA extension will almost certainly add ISA state.  We want
+	 * to ensure all user-visible ISA state can be saved and restored via a
+	 * ucontext, so we're putting this at the end in order to allow for
+	 * infinite extensibility.  Since we know this will be extended and we
+	 * assume sigset_t won't be extended an extreme amount, we're
+	 * prioritizing this. */
+	struct sigcontext uc_mcontext;
+};
+
+#endif /* _UAPI_ASM_RISCV_UCONTEXT_H */
diff --git a/arch/riscv/include/uapi/asm/unistd.h b/arch/riscv/include/uapi/asm/unistd.h
new file mode 100644
index 000000000..73d7cdd2e
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/unistd.h
@@ -0,0 +1,45 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2018 David Abdurachmanov <david.abdurachmanov@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <https://www.gnu.org/licenses/>.
+ */
+
+#if defined(__LP64__) && !defined(__SYSCALL_COMPAT)
+#define __ARCH_WANT_NEW_STAT
+#define __ARCH_WANT_SET_GET_RLIMIT
+#endif /* __LP64__ */
+
+#define __ARCH_WANT_SYS_CLONE3
+#define __ARCH_WANT_MEMFD_SECRET
+
+#include <asm-generic/unistd.h>
+
+/*
+ * Allows the instruction cache to be flushed from userspace.  Despite RISC-V
+ * having a direct 'fence.i' instruction available to userspace (which we
+ * can't trap!), that's not actually viable when running on Linux because the
+ * kernel might schedule a process on another hart.  There is no way for
+ * userspace to handle this without invoking the kernel (as it doesn't know the
+ * thread->hart mappings), so we've defined a RISC-V specific system call to
+ * flush the instruction cache.
+ *
+ * __NR_riscv_flush_icache is defined to flush the instruction cache over an
+ * address range, with the flush applying to either all threads or just the
+ * caller.  We don't currently do anything with the address range, that's just
+ * in there for forwards compatibility.
+ */
+#ifndef __NR_riscv_flush_icache
+#define __NR_riscv_flush_icache (__NR_arch_specific_syscall + 15)
+#endif
+__SYSCALL(__NR_riscv_flush_icache, sys_riscv_flush_icache)
diff --git a/arch/riscv/kernel/.gitignore b/arch/riscv/kernel/.gitignore
new file mode 100644
index 000000000..e052ed331
--- /dev/null
+++ b/arch/riscv/kernel/.gitignore
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+/vmlinux.lds
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
new file mode 100644
index 000000000..ab333cb79
--- /dev/null
+++ b/arch/riscv/kernel/Makefile
@@ -0,0 +1,91 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Makefile for the RISC-V Linux kernel
+#
+
+ifdef CONFIG_FTRACE
+CFLAGS_REMOVE_ftrace.o	= $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_patch.o	= $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_sbi.o	= $(CC_FLAGS_FTRACE)
+endif
+CFLAGS_syscall_table.o	+= $(call cc-option,-Wno-override-init,)
+CFLAGS_compat_syscall_table.o += $(call cc-option,-Wno-override-init,)
+
+ifdef CONFIG_KEXEC
+AFLAGS_kexec_relocate.o := -mcmodel=medany $(call cc-option,-mno-relax)
+endif
+
+# cmodel=medany and notrace when patching early
+ifdef CONFIG_RISCV_ALTERNATIVE_EARLY
+CFLAGS_alternative.o := -mcmodel=medany
+CFLAGS_cpufeature.o := -mcmodel=medany
+ifdef CONFIG_FTRACE
+CFLAGS_REMOVE_alternative.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_cpufeature.o = $(CC_FLAGS_FTRACE)
+endif
+ifdef CONFIG_KASAN
+KASAN_SANITIZE_alternative.o := n
+KASAN_SANITIZE_cpufeature.o := n
+endif
+endif
+
+extra-y += vmlinux.lds
+
+obj-y	+= head.o
+obj-y	+= soc.o
+obj-$(CONFIG_RISCV_ALTERNATIVE) += alternative.o
+obj-y	+= cpu.o
+obj-y	+= cpufeature.o
+obj-y	+= entry.o
+obj-y	+= irq.o
+obj-y	+= process.o
+obj-y	+= ptrace.o
+obj-y	+= reset.o
+obj-y	+= setup.o
+obj-y	+= signal.o
+obj-y	+= syscall_table.o
+obj-y	+= sys_riscv.o
+obj-y	+= time.o
+obj-y	+= traps.o
+obj-y	+= riscv_ksyms.o
+obj-y	+= stacktrace.o
+obj-y	+= cacheinfo.o
+obj-y	+= patch.o
+obj-y	+= probes/
+obj-$(CONFIG_MMU) += vdso.o vdso/
+
+obj-$(CONFIG_RISCV_M_MODE)	+= traps_misaligned.o
+obj-$(CONFIG_FPU)		+= fpu.o
+obj-$(CONFIG_SMP)		+= smpboot.o
+obj-$(CONFIG_SMP)		+= smp.o
+obj-$(CONFIG_SMP)		+= cpu_ops.o
+
+obj-$(CONFIG_RISCV_BOOT_SPINWAIT) += cpu_ops_spinwait.o
+obj-$(CONFIG_MODULES)		+= module.o
+obj-$(CONFIG_MODULE_SECTIONS)	+= module-sections.o
+
+obj-$(CONFIG_CPU_PM)		+= suspend_entry.o suspend.o
+
+obj-$(CONFIG_FUNCTION_TRACER)	+= mcount.o ftrace.o
+obj-$(CONFIG_DYNAMIC_FTRACE)	+= mcount-dyn.o
+
+obj-$(CONFIG_TRACE_IRQFLAGS)	+= trace_irq.o
+
+obj-$(CONFIG_PERF_EVENTS)	+= perf_callchain.o
+obj-$(CONFIG_HAVE_PERF_REGS)	+= perf_regs.o
+obj-$(CONFIG_RISCV_SBI)		+= sbi.o
+ifeq ($(CONFIG_RISCV_SBI), y)
+obj-$(CONFIG_SMP) += cpu_ops_sbi.o
+endif
+obj-$(CONFIG_HOTPLUG_CPU)	+= cpu-hotplug.o
+obj-$(CONFIG_KGDB)		+= kgdb.o
+obj-$(CONFIG_KEXEC_CORE)	+= kexec_relocate.o crash_save_regs.o machine_kexec.o
+obj-$(CONFIG_KEXEC_FILE)	+= elf_kexec.o machine_kexec_file.o
+obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
+
+obj-$(CONFIG_JUMP_LABEL)	+= jump_label.o
+
+obj-$(CONFIG_EFI)		+= efi.o
+obj-$(CONFIG_COMPAT)		+= compat_syscall_table.o
+obj-$(CONFIG_COMPAT)		+= compat_signal.o
+obj-$(CONFIG_COMPAT)		+= compat_vdso/
diff --git a/arch/riscv/kernel/alternative.c b/arch/riscv/kernel/alternative.c
new file mode 100644
index 000000000..a7d26a00b
--- /dev/null
+++ b/arch/riscv/kernel/alternative.c
@@ -0,0 +1,118 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * alternative runtime patching
+ * inspired by the ARM64 and x86 version
+ *
+ * Copyright (C) 2021 Sifive.
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/cpu.h>
+#include <linux/uaccess.h>
+#include <asm/alternative.h>
+#include <asm/sections.h>
+#include <asm/vendorid_list.h>
+#include <asm/sbi.h>
+#include <asm/csr.h>
+
+struct cpu_manufacturer_info_t {
+	unsigned long vendor_id;
+	unsigned long arch_id;
+	unsigned long imp_id;
+	void (*patch_func)(struct alt_entry *begin, struct alt_entry *end,
+				  unsigned long archid, unsigned long impid,
+				  unsigned int stage);
+};
+
+static void __init_or_module riscv_fill_cpu_mfr_info(struct cpu_manufacturer_info_t *cpu_mfr_info)
+{
+#ifdef CONFIG_RISCV_M_MODE
+	cpu_mfr_info->vendor_id = csr_read(CSR_MVENDORID);
+	cpu_mfr_info->arch_id = csr_read(CSR_MARCHID);
+	cpu_mfr_info->imp_id = csr_read(CSR_MIMPID);
+#else
+	cpu_mfr_info->vendor_id = sbi_get_mvendorid();
+	cpu_mfr_info->arch_id = sbi_get_marchid();
+	cpu_mfr_info->imp_id = sbi_get_mimpid();
+#endif
+
+	switch (cpu_mfr_info->vendor_id) {
+#ifdef CONFIG_ERRATA_SIFIVE
+	case SIFIVE_VENDOR_ID:
+		cpu_mfr_info->patch_func = sifive_errata_patch_func;
+		break;
+#endif
+#ifdef CONFIG_ERRATA_THEAD
+	case THEAD_VENDOR_ID:
+		cpu_mfr_info->patch_func = thead_errata_patch_func;
+		break;
+#endif
+	default:
+		cpu_mfr_info->patch_func = NULL;
+	}
+}
+
+/*
+ * This is called very early in the boot process (directly after we run
+ * a feature detect on the boot CPU). No need to worry about other CPUs
+ * here.
+ */
+static void __init_or_module _apply_alternatives(struct alt_entry *begin,
+						 struct alt_entry *end,
+						 unsigned int stage)
+{
+	struct cpu_manufacturer_info_t cpu_mfr_info;
+
+	riscv_fill_cpu_mfr_info(&cpu_mfr_info);
+
+	riscv_cpufeature_patch_func(begin, end, stage);
+
+	if (!cpu_mfr_info.patch_func)
+		return;
+
+	cpu_mfr_info.patch_func(begin, end,
+				cpu_mfr_info.arch_id,
+				cpu_mfr_info.imp_id,
+				stage);
+}
+
+void __init apply_boot_alternatives(void)
+{
+	/* If called on non-boot cpu things could go wrong */
+	WARN_ON(smp_processor_id() != 0);
+
+	_apply_alternatives((struct alt_entry *)__alt_start,
+			    (struct alt_entry *)__alt_end,
+			    RISCV_ALTERNATIVES_BOOT);
+}
+
+/*
+ * apply_early_boot_alternatives() is called from setup_vm() with MMU-off.
+ *
+ * Following requirements should be honoured for it to work correctly:
+ * 1) It should use PC-relative addressing for accessing kernel symbols.
+ *    To achieve this we always use GCC cmodel=medany.
+ * 2) The compiler instrumentation for FTRACE will not work for setup_vm()
+ *    so disable compiler instrumentation when FTRACE is enabled.
+ *
+ * Currently, the above requirements are honoured by using custom CFLAGS
+ * for alternative.o in kernel/Makefile.
+ */
+void __init apply_early_boot_alternatives(void)
+{
+#ifdef CONFIG_RISCV_ALTERNATIVE_EARLY
+	_apply_alternatives((struct alt_entry *)__alt_start,
+			    (struct alt_entry *)__alt_end,
+			    RISCV_ALTERNATIVES_EARLY_BOOT);
+#endif
+}
+
+#ifdef CONFIG_MODULES
+void apply_module_alternatives(void *start, size_t length)
+{
+	_apply_alternatives((struct alt_entry *)start,
+			    (struct alt_entry *)(start + length),
+			    RISCV_ALTERNATIVES_MODULE);
+}
+#endif
diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c
new file mode 100644
index 000000000..df9444397
--- /dev/null
+++ b/arch/riscv/kernel/asm-offsets.c
@@ -0,0 +1,477 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ * Copyright (C) 2017 SiFive
+ */
+
+#define GENERATING_ASM_OFFSETS
+
+#include <linux/kbuild.h>
+#include <linux/mm.h>
+#include <linux/sched.h>
+#include <asm/kvm_host.h>
+#include <asm/thread_info.h>
+#include <asm/ptrace.h>
+#include <asm/cpu_ops_sbi.h>
+#include <asm/suspend.h>
+
+void asm_offsets(void);
+
+void asm_offsets(void)
+{
+	OFFSET(TASK_THREAD_RA, task_struct, thread.ra);
+	OFFSET(TASK_THREAD_SP, task_struct, thread.sp);
+	OFFSET(TASK_THREAD_S0, task_struct, thread.s[0]);
+	OFFSET(TASK_THREAD_S1, task_struct, thread.s[1]);
+	OFFSET(TASK_THREAD_S2, task_struct, thread.s[2]);
+	OFFSET(TASK_THREAD_S3, task_struct, thread.s[3]);
+	OFFSET(TASK_THREAD_S4, task_struct, thread.s[4]);
+	OFFSET(TASK_THREAD_S5, task_struct, thread.s[5]);
+	OFFSET(TASK_THREAD_S6, task_struct, thread.s[6]);
+	OFFSET(TASK_THREAD_S7, task_struct, thread.s[7]);
+	OFFSET(TASK_THREAD_S8, task_struct, thread.s[8]);
+	OFFSET(TASK_THREAD_S9, task_struct, thread.s[9]);
+	OFFSET(TASK_THREAD_S10, task_struct, thread.s[10]);
+	OFFSET(TASK_THREAD_S11, task_struct, thread.s[11]);
+	OFFSET(TASK_TI_FLAGS, task_struct, thread_info.flags);
+	OFFSET(TASK_TI_PREEMPT_COUNT, task_struct, thread_info.preempt_count);
+	OFFSET(TASK_TI_KERNEL_SP, task_struct, thread_info.kernel_sp);
+	OFFSET(TASK_TI_USER_SP, task_struct, thread_info.user_sp);
+
+	OFFSET(TASK_THREAD_F0,  task_struct, thread.fstate.f[0]);
+	OFFSET(TASK_THREAD_F1,  task_struct, thread.fstate.f[1]);
+	OFFSET(TASK_THREAD_F2,  task_struct, thread.fstate.f[2]);
+	OFFSET(TASK_THREAD_F3,  task_struct, thread.fstate.f[3]);
+	OFFSET(TASK_THREAD_F4,  task_struct, thread.fstate.f[4]);
+	OFFSET(TASK_THREAD_F5,  task_struct, thread.fstate.f[5]);
+	OFFSET(TASK_THREAD_F6,  task_struct, thread.fstate.f[6]);
+	OFFSET(TASK_THREAD_F7,  task_struct, thread.fstate.f[7]);
+	OFFSET(TASK_THREAD_F8,  task_struct, thread.fstate.f[8]);
+	OFFSET(TASK_THREAD_F9,  task_struct, thread.fstate.f[9]);
+	OFFSET(TASK_THREAD_F10, task_struct, thread.fstate.f[10]);
+	OFFSET(TASK_THREAD_F11, task_struct, thread.fstate.f[11]);
+	OFFSET(TASK_THREAD_F12, task_struct, thread.fstate.f[12]);
+	OFFSET(TASK_THREAD_F13, task_struct, thread.fstate.f[13]);
+	OFFSET(TASK_THREAD_F14, task_struct, thread.fstate.f[14]);
+	OFFSET(TASK_THREAD_F15, task_struct, thread.fstate.f[15]);
+	OFFSET(TASK_THREAD_F16, task_struct, thread.fstate.f[16]);
+	OFFSET(TASK_THREAD_F17, task_struct, thread.fstate.f[17]);
+	OFFSET(TASK_THREAD_F18, task_struct, thread.fstate.f[18]);
+	OFFSET(TASK_THREAD_F19, task_struct, thread.fstate.f[19]);
+	OFFSET(TASK_THREAD_F20, task_struct, thread.fstate.f[20]);
+	OFFSET(TASK_THREAD_F21, task_struct, thread.fstate.f[21]);
+	OFFSET(TASK_THREAD_F22, task_struct, thread.fstate.f[22]);
+	OFFSET(TASK_THREAD_F23, task_struct, thread.fstate.f[23]);
+	OFFSET(TASK_THREAD_F24, task_struct, thread.fstate.f[24]);
+	OFFSET(TASK_THREAD_F25, task_struct, thread.fstate.f[25]);
+	OFFSET(TASK_THREAD_F26, task_struct, thread.fstate.f[26]);
+	OFFSET(TASK_THREAD_F27, task_struct, thread.fstate.f[27]);
+	OFFSET(TASK_THREAD_F28, task_struct, thread.fstate.f[28]);
+	OFFSET(TASK_THREAD_F29, task_struct, thread.fstate.f[29]);
+	OFFSET(TASK_THREAD_F30, task_struct, thread.fstate.f[30]);
+	OFFSET(TASK_THREAD_F31, task_struct, thread.fstate.f[31]);
+	OFFSET(TASK_THREAD_FCSR, task_struct, thread.fstate.fcsr);
+#ifdef CONFIG_STACKPROTECTOR
+	OFFSET(TSK_STACK_CANARY, task_struct, stack_canary);
+#endif
+
+	DEFINE(PT_SIZE, sizeof(struct pt_regs));
+	OFFSET(PT_EPC, pt_regs, epc);
+	OFFSET(PT_RA, pt_regs, ra);
+	OFFSET(PT_FP, pt_regs, s0);
+	OFFSET(PT_S0, pt_regs, s0);
+	OFFSET(PT_S1, pt_regs, s1);
+	OFFSET(PT_S2, pt_regs, s2);
+	OFFSET(PT_S3, pt_regs, s3);
+	OFFSET(PT_S4, pt_regs, s4);
+	OFFSET(PT_S5, pt_regs, s5);
+	OFFSET(PT_S6, pt_regs, s6);
+	OFFSET(PT_S7, pt_regs, s7);
+	OFFSET(PT_S8, pt_regs, s8);
+	OFFSET(PT_S9, pt_regs, s9);
+	OFFSET(PT_S10, pt_regs, s10);
+	OFFSET(PT_S11, pt_regs, s11);
+	OFFSET(PT_SP, pt_regs, sp);
+	OFFSET(PT_TP, pt_regs, tp);
+	OFFSET(PT_A0, pt_regs, a0);
+	OFFSET(PT_A1, pt_regs, a1);
+	OFFSET(PT_A2, pt_regs, a2);
+	OFFSET(PT_A3, pt_regs, a3);
+	OFFSET(PT_A4, pt_regs, a4);
+	OFFSET(PT_A5, pt_regs, a5);
+	OFFSET(PT_A6, pt_regs, a6);
+	OFFSET(PT_A7, pt_regs, a7);
+	OFFSET(PT_T0, pt_regs, t0);
+	OFFSET(PT_T1, pt_regs, t1);
+	OFFSET(PT_T2, pt_regs, t2);
+	OFFSET(PT_T3, pt_regs, t3);
+	OFFSET(PT_T4, pt_regs, t4);
+	OFFSET(PT_T5, pt_regs, t5);
+	OFFSET(PT_T6, pt_regs, t6);
+	OFFSET(PT_GP, pt_regs, gp);
+	OFFSET(PT_ORIG_A0, pt_regs, orig_a0);
+	OFFSET(PT_STATUS, pt_regs, status);
+	OFFSET(PT_BADADDR, pt_regs, badaddr);
+	OFFSET(PT_CAUSE, pt_regs, cause);
+
+	OFFSET(SUSPEND_CONTEXT_REGS, suspend_context, regs);
+
+	OFFSET(KVM_ARCH_GUEST_ZERO, kvm_vcpu_arch, guest_context.zero);
+	OFFSET(KVM_ARCH_GUEST_RA, kvm_vcpu_arch, guest_context.ra);
+	OFFSET(KVM_ARCH_GUEST_SP, kvm_vcpu_arch, guest_context.sp);
+	OFFSET(KVM_ARCH_GUEST_GP, kvm_vcpu_arch, guest_context.gp);
+	OFFSET(KVM_ARCH_GUEST_TP, kvm_vcpu_arch, guest_context.tp);
+	OFFSET(KVM_ARCH_GUEST_T0, kvm_vcpu_arch, guest_context.t0);
+	OFFSET(KVM_ARCH_GUEST_T1, kvm_vcpu_arch, guest_context.t1);
+	OFFSET(KVM_ARCH_GUEST_T2, kvm_vcpu_arch, guest_context.t2);
+	OFFSET(KVM_ARCH_GUEST_S0, kvm_vcpu_arch, guest_context.s0);
+	OFFSET(KVM_ARCH_GUEST_S1, kvm_vcpu_arch, guest_context.s1);
+	OFFSET(KVM_ARCH_GUEST_A0, kvm_vcpu_arch, guest_context.a0);
+	OFFSET(KVM_ARCH_GUEST_A1, kvm_vcpu_arch, guest_context.a1);
+	OFFSET(KVM_ARCH_GUEST_A2, kvm_vcpu_arch, guest_context.a2);
+	OFFSET(KVM_ARCH_GUEST_A3, kvm_vcpu_arch, guest_context.a3);
+	OFFSET(KVM_ARCH_GUEST_A4, kvm_vcpu_arch, guest_context.a4);
+	OFFSET(KVM_ARCH_GUEST_A5, kvm_vcpu_arch, guest_context.a5);
+	OFFSET(KVM_ARCH_GUEST_A6, kvm_vcpu_arch, guest_context.a6);
+	OFFSET(KVM_ARCH_GUEST_A7, kvm_vcpu_arch, guest_context.a7);
+	OFFSET(KVM_ARCH_GUEST_S2, kvm_vcpu_arch, guest_context.s2);
+	OFFSET(KVM_ARCH_GUEST_S3, kvm_vcpu_arch, guest_context.s3);
+	OFFSET(KVM_ARCH_GUEST_S4, kvm_vcpu_arch, guest_context.s4);
+	OFFSET(KVM_ARCH_GUEST_S5, kvm_vcpu_arch, guest_context.s5);
+	OFFSET(KVM_ARCH_GUEST_S6, kvm_vcpu_arch, guest_context.s6);
+	OFFSET(KVM_ARCH_GUEST_S7, kvm_vcpu_arch, guest_context.s7);
+	OFFSET(KVM_ARCH_GUEST_S8, kvm_vcpu_arch, guest_context.s8);
+	OFFSET(KVM_ARCH_GUEST_S9, kvm_vcpu_arch, guest_context.s9);
+	OFFSET(KVM_ARCH_GUEST_S10, kvm_vcpu_arch, guest_context.s10);
+	OFFSET(KVM_ARCH_GUEST_S11, kvm_vcpu_arch, guest_context.s11);
+	OFFSET(KVM_ARCH_GUEST_T3, kvm_vcpu_arch, guest_context.t3);
+	OFFSET(KVM_ARCH_GUEST_T4, kvm_vcpu_arch, guest_context.t4);
+	OFFSET(KVM_ARCH_GUEST_T5, kvm_vcpu_arch, guest_context.t5);
+	OFFSET(KVM_ARCH_GUEST_T6, kvm_vcpu_arch, guest_context.t6);
+	OFFSET(KVM_ARCH_GUEST_SEPC, kvm_vcpu_arch, guest_context.sepc);
+	OFFSET(KVM_ARCH_GUEST_SSTATUS, kvm_vcpu_arch, guest_context.sstatus);
+	OFFSET(KVM_ARCH_GUEST_HSTATUS, kvm_vcpu_arch, guest_context.hstatus);
+	OFFSET(KVM_ARCH_GUEST_SCOUNTEREN, kvm_vcpu_arch, guest_csr.scounteren);
+
+	OFFSET(KVM_ARCH_HOST_ZERO, kvm_vcpu_arch, host_context.zero);
+	OFFSET(KVM_ARCH_HOST_RA, kvm_vcpu_arch, host_context.ra);
+	OFFSET(KVM_ARCH_HOST_SP, kvm_vcpu_arch, host_context.sp);
+	OFFSET(KVM_ARCH_HOST_GP, kvm_vcpu_arch, host_context.gp);
+	OFFSET(KVM_ARCH_HOST_TP, kvm_vcpu_arch, host_context.tp);
+	OFFSET(KVM_ARCH_HOST_T0, kvm_vcpu_arch, host_context.t0);
+	OFFSET(KVM_ARCH_HOST_T1, kvm_vcpu_arch, host_context.t1);
+	OFFSET(KVM_ARCH_HOST_T2, kvm_vcpu_arch, host_context.t2);
+	OFFSET(KVM_ARCH_HOST_S0, kvm_vcpu_arch, host_context.s0);
+	OFFSET(KVM_ARCH_HOST_S1, kvm_vcpu_arch, host_context.s1);
+	OFFSET(KVM_ARCH_HOST_A0, kvm_vcpu_arch, host_context.a0);
+	OFFSET(KVM_ARCH_HOST_A1, kvm_vcpu_arch, host_context.a1);
+	OFFSET(KVM_ARCH_HOST_A2, kvm_vcpu_arch, host_context.a2);
+	OFFSET(KVM_ARCH_HOST_A3, kvm_vcpu_arch, host_context.a3);
+	OFFSET(KVM_ARCH_HOST_A4, kvm_vcpu_arch, host_context.a4);
+	OFFSET(KVM_ARCH_HOST_A5, kvm_vcpu_arch, host_context.a5);
+	OFFSET(KVM_ARCH_HOST_A6, kvm_vcpu_arch, host_context.a6);
+	OFFSET(KVM_ARCH_HOST_A7, kvm_vcpu_arch, host_context.a7);
+	OFFSET(KVM_ARCH_HOST_S2, kvm_vcpu_arch, host_context.s2);
+	OFFSET(KVM_ARCH_HOST_S3, kvm_vcpu_arch, host_context.s3);
+	OFFSET(KVM_ARCH_HOST_S4, kvm_vcpu_arch, host_context.s4);
+	OFFSET(KVM_ARCH_HOST_S5, kvm_vcpu_arch, host_context.s5);
+	OFFSET(KVM_ARCH_HOST_S6, kvm_vcpu_arch, host_context.s6);
+	OFFSET(KVM_ARCH_HOST_S7, kvm_vcpu_arch, host_context.s7);
+	OFFSET(KVM_ARCH_HOST_S8, kvm_vcpu_arch, host_context.s8);
+	OFFSET(KVM_ARCH_HOST_S9, kvm_vcpu_arch, host_context.s9);
+	OFFSET(KVM_ARCH_HOST_S10, kvm_vcpu_arch, host_context.s10);
+	OFFSET(KVM_ARCH_HOST_S11, kvm_vcpu_arch, host_context.s11);
+	OFFSET(KVM_ARCH_HOST_T3, kvm_vcpu_arch, host_context.t3);
+	OFFSET(KVM_ARCH_HOST_T4, kvm_vcpu_arch, host_context.t4);
+	OFFSET(KVM_ARCH_HOST_T5, kvm_vcpu_arch, host_context.t5);
+	OFFSET(KVM_ARCH_HOST_T6, kvm_vcpu_arch, host_context.t6);
+	OFFSET(KVM_ARCH_HOST_SEPC, kvm_vcpu_arch, host_context.sepc);
+	OFFSET(KVM_ARCH_HOST_SSTATUS, kvm_vcpu_arch, host_context.sstatus);
+	OFFSET(KVM_ARCH_HOST_HSTATUS, kvm_vcpu_arch, host_context.hstatus);
+	OFFSET(KVM_ARCH_HOST_SSCRATCH, kvm_vcpu_arch, host_sscratch);
+	OFFSET(KVM_ARCH_HOST_STVEC, kvm_vcpu_arch, host_stvec);
+	OFFSET(KVM_ARCH_HOST_SCOUNTEREN, kvm_vcpu_arch, host_scounteren);
+
+	OFFSET(KVM_ARCH_TRAP_SEPC, kvm_cpu_trap, sepc);
+	OFFSET(KVM_ARCH_TRAP_SCAUSE, kvm_cpu_trap, scause);
+	OFFSET(KVM_ARCH_TRAP_STVAL, kvm_cpu_trap, stval);
+	OFFSET(KVM_ARCH_TRAP_HTVAL, kvm_cpu_trap, htval);
+	OFFSET(KVM_ARCH_TRAP_HTINST, kvm_cpu_trap, htinst);
+
+	/* F extension */
+
+	OFFSET(KVM_ARCH_FP_F_F0, kvm_cpu_context, fp.f.f[0]);
+	OFFSET(KVM_ARCH_FP_F_F1, kvm_cpu_context, fp.f.f[1]);
+	OFFSET(KVM_ARCH_FP_F_F2, kvm_cpu_context, fp.f.f[2]);
+	OFFSET(KVM_ARCH_FP_F_F3, kvm_cpu_context, fp.f.f[3]);
+	OFFSET(KVM_ARCH_FP_F_F4, kvm_cpu_context, fp.f.f[4]);
+	OFFSET(KVM_ARCH_FP_F_F5, kvm_cpu_context, fp.f.f[5]);
+	OFFSET(KVM_ARCH_FP_F_F6, kvm_cpu_context, fp.f.f[6]);
+	OFFSET(KVM_ARCH_FP_F_F7, kvm_cpu_context, fp.f.f[7]);
+	OFFSET(KVM_ARCH_FP_F_F8, kvm_cpu_context, fp.f.f[8]);
+	OFFSET(KVM_ARCH_FP_F_F9, kvm_cpu_context, fp.f.f[9]);
+	OFFSET(KVM_ARCH_FP_F_F10, kvm_cpu_context, fp.f.f[10]);
+	OFFSET(KVM_ARCH_FP_F_F11, kvm_cpu_context, fp.f.f[11]);
+	OFFSET(KVM_ARCH_FP_F_F12, kvm_cpu_context, fp.f.f[12]);
+	OFFSET(KVM_ARCH_FP_F_F13, kvm_cpu_context, fp.f.f[13]);
+	OFFSET(KVM_ARCH_FP_F_F14, kvm_cpu_context, fp.f.f[14]);
+	OFFSET(KVM_ARCH_FP_F_F15, kvm_cpu_context, fp.f.f[15]);
+	OFFSET(KVM_ARCH_FP_F_F16, kvm_cpu_context, fp.f.f[16]);
+	OFFSET(KVM_ARCH_FP_F_F17, kvm_cpu_context, fp.f.f[17]);
+	OFFSET(KVM_ARCH_FP_F_F18, kvm_cpu_context, fp.f.f[18]);
+	OFFSET(KVM_ARCH_FP_F_F19, kvm_cpu_context, fp.f.f[19]);
+	OFFSET(KVM_ARCH_FP_F_F20, kvm_cpu_context, fp.f.f[20]);
+	OFFSET(KVM_ARCH_FP_F_F21, kvm_cpu_context, fp.f.f[21]);
+	OFFSET(KVM_ARCH_FP_F_F22, kvm_cpu_context, fp.f.f[22]);
+	OFFSET(KVM_ARCH_FP_F_F23, kvm_cpu_context, fp.f.f[23]);
+	OFFSET(KVM_ARCH_FP_F_F24, kvm_cpu_context, fp.f.f[24]);
+	OFFSET(KVM_ARCH_FP_F_F25, kvm_cpu_context, fp.f.f[25]);
+	OFFSET(KVM_ARCH_FP_F_F26, kvm_cpu_context, fp.f.f[26]);
+	OFFSET(KVM_ARCH_FP_F_F27, kvm_cpu_context, fp.f.f[27]);
+	OFFSET(KVM_ARCH_FP_F_F28, kvm_cpu_context, fp.f.f[28]);
+	OFFSET(KVM_ARCH_FP_F_F29, kvm_cpu_context, fp.f.f[29]);
+	OFFSET(KVM_ARCH_FP_F_F30, kvm_cpu_context, fp.f.f[30]);
+	OFFSET(KVM_ARCH_FP_F_F31, kvm_cpu_context, fp.f.f[31]);
+	OFFSET(KVM_ARCH_FP_F_FCSR, kvm_cpu_context, fp.f.fcsr);
+
+	/* D extension */
+
+	OFFSET(KVM_ARCH_FP_D_F0, kvm_cpu_context, fp.d.f[0]);
+	OFFSET(KVM_ARCH_FP_D_F1, kvm_cpu_context, fp.d.f[1]);
+	OFFSET(KVM_ARCH_FP_D_F2, kvm_cpu_context, fp.d.f[2]);
+	OFFSET(KVM_ARCH_FP_D_F3, kvm_cpu_context, fp.d.f[3]);
+	OFFSET(KVM_ARCH_FP_D_F4, kvm_cpu_context, fp.d.f[4]);
+	OFFSET(KVM_ARCH_FP_D_F5, kvm_cpu_context, fp.d.f[5]);
+	OFFSET(KVM_ARCH_FP_D_F6, kvm_cpu_context, fp.d.f[6]);
+	OFFSET(KVM_ARCH_FP_D_F7, kvm_cpu_context, fp.d.f[7]);
+	OFFSET(KVM_ARCH_FP_D_F8, kvm_cpu_context, fp.d.f[8]);
+	OFFSET(KVM_ARCH_FP_D_F9, kvm_cpu_context, fp.d.f[9]);
+	OFFSET(KVM_ARCH_FP_D_F10, kvm_cpu_context, fp.d.f[10]);
+	OFFSET(KVM_ARCH_FP_D_F11, kvm_cpu_context, fp.d.f[11]);
+	OFFSET(KVM_ARCH_FP_D_F12, kvm_cpu_context, fp.d.f[12]);
+	OFFSET(KVM_ARCH_FP_D_F13, kvm_cpu_context, fp.d.f[13]);
+	OFFSET(KVM_ARCH_FP_D_F14, kvm_cpu_context, fp.d.f[14]);
+	OFFSET(KVM_ARCH_FP_D_F15, kvm_cpu_context, fp.d.f[15]);
+	OFFSET(KVM_ARCH_FP_D_F16, kvm_cpu_context, fp.d.f[16]);
+	OFFSET(KVM_ARCH_FP_D_F17, kvm_cpu_context, fp.d.f[17]);
+	OFFSET(KVM_ARCH_FP_D_F18, kvm_cpu_context, fp.d.f[18]);
+	OFFSET(KVM_ARCH_FP_D_F19, kvm_cpu_context, fp.d.f[19]);
+	OFFSET(KVM_ARCH_FP_D_F20, kvm_cpu_context, fp.d.f[20]);
+	OFFSET(KVM_ARCH_FP_D_F21, kvm_cpu_context, fp.d.f[21]);
+	OFFSET(KVM_ARCH_FP_D_F22, kvm_cpu_context, fp.d.f[22]);
+	OFFSET(KVM_ARCH_FP_D_F23, kvm_cpu_context, fp.d.f[23]);
+	OFFSET(KVM_ARCH_FP_D_F24, kvm_cpu_context, fp.d.f[24]);
+	OFFSET(KVM_ARCH_FP_D_F25, kvm_cpu_context, fp.d.f[25]);
+	OFFSET(KVM_ARCH_FP_D_F26, kvm_cpu_context, fp.d.f[26]);
+	OFFSET(KVM_ARCH_FP_D_F27, kvm_cpu_context, fp.d.f[27]);
+	OFFSET(KVM_ARCH_FP_D_F28, kvm_cpu_context, fp.d.f[28]);
+	OFFSET(KVM_ARCH_FP_D_F29, kvm_cpu_context, fp.d.f[29]);
+	OFFSET(KVM_ARCH_FP_D_F30, kvm_cpu_context, fp.d.f[30]);
+	OFFSET(KVM_ARCH_FP_D_F31, kvm_cpu_context, fp.d.f[31]);
+	OFFSET(KVM_ARCH_FP_D_FCSR, kvm_cpu_context, fp.d.fcsr);
+
+	/*
+	 * THREAD_{F,X}* might be larger than a S-type offset can handle, but
+	 * these are used in performance-sensitive assembly so we can't resort
+	 * to loading the long immediate every time.
+	 */
+	DEFINE(TASK_THREAD_RA_RA,
+		  offsetof(struct task_struct, thread.ra)
+		- offsetof(struct task_struct, thread.ra)
+	);
+	DEFINE(TASK_THREAD_SP_RA,
+		  offsetof(struct task_struct, thread.sp)
+		- offsetof(struct task_struct, thread.ra)
+	);
+	DEFINE(TASK_THREAD_S0_RA,
+		  offsetof(struct task_struct, thread.s[0])
+		- offsetof(struct task_struct, thread.ra)
+	);
+	DEFINE(TASK_THREAD_S1_RA,
+		  offsetof(struct task_struct, thread.s[1])
+		- offsetof(struct task_struct, thread.ra)
+	);
+	DEFINE(TASK_THREAD_S2_RA,
+		  offsetof(struct task_struct, thread.s[2])
+		- offsetof(struct task_struct, thread.ra)
+	);
+	DEFINE(TASK_THREAD_S3_RA,
+		  offsetof(struct task_struct, thread.s[3])
+		- offsetof(struct task_struct, thread.ra)
+	);
+	DEFINE(TASK_THREAD_S4_RA,
+		  offsetof(struct task_struct, thread.s[4])
+		- offsetof(struct task_struct, thread.ra)
+	);
+	DEFINE(TASK_THREAD_S5_RA,
+		  offsetof(struct task_struct, thread.s[5])
+		- offsetof(struct task_struct, thread.ra)
+	);
+	DEFINE(TASK_THREAD_S6_RA,
+		  offsetof(struct task_struct, thread.s[6])
+		- offsetof(struct task_struct, thread.ra)
+	);
+	DEFINE(TASK_THREAD_S7_RA,
+		  offsetof(struct task_struct, thread.s[7])
+		- offsetof(struct task_struct, thread.ra)
+	);
+	DEFINE(TASK_THREAD_S8_RA,
+		  offsetof(struct task_struct, thread.s[8])
+		- offsetof(struct task_struct, thread.ra)
+	);
+	DEFINE(TASK_THREAD_S9_RA,
+		  offsetof(struct task_struct, thread.s[9])
+		- offsetof(struct task_struct, thread.ra)
+	);
+	DEFINE(TASK_THREAD_S10_RA,
+		  offsetof(struct task_struct, thread.s[10])
+		- offsetof(struct task_struct, thread.ra)
+	);
+	DEFINE(TASK_THREAD_S11_RA,
+		  offsetof(struct task_struct, thread.s[11])
+		- offsetof(struct task_struct, thread.ra)
+	);
+
+	DEFINE(TASK_THREAD_F0_F0,
+		  offsetof(struct task_struct, thread.fstate.f[0])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F1_F0,
+		  offsetof(struct task_struct, thread.fstate.f[1])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F2_F0,
+		  offsetof(struct task_struct, thread.fstate.f[2])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F3_F0,
+		  offsetof(struct task_struct, thread.fstate.f[3])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F4_F0,
+		  offsetof(struct task_struct, thread.fstate.f[4])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F5_F0,
+		  offsetof(struct task_struct, thread.fstate.f[5])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F6_F0,
+		  offsetof(struct task_struct, thread.fstate.f[6])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F7_F0,
+		  offsetof(struct task_struct, thread.fstate.f[7])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F8_F0,
+		  offsetof(struct task_struct, thread.fstate.f[8])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F9_F0,
+		  offsetof(struct task_struct, thread.fstate.f[9])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F10_F0,
+		  offsetof(struct task_struct, thread.fstate.f[10])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F11_F0,
+		  offsetof(struct task_struct, thread.fstate.f[11])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F12_F0,
+		  offsetof(struct task_struct, thread.fstate.f[12])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F13_F0,
+		  offsetof(struct task_struct, thread.fstate.f[13])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F14_F0,
+		  offsetof(struct task_struct, thread.fstate.f[14])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F15_F0,
+		  offsetof(struct task_struct, thread.fstate.f[15])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F16_F0,
+		  offsetof(struct task_struct, thread.fstate.f[16])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F17_F0,
+		  offsetof(struct task_struct, thread.fstate.f[17])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F18_F0,
+		  offsetof(struct task_struct, thread.fstate.f[18])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F19_F0,
+		  offsetof(struct task_struct, thread.fstate.f[19])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F20_F0,
+		  offsetof(struct task_struct, thread.fstate.f[20])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F21_F0,
+		  offsetof(struct task_struct, thread.fstate.f[21])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F22_F0,
+		  offsetof(struct task_struct, thread.fstate.f[22])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F23_F0,
+		  offsetof(struct task_struct, thread.fstate.f[23])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F24_F0,
+		  offsetof(struct task_struct, thread.fstate.f[24])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F25_F0,
+		  offsetof(struct task_struct, thread.fstate.f[25])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F26_F0,
+		  offsetof(struct task_struct, thread.fstate.f[26])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F27_F0,
+		  offsetof(struct task_struct, thread.fstate.f[27])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F28_F0,
+		  offsetof(struct task_struct, thread.fstate.f[28])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F29_F0,
+		  offsetof(struct task_struct, thread.fstate.f[29])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F30_F0,
+		  offsetof(struct task_struct, thread.fstate.f[30])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F31_F0,
+		  offsetof(struct task_struct, thread.fstate.f[31])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_FCSR_F0,
+		  offsetof(struct task_struct, thread.fstate.fcsr)
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+
+	/*
+	 * We allocate a pt_regs on the stack when entering the kernel.  This
+	 * ensures the alignment is sane.
+	 */
+	DEFINE(PT_SIZE_ON_STACK, ALIGN(sizeof(struct pt_regs), STACK_ALIGN));
+
+	OFFSET(KERNEL_MAP_VIRT_ADDR, kernel_mapping, virt_addr);
+	OFFSET(SBI_HART_BOOT_TASK_PTR_OFFSET, sbi_hart_boot_data, task_ptr);
+	OFFSET(SBI_HART_BOOT_STACK_PTR_OFFSET, sbi_hart_boot_data, stack_ptr);
+}
diff --git a/arch/riscv/kernel/cacheinfo.c b/arch/riscv/kernel/cacheinfo.c
new file mode 100644
index 000000000..90deabfe6
--- /dev/null
+++ b/arch/riscv/kernel/cacheinfo.c
@@ -0,0 +1,189 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2017 SiFive
+ */
+
+#include <linux/cpu.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <asm/cacheinfo.h>
+
+static struct riscv_cacheinfo_ops *rv_cache_ops;
+
+void riscv_set_cacheinfo_ops(struct riscv_cacheinfo_ops *ops)
+{
+	rv_cache_ops = ops;
+}
+EXPORT_SYMBOL_GPL(riscv_set_cacheinfo_ops);
+
+const struct attribute_group *
+cache_get_priv_group(struct cacheinfo *this_leaf)
+{
+	if (rv_cache_ops && rv_cache_ops->get_priv_group)
+		return rv_cache_ops->get_priv_group(this_leaf);
+	return NULL;
+}
+
+static struct cacheinfo *get_cacheinfo(u32 level, enum cache_type type)
+{
+	/*
+	 * Using raw_smp_processor_id() elides a preemptability check, but this
+	 * is really indicative of a larger problem: the cacheinfo UABI assumes
+	 * that cores have a homonogenous view of the cache hierarchy.  That
+	 * happens to be the case for the current set of RISC-V systems, but
+	 * likely won't be true in general.  Since there's no way to provide
+	 * correct information for these systems via the current UABI we're
+	 * just eliding the check for now.
+	 */
+	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(raw_smp_processor_id());
+	struct cacheinfo *this_leaf;
+	int index;
+
+	for (index = 0; index < this_cpu_ci->num_leaves; index++) {
+		this_leaf = this_cpu_ci->info_list + index;
+		if (this_leaf->level == level && this_leaf->type == type)
+			return this_leaf;
+	}
+
+	return NULL;
+}
+
+uintptr_t get_cache_size(u32 level, enum cache_type type)
+{
+	struct cacheinfo *this_leaf = get_cacheinfo(level, type);
+
+	return this_leaf ? this_leaf->size : 0;
+}
+
+uintptr_t get_cache_geometry(u32 level, enum cache_type type)
+{
+	struct cacheinfo *this_leaf = get_cacheinfo(level, type);
+
+	return this_leaf ? (this_leaf->ways_of_associativity << 16 |
+			    this_leaf->coherency_line_size) :
+			   0;
+}
+
+static void ci_leaf_init(struct cacheinfo *this_leaf, enum cache_type type,
+			 unsigned int level, unsigned int size,
+			 unsigned int sets, unsigned int line_size)
+{
+	this_leaf->level = level;
+	this_leaf->type = type;
+	this_leaf->size = size;
+	this_leaf->number_of_sets = sets;
+	this_leaf->coherency_line_size = line_size;
+
+	/*
+	 * If the cache is fully associative, there is no need to
+	 * check the other properties.
+	 */
+	if (sets == 1)
+		return;
+
+	/*
+	 * Set the ways number for n-ways associative, make sure
+	 * all properties are big than zero.
+	 */
+	if (sets > 0 && size > 0 && line_size > 0)
+		this_leaf->ways_of_associativity = (size / sets) / line_size;
+}
+
+static void fill_cacheinfo(struct cacheinfo **this_leaf,
+			   struct device_node *node, unsigned int level)
+{
+	unsigned int size, sets, line_size;
+
+	if (!of_property_read_u32(node, "cache-size", &size) &&
+	    !of_property_read_u32(node, "cache-block-size", &line_size) &&
+	    !of_property_read_u32(node, "cache-sets", &sets)) {
+		ci_leaf_init((*this_leaf)++, CACHE_TYPE_UNIFIED, level, size, sets, line_size);
+	}
+
+	if (!of_property_read_u32(node, "i-cache-size", &size) &&
+	    !of_property_read_u32(node, "i-cache-sets", &sets) &&
+	    !of_property_read_u32(node, "i-cache-block-size", &line_size)) {
+		ci_leaf_init((*this_leaf)++, CACHE_TYPE_INST, level, size, sets, line_size);
+	}
+
+	if (!of_property_read_u32(node, "d-cache-size", &size) &&
+	    !of_property_read_u32(node, "d-cache-sets", &sets) &&
+	    !of_property_read_u32(node, "d-cache-block-size", &line_size)) {
+		ci_leaf_init((*this_leaf)++, CACHE_TYPE_DATA, level, size, sets, line_size);
+	}
+}
+
+int init_cache_level(unsigned int cpu)
+{
+	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+	struct device_node *np = of_cpu_device_node_get(cpu);
+	struct device_node *prev = NULL;
+	int levels = 0, leaves = 0, level;
+
+	if (of_property_read_bool(np, "cache-size"))
+		++leaves;
+	if (of_property_read_bool(np, "i-cache-size"))
+		++leaves;
+	if (of_property_read_bool(np, "d-cache-size"))
+		++leaves;
+	if (leaves > 0)
+		levels = 1;
+
+	prev = np;
+	while ((np = of_find_next_cache_node(np))) {
+		of_node_put(prev);
+		prev = np;
+		if (!of_device_is_compatible(np, "cache"))
+			break;
+		if (of_property_read_u32(np, "cache-level", &level))
+			break;
+		if (level <= levels)
+			break;
+		if (of_property_read_bool(np, "cache-size"))
+			++leaves;
+		if (of_property_read_bool(np, "i-cache-size"))
+			++leaves;
+		if (of_property_read_bool(np, "d-cache-size"))
+			++leaves;
+		levels = level;
+	}
+
+	of_node_put(np);
+	this_cpu_ci->num_levels = levels;
+	this_cpu_ci->num_leaves = leaves;
+
+	return 0;
+}
+
+int populate_cache_leaves(unsigned int cpu)
+{
+	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+	struct cacheinfo *this_leaf = this_cpu_ci->info_list;
+	struct device_node *np = of_cpu_device_node_get(cpu);
+	struct device_node *prev = NULL;
+	int levels = 1, level = 1;
+
+	/* Level 1 caches in cpu node */
+	fill_cacheinfo(&this_leaf, np, level);
+
+	/* Next level caches in cache nodes */
+	prev = np;
+	while ((np = of_find_next_cache_node(np))) {
+		of_node_put(prev);
+		prev = np;
+
+		if (!of_device_is_compatible(np, "cache"))
+			break;
+		if (of_property_read_u32(np, "cache-level", &level))
+			break;
+		if (level <= levels)
+			break;
+
+		fill_cacheinfo(&this_leaf, np, level);
+
+		levels = level;
+	}
+	of_node_put(np);
+
+	return 0;
+}
diff --git a/arch/riscv/kernel/compat_signal.c b/arch/riscv/kernel/compat_signal.c
new file mode 100644
index 000000000..6ec4e3425
--- /dev/null
+++ b/arch/riscv/kernel/compat_signal.c
@@ -0,0 +1,243 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/compat.h>
+#include <linux/signal.h>
+#include <linux/uaccess.h>
+#include <linux/syscalls.h>
+#include <linux/linkage.h>
+
+#include <asm/csr.h>
+#include <asm/signal32.h>
+#include <asm/switch_to.h>
+#include <asm/ucontext.h>
+#include <asm/vdso.h>
+
+#define COMPAT_DEBUG_SIG 0
+
+struct compat_sigcontext {
+	struct compat_user_regs_struct sc_regs;
+	union __riscv_fp_state sc_fpregs;
+};
+
+struct compat_ucontext {
+	compat_ulong_t		uc_flags;
+	struct compat_ucontext	*uc_link;
+	compat_stack_t		uc_stack;
+	sigset_t		uc_sigmask;
+	/* There's some padding here to allow sigset_t to be expanded in the
+	 * future.  Though this is unlikely, other architectures put uc_sigmask
+	 * at the end of this structure and explicitly state it can be
+	 * expanded, so we didn't want to box ourselves in here. */
+	__u8		  __unused[1024 / 8 - sizeof(sigset_t)];
+	/* We can't put uc_sigmask at the end of this structure because we need
+	 * to be able to expand sigcontext in the future.  For example, the
+	 * vector ISA extension will almost certainly add ISA state.  We want
+	 * to ensure all user-visible ISA state can be saved and restored via a
+	 * ucontext, so we're putting this at the end in order to allow for
+	 * infinite extensibility.  Since we know this will be extended and we
+	 * assume sigset_t won't be extended an extreme amount, we're
+	 * prioritizing this. */
+	struct compat_sigcontext uc_mcontext;
+};
+
+struct compat_rt_sigframe {
+	struct compat_siginfo info;
+	struct compat_ucontext uc;
+};
+
+#ifdef CONFIG_FPU
+static long compat_restore_fp_state(struct pt_regs *regs,
+	union __riscv_fp_state __user *sc_fpregs)
+{
+	long err;
+	struct __riscv_d_ext_state __user *state = &sc_fpregs->d;
+	size_t i;
+
+	err = __copy_from_user(&current->thread.fstate, state, sizeof(*state));
+	if (unlikely(err))
+		return err;
+
+	fstate_restore(current, regs);
+
+	/* We support no other extension state at this time. */
+	for (i = 0; i < ARRAY_SIZE(sc_fpregs->q.reserved); i++) {
+		u32 value;
+
+		err = __get_user(value, &sc_fpregs->q.reserved[i]);
+		if (unlikely(err))
+			break;
+		if (value != 0)
+			return -EINVAL;
+	}
+
+	return err;
+}
+
+static long compat_save_fp_state(struct pt_regs *regs,
+			  union __riscv_fp_state __user *sc_fpregs)
+{
+	long err;
+	struct __riscv_d_ext_state __user *state = &sc_fpregs->d;
+	size_t i;
+
+	fstate_save(current, regs);
+	err = __copy_to_user(state, &current->thread.fstate, sizeof(*state));
+	if (unlikely(err))
+		return err;
+
+	/* We support no other extension state at this time. */
+	for (i = 0; i < ARRAY_SIZE(sc_fpregs->q.reserved); i++) {
+		err = __put_user(0, &sc_fpregs->q.reserved[i]);
+		if (unlikely(err))
+			break;
+	}
+
+	return err;
+}
+#else
+#define compat_save_fp_state(task, regs) (0)
+#define compat_restore_fp_state(task, regs) (0)
+#endif
+
+static long compat_restore_sigcontext(struct pt_regs *regs,
+	struct compat_sigcontext __user *sc)
+{
+	long err;
+	struct compat_user_regs_struct cregs;
+
+	/* sc_regs is structured the same as the start of pt_regs */
+	err = __copy_from_user(&cregs, &sc->sc_regs, sizeof(sc->sc_regs));
+
+	cregs_to_regs(&cregs, regs);
+
+	/* Restore the floating-point state. */
+	if (has_fpu())
+		err |= compat_restore_fp_state(regs, &sc->sc_fpregs);
+	return err;
+}
+
+COMPAT_SYSCALL_DEFINE0(rt_sigreturn)
+{
+	struct pt_regs *regs = current_pt_regs();
+	struct compat_rt_sigframe __user *frame;
+	struct task_struct *task;
+	sigset_t set;
+
+	/* Always make any pending restarted system calls return -EINTR */
+	current->restart_block.fn = do_no_restart_syscall;
+
+	frame = (struct compat_rt_sigframe __user *)regs->sp;
+
+	if (!access_ok(frame, sizeof(*frame)))
+		goto badframe;
+
+	if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
+		goto badframe;
+
+	set_current_blocked(&set);
+
+	if (compat_restore_sigcontext(regs, &frame->uc.uc_mcontext))
+		goto badframe;
+
+	if (compat_restore_altstack(&frame->uc.uc_stack))
+		goto badframe;
+
+	return regs->a0;
+
+badframe:
+	task = current;
+	if (show_unhandled_signals) {
+		pr_info_ratelimited(
+			"%s[%d]: bad frame in %s: frame=%p pc=%p sp=%p\n",
+			task->comm, task_pid_nr(task), __func__,
+			frame, (void *)regs->epc, (void *)regs->sp);
+	}
+	force_sig(SIGSEGV);
+	return 0;
+}
+
+static long compat_setup_sigcontext(struct compat_rt_sigframe __user *frame,
+	struct pt_regs *regs)
+{
+	struct compat_sigcontext __user *sc = &frame->uc.uc_mcontext;
+	struct compat_user_regs_struct cregs;
+	long err;
+
+	regs_to_cregs(&cregs, regs);
+
+	/* sc_regs is structured the same as the start of pt_regs */
+	err = __copy_to_user(&sc->sc_regs, &cregs, sizeof(sc->sc_regs));
+	/* Save the floating-point state. */
+	if (has_fpu())
+		err |= compat_save_fp_state(regs, &sc->sc_fpregs);
+	return err;
+}
+
+static inline void __user *compat_get_sigframe(struct ksignal *ksig,
+	struct pt_regs *regs, size_t framesize)
+{
+	unsigned long sp;
+	/* Default to using normal stack */
+	sp = regs->sp;
+
+	/*
+	 * If we are on the alternate signal stack and would overflow it, don't.
+	 * Return an always-bogus address instead so we will die with SIGSEGV.
+	 */
+	if (on_sig_stack(sp) && !likely(on_sig_stack(sp - framesize)))
+		return (void __user __force *)(-1UL);
+
+	/* This is the X/Open sanctioned signal stack switching. */
+	sp = sigsp(sp, ksig) - framesize;
+
+	/* Align the stack frame. */
+	sp &= ~0xfUL;
+
+	return (void __user *)sp;
+}
+
+int compat_setup_rt_frame(struct ksignal *ksig, sigset_t *set,
+	struct pt_regs *regs)
+{
+	struct compat_rt_sigframe __user *frame;
+	long err = 0;
+
+	frame = compat_get_sigframe(ksig, regs, sizeof(*frame));
+	if (!access_ok(frame, sizeof(*frame)))
+		return -EFAULT;
+
+	err |= copy_siginfo_to_user32(&frame->info, &ksig->info);
+
+	/* Create the ucontext. */
+	err |= __put_user(0, &frame->uc.uc_flags);
+	err |= __put_user(NULL, &frame->uc.uc_link);
+	err |= __compat_save_altstack(&frame->uc.uc_stack, regs->sp);
+	err |= compat_setup_sigcontext(frame, regs);
+	err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
+	if (err)
+		return -EFAULT;
+
+	regs->ra = (unsigned long)COMPAT_VDSO_SYMBOL(
+			current->mm->context.vdso, rt_sigreturn);
+
+	/*
+	 * Set up registers for signal handler.
+	 * Registers that we don't modify keep the value they had from
+	 * user-space at the time we took the signal.
+	 * We always pass siginfo and mcontext, regardless of SA_SIGINFO,
+	 * since some things rely on this (e.g. glibc's debug/segfault.c).
+	 */
+	regs->epc = (unsigned long)ksig->ka.sa.sa_handler;
+	regs->sp = (unsigned long)frame;
+	regs->a0 = ksig->sig;                     /* a0: signal number */
+	regs->a1 = (unsigned long)(&frame->info); /* a1: siginfo pointer */
+	regs->a2 = (unsigned long)(&frame->uc);   /* a2: ucontext pointer */
+
+#if COMPAT_DEBUG_SIG
+	pr_info("SIG deliver (%s:%d): sig=%d pc=%p ra=%p sp=%p\n",
+		current->comm, task_pid_nr(current), ksig->sig,
+		(void *)regs->epc, (void *)regs->ra, frame);
+#endif
+
+	return 0;
+}
diff --git a/arch/riscv/kernel/compat_syscall_table.c b/arch/riscv/kernel/compat_syscall_table.c
new file mode 100644
index 000000000..651f2b009
--- /dev/null
+++ b/arch/riscv/kernel/compat_syscall_table.c
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#define __SYSCALL_COMPAT
+
+#include <linux/compat.h>
+#include <linux/syscalls.h>
+#include <asm-generic/mman-common.h>
+#include <asm-generic/syscalls.h>
+#include <asm/syscall.h>
+
+#undef __SYSCALL
+#define __SYSCALL(nr, call)      [nr] = (call),
+
+asmlinkage long compat_sys_rt_sigreturn(void);
+
+void * const compat_sys_call_table[__NR_syscalls] = {
+	[0 ... __NR_syscalls - 1] = sys_ni_syscall,
+#include <asm/unistd.h>
+};
diff --git a/arch/riscv/kernel/compat_vdso/.gitignore b/arch/riscv/kernel/compat_vdso/.gitignore
new file mode 100644
index 000000000..19d83d846
--- /dev/null
+++ b/arch/riscv/kernel/compat_vdso/.gitignore
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+compat_vdso.lds
diff --git a/arch/riscv/kernel/compat_vdso/Makefile b/arch/riscv/kernel/compat_vdso/Makefile
new file mode 100644
index 000000000..737c0857b
--- /dev/null
+++ b/arch/riscv/kernel/compat_vdso/Makefile
@@ -0,0 +1,88 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Makefile for compat_vdso
+#
+
+# Symbols present in the compat_vdso
+compat_vdso-syms  = rt_sigreturn
+compat_vdso-syms += getcpu
+compat_vdso-syms += flush_icache
+
+COMPAT_CC := $(CC)
+COMPAT_LD := $(LD)
+
+# binutils 2.35 does not support the zifencei extension, but in the ISA
+# spec 20191213, G stands for IMAFD_ZICSR_ZIFENCEI.
+ifdef CONFIG_TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI
+	COMPAT_CC_FLAGS := -march=rv32g -mabi=ilp32
+else
+	COMPAT_CC_FLAGS := -march=rv32imafd -mabi=ilp32
+endif
+COMPAT_LD_FLAGS := -melf32lriscv
+
+# Disable attributes, as they're useless and break the build.
+COMPAT_CC_FLAGS += $(call cc-option,-mno-riscv-attribute)
+COMPAT_CC_FLAGS += $(call as-option,-Wa$(comma)-mno-arch-attr)
+
+# Files to link into the compat_vdso
+obj-compat_vdso = $(patsubst %, %.o, $(compat_vdso-syms)) note.o
+
+# Build rules
+targets := $(obj-compat_vdso) compat_vdso.so compat_vdso.so.dbg compat_vdso.lds
+obj-compat_vdso := $(addprefix $(obj)/, $(obj-compat_vdso))
+
+obj-y += compat_vdso.o
+CPPFLAGS_compat_vdso.lds += -P -C -U$(ARCH)
+
+# Disable profiling and instrumentation for VDSO code
+GCOV_PROFILE := n
+KCOV_INSTRUMENT := n
+KASAN_SANITIZE := n
+UBSAN_SANITIZE := n
+
+# Force dependency
+$(obj)/compat_vdso.o: $(obj)/compat_vdso.so
+
+# link rule for the .so file, .lds has to be first
+$(obj)/compat_vdso.so.dbg: $(obj)/compat_vdso.lds $(obj-compat_vdso) FORCE
+	$(call if_changed,compat_vdsold)
+LDFLAGS_compat_vdso.so.dbg = -shared -S -soname=linux-compat_vdso.so.1 \
+	--build-id=sha1 --hash-style=both --eh-frame-hdr
+
+$(obj-compat_vdso): %.o: %.S FORCE
+	$(call if_changed_dep,compat_vdsoas)
+
+# strip rule for the .so file
+$(obj)/%.so: OBJCOPYFLAGS := -S
+$(obj)/%.so: $(obj)/%.so.dbg FORCE
+	$(call if_changed,objcopy)
+
+# Generate VDSO offsets using helper script
+gen-compat_vdsosym := $(srctree)/$(src)/gen_compat_vdso_offsets.sh
+quiet_cmd_compat_vdsosym = VDSOSYM $@
+	cmd_compat_vdsosym = $(NM) $< | $(gen-compat_vdsosym) | LC_ALL=C sort > $@
+
+include/generated/compat_vdso-offsets.h: $(obj)/compat_vdso.so.dbg FORCE
+	$(call if_changed,compat_vdsosym)
+
+# actual build commands
+# The DSO images are built using a special linker script
+# Make sure only to export the intended __compat_vdso_xxx symbol offsets.
+quiet_cmd_compat_vdsold = VDSOLD  $@
+      cmd_compat_vdsold = $(COMPAT_LD) $(ld_flags) $(COMPAT_LD_FLAGS) -T $(filter-out FORCE,$^) -o $@.tmp && \
+                   $(OBJCOPY) $(patsubst %, -G __compat_vdso_%, $(compat_vdso-syms)) $@.tmp $@ && \
+                   rm $@.tmp
+
+# actual build commands
+quiet_cmd_compat_vdsoas = VDSOAS $@
+      cmd_compat_vdsoas = $(COMPAT_CC) $(a_flags) $(COMPAT_CC_FLAGS) -c -o $@ $<
+
+# install commands for the unstripped file
+quiet_cmd_compat_vdso_install = INSTALL $@
+      cmd_compat_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/compat_vdso/$@
+
+compat_vdso.so: $(obj)/compat_vdso.so.dbg
+	@mkdir -p $(MODLIB)/compat_vdso
+	$(call cmd,compat_vdso_install)
+
+compat_vdso_install: compat_vdso.so
diff --git a/arch/riscv/kernel/compat_vdso/compat_vdso.S b/arch/riscv/kernel/compat_vdso/compat_vdso.S
new file mode 100644
index 000000000..ffd66237e
--- /dev/null
+++ b/arch/riscv/kernel/compat_vdso/compat_vdso.S
@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#define	vdso_start	compat_vdso_start
+#define	vdso_end	compat_vdso_end
+
+#define	__VDSO_PATH	"arch/riscv/kernel/compat_vdso/compat_vdso.so"
+
+#include "../vdso/vdso.S"
diff --git a/arch/riscv/kernel/compat_vdso/compat_vdso.lds.S b/arch/riscv/kernel/compat_vdso/compat_vdso.lds.S
new file mode 100644
index 000000000..c7c9355d3
--- /dev/null
+++ b/arch/riscv/kernel/compat_vdso/compat_vdso.lds.S
@@ -0,0 +1,3 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#include "../vdso/vdso.lds.S"
diff --git a/arch/riscv/kernel/compat_vdso/flush_icache.S b/arch/riscv/kernel/compat_vdso/flush_icache.S
new file mode 100644
index 000000000..523dd8b96
--- /dev/null
+++ b/arch/riscv/kernel/compat_vdso/flush_icache.S
@@ -0,0 +1,3 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#include "../vdso/flush_icache.S"
diff --git a/arch/riscv/kernel/compat_vdso/gen_compat_vdso_offsets.sh b/arch/riscv/kernel/compat_vdso/gen_compat_vdso_offsets.sh
new file mode 100755
index 000000000..8ac070c78
--- /dev/null
+++ b/arch/riscv/kernel/compat_vdso/gen_compat_vdso_offsets.sh
@@ -0,0 +1,5 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+LC_ALL=C
+sed -n -e 's/^[0]\+\(0[0-9a-fA-F]*\) . \(__vdso_[a-zA-Z0-9_]*\)$/\#define compat\2_offset\t0x\1/p'
diff --git a/arch/riscv/kernel/compat_vdso/getcpu.S b/arch/riscv/kernel/compat_vdso/getcpu.S
new file mode 100644
index 000000000..10f463efe
--- /dev/null
+++ b/arch/riscv/kernel/compat_vdso/getcpu.S
@@ -0,0 +1,3 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#include "../vdso/getcpu.S"
diff --git a/arch/riscv/kernel/compat_vdso/note.S b/arch/riscv/kernel/compat_vdso/note.S
new file mode 100644
index 000000000..b10312907
--- /dev/null
+++ b/arch/riscv/kernel/compat_vdso/note.S
@@ -0,0 +1,3 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#include "../vdso/note.S"
diff --git a/arch/riscv/kernel/compat_vdso/rt_sigreturn.S b/arch/riscv/kernel/compat_vdso/rt_sigreturn.S
new file mode 100644
index 000000000..884aada4f
--- /dev/null
+++ b/arch/riscv/kernel/compat_vdso/rt_sigreturn.S
@@ -0,0 +1,3 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#include "../vdso/rt_sigreturn.S"
diff --git a/arch/riscv/kernel/cpu-hotplug.c b/arch/riscv/kernel/cpu-hotplug.c
new file mode 100644
index 000000000..f7a832e3a
--- /dev/null
+++ b/arch/riscv/kernel/cpu-hotplug.c
@@ -0,0 +1,83 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020 Western Digital Corporation or its affiliates.
+ */
+
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/sched.h>
+#include <linux/err.h>
+#include <linux/irq.h>
+#include <linux/cpu.h>
+#include <linux/sched/hotplug.h>
+#include <asm/irq.h>
+#include <asm/cpu_ops.h>
+#include <asm/numa.h>
+#include <asm/sbi.h>
+
+bool cpu_has_hotplug(unsigned int cpu)
+{
+	if (cpu_ops[cpu]->cpu_stop)
+		return true;
+
+	return false;
+}
+
+/*
+ * __cpu_disable runs on the processor to be shutdown.
+ */
+int __cpu_disable(void)
+{
+	int ret = 0;
+	unsigned int cpu = smp_processor_id();
+
+	if (!cpu_ops[cpu] || !cpu_ops[cpu]->cpu_stop)
+		return -EOPNOTSUPP;
+
+	if (cpu_ops[cpu]->cpu_disable)
+		ret = cpu_ops[cpu]->cpu_disable(cpu);
+
+	if (ret)
+		return ret;
+
+	remove_cpu_topology(cpu);
+	numa_remove_cpu(cpu);
+	set_cpu_online(cpu, false);
+	irq_migrate_all_off_this_cpu();
+
+	return ret;
+}
+
+/*
+ * Called on the thread which is asking for a CPU to be shutdown.
+ */
+void __cpu_die(unsigned int cpu)
+{
+	int ret = 0;
+
+	if (!cpu_wait_death(cpu, 5)) {
+		pr_err("CPU %u: didn't die\n", cpu);
+		return;
+	}
+	pr_notice("CPU%u: off\n", cpu);
+
+	/* Verify from the firmware if the cpu is really stopped*/
+	if (cpu_ops[cpu]->cpu_is_stopped)
+		ret = cpu_ops[cpu]->cpu_is_stopped(cpu);
+	if (ret)
+		pr_warn("CPU%d may not have stopped: %d\n", cpu, ret);
+}
+
+/*
+ * Called from the idle thread for the CPU which has been shutdown.
+ */
+void arch_cpu_idle_dead(void)
+{
+	idle_task_exit();
+
+	(void)cpu_report_death();
+
+	cpu_ops[smp_processor_id()]->cpu_stop();
+	/* It should never reach here */
+	BUG();
+}
diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c
new file mode 100644
index 000000000..0f76181dc
--- /dev/null
+++ b/arch/riscv/kernel/cpu.c
@@ -0,0 +1,267 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ */
+
+#include <linux/cpu.h>
+#include <linux/init.h>
+#include <linux/seq_file.h>
+#include <linux/of.h>
+#include <asm/csr.h>
+#include <asm/hwcap.h>
+#include <asm/sbi.h>
+#include <asm/smp.h>
+#include <asm/pgtable.h>
+
+/*
+ * Returns the hart ID of the given device tree node, or -ENODEV if the node
+ * isn't an enabled and valid RISC-V hart node.
+ */
+int riscv_of_processor_hartid(struct device_node *node, unsigned long *hart)
+{
+	const char *isa;
+
+	if (!of_device_is_compatible(node, "riscv")) {
+		pr_warn("Found incompatible CPU\n");
+		return -ENODEV;
+	}
+
+	*hart = (unsigned long) of_get_cpu_hwid(node, 0);
+	if (*hart == ~0UL) {
+		pr_warn("Found CPU without hart ID\n");
+		return -ENODEV;
+	}
+
+	if (!of_device_is_available(node)) {
+		pr_info("CPU with hartid=%lu is not available\n", *hart);
+		return -ENODEV;
+	}
+
+	if (of_property_read_string(node, "riscv,isa", &isa)) {
+		pr_warn("CPU with hartid=%lu has no \"riscv,isa\" property\n", *hart);
+		return -ENODEV;
+	}
+	if (isa[0] != 'r' || isa[1] != 'v') {
+		pr_warn("CPU with hartid=%lu has an invalid ISA of \"%s\"\n", *hart, isa);
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+/*
+ * Find hart ID of the CPU DT node under which given DT node falls.
+ *
+ * To achieve this, we walk up the DT tree until we find an active
+ * RISC-V core (HART) node and extract the cpuid from it.
+ */
+int riscv_of_parent_hartid(struct device_node *node, unsigned long *hartid)
+{
+	for (; node; node = node->parent) {
+		if (of_device_is_compatible(node, "riscv")) {
+			*hartid = (unsigned long)of_get_cpu_hwid(node, 0);
+			if (*hartid == ~0UL) {
+				pr_warn("Found CPU without hart ID\n");
+				return -ENODEV;
+			}
+			return 0;
+		}
+	}
+
+	return -1;
+}
+
+#ifdef CONFIG_PROC_FS
+
+struct riscv_cpuinfo {
+	unsigned long mvendorid;
+	unsigned long marchid;
+	unsigned long mimpid;
+};
+static DEFINE_PER_CPU(struct riscv_cpuinfo, riscv_cpuinfo);
+
+static int riscv_cpuinfo_starting(unsigned int cpu)
+{
+	struct riscv_cpuinfo *ci = this_cpu_ptr(&riscv_cpuinfo);
+
+#if IS_ENABLED(CONFIG_RISCV_SBI)
+	ci->mvendorid = sbi_spec_is_0_1() ? 0 : sbi_get_mvendorid();
+	ci->marchid = sbi_spec_is_0_1() ? 0 : sbi_get_marchid();
+	ci->mimpid = sbi_spec_is_0_1() ? 0 : sbi_get_mimpid();
+#elif IS_ENABLED(CONFIG_RISCV_M_MODE)
+	ci->mvendorid = csr_read(CSR_MVENDORID);
+	ci->marchid = csr_read(CSR_MARCHID);
+	ci->mimpid = csr_read(CSR_MIMPID);
+#else
+	ci->mvendorid = 0;
+	ci->marchid = 0;
+	ci->mimpid = 0;
+#endif
+
+	return 0;
+}
+
+static int __init riscv_cpuinfo_init(void)
+{
+	int ret;
+
+	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "riscv/cpuinfo:starting",
+				riscv_cpuinfo_starting, NULL);
+	if (ret < 0) {
+		pr_err("cpuinfo: failed to register hotplug callbacks.\n");
+		return ret;
+	}
+
+	return 0;
+}
+device_initcall(riscv_cpuinfo_init);
+
+#define __RISCV_ISA_EXT_DATA(UPROP, EXTID) \
+	{							\
+		.uprop = #UPROP,				\
+		.isa_ext_id = EXTID,				\
+	}
+/*
+ * Here are the ordering rules of extension naming defined by RISC-V
+ * specification :
+ * 1. All extensions should be separated from other multi-letter extensions
+ *    by an underscore.
+ * 2. The first letter following the 'Z' conventionally indicates the most
+ *    closely related alphabetical extension category, IMAFDQLCBKJTPVH.
+ *    If multiple 'Z' extensions are named, they should be ordered first
+ *    by category, then alphabetically within a category.
+ * 3. Standard supervisor-level extensions (starts with 'S') should be
+ *    listed after standard unprivileged extensions.  If multiple
+ *    supervisor-level extensions are listed, they should be ordered
+ *    alphabetically.
+ * 4. Non-standard extensions (starts with 'X') must be listed after all
+ *    standard extensions. They must be separated from other multi-letter
+ *    extensions by an underscore.
+ */
+static struct riscv_isa_ext_data isa_ext_arr[] = {
+	__RISCV_ISA_EXT_DATA(sscofpmf, RISCV_ISA_EXT_SSCOFPMF),
+	__RISCV_ISA_EXT_DATA(sstc, RISCV_ISA_EXT_SSTC),
+	__RISCV_ISA_EXT_DATA(svinval, RISCV_ISA_EXT_SVINVAL),
+	__RISCV_ISA_EXT_DATA(svpbmt, RISCV_ISA_EXT_SVPBMT),
+	__RISCV_ISA_EXT_DATA(zicbom, RISCV_ISA_EXT_ZICBOM),
+	__RISCV_ISA_EXT_DATA(zihintpause, RISCV_ISA_EXT_ZIHINTPAUSE),
+	__RISCV_ISA_EXT_DATA("", RISCV_ISA_EXT_MAX),
+};
+
+static void print_isa_ext(struct seq_file *f)
+{
+	struct riscv_isa_ext_data *edata;
+	int i = 0, arr_sz;
+
+	arr_sz = ARRAY_SIZE(isa_ext_arr) - 1;
+
+	/* No extension support available */
+	if (arr_sz <= 0)
+		return;
+
+	for (i = 0; i <= arr_sz; i++) {
+		edata = &isa_ext_arr[i];
+		if (!__riscv_isa_extension_available(NULL, edata->isa_ext_id))
+			continue;
+		seq_printf(f, "_%s", edata->uprop);
+	}
+}
+
+/*
+ * These are the only valid base (single letter) ISA extensions as per the spec.
+ * It also specifies the canonical order in which it appears in the spec.
+ * Some of the extension may just be a place holder for now (B, K, P, J).
+ * This should be updated once corresponding extensions are ratified.
+ */
+static const char base_riscv_exts[13] = "imafdqcbkjpvh";
+
+static void print_isa(struct seq_file *f, const char *isa)
+{
+	int i;
+
+	seq_puts(f, "isa\t\t: ");
+	/* Print the rv[64/32] part */
+	seq_write(f, isa, 4);
+	for (i = 0; i < sizeof(base_riscv_exts); i++) {
+		if (__riscv_isa_extension_available(NULL, base_riscv_exts[i] - 'a'))
+			/* Print only enabled the base ISA extensions */
+			seq_write(f, &base_riscv_exts[i], 1);
+	}
+	print_isa_ext(f);
+	seq_puts(f, "\n");
+}
+
+static void print_mmu(struct seq_file *f)
+{
+	char sv_type[16];
+
+#ifdef CONFIG_MMU
+#if defined(CONFIG_32BIT)
+	strncpy(sv_type, "sv32", 5);
+#elif defined(CONFIG_64BIT)
+	if (pgtable_l5_enabled)
+		strncpy(sv_type, "sv57", 5);
+	else if (pgtable_l4_enabled)
+		strncpy(sv_type, "sv48", 5);
+	else
+		strncpy(sv_type, "sv39", 5);
+#endif
+#else
+	strncpy(sv_type, "none", 5);
+#endif /* CONFIG_MMU */
+	seq_printf(f, "mmu\t\t: %s\n", sv_type);
+}
+
+static void *c_start(struct seq_file *m, loff_t *pos)
+{
+	if (*pos == nr_cpu_ids)
+		return NULL;
+
+	*pos = cpumask_next(*pos - 1, cpu_online_mask);
+	if ((*pos) < nr_cpu_ids)
+		return (void *)(uintptr_t)(1 + *pos);
+	return 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)
+{
+}
+
+static int c_show(struct seq_file *m, void *v)
+{
+	unsigned long cpu_id = (unsigned long)v - 1;
+	struct device_node *node = of_get_cpu_node(cpu_id, NULL);
+	struct riscv_cpuinfo *ci = per_cpu_ptr(&riscv_cpuinfo, cpu_id);
+	const char *compat, *isa;
+
+	seq_printf(m, "processor\t: %lu\n", cpu_id);
+	seq_printf(m, "hart\t\t: %lu\n", cpuid_to_hartid_map(cpu_id));
+	if (!of_property_read_string(node, "riscv,isa", &isa))
+		print_isa(m, isa);
+	print_mmu(m);
+	if (!of_property_read_string(node, "compatible", &compat)
+	    && strcmp(compat, "riscv"))
+		seq_printf(m, "uarch\t\t: %s\n", compat);
+	seq_printf(m, "mvendorid\t: 0x%lx\n", ci->mvendorid);
+	seq_printf(m, "marchid\t\t: 0x%lx\n", ci->marchid);
+	seq_printf(m, "mimpid\t\t: 0x%lx\n", ci->mimpid);
+	seq_puts(m, "\n");
+	of_node_put(node);
+
+	return 0;
+}
+
+const struct seq_operations cpuinfo_op = {
+	.start	= c_start,
+	.next	= c_next,
+	.stop	= c_stop,
+	.show	= c_show
+};
+
+#endif /* CONFIG_PROC_FS */
diff --git a/arch/riscv/kernel/cpu_ops.c b/arch/riscv/kernel/cpu_ops.c
new file mode 100644
index 000000000..eb479a88a
--- /dev/null
+++ b/arch/riscv/kernel/cpu_ops.c
@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2020 Western Digital Corporation or its affiliates.
+ */
+
+#include <linux/errno.h>
+#include <linux/mm.h>
+#include <linux/of.h>
+#include <linux/string.h>
+#include <linux/sched.h>
+#include <asm/cpu_ops.h>
+#include <asm/cpu_ops_sbi.h>
+#include <asm/sbi.h>
+#include <asm/smp.h>
+
+const struct cpu_operations *cpu_ops[NR_CPUS] __ro_after_init;
+
+extern const struct cpu_operations cpu_ops_sbi;
+#ifndef CONFIG_RISCV_BOOT_SPINWAIT
+const struct cpu_operations cpu_ops_spinwait = {
+	.name		= "",
+	.cpu_prepare	= NULL,
+	.cpu_start	= NULL,
+};
+#endif
+
+void __init cpu_set_ops(int cpuid)
+{
+#if IS_ENABLED(CONFIG_RISCV_SBI)
+	if (sbi_probe_extension(SBI_EXT_HSM)) {
+		if (!cpuid)
+			pr_info("SBI HSM extension detected\n");
+		cpu_ops[cpuid] = &cpu_ops_sbi;
+	} else
+#endif
+		cpu_ops[cpuid] = &cpu_ops_spinwait;
+}
diff --git a/arch/riscv/kernel/cpu_ops_sbi.c b/arch/riscv/kernel/cpu_ops_sbi.c
new file mode 100644
index 000000000..efa0f0816
--- /dev/null
+++ b/arch/riscv/kernel/cpu_ops_sbi.c
@@ -0,0 +1,129 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * HSM extension and cpu_ops implementation.
+ *
+ * Copyright (c) 2020 Western Digital Corporation or its affiliates.
+ */
+
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/sched/task_stack.h>
+#include <asm/cpu_ops.h>
+#include <asm/cpu_ops_sbi.h>
+#include <asm/sbi.h>
+#include <asm/smp.h>
+
+extern char secondary_start_sbi[];
+const struct cpu_operations cpu_ops_sbi;
+
+/*
+ * Ordered booting via HSM brings one cpu at a time. However, cpu hotplug can
+ * be invoked from multiple threads in parallel. Define a per cpu data
+ * to handle that.
+ */
+static DEFINE_PER_CPU(struct sbi_hart_boot_data, boot_data);
+
+static int sbi_hsm_hart_start(unsigned long hartid, unsigned long saddr,
+			      unsigned long priv)
+{
+	struct sbiret ret;
+
+	ret = sbi_ecall(SBI_EXT_HSM, SBI_EXT_HSM_HART_START,
+			hartid, saddr, priv, 0, 0, 0);
+	if (ret.error)
+		return sbi_err_map_linux_errno(ret.error);
+	else
+		return 0;
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+static int sbi_hsm_hart_stop(void)
+{
+	struct sbiret ret;
+
+	ret = sbi_ecall(SBI_EXT_HSM, SBI_EXT_HSM_HART_STOP, 0, 0, 0, 0, 0, 0);
+
+	if (ret.error)
+		return sbi_err_map_linux_errno(ret.error);
+	else
+		return 0;
+}
+
+static int sbi_hsm_hart_get_status(unsigned long hartid)
+{
+	struct sbiret ret;
+
+	ret = sbi_ecall(SBI_EXT_HSM, SBI_EXT_HSM_HART_STATUS,
+			hartid, 0, 0, 0, 0, 0);
+	if (ret.error)
+		return sbi_err_map_linux_errno(ret.error);
+	else
+		return ret.value;
+}
+#endif
+
+static int sbi_cpu_start(unsigned int cpuid, struct task_struct *tidle)
+{
+	unsigned long boot_addr = __pa_symbol(secondary_start_sbi);
+	unsigned long hartid = cpuid_to_hartid_map(cpuid);
+	unsigned long hsm_data;
+	struct sbi_hart_boot_data *bdata = &per_cpu(boot_data, cpuid);
+
+	/* Make sure tidle is updated */
+	smp_mb();
+	bdata->task_ptr = tidle;
+	bdata->stack_ptr = task_stack_page(tidle) + THREAD_SIZE;
+	/* Make sure boot data is updated */
+	smp_mb();
+	hsm_data = __pa(bdata);
+	return sbi_hsm_hart_start(hartid, boot_addr, hsm_data);
+}
+
+static int sbi_cpu_prepare(unsigned int cpuid)
+{
+	if (!cpu_ops_sbi.cpu_start) {
+		pr_err("cpu start method not defined for CPU [%d]\n", cpuid);
+		return -ENODEV;
+	}
+	return 0;
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+static int sbi_cpu_disable(unsigned int cpuid)
+{
+	if (!cpu_ops_sbi.cpu_stop)
+		return -EOPNOTSUPP;
+	return 0;
+}
+
+static void sbi_cpu_stop(void)
+{
+	int ret;
+
+	ret = sbi_hsm_hart_stop();
+	pr_crit("Unable to stop the cpu %u (%d)\n", smp_processor_id(), ret);
+}
+
+static int sbi_cpu_is_stopped(unsigned int cpuid)
+{
+	int rc;
+	unsigned long hartid = cpuid_to_hartid_map(cpuid);
+
+	rc = sbi_hsm_hart_get_status(hartid);
+
+	if (rc == SBI_HSM_STATE_STOPPED)
+		return 0;
+	return rc;
+}
+#endif
+
+const struct cpu_operations cpu_ops_sbi = {
+	.name		= "sbi",
+	.cpu_prepare	= sbi_cpu_prepare,
+	.cpu_start	= sbi_cpu_start,
+#ifdef CONFIG_HOTPLUG_CPU
+	.cpu_disable	= sbi_cpu_disable,
+	.cpu_stop	= sbi_cpu_stop,
+	.cpu_is_stopped	= sbi_cpu_is_stopped,
+#endif
+};
diff --git a/arch/riscv/kernel/cpu_ops_spinwait.c b/arch/riscv/kernel/cpu_ops_spinwait.c
new file mode 100644
index 000000000..d98d19226
--- /dev/null
+++ b/arch/riscv/kernel/cpu_ops_spinwait.c
@@ -0,0 +1,70 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2020 Western Digital Corporation or its affiliates.
+ */
+
+#include <linux/errno.h>
+#include <linux/of.h>
+#include <linux/string.h>
+#include <linux/sched/task_stack.h>
+#include <asm/cpu_ops.h>
+#include <asm/sbi.h>
+#include <asm/smp.h>
+
+#include "head.h"
+
+const struct cpu_operations cpu_ops_spinwait;
+void *__cpu_spinwait_stack_pointer[NR_CPUS] __section(".data");
+void *__cpu_spinwait_task_pointer[NR_CPUS] __section(".data");
+
+static void cpu_update_secondary_bootdata(unsigned int cpuid,
+				   struct task_struct *tidle)
+{
+	unsigned long hartid = cpuid_to_hartid_map(cpuid);
+
+	/*
+	 * The hartid must be less than NR_CPUS to avoid out-of-bound access
+	 * errors for __cpu_spinwait_stack/task_pointer. That is not always possible
+	 * for platforms with discontiguous hartid numbering scheme. That's why
+	 * spinwait booting is not the recommended approach for any platforms
+	 * booting Linux in S-mode and can be disabled in the future.
+	 */
+	if (hartid == INVALID_HARTID || hartid >= (unsigned long) NR_CPUS)
+		return;
+
+	/* Make sure tidle is updated */
+	smp_mb();
+	WRITE_ONCE(__cpu_spinwait_stack_pointer[hartid],
+		   task_stack_page(tidle) + THREAD_SIZE);
+	WRITE_ONCE(__cpu_spinwait_task_pointer[hartid], tidle);
+}
+
+static int spinwait_cpu_prepare(unsigned int cpuid)
+{
+	if (!cpu_ops_spinwait.cpu_start) {
+		pr_err("cpu start method not defined for CPU [%d]\n", cpuid);
+		return -ENODEV;
+	}
+	return 0;
+}
+
+static int spinwait_cpu_start(unsigned int cpuid, struct task_struct *tidle)
+{
+	/*
+	 * In this protocol, all cpus boot on their own accord.  _start
+	 * selects the first cpu to boot the kernel and causes the remainder
+	 * of the cpus to spin in a loop waiting for their stack pointer to be
+	 * setup by that main cpu.  Writing to bootdata
+	 * (i.e __cpu_spinwait_stack_pointer) signals to the spinning cpus that they
+	 * can continue the boot process.
+	 */
+	cpu_update_secondary_bootdata(cpuid, tidle);
+
+	return 0;
+}
+
+const struct cpu_operations cpu_ops_spinwait = {
+	.name		= "spinwait",
+	.cpu_prepare	= spinwait_cpu_prepare,
+	.cpu_start	= spinwait_cpu_start,
+};
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
new file mode 100644
index 000000000..fd1238df6
--- /dev/null
+++ b/arch/riscv/kernel/cpufeature.c
@@ -0,0 +1,327 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copied from arch/arm64/kernel/cpufeature.c
+ *
+ * Copyright (C) 2015 ARM Ltd.
+ * Copyright (C) 2017 SiFive
+ */
+
+#include <linux/bitmap.h>
+#include <linux/ctype.h>
+#include <linux/libfdt.h>
+#include <linux/memory.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <asm/alternative.h>
+#include <asm/cacheflush.h>
+#include <asm/errata_list.h>
+#include <asm/hwcap.h>
+#include <asm/patch.h>
+#include <asm/pgtable.h>
+#include <asm/processor.h>
+#include <asm/smp.h>
+#include <asm/switch_to.h>
+
+#define NUM_ALPHA_EXTS ('z' - 'a' + 1)
+
+unsigned long elf_hwcap __read_mostly;
+
+/* Host ISA bitmap */
+static DECLARE_BITMAP(riscv_isa, RISCV_ISA_EXT_MAX) __read_mostly;
+
+DEFINE_STATIC_KEY_ARRAY_FALSE(riscv_isa_ext_keys, RISCV_ISA_EXT_KEY_MAX);
+EXPORT_SYMBOL(riscv_isa_ext_keys);
+
+/**
+ * riscv_isa_extension_base() - Get base extension word
+ *
+ * @isa_bitmap: ISA bitmap to use
+ * Return: base extension word as unsigned long value
+ *
+ * NOTE: If isa_bitmap is NULL then Host ISA bitmap will be used.
+ */
+unsigned long riscv_isa_extension_base(const unsigned long *isa_bitmap)
+{
+	if (!isa_bitmap)
+		return riscv_isa[0];
+	return isa_bitmap[0];
+}
+EXPORT_SYMBOL_GPL(riscv_isa_extension_base);
+
+/**
+ * __riscv_isa_extension_available() - Check whether given extension
+ * is available or not
+ *
+ * @isa_bitmap: ISA bitmap to use
+ * @bit: bit position of the desired extension
+ * Return: true or false
+ *
+ * NOTE: If isa_bitmap is NULL then Host ISA bitmap will be used.
+ */
+bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, int bit)
+{
+	const unsigned long *bmap = (isa_bitmap) ? isa_bitmap : riscv_isa;
+
+	if (bit >= RISCV_ISA_EXT_MAX)
+		return false;
+
+	return test_bit(bit, bmap) ? true : false;
+}
+EXPORT_SYMBOL_GPL(__riscv_isa_extension_available);
+
+void __init riscv_fill_hwcap(void)
+{
+	struct device_node *node;
+	const char *isa;
+	char print_str[NUM_ALPHA_EXTS + 1];
+	int i, j, rc;
+	static unsigned long isa2hwcap[256] = {0};
+	unsigned long hartid;
+
+	isa2hwcap['i'] = isa2hwcap['I'] = COMPAT_HWCAP_ISA_I;
+	isa2hwcap['m'] = isa2hwcap['M'] = COMPAT_HWCAP_ISA_M;
+	isa2hwcap['a'] = isa2hwcap['A'] = COMPAT_HWCAP_ISA_A;
+	isa2hwcap['f'] = isa2hwcap['F'] = COMPAT_HWCAP_ISA_F;
+	isa2hwcap['d'] = isa2hwcap['D'] = COMPAT_HWCAP_ISA_D;
+	isa2hwcap['c'] = isa2hwcap['C'] = COMPAT_HWCAP_ISA_C;
+
+	elf_hwcap = 0;
+
+	bitmap_zero(riscv_isa, RISCV_ISA_EXT_MAX);
+
+	for_each_of_cpu_node(node) {
+		unsigned long this_hwcap = 0;
+		DECLARE_BITMAP(this_isa, RISCV_ISA_EXT_MAX);
+		const char *temp;
+
+		rc = riscv_of_processor_hartid(node, &hartid);
+		if (rc < 0)
+			continue;
+
+		if (of_property_read_string(node, "riscv,isa", &isa)) {
+			pr_warn("Unable to find \"riscv,isa\" devicetree entry\n");
+			continue;
+		}
+
+		temp = isa;
+#if IS_ENABLED(CONFIG_32BIT)
+		if (!strncmp(isa, "rv32", 4))
+			isa += 4;
+#elif IS_ENABLED(CONFIG_64BIT)
+		if (!strncmp(isa, "rv64", 4))
+			isa += 4;
+#endif
+		/* The riscv,isa DT property must start with rv64 or rv32 */
+		if (temp == isa)
+			continue;
+		bitmap_zero(this_isa, RISCV_ISA_EXT_MAX);
+		for (; *isa; ++isa) {
+			const char *ext = isa++;
+			const char *ext_end = isa;
+			bool ext_long = false, ext_err = false;
+
+			switch (*ext) {
+			case 's':
+				/**
+				 * Workaround for invalid single-letter 's' & 'u'(QEMU).
+				 * No need to set the bit in riscv_isa as 's' & 'u' are
+				 * not valid ISA extensions. It works until multi-letter
+				 * extension starting with "Su" appears.
+				 */
+				if (ext[-1] != '_' && ext[1] == 'u') {
+					++isa;
+					ext_err = true;
+					break;
+				}
+				fallthrough;
+			case 'x':
+			case 'z':
+				ext_long = true;
+				/* Multi-letter extension must be delimited */
+				for (; *isa && *isa != '_'; ++isa)
+					if (unlikely(!islower(*isa)
+						     && !isdigit(*isa)))
+						ext_err = true;
+				/* Parse backwards */
+				ext_end = isa;
+				if (unlikely(ext_err))
+					break;
+				if (!isdigit(ext_end[-1]))
+					break;
+				/* Skip the minor version */
+				while (isdigit(*--ext_end))
+					;
+				if (ext_end[0] != 'p'
+				    || !isdigit(ext_end[-1])) {
+					/* Advance it to offset the pre-decrement */
+					++ext_end;
+					break;
+				}
+				/* Skip the major version */
+				while (isdigit(*--ext_end))
+					;
+				++ext_end;
+				break;
+			default:
+				if (unlikely(!islower(*ext))) {
+					ext_err = true;
+					break;
+				}
+				/* Find next extension */
+				if (!isdigit(*isa))
+					break;
+				/* Skip the minor version */
+				while (isdigit(*++isa))
+					;
+				if (*isa != 'p')
+					break;
+				if (!isdigit(*++isa)) {
+					--isa;
+					break;
+				}
+				/* Skip the major version */
+				while (isdigit(*++isa))
+					;
+				break;
+			}
+			if (*isa != '_')
+				--isa;
+
+#define SET_ISA_EXT_MAP(name, bit)						\
+			do {							\
+				if ((ext_end - ext == sizeof(name) - 1) &&	\
+				     !memcmp(ext, name, sizeof(name) - 1))	\
+					set_bit(bit, this_isa);			\
+			} while (false)						\
+
+			if (unlikely(ext_err))
+				continue;
+			if (!ext_long) {
+				this_hwcap |= isa2hwcap[(unsigned char)(*ext)];
+				set_bit(*ext - 'a', this_isa);
+			} else {
+				SET_ISA_EXT_MAP("sscofpmf", RISCV_ISA_EXT_SSCOFPMF);
+				SET_ISA_EXT_MAP("svpbmt", RISCV_ISA_EXT_SVPBMT);
+				SET_ISA_EXT_MAP("zicbom", RISCV_ISA_EXT_ZICBOM);
+				SET_ISA_EXT_MAP("zihintpause", RISCV_ISA_EXT_ZIHINTPAUSE);
+				SET_ISA_EXT_MAP("sstc", RISCV_ISA_EXT_SSTC);
+				SET_ISA_EXT_MAP("svinval", RISCV_ISA_EXT_SVINVAL);
+			}
+#undef SET_ISA_EXT_MAP
+		}
+
+		/*
+		 * All "okay" hart should have same isa. Set HWCAP based on
+		 * common capabilities of every "okay" hart, in case they don't
+		 * have.
+		 */
+		if (elf_hwcap)
+			elf_hwcap &= this_hwcap;
+		else
+			elf_hwcap = this_hwcap;
+
+		if (bitmap_empty(riscv_isa, RISCV_ISA_EXT_MAX))
+			bitmap_copy(riscv_isa, this_isa, RISCV_ISA_EXT_MAX);
+		else
+			bitmap_and(riscv_isa, riscv_isa, this_isa, RISCV_ISA_EXT_MAX);
+	}
+
+	/* We don't support systems with F but without D, so mask those out
+	 * here. */
+	if ((elf_hwcap & COMPAT_HWCAP_ISA_F) && !(elf_hwcap & COMPAT_HWCAP_ISA_D)) {
+		pr_info("This kernel does not support systems with F but not D\n");
+		elf_hwcap &= ~COMPAT_HWCAP_ISA_F;
+	}
+
+	memset(print_str, 0, sizeof(print_str));
+	for (i = 0, j = 0; i < NUM_ALPHA_EXTS; i++)
+		if (riscv_isa[0] & BIT_MASK(i))
+			print_str[j++] = (char)('a' + i);
+	pr_info("riscv: base ISA extensions %s\n", print_str);
+
+	memset(print_str, 0, sizeof(print_str));
+	for (i = 0, j = 0; i < NUM_ALPHA_EXTS; i++)
+		if (elf_hwcap & BIT_MASK(i))
+			print_str[j++] = (char)('a' + i);
+	pr_info("riscv: ELF capabilities %s\n", print_str);
+
+	for_each_set_bit(i, riscv_isa, RISCV_ISA_EXT_MAX) {
+		j = riscv_isa_ext2key(i);
+		if (j >= 0)
+			static_branch_enable(&riscv_isa_ext_keys[j]);
+	}
+}
+
+#ifdef CONFIG_RISCV_ALTERNATIVE
+static bool __init_or_module cpufeature_probe_svpbmt(unsigned int stage)
+{
+	if (!IS_ENABLED(CONFIG_RISCV_ISA_SVPBMT))
+		return false;
+
+	if (stage == RISCV_ALTERNATIVES_EARLY_BOOT)
+		return false;
+
+	return riscv_isa_extension_available(NULL, SVPBMT);
+}
+
+static bool __init_or_module cpufeature_probe_zicbom(unsigned int stage)
+{
+	if (!IS_ENABLED(CONFIG_RISCV_ISA_ZICBOM))
+		return false;
+
+	if (stage == RISCV_ALTERNATIVES_EARLY_BOOT)
+		return false;
+
+	if (!riscv_isa_extension_available(NULL, ZICBOM))
+		return false;
+
+	riscv_noncoherent_supported();
+	return true;
+}
+
+/*
+ * Probe presence of individual extensions.
+ *
+ * This code may also be executed before kernel relocation, so we cannot use
+ * addresses generated by the address-of operator as they won't be valid in
+ * this context.
+ */
+static u32 __init_or_module cpufeature_probe(unsigned int stage)
+{
+	u32 cpu_req_feature = 0;
+
+	if (cpufeature_probe_svpbmt(stage))
+		cpu_req_feature |= BIT(CPUFEATURE_SVPBMT);
+
+	if (cpufeature_probe_zicbom(stage))
+		cpu_req_feature |= BIT(CPUFEATURE_ZICBOM);
+
+	return cpu_req_feature;
+}
+
+void __init_or_module riscv_cpufeature_patch_func(struct alt_entry *begin,
+						  struct alt_entry *end,
+						  unsigned int stage)
+{
+	u32 cpu_req_feature = cpufeature_probe(stage);
+	struct alt_entry *alt;
+	u32 tmp;
+
+	for (alt = begin; alt < end; alt++) {
+		if (alt->vendor_id != 0)
+			continue;
+		if (alt->errata_id >= CPUFEATURE_NUMBER) {
+			WARN(1, "This feature id:%d is not in kernel cpufeature list",
+				alt->errata_id);
+			continue;
+		}
+
+		tmp = (1U << alt->errata_id);
+		if (cpu_req_feature & tmp) {
+			mutex_lock(&text_mutex);
+			patch_text_nosync(alt->old_ptr, alt->alt_ptr, alt->alt_len);
+			mutex_unlock(&text_mutex);
+		}
+	}
+}
+#endif
diff --git a/arch/riscv/kernel/crash_dump.c b/arch/riscv/kernel/crash_dump.c
new file mode 100644
index 000000000..ea2158cee
--- /dev/null
+++ b/arch/riscv/kernel/crash_dump.c
@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * This code comes from arch/arm64/kernel/crash_dump.c
+ * Created by: AKASHI Takahiro <takahiro.akashi@linaro.org>
+ * Copyright (C) 2017 Linaro Limited
+ */
+
+#include <linux/crash_dump.h>
+#include <linux/io.h>
+#include <linux/uio.h>
+
+ssize_t copy_oldmem_page(struct iov_iter *iter, unsigned long pfn,
+			 size_t csize, unsigned long offset)
+{
+	void *vaddr;
+
+	if (!csize)
+		return 0;
+
+	vaddr = memremap(__pfn_to_phys(pfn), PAGE_SIZE, MEMREMAP_WB);
+	if (!vaddr)
+		return -ENOMEM;
+
+	csize = copy_to_iter(vaddr + offset, csize, iter);
+
+	memunmap(vaddr);
+	return csize;
+}
diff --git a/arch/riscv/kernel/crash_save_regs.S b/arch/riscv/kernel/crash_save_regs.S
new file mode 100644
index 000000000..b2a1908c0
--- /dev/null
+++ b/arch/riscv/kernel/crash_save_regs.S
@@ -0,0 +1,56 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020 FORTH-ICS/CARV
+ *  Nick Kossifidis <mick@ics.forth.gr>
+ */
+
+#include <asm/asm.h>    	/* For RISCV_* and REG_* macros */
+#include <asm/csr.h>		/* For CSR_* macros */
+#include <asm/asm-offsets.h>	/* For offsets on pt_regs */
+#include <linux/linkage.h>	/* For SYM_* macros */
+
+.section ".text"
+SYM_CODE_START(riscv_crash_save_regs)
+	REG_S ra,  PT_RA(a0)	/* x1 */
+	REG_S sp,  PT_SP(a0)	/* x2 */
+	REG_S gp,  PT_GP(a0)	/* x3 */
+	REG_S tp,  PT_TP(a0)	/* x4 */
+	REG_S t0,  PT_T0(a0)	/* x5 */
+	REG_S t1,  PT_T1(a0)	/* x6 */
+	REG_S t2,  PT_T2(a0)	/* x7 */
+	REG_S s0,  PT_S0(a0)	/* x8/fp */
+	REG_S s1,  PT_S1(a0)	/* x9 */
+	REG_S a0,  PT_A0(a0)	/* x10 */
+	REG_S a1,  PT_A1(a0)	/* x11 */
+	REG_S a2,  PT_A2(a0)	/* x12 */
+	REG_S a3,  PT_A3(a0)	/* x13 */
+	REG_S a4,  PT_A4(a0)	/* x14 */
+	REG_S a5,  PT_A5(a0)	/* x15 */
+	REG_S a6,  PT_A6(a0)	/* x16 */
+	REG_S a7,  PT_A7(a0)	/* x17 */
+	REG_S s2,  PT_S2(a0)	/* x18 */
+	REG_S s3,  PT_S3(a0)	/* x19 */
+	REG_S s4,  PT_S4(a0)	/* x20 */
+	REG_S s5,  PT_S5(a0)	/* x21 */
+	REG_S s6,  PT_S6(a0)	/* x22 */
+	REG_S s7,  PT_S7(a0)	/* x23 */
+	REG_S s8,  PT_S8(a0)	/* x24 */
+	REG_S s9,  PT_S9(a0)	/* x25 */
+	REG_S s10, PT_S10(a0)	/* x26 */
+	REG_S s11, PT_S11(a0)	/* x27 */
+	REG_S t3,  PT_T3(a0)	/* x28 */
+	REG_S t4,  PT_T4(a0)	/* x29 */
+	REG_S t5,  PT_T5(a0)	/* x30 */
+	REG_S t6,  PT_T6(a0)	/* x31 */
+
+	csrr t1, CSR_STATUS
+	auipc t2, 0x0
+	csrr t3, CSR_TVAL
+	csrr t4, CSR_CAUSE
+
+	REG_S t1, PT_STATUS(a0)
+	REG_S t2, PT_EPC(a0)
+	REG_S t3, PT_BADADDR(a0)
+	REG_S t4, PT_CAUSE(a0)
+	ret
+SYM_CODE_END(riscv_crash_save_regs)
diff --git a/arch/riscv/kernel/efi-header.S b/arch/riscv/kernel/efi-header.S
new file mode 100644
index 000000000..8e733aa48
--- /dev/null
+++ b/arch/riscv/kernel/efi-header.S
@@ -0,0 +1,111 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2020 Western Digital Corporation or its affiliates.
+ * Adapted from arch/arm64/kernel/efi-header.S
+ */
+
+#include <linux/pe.h>
+#include <linux/sizes.h>
+
+	.macro	__EFI_PE_HEADER
+	.long	PE_MAGIC
+coff_header:
+#ifdef CONFIG_64BIT
+	.short	IMAGE_FILE_MACHINE_RISCV64		// Machine
+#else
+	.short	IMAGE_FILE_MACHINE_RISCV32		// Machine
+#endif
+	.short	section_count				// NumberOfSections
+	.long	0 					// TimeDateStamp
+	.long	0					// PointerToSymbolTable
+	.long	0					// NumberOfSymbols
+	.short	section_table - optional_header		// SizeOfOptionalHeader
+	.short	IMAGE_FILE_DEBUG_STRIPPED | \
+		IMAGE_FILE_EXECUTABLE_IMAGE | \
+		IMAGE_FILE_LINE_NUMS_STRIPPED		// Characteristics
+
+optional_header:
+#ifdef CONFIG_64BIT
+	.short	PE_OPT_MAGIC_PE32PLUS			// PE32+ format
+#else
+	.short	PE_OPT_MAGIC_PE32			// PE32 format
+#endif
+	.byte	0x02					// MajorLinkerVersion
+	.byte	0x14					// MinorLinkerVersion
+	.long	__pecoff_text_end - efi_header_end	// SizeOfCode
+	.long	__pecoff_data_virt_size			// SizeOfInitializedData
+	.long	0					// SizeOfUninitializedData
+	.long	__efistub_efi_pe_entry - _start		// AddressOfEntryPoint
+	.long	efi_header_end - _start			// BaseOfCode
+#ifdef CONFIG_32BIT
+	.long  __pecoff_text_end - _start		// BaseOfData
+#endif
+
+extra_header_fields:
+	.quad	0					// ImageBase
+	.long	PECOFF_SECTION_ALIGNMENT		// SectionAlignment
+	.long	PECOFF_FILE_ALIGNMENT			// FileAlignment
+	.short	0					// MajorOperatingSystemVersion
+	.short	0					// MinorOperatingSystemVersion
+	.short	LINUX_EFISTUB_MAJOR_VERSION		// MajorImageVersion
+	.short	LINUX_EFISTUB_MINOR_VERSION		// MinorImageVersion
+	.short	0					// MajorSubsystemVersion
+	.short	0					// MinorSubsystemVersion
+	.long	0					// Win32VersionValue
+
+	.long	_end - _start				// SizeOfImage
+
+	// Everything before the kernel image is considered part of the header
+	.long	efi_header_end - _start			// SizeOfHeaders
+	.long	0					// CheckSum
+	.short	IMAGE_SUBSYSTEM_EFI_APPLICATION		// Subsystem
+	.short	0					// DllCharacteristics
+	.quad	0					// SizeOfStackReserve
+	.quad	0					// SizeOfStackCommit
+	.quad	0					// SizeOfHeapReserve
+	.quad	0					// SizeOfHeapCommit
+	.long	0					// LoaderFlags
+	.long	(section_table - .) / 8			// NumberOfRvaAndSizes
+
+	.quad	0					// ExportTable
+	.quad	0					// ImportTable
+	.quad	0					// ResourceTable
+	.quad	0					// ExceptionTable
+	.quad	0					// CertificationTable
+	.quad	0					// BaseRelocationTable
+
+	// Section table
+section_table:
+	.ascii	".text\0\0\0"
+	.long	__pecoff_text_end - efi_header_end	// VirtualSize
+	.long	efi_header_end - _start			// VirtualAddress
+	.long	__pecoff_text_end - efi_header_end	// SizeOfRawData
+	.long	efi_header_end - _start			// PointerToRawData
+
+	.long	0					// PointerToRelocations
+	.long	0					// PointerToLineNumbers
+	.short	0					// NumberOfRelocations
+	.short	0					// NumberOfLineNumbers
+	.long	IMAGE_SCN_CNT_CODE | \
+		IMAGE_SCN_MEM_READ | \
+		IMAGE_SCN_MEM_EXECUTE			// Characteristics
+
+	.ascii	".data\0\0\0"
+	.long	__pecoff_data_virt_size			// VirtualSize
+	.long	__pecoff_text_end - _start		// VirtualAddress
+	.long	__pecoff_data_raw_size			// SizeOfRawData
+	.long	__pecoff_text_end - _start		// PointerToRawData
+
+	.long	0					// PointerToRelocations
+	.long	0					// PointerToLineNumbers
+	.short	0					// NumberOfRelocations
+	.short	0					// NumberOfLineNumbers
+	.long	IMAGE_SCN_CNT_INITIALIZED_DATA | \
+		IMAGE_SCN_MEM_READ | \
+		IMAGE_SCN_MEM_WRITE			// Characteristics
+
+	.set	section_count, (. - section_table) / 40
+
+	.balign	0x1000
+efi_header_end:
+	.endm
diff --git a/arch/riscv/kernel/efi.c b/arch/riscv/kernel/efi.c
new file mode 100644
index 000000000..1aa540350
--- /dev/null
+++ b/arch/riscv/kernel/efi.c
@@ -0,0 +1,96 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020 Western Digital Corporation or its affiliates.
+ * Adapted from arch/arm64/kernel/efi.c
+ */
+
+#include <linux/efi.h>
+#include <linux/init.h>
+
+#include <asm/efi.h>
+#include <asm/pgtable.h>
+#include <asm/pgtable-bits.h>
+
+/*
+ * Only regions of type EFI_RUNTIME_SERVICES_CODE need to be
+ * executable, everything else can be mapped with the XN bits
+ * set. Also take the new (optional) RO/XP bits into account.
+ */
+static __init pgprot_t efimem_to_pgprot_map(efi_memory_desc_t *md)
+{
+	u64 attr = md->attribute;
+	u32 type = md->type;
+
+	if (type == EFI_MEMORY_MAPPED_IO)
+		return PAGE_KERNEL;
+
+	/* R-- */
+	if ((attr & (EFI_MEMORY_XP | EFI_MEMORY_RO)) ==
+	    (EFI_MEMORY_XP | EFI_MEMORY_RO))
+		return PAGE_KERNEL_READ;
+
+	/* R-X */
+	if (attr & EFI_MEMORY_RO)
+		return PAGE_KERNEL_READ_EXEC;
+
+	/* RW- */
+	if (((attr & (EFI_MEMORY_RP | EFI_MEMORY_WP | EFI_MEMORY_XP)) ==
+	     EFI_MEMORY_XP) ||
+	    type != EFI_RUNTIME_SERVICES_CODE)
+		return PAGE_KERNEL;
+
+	/* RWX */
+	return PAGE_KERNEL_EXEC;
+}
+
+int __init efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md)
+{
+	pgprot_t prot = __pgprot(pgprot_val(efimem_to_pgprot_map(md)) &
+				~(_PAGE_GLOBAL));
+	int i;
+
+	/* RISC-V maps one page at a time */
+	for (i = 0; i < md->num_pages; i++)
+		create_pgd_mapping(mm->pgd, md->virt_addr + i * PAGE_SIZE,
+				   md->phys_addr + i * PAGE_SIZE,
+				   PAGE_SIZE, prot);
+	return 0;
+}
+
+static int __init set_permissions(pte_t *ptep, unsigned long addr, void *data)
+{
+	efi_memory_desc_t *md = data;
+	pte_t pte = READ_ONCE(*ptep);
+	unsigned long val;
+
+	if (md->attribute & EFI_MEMORY_RO) {
+		val = pte_val(pte) & ~_PAGE_WRITE;
+		val |= _PAGE_READ;
+		pte = __pte(val);
+	}
+	if (md->attribute & EFI_MEMORY_XP) {
+		val = pte_val(pte) & ~_PAGE_EXEC;
+		pte = __pte(val);
+	}
+	set_pte(ptep, pte);
+
+	return 0;
+}
+
+int __init efi_set_mapping_permissions(struct mm_struct *mm,
+				       efi_memory_desc_t *md)
+{
+	BUG_ON(md->type != EFI_RUNTIME_SERVICES_CODE &&
+	       md->type != EFI_RUNTIME_SERVICES_DATA);
+
+	/*
+	 * Calling apply_to_page_range() is only safe on regions that are
+	 * guaranteed to be mapped down to pages. Since we are only called
+	 * for regions that have been mapped using efi_create_mapping() above
+	 * (and this is checked by the generic Memory Attributes table parsing
+	 * routines), there is no need to check that again here.
+	 */
+	return apply_to_page_range(mm, md->virt_addr,
+				   md->num_pages << EFI_PAGE_SHIFT,
+				   set_permissions, md);
+}
diff --git a/arch/riscv/kernel/elf_kexec.c b/arch/riscv/kernel/elf_kexec.c
new file mode 100644
index 000000000..b3b96ff46
--- /dev/null
+++ b/arch/riscv/kernel/elf_kexec.c
@@ -0,0 +1,469 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Load ELF vmlinux file for the kexec_file_load syscall.
+ *
+ * Copyright (C) 2021 Huawei Technologies Co, Ltd.
+ *
+ * Author: Liao Chang (liaochang1@huawei.com)
+ *
+ * Based on kexec-tools' kexec-elf-riscv.c, heavily modified
+ * for kernel.
+ */
+
+#define pr_fmt(fmt)	"kexec_image: " fmt
+
+#include <linux/elf.h>
+#include <linux/kexec.h>
+#include <linux/slab.h>
+#include <linux/of.h>
+#include <linux/libfdt.h>
+#include <linux/types.h>
+#include <linux/memblock.h>
+#include <asm/setup.h>
+
+int arch_kimage_file_post_load_cleanup(struct kimage *image)
+{
+	kvfree(image->arch.fdt);
+	image->arch.fdt = NULL;
+
+	vfree(image->elf_headers);
+	image->elf_headers = NULL;
+	image->elf_headers_sz = 0;
+
+	return kexec_image_post_load_cleanup_default(image);
+}
+
+static int riscv_kexec_elf_load(struct kimage *image, struct elfhdr *ehdr,
+				struct kexec_elf_info *elf_info, unsigned long old_pbase,
+				unsigned long new_pbase)
+{
+	int i;
+	int ret = 0;
+	size_t size;
+	struct kexec_buf kbuf;
+	const struct elf_phdr *phdr;
+
+	kbuf.image = image;
+
+	for (i = 0; i < ehdr->e_phnum; i++) {
+		phdr = &elf_info->proghdrs[i];
+		if (phdr->p_type != PT_LOAD)
+			continue;
+
+		size = phdr->p_filesz;
+		if (size > phdr->p_memsz)
+			size = phdr->p_memsz;
+
+		kbuf.buffer = (void *) elf_info->buffer + phdr->p_offset;
+		kbuf.bufsz = size;
+		kbuf.buf_align = phdr->p_align;
+		kbuf.mem = phdr->p_paddr - old_pbase + new_pbase;
+		kbuf.memsz = phdr->p_memsz;
+		kbuf.top_down = false;
+		ret = kexec_add_buffer(&kbuf);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
+/*
+ * Go through the available phsyical memory regions and find one that hold
+ * an image of the specified size.
+ */
+static int elf_find_pbase(struct kimage *image, unsigned long kernel_len,
+			  struct elfhdr *ehdr, struct kexec_elf_info *elf_info,
+			  unsigned long *old_pbase, unsigned long *new_pbase)
+{
+	int i;
+	int ret;
+	struct kexec_buf kbuf;
+	const struct elf_phdr *phdr;
+	unsigned long lowest_paddr = ULONG_MAX;
+	unsigned long lowest_vaddr = ULONG_MAX;
+
+	for (i = 0; i < ehdr->e_phnum; i++) {
+		phdr = &elf_info->proghdrs[i];
+		if (phdr->p_type != PT_LOAD)
+			continue;
+
+		if (lowest_paddr > phdr->p_paddr)
+			lowest_paddr = phdr->p_paddr;
+
+		if (lowest_vaddr > phdr->p_vaddr)
+			lowest_vaddr = phdr->p_vaddr;
+	}
+
+	kbuf.image = image;
+	kbuf.buf_min = lowest_paddr;
+	kbuf.buf_max = ULONG_MAX;
+
+	/*
+	 * Current riscv boot protocol requires 2MB alignment for
+	 * RV64 and 4MB alignment for RV32
+	 *
+	 */
+	kbuf.buf_align = PMD_SIZE;
+	kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
+	kbuf.memsz = ALIGN(kernel_len, PAGE_SIZE);
+	kbuf.top_down = false;
+	ret = arch_kexec_locate_mem_hole(&kbuf);
+	if (!ret) {
+		*old_pbase = lowest_paddr;
+		*new_pbase = kbuf.mem;
+		image->start = ehdr->e_entry - lowest_vaddr + kbuf.mem;
+	}
+	return ret;
+}
+
+static int get_nr_ram_ranges_callback(struct resource *res, void *arg)
+{
+	unsigned int *nr_ranges = arg;
+
+	(*nr_ranges)++;
+	return 0;
+}
+
+static int prepare_elf64_ram_headers_callback(struct resource *res, void *arg)
+{
+	struct crash_mem *cmem = arg;
+
+	cmem->ranges[cmem->nr_ranges].start = res->start;
+	cmem->ranges[cmem->nr_ranges].end = res->end;
+	cmem->nr_ranges++;
+
+	return 0;
+}
+
+static int prepare_elf_headers(void **addr, unsigned long *sz)
+{
+	struct crash_mem *cmem;
+	unsigned int nr_ranges;
+	int ret;
+
+	nr_ranges = 1; /* For exclusion of crashkernel region */
+	walk_system_ram_res(0, -1, &nr_ranges, get_nr_ram_ranges_callback);
+
+	cmem = kmalloc(struct_size(cmem, ranges, nr_ranges), GFP_KERNEL);
+	if (!cmem)
+		return -ENOMEM;
+
+	cmem->max_nr_ranges = nr_ranges;
+	cmem->nr_ranges = 0;
+	ret = walk_system_ram_res(0, -1, cmem, prepare_elf64_ram_headers_callback);
+	if (ret)
+		goto out;
+
+	/* Exclude crashkernel region */
+	ret = crash_exclude_mem_range(cmem, crashk_res.start, crashk_res.end);
+	if (!ret)
+		ret = crash_prepare_elf64_headers(cmem, true, addr, sz);
+
+out:
+	kfree(cmem);
+	return ret;
+}
+
+static char *setup_kdump_cmdline(struct kimage *image, char *cmdline,
+				 unsigned long cmdline_len)
+{
+	int elfcorehdr_strlen;
+	char *cmdline_ptr;
+
+	cmdline_ptr = kzalloc(COMMAND_LINE_SIZE, GFP_KERNEL);
+	if (!cmdline_ptr)
+		return NULL;
+
+	elfcorehdr_strlen = sprintf(cmdline_ptr, "elfcorehdr=0x%lx ",
+		image->elf_load_addr);
+
+	if (elfcorehdr_strlen + cmdline_len > COMMAND_LINE_SIZE) {
+		pr_err("Appending elfcorehdr=<addr> exceeds cmdline size\n");
+		kfree(cmdline_ptr);
+		return NULL;
+	}
+
+	memcpy(cmdline_ptr + elfcorehdr_strlen, cmdline, cmdline_len);
+	/* Ensure it's nul terminated */
+	cmdline_ptr[COMMAND_LINE_SIZE - 1] = '\0';
+	return cmdline_ptr;
+}
+
+static void *elf_kexec_load(struct kimage *image, char *kernel_buf,
+			    unsigned long kernel_len, char *initrd,
+			    unsigned long initrd_len, char *cmdline,
+			    unsigned long cmdline_len)
+{
+	int ret;
+	unsigned long old_kernel_pbase = ULONG_MAX;
+	unsigned long new_kernel_pbase = 0UL;
+	unsigned long initrd_pbase = 0UL;
+	unsigned long headers_sz;
+	unsigned long kernel_start;
+	void *fdt, *headers;
+	struct elfhdr ehdr;
+	struct kexec_buf kbuf;
+	struct kexec_elf_info elf_info;
+	char *modified_cmdline = NULL;
+
+	ret = kexec_build_elf_info(kernel_buf, kernel_len, &ehdr, &elf_info);
+	if (ret)
+		return ERR_PTR(ret);
+
+	ret = elf_find_pbase(image, kernel_len, &ehdr, &elf_info,
+			     &old_kernel_pbase, &new_kernel_pbase);
+	if (ret)
+		goto out;
+	kernel_start = image->start;
+	pr_notice("The entry point of kernel at 0x%lx\n", image->start);
+
+	/* Add the kernel binary to the image */
+	ret = riscv_kexec_elf_load(image, &ehdr, &elf_info,
+				   old_kernel_pbase, new_kernel_pbase);
+	if (ret)
+		goto out;
+
+	kbuf.image = image;
+	kbuf.buf_min = new_kernel_pbase + kernel_len;
+	kbuf.buf_max = ULONG_MAX;
+
+	/* Add elfcorehdr */
+	if (image->type == KEXEC_TYPE_CRASH) {
+		ret = prepare_elf_headers(&headers, &headers_sz);
+		if (ret) {
+			pr_err("Preparing elf core header failed\n");
+			goto out;
+		}
+
+		kbuf.buffer = headers;
+		kbuf.bufsz = headers_sz;
+		kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
+		kbuf.memsz = headers_sz;
+		kbuf.buf_align = ELF_CORE_HEADER_ALIGN;
+		kbuf.top_down = true;
+
+		ret = kexec_add_buffer(&kbuf);
+		if (ret) {
+			vfree(headers);
+			goto out;
+		}
+		image->elf_headers = headers;
+		image->elf_load_addr = kbuf.mem;
+		image->elf_headers_sz = headers_sz;
+
+		pr_debug("Loaded elf core header at 0x%lx bufsz=0x%lx memsz=0x%lx\n",
+			 image->elf_load_addr, kbuf.bufsz, kbuf.memsz);
+
+		/* Setup cmdline for kdump kernel case */
+		modified_cmdline = setup_kdump_cmdline(image, cmdline,
+						       cmdline_len);
+		if (!modified_cmdline) {
+			pr_err("Setting up cmdline for kdump kernel failed\n");
+			ret = -EINVAL;
+			goto out;
+		}
+		cmdline = modified_cmdline;
+	}
+
+#ifdef CONFIG_ARCH_HAS_KEXEC_PURGATORY
+	/* Add purgatory to the image */
+	kbuf.top_down = true;
+	kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
+	ret = kexec_load_purgatory(image, &kbuf);
+	if (ret) {
+		pr_err("Error loading purgatory ret=%d\n", ret);
+		goto out;
+	}
+	ret = kexec_purgatory_get_set_symbol(image, "riscv_kernel_entry",
+					     &kernel_start,
+					     sizeof(kernel_start), 0);
+	if (ret)
+		pr_err("Error update purgatory ret=%d\n", ret);
+#endif /* CONFIG_ARCH_HAS_KEXEC_PURGATORY */
+
+	/* Add the initrd to the image */
+	if (initrd != NULL) {
+		kbuf.buffer = initrd;
+		kbuf.bufsz = kbuf.memsz = initrd_len;
+		kbuf.buf_align = PAGE_SIZE;
+		kbuf.top_down = true;
+		kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
+		ret = kexec_add_buffer(&kbuf);
+		if (ret)
+			goto out;
+		initrd_pbase = kbuf.mem;
+		pr_notice("Loaded initrd at 0x%lx\n", initrd_pbase);
+	}
+
+	/* Add the DTB to the image */
+	fdt = of_kexec_alloc_and_setup_fdt(image, initrd_pbase,
+					   initrd_len, cmdline, 0);
+	if (!fdt) {
+		pr_err("Error setting up the new device tree.\n");
+		ret = -EINVAL;
+		goto out;
+	}
+
+	fdt_pack(fdt);
+	kbuf.buffer = fdt;
+	kbuf.bufsz = kbuf.memsz = fdt_totalsize(fdt);
+	kbuf.buf_align = PAGE_SIZE;
+	kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
+	kbuf.top_down = true;
+	ret = kexec_add_buffer(&kbuf);
+	if (ret) {
+		pr_err("Error add DTB kbuf ret=%d\n", ret);
+		goto out_free_fdt;
+	}
+	/* Cache the fdt buffer address for memory cleanup */
+	image->arch.fdt = fdt;
+	pr_notice("Loaded device tree at 0x%lx\n", kbuf.mem);
+	goto out;
+
+out_free_fdt:
+	kvfree(fdt);
+out:
+	kfree(modified_cmdline);
+	kexec_free_elf_info(&elf_info);
+	return ret ? ERR_PTR(ret) : NULL;
+}
+
+#define RV_X(x, s, n)  (((x) >> (s)) & ((1 << (n)) - 1))
+#define RISCV_IMM_BITS 12
+#define RISCV_IMM_REACH (1LL << RISCV_IMM_BITS)
+#define RISCV_CONST_HIGH_PART(x) \
+	(((x) + (RISCV_IMM_REACH >> 1)) & ~(RISCV_IMM_REACH - 1))
+#define RISCV_CONST_LOW_PART(x) ((x) - RISCV_CONST_HIGH_PART(x))
+
+#define ENCODE_ITYPE_IMM(x) \
+	(RV_X(x, 0, 12) << 20)
+#define ENCODE_BTYPE_IMM(x) \
+	((RV_X(x, 1, 4) << 8) | (RV_X(x, 5, 6) << 25) | \
+	(RV_X(x, 11, 1) << 7) | (RV_X(x, 12, 1) << 31))
+#define ENCODE_UTYPE_IMM(x) \
+	(RV_X(x, 12, 20) << 12)
+#define ENCODE_JTYPE_IMM(x) \
+	((RV_X(x, 1, 10) << 21) | (RV_X(x, 11, 1) << 20) | \
+	(RV_X(x, 12, 8) << 12) | (RV_X(x, 20, 1) << 31))
+#define ENCODE_CBTYPE_IMM(x) \
+	((RV_X(x, 1, 2) << 3) | (RV_X(x, 3, 2) << 10) | (RV_X(x, 5, 1) << 2) | \
+	(RV_X(x, 6, 2) << 5) | (RV_X(x, 8, 1) << 12))
+#define ENCODE_CJTYPE_IMM(x) \
+	((RV_X(x, 1, 3) << 3) | (RV_X(x, 4, 1) << 11) | (RV_X(x, 5, 1) << 2) | \
+	(RV_X(x, 6, 1) << 7) | (RV_X(x, 7, 1) << 6) | (RV_X(x, 8, 2) << 9) | \
+	(RV_X(x, 10, 1) << 8) | (RV_X(x, 11, 1) << 12))
+#define ENCODE_UJTYPE_IMM(x) \
+	(ENCODE_UTYPE_IMM(RISCV_CONST_HIGH_PART(x)) | \
+	(ENCODE_ITYPE_IMM(RISCV_CONST_LOW_PART(x)) << 32))
+#define ENCODE_UITYPE_IMM(x) \
+	(ENCODE_UTYPE_IMM(x) | (ENCODE_ITYPE_IMM(x) << 32))
+
+#define CLEAN_IMM(type, x) \
+	((~ENCODE_##type##_IMM((uint64_t)(-1))) & (x))
+
+int arch_kexec_apply_relocations_add(struct purgatory_info *pi,
+				     Elf_Shdr *section,
+				     const Elf_Shdr *relsec,
+				     const Elf_Shdr *symtab)
+{
+	const char *strtab, *name, *shstrtab;
+	const Elf_Shdr *sechdrs;
+	Elf64_Rela *relas;
+	int i, r_type;
+
+	/* String & section header string table */
+	sechdrs = (void *)pi->ehdr + pi->ehdr->e_shoff;
+	strtab = (char *)pi->ehdr + sechdrs[symtab->sh_link].sh_offset;
+	shstrtab = (char *)pi->ehdr + sechdrs[pi->ehdr->e_shstrndx].sh_offset;
+
+	relas = (void *)pi->ehdr + relsec->sh_offset;
+
+	for (i = 0; i < relsec->sh_size / sizeof(*relas); i++) {
+		const Elf_Sym *sym;	/* symbol to relocate */
+		unsigned long addr;	/* final location after relocation */
+		unsigned long val;	/* relocated symbol value */
+		unsigned long sec_base;	/* relocated symbol value */
+		void *loc;		/* tmp location to modify */
+
+		sym = (void *)pi->ehdr + symtab->sh_offset;
+		sym += ELF64_R_SYM(relas[i].r_info);
+
+		if (sym->st_name)
+			name = strtab + sym->st_name;
+		else
+			name = shstrtab + sechdrs[sym->st_shndx].sh_name;
+
+		loc = pi->purgatory_buf;
+		loc += section->sh_offset;
+		loc += relas[i].r_offset;
+
+		if (sym->st_shndx == SHN_ABS)
+			sec_base = 0;
+		else if (sym->st_shndx >= pi->ehdr->e_shnum) {
+			pr_err("Invalid section %d for symbol %s\n",
+			       sym->st_shndx, name);
+			return -ENOEXEC;
+		} else
+			sec_base = pi->sechdrs[sym->st_shndx].sh_addr;
+
+		val = sym->st_value;
+		val += sec_base;
+		val += relas[i].r_addend;
+
+		addr = section->sh_addr + relas[i].r_offset;
+
+		r_type = ELF64_R_TYPE(relas[i].r_info);
+
+		switch (r_type) {
+		case R_RISCV_BRANCH:
+			*(u32 *)loc = CLEAN_IMM(BTYPE, *(u32 *)loc) |
+				 ENCODE_BTYPE_IMM(val - addr);
+			break;
+		case R_RISCV_JAL:
+			*(u32 *)loc = CLEAN_IMM(JTYPE, *(u32 *)loc) |
+				 ENCODE_JTYPE_IMM(val - addr);
+			break;
+		/*
+		 * With no R_RISCV_PCREL_LO12_S, R_RISCV_PCREL_LO12_I
+		 * sym is expected to be next to R_RISCV_PCREL_HI20
+		 * in purgatory relsec. Handle it like R_RISCV_CALL
+		 * sym, instead of searching the whole relsec.
+		 */
+		case R_RISCV_PCREL_HI20:
+		case R_RISCV_CALL_PLT:
+		case R_RISCV_CALL:
+			*(u64 *)loc = CLEAN_IMM(UITYPE, *(u64 *)loc) |
+				 ENCODE_UJTYPE_IMM(val - addr);
+			break;
+		case R_RISCV_RVC_BRANCH:
+			*(u32 *)loc = CLEAN_IMM(CBTYPE, *(u32 *)loc) |
+				 ENCODE_CBTYPE_IMM(val - addr);
+			break;
+		case R_RISCV_RVC_JUMP:
+			*(u32 *)loc = CLEAN_IMM(CJTYPE, *(u32 *)loc) |
+				 ENCODE_CJTYPE_IMM(val - addr);
+			break;
+		case R_RISCV_ADD32:
+			*(u32 *)loc += val;
+			break;
+		case R_RISCV_SUB32:
+			*(u32 *)loc -= val;
+			break;
+		/* It has been applied by R_RISCV_PCREL_HI20 sym */
+		case R_RISCV_PCREL_LO12_I:
+		case R_RISCV_ALIGN:
+		case R_RISCV_RELAX:
+			break;
+		default:
+			pr_err("Unknown rela relocation: %d\n", r_type);
+			return -ENOEXEC;
+		}
+	}
+	return 0;
+}
+
+const struct kexec_file_ops elf_kexec_ops = {
+	.probe = kexec_elf_probe,
+	.load  = elf_kexec_load,
+};
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
new file mode 100644
index 000000000..3221a9e5f
--- /dev/null
+++ b/arch/riscv/kernel/entry.S
@@ -0,0 +1,607 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ * Copyright (C) 2017 SiFive
+ */
+
+#include <linux/init.h>
+#include <linux/linkage.h>
+
+#include <asm/asm.h>
+#include <asm/csr.h>
+#include <asm/unistd.h>
+#include <asm/thread_info.h>
+#include <asm/asm-offsets.h>
+#include <asm/errata_list.h>
+
+#if !IS_ENABLED(CONFIG_PREEMPTION)
+.set resume_kernel, restore_all
+#endif
+
+ENTRY(handle_exception)
+	/*
+	 * If coming from userspace, preserve the user thread pointer and load
+	 * the kernel thread pointer.  If we came from the kernel, the scratch
+	 * register will contain 0, and we should continue on the current TP.
+	 */
+	csrrw tp, CSR_SCRATCH, tp
+	bnez tp, _save_context
+
+_restore_kernel_tpsp:
+	csrr tp, CSR_SCRATCH
+	REG_S sp, TASK_TI_KERNEL_SP(tp)
+
+#ifdef CONFIG_VMAP_STACK
+	addi sp, sp, -(PT_SIZE_ON_STACK)
+	srli sp, sp, THREAD_SHIFT
+	andi sp, sp, 0x1
+	bnez sp, handle_kernel_stack_overflow
+	REG_L sp, TASK_TI_KERNEL_SP(tp)
+#endif
+
+_save_context:
+	REG_S sp, TASK_TI_USER_SP(tp)
+	REG_L sp, TASK_TI_KERNEL_SP(tp)
+	addi sp, sp, -(PT_SIZE_ON_STACK)
+	REG_S x1,  PT_RA(sp)
+	REG_S x3,  PT_GP(sp)
+	REG_S x5,  PT_T0(sp)
+	REG_S x6,  PT_T1(sp)
+	REG_S x7,  PT_T2(sp)
+	REG_S x8,  PT_S0(sp)
+	REG_S x9,  PT_S1(sp)
+	REG_S x10, PT_A0(sp)
+	REG_S x11, PT_A1(sp)
+	REG_S x12, PT_A2(sp)
+	REG_S x13, PT_A3(sp)
+	REG_S x14, PT_A4(sp)
+	REG_S x15, PT_A5(sp)
+	REG_S x16, PT_A6(sp)
+	REG_S x17, PT_A7(sp)
+	REG_S x18, PT_S2(sp)
+	REG_S x19, PT_S3(sp)
+	REG_S x20, PT_S4(sp)
+	REG_S x21, PT_S5(sp)
+	REG_S x22, PT_S6(sp)
+	REG_S x23, PT_S7(sp)
+	REG_S x24, PT_S8(sp)
+	REG_S x25, PT_S9(sp)
+	REG_S x26, PT_S10(sp)
+	REG_S x27, PT_S11(sp)
+	REG_S x28, PT_T3(sp)
+	REG_S x29, PT_T4(sp)
+	REG_S x30, PT_T5(sp)
+	REG_S x31, PT_T6(sp)
+
+	/*
+	 * Disable user-mode memory access as it should only be set in the
+	 * actual user copy routines.
+	 *
+	 * Disable the FPU to detect illegal usage of floating point in kernel
+	 * space.
+	 */
+	li t0, SR_SUM | SR_FS
+
+	REG_L s0, TASK_TI_USER_SP(tp)
+	csrrc s1, CSR_STATUS, t0
+	csrr s2, CSR_EPC
+	csrr s3, CSR_TVAL
+	csrr s4, CSR_CAUSE
+	csrr s5, CSR_SCRATCH
+	REG_S s0, PT_SP(sp)
+	REG_S s1, PT_STATUS(sp)
+	REG_S s2, PT_EPC(sp)
+	REG_S s3, PT_BADADDR(sp)
+	REG_S s4, PT_CAUSE(sp)
+	REG_S s5, PT_TP(sp)
+
+	/*
+	 * Set the scratch register to 0, so that if a recursive exception
+	 * occurs, the exception vector knows it came from the kernel
+	 */
+	csrw CSR_SCRATCH, x0
+
+	/* Load the global pointer */
+.option push
+.option norelax
+	la gp, __global_pointer$
+.option pop
+
+#ifdef CONFIG_TRACE_IRQFLAGS
+	call __trace_hardirqs_off
+#endif
+
+#ifdef CONFIG_CONTEXT_TRACKING_USER
+	/* If previous state is in user mode, call user_exit_callable(). */
+	li   a0, SR_PP
+	and a0, s1, a0
+	bnez a0, skip_context_tracking
+	call user_exit_callable
+skip_context_tracking:
+#endif
+
+	/*
+	 * MSB of cause differentiates between
+	 * interrupts and exceptions
+	 */
+	bge s4, zero, 1f
+
+	la ra, ret_from_exception
+
+	/* Handle interrupts */
+	move a0, sp /* pt_regs */
+	la a1, generic_handle_arch_irq
+	jr a1
+1:
+	/*
+	 * Exceptions run with interrupts enabled or disabled depending on the
+	 * state of SR_PIE in m/sstatus.
+	 */
+	andi t0, s1, SR_PIE
+	beqz t0, 1f
+	/* kprobes, entered via ebreak, must have interrupts disabled. */
+	li t0, EXC_BREAKPOINT
+	beq s4, t0, 1f
+#ifdef CONFIG_TRACE_IRQFLAGS
+	call __trace_hardirqs_on
+#endif
+	csrs CSR_STATUS, SR_IE
+
+1:
+	la ra, ret_from_exception
+	/* Handle syscalls */
+	li t0, EXC_SYSCALL
+	beq s4, t0, handle_syscall
+
+	/* Handle other exceptions */
+	slli t0, s4, RISCV_LGPTR
+	la t1, excp_vect_table
+	la t2, excp_vect_table_end
+	move a0, sp /* pt_regs */
+	add t0, t1, t0
+	/* Check if exception code lies within bounds */
+	bgeu t0, t2, 1f
+	REG_L t0, 0(t0)
+	jr t0
+1:
+	tail do_trap_unknown
+
+handle_syscall:
+#ifdef CONFIG_RISCV_M_MODE
+	/*
+	 * When running is M-Mode (no MMU config), MPIE does not get set.
+	 * As a result, we need to force enable interrupts here because
+	 * handle_exception did not do set SR_IE as it always sees SR_PIE
+	 * being cleared.
+	 */
+	csrs CSR_STATUS, SR_IE
+#endif
+#if defined(CONFIG_TRACE_IRQFLAGS) || defined(CONFIG_CONTEXT_TRACKING_USER)
+	/* Recover a0 - a7 for system calls */
+	REG_L a0, PT_A0(sp)
+	REG_L a1, PT_A1(sp)
+	REG_L a2, PT_A2(sp)
+	REG_L a3, PT_A3(sp)
+	REG_L a4, PT_A4(sp)
+	REG_L a5, PT_A5(sp)
+	REG_L a6, PT_A6(sp)
+	REG_L a7, PT_A7(sp)
+#endif
+	 /* save the initial A0 value (needed in signal handlers) */
+	REG_S a0, PT_ORIG_A0(sp)
+	/*
+	 * Advance SEPC to avoid executing the original
+	 * scall instruction on sret
+	 */
+	addi s2, s2, 0x4
+	REG_S s2, PT_EPC(sp)
+	/* Trace syscalls, but only if requested by the user. */
+	REG_L t0, TASK_TI_FLAGS(tp)
+	andi t0, t0, _TIF_SYSCALL_WORK
+	bnez t0, handle_syscall_trace_enter
+check_syscall_nr:
+	/* Check to make sure we don't jump to a bogus syscall number. */
+	li t0, __NR_syscalls
+	la s0, sys_ni_syscall
+	/*
+	 * Syscall number held in a7.
+	 * If syscall number is above allowed value, redirect to ni_syscall.
+	 */
+	bgeu a7, t0, 3f
+#ifdef CONFIG_COMPAT
+	REG_L s0, PT_STATUS(sp)
+	srli s0, s0, SR_UXL_SHIFT
+	andi s0, s0, (SR_UXL >> SR_UXL_SHIFT)
+	li t0, (SR_UXL_32 >> SR_UXL_SHIFT)
+	sub t0, s0, t0
+	bnez t0, 1f
+
+	/* Call compat_syscall */
+	la s0, compat_sys_call_table
+	j 2f
+1:
+#endif
+	/* Call syscall */
+	la s0, sys_call_table
+2:
+	slli t0, a7, RISCV_LGPTR
+	add s0, s0, t0
+	REG_L s0, 0(s0)
+3:
+	jalr s0
+
+ret_from_syscall:
+	/* Set user a0 to kernel a0 */
+	REG_S a0, PT_A0(sp)
+	/*
+	 * We didn't execute the actual syscall.
+	 * Seccomp already set return value for the current task pt_regs.
+	 * (If it was configured with SECCOMP_RET_ERRNO/TRACE)
+	 */
+ret_from_syscall_rejected:
+#ifdef CONFIG_DEBUG_RSEQ
+	move a0, sp
+	call rseq_syscall
+#endif
+	/* Trace syscalls, but only if requested by the user. */
+	REG_L t0, TASK_TI_FLAGS(tp)
+	andi t0, t0, _TIF_SYSCALL_WORK
+	bnez t0, handle_syscall_trace_exit
+
+ret_from_exception:
+	REG_L s0, PT_STATUS(sp)
+	csrc CSR_STATUS, SR_IE
+#ifdef CONFIG_TRACE_IRQFLAGS
+	call __trace_hardirqs_off
+#endif
+#ifdef CONFIG_RISCV_M_MODE
+	/* the MPP value is too large to be used as an immediate arg for addi */
+	li t0, SR_MPP
+	and s0, s0, t0
+#else
+	andi s0, s0, SR_SPP
+#endif
+	bnez s0, resume_kernel
+
+	/* Interrupts must be disabled here so flags are checked atomically */
+	REG_L s0, TASK_TI_FLAGS(tp) /* current_thread_info->flags */
+	andi s1, s0, _TIF_WORK_MASK
+	bnez s1, resume_userspace_slow
+resume_userspace:
+#ifdef CONFIG_CONTEXT_TRACKING_USER
+	call user_enter_callable
+#endif
+
+	/* Save unwound kernel stack pointer in thread_info */
+	addi s0, sp, PT_SIZE_ON_STACK
+	REG_S s0, TASK_TI_KERNEL_SP(tp)
+
+	/*
+	 * Save TP into the scratch register , so we can find the kernel data
+	 * structures again.
+	 */
+	csrw CSR_SCRATCH, tp
+
+restore_all:
+#ifdef CONFIG_TRACE_IRQFLAGS
+	REG_L s1, PT_STATUS(sp)
+	andi t0, s1, SR_PIE
+	beqz t0, 1f
+	call __trace_hardirqs_on
+	j 2f
+1:
+	call __trace_hardirqs_off
+2:
+#endif
+	REG_L a0, PT_STATUS(sp)
+	/*
+	 * The current load reservation is effectively part of the processor's
+	 * state, in the sense that load reservations cannot be shared between
+	 * different hart contexts.  We can't actually save and restore a load
+	 * reservation, so instead here we clear any existing reservation --
+	 * it's always legal for implementations to clear load reservations at
+	 * any point (as long as the forward progress guarantee is kept, but
+	 * we'll ignore that here).
+	 *
+	 * Dangling load reservations can be the result of taking a trap in the
+	 * middle of an LR/SC sequence, but can also be the result of a taken
+	 * forward branch around an SC -- which is how we implement CAS.  As a
+	 * result we need to clear reservations between the last CAS and the
+	 * jump back to the new context.  While it is unlikely the store
+	 * completes, implementations are allowed to expand reservations to be
+	 * arbitrarily large.
+	 */
+	REG_L  a2, PT_EPC(sp)
+	REG_SC x0, a2, PT_EPC(sp)
+
+	csrw CSR_STATUS, a0
+	csrw CSR_EPC, a2
+
+	REG_L x1,  PT_RA(sp)
+	REG_L x3,  PT_GP(sp)
+	REG_L x4,  PT_TP(sp)
+	REG_L x5,  PT_T0(sp)
+	REG_L x6,  PT_T1(sp)
+	REG_L x7,  PT_T2(sp)
+	REG_L x8,  PT_S0(sp)
+	REG_L x9,  PT_S1(sp)
+	REG_L x10, PT_A0(sp)
+	REG_L x11, PT_A1(sp)
+	REG_L x12, PT_A2(sp)
+	REG_L x13, PT_A3(sp)
+	REG_L x14, PT_A4(sp)
+	REG_L x15, PT_A5(sp)
+	REG_L x16, PT_A6(sp)
+	REG_L x17, PT_A7(sp)
+	REG_L x18, PT_S2(sp)
+	REG_L x19, PT_S3(sp)
+	REG_L x20, PT_S4(sp)
+	REG_L x21, PT_S5(sp)
+	REG_L x22, PT_S6(sp)
+	REG_L x23, PT_S7(sp)
+	REG_L x24, PT_S8(sp)
+	REG_L x25, PT_S9(sp)
+	REG_L x26, PT_S10(sp)
+	REG_L x27, PT_S11(sp)
+	REG_L x28, PT_T3(sp)
+	REG_L x29, PT_T4(sp)
+	REG_L x30, PT_T5(sp)
+	REG_L x31, PT_T6(sp)
+
+	REG_L x2,  PT_SP(sp)
+
+#ifdef CONFIG_RISCV_M_MODE
+	mret
+#else
+	sret
+#endif
+
+#if IS_ENABLED(CONFIG_PREEMPTION)
+resume_kernel:
+	REG_L s0, TASK_TI_PREEMPT_COUNT(tp)
+	bnez s0, restore_all
+	REG_L s0, TASK_TI_FLAGS(tp)
+	andi s0, s0, _TIF_NEED_RESCHED
+	beqz s0, restore_all
+	call preempt_schedule_irq
+	j restore_all
+#endif
+
+resume_userspace_slow:
+	/* Enter slow path for supplementary processing */
+	move a0, sp /* pt_regs */
+	move a1, s0 /* current_thread_info->flags */
+	call do_work_pending
+	j resume_userspace
+
+/* Slow paths for ptrace. */
+handle_syscall_trace_enter:
+	move a0, sp
+	call do_syscall_trace_enter
+	move t0, a0
+	REG_L a0, PT_A0(sp)
+	REG_L a1, PT_A1(sp)
+	REG_L a2, PT_A2(sp)
+	REG_L a3, PT_A3(sp)
+	REG_L a4, PT_A4(sp)
+	REG_L a5, PT_A5(sp)
+	REG_L a6, PT_A6(sp)
+	REG_L a7, PT_A7(sp)
+	bnez t0, ret_from_syscall_rejected
+	j check_syscall_nr
+handle_syscall_trace_exit:
+	move a0, sp
+	call do_syscall_trace_exit
+	j ret_from_exception
+
+#ifdef CONFIG_VMAP_STACK
+handle_kernel_stack_overflow:
+	/*
+	 * Takes the psuedo-spinlock for the shadow stack, in case multiple
+	 * harts are concurrently overflowing their kernel stacks.  We could
+	 * store any value here, but since we're overflowing the kernel stack
+	 * already we only have SP to use as a scratch register.  So we just
+	 * swap in the address of the spinlock, as that's definately non-zero.
+	 *
+	 * Pairs with a store_release in handle_bad_stack().
+	 */
+1:	la sp, spin_shadow_stack
+	REG_AMOSWAP_AQ sp, sp, (sp)
+	bnez sp, 1b
+
+	la sp, shadow_stack
+	addi sp, sp, SHADOW_OVERFLOW_STACK_SIZE
+
+	//save caller register to shadow stack
+	addi sp, sp, -(PT_SIZE_ON_STACK)
+	REG_S x1,  PT_RA(sp)
+	REG_S x5,  PT_T0(sp)
+	REG_S x6,  PT_T1(sp)
+	REG_S x7,  PT_T2(sp)
+	REG_S x10, PT_A0(sp)
+	REG_S x11, PT_A1(sp)
+	REG_S x12, PT_A2(sp)
+	REG_S x13, PT_A3(sp)
+	REG_S x14, PT_A4(sp)
+	REG_S x15, PT_A5(sp)
+	REG_S x16, PT_A6(sp)
+	REG_S x17, PT_A7(sp)
+	REG_S x28, PT_T3(sp)
+	REG_S x29, PT_T4(sp)
+	REG_S x30, PT_T5(sp)
+	REG_S x31, PT_T6(sp)
+
+	la ra, restore_caller_reg
+	tail get_overflow_stack
+
+restore_caller_reg:
+	//save per-cpu overflow stack
+	REG_S a0, -8(sp)
+	//restore caller register from shadow_stack
+	REG_L x1,  PT_RA(sp)
+	REG_L x5,  PT_T0(sp)
+	REG_L x6,  PT_T1(sp)
+	REG_L x7,  PT_T2(sp)
+	REG_L x10, PT_A0(sp)
+	REG_L x11, PT_A1(sp)
+	REG_L x12, PT_A2(sp)
+	REG_L x13, PT_A3(sp)
+	REG_L x14, PT_A4(sp)
+	REG_L x15, PT_A5(sp)
+	REG_L x16, PT_A6(sp)
+	REG_L x17, PT_A7(sp)
+	REG_L x28, PT_T3(sp)
+	REG_L x29, PT_T4(sp)
+	REG_L x30, PT_T5(sp)
+	REG_L x31, PT_T6(sp)
+
+	//load per-cpu overflow stack
+	REG_L sp, -8(sp)
+	addi sp, sp, -(PT_SIZE_ON_STACK)
+
+	//save context to overflow stack
+	REG_S x1,  PT_RA(sp)
+	REG_S x3,  PT_GP(sp)
+	REG_S x5,  PT_T0(sp)
+	REG_S x6,  PT_T1(sp)
+	REG_S x7,  PT_T2(sp)
+	REG_S x8,  PT_S0(sp)
+	REG_S x9,  PT_S1(sp)
+	REG_S x10, PT_A0(sp)
+	REG_S x11, PT_A1(sp)
+	REG_S x12, PT_A2(sp)
+	REG_S x13, PT_A3(sp)
+	REG_S x14, PT_A4(sp)
+	REG_S x15, PT_A5(sp)
+	REG_S x16, PT_A6(sp)
+	REG_S x17, PT_A7(sp)
+	REG_S x18, PT_S2(sp)
+	REG_S x19, PT_S3(sp)
+	REG_S x20, PT_S4(sp)
+	REG_S x21, PT_S5(sp)
+	REG_S x22, PT_S6(sp)
+	REG_S x23, PT_S7(sp)
+	REG_S x24, PT_S8(sp)
+	REG_S x25, PT_S9(sp)
+	REG_S x26, PT_S10(sp)
+	REG_S x27, PT_S11(sp)
+	REG_S x28, PT_T3(sp)
+	REG_S x29, PT_T4(sp)
+	REG_S x30, PT_T5(sp)
+	REG_S x31, PT_T6(sp)
+
+	REG_L s0, TASK_TI_KERNEL_SP(tp)
+	csrr s1, CSR_STATUS
+	csrr s2, CSR_EPC
+	csrr s3, CSR_TVAL
+	csrr s4, CSR_CAUSE
+	csrr s5, CSR_SCRATCH
+	REG_S s0, PT_SP(sp)
+	REG_S s1, PT_STATUS(sp)
+	REG_S s2, PT_EPC(sp)
+	REG_S s3, PT_BADADDR(sp)
+	REG_S s4, PT_CAUSE(sp)
+	REG_S s5, PT_TP(sp)
+	move a0, sp
+	tail handle_bad_stack
+#endif
+
+END(handle_exception)
+
+ENTRY(ret_from_fork)
+	la ra, ret_from_exception
+	tail schedule_tail
+ENDPROC(ret_from_fork)
+
+ENTRY(ret_from_kernel_thread)
+	call schedule_tail
+	/* Call fn(arg) */
+	la ra, ret_from_exception
+	move a0, s1
+	jr s0
+ENDPROC(ret_from_kernel_thread)
+
+
+/*
+ * Integer register context switch
+ * The callee-saved registers must be saved and restored.
+ *
+ *   a0: previous task_struct (must be preserved across the switch)
+ *   a1: next task_struct
+ *
+ * The value of a0 and a1 must be preserved by this function, as that's how
+ * arguments are passed to schedule_tail.
+ */
+ENTRY(__switch_to)
+	/* Save context into prev->thread */
+	li    a4,  TASK_THREAD_RA
+	add   a3, a0, a4
+	add   a4, a1, a4
+	REG_S ra,  TASK_THREAD_RA_RA(a3)
+	REG_S sp,  TASK_THREAD_SP_RA(a3)
+	REG_S s0,  TASK_THREAD_S0_RA(a3)
+	REG_S s1,  TASK_THREAD_S1_RA(a3)
+	REG_S s2,  TASK_THREAD_S2_RA(a3)
+	REG_S s3,  TASK_THREAD_S3_RA(a3)
+	REG_S s4,  TASK_THREAD_S4_RA(a3)
+	REG_S s5,  TASK_THREAD_S5_RA(a3)
+	REG_S s6,  TASK_THREAD_S6_RA(a3)
+	REG_S s7,  TASK_THREAD_S7_RA(a3)
+	REG_S s8,  TASK_THREAD_S8_RA(a3)
+	REG_S s9,  TASK_THREAD_S9_RA(a3)
+	REG_S s10, TASK_THREAD_S10_RA(a3)
+	REG_S s11, TASK_THREAD_S11_RA(a3)
+	/* Restore context from next->thread */
+	REG_L ra,  TASK_THREAD_RA_RA(a4)
+	REG_L sp,  TASK_THREAD_SP_RA(a4)
+	REG_L s0,  TASK_THREAD_S0_RA(a4)
+	REG_L s1,  TASK_THREAD_S1_RA(a4)
+	REG_L s2,  TASK_THREAD_S2_RA(a4)
+	REG_L s3,  TASK_THREAD_S3_RA(a4)
+	REG_L s4,  TASK_THREAD_S4_RA(a4)
+	REG_L s5,  TASK_THREAD_S5_RA(a4)
+	REG_L s6,  TASK_THREAD_S6_RA(a4)
+	REG_L s7,  TASK_THREAD_S7_RA(a4)
+	REG_L s8,  TASK_THREAD_S8_RA(a4)
+	REG_L s9,  TASK_THREAD_S9_RA(a4)
+	REG_L s10, TASK_THREAD_S10_RA(a4)
+	REG_L s11, TASK_THREAD_S11_RA(a4)
+	/* The offset of thread_info in task_struct is zero. */
+	move tp, a1
+	ret
+ENDPROC(__switch_to)
+
+#ifndef CONFIG_MMU
+#define do_page_fault do_trap_unknown
+#endif
+
+	.section ".rodata"
+	.align LGREG
+	/* Exception vector table */
+ENTRY(excp_vect_table)
+	RISCV_PTR do_trap_insn_misaligned
+	ALT_INSN_FAULT(RISCV_PTR do_trap_insn_fault)
+	RISCV_PTR do_trap_insn_illegal
+	RISCV_PTR do_trap_break
+	RISCV_PTR do_trap_load_misaligned
+	RISCV_PTR do_trap_load_fault
+	RISCV_PTR do_trap_store_misaligned
+	RISCV_PTR do_trap_store_fault
+	RISCV_PTR do_trap_ecall_u /* system call, gets intercepted */
+	RISCV_PTR do_trap_ecall_s
+	RISCV_PTR do_trap_unknown
+	RISCV_PTR do_trap_ecall_m
+	/* instruciton page fault */
+	ALT_PAGE_FAULT(RISCV_PTR do_page_fault)
+	RISCV_PTR do_page_fault   /* load page fault */
+	RISCV_PTR do_trap_unknown
+	RISCV_PTR do_page_fault   /* store page fault */
+excp_vect_table_end:
+END(excp_vect_table)
+
+#ifndef CONFIG_MMU
+ENTRY(__user_rt_sigreturn)
+	li a7, __NR_rt_sigreturn
+	scall
+END(__user_rt_sigreturn)
+#endif
diff --git a/arch/riscv/kernel/fpu.S b/arch/riscv/kernel/fpu.S
new file mode 100644
index 000000000..dd2205473
--- /dev/null
+++ b/arch/riscv/kernel/fpu.S
@@ -0,0 +1,106 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ * Copyright (C) 2017 SiFive
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful,
+ *   but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *   GNU General Public License for more details.
+ */
+
+#include <linux/linkage.h>
+
+#include <asm/asm.h>
+#include <asm/csr.h>
+#include <asm/asm-offsets.h>
+
+ENTRY(__fstate_save)
+	li  a2,  TASK_THREAD_F0
+	add a0, a0, a2
+	li t1, SR_FS
+	csrs CSR_STATUS, t1
+	frcsr t0
+	fsd f0,  TASK_THREAD_F0_F0(a0)
+	fsd f1,  TASK_THREAD_F1_F0(a0)
+	fsd f2,  TASK_THREAD_F2_F0(a0)
+	fsd f3,  TASK_THREAD_F3_F0(a0)
+	fsd f4,  TASK_THREAD_F4_F0(a0)
+	fsd f5,  TASK_THREAD_F5_F0(a0)
+	fsd f6,  TASK_THREAD_F6_F0(a0)
+	fsd f7,  TASK_THREAD_F7_F0(a0)
+	fsd f8,  TASK_THREAD_F8_F0(a0)
+	fsd f9,  TASK_THREAD_F9_F0(a0)
+	fsd f10, TASK_THREAD_F10_F0(a0)
+	fsd f11, TASK_THREAD_F11_F0(a0)
+	fsd f12, TASK_THREAD_F12_F0(a0)
+	fsd f13, TASK_THREAD_F13_F0(a0)
+	fsd f14, TASK_THREAD_F14_F0(a0)
+	fsd f15, TASK_THREAD_F15_F0(a0)
+	fsd f16, TASK_THREAD_F16_F0(a0)
+	fsd f17, TASK_THREAD_F17_F0(a0)
+	fsd f18, TASK_THREAD_F18_F0(a0)
+	fsd f19, TASK_THREAD_F19_F0(a0)
+	fsd f20, TASK_THREAD_F20_F0(a0)
+	fsd f21, TASK_THREAD_F21_F0(a0)
+	fsd f22, TASK_THREAD_F22_F0(a0)
+	fsd f23, TASK_THREAD_F23_F0(a0)
+	fsd f24, TASK_THREAD_F24_F0(a0)
+	fsd f25, TASK_THREAD_F25_F0(a0)
+	fsd f26, TASK_THREAD_F26_F0(a0)
+	fsd f27, TASK_THREAD_F27_F0(a0)
+	fsd f28, TASK_THREAD_F28_F0(a0)
+	fsd f29, TASK_THREAD_F29_F0(a0)
+	fsd f30, TASK_THREAD_F30_F0(a0)
+	fsd f31, TASK_THREAD_F31_F0(a0)
+	sw t0, TASK_THREAD_FCSR_F0(a0)
+	csrc CSR_STATUS, t1
+	ret
+ENDPROC(__fstate_save)
+
+ENTRY(__fstate_restore)
+	li  a2,  TASK_THREAD_F0
+	add a0, a0, a2
+	li t1, SR_FS
+	lw t0, TASK_THREAD_FCSR_F0(a0)
+	csrs CSR_STATUS, t1
+	fld f0,  TASK_THREAD_F0_F0(a0)
+	fld f1,  TASK_THREAD_F1_F0(a0)
+	fld f2,  TASK_THREAD_F2_F0(a0)
+	fld f3,  TASK_THREAD_F3_F0(a0)
+	fld f4,  TASK_THREAD_F4_F0(a0)
+	fld f5,  TASK_THREAD_F5_F0(a0)
+	fld f6,  TASK_THREAD_F6_F0(a0)
+	fld f7,  TASK_THREAD_F7_F0(a0)
+	fld f8,  TASK_THREAD_F8_F0(a0)
+	fld f9,  TASK_THREAD_F9_F0(a0)
+	fld f10, TASK_THREAD_F10_F0(a0)
+	fld f11, TASK_THREAD_F11_F0(a0)
+	fld f12, TASK_THREAD_F12_F0(a0)
+	fld f13, TASK_THREAD_F13_F0(a0)
+	fld f14, TASK_THREAD_F14_F0(a0)
+	fld f15, TASK_THREAD_F15_F0(a0)
+	fld f16, TASK_THREAD_F16_F0(a0)
+	fld f17, TASK_THREAD_F17_F0(a0)
+	fld f18, TASK_THREAD_F18_F0(a0)
+	fld f19, TASK_THREAD_F19_F0(a0)
+	fld f20, TASK_THREAD_F20_F0(a0)
+	fld f21, TASK_THREAD_F21_F0(a0)
+	fld f22, TASK_THREAD_F22_F0(a0)
+	fld f23, TASK_THREAD_F23_F0(a0)
+	fld f24, TASK_THREAD_F24_F0(a0)
+	fld f25, TASK_THREAD_F25_F0(a0)
+	fld f26, TASK_THREAD_F26_F0(a0)
+	fld f27, TASK_THREAD_F27_F0(a0)
+	fld f28, TASK_THREAD_F28_F0(a0)
+	fld f29, TASK_THREAD_F29_F0(a0)
+	fld f30, TASK_THREAD_F30_F0(a0)
+	fld f31, TASK_THREAD_F31_F0(a0)
+	fscsr t0
+	csrc CSR_STATUS, t1
+	ret
+ENDPROC(__fstate_restore)
diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c
new file mode 100644
index 000000000..03a6434a8
--- /dev/null
+++ b/arch/riscv/kernel/ftrace.c
@@ -0,0 +1,209 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2013 Linaro Limited
+ * Author: AKASHI Takahiro <takahiro.akashi@linaro.org>
+ * Copyright (C) 2017 Andes Technology Corporation
+ */
+
+#include <linux/ftrace.h>
+#include <linux/uaccess.h>
+#include <linux/memory.h>
+#include <asm/cacheflush.h>
+#include <asm/patch.h>
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+void ftrace_arch_code_modify_prepare(void) __acquires(&text_mutex)
+{
+	mutex_lock(&text_mutex);
+
+	/*
+	 * The code sequences we use for ftrace can't be patched while the
+	 * kernel is running, so we need to use stop_machine() to modify them
+	 * for now.  This doesn't play nice with text_mutex, we use this flag
+	 * to elide the check.
+	 */
+	riscv_patch_in_stop_machine = true;
+}
+
+void ftrace_arch_code_modify_post_process(void) __releases(&text_mutex)
+{
+	riscv_patch_in_stop_machine = false;
+	mutex_unlock(&text_mutex);
+}
+
+static int ftrace_check_current_call(unsigned long hook_pos,
+				     unsigned int *expected)
+{
+	unsigned int replaced[2];
+	unsigned int nops[2] = {NOP4, NOP4};
+
+	/* we expect nops at the hook position */
+	if (!expected)
+		expected = nops;
+
+	/*
+	 * Read the text we want to modify;
+	 * return must be -EFAULT on read error
+	 */
+	if (copy_from_kernel_nofault(replaced, (void *)hook_pos,
+			MCOUNT_INSN_SIZE))
+		return -EFAULT;
+
+	/*
+	 * Make sure it is what we expect it to be;
+	 * return must be -EINVAL on failed comparison
+	 */
+	if (memcmp(expected, replaced, sizeof(replaced))) {
+		pr_err("%p: expected (%08x %08x) but got (%08x %08x)\n",
+		       (void *)hook_pos, expected[0], expected[1], replaced[0],
+		       replaced[1]);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int __ftrace_modify_call(unsigned long hook_pos, unsigned long target,
+				bool enable, bool ra)
+{
+	unsigned int call[2];
+	unsigned int nops[2] = {NOP4, NOP4};
+
+	if (ra)
+		make_call_ra(hook_pos, target, call);
+	else
+		make_call_t0(hook_pos, target, call);
+
+	/* Replace the auipc-jalr pair at once. Return -EPERM on write error. */
+	if (patch_text_nosync
+	    ((void *)hook_pos, enable ? call : nops, MCOUNT_INSN_SIZE))
+		return -EPERM;
+
+	return 0;
+}
+
+int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned int call[2];
+
+	make_call_t0(rec->ip, addr, call);
+
+	if (patch_text_nosync((void *)rec->ip, call, MCOUNT_INSN_SIZE))
+		return -EPERM;
+
+	return 0;
+}
+
+int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
+		    unsigned long addr)
+{
+	unsigned int nops[2] = {NOP4, NOP4};
+
+	if (patch_text_nosync((void *)rec->ip, nops, MCOUNT_INSN_SIZE))
+		return -EPERM;
+
+	return 0;
+}
+
+/*
+ * This is called early on, and isn't wrapped by
+ * ftrace_arch_code_modify_{prepare,post_process}() and therefor doesn't hold
+ * text_mutex, which triggers a lockdep failure.  SMP isn't running so we could
+ * just directly poke the text, but it's simpler to just take the lock
+ * ourselves.
+ */
+int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec)
+{
+	int out;
+
+	mutex_lock(&text_mutex);
+	out = ftrace_make_nop(mod, rec, MCOUNT_ADDR);
+	mutex_unlock(&text_mutex);
+
+	return out;
+}
+
+int ftrace_update_ftrace_func(ftrace_func_t func)
+{
+	int ret = __ftrace_modify_call((unsigned long)&ftrace_call,
+				       (unsigned long)func, true, true);
+	if (!ret) {
+		ret = __ftrace_modify_call((unsigned long)&ftrace_regs_call,
+					   (unsigned long)func, true, true);
+	}
+
+	return ret;
+}
+#endif
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
+		       unsigned long addr)
+{
+	unsigned int call[2];
+	unsigned long caller = rec->ip;
+	int ret;
+
+	make_call_t0(caller, old_addr, call);
+	ret = ftrace_check_current_call(caller, call);
+
+	if (ret)
+		return ret;
+
+	return __ftrace_modify_call(caller, addr, true, false);
+}
+#endif
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+/*
+ * Most of this function is copied from arm64.
+ */
+void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
+			   unsigned long frame_pointer)
+{
+	unsigned long return_hooker = (unsigned long)&return_to_handler;
+	unsigned long old;
+
+	if (unlikely(atomic_read(&current->tracing_graph_pause)))
+		return;
+
+	/*
+	 * We don't suffer access faults, so no extra fault-recovery assembly
+	 * is needed here.
+	 */
+	old = *parent;
+
+	if (!function_graph_enter(old, self_addr, frame_pointer, parent))
+		*parent = return_hooker;
+}
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+extern void ftrace_graph_call(void);
+extern void ftrace_graph_regs_call(void);
+int ftrace_enable_ftrace_graph_caller(void)
+{
+	int ret;
+
+	ret = __ftrace_modify_call((unsigned long)&ftrace_graph_call,
+				    (unsigned long)&prepare_ftrace_return, true, true);
+	if (ret)
+		return ret;
+
+	return __ftrace_modify_call((unsigned long)&ftrace_graph_regs_call,
+				    (unsigned long)&prepare_ftrace_return, true, true);
+}
+
+int ftrace_disable_ftrace_graph_caller(void)
+{
+	int ret;
+
+	ret = __ftrace_modify_call((unsigned long)&ftrace_graph_call,
+				    (unsigned long)&prepare_ftrace_return, false, true);
+	if (ret)
+		return ret;
+
+	return __ftrace_modify_call((unsigned long)&ftrace_graph_regs_call,
+				    (unsigned long)&prepare_ftrace_return, false, true);
+}
+#endif /* CONFIG_DYNAMIC_FTRACE */
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
new file mode 100644
index 000000000..4bf6c449d
--- /dev/null
+++ b/arch/riscv/kernel/head.S
@@ -0,0 +1,437 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ */
+
+#include <asm/asm-offsets.h>
+#include <asm/asm.h>
+#include <linux/init.h>
+#include <linux/linkage.h>
+#include <asm/thread_info.h>
+#include <asm/page.h>
+#include <asm/pgtable.h>
+#include <asm/csr.h>
+#include <asm/cpu_ops_sbi.h>
+#include <asm/hwcap.h>
+#include <asm/image.h>
+#include <asm/xip_fixup.h>
+#include "efi-header.S"
+
+__HEAD
+ENTRY(_start)
+	/*
+	 * Image header expected by Linux boot-loaders. The image header data
+	 * structure is described in asm/image.h.
+	 * Do not modify it without modifying the structure and all bootloaders
+	 * that expects this header format!!
+	 */
+#ifdef CONFIG_EFI
+	/*
+	 * This instruction decodes to "MZ" ASCII required by UEFI.
+	 */
+	c.li s4,-13
+	j _start_kernel
+#else
+	/* jump to start kernel */
+	j _start_kernel
+	/* reserved */
+	.word 0
+#endif
+	.balign 8
+#ifdef CONFIG_RISCV_M_MODE
+	/* Image load offset (0MB) from start of RAM for M-mode */
+	.dword 0
+#else
+#if __riscv_xlen == 64
+	/* Image load offset(2MB) from start of RAM */
+	.dword 0x200000
+#else
+	/* Image load offset(4MB) from start of RAM */
+	.dword 0x400000
+#endif
+#endif
+	/* Effective size of kernel image */
+	.dword _end - _start
+	.dword __HEAD_FLAGS
+	.word RISCV_HEADER_VERSION
+	.word 0
+	.dword 0
+	.ascii RISCV_IMAGE_MAGIC
+	.balign 4
+	.ascii RISCV_IMAGE_MAGIC2
+#ifdef CONFIG_EFI
+	.word pe_head_start - _start
+pe_head_start:
+
+	__EFI_PE_HEADER
+#else
+	.word 0
+#endif
+
+.align 2
+#ifdef CONFIG_MMU
+	.global relocate_enable_mmu
+relocate_enable_mmu:
+	/* Relocate return address */
+	la a1, kernel_map
+	XIP_FIXUP_OFFSET a1
+	REG_L a1, KERNEL_MAP_VIRT_ADDR(a1)
+	la a2, _start
+	sub a1, a1, a2
+	add ra, ra, a1
+
+	/* Point stvec to virtual address of intruction after satp write */
+	la a2, 1f
+	add a2, a2, a1
+	csrw CSR_TVEC, a2
+
+	/* Compute satp for kernel page tables, but don't load it yet */
+	srl a2, a0, PAGE_SHIFT
+	la a1, satp_mode
+	REG_L a1, 0(a1)
+	or a2, a2, a1
+
+	/*
+	 * Load trampoline page directory, which will cause us to trap to
+	 * stvec if VA != PA, or simply fall through if VA == PA.  We need a
+	 * full fence here because setup_vm() just wrote these PTEs and we need
+	 * to ensure the new translations are in use.
+	 */
+	la a0, trampoline_pg_dir
+	XIP_FIXUP_OFFSET a0
+	srl a0, a0, PAGE_SHIFT
+	or a0, a0, a1
+	sfence.vma
+	csrw CSR_SATP, a0
+.align 2
+1:
+	/* Set trap vector to spin forever to help debug */
+	la a0, .Lsecondary_park
+	csrw CSR_TVEC, a0
+
+	/* Reload the global pointer */
+.option push
+.option norelax
+	la gp, __global_pointer$
+.option pop
+
+	/*
+	 * Switch to kernel page tables.  A full fence is necessary in order to
+	 * avoid using the trampoline translations, which are only correct for
+	 * the first superpage.  Fetching the fence is guaranteed to work
+	 * because that first superpage is translated the same way.
+	 */
+	csrw CSR_SATP, a2
+	sfence.vma
+
+	ret
+#endif /* CONFIG_MMU */
+#ifdef CONFIG_SMP
+	.global secondary_start_sbi
+secondary_start_sbi:
+	/* Mask all interrupts */
+	csrw CSR_IE, zero
+	csrw CSR_IP, zero
+
+	/* Load the global pointer */
+	.option push
+	.option norelax
+		la gp, __global_pointer$
+	.option pop
+
+	/*
+	 * Disable FPU to detect illegal usage of
+	 * floating point in kernel space
+	 */
+	li t0, SR_FS
+	csrc CSR_STATUS, t0
+
+	/* Set trap vector to spin forever to help debug */
+	la a3, .Lsecondary_park
+	csrw CSR_TVEC, a3
+
+	/* a0 contains the hartid & a1 contains boot data */
+	li a2, SBI_HART_BOOT_TASK_PTR_OFFSET
+	XIP_FIXUP_OFFSET a2
+	add a2, a2, a1
+	REG_L tp, (a2)
+	li a3, SBI_HART_BOOT_STACK_PTR_OFFSET
+	XIP_FIXUP_OFFSET a3
+	add a3, a3, a1
+	REG_L sp, (a3)
+
+.Lsecondary_start_common:
+
+#ifdef CONFIG_MMU
+	/* Enable virtual memory and relocate to virtual address */
+	la a0, swapper_pg_dir
+	XIP_FIXUP_OFFSET a0
+	call relocate_enable_mmu
+#endif
+	call setup_trap_vector
+	tail smp_callin
+#endif /* CONFIG_SMP */
+
+.align 2
+setup_trap_vector:
+	/* Set trap vector to exception handler */
+	la a0, handle_exception
+	csrw CSR_TVEC, a0
+
+	/*
+	 * Set sup0 scratch register to 0, indicating to exception vector that
+	 * we are presently executing in kernel.
+	 */
+	csrw CSR_SCRATCH, zero
+	ret
+
+.align 2
+.Lsecondary_park:
+	/* We lack SMP support or have too many harts, so park this hart */
+	wfi
+	j .Lsecondary_park
+
+END(_start)
+
+ENTRY(_start_kernel)
+	/* Mask all interrupts */
+	csrw CSR_IE, zero
+	csrw CSR_IP, zero
+
+#ifdef CONFIG_RISCV_M_MODE
+	/* flush the instruction cache */
+	fence.i
+
+	/* Reset all registers except ra, a0, a1 */
+	call reset_regs
+
+	/*
+	 * Setup a PMP to permit access to all of memory.  Some machines may
+	 * not implement PMPs, so we set up a quick trap handler to just skip
+	 * touching the PMPs on any trap.
+	 */
+	la a0, pmp_done
+	csrw CSR_TVEC, a0
+
+	li a0, -1
+	csrw CSR_PMPADDR0, a0
+	li a0, (PMP_A_NAPOT | PMP_R | PMP_W | PMP_X)
+	csrw CSR_PMPCFG0, a0
+.align 2
+pmp_done:
+
+	/*
+	 * The hartid in a0 is expected later on, and we have no firmware
+	 * to hand it to us.
+	 */
+	csrr a0, CSR_MHARTID
+#endif /* CONFIG_RISCV_M_MODE */
+
+	/* Load the global pointer */
+.option push
+.option norelax
+	la gp, __global_pointer$
+.option pop
+
+	/*
+	 * Disable FPU to detect illegal usage of
+	 * floating point in kernel space
+	 */
+	li t0, SR_FS
+	csrc CSR_STATUS, t0
+
+#ifdef CONFIG_RISCV_BOOT_SPINWAIT
+	li t0, CONFIG_NR_CPUS
+	blt a0, t0, .Lgood_cores
+	tail .Lsecondary_park
+.Lgood_cores:
+
+	/* The lottery system is only required for spinwait booting method */
+#ifndef CONFIG_XIP_KERNEL
+	/* Pick one hart to run the main boot sequence */
+	la a3, hart_lottery
+	li a2, 1
+	amoadd.w a3, a2, (a3)
+	bnez a3, .Lsecondary_start
+
+#else
+	/* hart_lottery in flash contains a magic number */
+	la a3, hart_lottery
+	mv a2, a3
+	XIP_FIXUP_OFFSET a2
+	XIP_FIXUP_FLASH_OFFSET a3
+	lw t1, (a3)
+	amoswap.w t0, t1, (a2)
+	/* first time here if hart_lottery in RAM is not set */
+	beq t0, t1, .Lsecondary_start
+
+#endif /* CONFIG_XIP */
+#endif /* CONFIG_RISCV_BOOT_SPINWAIT */
+
+#ifdef CONFIG_XIP_KERNEL
+	la sp, _end + THREAD_SIZE
+	XIP_FIXUP_OFFSET sp
+	mv s0, a0
+	call __copy_data
+
+	/* Restore a0 copy */
+	mv a0, s0
+#endif
+
+#ifndef CONFIG_XIP_KERNEL
+	/* Clear BSS for flat non-ELF images */
+	la a3, __bss_start
+	la a4, __bss_stop
+	ble a4, a3, clear_bss_done
+clear_bss:
+	REG_S zero, (a3)
+	add a3, a3, RISCV_SZPTR
+	blt a3, a4, clear_bss
+clear_bss_done:
+#endif
+	/* Save hart ID and DTB physical address */
+	mv s0, a0
+	mv s1, a1
+
+	la a2, boot_cpu_hartid
+	XIP_FIXUP_OFFSET a2
+	REG_S a0, (a2)
+
+	/* Initialize page tables and relocate to virtual addresses */
+	la tp, init_task
+	la sp, init_thread_union + THREAD_SIZE
+	XIP_FIXUP_OFFSET sp
+#ifdef CONFIG_BUILTIN_DTB
+	la a0, __dtb_start
+	XIP_FIXUP_OFFSET a0
+#else
+	mv a0, s1
+#endif /* CONFIG_BUILTIN_DTB */
+	call setup_vm
+#ifdef CONFIG_MMU
+	la a0, early_pg_dir
+	XIP_FIXUP_OFFSET a0
+	call relocate_enable_mmu
+#endif /* CONFIG_MMU */
+
+	call setup_trap_vector
+	/* Restore C environment */
+	la tp, init_task
+	la sp, init_thread_union + THREAD_SIZE
+
+#ifdef CONFIG_KASAN
+	call kasan_early_init
+#endif
+	/* Start the kernel */
+	call soc_early_init
+	tail start_kernel
+
+#ifdef CONFIG_RISCV_BOOT_SPINWAIT
+.Lsecondary_start:
+	/* Set trap vector to spin forever to help debug */
+	la a3, .Lsecondary_park
+	csrw CSR_TVEC, a3
+
+	slli a3, a0, LGREG
+	la a1, __cpu_spinwait_stack_pointer
+	XIP_FIXUP_OFFSET a1
+	la a2, __cpu_spinwait_task_pointer
+	XIP_FIXUP_OFFSET a2
+	add a1, a3, a1
+	add a2, a3, a2
+
+	/*
+	 * This hart didn't win the lottery, so we wait for the winning hart to
+	 * get far enough along the boot process that it should continue.
+	 */
+.Lwait_for_cpu_up:
+	/* FIXME: We should WFI to save some energy here. */
+	REG_L sp, (a1)
+	REG_L tp, (a2)
+	beqz sp, .Lwait_for_cpu_up
+	beqz tp, .Lwait_for_cpu_up
+	fence
+
+	tail .Lsecondary_start_common
+#endif /* CONFIG_RISCV_BOOT_SPINWAIT */
+
+END(_start_kernel)
+
+#ifdef CONFIG_RISCV_M_MODE
+ENTRY(reset_regs)
+	li	sp, 0
+	li	gp, 0
+	li	tp, 0
+	li	t0, 0
+	li	t1, 0
+	li	t2, 0
+	li	s0, 0
+	li	s1, 0
+	li	a2, 0
+	li	a3, 0
+	li	a4, 0
+	li	a5, 0
+	li	a6, 0
+	li	a7, 0
+	li	s2, 0
+	li	s3, 0
+	li	s4, 0
+	li	s5, 0
+	li	s6, 0
+	li	s7, 0
+	li	s8, 0
+	li	s9, 0
+	li	s10, 0
+	li	s11, 0
+	li	t3, 0
+	li	t4, 0
+	li	t5, 0
+	li	t6, 0
+	csrw	CSR_SCRATCH, 0
+
+#ifdef CONFIG_FPU
+	csrr	t0, CSR_MISA
+	andi	t0, t0, (COMPAT_HWCAP_ISA_F | COMPAT_HWCAP_ISA_D)
+	beqz	t0, .Lreset_regs_done
+
+	li	t1, SR_FS
+	csrs	CSR_STATUS, t1
+	fmv.s.x	f0, zero
+	fmv.s.x	f1, zero
+	fmv.s.x	f2, zero
+	fmv.s.x	f3, zero
+	fmv.s.x	f4, zero
+	fmv.s.x	f5, zero
+	fmv.s.x	f6, zero
+	fmv.s.x	f7, zero
+	fmv.s.x	f8, zero
+	fmv.s.x	f9, zero
+	fmv.s.x	f10, zero
+	fmv.s.x	f11, zero
+	fmv.s.x	f12, zero
+	fmv.s.x	f13, zero
+	fmv.s.x	f14, zero
+	fmv.s.x	f15, zero
+	fmv.s.x	f16, zero
+	fmv.s.x	f17, zero
+	fmv.s.x	f18, zero
+	fmv.s.x	f19, zero
+	fmv.s.x	f20, zero
+	fmv.s.x	f21, zero
+	fmv.s.x	f22, zero
+	fmv.s.x	f23, zero
+	fmv.s.x	f24, zero
+	fmv.s.x	f25, zero
+	fmv.s.x	f26, zero
+	fmv.s.x	f27, zero
+	fmv.s.x	f28, zero
+	fmv.s.x	f29, zero
+	fmv.s.x	f30, zero
+	fmv.s.x	f31, zero
+	csrw	fcsr, 0
+	/* note that the caller must clear SR_FS */
+#endif /* CONFIG_FPU */
+.Lreset_regs_done:
+	ret
+END(reset_regs)
+#endif /* CONFIG_RISCV_M_MODE */
diff --git a/arch/riscv/kernel/head.h b/arch/riscv/kernel/head.h
new file mode 100644
index 000000000..726731ada
--- /dev/null
+++ b/arch/riscv/kernel/head.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2019 SiFive, Inc.
+ */
+#ifndef __ASM_HEAD_H
+#define __ASM_HEAD_H
+
+#include <linux/linkage.h>
+#include <linux/init.h>
+
+extern atomic_t hart_lottery;
+
+asmlinkage void do_page_fault(struct pt_regs *regs);
+asmlinkage void __init setup_vm(uintptr_t dtb_pa);
+#ifdef CONFIG_XIP_KERNEL
+asmlinkage void __init __copy_data(void);
+#endif
+
+#ifdef CONFIG_RISCV_BOOT_SPINWAIT
+extern void *__cpu_spinwait_stack_pointer[];
+extern void *__cpu_spinwait_task_pointer[];
+#endif
+
+#endif /* __ASM_HEAD_H */
diff --git a/arch/riscv/kernel/image-vars.h b/arch/riscv/kernel/image-vars.h
new file mode 100644
index 000000000..d6e5f7399
--- /dev/null
+++ b/arch/riscv/kernel/image-vars.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2020 Western Digital Corporation or its affiliates.
+ * Linker script variables to be set after section resolution, as
+ * ld.lld does not like variables assigned before SECTIONS is processed.
+ * Based on arch/arm64/kernel/image-vars.h
+ */
+#ifndef __RISCV_KERNEL_IMAGE_VARS_H
+#define __RISCV_KERNEL_IMAGE_VARS_H
+
+#ifndef LINKER_SCRIPT
+#error This file should only be included in vmlinux.lds.S
+#endif
+
+#ifdef CONFIG_EFI
+
+/*
+ * The EFI stub has its own symbol namespace prefixed by __efistub_, to
+ * isolate it from the kernel proper. The following symbols are legally
+ * accessed by the stub, so provide some aliases to make them accessible.
+ * Only include data symbols here, or text symbols of functions that are
+ * guaranteed to be safe when executed at another offset than they were
+ * linked at. The routines below are all implemented in assembler in a
+ * position independent manner
+ */
+__efistub_memcmp		= memcmp;
+__efistub_memchr		= memchr;
+__efistub_strlen		= strlen;
+__efistub_strnlen		= strnlen;
+__efistub_strcmp		= strcmp;
+__efistub_strncmp		= strncmp;
+__efistub_strrchr		= strrchr;
+
+__efistub__start		= _start;
+__efistub__start_kernel		= _start_kernel;
+__efistub__end			= _end;
+__efistub__edata		= _edata;
+__efistub_screen_info		= screen_info;
+
+#endif
+
+#endif /* __RISCV_KERNEL_IMAGE_VARS_H */
diff --git a/arch/riscv/kernel/irq.c b/arch/riscv/kernel/irq.c
new file mode 100644
index 000000000..7207fa08d
--- /dev/null
+++ b/arch/riscv/kernel/irq.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ * Copyright (C) 2017 SiFive
+ * Copyright (C) 2018 Christoph Hellwig
+ */
+
+#include <linux/interrupt.h>
+#include <linux/irqchip.h>
+#include <linux/seq_file.h>
+#include <asm/smp.h>
+
+int arch_show_interrupts(struct seq_file *p, int prec)
+{
+	show_ipi_stats(p, prec);
+	return 0;
+}
+
+void __init init_IRQ(void)
+{
+	irqchip_init();
+	if (!handle_arch_irq)
+		panic("No interrupt controller found.");
+}
diff --git a/arch/riscv/kernel/jump_label.c b/arch/riscv/kernel/jump_label.c
new file mode 100644
index 000000000..e6694759d
--- /dev/null
+++ b/arch/riscv/kernel/jump_label.c
@@ -0,0 +1,41 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020 Emil Renner Berthing
+ *
+ * Based on arch/arm64/kernel/jump_label.c
+ */
+#include <linux/jump_label.h>
+#include <linux/kernel.h>
+#include <linux/memory.h>
+#include <linux/mutex.h>
+#include <asm/bug.h>
+#include <asm/patch.h>
+
+#define RISCV_INSN_NOP 0x00000013U
+#define RISCV_INSN_JAL 0x0000006fU
+
+void arch_jump_label_transform(struct jump_entry *entry,
+			       enum jump_label_type type)
+{
+	void *addr = (void *)jump_entry_code(entry);
+	u32 insn;
+
+	if (type == JUMP_LABEL_JMP) {
+		long offset = jump_entry_target(entry) - jump_entry_code(entry);
+
+		if (WARN_ON(offset & 1 || offset < -524288 || offset >= 524288))
+			return;
+
+		insn = RISCV_INSN_JAL |
+			(((u32)offset & GENMASK(19, 12)) << (12 - 12)) |
+			(((u32)offset & GENMASK(11, 11)) << (20 - 11)) |
+			(((u32)offset & GENMASK(10,  1)) << (21 -  1)) |
+			(((u32)offset & GENMASK(20, 20)) << (31 - 20));
+	} else {
+		insn = RISCV_INSN_NOP;
+	}
+
+	mutex_lock(&text_mutex);
+	patch_text_nosync(addr, &insn, sizeof(insn));
+	mutex_unlock(&text_mutex);
+}
diff --git a/arch/riscv/kernel/kexec_relocate.S b/arch/riscv/kernel/kexec_relocate.S
new file mode 100644
index 000000000..059c5e216
--- /dev/null
+++ b/arch/riscv/kernel/kexec_relocate.S
@@ -0,0 +1,221 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2019 FORTH-ICS/CARV
+ *  Nick Kossifidis <mick@ics.forth.gr>
+ */
+
+#include <asm/asm.h>	/* For RISCV_* and REG_* macros */
+#include <asm/csr.h>	/* For CSR_* macros */
+#include <asm/page.h>	/* For PAGE_SIZE */
+#include <linux/linkage.h> /* For SYM_* macros */
+
+.section ".rodata"
+SYM_CODE_START(riscv_kexec_relocate)
+
+	/*
+	 * s0: Pointer to the current entry
+	 * s1: (const) Phys address to jump to after relocation
+	 * s2: (const) Phys address of the FDT image
+	 * s3: (const) The hartid of the current hart
+	 * s4: Pointer to the destination address for the relocation
+	 * s5: (const) Number of words per page
+	 * s6: (const) 1, used for subtraction
+	 * s7: (const) kernel_map.va_pa_offset, used when switching MMU off
+	 * s8: (const) Physical address of the main loop
+	 * s9: (debug) indirection page counter
+	 * s10: (debug) entry counter
+	 * s11: (debug) copied words counter
+	 */
+	mv	s0, a0
+	mv	s1, a1
+	mv	s2, a2
+	mv	s3, a3
+	mv	s4, zero
+	li	s5, (PAGE_SIZE / RISCV_SZPTR)
+	li	s6, 1
+	mv	s7, a4
+	mv	s8, zero
+	mv	s9, zero
+	mv	s10, zero
+	mv	s11, zero
+
+	/* Disable / cleanup interrupts */
+	csrw	CSR_SIE, zero
+	csrw	CSR_SIP, zero
+
+	/*
+	 * When we switch SATP.MODE to "Bare" we'll only
+	 * play with physical addresses. However the first time
+	 * we try to jump somewhere, the offset on the jump
+	 * will be relative to pc which will still be on VA. To
+	 * deal with this we set stvec to the physical address at
+	 * the start of the loop below so that we jump there in
+	 * any case.
+	 */
+	la	s8, 1f
+	sub	s8, s8, s7
+	csrw	CSR_STVEC, s8
+
+	/* Process entries in a loop */
+.align 2
+1:
+	addi	s10, s10, 1
+	REG_L	t0, 0(s0)		/* t0 = *image->entry */
+	addi	s0, s0, RISCV_SZPTR	/* image->entry++ */
+
+	/* IND_DESTINATION entry ? -> save destination address */
+	andi	t1, t0, 0x1
+	beqz	t1, 2f
+	andi	s4, t0, ~0x1
+	j	1b
+
+2:
+	/* IND_INDIRECTION entry ? -> update next entry ptr (PA) */
+	andi	t1, t0, 0x2
+	beqz	t1, 2f
+	andi	s0, t0, ~0x2
+	addi	s9, s9, 1
+	csrw	CSR_SATP, zero
+	jalr	zero, s8, 0
+
+2:
+	/* IND_DONE entry ? -> jump to done label */
+	andi	t1, t0, 0x4
+	beqz	t1, 2f
+	j	4f
+
+2:
+	/*
+	 * IND_SOURCE entry ? -> copy page word by word to the
+	 * destination address we got from IND_DESTINATION
+	 */
+	andi	t1, t0, 0x8
+	beqz	t1, 1b		/* Unknown entry type, ignore it */
+	andi	t0, t0, ~0x8
+	mv	t3, s5		/* i = num words per page */
+3:	/* copy loop */
+	REG_L	t1, (t0)	/* t1 = *src_ptr */
+	REG_S	t1, (s4)	/* *dst_ptr = *src_ptr */
+	addi	t0, t0, RISCV_SZPTR /* stc_ptr++ */
+	addi	s4, s4, RISCV_SZPTR /* dst_ptr++ */
+	sub	t3, t3, s6	/* i-- */
+	addi	s11, s11, 1	/* c++ */
+	beqz	t3, 1b		/* copy done ? */
+	j	3b
+
+4:
+	/* Pass the arguments to the next kernel  / Cleanup*/
+	mv	a0, s3
+	mv	a1, s2
+	mv	a2, s1
+
+	/* Cleanup */
+	mv	a3, zero
+	mv	a4, zero
+	mv	a5, zero
+	mv	a6, zero
+	mv	a7, zero
+
+	mv	s0, zero
+	mv	s1, zero
+	mv	s2, zero
+	mv	s3, zero
+	mv	s4, zero
+	mv	s5, zero
+	mv	s6, zero
+	mv	s7, zero
+	mv	s8, zero
+	mv	s9, zero
+	mv	s10, zero
+	mv	s11, zero
+
+	mv	t0, zero
+	mv	t1, zero
+	mv	t2, zero
+	mv	t3, zero
+	mv	t4, zero
+	mv	t5, zero
+	mv	t6, zero
+	csrw	CSR_SEPC, zero
+	csrw	CSR_SCAUSE, zero
+	csrw	CSR_SSCRATCH, zero
+
+	/*
+	 * Make sure the relocated code is visible
+	 * and jump to the new kernel
+	 */
+	fence.i
+
+	jalr	zero, a2, 0
+
+SYM_CODE_END(riscv_kexec_relocate)
+riscv_kexec_relocate_end:
+
+
+/* Used for jumping to crashkernel */
+.section ".text"
+SYM_CODE_START(riscv_kexec_norelocate)
+	/*
+	 * s0: (const) Phys address to jump to
+	 * s1: (const) Phys address of the FDT image
+	 * s2: (const) The hartid of the current hart
+	 */
+	mv	s0, a1
+	mv	s1, a2
+	mv	s2, a3
+
+	/* Disable / cleanup interrupts */
+	csrw	CSR_SIE, zero
+	csrw	CSR_SIP, zero
+
+	/* Pass the arguments to the next kernel  / Cleanup*/
+	mv	a0, s2
+	mv	a1, s1
+	mv	a2, s0
+
+	/* Cleanup */
+	mv	a3, zero
+	mv	a4, zero
+	mv	a5, zero
+	mv	a6, zero
+	mv	a7, zero
+
+	mv	s0, zero
+	mv	s1, zero
+	mv	s2, zero
+	mv	s3, zero
+	mv	s4, zero
+	mv	s5, zero
+	mv	s6, zero
+	mv	s7, zero
+	mv	s8, zero
+	mv	s9, zero
+	mv	s10, zero
+	mv	s11, zero
+
+	mv	t0, zero
+	mv	t1, zero
+	mv	t2, zero
+	mv	t3, zero
+	mv	t4, zero
+	mv	t5, zero
+	mv	t6, zero
+	csrw	CSR_SEPC, zero
+	csrw	CSR_SCAUSE, zero
+	csrw	CSR_SSCRATCH, zero
+
+	/*
+	 * Switch to physical addressing
+	 * This will also trigger a jump to CSR_STVEC
+	 * which in this case is the address of the new
+	 * kernel.
+	 */
+	csrw	CSR_STVEC, a2
+	csrw	CSR_SATP, zero
+
+SYM_CODE_END(riscv_kexec_norelocate)
+
+.section ".rodata"
+SYM_DATA(riscv_kexec_relocate_size,
+	.long riscv_kexec_relocate_end - riscv_kexec_relocate)
+
diff --git a/arch/riscv/kernel/kgdb.c b/arch/riscv/kernel/kgdb.c
new file mode 100644
index 000000000..963ed7edc
--- /dev/null
+++ b/arch/riscv/kernel/kgdb.c
@@ -0,0 +1,390 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020 SiFive
+ */
+
+#include <linux/ptrace.h>
+#include <linux/kdebug.h>
+#include <linux/bug.h>
+#include <linux/kgdb.h>
+#include <linux/irqflags.h>
+#include <linux/string.h>
+#include <asm/cacheflush.h>
+#include <asm/gdb_xml.h>
+#include <asm/parse_asm.h>
+
+enum {
+	NOT_KGDB_BREAK = 0,
+	KGDB_SW_BREAK,
+	KGDB_COMPILED_BREAK,
+	KGDB_SW_SINGLE_STEP
+};
+
+static unsigned long stepped_address;
+static unsigned int stepped_opcode;
+
+#if __riscv_xlen == 32
+/* C.JAL is an RV32C-only instruction */
+DECLARE_INSN(c_jal, MATCH_C_JAL, MASK_C_JAL)
+#else
+#define is_c_jal_insn(opcode) 0
+#endif
+DECLARE_INSN(jalr, MATCH_JALR, MASK_JALR)
+DECLARE_INSN(jal, MATCH_JAL, MASK_JAL)
+DECLARE_INSN(c_jr, MATCH_C_JR, MASK_C_JR)
+DECLARE_INSN(c_jalr, MATCH_C_JALR, MASK_C_JALR)
+DECLARE_INSN(c_j, MATCH_C_J, MASK_C_J)
+DECLARE_INSN(beq, MATCH_BEQ, MASK_BEQ)
+DECLARE_INSN(bne, MATCH_BNE, MASK_BNE)
+DECLARE_INSN(blt, MATCH_BLT, MASK_BLT)
+DECLARE_INSN(bge, MATCH_BGE, MASK_BGE)
+DECLARE_INSN(bltu, MATCH_BLTU, MASK_BLTU)
+DECLARE_INSN(bgeu, MATCH_BGEU, MASK_BGEU)
+DECLARE_INSN(c_beqz, MATCH_C_BEQZ, MASK_C_BEQZ)
+DECLARE_INSN(c_bnez, MATCH_C_BNEZ, MASK_C_BNEZ)
+DECLARE_INSN(sret, MATCH_SRET, MASK_SRET)
+
+static int decode_register_index(unsigned long opcode, int offset)
+{
+	return (opcode >> offset) & 0x1F;
+}
+
+static int decode_register_index_short(unsigned long opcode, int offset)
+{
+	return ((opcode >> offset) & 0x7) + 8;
+}
+
+/* Calculate the new address for after a step */
+static int get_step_address(struct pt_regs *regs, unsigned long *next_addr)
+{
+	unsigned long pc = regs->epc;
+	unsigned long *regs_ptr = (unsigned long *)regs;
+	unsigned int rs1_num, rs2_num;
+	int op_code;
+
+	if (get_kernel_nofault(op_code, (void *)pc))
+		return -EINVAL;
+	if ((op_code & __INSN_LENGTH_MASK) != __INSN_LENGTH_GE_32) {
+		if (is_c_jalr_insn(op_code) || is_c_jr_insn(op_code)) {
+			rs1_num = decode_register_index(op_code, RVC_C2_RS1_OPOFF);
+			*next_addr = regs_ptr[rs1_num];
+		} else if (is_c_j_insn(op_code) || is_c_jal_insn(op_code)) {
+			*next_addr = EXTRACT_RVC_J_IMM(op_code) + pc;
+		} else if (is_c_beqz_insn(op_code)) {
+			rs1_num = decode_register_index_short(op_code,
+							      RVC_C1_RS1_OPOFF);
+			if (!rs1_num || regs_ptr[rs1_num] == 0)
+				*next_addr = EXTRACT_RVC_B_IMM(op_code) + pc;
+			else
+				*next_addr = pc + 2;
+		} else if (is_c_bnez_insn(op_code)) {
+			rs1_num =
+			    decode_register_index_short(op_code, RVC_C1_RS1_OPOFF);
+			if (rs1_num && regs_ptr[rs1_num] != 0)
+				*next_addr = EXTRACT_RVC_B_IMM(op_code) + pc;
+			else
+				*next_addr = pc + 2;
+		} else {
+			*next_addr = pc + 2;
+		}
+	} else {
+		if ((op_code & __INSN_OPCODE_MASK) == __INSN_BRANCH_OPCODE) {
+			bool result = false;
+			long imm = EXTRACT_BTYPE_IMM(op_code);
+			unsigned long rs1_val = 0, rs2_val = 0;
+
+			rs1_num = decode_register_index(op_code, RVG_RS1_OPOFF);
+			rs2_num = decode_register_index(op_code, RVG_RS2_OPOFF);
+			if (rs1_num)
+				rs1_val = regs_ptr[rs1_num];
+			if (rs2_num)
+				rs2_val = regs_ptr[rs2_num];
+
+			if (is_beq_insn(op_code))
+				result = (rs1_val == rs2_val) ? true : false;
+			else if (is_bne_insn(op_code))
+				result = (rs1_val != rs2_val) ? true : false;
+			else if (is_blt_insn(op_code))
+				result =
+				    ((long)rs1_val <
+				     (long)rs2_val) ? true : false;
+			else if (is_bge_insn(op_code))
+				result =
+				    ((long)rs1_val >=
+				     (long)rs2_val) ? true : false;
+			else if (is_bltu_insn(op_code))
+				result = (rs1_val < rs2_val) ? true : false;
+			else if (is_bgeu_insn(op_code))
+				result = (rs1_val >= rs2_val) ? true : false;
+			if (result)
+				*next_addr = imm + pc;
+			else
+				*next_addr = pc + 4;
+		} else if (is_jal_insn(op_code)) {
+			*next_addr = EXTRACT_JTYPE_IMM(op_code) + pc;
+		} else if (is_jalr_insn(op_code)) {
+			rs1_num = decode_register_index(op_code, RVG_RS1_OPOFF);
+			if (rs1_num)
+				*next_addr = ((unsigned long *)regs)[rs1_num];
+			*next_addr += EXTRACT_ITYPE_IMM(op_code);
+		} else if (is_sret_insn(op_code)) {
+			*next_addr = pc;
+		} else {
+			*next_addr = pc + 4;
+		}
+	}
+	return 0;
+}
+
+static int do_single_step(struct pt_regs *regs)
+{
+	/* Determine where the target instruction will send us to */
+	unsigned long addr = 0;
+	int error = get_step_address(regs, &addr);
+
+	if (error)
+		return error;
+
+	/* Store the op code in the stepped address */
+	error = get_kernel_nofault(stepped_opcode, (void *)addr);
+	if (error)
+		return error;
+
+	stepped_address = addr;
+
+	/* Replace the op code with the break instruction */
+	error = copy_to_kernel_nofault((void *)stepped_address,
+				   arch_kgdb_ops.gdb_bpt_instr,
+				   BREAK_INSTR_SIZE);
+	/* Flush and return */
+	if (!error) {
+		flush_icache_range(addr, addr + BREAK_INSTR_SIZE);
+		kgdb_single_step = 1;
+		atomic_set(&kgdb_cpu_doing_single_step,
+			   raw_smp_processor_id());
+	} else {
+		stepped_address = 0;
+		stepped_opcode = 0;
+	}
+	return error;
+}
+
+/* Undo a single step */
+static void undo_single_step(struct pt_regs *regs)
+{
+	if (stepped_opcode != 0) {
+		copy_to_kernel_nofault((void *)stepped_address,
+				   (void *)&stepped_opcode, BREAK_INSTR_SIZE);
+		flush_icache_range(stepped_address,
+				   stepped_address + BREAK_INSTR_SIZE);
+	}
+	stepped_address = 0;
+	stepped_opcode = 0;
+	kgdb_single_step = 0;
+	atomic_set(&kgdb_cpu_doing_single_step, -1);
+}
+
+struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = {
+	{DBG_REG_ZERO, GDB_SIZEOF_REG, -1},
+	{DBG_REG_RA, GDB_SIZEOF_REG, offsetof(struct pt_regs, ra)},
+	{DBG_REG_SP, GDB_SIZEOF_REG, offsetof(struct pt_regs, sp)},
+	{DBG_REG_GP, GDB_SIZEOF_REG, offsetof(struct pt_regs, gp)},
+	{DBG_REG_TP, GDB_SIZEOF_REG, offsetof(struct pt_regs, tp)},
+	{DBG_REG_T0, GDB_SIZEOF_REG, offsetof(struct pt_regs, t0)},
+	{DBG_REG_T1, GDB_SIZEOF_REG, offsetof(struct pt_regs, t1)},
+	{DBG_REG_T2, GDB_SIZEOF_REG, offsetof(struct pt_regs, t2)},
+	{DBG_REG_FP, GDB_SIZEOF_REG, offsetof(struct pt_regs, s0)},
+	{DBG_REG_S1, GDB_SIZEOF_REG, offsetof(struct pt_regs, a1)},
+	{DBG_REG_A0, GDB_SIZEOF_REG, offsetof(struct pt_regs, a0)},
+	{DBG_REG_A1, GDB_SIZEOF_REG, offsetof(struct pt_regs, a1)},
+	{DBG_REG_A2, GDB_SIZEOF_REG, offsetof(struct pt_regs, a2)},
+	{DBG_REG_A3, GDB_SIZEOF_REG, offsetof(struct pt_regs, a3)},
+	{DBG_REG_A4, GDB_SIZEOF_REG, offsetof(struct pt_regs, a4)},
+	{DBG_REG_A5, GDB_SIZEOF_REG, offsetof(struct pt_regs, a5)},
+	{DBG_REG_A6, GDB_SIZEOF_REG, offsetof(struct pt_regs, a6)},
+	{DBG_REG_A7, GDB_SIZEOF_REG, offsetof(struct pt_regs, a7)},
+	{DBG_REG_S2, GDB_SIZEOF_REG, offsetof(struct pt_regs, s2)},
+	{DBG_REG_S3, GDB_SIZEOF_REG, offsetof(struct pt_regs, s3)},
+	{DBG_REG_S4, GDB_SIZEOF_REG, offsetof(struct pt_regs, s4)},
+	{DBG_REG_S5, GDB_SIZEOF_REG, offsetof(struct pt_regs, s5)},
+	{DBG_REG_S6, GDB_SIZEOF_REG, offsetof(struct pt_regs, s6)},
+	{DBG_REG_S7, GDB_SIZEOF_REG, offsetof(struct pt_regs, s7)},
+	{DBG_REG_S8, GDB_SIZEOF_REG, offsetof(struct pt_regs, s8)},
+	{DBG_REG_S9, GDB_SIZEOF_REG, offsetof(struct pt_regs, s9)},
+	{DBG_REG_S10, GDB_SIZEOF_REG, offsetof(struct pt_regs, s10)},
+	{DBG_REG_S11, GDB_SIZEOF_REG, offsetof(struct pt_regs, s11)},
+	{DBG_REG_T3, GDB_SIZEOF_REG, offsetof(struct pt_regs, t3)},
+	{DBG_REG_T4, GDB_SIZEOF_REG, offsetof(struct pt_regs, t4)},
+	{DBG_REG_T5, GDB_SIZEOF_REG, offsetof(struct pt_regs, t5)},
+	{DBG_REG_T6, GDB_SIZEOF_REG, offsetof(struct pt_regs, t6)},
+	{DBG_REG_EPC, GDB_SIZEOF_REG, offsetof(struct pt_regs, epc)},
+	{DBG_REG_STATUS, GDB_SIZEOF_REG, offsetof(struct pt_regs, status)},
+	{DBG_REG_BADADDR, GDB_SIZEOF_REG, offsetof(struct pt_regs, badaddr)},
+	{DBG_REG_CAUSE, GDB_SIZEOF_REG, offsetof(struct pt_regs, cause)},
+};
+
+char *dbg_get_reg(int regno, void *mem, struct pt_regs *regs)
+{
+	if (regno >= DBG_MAX_REG_NUM || regno < 0)
+		return NULL;
+
+	if (dbg_reg_def[regno].offset != -1)
+		memcpy(mem, (void *)regs + dbg_reg_def[regno].offset,
+		       dbg_reg_def[regno].size);
+	else
+		memset(mem, 0, dbg_reg_def[regno].size);
+	return dbg_reg_def[regno].name;
+}
+
+int dbg_set_reg(int regno, void *mem, struct pt_regs *regs)
+{
+	if (regno >= DBG_MAX_REG_NUM || regno < 0)
+		return -EINVAL;
+
+	if (dbg_reg_def[regno].offset != -1)
+		memcpy((void *)regs + dbg_reg_def[regno].offset, mem,
+		       dbg_reg_def[regno].size);
+	return 0;
+}
+
+void
+sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *task)
+{
+	/* Initialize to zero */
+	memset((char *)gdb_regs, 0, NUMREGBYTES);
+
+	gdb_regs[DBG_REG_SP_OFF] = task->thread.sp;
+	gdb_regs[DBG_REG_FP_OFF] = task->thread.s[0];
+	gdb_regs[DBG_REG_S1_OFF] = task->thread.s[1];
+	gdb_regs[DBG_REG_S2_OFF] = task->thread.s[2];
+	gdb_regs[DBG_REG_S3_OFF] = task->thread.s[3];
+	gdb_regs[DBG_REG_S4_OFF] = task->thread.s[4];
+	gdb_regs[DBG_REG_S5_OFF] = task->thread.s[5];
+	gdb_regs[DBG_REG_S6_OFF] = task->thread.s[6];
+	gdb_regs[DBG_REG_S7_OFF] = task->thread.s[7];
+	gdb_regs[DBG_REG_S8_OFF] = task->thread.s[8];
+	gdb_regs[DBG_REG_S9_OFF] = task->thread.s[10];
+	gdb_regs[DBG_REG_S10_OFF] = task->thread.s[11];
+	gdb_regs[DBG_REG_EPC_OFF] = task->thread.ra;
+}
+
+void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long pc)
+{
+	regs->epc = pc;
+}
+
+void kgdb_arch_handle_qxfer_pkt(char *remcom_in_buffer,
+				char *remcom_out_buffer)
+{
+	if (!strncmp(remcom_in_buffer, gdb_xfer_read_target,
+		     sizeof(gdb_xfer_read_target)))
+		strcpy(remcom_out_buffer, riscv_gdb_stub_target_desc);
+	else if (!strncmp(remcom_in_buffer, gdb_xfer_read_cpuxml,
+			  sizeof(gdb_xfer_read_cpuxml)))
+		strcpy(remcom_out_buffer, riscv_gdb_stub_cpuxml);
+}
+
+static inline void kgdb_arch_update_addr(struct pt_regs *regs,
+					 char *remcom_in_buffer)
+{
+	unsigned long addr;
+	char *ptr;
+
+	ptr = &remcom_in_buffer[1];
+	if (kgdb_hex2long(&ptr, &addr))
+		regs->epc = addr;
+}
+
+int kgdb_arch_handle_exception(int vector, int signo, int err_code,
+			       char *remcom_in_buffer, char *remcom_out_buffer,
+			       struct pt_regs *regs)
+{
+	int err = 0;
+
+	undo_single_step(regs);
+
+	switch (remcom_in_buffer[0]) {
+	case 'c':
+	case 'D':
+	case 'k':
+		if (remcom_in_buffer[0] == 'c')
+			kgdb_arch_update_addr(regs, remcom_in_buffer);
+		break;
+	case 's':
+		kgdb_arch_update_addr(regs, remcom_in_buffer);
+		err = do_single_step(regs);
+		break;
+	default:
+		err = -1;
+	}
+	return err;
+}
+
+static int kgdb_riscv_kgdbbreak(unsigned long addr)
+{
+	if (stepped_address == addr)
+		return KGDB_SW_SINGLE_STEP;
+	if (atomic_read(&kgdb_setting_breakpoint))
+		if (addr == (unsigned long)&kgdb_compiled_break)
+			return KGDB_COMPILED_BREAK;
+
+	return kgdb_has_hit_break(addr);
+}
+
+static int kgdb_riscv_notify(struct notifier_block *self, unsigned long cmd,
+			     void *ptr)
+{
+	struct die_args *args = (struct die_args *)ptr;
+	struct pt_regs *regs = args->regs;
+	unsigned long flags;
+	int type;
+
+	if (user_mode(regs))
+		return NOTIFY_DONE;
+
+	type = kgdb_riscv_kgdbbreak(regs->epc);
+	if (type == NOT_KGDB_BREAK && cmd == DIE_TRAP)
+		return NOTIFY_DONE;
+
+	local_irq_save(flags);
+
+	if (kgdb_handle_exception(type == KGDB_SW_SINGLE_STEP ? 0 : 1,
+				  args->signr, cmd, regs))
+		return NOTIFY_DONE;
+
+	if (type == KGDB_COMPILED_BREAK)
+		regs->epc += 4;
+
+	local_irq_restore(flags);
+
+	return NOTIFY_STOP;
+}
+
+static struct notifier_block kgdb_notifier = {
+	.notifier_call = kgdb_riscv_notify,
+};
+
+int kgdb_arch_init(void)
+{
+	register_die_notifier(&kgdb_notifier);
+
+	return 0;
+}
+
+void kgdb_arch_exit(void)
+{
+	unregister_die_notifier(&kgdb_notifier);
+}
+
+/*
+ * Global data
+ */
+#ifdef CONFIG_RISCV_ISA_C
+const struct kgdb_arch arch_kgdb_ops = {
+	.gdb_bpt_instr = {0x02, 0x90},	/* c.ebreak */
+};
+#else
+const struct kgdb_arch arch_kgdb_ops = {
+	.gdb_bpt_instr = {0x73, 0x00, 0x10, 0x00},	/* ebreak */
+};
+#endif
diff --git a/arch/riscv/kernel/machine_kexec.c b/arch/riscv/kernel/machine_kexec.c
new file mode 100644
index 000000000..2d139b724
--- /dev/null
+++ b/arch/riscv/kernel/machine_kexec.c
@@ -0,0 +1,239 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 FORTH-ICS/CARV
+ *  Nick Kossifidis <mick@ics.forth.gr>
+ */
+
+#include <linux/kexec.h>
+#include <asm/kexec.h>		/* For riscv_kexec_* symbol defines */
+#include <linux/smp.h>		/* For smp_send_stop () */
+#include <asm/cacheflush.h>	/* For local_flush_icache_all() */
+#include <asm/barrier.h>	/* For smp_wmb() */
+#include <asm/page.h>		/* For PAGE_MASK */
+#include <linux/libfdt.h>	/* For fdt_check_header() */
+#include <asm/set_memory.h>	/* For set_memory_x() */
+#include <linux/compiler.h>	/* For unreachable() */
+#include <linux/cpu.h>		/* For cpu_down() */
+#include <linux/reboot.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+
+/*
+ * kexec_image_info - Print received image details
+ */
+static void
+kexec_image_info(const struct kimage *image)
+{
+	unsigned long i;
+
+	pr_debug("Kexec image info:\n");
+	pr_debug("\ttype:        %d\n", image->type);
+	pr_debug("\tstart:       %lx\n", image->start);
+	pr_debug("\thead:        %lx\n", image->head);
+	pr_debug("\tnr_segments: %lu\n", image->nr_segments);
+
+	for (i = 0; i < image->nr_segments; i++) {
+		pr_debug("\t    segment[%lu]: %016lx - %016lx", i,
+			image->segment[i].mem,
+			image->segment[i].mem + image->segment[i].memsz);
+		pr_debug("\t\t0x%lx bytes, %lu pages\n",
+			(unsigned long) image->segment[i].memsz,
+			(unsigned long) image->segment[i].memsz /  PAGE_SIZE);
+	}
+}
+
+/*
+ * machine_kexec_prepare - Initialize kexec
+ *
+ * This function is called from do_kexec_load, when the user has
+ * provided us with an image to be loaded. Its goal is to validate
+ * the image and prepare the control code buffer as needed.
+ * Note that kimage_alloc_init has already been called and the
+ * control buffer has already been allocated.
+ */
+int
+machine_kexec_prepare(struct kimage *image)
+{
+	struct kimage_arch *internal = &image->arch;
+	struct fdt_header fdt = {0};
+	void *control_code_buffer = NULL;
+	unsigned int control_code_buffer_sz = 0;
+	int i = 0;
+
+	kexec_image_info(image);
+
+	/* Find the Flattened Device Tree and save its physical address */
+	for (i = 0; i < image->nr_segments; i++) {
+		if (image->segment[i].memsz <= sizeof(fdt))
+			continue;
+
+		if (image->file_mode)
+			memcpy(&fdt, image->segment[i].buf, sizeof(fdt));
+		else if (copy_from_user(&fdt, image->segment[i].buf, sizeof(fdt)))
+			continue;
+
+		if (fdt_check_header(&fdt))
+			continue;
+
+		internal->fdt_addr = (unsigned long) image->segment[i].mem;
+		break;
+	}
+
+	if (!internal->fdt_addr) {
+		pr_err("Device tree not included in the provided image\n");
+		return -EINVAL;
+	}
+
+	/* Copy the assembler code for relocation to the control page */
+	if (image->type != KEXEC_TYPE_CRASH) {
+		control_code_buffer = page_address(image->control_code_page);
+		control_code_buffer_sz = page_size(image->control_code_page);
+
+		if (unlikely(riscv_kexec_relocate_size > control_code_buffer_sz)) {
+			pr_err("Relocation code doesn't fit within a control page\n");
+			return -EINVAL;
+		}
+
+		memcpy(control_code_buffer, riscv_kexec_relocate,
+			riscv_kexec_relocate_size);
+
+		/* Mark the control page executable */
+		set_memory_x((unsigned long) control_code_buffer, 1);
+	}
+
+	return 0;
+}
+
+
+/*
+ * machine_kexec_cleanup - Cleanup any leftovers from
+ *			   machine_kexec_prepare
+ *
+ * This function is called by kimage_free to handle any arch-specific
+ * allocations done on machine_kexec_prepare. Since we didn't do any
+ * allocations there, this is just an empty function. Note that the
+ * control buffer is freed by kimage_free.
+ */
+void
+machine_kexec_cleanup(struct kimage *image)
+{
+}
+
+
+/*
+ * machine_shutdown - Prepare for a kexec reboot
+ *
+ * This function is called by kernel_kexec just before machine_kexec
+ * below. Its goal is to prepare the rest of the system (the other
+ * harts and possibly devices etc) for a kexec reboot.
+ */
+void machine_shutdown(void)
+{
+	/*
+	 * No more interrupts on this hart
+	 * until we are back up.
+	 */
+	local_irq_disable();
+
+#if defined(CONFIG_HOTPLUG_CPU)
+	smp_shutdown_nonboot_cpus(smp_processor_id());
+#endif
+}
+
+static void machine_kexec_mask_interrupts(void)
+{
+	unsigned int i;
+	struct irq_desc *desc;
+
+	for_each_irq_desc(i, desc) {
+		struct irq_chip *chip;
+		int ret;
+
+		chip = irq_desc_get_chip(desc);
+		if (!chip)
+			continue;
+
+		/*
+		 * First try to remove the active state. If this
+		 * fails, try to EOI the interrupt.
+		 */
+		ret = irq_set_irqchip_state(i, IRQCHIP_STATE_ACTIVE, false);
+
+		if (ret && irqd_irq_inprogress(&desc->irq_data) &&
+		    chip->irq_eoi)
+			chip->irq_eoi(&desc->irq_data);
+
+		if (chip->irq_mask)
+			chip->irq_mask(&desc->irq_data);
+
+		if (chip->irq_disable && !irqd_irq_disabled(&desc->irq_data))
+			chip->irq_disable(&desc->irq_data);
+	}
+}
+
+/*
+ * machine_crash_shutdown - Prepare to kexec after a kernel crash
+ *
+ * This function is called by crash_kexec just before machine_kexec
+ * and its goal is to shutdown non-crashing cpus and save registers.
+ */
+void
+machine_crash_shutdown(struct pt_regs *regs)
+{
+	local_irq_disable();
+
+	/* shutdown non-crashing cpus */
+	crash_smp_send_stop();
+
+	crash_save_cpu(regs, smp_processor_id());
+	machine_kexec_mask_interrupts();
+
+	pr_info("Starting crashdump kernel...\n");
+}
+
+/*
+ * machine_kexec - Jump to the loaded kimage
+ *
+ * This function is called by kernel_kexec which is called by the
+ * reboot system call when the reboot cmd is LINUX_REBOOT_CMD_KEXEC,
+ * or by crash_kernel which is called by the kernel's arch-specific
+ * trap handler in case of a kernel panic. It's the final stage of
+ * the kexec process where the pre-loaded kimage is ready to be
+ * executed. We assume at this point that all other harts are
+ * suspended and this hart will be the new boot hart.
+ */
+void __noreturn
+machine_kexec(struct kimage *image)
+{
+	struct kimage_arch *internal = &image->arch;
+	unsigned long jump_addr = (unsigned long) image->start;
+	unsigned long first_ind_entry = (unsigned long) &image->head;
+	unsigned long this_cpu_id = __smp_processor_id();
+	unsigned long this_hart_id = cpuid_to_hartid_map(this_cpu_id);
+	unsigned long fdt_addr = internal->fdt_addr;
+	void *control_code_buffer = page_address(image->control_code_page);
+	riscv_kexec_method kexec_method = NULL;
+
+#ifdef CONFIG_SMP
+	WARN(smp_crash_stop_failed(),
+		"Some CPUs may be stale, kdump will be unreliable.\n");
+#endif
+
+	if (image->type != KEXEC_TYPE_CRASH)
+		kexec_method = control_code_buffer;
+	else
+		kexec_method = (riscv_kexec_method) &riscv_kexec_norelocate;
+
+	pr_notice("Will call new kernel at %08lx from hart id %lx\n",
+		  jump_addr, this_hart_id);
+	pr_notice("FDT image at %08lx\n", fdt_addr);
+
+	/* Make sure the relocation code is visible to the hart */
+	local_flush_icache_all();
+
+	/* Jump to the relocation code */
+	pr_notice("Bye...\n");
+	kexec_method(first_ind_entry, jump_addr, fdt_addr,
+		     this_hart_id, kernel_map.va_pa_offset);
+	unreachable();
+}
diff --git a/arch/riscv/kernel/machine_kexec_file.c b/arch/riscv/kernel/machine_kexec_file.c
new file mode 100644
index 000000000..b0bf8c172
--- /dev/null
+++ b/arch/riscv/kernel/machine_kexec_file.c
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * kexec_file for riscv, use vmlinux as the dump-capture kernel image.
+ *
+ * Copyright (C) 2021 Huawei Technologies Co, Ltd.
+ *
+ * Author: Liao Chang (liaochang1@huawei.com)
+ */
+#include <linux/kexec.h>
+
+const struct kexec_file_ops * const kexec_file_loaders[] = {
+	&elf_kexec_ops,
+	NULL
+};
diff --git a/arch/riscv/kernel/mcount-dyn.S b/arch/riscv/kernel/mcount-dyn.S
new file mode 100644
index 000000000..125de818d
--- /dev/null
+++ b/arch/riscv/kernel/mcount-dyn.S
@@ -0,0 +1,191 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2017 Andes Technology Corporation */
+
+#include <linux/init.h>
+#include <linux/linkage.h>
+#include <asm/asm.h>
+#include <asm/csr.h>
+#include <asm/unistd.h>
+#include <asm/thread_info.h>
+#include <asm/asm-offsets.h>
+#include <asm-generic/export.h>
+#include <asm/ftrace.h>
+
+	.text
+
+#define FENTRY_RA_OFFSET	8
+#define ABI_SIZE_ON_STACK	80
+#define ABI_A0			0
+#define ABI_A1			8
+#define ABI_A2			16
+#define ABI_A3			24
+#define ABI_A4			32
+#define ABI_A5			40
+#define ABI_A6			48
+#define ABI_A7			56
+#define ABI_T0			64
+#define ABI_RA			72
+
+	.macro SAVE_ABI
+	addi	sp, sp, -ABI_SIZE_ON_STACK
+
+	REG_S	a0, ABI_A0(sp)
+	REG_S	a1, ABI_A1(sp)
+	REG_S	a2, ABI_A2(sp)
+	REG_S	a3, ABI_A3(sp)
+	REG_S	a4, ABI_A4(sp)
+	REG_S	a5, ABI_A5(sp)
+	REG_S	a6, ABI_A6(sp)
+	REG_S	a7, ABI_A7(sp)
+	REG_S	t0, ABI_T0(sp)
+	REG_S	ra, ABI_RA(sp)
+	.endm
+
+	.macro RESTORE_ABI
+	REG_L	a0, ABI_A0(sp)
+	REG_L	a1, ABI_A1(sp)
+	REG_L	a2, ABI_A2(sp)
+	REG_L	a3, ABI_A3(sp)
+	REG_L	a4, ABI_A4(sp)
+	REG_L	a5, ABI_A5(sp)
+	REG_L	a6, ABI_A6(sp)
+	REG_L	a7, ABI_A7(sp)
+	REG_L	t0, ABI_T0(sp)
+	REG_L	ra, ABI_RA(sp)
+
+	addi	sp, sp, ABI_SIZE_ON_STACK
+	.endm
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+	.macro SAVE_ALL
+	addi	sp, sp, -PT_SIZE_ON_STACK
+
+	REG_S t0,  PT_EPC(sp)
+	REG_S x1,  PT_RA(sp)
+	REG_S x2,  PT_SP(sp)
+	REG_S x3,  PT_GP(sp)
+	REG_S x4,  PT_TP(sp)
+	REG_S x5,  PT_T0(sp)
+	REG_S x6,  PT_T1(sp)
+	REG_S x7,  PT_T2(sp)
+	REG_S x8,  PT_S0(sp)
+	REG_S x9,  PT_S1(sp)
+	REG_S x10, PT_A0(sp)
+	REG_S x11, PT_A1(sp)
+	REG_S x12, PT_A2(sp)
+	REG_S x13, PT_A3(sp)
+	REG_S x14, PT_A4(sp)
+	REG_S x15, PT_A5(sp)
+	REG_S x16, PT_A6(sp)
+	REG_S x17, PT_A7(sp)
+	REG_S x18, PT_S2(sp)
+	REG_S x19, PT_S3(sp)
+	REG_S x20, PT_S4(sp)
+	REG_S x21, PT_S5(sp)
+	REG_S x22, PT_S6(sp)
+	REG_S x23, PT_S7(sp)
+	REG_S x24, PT_S8(sp)
+	REG_S x25, PT_S9(sp)
+	REG_S x26, PT_S10(sp)
+	REG_S x27, PT_S11(sp)
+	REG_S x28, PT_T3(sp)
+	REG_S x29, PT_T4(sp)
+	REG_S x30, PT_T5(sp)
+	REG_S x31, PT_T6(sp)
+	.endm
+
+	.macro RESTORE_ALL
+	REG_L t0,  PT_EPC(sp)
+	REG_L x1,  PT_RA(sp)
+	REG_L x2,  PT_SP(sp)
+	REG_L x3,  PT_GP(sp)
+	REG_L x4,  PT_TP(sp)
+	REG_L x6,  PT_T1(sp)
+	REG_L x7,  PT_T2(sp)
+	REG_L x8,  PT_S0(sp)
+	REG_L x9,  PT_S1(sp)
+	REG_L x10, PT_A0(sp)
+	REG_L x11, PT_A1(sp)
+	REG_L x12, PT_A2(sp)
+	REG_L x13, PT_A3(sp)
+	REG_L x14, PT_A4(sp)
+	REG_L x15, PT_A5(sp)
+	REG_L x16, PT_A6(sp)
+	REG_L x17, PT_A7(sp)
+	REG_L x18, PT_S2(sp)
+	REG_L x19, PT_S3(sp)
+	REG_L x20, PT_S4(sp)
+	REG_L x21, PT_S5(sp)
+	REG_L x22, PT_S6(sp)
+	REG_L x23, PT_S7(sp)
+	REG_L x24, PT_S8(sp)
+	REG_L x25, PT_S9(sp)
+	REG_L x26, PT_S10(sp)
+	REG_L x27, PT_S11(sp)
+	REG_L x28, PT_T3(sp)
+	REG_L x29, PT_T4(sp)
+	REG_L x30, PT_T5(sp)
+	REG_L x31, PT_T6(sp)
+
+	addi	sp, sp, PT_SIZE_ON_STACK
+	.endm
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
+
+ENTRY(ftrace_caller)
+	SAVE_ABI
+
+	addi	a0, t0, -FENTRY_RA_OFFSET
+	la	a1, function_trace_op
+	REG_L	a2, 0(a1)
+	mv	a1, ra
+	mv	a3, sp
+
+ftrace_call:
+	.global ftrace_call
+	call	ftrace_stub
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	addi	a0, sp, ABI_RA
+	REG_L	a1, ABI_T0(sp)
+	addi	a1, a1, -FENTRY_RA_OFFSET
+#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
+	mv	a2, s0
+#endif
+ftrace_graph_call:
+	.global ftrace_graph_call
+	call	ftrace_stub
+#endif
+	RESTORE_ABI
+	jr t0
+ENDPROC(ftrace_caller)
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+ENTRY(ftrace_regs_caller)
+	SAVE_ALL
+
+	addi	a0, t0, -FENTRY_RA_OFFSET
+	la	a1, function_trace_op
+	REG_L	a2, 0(a1)
+	mv	a1, ra
+	mv	a3, sp
+
+ftrace_regs_call:
+	.global ftrace_regs_call
+	call	ftrace_stub
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	addi	a0, sp, PT_RA
+	REG_L	a1, PT_EPC(sp)
+	addi	a1, a1, -FENTRY_RA_OFFSET
+#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
+	mv	a2, s0
+#endif
+ftrace_graph_regs_call:
+	.global ftrace_graph_regs_call
+	call	ftrace_stub
+#endif
+
+	RESTORE_ALL
+	jr t0
+ENDPROC(ftrace_regs_caller)
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
diff --git a/arch/riscv/kernel/mcount.S b/arch/riscv/kernel/mcount.S
new file mode 100644
index 000000000..6d462681c
--- /dev/null
+++ b/arch/riscv/kernel/mcount.S
@@ -0,0 +1,129 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2017 Andes Technology Corporation */
+
+#include <linux/init.h>
+#include <linux/linkage.h>
+#include <asm/asm.h>
+#include <asm/csr.h>
+#include <asm/unistd.h>
+#include <asm/thread_info.h>
+#include <asm/asm-offsets.h>
+#include <asm-generic/export.h>
+#include <asm/ftrace.h>
+
+	.text
+
+	.macro SAVE_ABI_STATE
+	addi	sp, sp, -16
+	sd	s0, 0(sp)
+	sd	ra, 8(sp)
+	addi	s0, sp, 16
+	.endm
+
+	/*
+	 * The call to ftrace_return_to_handler would overwrite the return
+	 * register if a0 was not saved.
+	 */
+	.macro SAVE_RET_ABI_STATE
+	addi	sp, sp, -32
+	sd	s0, 16(sp)
+	sd	ra, 24(sp)
+	sd	a0, 8(sp)
+	addi	s0, sp, 32
+	.endm
+
+	.macro RESTORE_ABI_STATE
+	ld	ra, 8(sp)
+	ld	s0, 0(sp)
+	addi	sp, sp, 16
+	.endm
+
+	.macro RESTORE_RET_ABI_STATE
+	ld	ra, 24(sp)
+	ld	s0, 16(sp)
+	ld	a0, 8(sp)
+	addi	sp, sp, 32
+	.endm
+
+ENTRY(ftrace_stub)
+#ifdef CONFIG_DYNAMIC_FTRACE
+       .global MCOUNT_NAME
+       .set    MCOUNT_NAME, ftrace_stub
+#endif
+	ret
+ENDPROC(ftrace_stub)
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ENTRY(return_to_handler)
+/*
+ * On implementing the frame point test, the ideal way is to compare the
+ * s0 (frame pointer, if enabled) on entry and the sp (stack pointer) on return.
+ * However, the psABI of variable-length-argument functions does not allow this.
+ *
+ * So alternatively we check the *old* frame pointer position, that is, the
+ * value stored in -16(s0) on entry, and the s0 on return.
+ */
+#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
+	mv	t6, s0
+#endif
+	SAVE_RET_ABI_STATE
+#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
+	mv	a0, t6
+#endif
+	call	ftrace_return_to_handler
+	mv	a1, a0
+	RESTORE_RET_ABI_STATE
+	jalr	a1
+ENDPROC(return_to_handler)
+#endif
+
+#ifndef CONFIG_DYNAMIC_FTRACE
+ENTRY(MCOUNT_NAME)
+	la	t4, ftrace_stub
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	la	t0, ftrace_graph_return
+	ld	t1, 0(t0)
+	bne	t1, t4, do_ftrace_graph_caller
+
+	la	t3, ftrace_graph_entry
+	ld	t2, 0(t3)
+	la	t6, ftrace_graph_entry_stub
+	bne	t2, t6, do_ftrace_graph_caller
+#endif
+	la	t3, ftrace_trace_function
+	ld	t5, 0(t3)
+	bne	t5, t4, do_trace
+	ret
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+/*
+ * A pseudo representation for the function graph tracer:
+ * prepare_to_return(&ra_to_caller_of_caller, ra_to_caller)
+ */
+do_ftrace_graph_caller:
+	addi	a0, s0, -8
+	mv	a1, ra
+#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
+	ld	a2, -16(s0)
+#endif
+	SAVE_ABI_STATE
+	call	prepare_ftrace_return
+	RESTORE_ABI_STATE
+	ret
+#endif
+
+/*
+ * A pseudo representation for the function tracer:
+ * (*ftrace_trace_function)(ra_to_caller, ra_to_caller_of_caller)
+ */
+do_trace:
+	ld	a1, -8(s0)
+	mv	a0, ra
+
+	SAVE_ABI_STATE
+	jalr	t5
+	RESTORE_ABI_STATE
+	ret
+ENDPROC(MCOUNT_NAME)
+#endif
+EXPORT_SYMBOL(MCOUNT_NAME)
diff --git a/arch/riscv/kernel/module-sections.c b/arch/riscv/kernel/module-sections.c
new file mode 100644
index 000000000..e264e59e5
--- /dev/null
+++ b/arch/riscv/kernel/module-sections.c
@@ -0,0 +1,159 @@
+/* SPDX-License-Identifier: GPL-2.0
+ *
+ * Copyright (C) 2014-2017 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * Copyright (C) 2018 Andes Technology Corporation <zong@andestech.com>
+ */
+
+#include <linux/elf.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/moduleloader.h>
+
+unsigned long module_emit_got_entry(struct module *mod, unsigned long val)
+{
+	struct mod_section *got_sec = &mod->arch.got;
+	int i = got_sec->num_entries;
+	struct got_entry *got = get_got_entry(val, got_sec);
+
+	if (got)
+		return (unsigned long)got;
+
+	/* There is no duplicate entry, create a new one */
+	got = (struct got_entry *)got_sec->shdr->sh_addr;
+	got[i] = emit_got_entry(val);
+
+	got_sec->num_entries++;
+	BUG_ON(got_sec->num_entries > got_sec->max_entries);
+
+	return (unsigned long)&got[i];
+}
+
+unsigned long module_emit_plt_entry(struct module *mod, unsigned long val)
+{
+	struct mod_section *got_plt_sec = &mod->arch.got_plt;
+	struct got_entry *got_plt;
+	struct mod_section *plt_sec = &mod->arch.plt;
+	struct plt_entry *plt = get_plt_entry(val, plt_sec, got_plt_sec);
+	int i = plt_sec->num_entries;
+
+	if (plt)
+		return (unsigned long)plt;
+
+	/* There is no duplicate entry, create a new one */
+	got_plt = (struct got_entry *)got_plt_sec->shdr->sh_addr;
+	got_plt[i] = emit_got_entry(val);
+	plt = (struct plt_entry *)plt_sec->shdr->sh_addr;
+	plt[i] = emit_plt_entry(val,
+				(unsigned long)&plt[i],
+				(unsigned long)&got_plt[i]);
+
+	plt_sec->num_entries++;
+	got_plt_sec->num_entries++;
+	BUG_ON(plt_sec->num_entries > plt_sec->max_entries);
+
+	return (unsigned long)&plt[i];
+}
+
+static int is_rela_equal(const Elf_Rela *x, const Elf_Rela *y)
+{
+	return x->r_info == y->r_info && x->r_addend == y->r_addend;
+}
+
+static bool duplicate_rela(const Elf_Rela *rela, int idx)
+{
+	int i;
+	for (i = 0; i < idx; i++) {
+		if (is_rela_equal(&rela[i], &rela[idx]))
+			return true;
+	}
+	return false;
+}
+
+static void count_max_entries(Elf_Rela *relas, int num,
+			      unsigned int *plts, unsigned int *gots)
+{
+	unsigned int type, i;
+
+	for (i = 0; i < num; i++) {
+		type = ELF_RISCV_R_TYPE(relas[i].r_info);
+		if (type == R_RISCV_CALL_PLT) {
+			if (!duplicate_rela(relas, i))
+				(*plts)++;
+		} else if (type == R_RISCV_GOT_HI20) {
+			if (!duplicate_rela(relas, i))
+				(*gots)++;
+		}
+	}
+}
+
+int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
+			      char *secstrings, struct module *mod)
+{
+	unsigned int num_plts = 0;
+	unsigned int num_gots = 0;
+	int i;
+
+	/*
+	 * Find the empty .got and .plt sections.
+	 */
+	for (i = 0; i < ehdr->e_shnum; i++) {
+		if (!strcmp(secstrings + sechdrs[i].sh_name, ".plt"))
+			mod->arch.plt.shdr = sechdrs + i;
+		else if (!strcmp(secstrings + sechdrs[i].sh_name, ".got"))
+			mod->arch.got.shdr = sechdrs + i;
+		else if (!strcmp(secstrings + sechdrs[i].sh_name, ".got.plt"))
+			mod->arch.got_plt.shdr = sechdrs + i;
+	}
+
+	if (!mod->arch.plt.shdr) {
+		pr_err("%s: module PLT section(s) missing\n", mod->name);
+		return -ENOEXEC;
+	}
+	if (!mod->arch.got.shdr) {
+		pr_err("%s: module GOT section(s) missing\n", mod->name);
+		return -ENOEXEC;
+	}
+	if (!mod->arch.got_plt.shdr) {
+		pr_err("%s: module GOT.PLT section(s) missing\n", mod->name);
+		return -ENOEXEC;
+	}
+
+	/* Calculate the maxinum number of entries */
+	for (i = 0; i < ehdr->e_shnum; i++) {
+		Elf_Rela *relas = (void *)ehdr + sechdrs[i].sh_offset;
+		int num_rela = sechdrs[i].sh_size / sizeof(Elf_Rela);
+		Elf_Shdr *dst_sec = sechdrs + sechdrs[i].sh_info;
+
+		if (sechdrs[i].sh_type != SHT_RELA)
+			continue;
+
+		/* ignore relocations that operate on non-exec sections */
+		if (!(dst_sec->sh_flags & SHF_EXECINSTR))
+			continue;
+
+		count_max_entries(relas, num_rela, &num_plts, &num_gots);
+	}
+
+	mod->arch.plt.shdr->sh_type = SHT_NOBITS;
+	mod->arch.plt.shdr->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
+	mod->arch.plt.shdr->sh_addralign = L1_CACHE_BYTES;
+	mod->arch.plt.shdr->sh_size = (num_plts + 1) * sizeof(struct plt_entry);
+	mod->arch.plt.num_entries = 0;
+	mod->arch.plt.max_entries = num_plts;
+
+	mod->arch.got.shdr->sh_type = SHT_NOBITS;
+	mod->arch.got.shdr->sh_flags = SHF_ALLOC;
+	mod->arch.got.shdr->sh_addralign = L1_CACHE_BYTES;
+	mod->arch.got.shdr->sh_size = (num_gots + 1) * sizeof(struct got_entry);
+	mod->arch.got.num_entries = 0;
+	mod->arch.got.max_entries = num_gots;
+
+	mod->arch.got_plt.shdr->sh_type = SHT_NOBITS;
+	mod->arch.got_plt.shdr->sh_flags = SHF_ALLOC;
+	mod->arch.got_plt.shdr->sh_addralign = L1_CACHE_BYTES;
+	mod->arch.got_plt.shdr->sh_size = (num_plts + 1) * sizeof(struct got_entry);
+	mod->arch.got_plt.num_entries = 0;
+	mod->arch.got_plt.max_entries = num_plts;
+	return 0;
+}
diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c
new file mode 100644
index 000000000..a331001e3
--- /dev/null
+++ b/arch/riscv/kernel/module.c
@@ -0,0 +1,459 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ *
+ *  Copyright (C) 2017 Zihao Yu
+ */
+
+#include <linux/elf.h>
+#include <linux/err.h>
+#include <linux/errno.h>
+#include <linux/moduleloader.h>
+#include <linux/vmalloc.h>
+#include <linux/sizes.h>
+#include <linux/pgtable.h>
+#include <asm/alternative.h>
+#include <asm/sections.h>
+
+/*
+ * The auipc+jalr instruction pair can reach any PC-relative offset
+ * in the range [-2^31 - 2^11, 2^31 - 2^11)
+ */
+static bool riscv_insn_valid_32bit_offset(ptrdiff_t val)
+{
+#ifdef CONFIG_32BIT
+	return true;
+#else
+	return (-(1L << 31) - (1L << 11)) <= val && val < ((1L << 31) - (1L << 11));
+#endif
+}
+
+static int apply_r_riscv_32_rela(struct module *me, u32 *location, Elf_Addr v)
+{
+	if (v != (u32)v) {
+		pr_err("%s: value %016llx out of range for 32-bit field\n",
+		       me->name, (long long)v);
+		return -EINVAL;
+	}
+	*location = v;
+	return 0;
+}
+
+static int apply_r_riscv_64_rela(struct module *me, u32 *location, Elf_Addr v)
+{
+	*(u64 *)location = v;
+	return 0;
+}
+
+static int apply_r_riscv_branch_rela(struct module *me, u32 *location,
+				     Elf_Addr v)
+{
+	ptrdiff_t offset = (void *)v - (void *)location;
+	u32 imm12 = (offset & 0x1000) << (31 - 12);
+	u32 imm11 = (offset & 0x800) >> (11 - 7);
+	u32 imm10_5 = (offset & 0x7e0) << (30 - 10);
+	u32 imm4_1 = (offset & 0x1e) << (11 - 4);
+
+	*location = (*location & 0x1fff07f) | imm12 | imm11 | imm10_5 | imm4_1;
+	return 0;
+}
+
+static int apply_r_riscv_jal_rela(struct module *me, u32 *location,
+				  Elf_Addr v)
+{
+	ptrdiff_t offset = (void *)v - (void *)location;
+	u32 imm20 = (offset & 0x100000) << (31 - 20);
+	u32 imm19_12 = (offset & 0xff000);
+	u32 imm11 = (offset & 0x800) << (20 - 11);
+	u32 imm10_1 = (offset & 0x7fe) << (30 - 10);
+
+	*location = (*location & 0xfff) | imm20 | imm19_12 | imm11 | imm10_1;
+	return 0;
+}
+
+static int apply_r_riscv_rvc_branch_rela(struct module *me, u32 *location,
+					 Elf_Addr v)
+{
+	ptrdiff_t offset = (void *)v - (void *)location;
+	u16 imm8 = (offset & 0x100) << (12 - 8);
+	u16 imm7_6 = (offset & 0xc0) >> (6 - 5);
+	u16 imm5 = (offset & 0x20) >> (5 - 2);
+	u16 imm4_3 = (offset & 0x18) << (12 - 5);
+	u16 imm2_1 = (offset & 0x6) << (12 - 10);
+
+	*(u16 *)location = (*(u16 *)location & 0xe383) |
+		    imm8 | imm7_6 | imm5 | imm4_3 | imm2_1;
+	return 0;
+}
+
+static int apply_r_riscv_rvc_jump_rela(struct module *me, u32 *location,
+				       Elf_Addr v)
+{
+	ptrdiff_t offset = (void *)v - (void *)location;
+	u16 imm11 = (offset & 0x800) << (12 - 11);
+	u16 imm10 = (offset & 0x400) >> (10 - 8);
+	u16 imm9_8 = (offset & 0x300) << (12 - 11);
+	u16 imm7 = (offset & 0x80) >> (7 - 6);
+	u16 imm6 = (offset & 0x40) << (12 - 11);
+	u16 imm5 = (offset & 0x20) >> (5 - 2);
+	u16 imm4 = (offset & 0x10) << (12 - 5);
+	u16 imm3_1 = (offset & 0xe) << (12 - 10);
+
+	*(u16 *)location = (*(u16 *)location & 0xe003) |
+		    imm11 | imm10 | imm9_8 | imm7 | imm6 | imm5 | imm4 | imm3_1;
+	return 0;
+}
+
+static int apply_r_riscv_pcrel_hi20_rela(struct module *me, u32 *location,
+					 Elf_Addr v)
+{
+	ptrdiff_t offset = (void *)v - (void *)location;
+	s32 hi20;
+
+	if (!riscv_insn_valid_32bit_offset(offset)) {
+		pr_err(
+		  "%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n",
+		  me->name, (long long)v, location);
+		return -EINVAL;
+	}
+
+	hi20 = (offset + 0x800) & 0xfffff000;
+	*location = (*location & 0xfff) | hi20;
+	return 0;
+}
+
+static int apply_r_riscv_pcrel_lo12_i_rela(struct module *me, u32 *location,
+					   Elf_Addr v)
+{
+	/*
+	 * v is the lo12 value to fill. It is calculated before calling this
+	 * handler.
+	 */
+	*location = (*location & 0xfffff) | ((v & 0xfff) << 20);
+	return 0;
+}
+
+static int apply_r_riscv_pcrel_lo12_s_rela(struct module *me, u32 *location,
+					   Elf_Addr v)
+{
+	/*
+	 * v is the lo12 value to fill. It is calculated before calling this
+	 * handler.
+	 */
+	u32 imm11_5 = (v & 0xfe0) << (31 - 11);
+	u32 imm4_0 = (v & 0x1f) << (11 - 4);
+
+	*location = (*location & 0x1fff07f) | imm11_5 | imm4_0;
+	return 0;
+}
+
+static int apply_r_riscv_hi20_rela(struct module *me, u32 *location,
+				   Elf_Addr v)
+{
+	s32 hi20;
+
+	if (IS_ENABLED(CONFIG_CMODEL_MEDLOW)) {
+		pr_err(
+		  "%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n",
+		  me->name, (long long)v, location);
+		return -EINVAL;
+	}
+
+	hi20 = ((s32)v + 0x800) & 0xfffff000;
+	*location = (*location & 0xfff) | hi20;
+	return 0;
+}
+
+static int apply_r_riscv_lo12_i_rela(struct module *me, u32 *location,
+				     Elf_Addr v)
+{
+	/* Skip medlow checking because of filtering by HI20 already */
+	s32 hi20 = ((s32)v + 0x800) & 0xfffff000;
+	s32 lo12 = ((s32)v - hi20);
+	*location = (*location & 0xfffff) | ((lo12 & 0xfff) << 20);
+	return 0;
+}
+
+static int apply_r_riscv_lo12_s_rela(struct module *me, u32 *location,
+				     Elf_Addr v)
+{
+	/* Skip medlow checking because of filtering by HI20 already */
+	s32 hi20 = ((s32)v + 0x800) & 0xfffff000;
+	s32 lo12 = ((s32)v - hi20);
+	u32 imm11_5 = (lo12 & 0xfe0) << (31 - 11);
+	u32 imm4_0 = (lo12 & 0x1f) << (11 - 4);
+	*location = (*location & 0x1fff07f) | imm11_5 | imm4_0;
+	return 0;
+}
+
+static int apply_r_riscv_got_hi20_rela(struct module *me, u32 *location,
+				       Elf_Addr v)
+{
+	ptrdiff_t offset = (void *)v - (void *)location;
+	s32 hi20;
+
+	/* Always emit the got entry */
+	if (IS_ENABLED(CONFIG_MODULE_SECTIONS)) {
+		offset = module_emit_got_entry(me, v);
+		offset = (void *)offset - (void *)location;
+	} else {
+		pr_err(
+		  "%s: can not generate the GOT entry for symbol = %016llx from PC = %p\n",
+		  me->name, (long long)v, location);
+		return -EINVAL;
+	}
+
+	hi20 = (offset + 0x800) & 0xfffff000;
+	*location = (*location & 0xfff) | hi20;
+	return 0;
+}
+
+static int apply_r_riscv_call_plt_rela(struct module *me, u32 *location,
+				       Elf_Addr v)
+{
+	ptrdiff_t offset = (void *)v - (void *)location;
+	u32 hi20, lo12;
+
+	if (!riscv_insn_valid_32bit_offset(offset)) {
+		/* Only emit the plt entry if offset over 32-bit range */
+		if (IS_ENABLED(CONFIG_MODULE_SECTIONS)) {
+			offset = module_emit_plt_entry(me, v);
+			offset = (void *)offset - (void *)location;
+		} else {
+			pr_err(
+			  "%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n",
+			  me->name, (long long)v, location);
+			return -EINVAL;
+		}
+	}
+
+	hi20 = (offset + 0x800) & 0xfffff000;
+	lo12 = (offset - hi20) & 0xfff;
+	*location = (*location & 0xfff) | hi20;
+	*(location + 1) = (*(location + 1) & 0xfffff) | (lo12 << 20);
+	return 0;
+}
+
+static int apply_r_riscv_call_rela(struct module *me, u32 *location,
+				   Elf_Addr v)
+{
+	ptrdiff_t offset = (void *)v - (void *)location;
+	u32 hi20, lo12;
+
+	if (!riscv_insn_valid_32bit_offset(offset)) {
+		pr_err(
+		  "%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n",
+		  me->name, (long long)v, location);
+		return -EINVAL;
+	}
+
+	hi20 = (offset + 0x800) & 0xfffff000;
+	lo12 = (offset - hi20) & 0xfff;
+	*location = (*location & 0xfff) | hi20;
+	*(location + 1) = (*(location + 1) & 0xfffff) | (lo12 << 20);
+	return 0;
+}
+
+static int apply_r_riscv_relax_rela(struct module *me, u32 *location,
+				    Elf_Addr v)
+{
+	return 0;
+}
+
+static int apply_r_riscv_align_rela(struct module *me, u32 *location,
+				    Elf_Addr v)
+{
+	pr_err(
+	  "%s: The unexpected relocation type 'R_RISCV_ALIGN' from PC = %p\n",
+	  me->name, location);
+	return -EINVAL;
+}
+
+static int apply_r_riscv_add32_rela(struct module *me, u32 *location,
+				    Elf_Addr v)
+{
+	*(u32 *)location += (u32)v;
+	return 0;
+}
+
+static int apply_r_riscv_add64_rela(struct module *me, u32 *location,
+				    Elf_Addr v)
+{
+	*(u64 *)location += (u64)v;
+	return 0;
+}
+
+static int apply_r_riscv_sub32_rela(struct module *me, u32 *location,
+				    Elf_Addr v)
+{
+	*(u32 *)location -= (u32)v;
+	return 0;
+}
+
+static int apply_r_riscv_sub64_rela(struct module *me, u32 *location,
+				    Elf_Addr v)
+{
+	*(u64 *)location -= (u64)v;
+	return 0;
+}
+
+static int (*reloc_handlers_rela[]) (struct module *me, u32 *location,
+				Elf_Addr v) = {
+	[R_RISCV_32]			= apply_r_riscv_32_rela,
+	[R_RISCV_64]			= apply_r_riscv_64_rela,
+	[R_RISCV_BRANCH]		= apply_r_riscv_branch_rela,
+	[R_RISCV_JAL]			= apply_r_riscv_jal_rela,
+	[R_RISCV_RVC_BRANCH]		= apply_r_riscv_rvc_branch_rela,
+	[R_RISCV_RVC_JUMP]		= apply_r_riscv_rvc_jump_rela,
+	[R_RISCV_PCREL_HI20]		= apply_r_riscv_pcrel_hi20_rela,
+	[R_RISCV_PCREL_LO12_I]		= apply_r_riscv_pcrel_lo12_i_rela,
+	[R_RISCV_PCREL_LO12_S]		= apply_r_riscv_pcrel_lo12_s_rela,
+	[R_RISCV_HI20]			= apply_r_riscv_hi20_rela,
+	[R_RISCV_LO12_I]		= apply_r_riscv_lo12_i_rela,
+	[R_RISCV_LO12_S]		= apply_r_riscv_lo12_s_rela,
+	[R_RISCV_GOT_HI20]		= apply_r_riscv_got_hi20_rela,
+	[R_RISCV_CALL_PLT]		= apply_r_riscv_call_plt_rela,
+	[R_RISCV_CALL]			= apply_r_riscv_call_rela,
+	[R_RISCV_RELAX]			= apply_r_riscv_relax_rela,
+	[R_RISCV_ALIGN]			= apply_r_riscv_align_rela,
+	[R_RISCV_ADD32]			= apply_r_riscv_add32_rela,
+	[R_RISCV_ADD64]			= apply_r_riscv_add64_rela,
+	[R_RISCV_SUB32]			= apply_r_riscv_sub32_rela,
+	[R_RISCV_SUB64]			= apply_r_riscv_sub64_rela,
+};
+
+int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
+		       unsigned int symindex, unsigned int relsec,
+		       struct module *me)
+{
+	Elf_Rela *rel = (void *) sechdrs[relsec].sh_addr;
+	int (*handler)(struct module *me, u32 *location, Elf_Addr v);
+	Elf_Sym *sym;
+	u32 *location;
+	unsigned int i, type;
+	Elf_Addr v;
+	int res;
+
+	pr_debug("Applying relocate section %u to %u\n", relsec,
+	       sechdrs[relsec].sh_info);
+
+	for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rel); i++) {
+		/* This is where to make the change */
+		location = (void *)sechdrs[sechdrs[relsec].sh_info].sh_addr
+			+ rel[i].r_offset;
+		/* This is the symbol it is referring to */
+		sym = (Elf_Sym *)sechdrs[symindex].sh_addr
+			+ ELF_RISCV_R_SYM(rel[i].r_info);
+		if (IS_ERR_VALUE(sym->st_value)) {
+			/* Ignore unresolved weak symbol */
+			if (ELF_ST_BIND(sym->st_info) == STB_WEAK)
+				continue;
+			pr_warn("%s: Unknown symbol %s\n",
+				me->name, strtab + sym->st_name);
+			return -ENOENT;
+		}
+
+		type = ELF_RISCV_R_TYPE(rel[i].r_info);
+
+		if (type < ARRAY_SIZE(reloc_handlers_rela))
+			handler = reloc_handlers_rela[type];
+		else
+			handler = NULL;
+
+		if (!handler) {
+			pr_err("%s: Unknown relocation type %u\n",
+			       me->name, type);
+			return -EINVAL;
+		}
+
+		v = sym->st_value + rel[i].r_addend;
+
+		if (type == R_RISCV_PCREL_LO12_I || type == R_RISCV_PCREL_LO12_S) {
+			unsigned int j;
+
+			for (j = 0; j < sechdrs[relsec].sh_size / sizeof(*rel); j++) {
+				unsigned long hi20_loc =
+					sechdrs[sechdrs[relsec].sh_info].sh_addr
+					+ rel[j].r_offset;
+				u32 hi20_type = ELF_RISCV_R_TYPE(rel[j].r_info);
+
+				/* Find the corresponding HI20 relocation entry */
+				if (hi20_loc == sym->st_value
+				    && (hi20_type == R_RISCV_PCREL_HI20
+					|| hi20_type == R_RISCV_GOT_HI20)) {
+					s32 hi20, lo12;
+					Elf_Sym *hi20_sym =
+						(Elf_Sym *)sechdrs[symindex].sh_addr
+						+ ELF_RISCV_R_SYM(rel[j].r_info);
+					unsigned long hi20_sym_val =
+						hi20_sym->st_value
+						+ rel[j].r_addend;
+
+					/* Calculate lo12 */
+					size_t offset = hi20_sym_val - hi20_loc;
+					if (IS_ENABLED(CONFIG_MODULE_SECTIONS)
+					    && hi20_type == R_RISCV_GOT_HI20) {
+						offset = module_emit_got_entry(
+							 me, hi20_sym_val);
+						offset = offset - hi20_loc;
+					}
+					hi20 = (offset + 0x800) & 0xfffff000;
+					lo12 = offset - hi20;
+					v = lo12;
+
+					break;
+				}
+			}
+			if (j == sechdrs[relsec].sh_size / sizeof(*rel)) {
+				pr_err(
+				  "%s: Can not find HI20 relocation information\n",
+				  me->name);
+				return -EINVAL;
+			}
+		}
+
+		res = handler(me, location, v);
+		if (res)
+			return res;
+	}
+
+	return 0;
+}
+
+#if defined(CONFIG_MMU) && defined(CONFIG_64BIT)
+void *module_alloc(unsigned long size)
+{
+	return __vmalloc_node_range(size, 1, MODULES_VADDR,
+				    MODULES_END, GFP_KERNEL,
+				    PAGE_KERNEL, VM_FLUSH_RESET_PERMS,
+				    NUMA_NO_NODE,
+				    __builtin_return_address(0));
+}
+#endif
+
+static const Elf_Shdr *find_section(const Elf_Ehdr *hdr,
+				    const Elf_Shdr *sechdrs,
+				    const char *name)
+{
+	const Elf_Shdr *s, *se;
+	const char *secstrs = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
+
+	for (s = sechdrs, se = sechdrs + hdr->e_shnum; s < se; s++) {
+		if (strcmp(name, secstrs + s->sh_name) == 0)
+			return s;
+	}
+
+	return NULL;
+}
+
+int module_finalize(const Elf_Ehdr *hdr,
+		    const Elf_Shdr *sechdrs,
+		    struct module *me)
+{
+	const Elf_Shdr *s;
+
+	s = find_section(hdr, sechdrs, ".alternative");
+	if (s)
+		apply_module_alternatives((void *)s->sh_addr, s->sh_size);
+
+	return 0;
+}
diff --git a/arch/riscv/kernel/patch.c b/arch/riscv/kernel/patch.c
new file mode 100644
index 000000000..160e5c1ca
--- /dev/null
+++ b/arch/riscv/kernel/patch.c
@@ -0,0 +1,164 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020 SiFive
+ */
+
+#include <linux/spinlock.h>
+#include <linux/mm.h>
+#include <linux/memory.h>
+#include <linux/uaccess.h>
+#include <linux/stop_machine.h>
+#include <asm/kprobes.h>
+#include <asm/cacheflush.h>
+#include <asm/fixmap.h>
+#include <asm/ftrace.h>
+#include <asm/patch.h>
+#include <asm/sections.h>
+
+struct patch_insn {
+	void *addr;
+	u32 insn;
+	atomic_t cpu_count;
+};
+
+int riscv_patch_in_stop_machine = false;
+
+#ifdef CONFIG_MMU
+
+static inline bool is_kernel_exittext(uintptr_t addr)
+{
+	return system_state < SYSTEM_RUNNING &&
+		addr >= (uintptr_t)__exittext_begin &&
+		addr < (uintptr_t)__exittext_end;
+}
+
+/*
+ * The fix_to_virt(, idx) needs a const value (not a dynamic variable of
+ * reg-a0) or BUILD_BUG_ON failed with "idx >= __end_of_fixed_addresses".
+ * So use '__always_inline' and 'const unsigned int fixmap' here.
+ */
+static __always_inline void *patch_map(void *addr, const unsigned int fixmap)
+{
+	uintptr_t uintaddr = (uintptr_t) addr;
+	struct page *page;
+
+	if (core_kernel_text(uintaddr) || is_kernel_exittext(uintaddr))
+		page = phys_to_page(__pa_symbol(addr));
+	else if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX))
+		page = vmalloc_to_page(addr);
+	else
+		return addr;
+
+	BUG_ON(!page);
+
+	return (void *)set_fixmap_offset(fixmap, page_to_phys(page) +
+					 (uintaddr & ~PAGE_MASK));
+}
+
+static void patch_unmap(int fixmap)
+{
+	clear_fixmap(fixmap);
+}
+NOKPROBE_SYMBOL(patch_unmap);
+
+static int patch_insn_write(void *addr, const void *insn, size_t len)
+{
+	void *waddr = addr;
+	bool across_pages = (((uintptr_t) addr & ~PAGE_MASK) + len) > PAGE_SIZE;
+	int ret;
+
+	/*
+	 * Before reaching here, it was expected to lock the text_mutex
+	 * already, so we don't need to give another lock here and could
+	 * ensure that it was safe between each cores.
+	 *
+	 * We're currently using stop_machine() for ftrace & kprobes, and while
+	 * that ensures text_mutex is held before installing the mappings it
+	 * does not ensure text_mutex is held by the calling thread.  That's
+	 * safe but triggers a lockdep failure, so just elide it for that
+	 * specific case.
+	 */
+	if (!riscv_patch_in_stop_machine)
+		lockdep_assert_held(&text_mutex);
+
+	if (across_pages)
+		patch_map(addr + len, FIX_TEXT_POKE1);
+
+	waddr = patch_map(addr, FIX_TEXT_POKE0);
+
+	ret = copy_to_kernel_nofault(waddr, insn, len);
+
+	patch_unmap(FIX_TEXT_POKE0);
+
+	if (across_pages)
+		patch_unmap(FIX_TEXT_POKE1);
+
+	return ret;
+}
+NOKPROBE_SYMBOL(patch_insn_write);
+#else
+static int patch_insn_write(void *addr, const void *insn, size_t len)
+{
+	return copy_to_kernel_nofault(addr, insn, len);
+}
+NOKPROBE_SYMBOL(patch_insn_write);
+#endif /* CONFIG_MMU */
+
+int patch_text_nosync(void *addr, const void *insns, size_t len)
+{
+	u32 *tp = addr;
+	int ret;
+
+	ret = patch_insn_write(tp, insns, len);
+
+	if (!ret)
+		flush_icache_range((uintptr_t) tp, (uintptr_t) tp + len);
+
+	return ret;
+}
+NOKPROBE_SYMBOL(patch_text_nosync);
+
+static int patch_text_cb(void *data)
+{
+	struct patch_insn *patch = data;
+	int ret = 0;
+
+	if (atomic_inc_return(&patch->cpu_count) == num_online_cpus()) {
+		ret =
+		    patch_text_nosync(patch->addr, &patch->insn,
+					    GET_INSN_LENGTH(patch->insn));
+		atomic_inc(&patch->cpu_count);
+	} else {
+		while (atomic_read(&patch->cpu_count) <= num_online_cpus())
+			cpu_relax();
+		smp_mb();
+	}
+
+	return ret;
+}
+NOKPROBE_SYMBOL(patch_text_cb);
+
+int patch_text(void *addr, u32 insn)
+{
+	int ret;
+	struct patch_insn patch = {
+		.addr = addr,
+		.insn = insn,
+		.cpu_count = ATOMIC_INIT(0),
+	};
+
+	/*
+	 * kprobes takes text_mutex, before calling patch_text(), but as we call
+	 * calls stop_machine(), the lockdep assertion in patch_insn_write()
+	 * gets confused by the context in which the lock is taken.
+	 * Instead, ensure the lock is held before calling stop_machine(), and
+	 * set riscv_patch_in_stop_machine to skip the check in
+	 * patch_insn_write().
+	 */
+	lockdep_assert_held(&text_mutex);
+	riscv_patch_in_stop_machine = true;
+	ret = stop_machine_cpuslocked(patch_text_cb, &patch, cpu_online_mask);
+	riscv_patch_in_stop_machine = false;
+	return ret;
+}
+NOKPROBE_SYMBOL(patch_text);
diff --git a/arch/riscv/kernel/perf_callchain.c b/arch/riscv/kernel/perf_callchain.c
new file mode 100644
index 000000000..3348a61de
--- /dev/null
+++ b/arch/riscv/kernel/perf_callchain.c
@@ -0,0 +1,78 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd. */
+
+#include <linux/perf_event.h>
+#include <linux/uaccess.h>
+
+#include <asm/stacktrace.h>
+
+/*
+ * Get the return address for a single stackframe and return a pointer to the
+ * next frame tail.
+ */
+static unsigned long user_backtrace(struct perf_callchain_entry_ctx *entry,
+				    unsigned long fp, unsigned long reg_ra)
+{
+	struct stackframe buftail;
+	unsigned long ra = 0;
+	unsigned long __user *user_frame_tail =
+		(unsigned long __user *)(fp - sizeof(struct stackframe));
+
+	/* Check accessibility of one struct frame_tail beyond */
+	if (!access_ok(user_frame_tail, sizeof(buftail)))
+		return 0;
+	if (__copy_from_user_inatomic(&buftail, user_frame_tail,
+				      sizeof(buftail)))
+		return 0;
+
+	if (reg_ra != 0)
+		ra = reg_ra;
+	else
+		ra = buftail.ra;
+
+	fp = buftail.fp;
+	if (ra != 0)
+		perf_callchain_store(entry, ra);
+	else
+		return 0;
+
+	return fp;
+}
+
+/*
+ * This will be called when the target is in user mode
+ * This function will only be called when we use
+ * "PERF_SAMPLE_CALLCHAIN" in
+ * kernel/events/core.c:perf_prepare_sample()
+ *
+ * How to trigger perf_callchain_[user/kernel] :
+ * $ perf record -e cpu-clock --call-graph fp ./program
+ * $ perf report --call-graph
+ *
+ * On RISC-V platform, the program being sampled and the C library
+ * need to be compiled with -fno-omit-frame-pointer, otherwise
+ * the user stack will not contain function frame.
+ */
+void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
+			 struct pt_regs *regs)
+{
+	unsigned long fp = 0;
+
+	fp = regs->s0;
+	perf_callchain_store(entry, regs->epc);
+
+	fp = user_backtrace(entry, fp, regs->ra);
+	while (fp && !(fp & 0x3) && entry->nr < entry->max_stack)
+		fp = user_backtrace(entry, fp, 0);
+}
+
+static bool fill_callchain(void *entry, unsigned long pc)
+{
+	return perf_callchain_store(entry, pc) == 0;
+}
+
+void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
+			   struct pt_regs *regs)
+{
+	walk_stackframe(NULL, regs, fill_callchain, entry);
+}
diff --git a/arch/riscv/kernel/perf_regs.c b/arch/riscv/kernel/perf_regs.c
new file mode 100644
index 000000000..fd304a248
--- /dev/null
+++ b/arch/riscv/kernel/perf_regs.c
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd. */
+
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/perf_event.h>
+#include <linux/bug.h>
+#include <asm/perf_regs.h>
+#include <asm/ptrace.h>
+
+u64 perf_reg_value(struct pt_regs *regs, int idx)
+{
+	if (WARN_ON_ONCE((u32)idx >= PERF_REG_RISCV_MAX))
+		return 0;
+
+	return ((unsigned long *)regs)[idx];
+}
+
+#define REG_RESERVED (~((1ULL << PERF_REG_RISCV_MAX) - 1))
+
+int perf_reg_validate(u64 mask)
+{
+	if (!mask || mask & REG_RESERVED)
+		return -EINVAL;
+
+	return 0;
+}
+
+u64 perf_reg_abi(struct task_struct *task)
+{
+#if __riscv_xlen == 64
+	return PERF_SAMPLE_REGS_ABI_64;
+#else
+	return PERF_SAMPLE_REGS_ABI_32;
+#endif
+}
+
+void perf_get_regs_user(struct perf_regs *regs_user,
+			struct pt_regs *regs)
+{
+	regs_user->regs = task_pt_regs(current);
+	regs_user->abi = perf_reg_abi(current);
+}
diff --git a/arch/riscv/kernel/probes/Makefile b/arch/riscv/kernel/probes/Makefile
new file mode 100644
index 000000000..90dea3abd
--- /dev/null
+++ b/arch/riscv/kernel/probes/Makefile
@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_KPROBES)		+= kprobes.o decode-insn.o simulate-insn.o
+obj-$(CONFIG_KPROBES)		+= kprobes_trampoline.o
+obj-$(CONFIG_KPROBES_ON_FTRACE)	+= ftrace.o
+obj-$(CONFIG_UPROBES)		+= uprobes.o decode-insn.o simulate-insn.o
+CFLAGS_REMOVE_simulate-insn.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_rethook.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_rethook_trampoline.o = $(CC_FLAGS_FTRACE)
diff --git a/arch/riscv/kernel/probes/decode-insn.c b/arch/riscv/kernel/probes/decode-insn.c
new file mode 100644
index 000000000..64f6183b4
--- /dev/null
+++ b/arch/riscv/kernel/probes/decode-insn.c
@@ -0,0 +1,47 @@
+// SPDX-License-Identifier: GPL-2.0+
+
+#include <linux/kernel.h>
+#include <linux/kprobes.h>
+#include <linux/module.h>
+#include <linux/kallsyms.h>
+#include <asm/sections.h>
+
+#include "decode-insn.h"
+#include "simulate-insn.h"
+
+/* Return:
+ *   INSN_REJECTED     If instruction is one not allowed to kprobe,
+ *   INSN_GOOD_NO_SLOT If instruction is supported but doesn't use its slot.
+ */
+enum probe_insn __kprobes
+riscv_probe_decode_insn(probe_opcode_t *addr, struct arch_probe_insn *api)
+{
+	probe_opcode_t insn = *addr;
+
+	/*
+	 * Reject instructions list:
+	 */
+	RISCV_INSN_REJECTED(system,		insn);
+	RISCV_INSN_REJECTED(fence,		insn);
+
+	/*
+	 * Simulate instructions list:
+	 * TODO: the REJECTED ones below need to be implemented
+	 */
+#ifdef CONFIG_RISCV_ISA_C
+	RISCV_INSN_REJECTED(c_j,		insn);
+	RISCV_INSN_REJECTED(c_jr,		insn);
+	RISCV_INSN_REJECTED(c_jal,		insn);
+	RISCV_INSN_REJECTED(c_jalr,		insn);
+	RISCV_INSN_REJECTED(c_beqz,		insn);
+	RISCV_INSN_REJECTED(c_bnez,		insn);
+	RISCV_INSN_REJECTED(c_ebreak,		insn);
+#endif
+
+	RISCV_INSN_SET_SIMULATE(jal,		insn);
+	RISCV_INSN_SET_SIMULATE(jalr,		insn);
+	RISCV_INSN_SET_SIMULATE(auipc,		insn);
+	RISCV_INSN_SET_SIMULATE(branch,		insn);
+
+	return INSN_GOOD;
+}
diff --git a/arch/riscv/kernel/probes/decode-insn.h b/arch/riscv/kernel/probes/decode-insn.h
new file mode 100644
index 000000000..42269a7d6
--- /dev/null
+++ b/arch/riscv/kernel/probes/decode-insn.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+
+#ifndef _RISCV_KERNEL_KPROBES_DECODE_INSN_H
+#define _RISCV_KERNEL_KPROBES_DECODE_INSN_H
+
+#include <asm/sections.h>
+#include <asm/kprobes.h>
+
+enum probe_insn {
+	INSN_REJECTED,
+	INSN_GOOD_NO_SLOT,
+	INSN_GOOD,
+};
+
+enum probe_insn __kprobes
+riscv_probe_decode_insn(probe_opcode_t *addr, struct arch_probe_insn *asi);
+
+#endif /* _RISCV_KERNEL_KPROBES_DECODE_INSN_H */
diff --git a/arch/riscv/kernel/probes/ftrace.c b/arch/riscv/kernel/probes/ftrace.c
new file mode 100644
index 000000000..7142ec42e
--- /dev/null
+++ b/arch/riscv/kernel/probes/ftrace.c
@@ -0,0 +1,62 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/kprobes.h>
+
+/* Ftrace callback handler for kprobes -- called under preepmt disabled */
+void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
+			   struct ftrace_ops *ops, struct ftrace_regs *fregs)
+{
+	struct kprobe *p;
+	struct pt_regs *regs;
+	struct kprobe_ctlblk *kcb;
+	int bit;
+
+	bit = ftrace_test_recursion_trylock(ip, parent_ip);
+	if (bit < 0)
+		return;
+
+	p = get_kprobe((kprobe_opcode_t *)ip);
+	if (unlikely(!p) || kprobe_disabled(p))
+		goto out;
+
+	regs = ftrace_get_regs(fregs);
+	kcb = get_kprobe_ctlblk();
+	if (kprobe_running()) {
+		kprobes_inc_nmissed_count(p);
+	} else {
+		unsigned long orig_ip = instruction_pointer(regs);
+
+		instruction_pointer_set(regs, ip);
+
+		__this_cpu_write(current_kprobe, p);
+		kcb->kprobe_status = KPROBE_HIT_ACTIVE;
+		if (!p->pre_handler || !p->pre_handler(p, regs)) {
+			/*
+			 * Emulate singlestep (and also recover regs->pc)
+			 * as if there is a nop
+			 */
+			instruction_pointer_set(regs,
+				(unsigned long)p->addr + MCOUNT_INSN_SIZE);
+			if (unlikely(p->post_handler)) {
+				kcb->kprobe_status = KPROBE_HIT_SSDONE;
+				p->post_handler(p, regs, 0);
+			}
+			instruction_pointer_set(regs, orig_ip);
+		}
+
+		/*
+		 * If pre_handler returns !0, it changes regs->pc. We have to
+		 * skip emulating post_handler.
+		 */
+		__this_cpu_write(current_kprobe, NULL);
+	}
+out:
+	ftrace_test_recursion_unlock(bit);
+}
+NOKPROBE_SYMBOL(kprobe_ftrace_handler);
+
+int arch_prepare_kprobe_ftrace(struct kprobe *p)
+{
+	p->ainsn.api.insn = NULL;
+	return 0;
+}
diff --git a/arch/riscv/kernel/probes/kprobes.c b/arch/riscv/kernel/probes/kprobes.c
new file mode 100644
index 000000000..cca2b3a21
--- /dev/null
+++ b/arch/riscv/kernel/probes/kprobes.c
@@ -0,0 +1,389 @@
+// SPDX-License-Identifier: GPL-2.0+
+
+#define pr_fmt(fmt) "kprobes: " fmt
+
+#include <linux/kprobes.h>
+#include <linux/extable.h>
+#include <linux/slab.h>
+#include <linux/stop_machine.h>
+#include <asm/ptrace.h>
+#include <linux/uaccess.h>
+#include <asm/sections.h>
+#include <asm/cacheflush.h>
+#include <asm/bug.h>
+#include <asm/patch.h>
+
+#include "decode-insn.h"
+
+DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
+DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
+
+static void __kprobes
+post_kprobe_handler(struct kprobe *, struct kprobe_ctlblk *, struct pt_regs *);
+
+static void __kprobes arch_prepare_ss_slot(struct kprobe *p)
+{
+	unsigned long offset = GET_INSN_LENGTH(p->opcode);
+
+	p->ainsn.api.restore = (unsigned long)p->addr + offset;
+
+	patch_text(p->ainsn.api.insn, p->opcode);
+	patch_text((void *)((unsigned long)(p->ainsn.api.insn) + offset),
+		   __BUG_INSN_32);
+}
+
+static void __kprobes arch_prepare_simulate(struct kprobe *p)
+{
+	p->ainsn.api.restore = 0;
+}
+
+static void __kprobes arch_simulate_insn(struct kprobe *p, struct pt_regs *regs)
+{
+	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+
+	if (p->ainsn.api.handler)
+		p->ainsn.api.handler((u32)p->opcode,
+					(unsigned long)p->addr, regs);
+
+	post_kprobe_handler(p, kcb, regs);
+}
+
+static bool __kprobes arch_check_kprobe(struct kprobe *p)
+{
+	unsigned long tmp  = (unsigned long)p->addr - p->offset;
+	unsigned long addr = (unsigned long)p->addr;
+
+	while (tmp <= addr) {
+		if (tmp == addr)
+			return true;
+
+		tmp += GET_INSN_LENGTH(*(u16 *)tmp);
+	}
+
+	return false;
+}
+
+int __kprobes arch_prepare_kprobe(struct kprobe *p)
+{
+	u16 *insn = (u16 *)p->addr;
+
+	if ((unsigned long)insn & 0x1)
+		return -EILSEQ;
+
+	if (!arch_check_kprobe(p))
+		return -EILSEQ;
+
+	/* copy instruction */
+	p->opcode = (kprobe_opcode_t)(*insn++);
+	if (GET_INSN_LENGTH(p->opcode) == 4)
+		p->opcode |= (kprobe_opcode_t)(*insn) << 16;
+
+	/* decode instruction */
+	switch (riscv_probe_decode_insn(p->addr, &p->ainsn.api)) {
+	case INSN_REJECTED:	/* insn not supported */
+		return -EINVAL;
+
+	case INSN_GOOD_NO_SLOT:	/* insn need simulation */
+		p->ainsn.api.insn = NULL;
+		break;
+
+	case INSN_GOOD:	/* instruction uses slot */
+		p->ainsn.api.insn = get_insn_slot();
+		if (!p->ainsn.api.insn)
+			return -ENOMEM;
+		break;
+	}
+
+	/* prepare the instruction */
+	if (p->ainsn.api.insn)
+		arch_prepare_ss_slot(p);
+	else
+		arch_prepare_simulate(p);
+
+	return 0;
+}
+
+#ifdef CONFIG_MMU
+void *alloc_insn_page(void)
+{
+	return  __vmalloc_node_range(PAGE_SIZE, 1, VMALLOC_START, VMALLOC_END,
+				     GFP_KERNEL, PAGE_KERNEL_READ_EXEC,
+				     VM_FLUSH_RESET_PERMS, NUMA_NO_NODE,
+				     __builtin_return_address(0));
+}
+#endif
+
+/* install breakpoint in text */
+void __kprobes arch_arm_kprobe(struct kprobe *p)
+{
+	if ((p->opcode & __INSN_LENGTH_MASK) == __INSN_LENGTH_32)
+		patch_text(p->addr, __BUG_INSN_32);
+	else
+		patch_text(p->addr, __BUG_INSN_16);
+}
+
+/* remove breakpoint from text */
+void __kprobes arch_disarm_kprobe(struct kprobe *p)
+{
+	patch_text(p->addr, p->opcode);
+}
+
+void __kprobes arch_remove_kprobe(struct kprobe *p)
+{
+}
+
+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 void __kprobes set_current_kprobe(struct kprobe *p)
+{
+	__this_cpu_write(current_kprobe, p);
+}
+
+/*
+ * Interrupts need to be disabled before single-step mode is set, and not
+ * reenabled until after single-step mode ends.
+ * Without disabling interrupt on local CPU, there is a chance of
+ * interrupt occurrence in the period of exception return and  start of
+ * out-of-line single-step, that result in wrongly single stepping
+ * into the interrupt handler.
+ */
+static void __kprobes kprobes_save_local_irqflag(struct kprobe_ctlblk *kcb,
+						struct pt_regs *regs)
+{
+	kcb->saved_status = regs->status;
+	regs->status &= ~SR_SPIE;
+}
+
+static void __kprobes kprobes_restore_local_irqflag(struct kprobe_ctlblk *kcb,
+						struct pt_regs *regs)
+{
+	regs->status = kcb->saved_status;
+}
+
+static void __kprobes setup_singlestep(struct kprobe *p,
+				       struct pt_regs *regs,
+				       struct kprobe_ctlblk *kcb, int reenter)
+{
+	unsigned long slot;
+
+	if (reenter) {
+		save_previous_kprobe(kcb);
+		set_current_kprobe(p);
+		kcb->kprobe_status = KPROBE_REENTER;
+	} else {
+		kcb->kprobe_status = KPROBE_HIT_SS;
+	}
+
+	if (p->ainsn.api.insn) {
+		/* prepare for single stepping */
+		slot = (unsigned long)p->ainsn.api.insn;
+
+		/* IRQs and single stepping do not mix well. */
+		kprobes_save_local_irqflag(kcb, regs);
+
+		instruction_pointer_set(regs, slot);
+	} else {
+		/* insn simulation */
+		arch_simulate_insn(p, regs);
+	}
+}
+
+static int __kprobes reenter_kprobe(struct kprobe *p,
+				    struct pt_regs *regs,
+				    struct kprobe_ctlblk *kcb)
+{
+	switch (kcb->kprobe_status) {
+	case KPROBE_HIT_SSDONE:
+	case KPROBE_HIT_ACTIVE:
+		kprobes_inc_nmissed_count(p);
+		setup_singlestep(p, regs, kcb, 1);
+		break;
+	case KPROBE_HIT_SS:
+	case KPROBE_REENTER:
+		pr_warn("Failed to recover from reentered kprobes.\n");
+		dump_kprobe(p);
+		BUG();
+		break;
+	default:
+		WARN_ON(1);
+		return 0;
+	}
+
+	return 1;
+}
+
+static void __kprobes
+post_kprobe_handler(struct kprobe *cur, struct kprobe_ctlblk *kcb, struct pt_regs *regs)
+{
+	/* return addr restore if non-branching insn */
+	if (cur->ainsn.api.restore != 0)
+		regs->epc = cur->ainsn.api.restore;
+
+	/* restore back original saved kprobe variables and continue */
+	if (kcb->kprobe_status == KPROBE_REENTER) {
+		restore_previous_kprobe(kcb);
+		return;
+	}
+
+	/* call post handler */
+	kcb->kprobe_status = KPROBE_HIT_SSDONE;
+	if (cur->post_handler)	{
+		/* post_handler can hit breakpoint and single step
+		 * again, so we enable D-flag for recursive exception.
+		 */
+		cur->post_handler(cur, regs, 0);
+	}
+
+	reset_current_kprobe();
+}
+
+int __kprobes kprobe_fault_handler(struct pt_regs *regs, unsigned int 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 a page fault. We reset the current
+		 * kprobe and the ip points back to the probe address
+		 * and allow the page fault handler to continue as a
+		 * normal page fault.
+		 */
+		regs->epc = (unsigned long) cur->addr;
+		BUG_ON(!instruction_pointer(regs));
+
+		if (kcb->kprobe_status == KPROBE_REENTER)
+			restore_previous_kprobe(kcb);
+		else {
+			kprobes_restore_local_irqflag(kcb, regs);
+			reset_current_kprobe();
+		}
+
+		break;
+	case KPROBE_HIT_ACTIVE:
+	case KPROBE_HIT_SSDONE:
+		/*
+		 * In case the user-specified fault handler returned
+		 * zero, try to fix up.
+		 */
+		if (fixup_exception(regs))
+			return 1;
+	}
+	return 0;
+}
+
+bool __kprobes
+kprobe_breakpoint_handler(struct pt_regs *regs)
+{
+	struct kprobe *p, *cur_kprobe;
+	struct kprobe_ctlblk *kcb;
+	unsigned long addr = instruction_pointer(regs);
+
+	kcb = get_kprobe_ctlblk();
+	cur_kprobe = kprobe_running();
+
+	p = get_kprobe((kprobe_opcode_t *) addr);
+
+	if (p) {
+		if (cur_kprobe) {
+			if (reenter_kprobe(p, regs, kcb))
+				return true;
+		} else {
+			/* Probe hit */
+			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, it will
+			 * modify the execution path and no need to single
+			 * stepping. Let's just reset current kprobe and exit.
+			 *
+			 * pre_handler can hit a breakpoint and can step thru
+			 * before return.
+			 */
+			if (!p->pre_handler || !p->pre_handler(p, regs))
+				setup_singlestep(p, regs, kcb, 0);
+			else
+				reset_current_kprobe();
+		}
+		return true;
+	}
+
+	/*
+	 * The breakpoint instruction was removed right
+	 * after we hit it.  Another cpu has removed
+	 * either a probepoint or a debugger breakpoint
+	 * at this address.  In either case, no further
+	 * handling of this interrupt is appropriate.
+	 * Return back to original instruction, and continue.
+	 */
+	return false;
+}
+
+bool __kprobes
+kprobe_single_step_handler(struct pt_regs *regs)
+{
+	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+	unsigned long addr = instruction_pointer(regs);
+	struct kprobe *cur = kprobe_running();
+
+	if (cur && (kcb->kprobe_status & (KPROBE_HIT_SS | KPROBE_REENTER)) &&
+	    ((unsigned long)&cur->ainsn.api.insn[0] + GET_INSN_LENGTH(cur->opcode) == addr)) {
+		kprobes_restore_local_irqflag(kcb, regs);
+		post_kprobe_handler(cur, kcb, regs);
+		return true;
+	}
+	/* not ours, kprobes should ignore it */
+	return false;
+}
+
+/*
+ * Provide a blacklist of symbols identifying ranges which cannot be kprobed.
+ * This blacklist is exposed to userspace via debugfs (kprobes/blacklist).
+ */
+int __init arch_populate_kprobe_blacklist(void)
+{
+	int ret;
+
+	ret = kprobe_add_area_blacklist((unsigned long)__irqentry_text_start,
+					(unsigned long)__irqentry_text_end);
+	return ret;
+}
+
+void __kprobes __used *trampoline_probe_handler(struct pt_regs *regs)
+{
+	return (void *)kretprobe_trampoline_handler(regs, NULL);
+}
+
+void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
+				      struct pt_regs *regs)
+{
+	ri->ret_addr = (kprobe_opcode_t *)regs->ra;
+	ri->fp = NULL;
+	regs->ra = (unsigned long) &__kretprobe_trampoline;
+}
+
+int __kprobes arch_trampoline_kprobe(struct kprobe *p)
+{
+	return 0;
+}
+
+int __init arch_init_kprobes(void)
+{
+	return 0;
+}
diff --git a/arch/riscv/kernel/probes/kprobes_trampoline.S b/arch/riscv/kernel/probes/kprobes_trampoline.S
new file mode 100644
index 000000000..7bdb09ded
--- /dev/null
+++ b/arch/riscv/kernel/probes/kprobes_trampoline.S
@@ -0,0 +1,93 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Author: Patrick Stählin <me@packi.ch>
+ */
+#include <linux/linkage.h>
+
+#include <asm/asm.h>
+#include <asm/asm-offsets.h>
+
+	.text
+	.altmacro
+
+	.macro save_all_base_regs
+	REG_S x1,  PT_RA(sp)
+	REG_S x3,  PT_GP(sp)
+	REG_S x4,  PT_TP(sp)
+	REG_S x5,  PT_T0(sp)
+	REG_S x6,  PT_T1(sp)
+	REG_S x7,  PT_T2(sp)
+	REG_S x8,  PT_S0(sp)
+	REG_S x9,  PT_S1(sp)
+	REG_S x10, PT_A0(sp)
+	REG_S x11, PT_A1(sp)
+	REG_S x12, PT_A2(sp)
+	REG_S x13, PT_A3(sp)
+	REG_S x14, PT_A4(sp)
+	REG_S x15, PT_A5(sp)
+	REG_S x16, PT_A6(sp)
+	REG_S x17, PT_A7(sp)
+	REG_S x18, PT_S2(sp)
+	REG_S x19, PT_S3(sp)
+	REG_S x20, PT_S4(sp)
+	REG_S x21, PT_S5(sp)
+	REG_S x22, PT_S6(sp)
+	REG_S x23, PT_S7(sp)
+	REG_S x24, PT_S8(sp)
+	REG_S x25, PT_S9(sp)
+	REG_S x26, PT_S10(sp)
+	REG_S x27, PT_S11(sp)
+	REG_S x28, PT_T3(sp)
+	REG_S x29, PT_T4(sp)
+	REG_S x30, PT_T5(sp)
+	REG_S x31, PT_T6(sp)
+	.endm
+
+	.macro restore_all_base_regs
+	REG_L x3,  PT_GP(sp)
+	REG_L x4,  PT_TP(sp)
+	REG_L x5,  PT_T0(sp)
+	REG_L x6,  PT_T1(sp)
+	REG_L x7,  PT_T2(sp)
+	REG_L x8,  PT_S0(sp)
+	REG_L x9,  PT_S1(sp)
+	REG_L x10, PT_A0(sp)
+	REG_L x11, PT_A1(sp)
+	REG_L x12, PT_A2(sp)
+	REG_L x13, PT_A3(sp)
+	REG_L x14, PT_A4(sp)
+	REG_L x15, PT_A5(sp)
+	REG_L x16, PT_A6(sp)
+	REG_L x17, PT_A7(sp)
+	REG_L x18, PT_S2(sp)
+	REG_L x19, PT_S3(sp)
+	REG_L x20, PT_S4(sp)
+	REG_L x21, PT_S5(sp)
+	REG_L x22, PT_S6(sp)
+	REG_L x23, PT_S7(sp)
+	REG_L x24, PT_S8(sp)
+	REG_L x25, PT_S9(sp)
+	REG_L x26, PT_S10(sp)
+	REG_L x27, PT_S11(sp)
+	REG_L x28, PT_T3(sp)
+	REG_L x29, PT_T4(sp)
+	REG_L x30, PT_T5(sp)
+	REG_L x31, PT_T6(sp)
+	.endm
+
+ENTRY(__kretprobe_trampoline)
+	addi sp, sp, -(PT_SIZE_ON_STACK)
+	save_all_base_regs
+
+	move a0, sp /* pt_regs */
+
+	call trampoline_probe_handler
+
+	/* use the result as the return-address */
+	move ra, a0
+
+	restore_all_base_regs
+	addi sp, sp, PT_SIZE_ON_STACK
+
+	ret
+ENDPROC(__kretprobe_trampoline)
diff --git a/arch/riscv/kernel/probes/simulate-insn.c b/arch/riscv/kernel/probes/simulate-insn.c
new file mode 100644
index 000000000..41bf1eb01
--- /dev/null
+++ b/arch/riscv/kernel/probes/simulate-insn.c
@@ -0,0 +1,197 @@
+// SPDX-License-Identifier: GPL-2.0+
+
+#include <linux/bitops.h>
+#include <linux/kernel.h>
+#include <linux/kprobes.h>
+
+#include "decode-insn.h"
+#include "simulate-insn.h"
+
+static inline bool rv_insn_reg_get_val(struct pt_regs *regs, u32 index,
+				       unsigned long *ptr)
+{
+	if (index == 0)
+		*ptr = 0;
+	else if (index <= 31)
+		*ptr = *((unsigned long *)regs + index);
+	else
+		return false;
+
+	return true;
+}
+
+static inline bool rv_insn_reg_set_val(struct pt_regs *regs, u32 index,
+				       unsigned long val)
+{
+	if (index == 0)
+		return true;
+	else if (index <= 31)
+		*((unsigned long *)regs + index) = val;
+	else
+		return false;
+
+	return true;
+}
+
+bool __kprobes simulate_jal(u32 opcode, unsigned long addr, struct pt_regs *regs)
+{
+	/*
+	 *     31    30       21    20     19        12 11 7 6      0
+	 * imm [20] | imm[10:1] | imm[11] | imm[19:12] | rd | opcode
+	 *     1         10          1           8       5    JAL/J
+	 */
+	bool ret;
+	u32 imm;
+	u32 index = (opcode >> 7) & 0x1f;
+
+	ret = rv_insn_reg_set_val(regs, index, addr + 4);
+	if (!ret)
+		return ret;
+
+	imm  = ((opcode >> 21) & 0x3ff) << 1;
+	imm |= ((opcode >> 20) & 0x1)   << 11;
+	imm |= ((opcode >> 12) & 0xff)  << 12;
+	imm |= ((opcode >> 31) & 0x1)   << 20;
+
+	instruction_pointer_set(regs, addr + sign_extend32((imm), 20));
+
+	return ret;
+}
+
+bool __kprobes simulate_jalr(u32 opcode, unsigned long addr, struct pt_regs *regs)
+{
+	/*
+	 * 31          20 19 15 14 12 11 7 6      0
+	 *  offset[11:0] | rs1 | 010 | rd | opcode
+	 *      12         5      3    5    JALR/JR
+	 */
+	bool ret;
+	unsigned long base_addr;
+	u32 imm = (opcode >> 20) & 0xfff;
+	u32 rd_index = (opcode >> 7) & 0x1f;
+	u32 rs1_index = (opcode >> 15) & 0x1f;
+
+	ret = rv_insn_reg_get_val(regs, rs1_index, &base_addr);
+	if (!ret)
+		return ret;
+
+	ret = rv_insn_reg_set_val(regs, rd_index, addr + 4);
+	if (!ret)
+		return ret;
+
+	instruction_pointer_set(regs, (base_addr + sign_extend32((imm), 11))&~1);
+
+	return ret;
+}
+
+#define auipc_rd_idx(opcode) \
+	((opcode >> 7) & 0x1f)
+
+#define auipc_imm(opcode) \
+	((((opcode) >> 12) & 0xfffff) << 12)
+
+#if __riscv_xlen == 64
+#define auipc_offset(opcode)	sign_extend64(auipc_imm(opcode), 31)
+#elif __riscv_xlen == 32
+#define auipc_offset(opcode)	auipc_imm(opcode)
+#else
+#error "Unexpected __riscv_xlen"
+#endif
+
+bool __kprobes simulate_auipc(u32 opcode, unsigned long addr, struct pt_regs *regs)
+{
+	/*
+	 * auipc instruction:
+	 *  31        12 11 7 6      0
+	 * | imm[31:12] | rd | opcode |
+	 *        20       5     7
+	 */
+
+	u32 rd_idx = auipc_rd_idx(opcode);
+	unsigned long rd_val = addr + auipc_offset(opcode);
+
+	if (!rv_insn_reg_set_val(regs, rd_idx, rd_val))
+		return false;
+
+	instruction_pointer_set(regs, addr + 4);
+
+	return true;
+}
+
+#define branch_rs1_idx(opcode) \
+	(((opcode) >> 15) & 0x1f)
+
+#define branch_rs2_idx(opcode) \
+	(((opcode) >> 20) & 0x1f)
+
+#define branch_funct3(opcode) \
+	(((opcode) >> 12) & 0x7)
+
+#define branch_imm(opcode) \
+	(((((opcode) >>  8) & 0xf ) <<  1) | \
+	 ((((opcode) >> 25) & 0x3f) <<  5) | \
+	 ((((opcode) >>  7) & 0x1 ) << 11) | \
+	 ((((opcode) >> 31) & 0x1 ) << 12))
+
+#define branch_offset(opcode) \
+	sign_extend32((branch_imm(opcode)), 12)
+
+#define BRANCH_BEQ	0x0
+#define BRANCH_BNE	0x1
+#define BRANCH_BLT	0x4
+#define BRANCH_BGE	0x5
+#define BRANCH_BLTU	0x6
+#define BRANCH_BGEU	0x7
+
+bool __kprobes simulate_branch(u32 opcode, unsigned long addr, struct pt_regs *regs)
+{
+	/*
+	 * branch instructions:
+	 *      31    30       25 24 20 19 15 14    12 11       8    7      6      0
+	 * | imm[12] | imm[10:5] | rs2 | rs1 | funct3 | imm[4:1] | imm[11] | opcode |
+	 *     1           6        5     5      3         4         1         7
+	 *     imm[12|10:5]        rs2   rs1    000       imm[4:1|11]       1100011  BEQ
+	 *     imm[12|10:5]        rs2   rs1    001       imm[4:1|11]       1100011  BNE
+	 *     imm[12|10:5]        rs2   rs1    100       imm[4:1|11]       1100011  BLT
+	 *     imm[12|10:5]        rs2   rs1    101       imm[4:1|11]       1100011  BGE
+	 *     imm[12|10:5]        rs2   rs1    110       imm[4:1|11]       1100011  BLTU
+	 *     imm[12|10:5]        rs2   rs1    111       imm[4:1|11]       1100011  BGEU
+	 */
+
+	s32 offset;
+	s32 offset_tmp;
+	unsigned long rs1_val;
+	unsigned long rs2_val;
+
+	if (!rv_insn_reg_get_val(regs, branch_rs1_idx(opcode), &rs1_val) ||
+	    !rv_insn_reg_get_val(regs, branch_rs2_idx(opcode), &rs2_val))
+		return false;
+
+	offset_tmp = branch_offset(opcode);
+	switch (branch_funct3(opcode)) {
+	case BRANCH_BEQ:
+		offset = (rs1_val == rs2_val) ? offset_tmp : 4;
+		break;
+	case BRANCH_BNE:
+		offset = (rs1_val != rs2_val) ? offset_tmp : 4;
+		break;
+	case BRANCH_BLT:
+		offset = ((long)rs1_val < (long)rs2_val) ? offset_tmp : 4;
+		break;
+	case BRANCH_BGE:
+		offset = ((long)rs1_val >= (long)rs2_val) ? offset_tmp : 4;
+		break;
+	case BRANCH_BLTU:
+		offset = (rs1_val < rs2_val) ? offset_tmp : 4;
+		break;
+	case BRANCH_BGEU:
+		offset = (rs1_val >= rs2_val) ? offset_tmp : 4;
+		break;
+	default:
+		return false;
+	}
+
+	instruction_pointer_set(regs, addr + offset);
+
+	return true;
+}
diff --git a/arch/riscv/kernel/probes/simulate-insn.h b/arch/riscv/kernel/probes/simulate-insn.h
new file mode 100644
index 000000000..de8474146
--- /dev/null
+++ b/arch/riscv/kernel/probes/simulate-insn.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+
+#ifndef _RISCV_KERNEL_PROBES_SIMULATE_INSN_H
+#define _RISCV_KERNEL_PROBES_SIMULATE_INSN_H
+
+#define __RISCV_INSN_FUNCS(name, mask, val)				\
+static __always_inline bool riscv_insn_is_##name(probe_opcode_t code)	\
+{									\
+	BUILD_BUG_ON(~(mask) & (val));					\
+	return (code & (mask)) == (val);				\
+}									\
+bool simulate_##name(u32 opcode, unsigned long addr,			\
+		     struct pt_regs *regs)
+
+#define RISCV_INSN_REJECTED(name, code)					\
+	do {								\
+		if (riscv_insn_is_##name(code)) {			\
+			return INSN_REJECTED;				\
+		}							\
+	} while (0)
+
+__RISCV_INSN_FUNCS(system,	0x7f, 0x73);
+__RISCV_INSN_FUNCS(fence,	0x7f, 0x0f);
+
+#define RISCV_INSN_SET_SIMULATE(name, code)				\
+	do {								\
+		if (riscv_insn_is_##name(code)) {			\
+			api->handler = simulate_##name;			\
+			return INSN_GOOD_NO_SLOT;			\
+		}							\
+	} while (0)
+
+__RISCV_INSN_FUNCS(c_j,		0xe003, 0xa001);
+__RISCV_INSN_FUNCS(c_jr,	0xf07f, 0x8002);
+__RISCV_INSN_FUNCS(c_jal,	0xe003, 0x2001);
+__RISCV_INSN_FUNCS(c_jalr,	0xf07f, 0x9002);
+__RISCV_INSN_FUNCS(c_beqz,	0xe003, 0xc001);
+__RISCV_INSN_FUNCS(c_bnez,	0xe003, 0xe001);
+__RISCV_INSN_FUNCS(c_ebreak,	0xffff, 0x9002);
+
+__RISCV_INSN_FUNCS(auipc,	0x7f, 0x17);
+__RISCV_INSN_FUNCS(branch,	0x7f, 0x63);
+
+__RISCV_INSN_FUNCS(jal,		0x7f, 0x6f);
+__RISCV_INSN_FUNCS(jalr,	0x707f, 0x67);
+
+#endif /* _RISCV_KERNEL_PROBES_SIMULATE_INSN_H */
diff --git a/arch/riscv/kernel/probes/uprobes.c b/arch/riscv/kernel/probes/uprobes.c
new file mode 100644
index 000000000..194f166b2
--- /dev/null
+++ b/arch/riscv/kernel/probes/uprobes.c
@@ -0,0 +1,182 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/highmem.h>
+#include <linux/ptrace.h>
+#include <linux/uprobes.h>
+
+#include "decode-insn.h"
+
+#define UPROBE_TRAP_NR	UINT_MAX
+
+bool is_swbp_insn(uprobe_opcode_t *insn)
+{
+#ifdef CONFIG_RISCV_ISA_C
+	return (*insn & 0xffff) == UPROBE_SWBP_INSN;
+#else
+	return *insn == UPROBE_SWBP_INSN;
+#endif
+}
+
+unsigned long uprobe_get_swbp_addr(struct pt_regs *regs)
+{
+	return instruction_pointer(regs);
+}
+
+int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm,
+			     unsigned long addr)
+{
+	probe_opcode_t opcode;
+
+	opcode = *(probe_opcode_t *)(&auprobe->insn[0]);
+
+	auprobe->insn_size = GET_INSN_LENGTH(opcode);
+
+	switch (riscv_probe_decode_insn(&opcode, &auprobe->api)) {
+	case INSN_REJECTED:
+		return -EINVAL;
+
+	case INSN_GOOD_NO_SLOT:
+		auprobe->simulate = true;
+		break;
+
+	case INSN_GOOD:
+		auprobe->simulate = false;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int arch_uprobe_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+	struct uprobe_task *utask = current->utask;
+
+	utask->autask.saved_cause = current->thread.bad_cause;
+	current->thread.bad_cause = UPROBE_TRAP_NR;
+
+	instruction_pointer_set(regs, utask->xol_vaddr);
+
+	return 0;
+}
+
+int arch_uprobe_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+	struct uprobe_task *utask = current->utask;
+
+	WARN_ON_ONCE(current->thread.bad_cause != UPROBE_TRAP_NR);
+	current->thread.bad_cause = utask->autask.saved_cause;
+
+	instruction_pointer_set(regs, utask->vaddr + auprobe->insn_size);
+
+	return 0;
+}
+
+bool arch_uprobe_xol_was_trapped(struct task_struct *t)
+{
+	if (t->thread.bad_cause != UPROBE_TRAP_NR)
+		return true;
+
+	return false;
+}
+
+bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+	probe_opcode_t insn;
+	unsigned long addr;
+
+	if (!auprobe->simulate)
+		return false;
+
+	insn = *(probe_opcode_t *)(&auprobe->insn[0]);
+	addr = instruction_pointer(regs);
+
+	if (auprobe->api.handler)
+		auprobe->api.handler(insn, addr, regs);
+
+	return true;
+}
+
+void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+	struct uprobe_task *utask = current->utask;
+
+	current->thread.bad_cause = utask->autask.saved_cause;
+	/*
+	 * Task has received a fatal signal, so reset back to probbed
+	 * address.
+	 */
+	instruction_pointer_set(regs, utask->vaddr);
+}
+
+bool arch_uretprobe_is_alive(struct return_instance *ret, enum rp_check ctx,
+		struct pt_regs *regs)
+{
+	if (ctx == RP_CHECK_CHAIN_CALL)
+		return regs->sp <= ret->stack;
+	else
+		return regs->sp < ret->stack;
+}
+
+unsigned long
+arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr,
+				  struct pt_regs *regs)
+{
+	unsigned long ra;
+
+	ra = regs->ra;
+
+	regs->ra = trampoline_vaddr;
+
+	return ra;
+}
+
+int arch_uprobe_exception_notify(struct notifier_block *self,
+				 unsigned long val, void *data)
+{
+	return NOTIFY_DONE;
+}
+
+bool uprobe_breakpoint_handler(struct pt_regs *regs)
+{
+	if (uprobe_pre_sstep_notifier(regs))
+		return true;
+
+	return false;
+}
+
+bool uprobe_single_step_handler(struct pt_regs *regs)
+{
+	if (uprobe_post_sstep_notifier(regs))
+		return true;
+
+	return false;
+}
+
+void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr,
+			   void *src, unsigned long len)
+{
+	/* Initialize the slot */
+	void *kaddr = kmap_atomic(page);
+	void *dst = kaddr + (vaddr & ~PAGE_MASK);
+
+	memcpy(dst, src, len);
+
+	/* Add ebreak behind opcode to simulate singlestep */
+	if (vaddr) {
+		dst += GET_INSN_LENGTH(*(probe_opcode_t *)src);
+		*(uprobe_opcode_t *)dst = __BUG_INSN_32;
+	}
+
+	kunmap_atomic(kaddr);
+
+	/*
+	 * We probably need flush_icache_user_page() but it needs vma.
+	 * This should work on most of architectures by default. If
+	 * architecture needs to do something different it can define
+	 * its own version of the function.
+	 */
+	flush_dcache_page(page);
+}
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
new file mode 100644
index 000000000..8955f2432
--- /dev/null
+++ b/arch/riscv/kernel/process.c
@@ -0,0 +1,191 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2009 Sunplus Core Technology Co., Ltd.
+ *  Chen Liqin <liqin.chen@sunplusct.com>
+ *  Lennox Wu <lennox.wu@sunplusct.com>
+ * Copyright (C) 2012 Regents of the University of California
+ * Copyright (C) 2017 SiFive
+ */
+
+#include <linux/cpu.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/sched/debug.h>
+#include <linux/sched/task_stack.h>
+#include <linux/tick.h>
+#include <linux/ptrace.h>
+#include <linux/uaccess.h>
+
+#include <asm/unistd.h>
+#include <asm/processor.h>
+#include <asm/csr.h>
+#include <asm/stacktrace.h>
+#include <asm/string.h>
+#include <asm/switch_to.h>
+#include <asm/thread_info.h>
+#include <asm/cpuidle.h>
+
+register unsigned long gp_in_global __asm__("gp");
+
+#if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_STACKPROTECTOR_PER_TASK)
+#include <linux/stackprotector.h>
+unsigned long __stack_chk_guard __read_mostly;
+EXPORT_SYMBOL(__stack_chk_guard);
+#endif
+
+extern asmlinkage void ret_from_fork(void);
+extern asmlinkage void ret_from_kernel_thread(void);
+
+void arch_cpu_idle(void)
+{
+	cpu_do_idle();
+	raw_local_irq_enable();
+}
+
+void __show_regs(struct pt_regs *regs)
+{
+	show_regs_print_info(KERN_DEFAULT);
+
+	if (!user_mode(regs)) {
+		pr_cont("epc : %pS\n", (void *)regs->epc);
+		pr_cont(" ra : %pS\n", (void *)regs->ra);
+	}
+
+	pr_cont("epc : " REG_FMT " ra : " REG_FMT " sp : " REG_FMT "\n",
+		regs->epc, regs->ra, regs->sp);
+	pr_cont(" gp : " REG_FMT " tp : " REG_FMT " t0 : " REG_FMT "\n",
+		regs->gp, regs->tp, regs->t0);
+	pr_cont(" t1 : " REG_FMT " t2 : " REG_FMT " s0 : " REG_FMT "\n",
+		regs->t1, regs->t2, regs->s0);
+	pr_cont(" s1 : " REG_FMT " a0 : " REG_FMT " a1 : " REG_FMT "\n",
+		regs->s1, regs->a0, regs->a1);
+	pr_cont(" a2 : " REG_FMT " a3 : " REG_FMT " a4 : " REG_FMT "\n",
+		regs->a2, regs->a3, regs->a4);
+	pr_cont(" a5 : " REG_FMT " a6 : " REG_FMT " a7 : " REG_FMT "\n",
+		regs->a5, regs->a6, regs->a7);
+	pr_cont(" s2 : " REG_FMT " s3 : " REG_FMT " s4 : " REG_FMT "\n",
+		regs->s2, regs->s3, regs->s4);
+	pr_cont(" s5 : " REG_FMT " s6 : " REG_FMT " s7 : " REG_FMT "\n",
+		regs->s5, regs->s6, regs->s7);
+	pr_cont(" s8 : " REG_FMT " s9 : " REG_FMT " s10: " REG_FMT "\n",
+		regs->s8, regs->s9, regs->s10);
+	pr_cont(" s11: " REG_FMT " t3 : " REG_FMT " t4 : " REG_FMT "\n",
+		regs->s11, regs->t3, regs->t4);
+	pr_cont(" t5 : " REG_FMT " t6 : " REG_FMT "\n",
+		regs->t5, regs->t6);
+
+	pr_cont("status: " REG_FMT " badaddr: " REG_FMT " cause: " REG_FMT "\n",
+		regs->status, regs->badaddr, regs->cause);
+}
+void show_regs(struct pt_regs *regs)
+{
+	__show_regs(regs);
+	if (!user_mode(regs))
+		dump_backtrace(regs, NULL, KERN_DEFAULT);
+}
+
+#ifdef CONFIG_COMPAT
+static bool compat_mode_supported __read_mostly;
+
+bool compat_elf_check_arch(Elf32_Ehdr *hdr)
+{
+	return compat_mode_supported &&
+	       hdr->e_machine == EM_RISCV &&
+	       hdr->e_ident[EI_CLASS] == ELFCLASS32;
+}
+
+static int __init compat_mode_detect(void)
+{
+	unsigned long tmp = csr_read(CSR_STATUS);
+
+	csr_write(CSR_STATUS, (tmp & ~SR_UXL) | SR_UXL_32);
+	compat_mode_supported =
+			(csr_read(CSR_STATUS) & SR_UXL) == SR_UXL_32;
+
+	csr_write(CSR_STATUS, tmp);
+
+	pr_info("riscv: ELF compat mode %s",
+			compat_mode_supported ? "supported" : "unsupported");
+
+	return 0;
+}
+early_initcall(compat_mode_detect);
+#endif
+
+void start_thread(struct pt_regs *regs, unsigned long pc,
+	unsigned long sp)
+{
+	regs->status = SR_PIE;
+	if (has_fpu()) {
+		regs->status |= SR_FS_INITIAL;
+		/*
+		 * Restore the initial value to the FP register
+		 * before starting the user program.
+		 */
+		fstate_restore(current, regs);
+	}
+	regs->epc = pc;
+	regs->sp = sp;
+
+#ifdef CONFIG_64BIT
+	regs->status &= ~SR_UXL;
+
+	if (is_compat_task())
+		regs->status |= SR_UXL_32;
+	else
+		regs->status |= SR_UXL_64;
+#endif
+}
+
+void flush_thread(void)
+{
+#ifdef CONFIG_FPU
+	/*
+	 * Reset FPU state and context
+	 *	frm: round to nearest, ties to even (IEEE default)
+	 *	fflags: accrued exceptions cleared
+	 */
+	fstate_off(current, task_pt_regs(current));
+	memset(&current->thread.fstate, 0, sizeof(current->thread.fstate));
+#endif
+}
+
+int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
+{
+	fstate_save(src, task_pt_regs(src));
+	*dst = *src;
+	return 0;
+}
+
+int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
+{
+	unsigned long clone_flags = args->flags;
+	unsigned long usp = args->stack;
+	unsigned long tls = args->tls;
+	struct pt_regs *childregs = task_pt_regs(p);
+
+	memset(&p->thread.s, 0, sizeof(p->thread.s));
+
+	/* p->thread holds context to be restored by __switch_to() */
+	if (unlikely(args->fn)) {
+		/* Kernel thread */
+		memset(childregs, 0, sizeof(struct pt_regs));
+		childregs->gp = gp_in_global;
+		/* Supervisor/Machine, irqs on: */
+		childregs->status = SR_PP | SR_PIE;
+
+		p->thread.ra = (unsigned long)ret_from_kernel_thread;
+		p->thread.s[0] = (unsigned long)args->fn;
+		p->thread.s[1] = (unsigned long)args->fn_arg;
+	} else {
+		*childregs = *(current_pt_regs());
+		if (usp) /* User fork */
+			childregs->sp = usp;
+		if (clone_flags & CLONE_SETTLS)
+			childregs->tp = tls;
+		childregs->a0 = 0; /* Return value of fork() */
+		p->thread.ra = (unsigned long)ret_from_fork;
+	}
+	p->thread.sp = (unsigned long)childregs; /* kernel sp */
+	return 0;
+}
diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c
new file mode 100644
index 000000000..2ae8280ae
--- /dev/null
+++ b/arch/riscv/kernel/ptrace.c
@@ -0,0 +1,351 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright 2010 Tilera Corporation. All Rights Reserved.
+ * Copyright 2015 Regents of the University of California
+ * Copyright 2017 SiFive
+ *
+ * Copied from arch/tile/kernel/ptrace.c
+ */
+
+#include <asm/ptrace.h>
+#include <asm/syscall.h>
+#include <asm/thread_info.h>
+#include <asm/switch_to.h>
+#include <linux/audit.h>
+#include <linux/compat.h>
+#include <linux/ptrace.h>
+#include <linux/elf.h>
+#include <linux/regset.h>
+#include <linux/sched.h>
+#include <linux/sched/task_stack.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/syscalls.h>
+
+enum riscv_regset {
+	REGSET_X,
+#ifdef CONFIG_FPU
+	REGSET_F,
+#endif
+};
+
+static int riscv_gpr_get(struct task_struct *target,
+			 const struct user_regset *regset,
+			 struct membuf to)
+{
+	return membuf_write(&to, task_pt_regs(target),
+			    sizeof(struct user_regs_struct));
+}
+
+static int riscv_gpr_set(struct task_struct *target,
+			 const struct user_regset *regset,
+			 unsigned int pos, unsigned int count,
+			 const void *kbuf, const void __user *ubuf)
+{
+	struct pt_regs *regs;
+
+	regs = task_pt_regs(target);
+	return user_regset_copyin(&pos, &count, &kbuf, &ubuf, regs, 0, -1);
+}
+
+#ifdef CONFIG_FPU
+static int riscv_fpr_get(struct task_struct *target,
+			 const struct user_regset *regset,
+			 struct membuf to)
+{
+	struct __riscv_d_ext_state *fstate = &target->thread.fstate;
+
+	if (target == current)
+		fstate_save(current, task_pt_regs(current));
+
+	membuf_write(&to, fstate, offsetof(struct __riscv_d_ext_state, fcsr));
+	membuf_store(&to, fstate->fcsr);
+	return membuf_zero(&to, 4);	// explicitly pad
+}
+
+static int riscv_fpr_set(struct task_struct *target,
+			 const struct user_regset *regset,
+			 unsigned int pos, unsigned int count,
+			 const void *kbuf, const void __user *ubuf)
+{
+	int ret;
+	struct __riscv_d_ext_state *fstate = &target->thread.fstate;
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, fstate, 0,
+				 offsetof(struct __riscv_d_ext_state, fcsr));
+	if (!ret) {
+		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, fstate, 0,
+					 offsetof(struct __riscv_d_ext_state, fcsr) +
+					 sizeof(fstate->fcsr));
+	}
+
+	return ret;
+}
+#endif
+
+static const struct user_regset riscv_user_regset[] = {
+	[REGSET_X] = {
+		.core_note_type = NT_PRSTATUS,
+		.n = ELF_NGREG,
+		.size = sizeof(elf_greg_t),
+		.align = sizeof(elf_greg_t),
+		.regset_get = riscv_gpr_get,
+		.set = riscv_gpr_set,
+	},
+#ifdef CONFIG_FPU
+	[REGSET_F] = {
+		.core_note_type = NT_PRFPREG,
+		.n = ELF_NFPREG,
+		.size = sizeof(elf_fpreg_t),
+		.align = sizeof(elf_fpreg_t),
+		.regset_get = riscv_fpr_get,
+		.set = riscv_fpr_set,
+	},
+#endif
+};
+
+static const struct user_regset_view riscv_user_native_view = {
+	.name = "riscv",
+	.e_machine = EM_RISCV,
+	.regsets = riscv_user_regset,
+	.n = ARRAY_SIZE(riscv_user_regset),
+};
+
+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}
+
+static const struct pt_regs_offset regoffset_table[] = {
+	REG_OFFSET_NAME(epc),
+	REG_OFFSET_NAME(ra),
+	REG_OFFSET_NAME(sp),
+	REG_OFFSET_NAME(gp),
+	REG_OFFSET_NAME(tp),
+	REG_OFFSET_NAME(t0),
+	REG_OFFSET_NAME(t1),
+	REG_OFFSET_NAME(t2),
+	REG_OFFSET_NAME(s0),
+	REG_OFFSET_NAME(s1),
+	REG_OFFSET_NAME(a0),
+	REG_OFFSET_NAME(a1),
+	REG_OFFSET_NAME(a2),
+	REG_OFFSET_NAME(a3),
+	REG_OFFSET_NAME(a4),
+	REG_OFFSET_NAME(a5),
+	REG_OFFSET_NAME(a6),
+	REG_OFFSET_NAME(a7),
+	REG_OFFSET_NAME(s2),
+	REG_OFFSET_NAME(s3),
+	REG_OFFSET_NAME(s4),
+	REG_OFFSET_NAME(s5),
+	REG_OFFSET_NAME(s6),
+	REG_OFFSET_NAME(s7),
+	REG_OFFSET_NAME(s8),
+	REG_OFFSET_NAME(s9),
+	REG_OFFSET_NAME(s10),
+	REG_OFFSET_NAME(s11),
+	REG_OFFSET_NAME(t3),
+	REG_OFFSET_NAME(t4),
+	REG_OFFSET_NAME(t5),
+	REG_OFFSET_NAME(t6),
+	REG_OFFSET_NAME(status),
+	REG_OFFSET_NAME(badaddr),
+	REG_OFFSET_NAME(cause),
+	REG_OFFSET_NAME(orig_a0),
+	REG_OFFSET_END,
+};
+
+/**
+ * regs_query_register_offset() - query register offset from its name
+ * @name:	the name of a register
+ *
+ * regs_query_register_offset() returns the offset of a register in struct
+ * pt_regs from its name. If the name is invalid, this returns -EINVAL;
+ */
+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;
+}
+
+/**
+ * regs_within_kernel_stack() - check the address in the stack
+ * @regs:      pt_regs which contains kernel stack pointer.
+ * @addr:      address which is checked.
+ *
+ * regs_within_kernel_stack() checks @addr is within the kernel stack page(s).
+ * If @addr is within the kernel stack, it returns true. If not, returns false.
+ */
+static bool regs_within_kernel_stack(struct pt_regs *regs, unsigned long addr)
+{
+	return (addr & ~(THREAD_SIZE - 1))  ==
+		(kernel_stack_pointer(regs) & ~(THREAD_SIZE - 1));
+}
+
+/**
+ * regs_get_kernel_stack_nth() - get Nth entry of the stack
+ * @regs:	pt_regs which contains kernel stack pointer.
+ * @n:		stack entry number.
+ *
+ * regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which
+ * is specified by @regs. If the @n th entry is NOT in the kernel stack,
+ * this returns 0.
+ */
+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;
+}
+
+void ptrace_disable(struct task_struct *child)
+{
+	clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
+}
+
+long arch_ptrace(struct task_struct *child, long request,
+		 unsigned long addr, unsigned long data)
+{
+	long ret = -EIO;
+
+	switch (request) {
+	default:
+		ret = ptrace_request(child, request, addr, data);
+		break;
+	}
+
+	return ret;
+}
+
+/*
+ * Allows PTRACE_SYSCALL to work.  These are called from entry.S in
+ * {handle,ret_from}_syscall.
+ */
+__visible int do_syscall_trace_enter(struct pt_regs *regs)
+{
+	if (test_thread_flag(TIF_SYSCALL_TRACE))
+		if (ptrace_report_syscall_entry(regs))
+			return -1;
+
+	/*
+	 * Do the secure computing after ptrace; failures should be fast.
+	 * If this fails we might have return value in a0 from seccomp
+	 * (via SECCOMP_RET_ERRNO/TRACE).
+	 */
+	if (secure_computing() == -1)
+		return -1;
+
+#ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS
+	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
+		trace_sys_enter(regs, syscall_get_nr(current, regs));
+#endif
+
+	audit_syscall_entry(regs->a7, regs->a0, regs->a1, regs->a2, regs->a3);
+	return 0;
+}
+
+__visible void do_syscall_trace_exit(struct pt_regs *regs)
+{
+	audit_syscall_exit(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
+}
+
+#ifdef CONFIG_COMPAT
+static int compat_riscv_gpr_get(struct task_struct *target,
+				const struct user_regset *regset,
+				struct membuf to)
+{
+	struct compat_user_regs_struct cregs;
+
+	regs_to_cregs(&cregs, task_pt_regs(target));
+
+	return membuf_write(&to, &cregs,
+			    sizeof(struct compat_user_regs_struct));
+}
+
+static int compat_riscv_gpr_set(struct task_struct *target,
+				const struct user_regset *regset,
+				unsigned int pos, unsigned int count,
+				const void *kbuf, const void __user *ubuf)
+{
+	int ret;
+	struct compat_user_regs_struct cregs;
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &cregs, 0, -1);
+
+	cregs_to_regs(&cregs, task_pt_regs(target));
+
+	return ret;
+}
+
+static const struct user_regset compat_riscv_user_regset[] = {
+	[REGSET_X] = {
+		.core_note_type = NT_PRSTATUS,
+		.n = ELF_NGREG,
+		.size = sizeof(compat_elf_greg_t),
+		.align = sizeof(compat_elf_greg_t),
+		.regset_get = compat_riscv_gpr_get,
+		.set = compat_riscv_gpr_set,
+	},
+#ifdef CONFIG_FPU
+	[REGSET_F] = {
+		.core_note_type = NT_PRFPREG,
+		.n = ELF_NFPREG,
+		.size = sizeof(elf_fpreg_t),
+		.align = sizeof(elf_fpreg_t),
+		.regset_get = riscv_fpr_get,
+		.set = riscv_fpr_set,
+	},
+#endif
+};
+
+static const struct user_regset_view compat_riscv_user_native_view = {
+	.name = "riscv",
+	.e_machine = EM_RISCV,
+	.regsets = compat_riscv_user_regset,
+	.n = ARRAY_SIZE(compat_riscv_user_regset),
+};
+
+long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
+			compat_ulong_t caddr, compat_ulong_t cdata)
+{
+	long ret = -EIO;
+
+	switch (request) {
+	default:
+		ret = compat_ptrace_request(child, request, caddr, cdata);
+		break;
+	}
+
+	return ret;
+}
+#endif /* CONFIG_COMPAT */
+
+const struct user_regset_view *task_user_regset_view(struct task_struct *task)
+{
+#ifdef CONFIG_COMPAT
+	if (test_tsk_thread_flag(task, TIF_32BIT))
+		return &compat_riscv_user_native_view;
+	else
+#endif
+		return &riscv_user_native_view;
+}
diff --git a/arch/riscv/kernel/reset.c b/arch/riscv/kernel/reset.c
new file mode 100644
index 000000000..912288572
--- /dev/null
+++ b/arch/riscv/kernel/reset.c
@@ -0,0 +1,34 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ */
+
+#include <linux/reboot.h>
+#include <linux/pm.h>
+
+static void default_power_off(void)
+{
+	while (1)
+		wait_for_interrupt();
+}
+
+void (*pm_power_off)(void) = NULL;
+EXPORT_SYMBOL(pm_power_off);
+
+void machine_restart(char *cmd)
+{
+	do_kernel_restart(cmd);
+	while (1);
+}
+
+void machine_halt(void)
+{
+	do_kernel_power_off();
+	default_power_off();
+}
+
+void machine_power_off(void)
+{
+	do_kernel_power_off();
+	default_power_off();
+}
diff --git a/arch/riscv/kernel/riscv_ksyms.c b/arch/riscv/kernel/riscv_ksyms.c
new file mode 100644
index 000000000..5ab1c7e1a
--- /dev/null
+++ b/arch/riscv/kernel/riscv_ksyms.c
@@ -0,0 +1,17 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2017 Zihao Yu
+ */
+
+#include <linux/export.h>
+#include <linux/uaccess.h>
+
+/*
+ * Assembly functions that may be used (directly or indirectly) by modules
+ */
+EXPORT_SYMBOL(memset);
+EXPORT_SYMBOL(memcpy);
+EXPORT_SYMBOL(memmove);
+EXPORT_SYMBOL(__memset);
+EXPORT_SYMBOL(__memcpy);
+EXPORT_SYMBOL(__memmove);
diff --git a/arch/riscv/kernel/sbi.c b/arch/riscv/kernel/sbi.c
new file mode 100644
index 000000000..5238026f7
--- /dev/null
+++ b/arch/riscv/kernel/sbi.c
@@ -0,0 +1,697 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * SBI initialilization and all extension implementation.
+ *
+ * Copyright (c) 2020 Western Digital Corporation or its affiliates.
+ */
+
+#include <linux/bits.h>
+#include <linux/init.h>
+#include <linux/pm.h>
+#include <linux/reboot.h>
+#include <asm/sbi.h>
+#include <asm/smp.h>
+
+/* default SBI version is 0.1 */
+unsigned long sbi_spec_version __ro_after_init = SBI_SPEC_VERSION_DEFAULT;
+EXPORT_SYMBOL(sbi_spec_version);
+
+static void (*__sbi_set_timer)(uint64_t stime) __ro_after_init;
+static int (*__sbi_send_ipi)(const struct cpumask *cpu_mask) __ro_after_init;
+static int (*__sbi_rfence)(int fid, const struct cpumask *cpu_mask,
+			   unsigned long start, unsigned long size,
+			   unsigned long arg4, unsigned long arg5) __ro_after_init;
+
+struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0,
+			unsigned long arg1, unsigned long arg2,
+			unsigned long arg3, unsigned long arg4,
+			unsigned long arg5)
+{
+	struct sbiret ret;
+
+	register uintptr_t a0 asm ("a0") = (uintptr_t)(arg0);
+	register uintptr_t a1 asm ("a1") = (uintptr_t)(arg1);
+	register uintptr_t a2 asm ("a2") = (uintptr_t)(arg2);
+	register uintptr_t a3 asm ("a3") = (uintptr_t)(arg3);
+	register uintptr_t a4 asm ("a4") = (uintptr_t)(arg4);
+	register uintptr_t a5 asm ("a5") = (uintptr_t)(arg5);
+	register uintptr_t a6 asm ("a6") = (uintptr_t)(fid);
+	register uintptr_t a7 asm ("a7") = (uintptr_t)(ext);
+	asm volatile ("ecall"
+		      : "+r" (a0), "+r" (a1)
+		      : "r" (a2), "r" (a3), "r" (a4), "r" (a5), "r" (a6), "r" (a7)
+		      : "memory");
+	ret.error = a0;
+	ret.value = a1;
+
+	return ret;
+}
+EXPORT_SYMBOL(sbi_ecall);
+
+int sbi_err_map_linux_errno(int err)
+{
+	switch (err) {
+	case SBI_SUCCESS:
+		return 0;
+	case SBI_ERR_DENIED:
+		return -EPERM;
+	case SBI_ERR_INVALID_PARAM:
+		return -EINVAL;
+	case SBI_ERR_INVALID_ADDRESS:
+		return -EFAULT;
+	case SBI_ERR_NOT_SUPPORTED:
+	case SBI_ERR_FAILURE:
+	default:
+		return -ENOTSUPP;
+	};
+}
+EXPORT_SYMBOL(sbi_err_map_linux_errno);
+
+#ifdef CONFIG_RISCV_SBI_V01
+static unsigned long __sbi_v01_cpumask_to_hartmask(const struct cpumask *cpu_mask)
+{
+	unsigned long cpuid, hartid;
+	unsigned long hmask = 0;
+
+	/*
+	 * There is no maximum hartid concept in RISC-V and NR_CPUS must not be
+	 * associated with hartid. As SBI v0.1 is only kept for backward compatibility
+	 * and will be removed in the future, there is no point in supporting hartid
+	 * greater than BITS_PER_LONG (32 for RV32 and 64 for RV64). Ideally, SBI v0.2
+	 * should be used for platforms with hartid greater than BITS_PER_LONG.
+	 */
+	for_each_cpu(cpuid, cpu_mask) {
+		hartid = cpuid_to_hartid_map(cpuid);
+		if (hartid >= BITS_PER_LONG) {
+			pr_warn("Unable to send any request to hartid > BITS_PER_LONG for SBI v0.1\n");
+			break;
+		}
+		hmask |= BIT(hartid);
+	}
+
+	return hmask;
+}
+
+/**
+ * sbi_console_putchar() - Writes given character to the console device.
+ * @ch: The data to be written to the console.
+ *
+ * Return: None
+ */
+void sbi_console_putchar(int ch)
+{
+	sbi_ecall(SBI_EXT_0_1_CONSOLE_PUTCHAR, 0, ch, 0, 0, 0, 0, 0);
+}
+EXPORT_SYMBOL(sbi_console_putchar);
+
+/**
+ * sbi_console_getchar() - Reads a byte from console device.
+ *
+ * Returns the value read from console.
+ */
+int sbi_console_getchar(void)
+{
+	struct sbiret ret;
+
+	ret = sbi_ecall(SBI_EXT_0_1_CONSOLE_GETCHAR, 0, 0, 0, 0, 0, 0, 0);
+
+	return ret.error;
+}
+EXPORT_SYMBOL(sbi_console_getchar);
+
+/**
+ * sbi_shutdown() - Remove all the harts from executing supervisor code.
+ *
+ * Return: None
+ */
+void sbi_shutdown(void)
+{
+	sbi_ecall(SBI_EXT_0_1_SHUTDOWN, 0, 0, 0, 0, 0, 0, 0);
+}
+EXPORT_SYMBOL(sbi_shutdown);
+
+/**
+ * sbi_clear_ipi() - Clear any pending IPIs for the calling hart.
+ *
+ * Return: None
+ */
+void sbi_clear_ipi(void)
+{
+	sbi_ecall(SBI_EXT_0_1_CLEAR_IPI, 0, 0, 0, 0, 0, 0, 0);
+}
+EXPORT_SYMBOL(sbi_clear_ipi);
+
+/**
+ * __sbi_set_timer_v01() - Program the timer for next timer event.
+ * @stime_value: The value after which next timer event should fire.
+ *
+ * Return: None
+ */
+static void __sbi_set_timer_v01(uint64_t stime_value)
+{
+#if __riscv_xlen == 32
+	sbi_ecall(SBI_EXT_0_1_SET_TIMER, 0, stime_value,
+		  stime_value >> 32, 0, 0, 0, 0);
+#else
+	sbi_ecall(SBI_EXT_0_1_SET_TIMER, 0, stime_value, 0, 0, 0, 0, 0);
+#endif
+}
+
+static int __sbi_send_ipi_v01(const struct cpumask *cpu_mask)
+{
+	unsigned long hart_mask;
+
+	if (!cpu_mask || cpumask_empty(cpu_mask))
+		cpu_mask = cpu_online_mask;
+	hart_mask = __sbi_v01_cpumask_to_hartmask(cpu_mask);
+
+	sbi_ecall(SBI_EXT_0_1_SEND_IPI, 0, (unsigned long)(&hart_mask),
+		  0, 0, 0, 0, 0);
+	return 0;
+}
+
+static int __sbi_rfence_v01(int fid, const struct cpumask *cpu_mask,
+			    unsigned long start, unsigned long size,
+			    unsigned long arg4, unsigned long arg5)
+{
+	int result = 0;
+	unsigned long hart_mask;
+
+	if (!cpu_mask || cpumask_empty(cpu_mask))
+		cpu_mask = cpu_online_mask;
+	hart_mask = __sbi_v01_cpumask_to_hartmask(cpu_mask);
+
+	/* v0.2 function IDs are equivalent to v0.1 extension IDs */
+	switch (fid) {
+	case SBI_EXT_RFENCE_REMOTE_FENCE_I:
+		sbi_ecall(SBI_EXT_0_1_REMOTE_FENCE_I, 0,
+			  (unsigned long)&hart_mask, 0, 0, 0, 0, 0);
+		break;
+	case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA:
+		sbi_ecall(SBI_EXT_0_1_REMOTE_SFENCE_VMA, 0,
+			  (unsigned long)&hart_mask, start, size,
+			  0, 0, 0);
+		break;
+	case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID:
+		sbi_ecall(SBI_EXT_0_1_REMOTE_SFENCE_VMA_ASID, 0,
+			  (unsigned long)&hart_mask, start, size,
+			  arg4, 0, 0);
+		break;
+	default:
+		pr_err("SBI call [%d]not supported in SBI v0.1\n", fid);
+		result = -EINVAL;
+	}
+
+	return result;
+}
+
+static void sbi_set_power_off(void)
+{
+	pm_power_off = sbi_shutdown;
+}
+#else
+static void __sbi_set_timer_v01(uint64_t stime_value)
+{
+	pr_warn("Timer extension is not available in SBI v%lu.%lu\n",
+		sbi_major_version(), sbi_minor_version());
+}
+
+static int __sbi_send_ipi_v01(const struct cpumask *cpu_mask)
+{
+	pr_warn("IPI extension is not available in SBI v%lu.%lu\n",
+		sbi_major_version(), sbi_minor_version());
+
+	return 0;
+}
+
+static int __sbi_rfence_v01(int fid, const struct cpumask *cpu_mask,
+			    unsigned long start, unsigned long size,
+			    unsigned long arg4, unsigned long arg5)
+{
+	pr_warn("remote fence extension is not available in SBI v%lu.%lu\n",
+		sbi_major_version(), sbi_minor_version());
+
+	return 0;
+}
+
+static void sbi_set_power_off(void) {}
+#endif /* CONFIG_RISCV_SBI_V01 */
+
+static void __sbi_set_timer_v02(uint64_t stime_value)
+{
+#if __riscv_xlen == 32
+	sbi_ecall(SBI_EXT_TIME, SBI_EXT_TIME_SET_TIMER, stime_value,
+		  stime_value >> 32, 0, 0, 0, 0);
+#else
+	sbi_ecall(SBI_EXT_TIME, SBI_EXT_TIME_SET_TIMER, stime_value, 0,
+		  0, 0, 0, 0);
+#endif
+}
+
+static int __sbi_send_ipi_v02(const struct cpumask *cpu_mask)
+{
+	unsigned long hartid, cpuid, hmask = 0, hbase = 0, htop = 0;
+	struct sbiret ret = {0};
+	int result;
+
+	if (!cpu_mask || cpumask_empty(cpu_mask))
+		cpu_mask = cpu_online_mask;
+
+	for_each_cpu(cpuid, cpu_mask) {
+		hartid = cpuid_to_hartid_map(cpuid);
+		if (hmask) {
+			if (hartid + BITS_PER_LONG <= htop ||
+			    hbase + BITS_PER_LONG <= hartid) {
+				ret = sbi_ecall(SBI_EXT_IPI,
+						SBI_EXT_IPI_SEND_IPI, hmask,
+						hbase, 0, 0, 0, 0);
+				if (ret.error)
+					goto ecall_failed;
+				hmask = 0;
+			} else if (hartid < hbase) {
+				/* shift the mask to fit lower hartid */
+				hmask <<= hbase - hartid;
+				hbase = hartid;
+			}
+		}
+		if (!hmask) {
+			hbase = hartid;
+			htop = hartid;
+		} else if (hartid > htop) {
+			htop = hartid;
+		}
+		hmask |= BIT(hartid - hbase);
+	}
+
+	if (hmask) {
+		ret = sbi_ecall(SBI_EXT_IPI, SBI_EXT_IPI_SEND_IPI,
+				hmask, hbase, 0, 0, 0, 0);
+		if (ret.error)
+			goto ecall_failed;
+	}
+
+	return 0;
+
+ecall_failed:
+	result = sbi_err_map_linux_errno(ret.error);
+	pr_err("%s: hbase = [%lu] hmask = [0x%lx] failed (error [%d])\n",
+	       __func__, hbase, hmask, result);
+	return result;
+}
+
+static int __sbi_rfence_v02_call(unsigned long fid, unsigned long hmask,
+				 unsigned long hbase, unsigned long start,
+				 unsigned long size, unsigned long arg4,
+				 unsigned long arg5)
+{
+	struct sbiret ret = {0};
+	int ext = SBI_EXT_RFENCE;
+	int result = 0;
+
+	switch (fid) {
+	case SBI_EXT_RFENCE_REMOTE_FENCE_I:
+		ret = sbi_ecall(ext, fid, hmask, hbase, 0, 0, 0, 0);
+		break;
+	case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA:
+		ret = sbi_ecall(ext, fid, hmask, hbase, start,
+				size, 0, 0);
+		break;
+	case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID:
+		ret = sbi_ecall(ext, fid, hmask, hbase, start,
+				size, arg4, 0);
+		break;
+
+	case SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA:
+		ret = sbi_ecall(ext, fid, hmask, hbase, start,
+				size, 0, 0);
+		break;
+	case SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA_VMID:
+		ret = sbi_ecall(ext, fid, hmask, hbase, start,
+				size, arg4, 0);
+		break;
+	case SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA:
+		ret = sbi_ecall(ext, fid, hmask, hbase, start,
+				size, 0, 0);
+		break;
+	case SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA_ASID:
+		ret = sbi_ecall(ext, fid, hmask, hbase, start,
+				size, arg4, 0);
+		break;
+	default:
+		pr_err("unknown function ID [%lu] for SBI extension [%d]\n",
+		       fid, ext);
+		result = -EINVAL;
+	}
+
+	if (ret.error) {
+		result = sbi_err_map_linux_errno(ret.error);
+		pr_err("%s: hbase = [%lu] hmask = [0x%lx] failed (error [%d])\n",
+		       __func__, hbase, hmask, result);
+	}
+
+	return result;
+}
+
+static int __sbi_rfence_v02(int fid, const struct cpumask *cpu_mask,
+			    unsigned long start, unsigned long size,
+			    unsigned long arg4, unsigned long arg5)
+{
+	unsigned long hartid, cpuid, hmask = 0, hbase = 0, htop = 0;
+	int result;
+
+	if (!cpu_mask || cpumask_empty(cpu_mask))
+		cpu_mask = cpu_online_mask;
+
+	for_each_cpu(cpuid, cpu_mask) {
+		hartid = cpuid_to_hartid_map(cpuid);
+		if (hmask) {
+			if (hartid + BITS_PER_LONG <= htop ||
+			    hbase + BITS_PER_LONG <= hartid) {
+				result = __sbi_rfence_v02_call(fid, hmask,
+						hbase, start, size, arg4, arg5);
+				if (result)
+					return result;
+				hmask = 0;
+			} else if (hartid < hbase) {
+				/* shift the mask to fit lower hartid */
+				hmask <<= hbase - hartid;
+				hbase = hartid;
+			}
+		}
+		if (!hmask) {
+			hbase = hartid;
+			htop = hartid;
+		} else if (hartid > htop) {
+			htop = hartid;
+		}
+		hmask |= BIT(hartid - hbase);
+	}
+
+	if (hmask) {
+		result = __sbi_rfence_v02_call(fid, hmask, hbase,
+					       start, size, arg4, arg5);
+		if (result)
+			return result;
+	}
+
+	return 0;
+}
+
+/**
+ * sbi_set_timer() - Program the timer for next timer event.
+ * @stime_value: The value after which next timer event should fire.
+ *
+ * Return: None.
+ */
+void sbi_set_timer(uint64_t stime_value)
+{
+	__sbi_set_timer(stime_value);
+}
+
+/**
+ * sbi_send_ipi() - Send an IPI to any hart.
+ * @cpu_mask: A cpu mask containing all the target harts.
+ *
+ * Return: 0 on success, appropriate linux error code otherwise.
+ */
+int sbi_send_ipi(const struct cpumask *cpu_mask)
+{
+	return __sbi_send_ipi(cpu_mask);
+}
+EXPORT_SYMBOL(sbi_send_ipi);
+
+/**
+ * sbi_remote_fence_i() - Execute FENCE.I instruction on given remote harts.
+ * @cpu_mask: A cpu mask containing all the target harts.
+ *
+ * Return: 0 on success, appropriate linux error code otherwise.
+ */
+int sbi_remote_fence_i(const struct cpumask *cpu_mask)
+{
+	return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_FENCE_I,
+			    cpu_mask, 0, 0, 0, 0);
+}
+EXPORT_SYMBOL(sbi_remote_fence_i);
+
+/**
+ * sbi_remote_sfence_vma() - Execute SFENCE.VMA instructions on given remote
+ *			     harts for the specified virtual address range.
+ * @cpu_mask: A cpu mask containing all the target harts.
+ * @start: Start of the virtual address
+ * @size: Total size of the virtual address range.
+ *
+ * Return: 0 on success, appropriate linux error code otherwise.
+ */
+int sbi_remote_sfence_vma(const struct cpumask *cpu_mask,
+			   unsigned long start,
+			   unsigned long size)
+{
+	return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_SFENCE_VMA,
+			    cpu_mask, start, size, 0, 0);
+}
+EXPORT_SYMBOL(sbi_remote_sfence_vma);
+
+/**
+ * sbi_remote_sfence_vma_asid() - Execute SFENCE.VMA instructions on given
+ * remote harts for a virtual address range belonging to a specific ASID.
+ *
+ * @cpu_mask: A cpu mask containing all the target harts.
+ * @start: Start of the virtual address
+ * @size: Total size of the virtual address range.
+ * @asid: The value of address space identifier (ASID).
+ *
+ * Return: 0 on success, appropriate linux error code otherwise.
+ */
+int sbi_remote_sfence_vma_asid(const struct cpumask *cpu_mask,
+				unsigned long start,
+				unsigned long size,
+				unsigned long asid)
+{
+	return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID,
+			    cpu_mask, start, size, asid, 0);
+}
+EXPORT_SYMBOL(sbi_remote_sfence_vma_asid);
+
+/**
+ * sbi_remote_hfence_gvma() - Execute HFENCE.GVMA instructions on given remote
+ *			   harts for the specified guest physical address range.
+ * @cpu_mask: A cpu mask containing all the target harts.
+ * @start: Start of the guest physical address
+ * @size: Total size of the guest physical address range.
+ *
+ * Return: None
+ */
+int sbi_remote_hfence_gvma(const struct cpumask *cpu_mask,
+			   unsigned long start,
+			   unsigned long size)
+{
+	return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA,
+			    cpu_mask, start, size, 0, 0);
+}
+EXPORT_SYMBOL_GPL(sbi_remote_hfence_gvma);
+
+/**
+ * sbi_remote_hfence_gvma_vmid() - Execute HFENCE.GVMA instructions on given
+ * remote harts for a guest physical address range belonging to a specific VMID.
+ *
+ * @cpu_mask: A cpu mask containing all the target harts.
+ * @start: Start of the guest physical address
+ * @size: Total size of the guest physical address range.
+ * @vmid: The value of guest ID (VMID).
+ *
+ * Return: 0 if success, Error otherwise.
+ */
+int sbi_remote_hfence_gvma_vmid(const struct cpumask *cpu_mask,
+				unsigned long start,
+				unsigned long size,
+				unsigned long vmid)
+{
+	return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA_VMID,
+			    cpu_mask, start, size, vmid, 0);
+}
+EXPORT_SYMBOL(sbi_remote_hfence_gvma_vmid);
+
+/**
+ * sbi_remote_hfence_vvma() - Execute HFENCE.VVMA instructions on given remote
+ *			     harts for the current guest virtual address range.
+ * @cpu_mask: A cpu mask containing all the target harts.
+ * @start: Start of the current guest virtual address
+ * @size: Total size of the current guest virtual address range.
+ *
+ * Return: None
+ */
+int sbi_remote_hfence_vvma(const struct cpumask *cpu_mask,
+			   unsigned long start,
+			   unsigned long size)
+{
+	return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA,
+			    cpu_mask, start, size, 0, 0);
+}
+EXPORT_SYMBOL(sbi_remote_hfence_vvma);
+
+/**
+ * sbi_remote_hfence_vvma_asid() - Execute HFENCE.VVMA instructions on given
+ * remote harts for current guest virtual address range belonging to a specific
+ * ASID.
+ *
+ * @cpu_mask: A cpu mask containing all the target harts.
+ * @start: Start of the current guest virtual address
+ * @size: Total size of the current guest virtual address range.
+ * @asid: The value of address space identifier (ASID).
+ *
+ * Return: None
+ */
+int sbi_remote_hfence_vvma_asid(const struct cpumask *cpu_mask,
+				unsigned long start,
+				unsigned long size,
+				unsigned long asid)
+{
+	return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA_ASID,
+			    cpu_mask, start, size, asid, 0);
+}
+EXPORT_SYMBOL(sbi_remote_hfence_vvma_asid);
+
+static void sbi_srst_reset(unsigned long type, unsigned long reason)
+{
+	sbi_ecall(SBI_EXT_SRST, SBI_EXT_SRST_RESET, type, reason,
+		  0, 0, 0, 0);
+	pr_warn("%s: type=0x%lx reason=0x%lx failed\n",
+		__func__, type, reason);
+}
+
+static int sbi_srst_reboot(struct notifier_block *this,
+			   unsigned long mode, void *cmd)
+{
+	sbi_srst_reset((mode == REBOOT_WARM || mode == REBOOT_SOFT) ?
+		       SBI_SRST_RESET_TYPE_WARM_REBOOT :
+		       SBI_SRST_RESET_TYPE_COLD_REBOOT,
+		       SBI_SRST_RESET_REASON_NONE);
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block sbi_srst_reboot_nb;
+
+static void sbi_srst_power_off(void)
+{
+	sbi_srst_reset(SBI_SRST_RESET_TYPE_SHUTDOWN,
+		       SBI_SRST_RESET_REASON_NONE);
+}
+
+/**
+ * sbi_probe_extension() - Check if an SBI extension ID is supported or not.
+ * @extid: The extension ID to be probed.
+ *
+ * Return: 1 or an extension specific nonzero value if yes, 0 otherwise.
+ */
+long sbi_probe_extension(int extid)
+{
+	struct sbiret ret;
+
+	ret = sbi_ecall(SBI_EXT_BASE, SBI_EXT_BASE_PROBE_EXT, extid,
+			0, 0, 0, 0, 0);
+	if (!ret.error)
+		return ret.value;
+
+	return 0;
+}
+EXPORT_SYMBOL(sbi_probe_extension);
+
+static long __sbi_base_ecall(int fid)
+{
+	struct sbiret ret;
+
+	ret = sbi_ecall(SBI_EXT_BASE, fid, 0, 0, 0, 0, 0, 0);
+	if (!ret.error)
+		return ret.value;
+	else
+		return sbi_err_map_linux_errno(ret.error);
+}
+
+static inline long sbi_get_spec_version(void)
+{
+	return __sbi_base_ecall(SBI_EXT_BASE_GET_SPEC_VERSION);
+}
+
+static inline long sbi_get_firmware_id(void)
+{
+	return __sbi_base_ecall(SBI_EXT_BASE_GET_IMP_ID);
+}
+
+static inline long sbi_get_firmware_version(void)
+{
+	return __sbi_base_ecall(SBI_EXT_BASE_GET_IMP_VERSION);
+}
+
+long sbi_get_mvendorid(void)
+{
+	return __sbi_base_ecall(SBI_EXT_BASE_GET_MVENDORID);
+}
+
+long sbi_get_marchid(void)
+{
+	return __sbi_base_ecall(SBI_EXT_BASE_GET_MARCHID);
+}
+
+long sbi_get_mimpid(void)
+{
+	return __sbi_base_ecall(SBI_EXT_BASE_GET_MIMPID);
+}
+
+static void sbi_send_cpumask_ipi(const struct cpumask *target)
+{
+	sbi_send_ipi(target);
+}
+
+static const struct riscv_ipi_ops sbi_ipi_ops = {
+	.ipi_inject = sbi_send_cpumask_ipi
+};
+
+void __init sbi_init(void)
+{
+	int ret;
+
+	sbi_set_power_off();
+	ret = sbi_get_spec_version();
+	if (ret > 0)
+		sbi_spec_version = ret;
+
+	pr_info("SBI specification v%lu.%lu detected\n",
+		sbi_major_version(), sbi_minor_version());
+
+	if (!sbi_spec_is_0_1()) {
+		pr_info("SBI implementation ID=0x%lx Version=0x%lx\n",
+			sbi_get_firmware_id(), sbi_get_firmware_version());
+		if (sbi_probe_extension(SBI_EXT_TIME)) {
+			__sbi_set_timer = __sbi_set_timer_v02;
+			pr_info("SBI TIME extension detected\n");
+		} else {
+			__sbi_set_timer = __sbi_set_timer_v01;
+		}
+		if (sbi_probe_extension(SBI_EXT_IPI)) {
+			__sbi_send_ipi	= __sbi_send_ipi_v02;
+			pr_info("SBI IPI extension detected\n");
+		} else {
+			__sbi_send_ipi	= __sbi_send_ipi_v01;
+		}
+		if (sbi_probe_extension(SBI_EXT_RFENCE)) {
+			__sbi_rfence	= __sbi_rfence_v02;
+			pr_info("SBI RFENCE extension detected\n");
+		} else {
+			__sbi_rfence	= __sbi_rfence_v01;
+		}
+		if ((sbi_spec_version >= sbi_mk_version(0, 3)) &&
+		    sbi_probe_extension(SBI_EXT_SRST)) {
+			pr_info("SBI SRST extension detected\n");
+			pm_power_off = sbi_srst_power_off;
+			sbi_srst_reboot_nb.notifier_call = sbi_srst_reboot;
+			sbi_srst_reboot_nb.priority = 192;
+			register_restart_handler(&sbi_srst_reboot_nb);
+		}
+	} else {
+		__sbi_set_timer = __sbi_set_timer_v01;
+		__sbi_send_ipi	= __sbi_send_ipi_v01;
+		__sbi_rfence	= __sbi_rfence_v01;
+	}
+
+	riscv_set_ipi_ops(&sbi_ipi_ops);
+}
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
new file mode 100644
index 000000000..2acf51c23
--- /dev/null
+++ b/arch/riscv/kernel/setup.c
@@ -0,0 +1,328 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2009 Sunplus Core Technology Co., Ltd.
+ *  Chen Liqin <liqin.chen@sunplusct.com>
+ *  Lennox Wu <lennox.wu@sunplusct.com>
+ * Copyright (C) 2012 Regents of the University of California
+ * Copyright (C) 2020 FORTH-ICS/CARV
+ *  Nick Kossifidis <mick@ics.forth.gr>
+ */
+
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/memblock.h>
+#include <linux/sched.h>
+#include <linux/console.h>
+#include <linux/screen_info.h>
+#include <linux/of_fdt.h>
+#include <linux/of_platform.h>
+#include <linux/sched/task.h>
+#include <linux/smp.h>
+#include <linux/efi.h>
+#include <linux/crash_dump.h>
+
+#include <asm/alternative.h>
+#include <asm/cacheflush.h>
+#include <asm/cpu_ops.h>
+#include <asm/early_ioremap.h>
+#include <asm/pgtable.h>
+#include <asm/setup.h>
+#include <asm/set_memory.h>
+#include <asm/sections.h>
+#include <asm/sbi.h>
+#include <asm/tlbflush.h>
+#include <asm/thread_info.h>
+#include <asm/kasan.h>
+#include <asm/efi.h>
+
+#include "head.h"
+
+#if defined(CONFIG_DUMMY_CONSOLE) || defined(CONFIG_EFI)
+struct screen_info screen_info __section(".data") = {
+	.orig_video_lines	= 30,
+	.orig_video_cols	= 80,
+	.orig_video_mode	= 0,
+	.orig_video_ega_bx	= 0,
+	.orig_video_isVGA	= 1,
+	.orig_video_points	= 8
+};
+#endif
+
+/*
+ * The lucky hart to first increment this variable will boot the other cores.
+ * This is used before the kernel initializes the BSS so it can't be in the
+ * BSS.
+ */
+atomic_t hart_lottery __section(".sdata")
+#ifdef CONFIG_XIP_KERNEL
+= ATOMIC_INIT(0xC001BEEF)
+#endif
+;
+unsigned long boot_cpu_hartid;
+static DEFINE_PER_CPU(struct cpu, cpu_devices);
+
+/*
+ * Place kernel memory regions on the resource tree so that
+ * kexec-tools can retrieve them from /proc/iomem. While there
+ * also add "System RAM" regions for compatibility with other
+ * archs, and the rest of the known regions for completeness.
+ */
+static struct resource kimage_res = { .name = "Kernel image", };
+static struct resource code_res = { .name = "Kernel code", };
+static struct resource data_res = { .name = "Kernel data", };
+static struct resource rodata_res = { .name = "Kernel rodata", };
+static struct resource bss_res = { .name = "Kernel bss", };
+#ifdef CONFIG_CRASH_DUMP
+static struct resource elfcorehdr_res = { .name = "ELF Core hdr", };
+#endif
+
+static int __init add_resource(struct resource *parent,
+				struct resource *res)
+{
+	int ret = 0;
+
+	ret = insert_resource(parent, res);
+	if (ret < 0) {
+		pr_err("Failed to add a %s resource at %llx\n",
+			res->name, (unsigned long long) res->start);
+		return ret;
+	}
+
+	return 1;
+}
+
+static int __init add_kernel_resources(void)
+{
+	int ret = 0;
+
+	/*
+	 * The memory region of the kernel image is continuous and
+	 * was reserved on setup_bootmem, register it here as a
+	 * resource, with the various segments of the image as
+	 * child nodes.
+	 */
+
+	code_res.start = __pa_symbol(_text);
+	code_res.end = __pa_symbol(_etext) - 1;
+	code_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
+
+	rodata_res.start = __pa_symbol(__start_rodata);
+	rodata_res.end = __pa_symbol(__end_rodata) - 1;
+	rodata_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
+
+	data_res.start = __pa_symbol(_data);
+	data_res.end = __pa_symbol(_edata) - 1;
+	data_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
+
+	bss_res.start = __pa_symbol(__bss_start);
+	bss_res.end = __pa_symbol(__bss_stop) - 1;
+	bss_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
+
+	kimage_res.start = code_res.start;
+	kimage_res.end = bss_res.end;
+	kimage_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
+
+	ret = add_resource(&iomem_resource, &kimage_res);
+	if (ret < 0)
+		return ret;
+
+	ret = add_resource(&kimage_res, &code_res);
+	if (ret < 0)
+		return ret;
+
+	ret = add_resource(&kimage_res, &rodata_res);
+	if (ret < 0)
+		return ret;
+
+	ret = add_resource(&kimage_res, &data_res);
+	if (ret < 0)
+		return ret;
+
+	ret = add_resource(&kimage_res, &bss_res);
+
+	return ret;
+}
+
+static void __init init_resources(void)
+{
+	struct memblock_region *region = NULL;
+	struct resource *res = NULL;
+	struct resource *mem_res = NULL;
+	size_t mem_res_sz = 0;
+	int num_resources = 0, res_idx = 0;
+	int ret = 0;
+
+	/* + 1 as memblock_alloc() might increase memblock.reserved.cnt */
+	num_resources = memblock.memory.cnt + memblock.reserved.cnt + 1;
+	res_idx = num_resources - 1;
+
+	mem_res_sz = num_resources * sizeof(*mem_res);
+	mem_res = memblock_alloc(mem_res_sz, SMP_CACHE_BYTES);
+	if (!mem_res)
+		panic("%s: Failed to allocate %zu bytes\n", __func__, mem_res_sz);
+
+	/*
+	 * Start by adding the reserved regions, if they overlap
+	 * with /memory regions, insert_resource later on will take
+	 * care of it.
+	 */
+	ret = add_kernel_resources();
+	if (ret < 0)
+		goto error;
+
+#ifdef CONFIG_KEXEC_CORE
+	if (crashk_res.start != crashk_res.end) {
+		ret = add_resource(&iomem_resource, &crashk_res);
+		if (ret < 0)
+			goto error;
+	}
+#endif
+
+#ifdef CONFIG_CRASH_DUMP
+	if (elfcorehdr_size > 0) {
+		elfcorehdr_res.start = elfcorehdr_addr;
+		elfcorehdr_res.end = elfcorehdr_addr + elfcorehdr_size - 1;
+		elfcorehdr_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
+		add_resource(&iomem_resource, &elfcorehdr_res);
+	}
+#endif
+
+	for_each_reserved_mem_region(region) {
+		res = &mem_res[res_idx--];
+
+		res->name = "Reserved";
+		res->flags = IORESOURCE_MEM | IORESOURCE_EXCLUSIVE;
+		res->start = __pfn_to_phys(memblock_region_reserved_base_pfn(region));
+		res->end = __pfn_to_phys(memblock_region_reserved_end_pfn(region)) - 1;
+
+		/*
+		 * Ignore any other reserved regions within
+		 * system memory.
+		 */
+		if (memblock_is_memory(res->start)) {
+			/* Re-use this pre-allocated resource */
+			res_idx++;
+			continue;
+		}
+
+		ret = add_resource(&iomem_resource, res);
+		if (ret < 0)
+			goto error;
+	}
+
+	/* Add /memory regions to the resource tree */
+	for_each_mem_region(region) {
+		res = &mem_res[res_idx--];
+
+		if (unlikely(memblock_is_nomap(region))) {
+			res->name = "Reserved";
+			res->flags = IORESOURCE_MEM | IORESOURCE_EXCLUSIVE;
+		} else {
+			res->name = "System RAM";
+			res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
+		}
+
+		res->start = __pfn_to_phys(memblock_region_memory_base_pfn(region));
+		res->end = __pfn_to_phys(memblock_region_memory_end_pfn(region)) - 1;
+
+		ret = add_resource(&iomem_resource, res);
+		if (ret < 0)
+			goto error;
+	}
+
+	/* Clean-up any unused pre-allocated resources */
+	if (res_idx >= 0)
+		memblock_free(mem_res, (res_idx + 1) * sizeof(*mem_res));
+	return;
+
+ error:
+	/* Better an empty resource tree than an inconsistent one */
+	release_child_resources(&iomem_resource);
+	memblock_free(mem_res, mem_res_sz);
+}
+
+
+static void __init parse_dtb(void)
+{
+	/* Early scan of device tree from init memory */
+	if (early_init_dt_scan(dtb_early_va)) {
+		const char *name = of_flat_dt_get_machine_name();
+
+		if (name) {
+			pr_info("Machine model: %s\n", name);
+			dump_stack_set_arch_desc("%s (DT)", name);
+		}
+	} else {
+		pr_err("No DTB passed to the kernel\n");
+	}
+
+#ifdef CONFIG_CMDLINE_FORCE
+	strscpy(boot_command_line, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
+	pr_info("Forcing kernel command line to: %s\n", boot_command_line);
+#endif
+}
+
+void __init setup_arch(char **cmdline_p)
+{
+	parse_dtb();
+	setup_initial_init_mm(_stext, _etext, _edata, _end);
+
+	*cmdline_p = boot_command_line;
+
+	early_ioremap_setup();
+	jump_label_init();
+	parse_early_param();
+
+	efi_init();
+	paging_init();
+#if IS_ENABLED(CONFIG_BUILTIN_DTB)
+	unflatten_and_copy_device_tree();
+#else
+	unflatten_device_tree();
+#endif
+	misc_mem_init();
+
+	init_resources();
+	sbi_init();
+
+#ifdef CONFIG_KASAN
+	kasan_init();
+#endif
+
+#ifdef CONFIG_SMP
+	setup_smp();
+#endif
+
+	riscv_init_cbom_blocksize();
+	riscv_fill_hwcap();
+	apply_boot_alternatives();
+}
+
+static int __init topology_init(void)
+{
+	int i, ret;
+
+	for_each_possible_cpu(i) {
+		struct cpu *cpu = &per_cpu(cpu_devices, i);
+
+		cpu->hotpluggable = cpu_has_hotplug(i);
+		ret = register_cpu(cpu, i);
+		if (unlikely(ret))
+			pr_warn("Warning: %s: register_cpu %d failed (%d)\n",
+			       __func__, i, ret);
+	}
+
+	return 0;
+}
+subsys_initcall(topology_init);
+
+void free_initmem(void)
+{
+	if (IS_ENABLED(CONFIG_STRICT_KERNEL_RWX)) {
+		set_kernel_memory(lm_alias(__init_begin), lm_alias(__init_end), set_memory_rw_nx);
+		if (IS_ENABLED(CONFIG_64BIT))
+			set_kernel_memory(__init_begin, __init_end, set_memory_nx);
+	}
+
+	free_initmem_default(POISON_FREE_INITMEM);
+}
diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c
new file mode 100644
index 000000000..dee66c929
--- /dev/null
+++ b/arch/riscv/kernel/signal.c
@@ -0,0 +1,346 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2009 Sunplus Core Technology Co., Ltd.
+ *  Chen Liqin <liqin.chen@sunplusct.com>
+ *  Lennox Wu <lennox.wu@sunplusct.com>
+ * Copyright (C) 2012 Regents of the University of California
+ */
+
+#include <linux/compat.h>
+#include <linux/signal.h>
+#include <linux/uaccess.h>
+#include <linux/syscalls.h>
+#include <linux/resume_user_mode.h>
+#include <linux/linkage.h>
+
+#include <asm/ucontext.h>
+#include <asm/vdso.h>
+#include <asm/signal.h>
+#include <asm/signal32.h>
+#include <asm/switch_to.h>
+#include <asm/csr.h>
+#include <asm/cacheflush.h>
+
+extern u32 __user_rt_sigreturn[2];
+
+#define DEBUG_SIG 0
+
+struct rt_sigframe {
+	struct siginfo info;
+	struct ucontext uc;
+#ifndef CONFIG_MMU
+	u32 sigreturn_code[2];
+#endif
+};
+
+#ifdef CONFIG_FPU
+static long restore_fp_state(struct pt_regs *regs,
+			     union __riscv_fp_state __user *sc_fpregs)
+{
+	long err;
+	struct __riscv_d_ext_state __user *state = &sc_fpregs->d;
+	size_t i;
+
+	err = __copy_from_user(&current->thread.fstate, state, sizeof(*state));
+	if (unlikely(err))
+		return err;
+
+	fstate_restore(current, regs);
+
+	/* We support no other extension state at this time. */
+	for (i = 0; i < ARRAY_SIZE(sc_fpregs->q.reserved); i++) {
+		u32 value;
+
+		err = __get_user(value, &sc_fpregs->q.reserved[i]);
+		if (unlikely(err))
+			break;
+		if (value != 0)
+			return -EINVAL;
+	}
+
+	return err;
+}
+
+static long save_fp_state(struct pt_regs *regs,
+			  union __riscv_fp_state __user *sc_fpregs)
+{
+	long err;
+	struct __riscv_d_ext_state __user *state = &sc_fpregs->d;
+	size_t i;
+
+	fstate_save(current, regs);
+	err = __copy_to_user(state, &current->thread.fstate, sizeof(*state));
+	if (unlikely(err))
+		return err;
+
+	/* We support no other extension state at this time. */
+	for (i = 0; i < ARRAY_SIZE(sc_fpregs->q.reserved); i++) {
+		err = __put_user(0, &sc_fpregs->q.reserved[i]);
+		if (unlikely(err))
+			break;
+	}
+
+	return err;
+}
+#else
+#define save_fp_state(task, regs) (0)
+#define restore_fp_state(task, regs) (0)
+#endif
+
+static long restore_sigcontext(struct pt_regs *regs,
+	struct sigcontext __user *sc)
+{
+	long err;
+	/* sc_regs is structured the same as the start of pt_regs */
+	err = __copy_from_user(regs, &sc->sc_regs, sizeof(sc->sc_regs));
+	/* Restore the floating-point state. */
+	if (has_fpu())
+		err |= restore_fp_state(regs, &sc->sc_fpregs);
+	return err;
+}
+
+SYSCALL_DEFINE0(rt_sigreturn)
+{
+	struct pt_regs *regs = current_pt_regs();
+	struct rt_sigframe __user *frame;
+	struct task_struct *task;
+	sigset_t set;
+
+	/* Always make any pending restarted system calls return -EINTR */
+	current->restart_block.fn = do_no_restart_syscall;
+
+	frame = (struct rt_sigframe __user *)regs->sp;
+
+	if (!access_ok(frame, sizeof(*frame)))
+		goto badframe;
+
+	if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
+		goto badframe;
+
+	set_current_blocked(&set);
+
+	if (restore_sigcontext(regs, &frame->uc.uc_mcontext))
+		goto badframe;
+
+	if (restore_altstack(&frame->uc.uc_stack))
+		goto badframe;
+
+	regs->cause = -1UL;
+
+	return regs->a0;
+
+badframe:
+	task = current;
+	if (show_unhandled_signals) {
+		pr_info_ratelimited(
+			"%s[%d]: bad frame in %s: frame=%p pc=%p sp=%p\n",
+			task->comm, task_pid_nr(task), __func__,
+			frame, (void *)regs->epc, (void *)regs->sp);
+	}
+	force_sig(SIGSEGV);
+	return 0;
+}
+
+static long setup_sigcontext(struct rt_sigframe __user *frame,
+	struct pt_regs *regs)
+{
+	struct sigcontext __user *sc = &frame->uc.uc_mcontext;
+	long err;
+	/* sc_regs is structured the same as the start of pt_regs */
+	err = __copy_to_user(&sc->sc_regs, regs, sizeof(sc->sc_regs));
+	/* Save the floating-point state. */
+	if (has_fpu())
+		err |= save_fp_state(regs, &sc->sc_fpregs);
+	return err;
+}
+
+static inline void __user *get_sigframe(struct ksignal *ksig,
+	struct pt_regs *regs, size_t framesize)
+{
+	unsigned long sp;
+	/* Default to using normal stack */
+	sp = regs->sp;
+
+	/*
+	 * If we are on the alternate signal stack and would overflow it, don't.
+	 * Return an always-bogus address instead so we will die with SIGSEGV.
+	 */
+	if (on_sig_stack(sp) && !likely(on_sig_stack(sp - framesize)))
+		return (void __user __force *)(-1UL);
+
+	/* This is the X/Open sanctioned signal stack switching. */
+	sp = sigsp(sp, ksig) - framesize;
+
+	/* Align the stack frame. */
+	sp &= ~0xfUL;
+
+	return (void __user *)sp;
+}
+
+static int setup_rt_frame(struct ksignal *ksig, sigset_t *set,
+	struct pt_regs *regs)
+{
+	struct rt_sigframe __user *frame;
+	long err = 0;
+	unsigned long __maybe_unused addr;
+
+	frame = get_sigframe(ksig, regs, sizeof(*frame));
+	if (!access_ok(frame, sizeof(*frame)))
+		return -EFAULT;
+
+	err |= copy_siginfo_to_user(&frame->info, &ksig->info);
+
+	/* Create the ucontext. */
+	err |= __put_user(0, &frame->uc.uc_flags);
+	err |= __put_user(NULL, &frame->uc.uc_link);
+	err |= __save_altstack(&frame->uc.uc_stack, regs->sp);
+	err |= setup_sigcontext(frame, regs);
+	err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
+	if (err)
+		return -EFAULT;
+
+	/* Set up to return from userspace. */
+#ifdef CONFIG_MMU
+	regs->ra = (unsigned long)VDSO_SYMBOL(
+		current->mm->context.vdso, rt_sigreturn);
+#else
+	/*
+	 * For the nommu case we don't have a VDSO.  Instead we push two
+	 * instructions to call the rt_sigreturn syscall onto the user stack.
+	 */
+	if (copy_to_user(&frame->sigreturn_code, __user_rt_sigreturn,
+			 sizeof(frame->sigreturn_code)))
+		return -EFAULT;
+
+	addr = (unsigned long)&frame->sigreturn_code;
+	/* Make sure the two instructions are pushed to icache. */
+	flush_icache_range(addr, addr + sizeof(frame->sigreturn_code));
+
+	regs->ra = addr;
+#endif /* CONFIG_MMU */
+
+	/*
+	 * Set up registers for signal handler.
+	 * Registers that we don't modify keep the value they had from
+	 * user-space at the time we took the signal.
+	 * We always pass siginfo and mcontext, regardless of SA_SIGINFO,
+	 * since some things rely on this (e.g. glibc's debug/segfault.c).
+	 */
+	regs->epc = (unsigned long)ksig->ka.sa.sa_handler;
+	regs->sp = (unsigned long)frame;
+	regs->a0 = ksig->sig;                     /* a0: signal number */
+	regs->a1 = (unsigned long)(&frame->info); /* a1: siginfo pointer */
+	regs->a2 = (unsigned long)(&frame->uc);   /* a2: ucontext pointer */
+
+#if DEBUG_SIG
+	pr_info("SIG deliver (%s:%d): sig=%d pc=%p ra=%p sp=%p\n",
+		current->comm, task_pid_nr(current), ksig->sig,
+		(void *)regs->epc, (void *)regs->ra, frame);
+#endif
+
+	return 0;
+}
+
+static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
+{
+	sigset_t *oldset = sigmask_to_save();
+	int ret;
+
+	/* Are we from a system call? */
+	if (regs->cause == EXC_SYSCALL) {
+		/* Avoid additional syscall restarting via ret_from_exception */
+		regs->cause = -1UL;
+		/* If so, check system call restarting.. */
+		switch (regs->a0) {
+		case -ERESTART_RESTARTBLOCK:
+		case -ERESTARTNOHAND:
+			regs->a0 = -EINTR;
+			break;
+
+		case -ERESTARTSYS:
+			if (!(ksig->ka.sa.sa_flags & SA_RESTART)) {
+				regs->a0 = -EINTR;
+				break;
+			}
+			fallthrough;
+		case -ERESTARTNOINTR:
+                        regs->a0 = regs->orig_a0;
+			regs->epc -= 0x4;
+			break;
+		}
+	}
+
+	rseq_signal_deliver(ksig, regs);
+
+	/* Set up the stack frame */
+	if (is_compat_task())
+		ret = compat_setup_rt_frame(ksig, oldset, regs);
+	else
+		ret = setup_rt_frame(ksig, oldset, regs);
+
+	signal_setup_done(ret, ksig, 0);
+}
+
+static void do_signal(struct pt_regs *regs)
+{
+	struct ksignal ksig;
+
+	if (get_signal(&ksig)) {
+		/* Actually deliver the signal */
+		handle_signal(&ksig, regs);
+		return;
+	}
+
+	/* Did we come from a system call? */
+	if (regs->cause == EXC_SYSCALL) {
+		/* Avoid additional syscall restarting via ret_from_exception */
+		regs->cause = -1UL;
+
+		/* Restart the system call - no handlers present */
+		switch (regs->a0) {
+		case -ERESTARTNOHAND:
+		case -ERESTARTSYS:
+		case -ERESTARTNOINTR:
+                        regs->a0 = regs->orig_a0;
+			regs->epc -= 0x4;
+			break;
+		case -ERESTART_RESTARTBLOCK:
+                        regs->a0 = regs->orig_a0;
+			regs->a7 = __NR_restart_syscall;
+			regs->epc -= 0x4;
+			break;
+		}
+	}
+
+	/*
+	 * If there is no signal to deliver, we just put the saved
+	 * sigmask back.
+	 */
+	restore_saved_sigmask();
+}
+
+/*
+ * Handle any pending work on the resume-to-userspace path, as indicated by
+ * _TIF_WORK_MASK. Entered from assembly with IRQs off.
+ */
+asmlinkage __visible void do_work_pending(struct pt_regs *regs,
+					  unsigned long thread_info_flags)
+{
+	do {
+		if (thread_info_flags & _TIF_NEED_RESCHED) {
+			schedule();
+		} else {
+			local_irq_enable();
+			if (thread_info_flags & _TIF_UPROBE)
+				uprobe_notify_resume(regs);
+			/* Handle pending signal delivery */
+			if (thread_info_flags & (_TIF_SIGPENDING |
+						 _TIF_NOTIFY_SIGNAL))
+				do_signal(regs);
+			if (thread_info_flags & _TIF_NOTIFY_RESUME)
+				resume_user_mode_work(regs);
+		}
+		local_irq_disable();
+		thread_info_flags = read_thread_flags();
+	} while (thread_info_flags & _TIF_WORK_MASK);
+}
diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c
new file mode 100644
index 000000000..7f534023f
--- /dev/null
+++ b/arch/riscv/kernel/smp.c
@@ -0,0 +1,334 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * SMP initialisation and IPI support
+ * Based on arch/arm64/kernel/smp.c
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2015 Regents of the University of California
+ * Copyright (C) 2017 SiFive
+ */
+
+#include <linux/cpu.h>
+#include <linux/clockchips.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/kexec.h>
+#include <linux/profile.h>
+#include <linux/smp.h>
+#include <linux/sched.h>
+#include <linux/seq_file.h>
+#include <linux/delay.h>
+#include <linux/irq_work.h>
+
+#include <asm/sbi.h>
+#include <asm/tlbflush.h>
+#include <asm/cacheflush.h>
+#include <asm/cpu_ops.h>
+
+enum ipi_message_type {
+	IPI_RESCHEDULE,
+	IPI_CALL_FUNC,
+	IPI_CPU_STOP,
+	IPI_CPU_CRASH_STOP,
+	IPI_IRQ_WORK,
+	IPI_TIMER,
+	IPI_MAX
+};
+
+unsigned long __cpuid_to_hartid_map[NR_CPUS] __ro_after_init = {
+	[0 ... NR_CPUS-1] = INVALID_HARTID
+};
+
+void __init smp_setup_processor_id(void)
+{
+	cpuid_to_hartid_map(0) = boot_cpu_hartid;
+}
+
+/* A collection of single bit ipi messages.  */
+static struct {
+	unsigned long stats[IPI_MAX] ____cacheline_aligned;
+	unsigned long bits ____cacheline_aligned;
+} ipi_data[NR_CPUS] __cacheline_aligned;
+
+int riscv_hartid_to_cpuid(unsigned long hartid)
+{
+	int i;
+
+	for (i = 0; i < NR_CPUS; i++)
+		if (cpuid_to_hartid_map(i) == hartid)
+			return i;
+
+	return -ENOENT;
+}
+
+bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
+{
+	return phys_id == cpuid_to_hartid_map(cpu);
+}
+
+static void ipi_stop(void)
+{
+	set_cpu_online(smp_processor_id(), false);
+	while (1)
+		wait_for_interrupt();
+}
+
+#ifdef CONFIG_KEXEC_CORE
+static atomic_t waiting_for_crash_ipi = ATOMIC_INIT(0);
+
+static inline void ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs)
+{
+	crash_save_cpu(regs, cpu);
+
+	atomic_dec(&waiting_for_crash_ipi);
+
+	local_irq_disable();
+
+#ifdef CONFIG_HOTPLUG_CPU
+	if (cpu_has_hotplug(cpu))
+		cpu_ops[cpu]->cpu_stop();
+#endif
+
+	for(;;)
+		wait_for_interrupt();
+}
+#else
+static inline void ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs)
+{
+	unreachable();
+}
+#endif
+
+static const struct riscv_ipi_ops *ipi_ops __ro_after_init;
+
+void riscv_set_ipi_ops(const struct riscv_ipi_ops *ops)
+{
+	ipi_ops = ops;
+}
+EXPORT_SYMBOL_GPL(riscv_set_ipi_ops);
+
+void riscv_clear_ipi(void)
+{
+	if (ipi_ops && ipi_ops->ipi_clear)
+		ipi_ops->ipi_clear();
+
+	csr_clear(CSR_IP, IE_SIE);
+}
+EXPORT_SYMBOL_GPL(riscv_clear_ipi);
+
+static void send_ipi_mask(const struct cpumask *mask, enum ipi_message_type op)
+{
+	int cpu;
+
+	smp_mb__before_atomic();
+	for_each_cpu(cpu, mask)
+		set_bit(op, &ipi_data[cpu].bits);
+	smp_mb__after_atomic();
+
+	if (ipi_ops && ipi_ops->ipi_inject)
+		ipi_ops->ipi_inject(mask);
+	else
+		pr_warn("SMP: IPI inject method not available\n");
+}
+
+static void send_ipi_single(int cpu, enum ipi_message_type op)
+{
+	smp_mb__before_atomic();
+	set_bit(op, &ipi_data[cpu].bits);
+	smp_mb__after_atomic();
+
+	if (ipi_ops && ipi_ops->ipi_inject)
+		ipi_ops->ipi_inject(cpumask_of(cpu));
+	else
+		pr_warn("SMP: IPI inject method not available\n");
+}
+
+#ifdef CONFIG_IRQ_WORK
+void arch_irq_work_raise(void)
+{
+	send_ipi_single(smp_processor_id(), IPI_IRQ_WORK);
+}
+#endif
+
+void handle_IPI(struct pt_regs *regs)
+{
+	unsigned int cpu = smp_processor_id();
+	unsigned long *pending_ipis = &ipi_data[cpu].bits;
+	unsigned long *stats = ipi_data[cpu].stats;
+
+	riscv_clear_ipi();
+
+	while (true) {
+		unsigned long ops;
+
+		/* Order bit clearing and data access. */
+		mb();
+
+		ops = xchg(pending_ipis, 0);
+		if (ops == 0)
+			return;
+
+		if (ops & (1 << IPI_RESCHEDULE)) {
+			stats[IPI_RESCHEDULE]++;
+			scheduler_ipi();
+		}
+
+		if (ops & (1 << IPI_CALL_FUNC)) {
+			stats[IPI_CALL_FUNC]++;
+			generic_smp_call_function_interrupt();
+		}
+
+		if (ops & (1 << IPI_CPU_STOP)) {
+			stats[IPI_CPU_STOP]++;
+			ipi_stop();
+		}
+
+		if (ops & (1 << IPI_CPU_CRASH_STOP)) {
+			ipi_cpu_crash_stop(cpu, get_irq_regs());
+		}
+
+		if (ops & (1 << IPI_IRQ_WORK)) {
+			stats[IPI_IRQ_WORK]++;
+			irq_work_run();
+		}
+
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+		if (ops & (1 << IPI_TIMER)) {
+			stats[IPI_TIMER]++;
+			tick_receive_broadcast();
+		}
+#endif
+		BUG_ON((ops >> IPI_MAX) != 0);
+
+		/* Order data access and bit testing. */
+		mb();
+	}
+}
+
+static const char * const ipi_names[] = {
+	[IPI_RESCHEDULE]	= "Rescheduling interrupts",
+	[IPI_CALL_FUNC]		= "Function call interrupts",
+	[IPI_CPU_STOP]		= "CPU stop interrupts",
+	[IPI_CPU_CRASH_STOP]	= "CPU stop (for crash dump) interrupts",
+	[IPI_IRQ_WORK]		= "IRQ work interrupts",
+	[IPI_TIMER]		= "Timer broadcast interrupts",
+};
+
+void show_ipi_stats(struct seq_file *p, int prec)
+{
+	unsigned int cpu, i;
+
+	for (i = 0; i < IPI_MAX; i++) {
+		seq_printf(p, "%*s%u:%s", prec - 1, "IPI", i,
+			   prec >= 4 ? " " : "");
+		for_each_online_cpu(cpu)
+			seq_printf(p, "%10lu ", ipi_data[cpu].stats[i]);
+		seq_printf(p, " %s\n", ipi_names[i]);
+	}
+}
+
+void arch_send_call_function_ipi_mask(struct cpumask *mask)
+{
+	send_ipi_mask(mask, IPI_CALL_FUNC);
+}
+
+void arch_send_call_function_single_ipi(int cpu)
+{
+	send_ipi_single(cpu, IPI_CALL_FUNC);
+}
+
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+void tick_broadcast(const struct cpumask *mask)
+{
+	send_ipi_mask(mask, IPI_TIMER);
+}
+#endif
+
+void smp_send_stop(void)
+{
+	unsigned long timeout;
+
+	if (num_online_cpus() > 1) {
+		cpumask_t mask;
+
+		cpumask_copy(&mask, cpu_online_mask);
+		cpumask_clear_cpu(smp_processor_id(), &mask);
+
+		if (system_state <= SYSTEM_RUNNING)
+			pr_crit("SMP: stopping secondary CPUs\n");
+		send_ipi_mask(&mask, IPI_CPU_STOP);
+	}
+
+	/* Wait up to one second for other CPUs to stop */
+	timeout = USEC_PER_SEC;
+	while (num_online_cpus() > 1 && timeout--)
+		udelay(1);
+
+	if (num_online_cpus() > 1)
+		pr_warn("SMP: failed to stop secondary CPUs %*pbl\n",
+			   cpumask_pr_args(cpu_online_mask));
+}
+
+#ifdef CONFIG_KEXEC_CORE
+/*
+ * The number of CPUs online, not counting this CPU (which may not be
+ * fully online and so not counted in num_online_cpus()).
+ */
+static inline unsigned int num_other_online_cpus(void)
+{
+	unsigned int this_cpu_online = cpu_online(smp_processor_id());
+
+	return num_online_cpus() - this_cpu_online;
+}
+
+void crash_smp_send_stop(void)
+{
+	static int cpus_stopped;
+	cpumask_t mask;
+	unsigned long timeout;
+
+	/*
+	 * This function can be called twice in panic path, but obviously
+	 * we execute this only once.
+	 */
+	if (cpus_stopped)
+		return;
+
+	cpus_stopped = 1;
+
+	/*
+	 * If this cpu is the only one alive at this point in time, online or
+	 * not, there are no stop messages to be sent around, so just back out.
+	 */
+	if (num_other_online_cpus() == 0)
+		return;
+
+	cpumask_copy(&mask, cpu_online_mask);
+	cpumask_clear_cpu(smp_processor_id(), &mask);
+
+	atomic_set(&waiting_for_crash_ipi, num_other_online_cpus());
+
+	pr_crit("SMP: stopping secondary CPUs\n");
+	send_ipi_mask(&mask, IPI_CPU_CRASH_STOP);
+
+	/* Wait up to one second for other CPUs to stop */
+	timeout = USEC_PER_SEC;
+	while ((atomic_read(&waiting_for_crash_ipi) > 0) && timeout--)
+		udelay(1);
+
+	if (atomic_read(&waiting_for_crash_ipi) > 0)
+		pr_warn("SMP: failed to stop secondary CPUs %*pbl\n",
+			cpumask_pr_args(&mask));
+}
+
+bool smp_crash_stop_failed(void)
+{
+	return (atomic_read(&waiting_for_crash_ipi) > 0);
+}
+#endif
+
+void smp_send_reschedule(int cpu)
+{
+	send_ipi_single(cpu, IPI_RESCHEDULE);
+}
+EXPORT_SYMBOL_GPL(smp_send_reschedule);
diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c
new file mode 100644
index 000000000..ddb2afba6
--- /dev/null
+++ b/arch/riscv/kernel/smpboot.c
@@ -0,0 +1,184 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * SMP initialisation and IPI support
+ * Based on arch/arm64/kernel/smp.c
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2015 Regents of the University of California
+ * Copyright (C) 2017 SiFive
+ */
+
+#include <linux/arch_topology.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/sched.h>
+#include <linux/kernel_stat.h>
+#include <linux/notifier.h>
+#include <linux/cpu.h>
+#include <linux/percpu.h>
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/irq.h>
+#include <linux/of.h>
+#include <linux/sched/task_stack.h>
+#include <linux/sched/mm.h>
+#include <asm/cpu_ops.h>
+#include <asm/irq.h>
+#include <asm/mmu_context.h>
+#include <asm/numa.h>
+#include <asm/tlbflush.h>
+#include <asm/sections.h>
+#include <asm/sbi.h>
+#include <asm/smp.h>
+
+#include "head.h"
+
+static DECLARE_COMPLETION(cpu_running);
+
+void __init smp_prepare_boot_cpu(void)
+{
+}
+
+void __init smp_prepare_cpus(unsigned int max_cpus)
+{
+	int cpuid;
+	int ret;
+	unsigned int curr_cpuid;
+
+	init_cpu_topology();
+
+	curr_cpuid = smp_processor_id();
+	store_cpu_topology(curr_cpuid);
+	numa_store_cpu_info(curr_cpuid);
+	numa_add_cpu(curr_cpuid);
+
+	/* This covers non-smp usecase mandated by "nosmp" option */
+	if (max_cpus == 0)
+		return;
+
+	for_each_possible_cpu(cpuid) {
+		if (cpuid == curr_cpuid)
+			continue;
+		if (cpu_ops[cpuid]->cpu_prepare) {
+			ret = cpu_ops[cpuid]->cpu_prepare(cpuid);
+			if (ret)
+				continue;
+		}
+		set_cpu_present(cpuid, true);
+		numa_store_cpu_info(cpuid);
+	}
+}
+
+void __init setup_smp(void)
+{
+	struct device_node *dn;
+	unsigned long hart;
+	bool found_boot_cpu = false;
+	int cpuid = 1;
+	int rc;
+
+	cpu_set_ops(0);
+
+	for_each_of_cpu_node(dn) {
+		rc = riscv_of_processor_hartid(dn, &hart);
+		if (rc < 0)
+			continue;
+
+		if (hart == cpuid_to_hartid_map(0)) {
+			BUG_ON(found_boot_cpu);
+			found_boot_cpu = 1;
+			early_map_cpu_to_node(0, of_node_to_nid(dn));
+			continue;
+		}
+		if (cpuid >= NR_CPUS) {
+			pr_warn("Invalid cpuid [%d] for hartid [%lu]\n",
+				cpuid, hart);
+			continue;
+		}
+
+		cpuid_to_hartid_map(cpuid) = hart;
+		early_map_cpu_to_node(cpuid, of_node_to_nid(dn));
+		cpuid++;
+	}
+
+	BUG_ON(!found_boot_cpu);
+
+	if (cpuid > nr_cpu_ids)
+		pr_warn("Total number of cpus [%d] is greater than nr_cpus option value [%d]\n",
+			cpuid, nr_cpu_ids);
+
+	for (cpuid = 1; cpuid < nr_cpu_ids; cpuid++) {
+		if (cpuid_to_hartid_map(cpuid) != INVALID_HARTID) {
+			cpu_set_ops(cpuid);
+			set_cpu_possible(cpuid, true);
+		}
+	}
+}
+
+static int start_secondary_cpu(int cpu, struct task_struct *tidle)
+{
+	if (cpu_ops[cpu]->cpu_start)
+		return cpu_ops[cpu]->cpu_start(cpu, tidle);
+
+	return -EOPNOTSUPP;
+}
+
+int __cpu_up(unsigned int cpu, struct task_struct *tidle)
+{
+	int ret = 0;
+	tidle->thread_info.cpu = cpu;
+
+	ret = start_secondary_cpu(cpu, tidle);
+	if (!ret) {
+		wait_for_completion_timeout(&cpu_running,
+					    msecs_to_jiffies(1000));
+
+		if (!cpu_online(cpu)) {
+			pr_crit("CPU%u: failed to come online\n", cpu);
+			ret = -EIO;
+		}
+	} else {
+		pr_crit("CPU%u: failed to start\n", cpu);
+	}
+
+	return ret;
+}
+
+void __init smp_cpus_done(unsigned int max_cpus)
+{
+}
+
+/*
+ * C entry point for a secondary processor.
+ */
+asmlinkage __visible void smp_callin(void)
+{
+	struct mm_struct *mm = &init_mm;
+	unsigned int curr_cpuid = smp_processor_id();
+
+	riscv_clear_ipi();
+
+	/* All kernel threads share the same mm context.  */
+	mmgrab(mm);
+	current->active_mm = mm;
+
+	store_cpu_topology(curr_cpuid);
+	notify_cpu_starting(curr_cpuid);
+	numa_add_cpu(curr_cpuid);
+	set_cpu_online(curr_cpuid, 1);
+
+	/*
+	 * Remote TLB flushes are ignored while the CPU is offline, so emit
+	 * a local TLB flush right now just in case.
+	 */
+	local_flush_tlb_all();
+	complete(&cpu_running);
+	/*
+	 * Disable preemption before enabling interrupts, so we don't try to
+	 * schedule a CPU that hasn't actually started yet.
+	 */
+	local_irq_enable();
+	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
+}
diff --git a/arch/riscv/kernel/soc.c b/arch/riscv/kernel/soc.c
new file mode 100644
index 000000000..a0516172a
--- /dev/null
+++ b/arch/riscv/kernel/soc.c
@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2020 Western Digital Corporation or its affiliates.
+ */
+#include <linux/init.h>
+#include <linux/libfdt.h>
+#include <linux/pgtable.h>
+#include <asm/soc.h>
+
+/*
+ * This is called extremly early, before parse_dtb(), to allow initializing
+ * SoC hardware before memory or any device driver initialization.
+ */
+void __init soc_early_init(void)
+{
+	void (*early_fn)(const void *fdt);
+	const struct of_device_id *s;
+	const void *fdt = dtb_early_va;
+
+	for (s = (void *)&__soc_early_init_table_start;
+	     (void *)s < (void *)&__soc_early_init_table_end; s++) {
+		if (!fdt_node_check_compatible(fdt, 0, s->compatible)) {
+			early_fn = s->data;
+			early_fn(fdt);
+			return;
+		}
+	}
+}
diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c
new file mode 100644
index 000000000..17d7383f2
--- /dev/null
+++ b/arch/riscv/kernel/stacktrace.c
@@ -0,0 +1,146 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2008 ARM Limited
+ * Copyright (C) 2014 Regents of the University of California
+ */
+
+#include <linux/export.h>
+#include <linux/kallsyms.h>
+#include <linux/sched.h>
+#include <linux/sched/debug.h>
+#include <linux/sched/task_stack.h>
+#include <linux/stacktrace.h>
+#include <linux/ftrace.h>
+
+#include <asm/stacktrace.h>
+
+#ifdef CONFIG_FRAME_POINTER
+
+void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs,
+			     bool (*fn)(void *, unsigned long), void *arg)
+{
+	unsigned long fp, sp, pc;
+	int level = 0;
+
+	if (regs) {
+		fp = frame_pointer(regs);
+		sp = user_stack_pointer(regs);
+		pc = instruction_pointer(regs);
+	} else if (task == NULL || task == current) {
+		fp = (unsigned long)__builtin_frame_address(0);
+		sp = current_stack_pointer;
+		pc = (unsigned long)walk_stackframe;
+		level = -1;
+	} else {
+		/* task blocked in __switch_to */
+		fp = task->thread.s[0];
+		sp = task->thread.sp;
+		pc = task->thread.ra;
+	}
+
+	for (;;) {
+		unsigned long low, high;
+		struct stackframe *frame;
+
+		if (unlikely(!__kernel_text_address(pc) || (level++ >= 0 && !fn(arg, pc))))
+			break;
+
+		/* Validate frame pointer */
+		low = sp + sizeof(struct stackframe);
+		high = ALIGN(sp, THREAD_SIZE);
+		if (unlikely(fp < low || fp > high || fp & 0x7))
+			break;
+		/* Unwind stack frame */
+		frame = (struct stackframe *)fp - 1;
+		sp = fp;
+		if (regs && (regs->epc == pc) && (frame->fp & 0x7)) {
+			fp = frame->ra;
+			pc = regs->ra;
+		} else {
+			fp = frame->fp;
+			pc = ftrace_graph_ret_addr(current, NULL, frame->ra,
+						   &frame->ra);
+		}
+
+	}
+}
+
+#else /* !CONFIG_FRAME_POINTER */
+
+void notrace walk_stackframe(struct task_struct *task,
+	struct pt_regs *regs, bool (*fn)(void *, unsigned long), void *arg)
+{
+	unsigned long sp, pc;
+	unsigned long *ksp;
+
+	if (regs) {
+		sp = user_stack_pointer(regs);
+		pc = instruction_pointer(regs);
+	} else if (task == NULL || task == current) {
+		sp = current_stack_pointer;
+		pc = (unsigned long)walk_stackframe;
+	} else {
+		/* task blocked in __switch_to */
+		sp = task->thread.sp;
+		pc = task->thread.ra;
+	}
+
+	if (unlikely(sp & 0x7))
+		return;
+
+	ksp = (unsigned long *)sp;
+	while (!kstack_end(ksp)) {
+		if (__kernel_text_address(pc) && unlikely(!fn(arg, pc)))
+			break;
+		pc = READ_ONCE_NOCHECK(*ksp++) - 0x4;
+	}
+}
+
+#endif /* CONFIG_FRAME_POINTER */
+
+static bool print_trace_address(void *arg, unsigned long pc)
+{
+	const char *loglvl = arg;
+
+	print_ip_sym(loglvl, pc);
+	return true;
+}
+
+noinline void dump_backtrace(struct pt_regs *regs, struct task_struct *task,
+		    const char *loglvl)
+{
+	walk_stackframe(task, regs, print_trace_address, (void *)loglvl);
+}
+
+void show_stack(struct task_struct *task, unsigned long *sp, const char *loglvl)
+{
+	pr_cont("%sCall Trace:\n", loglvl);
+	dump_backtrace(NULL, task, loglvl);
+}
+
+static bool save_wchan(void *arg, unsigned long pc)
+{
+	if (!in_sched_functions(pc)) {
+		unsigned long *p = arg;
+		*p = pc;
+		return false;
+	}
+	return true;
+}
+
+unsigned long __get_wchan(struct task_struct *task)
+{
+	unsigned long pc = 0;
+
+	if (!try_get_task_stack(task))
+		return 0;
+	walk_stackframe(task, NULL, save_wchan, &pc);
+	put_task_stack(task);
+	return pc;
+}
+
+noinline void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie,
+		     struct task_struct *task, struct pt_regs *regs)
+{
+	walk_stackframe(task, regs, consume_entry, cookie);
+}
diff --git a/arch/riscv/kernel/suspend.c b/arch/riscv/kernel/suspend.c
new file mode 100644
index 000000000..9ba24fb8c
--- /dev/null
+++ b/arch/riscv/kernel/suspend.c
@@ -0,0 +1,87 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2021 Western Digital Corporation or its affiliates.
+ * Copyright (c) 2022 Ventana Micro Systems Inc.
+ */
+
+#include <linux/ftrace.h>
+#include <asm/csr.h>
+#include <asm/suspend.h>
+
+static void suspend_save_csrs(struct suspend_context *context)
+{
+	context->scratch = csr_read(CSR_SCRATCH);
+	context->tvec = csr_read(CSR_TVEC);
+	context->ie = csr_read(CSR_IE);
+
+	/*
+	 * No need to save/restore IP CSR (i.e. MIP or SIP) because:
+	 *
+	 * 1. For no-MMU (M-mode) kernel, the bits in MIP are set by
+	 *    external devices (such as interrupt controller, timer, etc).
+	 * 2. For MMU (S-mode) kernel, the bits in SIP are set by
+	 *    M-mode firmware and external devices (such as interrupt
+	 *    controller, etc).
+	 */
+
+#ifdef CONFIG_MMU
+	context->satp = csr_read(CSR_SATP);
+#endif
+}
+
+static void suspend_restore_csrs(struct suspend_context *context)
+{
+	csr_write(CSR_SCRATCH, context->scratch);
+	csr_write(CSR_TVEC, context->tvec);
+	csr_write(CSR_IE, context->ie);
+
+#ifdef CONFIG_MMU
+	csr_write(CSR_SATP, context->satp);
+#endif
+}
+
+int cpu_suspend(unsigned long arg,
+		int (*finish)(unsigned long arg,
+			      unsigned long entry,
+			      unsigned long context))
+{
+	int rc = 0;
+	struct suspend_context context = { 0 };
+
+	/* Finisher should be non-NULL */
+	if (!finish)
+		return -EINVAL;
+
+	/* Save additional CSRs*/
+	suspend_save_csrs(&context);
+
+	/*
+	 * Function graph tracer state gets incosistent when the kernel
+	 * calls functions that never return (aka finishers) hence disable
+	 * graph tracing during their execution.
+	 */
+	pause_graph_tracing();
+
+	/* Save context on stack */
+	if (__cpu_suspend_enter(&context)) {
+		/* Call the finisher */
+		rc = finish(arg, __pa_symbol(__cpu_resume_enter),
+			    (ulong)&context);
+
+		/*
+		 * Should never reach here, unless the suspend finisher
+		 * fails. Successful cpu_suspend() should return from
+		 * __cpu_resume_entry()
+		 */
+		if (!rc)
+			rc = -EOPNOTSUPP;
+	}
+
+	/* Enable function graph tracer */
+	unpause_graph_tracing();
+
+	/* Restore additional CSRs */
+	suspend_restore_csrs(&context);
+
+	return rc;
+}
diff --git a/arch/riscv/kernel/suspend_entry.S b/arch/riscv/kernel/suspend_entry.S
new file mode 100644
index 000000000..aafcca58c
--- /dev/null
+++ b/arch/riscv/kernel/suspend_entry.S
@@ -0,0 +1,125 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2021 Western Digital Corporation or its affiliates.
+ * Copyright (c) 2022 Ventana Micro Systems Inc.
+ */
+
+#include <linux/linkage.h>
+#include <asm/asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/csr.h>
+#include <asm/xip_fixup.h>
+
+	.text
+	.altmacro
+	.option norelax
+
+ENTRY(__cpu_suspend_enter)
+	/* Save registers (except A0 and T0-T6) */
+	REG_S	ra, (SUSPEND_CONTEXT_REGS + PT_RA)(a0)
+	REG_S	sp, (SUSPEND_CONTEXT_REGS + PT_SP)(a0)
+	REG_S	gp, (SUSPEND_CONTEXT_REGS + PT_GP)(a0)
+	REG_S	tp, (SUSPEND_CONTEXT_REGS + PT_TP)(a0)
+	REG_S	s0, (SUSPEND_CONTEXT_REGS + PT_S0)(a0)
+	REG_S	s1, (SUSPEND_CONTEXT_REGS + PT_S1)(a0)
+	REG_S	a1, (SUSPEND_CONTEXT_REGS + PT_A1)(a0)
+	REG_S	a2, (SUSPEND_CONTEXT_REGS + PT_A2)(a0)
+	REG_S	a3, (SUSPEND_CONTEXT_REGS + PT_A3)(a0)
+	REG_S	a4, (SUSPEND_CONTEXT_REGS + PT_A4)(a0)
+	REG_S	a5, (SUSPEND_CONTEXT_REGS + PT_A5)(a0)
+	REG_S	a6, (SUSPEND_CONTEXT_REGS + PT_A6)(a0)
+	REG_S	a7, (SUSPEND_CONTEXT_REGS + PT_A7)(a0)
+	REG_S	s2, (SUSPEND_CONTEXT_REGS + PT_S2)(a0)
+	REG_S	s3, (SUSPEND_CONTEXT_REGS + PT_S3)(a0)
+	REG_S	s4, (SUSPEND_CONTEXT_REGS + PT_S4)(a0)
+	REG_S	s5, (SUSPEND_CONTEXT_REGS + PT_S5)(a0)
+	REG_S	s6, (SUSPEND_CONTEXT_REGS + PT_S6)(a0)
+	REG_S	s7, (SUSPEND_CONTEXT_REGS + PT_S7)(a0)
+	REG_S	s8, (SUSPEND_CONTEXT_REGS + PT_S8)(a0)
+	REG_S	s9, (SUSPEND_CONTEXT_REGS + PT_S9)(a0)
+	REG_S	s10, (SUSPEND_CONTEXT_REGS + PT_S10)(a0)
+	REG_S	s11, (SUSPEND_CONTEXT_REGS + PT_S11)(a0)
+
+	/* Save CSRs */
+	csrr	t0, CSR_EPC
+	REG_S	t0, (SUSPEND_CONTEXT_REGS + PT_EPC)(a0)
+	csrr	t0, CSR_STATUS
+	REG_S	t0, (SUSPEND_CONTEXT_REGS + PT_STATUS)(a0)
+	csrr	t0, CSR_TVAL
+	REG_S	t0, (SUSPEND_CONTEXT_REGS + PT_BADADDR)(a0)
+	csrr	t0, CSR_CAUSE
+	REG_S	t0, (SUSPEND_CONTEXT_REGS + PT_CAUSE)(a0)
+
+	/* Return non-zero value */
+	li	a0, 1
+
+	/* Return to C code */
+	ret
+END(__cpu_suspend_enter)
+
+ENTRY(__cpu_resume_enter)
+	/* Load the global pointer */
+	.option push
+	.option norelax
+		la gp, __global_pointer$
+	.option pop
+
+#ifdef CONFIG_MMU
+	/* Save A0 and A1 */
+	add	t0, a0, zero
+	add	t1, a1, zero
+
+	/* Enable MMU */
+	la	a0, swapper_pg_dir
+	XIP_FIXUP_OFFSET a0
+	call	relocate_enable_mmu
+
+	/* Restore A0 and A1 */
+	add	a0, t0, zero
+	add	a1, t1, zero
+#endif
+
+	/* Make A0 point to suspend context */
+	add	a0, a1, zero
+
+	/* Restore CSRs */
+	REG_L	t0, (SUSPEND_CONTEXT_REGS + PT_EPC)(a0)
+	csrw	CSR_EPC, t0
+	REG_L	t0, (SUSPEND_CONTEXT_REGS + PT_STATUS)(a0)
+	csrw	CSR_STATUS, t0
+	REG_L	t0, (SUSPEND_CONTEXT_REGS + PT_BADADDR)(a0)
+	csrw	CSR_TVAL, t0
+	REG_L	t0, (SUSPEND_CONTEXT_REGS + PT_CAUSE)(a0)
+	csrw	CSR_CAUSE, t0
+
+	/* Restore registers (except A0 and T0-T6) */
+	REG_L	ra, (SUSPEND_CONTEXT_REGS + PT_RA)(a0)
+	REG_L	sp, (SUSPEND_CONTEXT_REGS + PT_SP)(a0)
+	REG_L	gp, (SUSPEND_CONTEXT_REGS + PT_GP)(a0)
+	REG_L	tp, (SUSPEND_CONTEXT_REGS + PT_TP)(a0)
+	REG_L	s0, (SUSPEND_CONTEXT_REGS + PT_S0)(a0)
+	REG_L	s1, (SUSPEND_CONTEXT_REGS + PT_S1)(a0)
+	REG_L	a1, (SUSPEND_CONTEXT_REGS + PT_A1)(a0)
+	REG_L	a2, (SUSPEND_CONTEXT_REGS + PT_A2)(a0)
+	REG_L	a3, (SUSPEND_CONTEXT_REGS + PT_A3)(a0)
+	REG_L	a4, (SUSPEND_CONTEXT_REGS + PT_A4)(a0)
+	REG_L	a5, (SUSPEND_CONTEXT_REGS + PT_A5)(a0)
+	REG_L	a6, (SUSPEND_CONTEXT_REGS + PT_A6)(a0)
+	REG_L	a7, (SUSPEND_CONTEXT_REGS + PT_A7)(a0)
+	REG_L	s2, (SUSPEND_CONTEXT_REGS + PT_S2)(a0)
+	REG_L	s3, (SUSPEND_CONTEXT_REGS + PT_S3)(a0)
+	REG_L	s4, (SUSPEND_CONTEXT_REGS + PT_S4)(a0)
+	REG_L	s5, (SUSPEND_CONTEXT_REGS + PT_S5)(a0)
+	REG_L	s6, (SUSPEND_CONTEXT_REGS + PT_S6)(a0)
+	REG_L	s7, (SUSPEND_CONTEXT_REGS + PT_S7)(a0)
+	REG_L	s8, (SUSPEND_CONTEXT_REGS + PT_S8)(a0)
+	REG_L	s9, (SUSPEND_CONTEXT_REGS + PT_S9)(a0)
+	REG_L	s10, (SUSPEND_CONTEXT_REGS + PT_S10)(a0)
+	REG_L	s11, (SUSPEND_CONTEXT_REGS + PT_S11)(a0)
+
+	/* Return zero value */
+	add	a0, zero, zero
+
+	/* Return to C code */
+	ret
+END(__cpu_resume_enter)
diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c
new file mode 100644
index 000000000..5d3f2fbeb
--- /dev/null
+++ b/arch/riscv/kernel/sys_riscv.c
@@ -0,0 +1,71 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ * Copyright (C) 2014 Darius Rad <darius@bluespec.com>
+ * Copyright (C) 2017 SiFive
+ */
+
+#include <linux/syscalls.h>
+#include <asm/unistd.h>
+#include <asm/cacheflush.h>
+#include <asm-generic/mman-common.h>
+
+static long riscv_sys_mmap(unsigned long addr, unsigned long len,
+			   unsigned long prot, unsigned long flags,
+			   unsigned long fd, off_t offset,
+			   unsigned long page_shift_offset)
+{
+	if (unlikely(offset & (~PAGE_MASK >> page_shift_offset)))
+		return -EINVAL;
+
+	return ksys_mmap_pgoff(addr, len, prot, flags, fd,
+			       offset >> (PAGE_SHIFT - page_shift_offset));
+}
+
+#ifdef CONFIG_64BIT
+SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len,
+	unsigned long, prot, unsigned long, flags,
+	unsigned long, fd, off_t, offset)
+{
+	return riscv_sys_mmap(addr, len, prot, flags, fd, offset, 0);
+}
+#endif
+
+#if defined(CONFIG_32BIT) || defined(CONFIG_COMPAT)
+SYSCALL_DEFINE6(mmap2, unsigned long, addr, unsigned long, len,
+	unsigned long, prot, unsigned long, flags,
+	unsigned long, fd, off_t, offset)
+{
+	/*
+	 * Note that the shift for mmap2 is constant (12),
+	 * regardless of PAGE_SIZE
+	 */
+	return riscv_sys_mmap(addr, len, prot, flags, fd, offset, 12);
+}
+#endif
+
+/*
+ * Allows the instruction cache to be flushed from userspace.  Despite RISC-V
+ * having a direct 'fence.i' instruction available to userspace (which we
+ * can't trap!), that's not actually viable when running on Linux because the
+ * kernel might schedule a process on another hart.  There is no way for
+ * userspace to handle this without invoking the kernel (as it doesn't know the
+ * thread->hart mappings), so we've defined a RISC-V specific system call to
+ * flush the instruction cache.
+ *
+ * sys_riscv_flush_icache() is defined to flush the instruction cache over an
+ * address range, with the flush applying to either all threads or just the
+ * caller.  We don't currently do anything with the address range, that's just
+ * in there for forwards compatibility.
+ */
+SYSCALL_DEFINE3(riscv_flush_icache, uintptr_t, start, uintptr_t, end,
+	uintptr_t, flags)
+{
+	/* Check the reserved flags. */
+	if (unlikely(flags & ~SYS_RISCV_FLUSH_ICACHE_ALL))
+		return -EINVAL;
+
+	flush_icache_mm(current->mm, flags & SYS_RISCV_FLUSH_ICACHE_LOCAL);
+
+	return 0;
+}
diff --git a/arch/riscv/kernel/syscall_table.c b/arch/riscv/kernel/syscall_table.c
new file mode 100644
index 000000000..44b1420a2
--- /dev/null
+++ b/arch/riscv/kernel/syscall_table.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2009 Arnd Bergmann <arnd@arndb.de>
+ * Copyright (C) 2012 Regents of the University of California
+ */
+
+#include <linux/linkage.h>
+#include <linux/syscalls.h>
+#include <asm-generic/syscalls.h>
+#include <asm/syscall.h>
+
+#undef __SYSCALL
+#define __SYSCALL(nr, call)	[nr] = (call),
+
+void * const sys_call_table[__NR_syscalls] = {
+	[0 ... __NR_syscalls - 1] = sys_ni_syscall,
+#include <asm/unistd.h>
+};
diff --git a/arch/riscv/kernel/time.c b/arch/riscv/kernel/time.c
new file mode 100644
index 000000000..1cf21db4f
--- /dev/null
+++ b/arch/riscv/kernel/time.c
@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ * Copyright (C) 2017 SiFive
+ */
+
+#include <linux/of_clk.h>
+#include <linux/clockchips.h>
+#include <linux/clocksource.h>
+#include <linux/delay.h>
+#include <asm/sbi.h>
+#include <asm/processor.h>
+#include <asm/timex.h>
+
+unsigned long riscv_timebase __ro_after_init;
+EXPORT_SYMBOL_GPL(riscv_timebase);
+
+void __init time_init(void)
+{
+	struct device_node *cpu;
+	u32 prop;
+
+	cpu = of_find_node_by_path("/cpus");
+	if (!cpu || of_property_read_u32(cpu, "timebase-frequency", &prop))
+		panic(KERN_WARNING "RISC-V system with no 'timebase-frequency' in DTS\n");
+	of_node_put(cpu);
+	riscv_timebase = prop;
+
+	lpj_fine = riscv_timebase / HZ;
+
+	of_clk_init(NULL);
+	timer_probe();
+
+	tick_setup_hrtimer_broadcast();
+}
+
+void clocksource_arch_init(struct clocksource *cs)
+{
+#ifdef CONFIG_GENERIC_GETTIMEOFDAY
+	cs->vdso_clock_mode = VDSO_CLOCKMODE_ARCHTIMER;
+#else
+	cs->vdso_clock_mode = VDSO_CLOCKMODE_NONE;
+#endif
+}
diff --git a/arch/riscv/kernel/trace_irq.c b/arch/riscv/kernel/trace_irq.c
new file mode 100644
index 000000000..095ac976d
--- /dev/null
+++ b/arch/riscv/kernel/trace_irq.c
@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2022 Changbin Du <changbin.du@gmail.com>
+ */
+
+#include <linux/irqflags.h>
+#include <linux/kprobes.h>
+#include "trace_irq.h"
+
+/*
+ * trace_hardirqs_on/off require the caller to setup frame pointer properly.
+ * Otherwise, CALLER_ADDR1 might trigger an pagging exception in kernel.
+ * Here we add one extra level so they can be safely called by low
+ * level entry code which $fp is used for other purpose.
+ */
+
+void __trace_hardirqs_on(void)
+{
+	trace_hardirqs_on();
+}
+NOKPROBE_SYMBOL(__trace_hardirqs_on);
+
+void __trace_hardirqs_off(void)
+{
+	trace_hardirqs_off();
+}
+NOKPROBE_SYMBOL(__trace_hardirqs_off);
diff --git a/arch/riscv/kernel/trace_irq.h b/arch/riscv/kernel/trace_irq.h
new file mode 100644
index 000000000..99fe67377
--- /dev/null
+++ b/arch/riscv/kernel/trace_irq.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2022 Changbin Du <changbin.du@gmail.com>
+ */
+#ifndef __TRACE_IRQ_H
+#define __TRACE_IRQ_H
+
+void __trace_hardirqs_on(void);
+void __trace_hardirqs_off(void);
+
+#endif /* __TRACE_IRQ_H */
diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
new file mode 100644
index 000000000..5d07f6b3c
--- /dev/null
+++ b/arch/riscv/kernel/traps.c
@@ -0,0 +1,262 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ */
+
+#include <linux/cpu.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/sched/debug.h>
+#include <linux/sched/signal.h>
+#include <linux/signal.h>
+#include <linux/kdebug.h>
+#include <linux/uaccess.h>
+#include <linux/kprobes.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/irq.h>
+#include <linux/kexec.h>
+
+#include <asm/asm-prototypes.h>
+#include <asm/bug.h>
+#include <asm/csr.h>
+#include <asm/processor.h>
+#include <asm/ptrace.h>
+#include <asm/thread_info.h>
+
+int show_unhandled_signals = 1;
+
+static DEFINE_SPINLOCK(die_lock);
+
+void die(struct pt_regs *regs, const char *str)
+{
+	static int die_counter;
+	int ret;
+	long cause;
+	unsigned long flags;
+
+	oops_enter();
+
+	spin_lock_irqsave(&die_lock, flags);
+	console_verbose();
+	bust_spinlocks(1);
+
+	pr_emerg("%s [#%d]\n", str, ++die_counter);
+	print_modules();
+	if (regs)
+		show_regs(regs);
+
+	cause = regs ? regs->cause : -1;
+	ret = notify_die(DIE_OOPS, str, regs, 0, cause, SIGSEGV);
+
+	if (kexec_should_crash(current))
+		crash_kexec(regs);
+
+	bust_spinlocks(0);
+	add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE);
+	spin_unlock_irqrestore(&die_lock, flags);
+	oops_exit();
+
+	if (in_interrupt())
+		panic("Fatal exception in interrupt");
+	if (panic_on_oops)
+		panic("Fatal exception");
+	if (ret != NOTIFY_STOP)
+		make_task_dead(SIGSEGV);
+}
+
+void do_trap(struct pt_regs *regs, int signo, int code, unsigned long addr)
+{
+	struct task_struct *tsk = current;
+
+	if (show_unhandled_signals && unhandled_signal(tsk, signo)
+	    && printk_ratelimit()) {
+		pr_info("%s[%d]: unhandled signal %d code 0x%x at 0x" REG_FMT,
+			tsk->comm, task_pid_nr(tsk), signo, code, addr);
+		print_vma_addr(KERN_CONT " in ", instruction_pointer(regs));
+		pr_cont("\n");
+		__show_regs(regs);
+	}
+
+	force_sig_fault(signo, code, (void __user *)addr);
+}
+
+static void do_trap_error(struct pt_regs *regs, int signo, int code,
+	unsigned long addr, const char *str)
+{
+	current->thread.bad_cause = regs->cause;
+
+	if (user_mode(regs)) {
+		do_trap(regs, signo, code, addr);
+	} else {
+		if (!fixup_exception(regs))
+			die(regs, str);
+	}
+}
+
+#if defined(CONFIG_XIP_KERNEL) && defined(CONFIG_RISCV_ALTERNATIVE)
+#define __trap_section		__section(".xip.traps")
+#else
+#define __trap_section
+#endif
+#define DO_ERROR_INFO(name, signo, code, str)				\
+asmlinkage __visible __trap_section void name(struct pt_regs *regs)	\
+{									\
+	do_trap_error(regs, signo, code, regs->epc, "Oops - " str);	\
+}
+
+DO_ERROR_INFO(do_trap_unknown,
+	SIGILL, ILL_ILLTRP, "unknown exception");
+DO_ERROR_INFO(do_trap_insn_misaligned,
+	SIGBUS, BUS_ADRALN, "instruction address misaligned");
+DO_ERROR_INFO(do_trap_insn_fault,
+	SIGSEGV, SEGV_ACCERR, "instruction access fault");
+DO_ERROR_INFO(do_trap_insn_illegal,
+	SIGILL, ILL_ILLOPC, "illegal instruction");
+DO_ERROR_INFO(do_trap_load_fault,
+	SIGSEGV, SEGV_ACCERR, "load access fault");
+#ifndef CONFIG_RISCV_M_MODE
+DO_ERROR_INFO(do_trap_load_misaligned,
+	SIGBUS, BUS_ADRALN, "Oops - load address misaligned");
+DO_ERROR_INFO(do_trap_store_misaligned,
+	SIGBUS, BUS_ADRALN, "Oops - store (or AMO) address misaligned");
+#else
+int handle_misaligned_load(struct pt_regs *regs);
+int handle_misaligned_store(struct pt_regs *regs);
+
+asmlinkage void __trap_section do_trap_load_misaligned(struct pt_regs *regs)
+{
+	if (!handle_misaligned_load(regs))
+		return;
+	do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->epc,
+		      "Oops - load address misaligned");
+}
+
+asmlinkage void __trap_section do_trap_store_misaligned(struct pt_regs *regs)
+{
+	if (!handle_misaligned_store(regs))
+		return;
+	do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->epc,
+		      "Oops - store (or AMO) address misaligned");
+}
+#endif
+DO_ERROR_INFO(do_trap_store_fault,
+	SIGSEGV, SEGV_ACCERR, "store (or AMO) access fault");
+DO_ERROR_INFO(do_trap_ecall_u,
+	SIGILL, ILL_ILLTRP, "environment call from U-mode");
+DO_ERROR_INFO(do_trap_ecall_s,
+	SIGILL, ILL_ILLTRP, "environment call from S-mode");
+DO_ERROR_INFO(do_trap_ecall_m,
+	SIGILL, ILL_ILLTRP, "environment call from M-mode");
+
+static inline unsigned long get_break_insn_length(unsigned long pc)
+{
+	bug_insn_t insn;
+
+	if (get_kernel_nofault(insn, (bug_insn_t *)pc))
+		return 0;
+
+	return GET_INSN_LENGTH(insn);
+}
+
+asmlinkage __visible __trap_section void do_trap_break(struct pt_regs *regs)
+{
+#ifdef CONFIG_KPROBES
+	if (kprobe_single_step_handler(regs))
+		return;
+
+	if (kprobe_breakpoint_handler(regs))
+		return;
+#endif
+#ifdef CONFIG_UPROBES
+	if (uprobe_single_step_handler(regs))
+		return;
+
+	if (uprobe_breakpoint_handler(regs))
+		return;
+#endif
+	current->thread.bad_cause = regs->cause;
+
+	if (user_mode(regs))
+		force_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *)regs->epc);
+#ifdef CONFIG_KGDB
+	else if (notify_die(DIE_TRAP, "EBREAK", regs, 0, regs->cause, SIGTRAP)
+								== NOTIFY_STOP)
+		return;
+#endif
+	else if (report_bug(regs->epc, regs) == BUG_TRAP_TYPE_WARN)
+		regs->epc += get_break_insn_length(regs->epc);
+	else
+		die(regs, "Kernel BUG");
+}
+NOKPROBE_SYMBOL(do_trap_break);
+
+#ifdef CONFIG_GENERIC_BUG
+int is_valid_bugaddr(unsigned long pc)
+{
+	bug_insn_t insn;
+
+	if (pc < VMALLOC_START)
+		return 0;
+	if (get_kernel_nofault(insn, (bug_insn_t *)pc))
+		return 0;
+	if ((insn & __INSN_LENGTH_MASK) == __INSN_LENGTH_32)
+		return (insn == __BUG_INSN_32);
+	else
+		return ((insn & __COMPRESSED_INSN_MASK) == __BUG_INSN_16);
+}
+#endif /* CONFIG_GENERIC_BUG */
+
+#ifdef CONFIG_VMAP_STACK
+static DEFINE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)],
+		overflow_stack)__aligned(16);
+/*
+ * shadow stack, handled_ kernel_ stack_ overflow(in kernel/entry.S) is used
+ * to get per-cpu overflow stack(get_overflow_stack).
+ */
+long shadow_stack[SHADOW_OVERFLOW_STACK_SIZE/sizeof(long)] __aligned(16);
+asmlinkage unsigned long get_overflow_stack(void)
+{
+	return (unsigned long)this_cpu_ptr(overflow_stack) +
+		OVERFLOW_STACK_SIZE;
+}
+
+/*
+ * A pseudo spinlock to protect the shadow stack from being used by multiple
+ * harts concurrently.  This isn't a real spinlock because the lock side must
+ * be taken without a valid stack and only a single register, it's only taken
+ * while in the process of panicing anyway so the performance and error
+ * checking a proper spinlock gives us doesn't matter.
+ */
+unsigned long spin_shadow_stack;
+
+asmlinkage void handle_bad_stack(struct pt_regs *regs)
+{
+	unsigned long tsk_stk = (unsigned long)current->stack;
+	unsigned long ovf_stk = (unsigned long)this_cpu_ptr(overflow_stack);
+
+	/*
+	 * We're done with the shadow stack by this point, as we're on the
+	 * overflow stack.  Tell any other concurrent overflowing harts that
+	 * they can proceed with panicing by releasing the pseudo-spinlock.
+	 *
+	 * This pairs with an amoswap.aq in handle_kernel_stack_overflow.
+	 */
+	smp_store_release(&spin_shadow_stack, 0);
+
+	console_verbose();
+
+	pr_emerg("Insufficient stack space to handle exception!\n");
+	pr_emerg("Task stack:     [0x%016lx..0x%016lx]\n",
+			tsk_stk, tsk_stk + THREAD_SIZE);
+	pr_emerg("Overflow stack: [0x%016lx..0x%016lx]\n",
+			ovf_stk, ovf_stk + OVERFLOW_STACK_SIZE);
+
+	__show_regs(regs);
+	panic("Kernel stack overflow");
+
+	for (;;)
+		wait_for_interrupt();
+}
+#endif
diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c
new file mode 100644
index 000000000..5348d842c
--- /dev/null
+++ b/arch/riscv/kernel/traps_misaligned.c
@@ -0,0 +1,366 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020 Western Digital Corporation or its affiliates.
+ */
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/irq.h>
+#include <linux/stringify.h>
+
+#include <asm/processor.h>
+#include <asm/ptrace.h>
+#include <asm/csr.h>
+
+#define INSN_MATCH_LB			0x3
+#define INSN_MASK_LB			0x707f
+#define INSN_MATCH_LH			0x1003
+#define INSN_MASK_LH			0x707f
+#define INSN_MATCH_LW			0x2003
+#define INSN_MASK_LW			0x707f
+#define INSN_MATCH_LD			0x3003
+#define INSN_MASK_LD			0x707f
+#define INSN_MATCH_LBU			0x4003
+#define INSN_MASK_LBU			0x707f
+#define INSN_MATCH_LHU			0x5003
+#define INSN_MASK_LHU			0x707f
+#define INSN_MATCH_LWU			0x6003
+#define INSN_MASK_LWU			0x707f
+#define INSN_MATCH_SB			0x23
+#define INSN_MASK_SB			0x707f
+#define INSN_MATCH_SH			0x1023
+#define INSN_MASK_SH			0x707f
+#define INSN_MATCH_SW			0x2023
+#define INSN_MASK_SW			0x707f
+#define INSN_MATCH_SD			0x3023
+#define INSN_MASK_SD			0x707f
+
+#define INSN_MATCH_FLW			0x2007
+#define INSN_MASK_FLW			0x707f
+#define INSN_MATCH_FLD			0x3007
+#define INSN_MASK_FLD			0x707f
+#define INSN_MATCH_FLQ			0x4007
+#define INSN_MASK_FLQ			0x707f
+#define INSN_MATCH_FSW			0x2027
+#define INSN_MASK_FSW			0x707f
+#define INSN_MATCH_FSD			0x3027
+#define INSN_MASK_FSD			0x707f
+#define INSN_MATCH_FSQ			0x4027
+#define INSN_MASK_FSQ			0x707f
+
+#define INSN_MATCH_C_LD			0x6000
+#define INSN_MASK_C_LD			0xe003
+#define INSN_MATCH_C_SD			0xe000
+#define INSN_MASK_C_SD			0xe003
+#define INSN_MATCH_C_LW			0x4000
+#define INSN_MASK_C_LW			0xe003
+#define INSN_MATCH_C_SW			0xc000
+#define INSN_MASK_C_SW			0xe003
+#define INSN_MATCH_C_LDSP		0x6002
+#define INSN_MASK_C_LDSP		0xe003
+#define INSN_MATCH_C_SDSP		0xe002
+#define INSN_MASK_C_SDSP		0xe003
+#define INSN_MATCH_C_LWSP		0x4002
+#define INSN_MASK_C_LWSP		0xe003
+#define INSN_MATCH_C_SWSP		0xc002
+#define INSN_MASK_C_SWSP		0xe003
+
+#define INSN_MATCH_C_FLD		0x2000
+#define INSN_MASK_C_FLD			0xe003
+#define INSN_MATCH_C_FLW		0x6000
+#define INSN_MASK_C_FLW			0xe003
+#define INSN_MATCH_C_FSD		0xa000
+#define INSN_MASK_C_FSD			0xe003
+#define INSN_MATCH_C_FSW		0xe000
+#define INSN_MASK_C_FSW			0xe003
+#define INSN_MATCH_C_FLDSP		0x2002
+#define INSN_MASK_C_FLDSP		0xe003
+#define INSN_MATCH_C_FSDSP		0xa002
+#define INSN_MASK_C_FSDSP		0xe003
+#define INSN_MATCH_C_FLWSP		0x6002
+#define INSN_MASK_C_FLWSP		0xe003
+#define INSN_MATCH_C_FSWSP		0xe002
+#define INSN_MASK_C_FSWSP		0xe003
+
+#define INSN_LEN(insn)			((((insn) & 0x3) < 0x3) ? 2 : 4)
+
+#if defined(CONFIG_64BIT)
+#define LOG_REGBYTES			3
+#define XLEN				64
+#else
+#define LOG_REGBYTES			2
+#define XLEN				32
+#endif
+#define REGBYTES			(1 << LOG_REGBYTES)
+#define XLEN_MINUS_16			((XLEN) - 16)
+
+#define SH_RD				7
+#define SH_RS1				15
+#define SH_RS2				20
+#define SH_RS2C				2
+
+#define RV_X(x, s, n)			(((x) >> (s)) & ((1 << (n)) - 1))
+#define RVC_LW_IMM(x)			((RV_X(x, 6, 1) << 2) | \
+					 (RV_X(x, 10, 3) << 3) | \
+					 (RV_X(x, 5, 1) << 6))
+#define RVC_LD_IMM(x)			((RV_X(x, 10, 3) << 3) | \
+					 (RV_X(x, 5, 2) << 6))
+#define RVC_LWSP_IMM(x)			((RV_X(x, 4, 3) << 2) | \
+					 (RV_X(x, 12, 1) << 5) | \
+					 (RV_X(x, 2, 2) << 6))
+#define RVC_LDSP_IMM(x)			((RV_X(x, 5, 2) << 3) | \
+					 (RV_X(x, 12, 1) << 5) | \
+					 (RV_X(x, 2, 3) << 6))
+#define RVC_SWSP_IMM(x)			((RV_X(x, 9, 4) << 2) | \
+					 (RV_X(x, 7, 2) << 6))
+#define RVC_SDSP_IMM(x)			((RV_X(x, 10, 3) << 3) | \
+					 (RV_X(x, 7, 3) << 6))
+#define RVC_RS1S(insn)			(8 + RV_X(insn, SH_RD, 3))
+#define RVC_RS2S(insn)			(8 + RV_X(insn, SH_RS2C, 3))
+#define RVC_RS2(insn)			RV_X(insn, SH_RS2C, 5)
+
+#define SHIFT_RIGHT(x, y)		\
+	((y) < 0 ? ((x) << -(y)) : ((x) >> (y)))
+
+#define REG_MASK			\
+	((1 << (5 + LOG_REGBYTES)) - (1 << LOG_REGBYTES))
+
+#define REG_OFFSET(insn, pos)		\
+	(SHIFT_RIGHT((insn), (pos) - LOG_REGBYTES) & REG_MASK)
+
+#define REG_PTR(insn, pos, regs)	\
+	(ulong *)((ulong)(regs) + REG_OFFSET(insn, pos))
+
+#define GET_RM(insn)			(((insn) >> 12) & 7)
+
+#define GET_RS1(insn, regs)		(*REG_PTR(insn, SH_RS1, regs))
+#define GET_RS2(insn, regs)		(*REG_PTR(insn, SH_RS2, regs))
+#define GET_RS1S(insn, regs)		(*REG_PTR(RVC_RS1S(insn), 0, regs))
+#define GET_RS2S(insn, regs)		(*REG_PTR(RVC_RS2S(insn), 0, regs))
+#define GET_RS2C(insn, regs)		(*REG_PTR(insn, SH_RS2C, regs))
+#define GET_SP(regs)			(*REG_PTR(2, 0, regs))
+#define SET_RD(insn, regs, val)		(*REG_PTR(insn, SH_RD, regs) = (val))
+#define IMM_I(insn)			((s32)(insn) >> 20)
+#define IMM_S(insn)			(((s32)(insn) >> 25 << 5) | \
+					 (s32)(((insn) >> 7) & 0x1f))
+#define MASK_FUNCT3			0x7000
+
+#define GET_PRECISION(insn) (((insn) >> 25) & 3)
+#define GET_RM(insn) (((insn) >> 12) & 7)
+#define PRECISION_S 0
+#define PRECISION_D 1
+
+#define DECLARE_UNPRIVILEGED_LOAD_FUNCTION(type, insn)			\
+static inline type load_##type(const type *addr)			\
+{									\
+	type val;							\
+	asm (#insn " %0, %1"						\
+	: "=&r" (val) : "m" (*addr));					\
+	return val;							\
+}
+
+#define DECLARE_UNPRIVILEGED_STORE_FUNCTION(type, insn)			\
+static inline void store_##type(type *addr, type val)			\
+{									\
+	asm volatile (#insn " %0, %1\n"					\
+	: : "r" (val), "m" (*addr));					\
+}
+
+DECLARE_UNPRIVILEGED_LOAD_FUNCTION(u8, lbu)
+DECLARE_UNPRIVILEGED_LOAD_FUNCTION(u16, lhu)
+DECLARE_UNPRIVILEGED_LOAD_FUNCTION(s8, lb)
+DECLARE_UNPRIVILEGED_LOAD_FUNCTION(s16, lh)
+DECLARE_UNPRIVILEGED_LOAD_FUNCTION(s32, lw)
+DECLARE_UNPRIVILEGED_STORE_FUNCTION(u8, sb)
+DECLARE_UNPRIVILEGED_STORE_FUNCTION(u16, sh)
+DECLARE_UNPRIVILEGED_STORE_FUNCTION(u32, sw)
+#if defined(CONFIG_64BIT)
+DECLARE_UNPRIVILEGED_LOAD_FUNCTION(u32, lwu)
+DECLARE_UNPRIVILEGED_LOAD_FUNCTION(u64, ld)
+DECLARE_UNPRIVILEGED_STORE_FUNCTION(u64, sd)
+DECLARE_UNPRIVILEGED_LOAD_FUNCTION(ulong, ld)
+#else
+DECLARE_UNPRIVILEGED_LOAD_FUNCTION(u32, lw)
+DECLARE_UNPRIVILEGED_LOAD_FUNCTION(ulong, lw)
+
+static inline u64 load_u64(const u64 *addr)
+{
+	return load_u32((u32 *)addr)
+		+ ((u64)load_u32((u32 *)addr + 1) << 32);
+}
+
+static inline void store_u64(u64 *addr, u64 val)
+{
+	store_u32((u32 *)addr, val);
+	store_u32((u32 *)addr + 1, val >> 32);
+}
+#endif
+
+static inline ulong get_insn(ulong mepc)
+{
+	register ulong __mepc asm ("a2") = mepc;
+	ulong val, rvc_mask = 3, tmp;
+
+	asm ("and %[tmp], %[addr], 2\n"
+		"bnez %[tmp], 1f\n"
+#if defined(CONFIG_64BIT)
+		__stringify(LWU) " %[insn], (%[addr])\n"
+#else
+		__stringify(LW) " %[insn], (%[addr])\n"
+#endif
+		"and %[tmp], %[insn], %[rvc_mask]\n"
+		"beq %[tmp], %[rvc_mask], 2f\n"
+		"sll %[insn], %[insn], %[xlen_minus_16]\n"
+		"srl %[insn], %[insn], %[xlen_minus_16]\n"
+		"j 2f\n"
+		"1:\n"
+		"lhu %[insn], (%[addr])\n"
+		"and %[tmp], %[insn], %[rvc_mask]\n"
+		"bne %[tmp], %[rvc_mask], 2f\n"
+		"lhu %[tmp], 2(%[addr])\n"
+		"sll %[tmp], %[tmp], 16\n"
+		"add %[insn], %[insn], %[tmp]\n"
+		"2:"
+	: [insn] "=&r" (val), [tmp] "=&r" (tmp)
+	: [addr] "r" (__mepc), [rvc_mask] "r" (rvc_mask),
+	  [xlen_minus_16] "i" (XLEN_MINUS_16));
+
+	return val;
+}
+
+union reg_data {
+	u8 data_bytes[8];
+	ulong data_ulong;
+	u64 data_u64;
+};
+
+int handle_misaligned_load(struct pt_regs *regs)
+{
+	union reg_data val;
+	unsigned long epc = regs->epc;
+	unsigned long insn = get_insn(epc);
+	unsigned long addr = csr_read(mtval);
+	int i, fp = 0, shift = 0, len = 0;
+
+	regs->epc = 0;
+
+	if ((insn & INSN_MASK_LW) == INSN_MATCH_LW) {
+		len = 4;
+		shift = 8 * (sizeof(unsigned long) - len);
+#if defined(CONFIG_64BIT)
+	} else if ((insn & INSN_MASK_LD) == INSN_MATCH_LD) {
+		len = 8;
+		shift = 8 * (sizeof(unsigned long) - len);
+	} else if ((insn & INSN_MASK_LWU) == INSN_MATCH_LWU) {
+		len = 4;
+#endif
+	} else if ((insn & INSN_MASK_FLD) == INSN_MATCH_FLD) {
+		fp = 1;
+		len = 8;
+	} else if ((insn & INSN_MASK_FLW) == INSN_MATCH_FLW) {
+		fp = 1;
+		len = 4;
+	} else if ((insn & INSN_MASK_LH) == INSN_MATCH_LH) {
+		len = 2;
+		shift = 8 * (sizeof(unsigned long) - len);
+	} else if ((insn & INSN_MASK_LHU) == INSN_MATCH_LHU) {
+		len = 2;
+#if defined(CONFIG_64BIT)
+	} else if ((insn & INSN_MASK_C_LD) == INSN_MATCH_C_LD) {
+		len = 8;
+		shift = 8 * (sizeof(unsigned long) - len);
+		insn = RVC_RS2S(insn) << SH_RD;
+	} else if ((insn & INSN_MASK_C_LDSP) == INSN_MATCH_C_LDSP &&
+		   ((insn >> SH_RD) & 0x1f)) {
+		len = 8;
+		shift = 8 * (sizeof(unsigned long) - len);
+#endif
+	} else if ((insn & INSN_MASK_C_LW) == INSN_MATCH_C_LW) {
+		len = 4;
+		shift = 8 * (sizeof(unsigned long) - len);
+		insn = RVC_RS2S(insn) << SH_RD;
+	} else if ((insn & INSN_MASK_C_LWSP) == INSN_MATCH_C_LWSP &&
+		   ((insn >> SH_RD) & 0x1f)) {
+		len = 4;
+		shift = 8 * (sizeof(unsigned long) - len);
+	} else if ((insn & INSN_MASK_C_FLD) == INSN_MATCH_C_FLD) {
+		fp = 1;
+		len = 8;
+		insn = RVC_RS2S(insn) << SH_RD;
+	} else if ((insn & INSN_MASK_C_FLDSP) == INSN_MATCH_C_FLDSP) {
+		fp = 1;
+		len = 8;
+#if defined(CONFIG_32BIT)
+	} else if ((insn & INSN_MASK_C_FLW) == INSN_MATCH_C_FLW) {
+		fp = 1;
+		len = 4;
+		insn = RVC_RS2S(insn) << SH_RD;
+	} else if ((insn & INSN_MASK_C_FLWSP) == INSN_MATCH_C_FLWSP) {
+		fp = 1;
+		len = 4;
+#endif
+	} else {
+		regs->epc = epc;
+		return -1;
+	}
+
+	val.data_u64 = 0;
+	for (i = 0; i < len; i++)
+		val.data_bytes[i] = load_u8((void *)(addr + i));
+
+	if (fp)
+		return -1;
+	SET_RD(insn, regs, val.data_ulong << shift >> shift);
+
+	regs->epc = epc + INSN_LEN(insn);
+
+	return 0;
+}
+
+int handle_misaligned_store(struct pt_regs *regs)
+{
+	union reg_data val;
+	unsigned long epc = regs->epc;
+	unsigned long insn = get_insn(epc);
+	unsigned long addr = csr_read(mtval);
+	int i, len = 0;
+
+	regs->epc = 0;
+
+	val.data_ulong = GET_RS2(insn, regs);
+
+	if ((insn & INSN_MASK_SW) == INSN_MATCH_SW) {
+		len = 4;
+#if defined(CONFIG_64BIT)
+	} else if ((insn & INSN_MASK_SD) == INSN_MATCH_SD) {
+		len = 8;
+#endif
+	} else if ((insn & INSN_MASK_SH) == INSN_MATCH_SH) {
+		len = 2;
+#if defined(CONFIG_64BIT)
+	} else if ((insn & INSN_MASK_C_SD) == INSN_MATCH_C_SD) {
+		len = 8;
+		val.data_ulong = GET_RS2S(insn, regs);
+	} else if ((insn & INSN_MASK_C_SDSP) == INSN_MATCH_C_SDSP) {
+		len = 8;
+		val.data_ulong = GET_RS2C(insn, regs);
+#endif
+	} else if ((insn & INSN_MASK_C_SW) == INSN_MATCH_C_SW) {
+		len = 4;
+		val.data_ulong = GET_RS2S(insn, regs);
+	} else if ((insn & INSN_MASK_C_SWSP) == INSN_MATCH_C_SWSP) {
+		len = 4;
+		val.data_ulong = GET_RS2C(insn, regs);
+	} else {
+		regs->epc = epc;
+		return -1;
+	}
+
+	for (i = 0; i < len; i++)
+		store_u8((void *)(addr + i), val.data_bytes[i]);
+
+	regs->epc = epc + INSN_LEN(insn);
+
+	return 0;
+}
diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c
new file mode 100644
index 000000000..123d05255
--- /dev/null
+++ b/arch/riscv/kernel/vdso.c
@@ -0,0 +1,322 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2004 Benjamin Herrenschmidt, IBM Corp.
+ *                    <benh@kernel.crashing.org>
+ * Copyright (C) 2012 ARM Limited
+ * Copyright (C) 2015 Regents of the University of California
+ */
+
+#include <linux/elf.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/binfmts.h>
+#include <linux/err.h>
+#include <asm/page.h>
+#include <asm/vdso.h>
+#include <linux/time_namespace.h>
+
+#ifdef CONFIG_GENERIC_TIME_VSYSCALL
+#include <vdso/datapage.h>
+#else
+struct vdso_data {
+};
+#endif
+
+extern char vdso_start[], vdso_end[];
+#ifdef CONFIG_COMPAT
+extern char compat_vdso_start[], compat_vdso_end[];
+#endif
+
+enum vvar_pages {
+	VVAR_DATA_PAGE_OFFSET,
+	VVAR_TIMENS_PAGE_OFFSET,
+	VVAR_NR_PAGES,
+};
+
+enum rv_vdso_map {
+	RV_VDSO_MAP_VVAR,
+	RV_VDSO_MAP_VDSO,
+};
+
+#define VVAR_SIZE  (VVAR_NR_PAGES << PAGE_SHIFT)
+
+/*
+ * The vDSO data page.
+ */
+static union {
+	struct vdso_data	data;
+	u8			page[PAGE_SIZE];
+} vdso_data_store __page_aligned_data;
+struct vdso_data *vdso_data = &vdso_data_store.data;
+
+struct __vdso_info {
+	const char *name;
+	const char *vdso_code_start;
+	const char *vdso_code_end;
+	unsigned long vdso_pages;
+	/* Data Mapping */
+	struct vm_special_mapping *dm;
+	/* Code Mapping */
+	struct vm_special_mapping *cm;
+};
+
+static struct __vdso_info vdso_info;
+#ifdef CONFIG_COMPAT
+static struct __vdso_info compat_vdso_info;
+#endif
+
+static int vdso_mremap(const struct vm_special_mapping *sm,
+		       struct vm_area_struct *new_vma)
+{
+	current->mm->context.vdso = (void *)new_vma->vm_start;
+
+	return 0;
+}
+
+static void __init __vdso_init(struct __vdso_info *vdso_info)
+{
+	unsigned int i;
+	struct page **vdso_pagelist;
+	unsigned long pfn;
+
+	if (memcmp(vdso_info->vdso_code_start, "\177ELF", 4))
+		panic("vDSO is not a valid ELF object!\n");
+
+	vdso_info->vdso_pages = (
+		vdso_info->vdso_code_end -
+		vdso_info->vdso_code_start) >>
+		PAGE_SHIFT;
+
+	vdso_pagelist = kcalloc(vdso_info->vdso_pages,
+				sizeof(struct page *),
+				GFP_KERNEL);
+	if (vdso_pagelist == NULL)
+		panic("vDSO kcalloc failed!\n");
+
+	/* Grab the vDSO code pages. */
+	pfn = sym_to_pfn(vdso_info->vdso_code_start);
+
+	for (i = 0; i < vdso_info->vdso_pages; i++)
+		vdso_pagelist[i] = pfn_to_page(pfn + i);
+
+	vdso_info->cm->pages = vdso_pagelist;
+}
+
+#ifdef CONFIG_TIME_NS
+struct vdso_data *arch_get_vdso_data(void *vvar_page)
+{
+	return (struct vdso_data *)(vvar_page);
+}
+
+/*
+ * The vvar mapping contains data for a specific time namespace, so when a task
+ * changes namespace we must unmap its vvar data for the old namespace.
+ * Subsequent faults will map in data for the new namespace.
+ *
+ * For more details see timens_setup_vdso_data().
+ */
+int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
+{
+	struct mm_struct *mm = task->mm;
+	struct vm_area_struct *vma;
+	VMA_ITERATOR(vmi, mm, 0);
+
+	mmap_read_lock(mm);
+
+	for_each_vma(vmi, vma) {
+		unsigned long size = vma->vm_end - vma->vm_start;
+
+		if (vma_is_special_mapping(vma, vdso_info.dm))
+			zap_page_range(vma, vma->vm_start, size);
+#ifdef CONFIG_COMPAT
+		if (vma_is_special_mapping(vma, compat_vdso_info.dm))
+			zap_page_range(vma, vma->vm_start, size);
+#endif
+	}
+
+	mmap_read_unlock(mm);
+	return 0;
+}
+
+static struct page *find_timens_vvar_page(struct vm_area_struct *vma)
+{
+	if (likely(vma->vm_mm == current->mm))
+		return current->nsproxy->time_ns->vvar_page;
+
+	/*
+	 * VM_PFNMAP | VM_IO protect .fault() handler from being called
+	 * through interfaces like /proc/$pid/mem or
+	 * process_vm_{readv,writev}() as long as there's no .access()
+	 * in special_mapping_vmops.
+	 * For more details check_vma_flags() and __access_remote_vm()
+	 */
+	WARN(1, "vvar_page accessed remotely");
+
+	return NULL;
+}
+#else
+static struct page *find_timens_vvar_page(struct vm_area_struct *vma)
+{
+	return NULL;
+}
+#endif
+
+static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
+			     struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	struct page *timens_page = find_timens_vvar_page(vma);
+	unsigned long pfn;
+
+	switch (vmf->pgoff) {
+	case VVAR_DATA_PAGE_OFFSET:
+		if (timens_page)
+			pfn = page_to_pfn(timens_page);
+		else
+			pfn = sym_to_pfn(vdso_data);
+		break;
+#ifdef CONFIG_TIME_NS
+	case VVAR_TIMENS_PAGE_OFFSET:
+		/*
+		 * If a task belongs to a time namespace then a namespace
+		 * specific VVAR is mapped with the VVAR_DATA_PAGE_OFFSET and
+		 * the real VVAR page is mapped with the VVAR_TIMENS_PAGE_OFFSET
+		 * offset.
+		 * See also the comment near timens_setup_vdso_data().
+		 */
+		if (!timens_page)
+			return VM_FAULT_SIGBUS;
+		pfn = sym_to_pfn(vdso_data);
+		break;
+#endif /* CONFIG_TIME_NS */
+	default:
+		return VM_FAULT_SIGBUS;
+	}
+
+	return vmf_insert_pfn(vma, vmf->address, pfn);
+}
+
+static struct vm_special_mapping rv_vdso_maps[] __ro_after_init = {
+	[RV_VDSO_MAP_VVAR] = {
+		.name   = "[vvar]",
+		.fault = vvar_fault,
+	},
+	[RV_VDSO_MAP_VDSO] = {
+		.name   = "[vdso]",
+		.mremap = vdso_mremap,
+	},
+};
+
+static struct __vdso_info vdso_info __ro_after_init = {
+	.name = "vdso",
+	.vdso_code_start = vdso_start,
+	.vdso_code_end = vdso_end,
+	.dm = &rv_vdso_maps[RV_VDSO_MAP_VVAR],
+	.cm = &rv_vdso_maps[RV_VDSO_MAP_VDSO],
+};
+
+#ifdef CONFIG_COMPAT
+static struct vm_special_mapping rv_compat_vdso_maps[] __ro_after_init = {
+	[RV_VDSO_MAP_VVAR] = {
+		.name   = "[vvar]",
+		.fault = vvar_fault,
+	},
+	[RV_VDSO_MAP_VDSO] = {
+		.name   = "[vdso]",
+		.mremap = vdso_mremap,
+	},
+};
+
+static struct __vdso_info compat_vdso_info __ro_after_init = {
+	.name = "compat_vdso",
+	.vdso_code_start = compat_vdso_start,
+	.vdso_code_end = compat_vdso_end,
+	.dm = &rv_compat_vdso_maps[RV_VDSO_MAP_VVAR],
+	.cm = &rv_compat_vdso_maps[RV_VDSO_MAP_VDSO],
+};
+#endif
+
+static int __init vdso_init(void)
+{
+	__vdso_init(&vdso_info);
+#ifdef CONFIG_COMPAT
+	__vdso_init(&compat_vdso_info);
+#endif
+
+	return 0;
+}
+arch_initcall(vdso_init);
+
+static int __setup_additional_pages(struct mm_struct *mm,
+				    struct linux_binprm *bprm,
+				    int uses_interp,
+				    struct __vdso_info *vdso_info)
+{
+	unsigned long vdso_base, vdso_text_len, vdso_mapping_len;
+	void *ret;
+
+	BUILD_BUG_ON(VVAR_NR_PAGES != __VVAR_PAGES);
+
+	vdso_text_len = vdso_info->vdso_pages << PAGE_SHIFT;
+	/* Be sure to map the data page */
+	vdso_mapping_len = vdso_text_len + VVAR_SIZE;
+
+	vdso_base = get_unmapped_area(NULL, 0, vdso_mapping_len, 0, 0);
+	if (IS_ERR_VALUE(vdso_base)) {
+		ret = ERR_PTR(vdso_base);
+		goto up_fail;
+	}
+
+	ret = _install_special_mapping(mm, vdso_base, VVAR_SIZE,
+		(VM_READ | VM_MAYREAD | VM_PFNMAP), vdso_info->dm);
+	if (IS_ERR(ret))
+		goto up_fail;
+
+	vdso_base += VVAR_SIZE;
+	mm->context.vdso = (void *)vdso_base;
+
+	ret =
+	   _install_special_mapping(mm, vdso_base, vdso_text_len,
+		(VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC),
+		vdso_info->cm);
+
+	if (IS_ERR(ret))
+		goto up_fail;
+
+	return 0;
+
+up_fail:
+	mm->context.vdso = NULL;
+	return PTR_ERR(ret);
+}
+
+#ifdef CONFIG_COMPAT
+int compat_arch_setup_additional_pages(struct linux_binprm *bprm,
+				       int uses_interp)
+{
+	struct mm_struct *mm = current->mm;
+	int ret;
+
+	if (mmap_write_lock_killable(mm))
+		return -EINTR;
+
+	ret = __setup_additional_pages(mm, bprm, uses_interp,
+							&compat_vdso_info);
+	mmap_write_unlock(mm);
+
+	return ret;
+}
+#endif
+
+int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
+{
+	struct mm_struct *mm = current->mm;
+	int ret;
+
+	if (mmap_write_lock_killable(mm))
+		return -EINTR;
+
+	ret = __setup_additional_pages(mm, bprm, uses_interp, &vdso_info);
+	mmap_write_unlock(mm);
+
+	return ret;
+}
diff --git a/arch/riscv/kernel/vdso/.gitignore b/arch/riscv/kernel/vdso/.gitignore
new file mode 100644
index 000000000..3a19def86
--- /dev/null
+++ b/arch/riscv/kernel/vdso/.gitignore
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
+vdso.lds
+*.tmp
+vdso-syms.S
diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile
new file mode 100644
index 000000000..06e6b27f3
--- /dev/null
+++ b/arch/riscv/kernel/vdso/Makefile
@@ -0,0 +1,83 @@
+# SPDX-License-Identifier: GPL-2.0-only
+# Copied from arch/tile/kernel/vdso/Makefile
+
+# Absolute relocation type $(ARCH_REL_TYPE_ABS) needs to be defined before
+# the inclusion of generic Makefile.
+ARCH_REL_TYPE_ABS := R_RISCV_32|R_RISCV_64|R_RISCV_JUMP_SLOT
+include $(srctree)/lib/vdso/Makefile
+# Symbols present in the vdso
+vdso-syms  = rt_sigreturn
+ifdef CONFIG_64BIT
+vdso-syms += vgettimeofday
+endif
+vdso-syms += getcpu
+vdso-syms += flush_icache
+
+# Files to link into the vdso
+obj-vdso = $(patsubst %, %.o, $(vdso-syms)) note.o
+
+ccflags-y := -fno-stack-protector
+ccflags-y += -DDISABLE_BRANCH_PROFILING
+
+ifneq ($(c-gettimeofday-y),)
+  CFLAGS_vgettimeofday.o += -fPIC -include $(c-gettimeofday-y)
+endif
+
+# Build rules
+targets := $(obj-vdso) vdso.so vdso.so.dbg vdso.lds
+obj-vdso := $(addprefix $(obj)/, $(obj-vdso))
+
+obj-y += vdso.o
+CPPFLAGS_vdso.lds += -P -C -U$(ARCH)
+ifneq ($(filter vgettimeofday, $(vdso-syms)),)
+CPPFLAGS_vdso.lds += -DHAS_VGETTIMEOFDAY
+endif
+
+# Disable -pg to prevent insert call site
+CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE)
+
+# Disable profiling and instrumentation for VDSO code
+GCOV_PROFILE := n
+KCOV_INSTRUMENT := n
+KASAN_SANITIZE := n
+UBSAN_SANITIZE := n
+
+# Force dependency
+$(obj)/vdso.o: $(obj)/vdso.so
+
+# link rule for the .so file, .lds has to be first
+$(obj)/vdso.so.dbg: $(obj)/vdso.lds $(obj-vdso) FORCE
+	$(call if_changed,vdsold)
+LDFLAGS_vdso.so.dbg = -shared -S -soname=linux-vdso.so.1 \
+	--build-id=sha1 --hash-style=both --eh-frame-hdr
+
+# strip rule for the .so file
+$(obj)/%.so: OBJCOPYFLAGS := -S
+$(obj)/%.so: $(obj)/%.so.dbg FORCE
+	$(call if_changed,objcopy)
+
+# Generate VDSO offsets using helper script
+gen-vdsosym := $(srctree)/$(src)/gen_vdso_offsets.sh
+quiet_cmd_vdsosym = VDSOSYM $@
+	cmd_vdsosym = $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@
+
+include/generated/vdso-offsets.h: $(obj)/vdso.so.dbg FORCE
+	$(call if_changed,vdsosym)
+
+# actual build commands
+# The DSO images are built using a special linker script
+# Make sure only to export the intended __vdso_xxx symbol offsets.
+quiet_cmd_vdsold = VDSOLD  $@
+      cmd_vdsold = $(LD) $(ld_flags) -T $(filter-out FORCE,$^) -o $@.tmp && \
+                   $(OBJCOPY) $(patsubst %, -G __vdso_%, $(vdso-syms)) $@.tmp $@ && \
+                   rm $@.tmp
+
+# install commands for the unstripped file
+quiet_cmd_vdso_install = INSTALL $@
+      cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@
+
+vdso.so: $(obj)/vdso.so.dbg
+	@mkdir -p $(MODLIB)/vdso
+	$(call cmd,vdso_install)
+
+vdso_install: vdso.so
diff --git a/arch/riscv/kernel/vdso/flush_icache.S b/arch/riscv/kernel/vdso/flush_icache.S
new file mode 100644
index 000000000..82f97d67c
--- /dev/null
+++ b/arch/riscv/kernel/vdso/flush_icache.S
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2017 SiFive
+ */
+
+#include <linux/linkage.h>
+#include <asm/unistd.h>
+
+	.text
+/* int __vdso_flush_icache(void *start, void *end, unsigned long flags); */
+ENTRY(__vdso_flush_icache)
+	.cfi_startproc
+#ifdef CONFIG_SMP
+	li a7, __NR_riscv_flush_icache
+	ecall
+#else
+	fence.i
+	li a0, 0
+#endif
+	ret
+	.cfi_endproc
+ENDPROC(__vdso_flush_icache)
diff --git a/arch/riscv/kernel/vdso/gen_vdso_offsets.sh b/arch/riscv/kernel/vdso/gen_vdso_offsets.sh
new file mode 100755
index 000000000..c2e5613f3
--- /dev/null
+++ b/arch/riscv/kernel/vdso/gen_vdso_offsets.sh
@@ -0,0 +1,5 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+LC_ALL=C
+sed -n -e 's/^[0]\+\(0[0-9a-fA-F]*\) . \(__vdso_[a-zA-Z0-9_]*\)$/\#define \2_offset\t0x\1/p'
diff --git a/arch/riscv/kernel/vdso/getcpu.S b/arch/riscv/kernel/vdso/getcpu.S
new file mode 100644
index 000000000..bb0c05e2f
--- /dev/null
+++ b/arch/riscv/kernel/vdso/getcpu.S
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2017 SiFive
+ */
+
+#include <linux/linkage.h>
+#include <asm/unistd.h>
+
+	.text
+/* int __vdso_getcpu(unsigned *cpu, unsigned *node, void *unused); */
+ENTRY(__vdso_getcpu)
+	.cfi_startproc
+	/* For now, just do the syscall. */
+	li a7, __NR_getcpu
+	ecall
+	ret
+	.cfi_endproc
+ENDPROC(__vdso_getcpu)
diff --git a/arch/riscv/kernel/vdso/note.S b/arch/riscv/kernel/vdso/note.S
new file mode 100644
index 000000000..2a956c942
--- /dev/null
+++ b/arch/riscv/kernel/vdso/note.S
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * This supplies .note.* sections to go into the PT_NOTE inside the vDSO text.
+ * Here we can supply some information useful to userland.
+ */
+
+#include <linux/elfnote.h>
+#include <linux/version.h>
+
+ELFNOTE_START(Linux, 0, "a")
+	.long LINUX_VERSION_CODE
+ELFNOTE_END
diff --git a/arch/riscv/kernel/vdso/rt_sigreturn.S b/arch/riscv/kernel/vdso/rt_sigreturn.S
new file mode 100644
index 000000000..0573705ea
--- /dev/null
+++ b/arch/riscv/kernel/vdso/rt_sigreturn.S
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2014 Regents of the University of California
+ */
+
+#include <linux/linkage.h>
+#include <asm/unistd.h>
+
+	.text
+ENTRY(__vdso_rt_sigreturn)
+	.cfi_startproc
+	.cfi_signal_frame
+	li a7, __NR_rt_sigreturn
+	scall
+	.cfi_endproc
+ENDPROC(__vdso_rt_sigreturn)
diff --git a/arch/riscv/kernel/vdso/vdso.S b/arch/riscv/kernel/vdso/vdso.S
new file mode 100644
index 000000000..83f1c899e
--- /dev/null
+++ b/arch/riscv/kernel/vdso/vdso.S
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2014 Regents of the University of California
+ */
+
+#include <linux/init.h>
+#include <linux/linkage.h>
+#include <asm/page.h>
+
+#ifndef __VDSO_PATH
+#define __VDSO_PATH "arch/riscv/kernel/vdso/vdso.so"
+#endif
+
+	__PAGE_ALIGNED_DATA
+
+	.globl vdso_start, vdso_end
+	.balign PAGE_SIZE
+vdso_start:
+	.incbin __VDSO_PATH
+	.balign PAGE_SIZE
+vdso_end:
+
+	.previous
diff --git a/arch/riscv/kernel/vdso/vdso.lds.S b/arch/riscv/kernel/vdso/vdso.lds.S
new file mode 100644
index 000000000..150b1a572
--- /dev/null
+++ b/arch/riscv/kernel/vdso/vdso.lds.S
@@ -0,0 +1,80 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ */
+#include <asm/page.h>
+#include <asm/vdso.h>
+
+OUTPUT_ARCH(riscv)
+
+SECTIONS
+{
+	PROVIDE(_vdso_data = . - __VVAR_PAGES * PAGE_SIZE);
+#ifdef CONFIG_TIME_NS
+	PROVIDE(_timens_data = _vdso_data + PAGE_SIZE);
+#endif
+	. = SIZEOF_HEADERS;
+
+	.hash		: { *(.hash) }			:text
+	.gnu.hash	: { *(.gnu.hash) }
+	.dynsym		: { *(.dynsym) }
+	.dynstr		: { *(.dynstr) }
+	.gnu.version	: { *(.gnu.version) }
+	.gnu.version_d	: { *(.gnu.version_d) }
+	.gnu.version_r	: { *(.gnu.version_r) }
+
+	.note		: { *(.note.*) }		:text	:note
+	.dynamic	: { *(.dynamic) }		:text	:dynamic
+
+	.eh_frame_hdr	: { *(.eh_frame_hdr) }		:text	:eh_frame_hdr
+	.eh_frame	: { KEEP (*(.eh_frame)) }	:text
+
+	.rodata		: { *(.rodata .rodata.* .gnu.linkonce.r.*) }
+
+	/*
+	 * This linker script is used both with -r and with -shared.
+	 * For the layouts to match, we need to skip more than enough
+	 * space for the dynamic symbol table, etc. If this amount is
+	 * insufficient, ld -shared will error; simply increase it here.
+	 */
+	. = 0x800;
+	.text		: { *(.text .text.*) }		:text
+
+	.data		: {
+		*(.got.plt) *(.got)
+		*(.data .data.* .gnu.linkonce.d.*)
+		*(.dynbss)
+		*(.bss .bss.* .gnu.linkonce.b.*)
+	}
+}
+
+/*
+ * We must supply the ELF program headers explicitly to get just one
+ * PT_LOAD segment, and set the flags explicitly to make segments read-only.
+ */
+PHDRS
+{
+	text		PT_LOAD		FLAGS(5) FILEHDR PHDRS; /* PF_R|PF_X */
+	dynamic		PT_DYNAMIC	FLAGS(4);		/* PF_R */
+	note		PT_NOTE		FLAGS(4);		/* PF_R */
+	eh_frame_hdr	PT_GNU_EH_FRAME;
+}
+
+/*
+ * This controls what symbols we export from the DSO.
+ */
+VERSION
+{
+	LINUX_4.15 {
+	global:
+		__vdso_rt_sigreturn;
+#ifdef HAS_VGETTIMEOFDAY
+		__vdso_gettimeofday;
+		__vdso_clock_gettime;
+		__vdso_clock_getres;
+#endif
+		__vdso_getcpu;
+		__vdso_flush_icache;
+	local: *;
+	};
+}
diff --git a/arch/riscv/kernel/vdso/vgettimeofday.c b/arch/riscv/kernel/vdso/vgettimeofday.c
new file mode 100644
index 000000000..cc0d80699
--- /dev/null
+++ b/arch/riscv/kernel/vdso/vgettimeofday.c
@@ -0,0 +1,31 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copied from arch/arm64/kernel/vdso/vgettimeofday.c
+ *
+ * Copyright (C) 2018 ARM Ltd.
+ * Copyright (C) 2020 SiFive
+ */
+
+#include <linux/time.h>
+#include <linux/types.h>
+
+extern
+int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts);
+int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts)
+{
+	return __cvdso_clock_gettime(clock, ts);
+}
+
+extern
+int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz);
+int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz)
+{
+	return __cvdso_gettimeofday(tv, tz);
+}
+
+extern
+int __vdso_clock_getres(clockid_t clock_id, struct __kernel_timespec *res);
+int __vdso_clock_getres(clockid_t clock_id, struct __kernel_timespec *res)
+{
+	return __cvdso_clock_getres(clock_id, res);
+}
diff --git a/arch/riscv/kernel/vmlinux-xip.lds.S b/arch/riscv/kernel/vmlinux-xip.lds.S
new file mode 100644
index 000000000..24a2fdd3b
--- /dev/null
+++ b/arch/riscv/kernel/vmlinux-xip.lds.S
@@ -0,0 +1,149 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ * Copyright (C) 2017 SiFive
+ * Copyright (C) 2020 Vitaly Wool, Konsulko AB
+ */
+
+#include <asm/pgtable.h>
+#define LOAD_OFFSET KERNEL_LINK_ADDR
+/* No __ro_after_init data in the .rodata section - which will always be ro */
+#define RO_AFTER_INIT_DATA
+
+#include <asm/vmlinux.lds.h>
+#include <asm/page.h>
+#include <asm/cache.h>
+#include <asm/thread_info.h>
+
+OUTPUT_ARCH(riscv)
+ENTRY(_start)
+
+jiffies = jiffies_64;
+
+SECTIONS
+{
+	/* Beginning of code and text segment */
+	. = LOAD_OFFSET;
+	_xiprom = .;
+	_start = .;
+	HEAD_TEXT_SECTION
+	INIT_TEXT_SECTION(PAGE_SIZE)
+	/* we have to discard exit text and such at runtime, not link time */
+	__exittext_begin = .;
+	.exit.text :
+	{
+		EXIT_TEXT
+	}
+	__exittext_end = .;
+
+	.text : {
+		_text = .;
+		_stext = .;
+		TEXT_TEXT
+		SCHED_TEXT
+		CPUIDLE_TEXT
+		LOCK_TEXT
+		KPROBES_TEXT
+		ENTRY_TEXT
+		IRQENTRY_TEXT
+		SOFTIRQENTRY_TEXT
+		_etext = .;
+	}
+	RO_DATA(L1_CACHE_BYTES)
+	.srodata : {
+		*(.srodata*)
+	}
+	.init.rodata : {
+		INIT_SETUP(16)
+		INIT_CALLS
+		CON_INITCALL
+		INIT_RAM_FS
+	}
+	_exiprom = .;			/* End of XIP ROM area */
+
+
+/*
+ * From this point, stuff is considered writable and will be copied to RAM
+ */
+	__data_loc = ALIGN(PAGE_SIZE);		/* location in file */
+	. = KERNEL_LINK_ADDR + XIP_OFFSET;	/* location in memory */
+
+#undef LOAD_OFFSET
+#define LOAD_OFFSET (KERNEL_LINK_ADDR + XIP_OFFSET - (__data_loc & XIP_OFFSET_MASK))
+
+	_sdata = .;			/* Start of data section */
+	_data = .;
+	RW_DATA(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
+	_edata = .;
+	__start_ro_after_init = .;
+	.data.ro_after_init : AT(ADDR(.data.ro_after_init) - LOAD_OFFSET) {
+		*(.data..ro_after_init)
+	}
+	__end_ro_after_init = .;
+
+	. = ALIGN(PAGE_SIZE);
+	__init_begin = .;
+	.init.data : {
+		INIT_DATA
+	}
+	.exit.data : {
+		EXIT_DATA
+	}
+	. = ALIGN(8);
+	__soc_early_init_table : {
+		__soc_early_init_table_start = .;
+		KEEP(*(__soc_early_init_table))
+		__soc_early_init_table_end = .;
+	}
+	__soc_builtin_dtb_table : {
+		__soc_builtin_dtb_table_start = .;
+		KEEP(*(__soc_builtin_dtb_table))
+		__soc_builtin_dtb_table_end = .;
+	}
+
+	. = ALIGN(8);
+	.alternative : {
+		__alt_start = .;
+		*(.alternative)
+		__alt_end = .;
+	}
+	__init_end = .;
+
+	. = ALIGN(16);
+	.xip.traps : {
+		__xip_traps_start = .;
+		*(.xip.traps)
+		__xip_traps_end = .;
+	}
+
+	. = ALIGN(PAGE_SIZE);
+	.sdata : {
+		__global_pointer$ = . + 0x800;
+		*(.sdata*)
+		*(.sbss*)
+	}
+
+	BSS_SECTION(PAGE_SIZE, PAGE_SIZE, 0)
+
+	PERCPU_SECTION(L1_CACHE_BYTES)
+
+	.rel.dyn : AT(ADDR(.rel.dyn) - LOAD_OFFSET) {
+		*(.rel.dyn*)
+	}
+
+	/*
+	 * End of copied data. We need a dummy section to get its LMA.
+	 * Also located before final ALIGN() as trailing padding is not stored
+	 * in the resulting binary file and useless to copy.
+	 */
+	.data.endmark : AT(ADDR(.data.endmark) - LOAD_OFFSET) { }
+	_edata_loc = LOADADDR(.data.endmark);
+
+	. = ALIGN(PAGE_SIZE);
+	_end = .;
+
+	STABS_DEBUG
+	DWARF_DEBUG
+
+	DISCARDS
+}
diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.lds.S
new file mode 100644
index 000000000..d478e063b
--- /dev/null
+++ b/arch/riscv/kernel/vmlinux.lds.S
@@ -0,0 +1,149 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ * Copyright (C) 2017 SiFive
+ */
+
+#define RO_EXCEPTION_TABLE_ALIGN	4
+
+#ifdef CONFIG_XIP_KERNEL
+#include "vmlinux-xip.lds.S"
+#else
+
+#include <asm/pgtable.h>
+#define LOAD_OFFSET KERNEL_LINK_ADDR
+
+#include <asm/vmlinux.lds.h>
+#include <asm/page.h>
+#include <asm/cache.h>
+#include <asm/thread_info.h>
+#include <asm/set_memory.h>
+#include "image-vars.h"
+
+#include <linux/sizes.h>
+OUTPUT_ARCH(riscv)
+ENTRY(_start)
+
+jiffies = jiffies_64;
+
+PECOFF_SECTION_ALIGNMENT = 0x1000;
+PECOFF_FILE_ALIGNMENT = 0x200;
+
+SECTIONS
+{
+	/* Beginning of code and text segment */
+	. = LOAD_OFFSET;
+	_start = .;
+	HEAD_TEXT_SECTION
+	. = ALIGN(PAGE_SIZE);
+
+	.text : {
+		_text = .;
+		_stext = .;
+		TEXT_TEXT
+		SCHED_TEXT
+		CPUIDLE_TEXT
+		LOCK_TEXT
+		KPROBES_TEXT
+		ENTRY_TEXT
+		IRQENTRY_TEXT
+		SOFTIRQENTRY_TEXT
+		_etext = .;
+	}
+
+	. = ALIGN(SECTION_ALIGN);
+	__init_begin = .;
+	__init_text_begin = .;
+	.init.text : AT(ADDR(.init.text) - LOAD_OFFSET) ALIGN(SECTION_ALIGN) { \
+		_sinittext = .;						\
+		INIT_TEXT						\
+		_einittext = .;						\
+	}
+
+	. = ALIGN(8);
+	__soc_early_init_table : {
+		__soc_early_init_table_start = .;
+		KEEP(*(__soc_early_init_table))
+		__soc_early_init_table_end = .;
+	}
+	__soc_builtin_dtb_table : {
+		__soc_builtin_dtb_table_start = .;
+		KEEP(*(__soc_builtin_dtb_table))
+		__soc_builtin_dtb_table_end = .;
+	}
+	/* we have to discard exit text and such at runtime, not link time */
+	__exittext_begin = .;
+	.exit.text :
+	{
+		EXIT_TEXT
+	}
+	__exittext_end = .;
+
+	__init_text_end = .;
+	. = ALIGN(SECTION_ALIGN);
+#ifdef CONFIG_EFI
+	. = ALIGN(PECOFF_SECTION_ALIGNMENT);
+	__pecoff_text_end = .;
+#endif
+	/* Start of init data section */
+	__init_data_begin = .;
+	INIT_DATA_SECTION(16)
+	.exit.data :
+	{
+		EXIT_DATA
+	}
+	PERCPU_SECTION(L1_CACHE_BYTES)
+
+	.rel.dyn : {
+		*(.rel.dyn*)
+	}
+
+	__init_data_end = .;
+
+	. = ALIGN(8);
+	.alternative : {
+		__alt_start = .;
+		*(.alternative)
+		__alt_end = .;
+	}
+	__init_end = .;
+
+	/* Start of data section */
+	_sdata = .;
+	RO_DATA(SECTION_ALIGN)
+	.srodata : {
+		*(.srodata*)
+	}
+
+	. = ALIGN(SECTION_ALIGN);
+	_data = .;
+
+	RW_DATA(L1_CACHE_BYTES, PAGE_SIZE, THREAD_ALIGN)
+	.sdata : {
+		__global_pointer$ = . + 0x800;
+		*(.sdata*)
+	}
+
+#ifdef CONFIG_EFI
+	.pecoff_edata_padding : { BYTE(0); . = ALIGN(PECOFF_FILE_ALIGNMENT); }
+	__pecoff_data_raw_size = ABSOLUTE(. - __pecoff_text_end);
+#endif
+
+	/* End of data section */
+	_edata = .;
+
+	BSS_SECTION(PAGE_SIZE, PAGE_SIZE, 0)
+
+#ifdef CONFIG_EFI
+	. = ALIGN(PECOFF_SECTION_ALIGNMENT);
+	__pecoff_data_virt_size = ABSOLUTE(. - __pecoff_text_end);
+#endif
+	_end = .;
+
+	STABS_DEBUG
+	DWARF_DEBUG
+	ELF_DETAILS
+
+	DISCARDS
+}
+#endif /* CONFIG_XIP_KERNEL */
diff --git a/arch/riscv/kvm/Kconfig b/arch/riscv/kvm/Kconfig
new file mode 100644
index 000000000..f36a737d5
--- /dev/null
+++ b/arch/riscv/kvm/Kconfig
@@ -0,0 +1,36 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# KVM configuration
+#
+
+source "virt/kvm/Kconfig"
+
+menuconfig VIRTUALIZATION
+	bool "Virtualization"
+	help
+	  Say Y here to get to see options for using your Linux host to run
+	  other operating systems inside virtual machines (guests).
+	  This option alone does not add any kernel code.
+
+	  If you say N, all options in this submenu will be skipped and
+	  disabled.
+
+if VIRTUALIZATION
+
+config KVM
+	tristate "Kernel-based Virtual Machine (KVM) support (EXPERIMENTAL)"
+	depends on RISCV_SBI && MMU
+	select MMU_NOTIFIER
+	select PREEMPT_NOTIFIERS
+	select KVM_MMIO
+	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
+	select KVM_XFER_TO_GUEST_WORK
+	select HAVE_KVM_VCPU_ASYNC_IOCTL
+	select HAVE_KVM_EVENTFD
+	select SRCU
+	help
+	  Support hosting virtualized guest machines.
+
+	  If unsure, say N.
+
+endif # VIRTUALIZATION
diff --git a/arch/riscv/kvm/Makefile b/arch/riscv/kvm/Makefile
new file mode 100644
index 000000000..019df9208
--- /dev/null
+++ b/arch/riscv/kvm/Makefile
@@ -0,0 +1,27 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for RISC-V KVM support
+#
+
+ccflags-y += -I $(srctree)/$(src)
+
+include $(srctree)/virt/kvm/Makefile.kvm
+
+obj-$(CONFIG_KVM) += kvm.o
+
+kvm-y += main.o
+kvm-y += vm.o
+kvm-y += vmid.o
+kvm-y += tlb.o
+kvm-y += mmu.o
+kvm-y += vcpu.o
+kvm-y += vcpu_exit.o
+kvm-y += vcpu_fp.o
+kvm-y += vcpu_insn.o
+kvm-y += vcpu_switch.o
+kvm-y += vcpu_sbi.o
+kvm-$(CONFIG_RISCV_SBI_V01) += vcpu_sbi_v01.o
+kvm-y += vcpu_sbi_base.o
+kvm-y += vcpu_sbi_replace.o
+kvm-y += vcpu_sbi_hsm.o
+kvm-y += vcpu_timer.o
diff --git a/arch/riscv/kvm/main.c b/arch/riscv/kvm/main.c
new file mode 100644
index 000000000..62eedad7e
--- /dev/null
+++ b/arch/riscv/kvm/main.c
@@ -0,0 +1,129 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 Western Digital Corporation or its affiliates.
+ *
+ * Authors:
+ *     Anup Patel <anup.patel@wdc.com>
+ */
+
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/kvm_host.h>
+#include <asm/csr.h>
+#include <asm/hwcap.h>
+#include <asm/sbi.h>
+
+long kvm_arch_dev_ioctl(struct file *filp,
+			unsigned int ioctl, unsigned long arg)
+{
+	return -EINVAL;
+}
+
+int kvm_arch_check_processor_compat(void *opaque)
+{
+	return 0;
+}
+
+int kvm_arch_hardware_setup(void *opaque)
+{
+	return 0;
+}
+
+int kvm_arch_hardware_enable(void)
+{
+	unsigned long hideleg, hedeleg;
+
+	hedeleg = 0;
+	hedeleg |= (1UL << EXC_INST_MISALIGNED);
+	hedeleg |= (1UL << EXC_BREAKPOINT);
+	hedeleg |= (1UL << EXC_SYSCALL);
+	hedeleg |= (1UL << EXC_INST_PAGE_FAULT);
+	hedeleg |= (1UL << EXC_LOAD_PAGE_FAULT);
+	hedeleg |= (1UL << EXC_STORE_PAGE_FAULT);
+	csr_write(CSR_HEDELEG, hedeleg);
+
+	hideleg = 0;
+	hideleg |= (1UL << IRQ_VS_SOFT);
+	hideleg |= (1UL << IRQ_VS_TIMER);
+	hideleg |= (1UL << IRQ_VS_EXT);
+	csr_write(CSR_HIDELEG, hideleg);
+
+	csr_write(CSR_HCOUNTEREN, -1UL);
+
+	csr_write(CSR_HVIP, 0);
+
+	return 0;
+}
+
+void kvm_arch_hardware_disable(void)
+{
+	/*
+	 * After clearing the hideleg CSR, the host kernel will receive
+	 * spurious interrupts if hvip CSR has pending interrupts and the
+	 * corresponding enable bits in vsie CSR are asserted. To avoid it,
+	 * hvip CSR and vsie CSR must be cleared before clearing hideleg CSR.
+	 */
+	csr_write(CSR_VSIE, 0);
+	csr_write(CSR_HVIP, 0);
+	csr_write(CSR_HEDELEG, 0);
+	csr_write(CSR_HIDELEG, 0);
+}
+
+int kvm_arch_init(void *opaque)
+{
+	const char *str;
+
+	if (!riscv_isa_extension_available(NULL, h)) {
+		kvm_info("hypervisor extension not available\n");
+		return -ENODEV;
+	}
+
+	if (sbi_spec_is_0_1()) {
+		kvm_info("require SBI v0.2 or higher\n");
+		return -ENODEV;
+	}
+
+	if (!sbi_probe_extension(SBI_EXT_RFENCE)) {
+		kvm_info("require SBI RFENCE extension\n");
+		return -ENODEV;
+	}
+
+	kvm_riscv_gstage_mode_detect();
+
+	kvm_riscv_gstage_vmid_detect();
+
+	kvm_info("hypervisor extension available\n");
+
+	switch (kvm_riscv_gstage_mode()) {
+	case HGATP_MODE_SV32X4:
+		str = "Sv32x4";
+		break;
+	case HGATP_MODE_SV39X4:
+		str = "Sv39x4";
+		break;
+	case HGATP_MODE_SV48X4:
+		str = "Sv48x4";
+		break;
+	case HGATP_MODE_SV57X4:
+		str = "Sv57x4";
+		break;
+	default:
+		return -ENODEV;
+	}
+	kvm_info("using %s G-stage page table format\n", str);
+
+	kvm_info("VMID %ld bits available\n", kvm_riscv_gstage_vmid_bits());
+
+	return 0;
+}
+
+void kvm_arch_exit(void)
+{
+}
+
+static int __init riscv_kvm_init(void)
+{
+	return kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
+}
+module_init(riscv_kvm_init);
diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c
new file mode 100644
index 000000000..e47aeb6f0
--- /dev/null
+++ b/arch/riscv/kvm/mmu.c
@@ -0,0 +1,802 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 Western Digital Corporation or its affiliates.
+ *
+ * Authors:
+ *     Anup Patel <anup.patel@wdc.com>
+ */
+
+#include <linux/bitops.h>
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/hugetlb.h>
+#include <linux/module.h>
+#include <linux/uaccess.h>
+#include <linux/vmalloc.h>
+#include <linux/kvm_host.h>
+#include <linux/sched/signal.h>
+#include <asm/csr.h>
+#include <asm/page.h>
+#include <asm/pgtable.h>
+
+#ifdef CONFIG_64BIT
+static unsigned long gstage_mode = (HGATP_MODE_SV39X4 << HGATP_MODE_SHIFT);
+static unsigned long gstage_pgd_levels = 3;
+#define gstage_index_bits	9
+#else
+static unsigned long gstage_mode = (HGATP_MODE_SV32X4 << HGATP_MODE_SHIFT);
+static unsigned long gstage_pgd_levels = 2;
+#define gstage_index_bits	10
+#endif
+
+#define gstage_pgd_xbits	2
+#define gstage_pgd_size	(1UL << (HGATP_PAGE_SHIFT + gstage_pgd_xbits))
+#define gstage_gpa_bits	(HGATP_PAGE_SHIFT + \
+			 (gstage_pgd_levels * gstage_index_bits) + \
+			 gstage_pgd_xbits)
+#define gstage_gpa_size	((gpa_t)(1ULL << gstage_gpa_bits))
+
+#define gstage_pte_leaf(__ptep)	\
+	(pte_val(*(__ptep)) & (_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC))
+
+static inline unsigned long gstage_pte_index(gpa_t addr, u32 level)
+{
+	unsigned long mask;
+	unsigned long shift = HGATP_PAGE_SHIFT + (gstage_index_bits * level);
+
+	if (level == (gstage_pgd_levels - 1))
+		mask = (PTRS_PER_PTE * (1UL << gstage_pgd_xbits)) - 1;
+	else
+		mask = PTRS_PER_PTE - 1;
+
+	return (addr >> shift) & mask;
+}
+
+static inline unsigned long gstage_pte_page_vaddr(pte_t pte)
+{
+	return (unsigned long)pfn_to_virt(__page_val_to_pfn(pte_val(pte)));
+}
+
+static int gstage_page_size_to_level(unsigned long page_size, u32 *out_level)
+{
+	u32 i;
+	unsigned long psz = 1UL << 12;
+
+	for (i = 0; i < gstage_pgd_levels; i++) {
+		if (page_size == (psz << (i * gstage_index_bits))) {
+			*out_level = i;
+			return 0;
+		}
+	}
+
+	return -EINVAL;
+}
+
+static int gstage_level_to_page_order(u32 level, unsigned long *out_pgorder)
+{
+	if (gstage_pgd_levels < level)
+		return -EINVAL;
+
+	*out_pgorder = 12 + (level * gstage_index_bits);
+	return 0;
+}
+
+static int gstage_level_to_page_size(u32 level, unsigned long *out_pgsize)
+{
+	int rc;
+	unsigned long page_order = PAGE_SHIFT;
+
+	rc = gstage_level_to_page_order(level, &page_order);
+	if (rc)
+		return rc;
+
+	*out_pgsize = BIT(page_order);
+	return 0;
+}
+
+static bool gstage_get_leaf_entry(struct kvm *kvm, gpa_t addr,
+				  pte_t **ptepp, u32 *ptep_level)
+{
+	pte_t *ptep;
+	u32 current_level = gstage_pgd_levels - 1;
+
+	*ptep_level = current_level;
+	ptep = (pte_t *)kvm->arch.pgd;
+	ptep = &ptep[gstage_pte_index(addr, current_level)];
+	while (ptep && pte_val(*ptep)) {
+		if (gstage_pte_leaf(ptep)) {
+			*ptep_level = current_level;
+			*ptepp = ptep;
+			return true;
+		}
+
+		if (current_level) {
+			current_level--;
+			*ptep_level = current_level;
+			ptep = (pte_t *)gstage_pte_page_vaddr(*ptep);
+			ptep = &ptep[gstage_pte_index(addr, current_level)];
+		} else {
+			ptep = NULL;
+		}
+	}
+
+	return false;
+}
+
+static void gstage_remote_tlb_flush(struct kvm *kvm, u32 level, gpa_t addr)
+{
+	unsigned long order = PAGE_SHIFT;
+
+	if (gstage_level_to_page_order(level, &order))
+		return;
+	addr &= ~(BIT(order) - 1);
+
+	kvm_riscv_hfence_gvma_vmid_gpa(kvm, -1UL, 0, addr, BIT(order), order);
+}
+
+static int gstage_set_pte(struct kvm *kvm, u32 level,
+			   struct kvm_mmu_memory_cache *pcache,
+			   gpa_t addr, const pte_t *new_pte)
+{
+	u32 current_level = gstage_pgd_levels - 1;
+	pte_t *next_ptep = (pte_t *)kvm->arch.pgd;
+	pte_t *ptep = &next_ptep[gstage_pte_index(addr, current_level)];
+
+	if (current_level < level)
+		return -EINVAL;
+
+	while (current_level != level) {
+		if (gstage_pte_leaf(ptep))
+			return -EEXIST;
+
+		if (!pte_val(*ptep)) {
+			if (!pcache)
+				return -ENOMEM;
+			next_ptep = kvm_mmu_memory_cache_alloc(pcache);
+			if (!next_ptep)
+				return -ENOMEM;
+			*ptep = pfn_pte(PFN_DOWN(__pa(next_ptep)),
+					__pgprot(_PAGE_TABLE));
+		} else {
+			if (gstage_pte_leaf(ptep))
+				return -EEXIST;
+			next_ptep = (pte_t *)gstage_pte_page_vaddr(*ptep);
+		}
+
+		current_level--;
+		ptep = &next_ptep[gstage_pte_index(addr, current_level)];
+	}
+
+	*ptep = *new_pte;
+	if (gstage_pte_leaf(ptep))
+		gstage_remote_tlb_flush(kvm, current_level, addr);
+
+	return 0;
+}
+
+static int gstage_map_page(struct kvm *kvm,
+			   struct kvm_mmu_memory_cache *pcache,
+			   gpa_t gpa, phys_addr_t hpa,
+			   unsigned long page_size,
+			   bool page_rdonly, bool page_exec)
+{
+	int ret;
+	u32 level = 0;
+	pte_t new_pte;
+	pgprot_t prot;
+
+	ret = gstage_page_size_to_level(page_size, &level);
+	if (ret)
+		return ret;
+
+	/*
+	 * A RISC-V implementation can choose to either:
+	 * 1) Update 'A' and 'D' PTE bits in hardware
+	 * 2) Generate page fault when 'A' and/or 'D' bits are not set
+	 *    PTE so that software can update these bits.
+	 *
+	 * We support both options mentioned above. To achieve this, we
+	 * always set 'A' and 'D' PTE bits at time of creating G-stage
+	 * mapping. To support KVM dirty page logging with both options
+	 * mentioned above, we will write-protect G-stage PTEs to track
+	 * dirty pages.
+	 */
+
+	if (page_exec) {
+		if (page_rdonly)
+			prot = PAGE_READ_EXEC;
+		else
+			prot = PAGE_WRITE_EXEC;
+	} else {
+		if (page_rdonly)
+			prot = PAGE_READ;
+		else
+			prot = PAGE_WRITE;
+	}
+	new_pte = pfn_pte(PFN_DOWN(hpa), prot);
+	new_pte = pte_mkdirty(new_pte);
+
+	return gstage_set_pte(kvm, level, pcache, gpa, &new_pte);
+}
+
+enum gstage_op {
+	GSTAGE_OP_NOP = 0,	/* Nothing */
+	GSTAGE_OP_CLEAR,	/* Clear/Unmap */
+	GSTAGE_OP_WP,		/* Write-protect */
+};
+
+static void gstage_op_pte(struct kvm *kvm, gpa_t addr,
+			  pte_t *ptep, u32 ptep_level, enum gstage_op op)
+{
+	int i, ret;
+	pte_t *next_ptep;
+	u32 next_ptep_level;
+	unsigned long next_page_size, page_size;
+
+	ret = gstage_level_to_page_size(ptep_level, &page_size);
+	if (ret)
+		return;
+
+	BUG_ON(addr & (page_size - 1));
+
+	if (!pte_val(*ptep))
+		return;
+
+	if (ptep_level && !gstage_pte_leaf(ptep)) {
+		next_ptep = (pte_t *)gstage_pte_page_vaddr(*ptep);
+		next_ptep_level = ptep_level - 1;
+		ret = gstage_level_to_page_size(next_ptep_level,
+						&next_page_size);
+		if (ret)
+			return;
+
+		if (op == GSTAGE_OP_CLEAR)
+			set_pte(ptep, __pte(0));
+		for (i = 0; i < PTRS_PER_PTE; i++)
+			gstage_op_pte(kvm, addr + i * next_page_size,
+					&next_ptep[i], next_ptep_level, op);
+		if (op == GSTAGE_OP_CLEAR)
+			put_page(virt_to_page(next_ptep));
+	} else {
+		if (op == GSTAGE_OP_CLEAR)
+			set_pte(ptep, __pte(0));
+		else if (op == GSTAGE_OP_WP)
+			set_pte(ptep, __pte(pte_val(*ptep) & ~_PAGE_WRITE));
+		gstage_remote_tlb_flush(kvm, ptep_level, addr);
+	}
+}
+
+static void gstage_unmap_range(struct kvm *kvm, gpa_t start,
+			       gpa_t size, bool may_block)
+{
+	int ret;
+	pte_t *ptep;
+	u32 ptep_level;
+	bool found_leaf;
+	unsigned long page_size;
+	gpa_t addr = start, end = start + size;
+
+	while (addr < end) {
+		found_leaf = gstage_get_leaf_entry(kvm, addr,
+						   &ptep, &ptep_level);
+		ret = gstage_level_to_page_size(ptep_level, &page_size);
+		if (ret)
+			break;
+
+		if (!found_leaf)
+			goto next;
+
+		if (!(addr & (page_size - 1)) && ((end - addr) >= page_size))
+			gstage_op_pte(kvm, addr, ptep,
+				      ptep_level, GSTAGE_OP_CLEAR);
+
+next:
+		addr += page_size;
+
+		/*
+		 * If the range is too large, release the kvm->mmu_lock
+		 * to prevent starvation and lockup detector warnings.
+		 */
+		if (may_block && addr < end)
+			cond_resched_lock(&kvm->mmu_lock);
+	}
+}
+
+static void gstage_wp_range(struct kvm *kvm, gpa_t start, gpa_t end)
+{
+	int ret;
+	pte_t *ptep;
+	u32 ptep_level;
+	bool found_leaf;
+	gpa_t addr = start;
+	unsigned long page_size;
+
+	while (addr < end) {
+		found_leaf = gstage_get_leaf_entry(kvm, addr,
+						   &ptep, &ptep_level);
+		ret = gstage_level_to_page_size(ptep_level, &page_size);
+		if (ret)
+			break;
+
+		if (!found_leaf)
+			goto next;
+
+		if (!(addr & (page_size - 1)) && ((end - addr) >= page_size))
+			gstage_op_pte(kvm, addr, ptep,
+				      ptep_level, GSTAGE_OP_WP);
+
+next:
+		addr += page_size;
+	}
+}
+
+static void gstage_wp_memory_region(struct kvm *kvm, int slot)
+{
+	struct kvm_memslots *slots = kvm_memslots(kvm);
+	struct kvm_memory_slot *memslot = id_to_memslot(slots, slot);
+	phys_addr_t start = memslot->base_gfn << PAGE_SHIFT;
+	phys_addr_t end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT;
+
+	spin_lock(&kvm->mmu_lock);
+	gstage_wp_range(kvm, start, end);
+	spin_unlock(&kvm->mmu_lock);
+	kvm_flush_remote_tlbs(kvm);
+}
+
+int kvm_riscv_gstage_ioremap(struct kvm *kvm, gpa_t gpa,
+			     phys_addr_t hpa, unsigned long size,
+			     bool writable, bool in_atomic)
+{
+	pte_t pte;
+	int ret = 0;
+	unsigned long pfn;
+	phys_addr_t addr, end;
+	struct kvm_mmu_memory_cache pcache = {
+		.gfp_custom = (in_atomic) ? GFP_ATOMIC | __GFP_ACCOUNT : 0,
+		.gfp_zero = __GFP_ZERO,
+	};
+
+	end = (gpa + size + PAGE_SIZE - 1) & PAGE_MASK;
+	pfn = __phys_to_pfn(hpa);
+
+	for (addr = gpa; addr < end; addr += PAGE_SIZE) {
+		pte = pfn_pte(pfn, PAGE_KERNEL_IO);
+
+		if (!writable)
+			pte = pte_wrprotect(pte);
+
+		ret = kvm_mmu_topup_memory_cache(&pcache, gstage_pgd_levels);
+		if (ret)
+			goto out;
+
+		spin_lock(&kvm->mmu_lock);
+		ret = gstage_set_pte(kvm, 0, &pcache, addr, &pte);
+		spin_unlock(&kvm->mmu_lock);
+		if (ret)
+			goto out;
+
+		pfn++;
+	}
+
+out:
+	kvm_mmu_free_memory_cache(&pcache);
+	return ret;
+}
+
+void kvm_riscv_gstage_iounmap(struct kvm *kvm, gpa_t gpa, unsigned long size)
+{
+	spin_lock(&kvm->mmu_lock);
+	gstage_unmap_range(kvm, gpa, size, false);
+	spin_unlock(&kvm->mmu_lock);
+}
+
+void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
+					     struct kvm_memory_slot *slot,
+					     gfn_t gfn_offset,
+					     unsigned long mask)
+{
+	phys_addr_t base_gfn = slot->base_gfn + gfn_offset;
+	phys_addr_t start = (base_gfn +  __ffs(mask)) << PAGE_SHIFT;
+	phys_addr_t end = (base_gfn + __fls(mask) + 1) << PAGE_SHIFT;
+
+	gstage_wp_range(kvm, start, end);
+}
+
+void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot)
+{
+}
+
+void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm,
+					const struct kvm_memory_slot *memslot)
+{
+	kvm_flush_remote_tlbs(kvm);
+}
+
+void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free)
+{
+}
+
+void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen)
+{
+}
+
+void kvm_arch_flush_shadow_all(struct kvm *kvm)
+{
+	kvm_riscv_gstage_free_pgd(kvm);
+}
+
+void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
+				   struct kvm_memory_slot *slot)
+{
+	gpa_t gpa = slot->base_gfn << PAGE_SHIFT;
+	phys_addr_t size = slot->npages << PAGE_SHIFT;
+
+	spin_lock(&kvm->mmu_lock);
+	gstage_unmap_range(kvm, gpa, size, false);
+	spin_unlock(&kvm->mmu_lock);
+}
+
+void kvm_arch_commit_memory_region(struct kvm *kvm,
+				struct kvm_memory_slot *old,
+				const struct kvm_memory_slot *new,
+				enum kvm_mr_change change)
+{
+	/*
+	 * At this point memslot has been committed and there is an
+	 * allocated dirty_bitmap[], dirty pages will be tracked while
+	 * the memory slot is write protected.
+	 */
+	if (change != KVM_MR_DELETE && new->flags & KVM_MEM_LOG_DIRTY_PAGES)
+		gstage_wp_memory_region(kvm, new->id);
+}
+
+int kvm_arch_prepare_memory_region(struct kvm *kvm,
+				const struct kvm_memory_slot *old,
+				struct kvm_memory_slot *new,
+				enum kvm_mr_change change)
+{
+	hva_t hva, reg_end, size;
+	gpa_t base_gpa;
+	bool writable;
+	int ret = 0;
+
+	if (change != KVM_MR_CREATE && change != KVM_MR_MOVE &&
+			change != KVM_MR_FLAGS_ONLY)
+		return 0;
+
+	/*
+	 * Prevent userspace from creating a memory region outside of the GPA
+	 * space addressable by the KVM guest GPA space.
+	 */
+	if ((new->base_gfn + new->npages) >=
+	    (gstage_gpa_size >> PAGE_SHIFT))
+		return -EFAULT;
+
+	hva = new->userspace_addr;
+	size = new->npages << PAGE_SHIFT;
+	reg_end = hva + size;
+	base_gpa = new->base_gfn << PAGE_SHIFT;
+	writable = !(new->flags & KVM_MEM_READONLY);
+
+	mmap_read_lock(current->mm);
+
+	/*
+	 * A memory region could potentially cover multiple VMAs, and
+	 * any holes between them, so iterate over all of them to find
+	 * out if we can map any of them right now.
+	 *
+	 *     +--------------------------------------------+
+	 * +---------------+----------------+   +----------------+
+	 * |   : VMA 1     |      VMA 2     |   |    VMA 3  :    |
+	 * +---------------+----------------+   +----------------+
+	 *     |               memory region                |
+	 *     +--------------------------------------------+
+	 */
+	do {
+		struct vm_area_struct *vma = find_vma(current->mm, hva);
+		hva_t vm_start, vm_end;
+
+		if (!vma || vma->vm_start >= reg_end)
+			break;
+
+		/*
+		 * Mapping a read-only VMA is only allowed if the
+		 * memory region is configured as read-only.
+		 */
+		if (writable && !(vma->vm_flags & VM_WRITE)) {
+			ret = -EPERM;
+			break;
+		}
+
+		/* Take the intersection of this VMA with the memory region */
+		vm_start = max(hva, vma->vm_start);
+		vm_end = min(reg_end, vma->vm_end);
+
+		if (vma->vm_flags & VM_PFNMAP) {
+			gpa_t gpa = base_gpa + (vm_start - hva);
+			phys_addr_t pa;
+
+			pa = (phys_addr_t)vma->vm_pgoff << PAGE_SHIFT;
+			pa += vm_start - vma->vm_start;
+
+			/* IO region dirty page logging not allowed */
+			if (new->flags & KVM_MEM_LOG_DIRTY_PAGES) {
+				ret = -EINVAL;
+				goto out;
+			}
+
+			ret = kvm_riscv_gstage_ioremap(kvm, gpa, pa,
+						       vm_end - vm_start,
+						       writable, false);
+			if (ret)
+				break;
+		}
+		hva = vm_end;
+	} while (hva < reg_end);
+
+	if (change == KVM_MR_FLAGS_ONLY)
+		goto out;
+
+	spin_lock(&kvm->mmu_lock);
+	if (ret)
+		gstage_unmap_range(kvm, base_gpa, size, false);
+	spin_unlock(&kvm->mmu_lock);
+
+out:
+	mmap_read_unlock(current->mm);
+	return ret;
+}
+
+bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
+{
+	if (!kvm->arch.pgd)
+		return false;
+
+	gstage_unmap_range(kvm, range->start << PAGE_SHIFT,
+			   (range->end - range->start) << PAGE_SHIFT,
+			   range->may_block);
+	return false;
+}
+
+bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
+{
+	int ret;
+	kvm_pfn_t pfn = pte_pfn(range->pte);
+
+	if (!kvm->arch.pgd)
+		return false;
+
+	WARN_ON(range->end - range->start != 1);
+
+	ret = gstage_map_page(kvm, NULL, range->start << PAGE_SHIFT,
+			      __pfn_to_phys(pfn), PAGE_SIZE, true, true);
+	if (ret) {
+		kvm_debug("Failed to map G-stage page (error %d)\n", ret);
+		return true;
+	}
+
+	return false;
+}
+
+bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
+{
+	pte_t *ptep;
+	u32 ptep_level = 0;
+	u64 size = (range->end - range->start) << PAGE_SHIFT;
+
+	if (!kvm->arch.pgd)
+		return false;
+
+	WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PGDIR_SIZE);
+
+	if (!gstage_get_leaf_entry(kvm, range->start << PAGE_SHIFT,
+				   &ptep, &ptep_level))
+		return false;
+
+	return ptep_test_and_clear_young(NULL, 0, ptep);
+}
+
+bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
+{
+	pte_t *ptep;
+	u32 ptep_level = 0;
+	u64 size = (range->end - range->start) << PAGE_SHIFT;
+
+	if (!kvm->arch.pgd)
+		return false;
+
+	WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PGDIR_SIZE);
+
+	if (!gstage_get_leaf_entry(kvm, range->start << PAGE_SHIFT,
+				   &ptep, &ptep_level))
+		return false;
+
+	return pte_young(*ptep);
+}
+
+int kvm_riscv_gstage_map(struct kvm_vcpu *vcpu,
+			 struct kvm_memory_slot *memslot,
+			 gpa_t gpa, unsigned long hva, bool is_write)
+{
+	int ret;
+	kvm_pfn_t hfn;
+	bool writable;
+	short vma_pageshift;
+	gfn_t gfn = gpa >> PAGE_SHIFT;
+	struct vm_area_struct *vma;
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_mmu_memory_cache *pcache = &vcpu->arch.mmu_page_cache;
+	bool logging = (memslot->dirty_bitmap &&
+			!(memslot->flags & KVM_MEM_READONLY)) ? true : false;
+	unsigned long vma_pagesize, mmu_seq;
+
+	/* We need minimum second+third level pages */
+	ret = kvm_mmu_topup_memory_cache(pcache, gstage_pgd_levels);
+	if (ret) {
+		kvm_err("Failed to topup G-stage cache\n");
+		return ret;
+	}
+
+	mmap_read_lock(current->mm);
+
+	vma = find_vma_intersection(current->mm, hva, hva + 1);
+	if (unlikely(!vma)) {
+		kvm_err("Failed to find VMA for hva 0x%lx\n", hva);
+		mmap_read_unlock(current->mm);
+		return -EFAULT;
+	}
+
+	if (is_vm_hugetlb_page(vma))
+		vma_pageshift = huge_page_shift(hstate_vma(vma));
+	else
+		vma_pageshift = PAGE_SHIFT;
+	vma_pagesize = 1ULL << vma_pageshift;
+	if (logging || (vma->vm_flags & VM_PFNMAP))
+		vma_pagesize = PAGE_SIZE;
+
+	if (vma_pagesize == PMD_SIZE || vma_pagesize == PGDIR_SIZE)
+		gfn = (gpa & huge_page_mask(hstate_vma(vma))) >> PAGE_SHIFT;
+
+	/*
+	 * Read mmu_invalidate_seq so that KVM can detect if the results of
+	 * vma_lookup() or gfn_to_pfn_prot() become stale priort to acquiring
+	 * kvm->mmu_lock.
+	 *
+	 * Rely on mmap_read_unlock() for an implicit smp_rmb(), which pairs
+	 * with the smp_wmb() in kvm_mmu_invalidate_end().
+	 */
+	mmu_seq = kvm->mmu_invalidate_seq;
+	mmap_read_unlock(current->mm);
+
+	if (vma_pagesize != PGDIR_SIZE &&
+	    vma_pagesize != PMD_SIZE &&
+	    vma_pagesize != PAGE_SIZE) {
+		kvm_err("Invalid VMA page size 0x%lx\n", vma_pagesize);
+		return -EFAULT;
+	}
+
+	hfn = gfn_to_pfn_prot(kvm, gfn, is_write, &writable);
+	if (hfn == KVM_PFN_ERR_HWPOISON) {
+		send_sig_mceerr(BUS_MCEERR_AR, (void __user *)hva,
+				vma_pageshift, current);
+		return 0;
+	}
+	if (is_error_noslot_pfn(hfn))
+		return -EFAULT;
+
+	/*
+	 * If logging is active then we allow writable pages only
+	 * for write faults.
+	 */
+	if (logging && !is_write)
+		writable = false;
+
+	spin_lock(&kvm->mmu_lock);
+
+	if (mmu_invalidate_retry(kvm, mmu_seq))
+		goto out_unlock;
+
+	if (writable) {
+		kvm_set_pfn_dirty(hfn);
+		mark_page_dirty(kvm, gfn);
+		ret = gstage_map_page(kvm, pcache, gpa, hfn << PAGE_SHIFT,
+				      vma_pagesize, false, true);
+	} else {
+		ret = gstage_map_page(kvm, pcache, gpa, hfn << PAGE_SHIFT,
+				      vma_pagesize, true, true);
+	}
+
+	if (ret)
+		kvm_err("Failed to map in G-stage\n");
+
+out_unlock:
+	spin_unlock(&kvm->mmu_lock);
+	kvm_set_pfn_accessed(hfn);
+	kvm_release_pfn_clean(hfn);
+	return ret;
+}
+
+int kvm_riscv_gstage_alloc_pgd(struct kvm *kvm)
+{
+	struct page *pgd_page;
+
+	if (kvm->arch.pgd != NULL) {
+		kvm_err("kvm_arch already initialized?\n");
+		return -EINVAL;
+	}
+
+	pgd_page = alloc_pages(GFP_KERNEL | __GFP_ZERO,
+				get_order(gstage_pgd_size));
+	if (!pgd_page)
+		return -ENOMEM;
+	kvm->arch.pgd = page_to_virt(pgd_page);
+	kvm->arch.pgd_phys = page_to_phys(pgd_page);
+
+	return 0;
+}
+
+void kvm_riscv_gstage_free_pgd(struct kvm *kvm)
+{
+	void *pgd = NULL;
+
+	spin_lock(&kvm->mmu_lock);
+	if (kvm->arch.pgd) {
+		gstage_unmap_range(kvm, 0UL, gstage_gpa_size, false);
+		pgd = READ_ONCE(kvm->arch.pgd);
+		kvm->arch.pgd = NULL;
+		kvm->arch.pgd_phys = 0;
+	}
+	spin_unlock(&kvm->mmu_lock);
+
+	if (pgd)
+		free_pages((unsigned long)pgd, get_order(gstage_pgd_size));
+}
+
+void kvm_riscv_gstage_update_hgatp(struct kvm_vcpu *vcpu)
+{
+	unsigned long hgatp = gstage_mode;
+	struct kvm_arch *k = &vcpu->kvm->arch;
+
+	hgatp |= (READ_ONCE(k->vmid.vmid) << HGATP_VMID_SHIFT) &
+		 HGATP_VMID_MASK;
+	hgatp |= (k->pgd_phys >> PAGE_SHIFT) & HGATP_PPN;
+
+	csr_write(CSR_HGATP, hgatp);
+
+	if (!kvm_riscv_gstage_vmid_bits())
+		kvm_riscv_local_hfence_gvma_all();
+}
+
+void kvm_riscv_gstage_mode_detect(void)
+{
+#ifdef CONFIG_64BIT
+	/* Try Sv57x4 G-stage mode */
+	csr_write(CSR_HGATP, HGATP_MODE_SV57X4 << HGATP_MODE_SHIFT);
+	if ((csr_read(CSR_HGATP) >> HGATP_MODE_SHIFT) == HGATP_MODE_SV57X4) {
+		gstage_mode = (HGATP_MODE_SV57X4 << HGATP_MODE_SHIFT);
+		gstage_pgd_levels = 5;
+		goto skip_sv48x4_test;
+	}
+
+	/* Try Sv48x4 G-stage mode */
+	csr_write(CSR_HGATP, HGATP_MODE_SV48X4 << HGATP_MODE_SHIFT);
+	if ((csr_read(CSR_HGATP) >> HGATP_MODE_SHIFT) == HGATP_MODE_SV48X4) {
+		gstage_mode = (HGATP_MODE_SV48X4 << HGATP_MODE_SHIFT);
+		gstage_pgd_levels = 4;
+	}
+skip_sv48x4_test:
+
+	csr_write(CSR_HGATP, 0);
+	kvm_riscv_local_hfence_gvma_all();
+#endif
+}
+
+unsigned long kvm_riscv_gstage_mode(void)
+{
+	return gstage_mode >> HGATP_MODE_SHIFT;
+}
+
+int kvm_riscv_gstage_gpa_bits(void)
+{
+	return gstage_gpa_bits;
+}
diff --git a/arch/riscv/kvm/tlb.c b/arch/riscv/kvm/tlb.c
new file mode 100644
index 000000000..309d79b3e
--- /dev/null
+++ b/arch/riscv/kvm/tlb.c
@@ -0,0 +1,402 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2022 Ventana Micro Systems Inc.
+ */
+
+#include <linux/bitmap.h>
+#include <linux/cpumask.h>
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/smp.h>
+#include <linux/kvm_host.h>
+#include <asm/cacheflush.h>
+#include <asm/csr.h>
+#include <asm/hwcap.h>
+#include <asm/insn-def.h>
+
+#define has_svinval()	\
+	static_branch_unlikely(&riscv_isa_ext_keys[RISCV_ISA_EXT_KEY_SVINVAL])
+
+void kvm_riscv_local_hfence_gvma_vmid_gpa(unsigned long vmid,
+					  gpa_t gpa, gpa_t gpsz,
+					  unsigned long order)
+{
+	gpa_t pos;
+
+	if (PTRS_PER_PTE < (gpsz >> order)) {
+		kvm_riscv_local_hfence_gvma_vmid_all(vmid);
+		return;
+	}
+
+	if (has_svinval()) {
+		asm volatile (SFENCE_W_INVAL() ::: "memory");
+		for (pos = gpa; pos < (gpa + gpsz); pos += BIT(order))
+			asm volatile (HINVAL_GVMA(%0, %1)
+			: : "r" (pos >> 2), "r" (vmid) : "memory");
+		asm volatile (SFENCE_INVAL_IR() ::: "memory");
+	} else {
+		for (pos = gpa; pos < (gpa + gpsz); pos += BIT(order))
+			asm volatile (HFENCE_GVMA(%0, %1)
+			: : "r" (pos >> 2), "r" (vmid) : "memory");
+	}
+}
+
+void kvm_riscv_local_hfence_gvma_vmid_all(unsigned long vmid)
+{
+	asm volatile(HFENCE_GVMA(zero, %0) : : "r" (vmid) : "memory");
+}
+
+void kvm_riscv_local_hfence_gvma_gpa(gpa_t gpa, gpa_t gpsz,
+				     unsigned long order)
+{
+	gpa_t pos;
+
+	if (PTRS_PER_PTE < (gpsz >> order)) {
+		kvm_riscv_local_hfence_gvma_all();
+		return;
+	}
+
+	if (has_svinval()) {
+		asm volatile (SFENCE_W_INVAL() ::: "memory");
+		for (pos = gpa; pos < (gpa + gpsz); pos += BIT(order))
+			asm volatile(HINVAL_GVMA(%0, zero)
+			: : "r" (pos >> 2) : "memory");
+		asm volatile (SFENCE_INVAL_IR() ::: "memory");
+	} else {
+		for (pos = gpa; pos < (gpa + gpsz); pos += BIT(order))
+			asm volatile(HFENCE_GVMA(%0, zero)
+			: : "r" (pos >> 2) : "memory");
+	}
+}
+
+void kvm_riscv_local_hfence_gvma_all(void)
+{
+	asm volatile(HFENCE_GVMA(zero, zero) : : : "memory");
+}
+
+void kvm_riscv_local_hfence_vvma_asid_gva(unsigned long vmid,
+					  unsigned long asid,
+					  unsigned long gva,
+					  unsigned long gvsz,
+					  unsigned long order)
+{
+	unsigned long pos, hgatp;
+
+	if (PTRS_PER_PTE < (gvsz >> order)) {
+		kvm_riscv_local_hfence_vvma_asid_all(vmid, asid);
+		return;
+	}
+
+	hgatp = csr_swap(CSR_HGATP, vmid << HGATP_VMID_SHIFT);
+
+	if (has_svinval()) {
+		asm volatile (SFENCE_W_INVAL() ::: "memory");
+		for (pos = gva; pos < (gva + gvsz); pos += BIT(order))
+			asm volatile(HINVAL_VVMA(%0, %1)
+			: : "r" (pos), "r" (asid) : "memory");
+		asm volatile (SFENCE_INVAL_IR() ::: "memory");
+	} else {
+		for (pos = gva; pos < (gva + gvsz); pos += BIT(order))
+			asm volatile(HFENCE_VVMA(%0, %1)
+			: : "r" (pos), "r" (asid) : "memory");
+	}
+
+	csr_write(CSR_HGATP, hgatp);
+}
+
+void kvm_riscv_local_hfence_vvma_asid_all(unsigned long vmid,
+					  unsigned long asid)
+{
+	unsigned long hgatp;
+
+	hgatp = csr_swap(CSR_HGATP, vmid << HGATP_VMID_SHIFT);
+
+	asm volatile(HFENCE_VVMA(zero, %0) : : "r" (asid) : "memory");
+
+	csr_write(CSR_HGATP, hgatp);
+}
+
+void kvm_riscv_local_hfence_vvma_gva(unsigned long vmid,
+				     unsigned long gva, unsigned long gvsz,
+				     unsigned long order)
+{
+	unsigned long pos, hgatp;
+
+	if (PTRS_PER_PTE < (gvsz >> order)) {
+		kvm_riscv_local_hfence_vvma_all(vmid);
+		return;
+	}
+
+	hgatp = csr_swap(CSR_HGATP, vmid << HGATP_VMID_SHIFT);
+
+	if (has_svinval()) {
+		asm volatile (SFENCE_W_INVAL() ::: "memory");
+		for (pos = gva; pos < (gva + gvsz); pos += BIT(order))
+			asm volatile(HINVAL_VVMA(%0, zero)
+			: : "r" (pos) : "memory");
+		asm volatile (SFENCE_INVAL_IR() ::: "memory");
+	} else {
+		for (pos = gva; pos < (gva + gvsz); pos += BIT(order))
+			asm volatile(HFENCE_VVMA(%0, zero)
+			: : "r" (pos) : "memory");
+	}
+
+	csr_write(CSR_HGATP, hgatp);
+}
+
+void kvm_riscv_local_hfence_vvma_all(unsigned long vmid)
+{
+	unsigned long hgatp;
+
+	hgatp = csr_swap(CSR_HGATP, vmid << HGATP_VMID_SHIFT);
+
+	asm volatile(HFENCE_VVMA(zero, zero) : : : "memory");
+
+	csr_write(CSR_HGATP, hgatp);
+}
+
+void kvm_riscv_local_tlb_sanitize(struct kvm_vcpu *vcpu)
+{
+	unsigned long vmid;
+
+	if (!kvm_riscv_gstage_vmid_bits() ||
+	    vcpu->arch.last_exit_cpu == vcpu->cpu)
+		return;
+
+	/*
+	 * On RISC-V platforms with hardware VMID support, we share same
+	 * VMID for all VCPUs of a particular Guest/VM. This means we might
+	 * have stale G-stage TLB entries on the current Host CPU due to
+	 * some other VCPU of the same Guest which ran previously on the
+	 * current Host CPU.
+	 *
+	 * To cleanup stale TLB entries, we simply flush all G-stage TLB
+	 * entries by VMID whenever underlying Host CPU changes for a VCPU.
+	 */
+
+	vmid = READ_ONCE(vcpu->kvm->arch.vmid.vmid);
+	kvm_riscv_local_hfence_gvma_vmid_all(vmid);
+}
+
+void kvm_riscv_fence_i_process(struct kvm_vcpu *vcpu)
+{
+	local_flush_icache_all();
+}
+
+void kvm_riscv_hfence_gvma_vmid_all_process(struct kvm_vcpu *vcpu)
+{
+	struct kvm_vmid *vmid;
+
+	vmid = &vcpu->kvm->arch.vmid;
+	kvm_riscv_local_hfence_gvma_vmid_all(READ_ONCE(vmid->vmid));
+}
+
+void kvm_riscv_hfence_vvma_all_process(struct kvm_vcpu *vcpu)
+{
+	struct kvm_vmid *vmid;
+
+	vmid = &vcpu->kvm->arch.vmid;
+	kvm_riscv_local_hfence_vvma_all(READ_ONCE(vmid->vmid));
+}
+
+static bool vcpu_hfence_dequeue(struct kvm_vcpu *vcpu,
+				struct kvm_riscv_hfence *out_data)
+{
+	bool ret = false;
+	struct kvm_vcpu_arch *varch = &vcpu->arch;
+
+	spin_lock(&varch->hfence_lock);
+
+	if (varch->hfence_queue[varch->hfence_head].type) {
+		memcpy(out_data, &varch->hfence_queue[varch->hfence_head],
+		       sizeof(*out_data));
+		varch->hfence_queue[varch->hfence_head].type = 0;
+
+		varch->hfence_head++;
+		if (varch->hfence_head == KVM_RISCV_VCPU_MAX_HFENCE)
+			varch->hfence_head = 0;
+
+		ret = true;
+	}
+
+	spin_unlock(&varch->hfence_lock);
+
+	return ret;
+}
+
+static bool vcpu_hfence_enqueue(struct kvm_vcpu *vcpu,
+				const struct kvm_riscv_hfence *data)
+{
+	bool ret = false;
+	struct kvm_vcpu_arch *varch = &vcpu->arch;
+
+	spin_lock(&varch->hfence_lock);
+
+	if (!varch->hfence_queue[varch->hfence_tail].type) {
+		memcpy(&varch->hfence_queue[varch->hfence_tail],
+		       data, sizeof(*data));
+
+		varch->hfence_tail++;
+		if (varch->hfence_tail == KVM_RISCV_VCPU_MAX_HFENCE)
+			varch->hfence_tail = 0;
+
+		ret = true;
+	}
+
+	spin_unlock(&varch->hfence_lock);
+
+	return ret;
+}
+
+void kvm_riscv_hfence_process(struct kvm_vcpu *vcpu)
+{
+	struct kvm_riscv_hfence d = { 0 };
+	struct kvm_vmid *v = &vcpu->kvm->arch.vmid;
+
+	while (vcpu_hfence_dequeue(vcpu, &d)) {
+		switch (d.type) {
+		case KVM_RISCV_HFENCE_UNKNOWN:
+			break;
+		case KVM_RISCV_HFENCE_GVMA_VMID_GPA:
+			kvm_riscv_local_hfence_gvma_vmid_gpa(
+						READ_ONCE(v->vmid),
+						d.addr, d.size, d.order);
+			break;
+		case KVM_RISCV_HFENCE_VVMA_ASID_GVA:
+			kvm_riscv_local_hfence_vvma_asid_gva(
+						READ_ONCE(v->vmid), d.asid,
+						d.addr, d.size, d.order);
+			break;
+		case KVM_RISCV_HFENCE_VVMA_ASID_ALL:
+			kvm_riscv_local_hfence_vvma_asid_all(
+						READ_ONCE(v->vmid), d.asid);
+			break;
+		case KVM_RISCV_HFENCE_VVMA_GVA:
+			kvm_riscv_local_hfence_vvma_gva(
+						READ_ONCE(v->vmid),
+						d.addr, d.size, d.order);
+			break;
+		default:
+			break;
+		}
+	}
+}
+
+static void make_xfence_request(struct kvm *kvm,
+				unsigned long hbase, unsigned long hmask,
+				unsigned int req, unsigned int fallback_req,
+				const struct kvm_riscv_hfence *data)
+{
+	unsigned long i;
+	struct kvm_vcpu *vcpu;
+	unsigned int actual_req = req;
+	DECLARE_BITMAP(vcpu_mask, KVM_MAX_VCPUS);
+
+	bitmap_clear(vcpu_mask, 0, KVM_MAX_VCPUS);
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		if (hbase != -1UL) {
+			if (vcpu->vcpu_id < hbase)
+				continue;
+			if (!(hmask & (1UL << (vcpu->vcpu_id - hbase))))
+				continue;
+		}
+
+		bitmap_set(vcpu_mask, i, 1);
+
+		if (!data || !data->type)
+			continue;
+
+		/*
+		 * Enqueue hfence data to VCPU hfence queue. If we don't
+		 * have space in the VCPU hfence queue then fallback to
+		 * a more conservative hfence request.
+		 */
+		if (!vcpu_hfence_enqueue(vcpu, data))
+			actual_req = fallback_req;
+	}
+
+	kvm_make_vcpus_request_mask(kvm, actual_req, vcpu_mask);
+}
+
+void kvm_riscv_fence_i(struct kvm *kvm,
+		       unsigned long hbase, unsigned long hmask)
+{
+	make_xfence_request(kvm, hbase, hmask, KVM_REQ_FENCE_I,
+			    KVM_REQ_FENCE_I, NULL);
+}
+
+void kvm_riscv_hfence_gvma_vmid_gpa(struct kvm *kvm,
+				    unsigned long hbase, unsigned long hmask,
+				    gpa_t gpa, gpa_t gpsz,
+				    unsigned long order)
+{
+	struct kvm_riscv_hfence data;
+
+	data.type = KVM_RISCV_HFENCE_GVMA_VMID_GPA;
+	data.asid = 0;
+	data.addr = gpa;
+	data.size = gpsz;
+	data.order = order;
+	make_xfence_request(kvm, hbase, hmask, KVM_REQ_HFENCE,
+			    KVM_REQ_HFENCE_GVMA_VMID_ALL, &data);
+}
+
+void kvm_riscv_hfence_gvma_vmid_all(struct kvm *kvm,
+				    unsigned long hbase, unsigned long hmask)
+{
+	make_xfence_request(kvm, hbase, hmask, KVM_REQ_HFENCE_GVMA_VMID_ALL,
+			    KVM_REQ_HFENCE_GVMA_VMID_ALL, NULL);
+}
+
+void kvm_riscv_hfence_vvma_asid_gva(struct kvm *kvm,
+				    unsigned long hbase, unsigned long hmask,
+				    unsigned long gva, unsigned long gvsz,
+				    unsigned long order, unsigned long asid)
+{
+	struct kvm_riscv_hfence data;
+
+	data.type = KVM_RISCV_HFENCE_VVMA_ASID_GVA;
+	data.asid = asid;
+	data.addr = gva;
+	data.size = gvsz;
+	data.order = order;
+	make_xfence_request(kvm, hbase, hmask, KVM_REQ_HFENCE,
+			    KVM_REQ_HFENCE_VVMA_ALL, &data);
+}
+
+void kvm_riscv_hfence_vvma_asid_all(struct kvm *kvm,
+				    unsigned long hbase, unsigned long hmask,
+				    unsigned long asid)
+{
+	struct kvm_riscv_hfence data;
+
+	data.type = KVM_RISCV_HFENCE_VVMA_ASID_ALL;
+	data.asid = asid;
+	data.addr = data.size = data.order = 0;
+	make_xfence_request(kvm, hbase, hmask, KVM_REQ_HFENCE,
+			    KVM_REQ_HFENCE_VVMA_ALL, &data);
+}
+
+void kvm_riscv_hfence_vvma_gva(struct kvm *kvm,
+			       unsigned long hbase, unsigned long hmask,
+			       unsigned long gva, unsigned long gvsz,
+			       unsigned long order)
+{
+	struct kvm_riscv_hfence data;
+
+	data.type = KVM_RISCV_HFENCE_VVMA_GVA;
+	data.asid = 0;
+	data.addr = gva;
+	data.size = gvsz;
+	data.order = order;
+	make_xfence_request(kvm, hbase, hmask, KVM_REQ_HFENCE,
+			    KVM_REQ_HFENCE_VVMA_ALL, &data);
+}
+
+void kvm_riscv_hfence_vvma_all(struct kvm *kvm,
+			       unsigned long hbase, unsigned long hmask)
+{
+	make_xfence_request(kvm, hbase, hmask, KVM_REQ_HFENCE_VVMA_ALL,
+			    KVM_REQ_HFENCE_VVMA_ALL, NULL);
+}
diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c
new file mode 100644
index 000000000..5174ef54a
--- /dev/null
+++ b/arch/riscv/kvm/vcpu.c
@@ -0,0 +1,1091 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 Western Digital Corporation or its affiliates.
+ *
+ * Authors:
+ *     Anup Patel <anup.patel@wdc.com>
+ */
+
+#include <linux/bitops.h>
+#include <linux/entry-kvm.h>
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/kdebug.h>
+#include <linux/module.h>
+#include <linux/percpu.h>
+#include <linux/uaccess.h>
+#include <linux/vmalloc.h>
+#include <linux/sched/signal.h>
+#include <linux/fs.h>
+#include <linux/kvm_host.h>
+#include <asm/csr.h>
+#include <asm/cacheflush.h>
+#include <asm/hwcap.h>
+
+const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = {
+	KVM_GENERIC_VCPU_STATS(),
+	STATS_DESC_COUNTER(VCPU, ecall_exit_stat),
+	STATS_DESC_COUNTER(VCPU, wfi_exit_stat),
+	STATS_DESC_COUNTER(VCPU, mmio_exit_user),
+	STATS_DESC_COUNTER(VCPU, mmio_exit_kernel),
+	STATS_DESC_COUNTER(VCPU, csr_exit_user),
+	STATS_DESC_COUNTER(VCPU, csr_exit_kernel),
+	STATS_DESC_COUNTER(VCPU, signal_exits),
+	STATS_DESC_COUNTER(VCPU, exits)
+};
+
+const struct kvm_stats_header kvm_vcpu_stats_header = {
+	.name_size = KVM_STATS_NAME_SIZE,
+	.num_desc = ARRAY_SIZE(kvm_vcpu_stats_desc),
+	.id_offset = sizeof(struct kvm_stats_header),
+	.desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE,
+	.data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE +
+		       sizeof(kvm_vcpu_stats_desc),
+};
+
+#define KVM_RISCV_BASE_ISA_MASK		GENMASK(25, 0)
+
+#define KVM_ISA_EXT_ARR(ext)		[KVM_RISCV_ISA_EXT_##ext] = RISCV_ISA_EXT_##ext
+
+/* Mapping between KVM ISA Extension ID & Host ISA extension ID */
+static const unsigned long kvm_isa_ext_arr[] = {
+	[KVM_RISCV_ISA_EXT_A] = RISCV_ISA_EXT_a,
+	[KVM_RISCV_ISA_EXT_C] = RISCV_ISA_EXT_c,
+	[KVM_RISCV_ISA_EXT_D] = RISCV_ISA_EXT_d,
+	[KVM_RISCV_ISA_EXT_F] = RISCV_ISA_EXT_f,
+	[KVM_RISCV_ISA_EXT_H] = RISCV_ISA_EXT_h,
+	[KVM_RISCV_ISA_EXT_I] = RISCV_ISA_EXT_i,
+	[KVM_RISCV_ISA_EXT_M] = RISCV_ISA_EXT_m,
+
+	KVM_ISA_EXT_ARR(SSTC),
+	KVM_ISA_EXT_ARR(SVINVAL),
+	KVM_ISA_EXT_ARR(SVPBMT),
+	KVM_ISA_EXT_ARR(ZIHINTPAUSE),
+	KVM_ISA_EXT_ARR(ZICBOM),
+};
+
+static unsigned long kvm_riscv_vcpu_base2isa_ext(unsigned long base_ext)
+{
+	unsigned long i;
+
+	for (i = 0; i < KVM_RISCV_ISA_EXT_MAX; i++) {
+		if (kvm_isa_ext_arr[i] == base_ext)
+			return i;
+	}
+
+	return KVM_RISCV_ISA_EXT_MAX;
+}
+
+static bool kvm_riscv_vcpu_isa_enable_allowed(unsigned long ext)
+{
+	switch (ext) {
+	case KVM_RISCV_ISA_EXT_H:
+		return false;
+	default:
+		break;
+	}
+
+	return true;
+}
+
+static bool kvm_riscv_vcpu_isa_disable_allowed(unsigned long ext)
+{
+	switch (ext) {
+	case KVM_RISCV_ISA_EXT_A:
+	case KVM_RISCV_ISA_EXT_C:
+	case KVM_RISCV_ISA_EXT_I:
+	case KVM_RISCV_ISA_EXT_M:
+	case KVM_RISCV_ISA_EXT_SSTC:
+	case KVM_RISCV_ISA_EXT_SVINVAL:
+	case KVM_RISCV_ISA_EXT_ZIHINTPAUSE:
+		return false;
+	default:
+		break;
+	}
+
+	return true;
+}
+
+static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu)
+{
+	struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
+	struct kvm_vcpu_csr *reset_csr = &vcpu->arch.guest_reset_csr;
+	struct kvm_cpu_context *cntx = &vcpu->arch.guest_context;
+	struct kvm_cpu_context *reset_cntx = &vcpu->arch.guest_reset_context;
+	bool loaded;
+
+	/**
+	 * The preemption should be disabled here because it races with
+	 * kvm_sched_out/kvm_sched_in(called from preempt notifiers) which
+	 * also calls vcpu_load/put.
+	 */
+	get_cpu();
+	loaded = (vcpu->cpu != -1);
+	if (loaded)
+		kvm_arch_vcpu_put(vcpu);
+
+	vcpu->arch.last_exit_cpu = -1;
+
+	memcpy(csr, reset_csr, sizeof(*csr));
+
+	memcpy(cntx, reset_cntx, sizeof(*cntx));
+
+	kvm_riscv_vcpu_fp_reset(vcpu);
+
+	kvm_riscv_vcpu_timer_reset(vcpu);
+
+	WRITE_ONCE(vcpu->arch.irqs_pending, 0);
+	WRITE_ONCE(vcpu->arch.irqs_pending_mask, 0);
+
+	vcpu->arch.hfence_head = 0;
+	vcpu->arch.hfence_tail = 0;
+	memset(vcpu->arch.hfence_queue, 0, sizeof(vcpu->arch.hfence_queue));
+
+	/* Reset the guest CSRs for hotplug usecase */
+	if (loaded)
+		kvm_arch_vcpu_load(vcpu, smp_processor_id());
+	put_cpu();
+}
+
+int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id)
+{
+	return 0;
+}
+
+int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpu_context *cntx;
+	struct kvm_vcpu_csr *reset_csr = &vcpu->arch.guest_reset_csr;
+	unsigned long host_isa, i;
+
+	/* Mark this VCPU never ran */
+	vcpu->arch.ran_atleast_once = false;
+	vcpu->arch.mmu_page_cache.gfp_zero = __GFP_ZERO;
+	bitmap_zero(vcpu->arch.isa, RISCV_ISA_EXT_MAX);
+
+	/* Setup ISA features available to VCPU */
+	for (i = 0; i < ARRAY_SIZE(kvm_isa_ext_arr); i++) {
+		host_isa = kvm_isa_ext_arr[i];
+		if (__riscv_isa_extension_available(NULL, host_isa) &&
+		    kvm_riscv_vcpu_isa_enable_allowed(i))
+			set_bit(host_isa, vcpu->arch.isa);
+	}
+
+	/* Setup VCPU hfence queue */
+	spin_lock_init(&vcpu->arch.hfence_lock);
+
+	/* Setup reset state of shadow SSTATUS and HSTATUS CSRs */
+	cntx = &vcpu->arch.guest_reset_context;
+	cntx->sstatus = SR_SPP | SR_SPIE;
+	cntx->hstatus = 0;
+	cntx->hstatus |= HSTATUS_VTW;
+	cntx->hstatus |= HSTATUS_SPVP;
+	cntx->hstatus |= HSTATUS_SPV;
+
+	/* By default, make CY, TM, and IR counters accessible in VU mode */
+	reset_csr->scounteren = 0x7;
+
+	/* Setup VCPU timer */
+	kvm_riscv_vcpu_timer_init(vcpu);
+
+	/* Reset VCPU */
+	kvm_riscv_reset_vcpu(vcpu);
+
+	return 0;
+}
+
+void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
+{
+	/**
+	 * vcpu with id 0 is the designated boot cpu.
+	 * Keep all vcpus with non-zero id in power-off state so that
+	 * they can be brought up using SBI HSM extension.
+	 */
+	if (vcpu->vcpu_idx != 0)
+		kvm_riscv_vcpu_power_off(vcpu);
+}
+
+void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
+{
+	/* Cleanup VCPU timer */
+	kvm_riscv_vcpu_timer_deinit(vcpu);
+
+	/* Free unused pages pre-allocated for G-stage page table mappings */
+	kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_cache);
+}
+
+int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
+{
+	return kvm_riscv_vcpu_timer_pending(vcpu);
+}
+
+void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu)
+{
+}
+
+void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu)
+{
+}
+
+int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
+{
+	return (kvm_riscv_vcpu_has_interrupts(vcpu, -1UL) &&
+		!vcpu->arch.power_off && !vcpu->arch.pause);
+}
+
+int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE;
+}
+
+bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
+{
+	return (vcpu->arch.guest_context.sstatus & SR_SPP) ? true : false;
+}
+
+vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
+{
+	return VM_FAULT_SIGBUS;
+}
+
+static int kvm_riscv_vcpu_get_reg_config(struct kvm_vcpu *vcpu,
+					 const struct kvm_one_reg *reg)
+{
+	unsigned long __user *uaddr =
+			(unsigned long __user *)(unsigned long)reg->addr;
+	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
+					    KVM_REG_SIZE_MASK |
+					    KVM_REG_RISCV_CONFIG);
+	unsigned long reg_val;
+
+	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
+		return -EINVAL;
+
+	switch (reg_num) {
+	case KVM_REG_RISCV_CONFIG_REG(isa):
+		reg_val = vcpu->arch.isa[0] & KVM_RISCV_BASE_ISA_MASK;
+		break;
+	case KVM_REG_RISCV_CONFIG_REG(zicbom_block_size):
+		if (!riscv_isa_extension_available(vcpu->arch.isa, ZICBOM))
+			return -EINVAL;
+		reg_val = riscv_cbom_block_size;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (copy_to_user(uaddr, &reg_val, KVM_REG_SIZE(reg->id)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int kvm_riscv_vcpu_set_reg_config(struct kvm_vcpu *vcpu,
+					 const struct kvm_one_reg *reg)
+{
+	unsigned long __user *uaddr =
+			(unsigned long __user *)(unsigned long)reg->addr;
+	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
+					    KVM_REG_SIZE_MASK |
+					    KVM_REG_RISCV_CONFIG);
+	unsigned long i, isa_ext, reg_val;
+
+	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
+		return -EINVAL;
+
+	if (copy_from_user(&reg_val, uaddr, KVM_REG_SIZE(reg->id)))
+		return -EFAULT;
+
+	switch (reg_num) {
+	case KVM_REG_RISCV_CONFIG_REG(isa):
+		/*
+		 * This ONE REG interface is only defined for
+		 * single letter extensions.
+		 */
+		if (fls(reg_val) >= RISCV_ISA_EXT_BASE)
+			return -EINVAL;
+
+		if (!vcpu->arch.ran_atleast_once) {
+			/* Ignore the enable/disable request for certain extensions */
+			for (i = 0; i < RISCV_ISA_EXT_BASE; i++) {
+				isa_ext = kvm_riscv_vcpu_base2isa_ext(i);
+				if (isa_ext >= KVM_RISCV_ISA_EXT_MAX) {
+					reg_val &= ~BIT(i);
+					continue;
+				}
+				if (!kvm_riscv_vcpu_isa_enable_allowed(isa_ext))
+					if (reg_val & BIT(i))
+						reg_val &= ~BIT(i);
+				if (!kvm_riscv_vcpu_isa_disable_allowed(isa_ext))
+					if (!(reg_val & BIT(i)))
+						reg_val |= BIT(i);
+			}
+			reg_val &= riscv_isa_extension_base(NULL);
+			/* Do not modify anything beyond single letter extensions */
+			reg_val = (vcpu->arch.isa[0] & ~KVM_RISCV_BASE_ISA_MASK) |
+				  (reg_val & KVM_RISCV_BASE_ISA_MASK);
+			vcpu->arch.isa[0] = reg_val;
+			kvm_riscv_vcpu_fp_reset(vcpu);
+		} else {
+			return -EOPNOTSUPP;
+		}
+		break;
+	case KVM_REG_RISCV_CONFIG_REG(zicbom_block_size):
+		return -EOPNOTSUPP;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int kvm_riscv_vcpu_get_reg_core(struct kvm_vcpu *vcpu,
+				       const struct kvm_one_reg *reg)
+{
+	struct kvm_cpu_context *cntx = &vcpu->arch.guest_context;
+	unsigned long __user *uaddr =
+			(unsigned long __user *)(unsigned long)reg->addr;
+	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
+					    KVM_REG_SIZE_MASK |
+					    KVM_REG_RISCV_CORE);
+	unsigned long reg_val;
+
+	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
+		return -EINVAL;
+	if (reg_num >= sizeof(struct kvm_riscv_core) / sizeof(unsigned long))
+		return -EINVAL;
+
+	if (reg_num == KVM_REG_RISCV_CORE_REG(regs.pc))
+		reg_val = cntx->sepc;
+	else if (KVM_REG_RISCV_CORE_REG(regs.pc) < reg_num &&
+		 reg_num <= KVM_REG_RISCV_CORE_REG(regs.t6))
+		reg_val = ((unsigned long *)cntx)[reg_num];
+	else if (reg_num == KVM_REG_RISCV_CORE_REG(mode))
+		reg_val = (cntx->sstatus & SR_SPP) ?
+				KVM_RISCV_MODE_S : KVM_RISCV_MODE_U;
+	else
+		return -EINVAL;
+
+	if (copy_to_user(uaddr, &reg_val, KVM_REG_SIZE(reg->id)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int kvm_riscv_vcpu_set_reg_core(struct kvm_vcpu *vcpu,
+				       const struct kvm_one_reg *reg)
+{
+	struct kvm_cpu_context *cntx = &vcpu->arch.guest_context;
+	unsigned long __user *uaddr =
+			(unsigned long __user *)(unsigned long)reg->addr;
+	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
+					    KVM_REG_SIZE_MASK |
+					    KVM_REG_RISCV_CORE);
+	unsigned long reg_val;
+
+	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
+		return -EINVAL;
+	if (reg_num >= sizeof(struct kvm_riscv_core) / sizeof(unsigned long))
+		return -EINVAL;
+
+	if (copy_from_user(&reg_val, uaddr, KVM_REG_SIZE(reg->id)))
+		return -EFAULT;
+
+	if (reg_num == KVM_REG_RISCV_CORE_REG(regs.pc))
+		cntx->sepc = reg_val;
+	else if (KVM_REG_RISCV_CORE_REG(regs.pc) < reg_num &&
+		 reg_num <= KVM_REG_RISCV_CORE_REG(regs.t6))
+		((unsigned long *)cntx)[reg_num] = reg_val;
+	else if (reg_num == KVM_REG_RISCV_CORE_REG(mode)) {
+		if (reg_val == KVM_RISCV_MODE_S)
+			cntx->sstatus |= SR_SPP;
+		else
+			cntx->sstatus &= ~SR_SPP;
+	} else
+		return -EINVAL;
+
+	return 0;
+}
+
+static int kvm_riscv_vcpu_get_reg_csr(struct kvm_vcpu *vcpu,
+				      const struct kvm_one_reg *reg)
+{
+	struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
+	unsigned long __user *uaddr =
+			(unsigned long __user *)(unsigned long)reg->addr;
+	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
+					    KVM_REG_SIZE_MASK |
+					    KVM_REG_RISCV_CSR);
+	unsigned long reg_val;
+
+	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
+		return -EINVAL;
+	if (reg_num >= sizeof(struct kvm_riscv_csr) / sizeof(unsigned long))
+		return -EINVAL;
+
+	if (reg_num == KVM_REG_RISCV_CSR_REG(sip)) {
+		kvm_riscv_vcpu_flush_interrupts(vcpu);
+		reg_val = (csr->hvip >> VSIP_TO_HVIP_SHIFT) & VSIP_VALID_MASK;
+	} else
+		reg_val = ((unsigned long *)csr)[reg_num];
+
+	if (copy_to_user(uaddr, &reg_val, KVM_REG_SIZE(reg->id)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int kvm_riscv_vcpu_set_reg_csr(struct kvm_vcpu *vcpu,
+				      const struct kvm_one_reg *reg)
+{
+	struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
+	unsigned long __user *uaddr =
+			(unsigned long __user *)(unsigned long)reg->addr;
+	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
+					    KVM_REG_SIZE_MASK |
+					    KVM_REG_RISCV_CSR);
+	unsigned long reg_val;
+
+	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
+		return -EINVAL;
+	if (reg_num >= sizeof(struct kvm_riscv_csr) / sizeof(unsigned long))
+		return -EINVAL;
+
+	if (copy_from_user(&reg_val, uaddr, KVM_REG_SIZE(reg->id)))
+		return -EFAULT;
+
+	if (reg_num == KVM_REG_RISCV_CSR_REG(sip)) {
+		reg_val &= VSIP_VALID_MASK;
+		reg_val <<= VSIP_TO_HVIP_SHIFT;
+	}
+
+	((unsigned long *)csr)[reg_num] = reg_val;
+
+	if (reg_num == KVM_REG_RISCV_CSR_REG(sip))
+		WRITE_ONCE(vcpu->arch.irqs_pending_mask, 0);
+
+	return 0;
+}
+
+static int kvm_riscv_vcpu_get_reg_isa_ext(struct kvm_vcpu *vcpu,
+					  const struct kvm_one_reg *reg)
+{
+	unsigned long __user *uaddr =
+			(unsigned long __user *)(unsigned long)reg->addr;
+	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
+					    KVM_REG_SIZE_MASK |
+					    KVM_REG_RISCV_ISA_EXT);
+	unsigned long reg_val = 0;
+	unsigned long host_isa_ext;
+
+	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
+		return -EINVAL;
+
+	if (reg_num >= KVM_RISCV_ISA_EXT_MAX ||
+	    reg_num >= ARRAY_SIZE(kvm_isa_ext_arr))
+		return -EINVAL;
+
+	host_isa_ext = kvm_isa_ext_arr[reg_num];
+	if (__riscv_isa_extension_available(vcpu->arch.isa, host_isa_ext))
+		reg_val = 1; /* Mark the given extension as available */
+
+	if (copy_to_user(uaddr, &reg_val, KVM_REG_SIZE(reg->id)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int kvm_riscv_vcpu_set_reg_isa_ext(struct kvm_vcpu *vcpu,
+					  const struct kvm_one_reg *reg)
+{
+	unsigned long __user *uaddr =
+			(unsigned long __user *)(unsigned long)reg->addr;
+	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
+					    KVM_REG_SIZE_MASK |
+					    KVM_REG_RISCV_ISA_EXT);
+	unsigned long reg_val;
+	unsigned long host_isa_ext;
+
+	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
+		return -EINVAL;
+
+	if (reg_num >= KVM_RISCV_ISA_EXT_MAX ||
+	    reg_num >= ARRAY_SIZE(kvm_isa_ext_arr))
+		return -EINVAL;
+
+	if (copy_from_user(&reg_val, uaddr, KVM_REG_SIZE(reg->id)))
+		return -EFAULT;
+
+	host_isa_ext = kvm_isa_ext_arr[reg_num];
+	if (!__riscv_isa_extension_available(NULL, host_isa_ext))
+		return	-EOPNOTSUPP;
+
+	if (!vcpu->arch.ran_atleast_once) {
+		/*
+		 * All multi-letter extension and a few single letter
+		 * extension can be disabled
+		 */
+		if (reg_val == 1 &&
+		    kvm_riscv_vcpu_isa_enable_allowed(reg_num))
+			set_bit(host_isa_ext, vcpu->arch.isa);
+		else if (!reg_val &&
+			 kvm_riscv_vcpu_isa_disable_allowed(reg_num))
+			clear_bit(host_isa_ext, vcpu->arch.isa);
+		else
+			return -EINVAL;
+		kvm_riscv_vcpu_fp_reset(vcpu);
+	} else {
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int kvm_riscv_vcpu_set_reg(struct kvm_vcpu *vcpu,
+				  const struct kvm_one_reg *reg)
+{
+	if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_CONFIG)
+		return kvm_riscv_vcpu_set_reg_config(vcpu, reg);
+	else if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_CORE)
+		return kvm_riscv_vcpu_set_reg_core(vcpu, reg);
+	else if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_CSR)
+		return kvm_riscv_vcpu_set_reg_csr(vcpu, reg);
+	else if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_TIMER)
+		return kvm_riscv_vcpu_set_reg_timer(vcpu, reg);
+	else if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_FP_F)
+		return kvm_riscv_vcpu_set_reg_fp(vcpu, reg,
+						 KVM_REG_RISCV_FP_F);
+	else if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_FP_D)
+		return kvm_riscv_vcpu_set_reg_fp(vcpu, reg,
+						 KVM_REG_RISCV_FP_D);
+	else if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_ISA_EXT)
+		return kvm_riscv_vcpu_set_reg_isa_ext(vcpu, reg);
+
+	return -EINVAL;
+}
+
+static int kvm_riscv_vcpu_get_reg(struct kvm_vcpu *vcpu,
+				  const struct kvm_one_reg *reg)
+{
+	if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_CONFIG)
+		return kvm_riscv_vcpu_get_reg_config(vcpu, reg);
+	else if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_CORE)
+		return kvm_riscv_vcpu_get_reg_core(vcpu, reg);
+	else if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_CSR)
+		return kvm_riscv_vcpu_get_reg_csr(vcpu, reg);
+	else if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_TIMER)
+		return kvm_riscv_vcpu_get_reg_timer(vcpu, reg);
+	else if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_FP_F)
+		return kvm_riscv_vcpu_get_reg_fp(vcpu, reg,
+						 KVM_REG_RISCV_FP_F);
+	else if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_FP_D)
+		return kvm_riscv_vcpu_get_reg_fp(vcpu, reg,
+						 KVM_REG_RISCV_FP_D);
+	else if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_ISA_EXT)
+		return kvm_riscv_vcpu_get_reg_isa_ext(vcpu, reg);
+
+	return -EINVAL;
+}
+
+long kvm_arch_vcpu_async_ioctl(struct file *filp,
+			       unsigned int ioctl, unsigned long arg)
+{
+	struct kvm_vcpu *vcpu = filp->private_data;
+	void __user *argp = (void __user *)arg;
+
+	if (ioctl == KVM_INTERRUPT) {
+		struct kvm_interrupt irq;
+
+		if (copy_from_user(&irq, argp, sizeof(irq)))
+			return -EFAULT;
+
+		if (irq.irq == KVM_INTERRUPT_SET)
+			return kvm_riscv_vcpu_set_interrupt(vcpu, IRQ_VS_EXT);
+		else
+			return kvm_riscv_vcpu_unset_interrupt(vcpu, IRQ_VS_EXT);
+	}
+
+	return -ENOIOCTLCMD;
+}
+
+long kvm_arch_vcpu_ioctl(struct file *filp,
+			 unsigned int ioctl, unsigned long arg)
+{
+	struct kvm_vcpu *vcpu = filp->private_data;
+	void __user *argp = (void __user *)arg;
+	long r = -EINVAL;
+
+	switch (ioctl) {
+	case KVM_SET_ONE_REG:
+	case KVM_GET_ONE_REG: {
+		struct kvm_one_reg reg;
+
+		r = -EFAULT;
+		if (copy_from_user(&reg, argp, sizeof(reg)))
+			break;
+
+		if (ioctl == KVM_SET_ONE_REG)
+			r = kvm_riscv_vcpu_set_reg(vcpu, &reg);
+		else
+			r = kvm_riscv_vcpu_get_reg(vcpu, &reg);
+		break;
+	}
+	default:
+		break;
+	}
+
+	return r;
+}
+
+int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
+				  struct kvm_sregs *sregs)
+{
+	return -EINVAL;
+}
+
+int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
+				  struct kvm_sregs *sregs)
+{
+	return -EINVAL;
+}
+
+int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
+{
+	return -EINVAL;
+}
+
+int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
+{
+	return -EINVAL;
+}
+
+int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
+				  struct kvm_translation *tr)
+{
+	return -EINVAL;
+}
+
+int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
+{
+	return -EINVAL;
+}
+
+int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
+{
+	return -EINVAL;
+}
+
+void kvm_riscv_vcpu_flush_interrupts(struct kvm_vcpu *vcpu)
+{
+	struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
+	unsigned long mask, val;
+
+	if (READ_ONCE(vcpu->arch.irqs_pending_mask)) {
+		mask = xchg_acquire(&vcpu->arch.irqs_pending_mask, 0);
+		val = READ_ONCE(vcpu->arch.irqs_pending) & mask;
+
+		csr->hvip &= ~mask;
+		csr->hvip |= val;
+	}
+}
+
+void kvm_riscv_vcpu_sync_interrupts(struct kvm_vcpu *vcpu)
+{
+	unsigned long hvip;
+	struct kvm_vcpu_arch *v = &vcpu->arch;
+	struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
+
+	/* Read current HVIP and VSIE CSRs */
+	csr->vsie = csr_read(CSR_VSIE);
+
+	/* Sync-up HVIP.VSSIP bit changes does by Guest */
+	hvip = csr_read(CSR_HVIP);
+	if ((csr->hvip ^ hvip) & (1UL << IRQ_VS_SOFT)) {
+		if (hvip & (1UL << IRQ_VS_SOFT)) {
+			if (!test_and_set_bit(IRQ_VS_SOFT,
+					      &v->irqs_pending_mask))
+				set_bit(IRQ_VS_SOFT, &v->irqs_pending);
+		} else {
+			if (!test_and_set_bit(IRQ_VS_SOFT,
+					      &v->irqs_pending_mask))
+				clear_bit(IRQ_VS_SOFT, &v->irqs_pending);
+		}
+	}
+
+	/* Sync-up timer CSRs */
+	kvm_riscv_vcpu_timer_sync(vcpu);
+}
+
+int kvm_riscv_vcpu_set_interrupt(struct kvm_vcpu *vcpu, unsigned int irq)
+{
+	if (irq != IRQ_VS_SOFT &&
+	    irq != IRQ_VS_TIMER &&
+	    irq != IRQ_VS_EXT)
+		return -EINVAL;
+
+	set_bit(irq, &vcpu->arch.irqs_pending);
+	smp_mb__before_atomic();
+	set_bit(irq, &vcpu->arch.irqs_pending_mask);
+
+	kvm_vcpu_kick(vcpu);
+
+	return 0;
+}
+
+int kvm_riscv_vcpu_unset_interrupt(struct kvm_vcpu *vcpu, unsigned int irq)
+{
+	if (irq != IRQ_VS_SOFT &&
+	    irq != IRQ_VS_TIMER &&
+	    irq != IRQ_VS_EXT)
+		return -EINVAL;
+
+	clear_bit(irq, &vcpu->arch.irqs_pending);
+	smp_mb__before_atomic();
+	set_bit(irq, &vcpu->arch.irqs_pending_mask);
+
+	return 0;
+}
+
+bool kvm_riscv_vcpu_has_interrupts(struct kvm_vcpu *vcpu, unsigned long mask)
+{
+	unsigned long ie = ((vcpu->arch.guest_csr.vsie & VSIP_VALID_MASK)
+			    << VSIP_TO_HVIP_SHIFT) & mask;
+
+	return (READ_ONCE(vcpu->arch.irqs_pending) & ie) ? true : false;
+}
+
+void kvm_riscv_vcpu_power_off(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.power_off = true;
+	kvm_make_request(KVM_REQ_SLEEP, vcpu);
+	kvm_vcpu_kick(vcpu);
+}
+
+void kvm_riscv_vcpu_power_on(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.power_off = false;
+	kvm_vcpu_wake_up(vcpu);
+}
+
+int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
+				    struct kvm_mp_state *mp_state)
+{
+	if (vcpu->arch.power_off)
+		mp_state->mp_state = KVM_MP_STATE_STOPPED;
+	else
+		mp_state->mp_state = KVM_MP_STATE_RUNNABLE;
+
+	return 0;
+}
+
+int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
+				    struct kvm_mp_state *mp_state)
+{
+	int ret = 0;
+
+	switch (mp_state->mp_state) {
+	case KVM_MP_STATE_RUNNABLE:
+		vcpu->arch.power_off = false;
+		break;
+	case KVM_MP_STATE_STOPPED:
+		kvm_riscv_vcpu_power_off(vcpu);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+
+int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
+					struct kvm_guest_debug *dbg)
+{
+	/* TODO; To be implemented later. */
+	return -EINVAL;
+}
+
+static void kvm_riscv_vcpu_update_config(const unsigned long *isa)
+{
+	u64 henvcfg = 0;
+
+	if (riscv_isa_extension_available(isa, SVPBMT))
+		henvcfg |= ENVCFG_PBMTE;
+
+	if (riscv_isa_extension_available(isa, SSTC))
+		henvcfg |= ENVCFG_STCE;
+
+	if (riscv_isa_extension_available(isa, ZICBOM))
+		henvcfg |= (ENVCFG_CBIE | ENVCFG_CBCFE);
+
+	csr_write(CSR_HENVCFG, henvcfg);
+#ifdef CONFIG_32BIT
+	csr_write(CSR_HENVCFGH, henvcfg >> 32);
+#endif
+}
+
+void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+{
+	struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
+
+	csr_write(CSR_VSSTATUS, csr->vsstatus);
+	csr_write(CSR_VSIE, csr->vsie);
+	csr_write(CSR_VSTVEC, csr->vstvec);
+	csr_write(CSR_VSSCRATCH, csr->vsscratch);
+	csr_write(CSR_VSEPC, csr->vsepc);
+	csr_write(CSR_VSCAUSE, csr->vscause);
+	csr_write(CSR_VSTVAL, csr->vstval);
+	csr_write(CSR_HVIP, csr->hvip);
+	csr_write(CSR_VSATP, csr->vsatp);
+
+	kvm_riscv_vcpu_update_config(vcpu->arch.isa);
+
+	kvm_riscv_gstage_update_hgatp(vcpu);
+
+	kvm_riscv_vcpu_timer_restore(vcpu);
+
+	kvm_riscv_vcpu_host_fp_save(&vcpu->arch.host_context);
+	kvm_riscv_vcpu_guest_fp_restore(&vcpu->arch.guest_context,
+					vcpu->arch.isa);
+
+	vcpu->cpu = cpu;
+}
+
+void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
+{
+	struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
+
+	vcpu->cpu = -1;
+
+	kvm_riscv_vcpu_guest_fp_save(&vcpu->arch.guest_context,
+				     vcpu->arch.isa);
+	kvm_riscv_vcpu_host_fp_restore(&vcpu->arch.host_context);
+
+	kvm_riscv_vcpu_timer_save(vcpu);
+
+	csr->vsstatus = csr_read(CSR_VSSTATUS);
+	csr->vsie = csr_read(CSR_VSIE);
+	csr->vstvec = csr_read(CSR_VSTVEC);
+	csr->vsscratch = csr_read(CSR_VSSCRATCH);
+	csr->vsepc = csr_read(CSR_VSEPC);
+	csr->vscause = csr_read(CSR_VSCAUSE);
+	csr->vstval = csr_read(CSR_VSTVAL);
+	csr->hvip = csr_read(CSR_HVIP);
+	csr->vsatp = csr_read(CSR_VSATP);
+}
+
+static void kvm_riscv_check_vcpu_requests(struct kvm_vcpu *vcpu)
+{
+	struct rcuwait *wait = kvm_arch_vcpu_get_wait(vcpu);
+
+	if (kvm_request_pending(vcpu)) {
+		if (kvm_check_request(KVM_REQ_SLEEP, vcpu)) {
+			kvm_vcpu_srcu_read_unlock(vcpu);
+			rcuwait_wait_event(wait,
+				(!vcpu->arch.power_off) && (!vcpu->arch.pause),
+				TASK_INTERRUPTIBLE);
+			kvm_vcpu_srcu_read_lock(vcpu);
+
+			if (vcpu->arch.power_off || vcpu->arch.pause) {
+				/*
+				 * Awaken to handle a signal, request to
+				 * sleep again later.
+				 */
+				kvm_make_request(KVM_REQ_SLEEP, vcpu);
+			}
+		}
+
+		if (kvm_check_request(KVM_REQ_VCPU_RESET, vcpu))
+			kvm_riscv_reset_vcpu(vcpu);
+
+		if (kvm_check_request(KVM_REQ_UPDATE_HGATP, vcpu))
+			kvm_riscv_gstage_update_hgatp(vcpu);
+
+		if (kvm_check_request(KVM_REQ_FENCE_I, vcpu))
+			kvm_riscv_fence_i_process(vcpu);
+
+		/*
+		 * The generic KVM_REQ_TLB_FLUSH is same as
+		 * KVM_REQ_HFENCE_GVMA_VMID_ALL
+		 */
+		if (kvm_check_request(KVM_REQ_HFENCE_GVMA_VMID_ALL, vcpu))
+			kvm_riscv_hfence_gvma_vmid_all_process(vcpu);
+
+		if (kvm_check_request(KVM_REQ_HFENCE_VVMA_ALL, vcpu))
+			kvm_riscv_hfence_vvma_all_process(vcpu);
+
+		if (kvm_check_request(KVM_REQ_HFENCE, vcpu))
+			kvm_riscv_hfence_process(vcpu);
+	}
+}
+
+static void kvm_riscv_update_hvip(struct kvm_vcpu *vcpu)
+{
+	struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
+
+	csr_write(CSR_HVIP, csr->hvip);
+}
+
+/*
+ * Actually run the vCPU, entering an RCU extended quiescent state (EQS) while
+ * the vCPU is running.
+ *
+ * This must be noinstr as instrumentation may make use of RCU, and this is not
+ * safe during the EQS.
+ */
+static void noinstr kvm_riscv_vcpu_enter_exit(struct kvm_vcpu *vcpu)
+{
+	guest_state_enter_irqoff();
+	__kvm_riscv_switch_to(&vcpu->arch);
+	vcpu->arch.last_exit_cpu = vcpu->cpu;
+	guest_state_exit_irqoff();
+}
+
+int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
+{
+	int ret;
+	struct kvm_cpu_trap trap;
+	struct kvm_run *run = vcpu->run;
+
+	/* Mark this VCPU ran at least once */
+	vcpu->arch.ran_atleast_once = true;
+
+	kvm_vcpu_srcu_read_lock(vcpu);
+
+	switch (run->exit_reason) {
+	case KVM_EXIT_MMIO:
+		/* Process MMIO value returned from user-space */
+		ret = kvm_riscv_vcpu_mmio_return(vcpu, vcpu->run);
+		break;
+	case KVM_EXIT_RISCV_SBI:
+		/* Process SBI value returned from user-space */
+		ret = kvm_riscv_vcpu_sbi_return(vcpu, vcpu->run);
+		break;
+	case KVM_EXIT_RISCV_CSR:
+		/* Process CSR value returned from user-space */
+		ret = kvm_riscv_vcpu_csr_return(vcpu, vcpu->run);
+		break;
+	default:
+		ret = 0;
+		break;
+	}
+	if (ret) {
+		kvm_vcpu_srcu_read_unlock(vcpu);
+		return ret;
+	}
+
+	if (run->immediate_exit) {
+		kvm_vcpu_srcu_read_unlock(vcpu);
+		return -EINTR;
+	}
+
+	vcpu_load(vcpu);
+
+	kvm_sigset_activate(vcpu);
+
+	ret = 1;
+	run->exit_reason = KVM_EXIT_UNKNOWN;
+	while (ret > 0) {
+		/* Check conditions before entering the guest */
+		ret = xfer_to_guest_mode_handle_work(vcpu);
+		if (!ret)
+			ret = 1;
+
+		kvm_riscv_gstage_vmid_update(vcpu);
+
+		kvm_riscv_check_vcpu_requests(vcpu);
+
+		local_irq_disable();
+
+		/*
+		 * Ensure we set mode to IN_GUEST_MODE after we disable
+		 * interrupts and before the final VCPU requests check.
+		 * See the comment in kvm_vcpu_exiting_guest_mode() and
+		 * Documentation/virt/kvm/vcpu-requests.rst
+		 */
+		vcpu->mode = IN_GUEST_MODE;
+
+		kvm_vcpu_srcu_read_unlock(vcpu);
+		smp_mb__after_srcu_read_unlock();
+
+		/*
+		 * We might have got VCPU interrupts updated asynchronously
+		 * so update it in HW.
+		 */
+		kvm_riscv_vcpu_flush_interrupts(vcpu);
+
+		/* Update HVIP CSR for current CPU */
+		kvm_riscv_update_hvip(vcpu);
+
+		if (ret <= 0 ||
+		    kvm_riscv_gstage_vmid_ver_changed(&vcpu->kvm->arch.vmid) ||
+		    kvm_request_pending(vcpu) ||
+		    xfer_to_guest_mode_work_pending()) {
+			vcpu->mode = OUTSIDE_GUEST_MODE;
+			local_irq_enable();
+			kvm_vcpu_srcu_read_lock(vcpu);
+			continue;
+		}
+
+		/*
+		 * Cleanup stale TLB enteries
+		 *
+		 * Note: This should be done after G-stage VMID has been
+		 * updated using kvm_riscv_gstage_vmid_ver_changed()
+		 */
+		kvm_riscv_local_tlb_sanitize(vcpu);
+
+		guest_timing_enter_irqoff();
+
+		kvm_riscv_vcpu_enter_exit(vcpu);
+
+		vcpu->mode = OUTSIDE_GUEST_MODE;
+		vcpu->stat.exits++;
+
+		/*
+		 * Save SCAUSE, STVAL, HTVAL, and HTINST because we might
+		 * get an interrupt between __kvm_riscv_switch_to() and
+		 * local_irq_enable() which can potentially change CSRs.
+		 */
+		trap.sepc = vcpu->arch.guest_context.sepc;
+		trap.scause = csr_read(CSR_SCAUSE);
+		trap.stval = csr_read(CSR_STVAL);
+		trap.htval = csr_read(CSR_HTVAL);
+		trap.htinst = csr_read(CSR_HTINST);
+
+		/* Syncup interrupts state with HW */
+		kvm_riscv_vcpu_sync_interrupts(vcpu);
+
+		preempt_disable();
+
+		/*
+		 * We must ensure that any pending interrupts are taken before
+		 * we exit guest timing so that timer ticks are accounted as
+		 * guest time. Transiently unmask interrupts so that any
+		 * pending interrupts are taken.
+		 *
+		 * There's no barrier which ensures that pending interrupts are
+		 * recognised, so we just hope that the CPU takes any pending
+		 * interrupts between the enable and disable.
+		 */
+		local_irq_enable();
+		local_irq_disable();
+
+		guest_timing_exit_irqoff();
+
+		local_irq_enable();
+
+		preempt_enable();
+
+		kvm_vcpu_srcu_read_lock(vcpu);
+
+		ret = kvm_riscv_vcpu_exit(vcpu, run, &trap);
+	}
+
+	kvm_sigset_deactivate(vcpu);
+
+	vcpu_put(vcpu);
+
+	kvm_vcpu_srcu_read_unlock(vcpu);
+
+	return ret;
+}
diff --git a/arch/riscv/kvm/vcpu_exit.c b/arch/riscv/kvm/vcpu_exit.c
new file mode 100644
index 000000000..c9f741ab2
--- /dev/null
+++ b/arch/riscv/kvm/vcpu_exit.c
@@ -0,0 +1,212 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 Western Digital Corporation or its affiliates.
+ *
+ * Authors:
+ *     Anup Patel <anup.patel@wdc.com>
+ */
+
+#include <linux/kvm_host.h>
+#include <asm/csr.h>
+#include <asm/insn-def.h>
+
+static int gstage_page_fault(struct kvm_vcpu *vcpu, struct kvm_run *run,
+			     struct kvm_cpu_trap *trap)
+{
+	struct kvm_memory_slot *memslot;
+	unsigned long hva, fault_addr;
+	bool writable;
+	gfn_t gfn;
+	int ret;
+
+	fault_addr = (trap->htval << 2) | (trap->stval & 0x3);
+	gfn = fault_addr >> PAGE_SHIFT;
+	memslot = gfn_to_memslot(vcpu->kvm, gfn);
+	hva = gfn_to_hva_memslot_prot(memslot, gfn, &writable);
+
+	if (kvm_is_error_hva(hva) ||
+	    (trap->scause == EXC_STORE_GUEST_PAGE_FAULT && !writable)) {
+		switch (trap->scause) {
+		case EXC_LOAD_GUEST_PAGE_FAULT:
+			return kvm_riscv_vcpu_mmio_load(vcpu, run,
+							fault_addr,
+							trap->htinst);
+		case EXC_STORE_GUEST_PAGE_FAULT:
+			return kvm_riscv_vcpu_mmio_store(vcpu, run,
+							 fault_addr,
+							 trap->htinst);
+		default:
+			return -EOPNOTSUPP;
+		};
+	}
+
+	ret = kvm_riscv_gstage_map(vcpu, memslot, fault_addr, hva,
+		(trap->scause == EXC_STORE_GUEST_PAGE_FAULT) ? true : false);
+	if (ret < 0)
+		return ret;
+
+	return 1;
+}
+
+/**
+ * kvm_riscv_vcpu_unpriv_read -- Read machine word from Guest memory
+ *
+ * @vcpu: The VCPU pointer
+ * @read_insn: Flag representing whether we are reading instruction
+ * @guest_addr: Guest address to read
+ * @trap: Output pointer to trap details
+ */
+unsigned long kvm_riscv_vcpu_unpriv_read(struct kvm_vcpu *vcpu,
+					 bool read_insn,
+					 unsigned long guest_addr,
+					 struct kvm_cpu_trap *trap)
+{
+	register unsigned long taddr asm("a0") = (unsigned long)trap;
+	register unsigned long ttmp asm("a1");
+	unsigned long flags, val, tmp, old_stvec, old_hstatus;
+
+	local_irq_save(flags);
+
+	old_hstatus = csr_swap(CSR_HSTATUS, vcpu->arch.guest_context.hstatus);
+	old_stvec = csr_swap(CSR_STVEC, (ulong)&__kvm_riscv_unpriv_trap);
+
+	if (read_insn) {
+		/*
+		 * HLVX.HU instruction
+		 * 0110010 00011 rs1 100 rd 1110011
+		 */
+		asm volatile ("\n"
+			".option push\n"
+			".option norvc\n"
+			"add %[ttmp], %[taddr], 0\n"
+			HLVX_HU(%[val], %[addr])
+			"andi %[tmp], %[val], 3\n"
+			"addi %[tmp], %[tmp], -3\n"
+			"bne %[tmp], zero, 2f\n"
+			"addi %[addr], %[addr], 2\n"
+			HLVX_HU(%[tmp], %[addr])
+			"sll %[tmp], %[tmp], 16\n"
+			"add %[val], %[val], %[tmp]\n"
+			"2:\n"
+			".option pop"
+		: [val] "=&r" (val), [tmp] "=&r" (tmp),
+		  [taddr] "+&r" (taddr), [ttmp] "+&r" (ttmp),
+		  [addr] "+&r" (guest_addr) : : "memory");
+
+		if (trap->scause == EXC_LOAD_PAGE_FAULT)
+			trap->scause = EXC_INST_PAGE_FAULT;
+	} else {
+		/*
+		 * HLV.D instruction
+		 * 0110110 00000 rs1 100 rd 1110011
+		 *
+		 * HLV.W instruction
+		 * 0110100 00000 rs1 100 rd 1110011
+		 */
+		asm volatile ("\n"
+			".option push\n"
+			".option norvc\n"
+			"add %[ttmp], %[taddr], 0\n"
+#ifdef CONFIG_64BIT
+			HLV_D(%[val], %[addr])
+#else
+			HLV_W(%[val], %[addr])
+#endif
+			".option pop"
+		: [val] "=&r" (val),
+		  [taddr] "+&r" (taddr), [ttmp] "+&r" (ttmp)
+		: [addr] "r" (guest_addr) : "memory");
+	}
+
+	csr_write(CSR_STVEC, old_stvec);
+	csr_write(CSR_HSTATUS, old_hstatus);
+
+	local_irq_restore(flags);
+
+	return val;
+}
+
+/**
+ * kvm_riscv_vcpu_trap_redirect -- Redirect trap to Guest
+ *
+ * @vcpu: The VCPU pointer
+ * @trap: Trap details
+ */
+void kvm_riscv_vcpu_trap_redirect(struct kvm_vcpu *vcpu,
+				  struct kvm_cpu_trap *trap)
+{
+	unsigned long vsstatus = csr_read(CSR_VSSTATUS);
+
+	/* Change Guest SSTATUS.SPP bit */
+	vsstatus &= ~SR_SPP;
+	if (vcpu->arch.guest_context.sstatus & SR_SPP)
+		vsstatus |= SR_SPP;
+
+	/* Change Guest SSTATUS.SPIE bit */
+	vsstatus &= ~SR_SPIE;
+	if (vsstatus & SR_SIE)
+		vsstatus |= SR_SPIE;
+
+	/* Clear Guest SSTATUS.SIE bit */
+	vsstatus &= ~SR_SIE;
+
+	/* Update Guest SSTATUS */
+	csr_write(CSR_VSSTATUS, vsstatus);
+
+	/* Update Guest SCAUSE, STVAL, and SEPC */
+	csr_write(CSR_VSCAUSE, trap->scause);
+	csr_write(CSR_VSTVAL, trap->stval);
+	csr_write(CSR_VSEPC, trap->sepc);
+
+	/* Set Guest PC to Guest exception vector */
+	vcpu->arch.guest_context.sepc = csr_read(CSR_VSTVEC);
+}
+
+/*
+ * Return > 0 to return to guest, < 0 on error, 0 (and set exit_reason) on
+ * proper exit to userspace.
+ */
+int kvm_riscv_vcpu_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
+			struct kvm_cpu_trap *trap)
+{
+	int ret;
+
+	/* If we got host interrupt then do nothing */
+	if (trap->scause & CAUSE_IRQ_FLAG)
+		return 1;
+
+	/* Handle guest traps */
+	ret = -EFAULT;
+	run->exit_reason = KVM_EXIT_UNKNOWN;
+	switch (trap->scause) {
+	case EXC_VIRTUAL_INST_FAULT:
+		if (vcpu->arch.guest_context.hstatus & HSTATUS_SPV)
+			ret = kvm_riscv_vcpu_virtual_insn(vcpu, run, trap);
+		break;
+	case EXC_INST_GUEST_PAGE_FAULT:
+	case EXC_LOAD_GUEST_PAGE_FAULT:
+	case EXC_STORE_GUEST_PAGE_FAULT:
+		if (vcpu->arch.guest_context.hstatus & HSTATUS_SPV)
+			ret = gstage_page_fault(vcpu, run, trap);
+		break;
+	case EXC_SUPERVISOR_SYSCALL:
+		if (vcpu->arch.guest_context.hstatus & HSTATUS_SPV)
+			ret = kvm_riscv_vcpu_sbi_ecall(vcpu, run);
+		break;
+	default:
+		break;
+	}
+
+	/* Print details in-case of error */
+	if (ret < 0) {
+		kvm_err("VCPU exit error %d\n", ret);
+		kvm_err("SEPC=0x%lx SSTATUS=0x%lx HSTATUS=0x%lx\n",
+			vcpu->arch.guest_context.sepc,
+			vcpu->arch.guest_context.sstatus,
+			vcpu->arch.guest_context.hstatus);
+		kvm_err("SCAUSE=0x%lx STVAL=0x%lx HTVAL=0x%lx HTINST=0x%lx\n",
+			trap->scause, trap->stval, trap->htval, trap->htinst);
+	}
+
+	return ret;
+}
diff --git a/arch/riscv/kvm/vcpu_fp.c b/arch/riscv/kvm/vcpu_fp.c
new file mode 100644
index 000000000..9d8cbc420
--- /dev/null
+++ b/arch/riscv/kvm/vcpu_fp.c
@@ -0,0 +1,165 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 Western Digital Corporation or its affiliates.
+ *
+ * Authors:
+ *     Atish Patra <atish.patra@wdc.com>
+ *     Anup Patel <anup.patel@wdc.com>
+ */
+
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/kvm_host.h>
+#include <linux/uaccess.h>
+#include <asm/hwcap.h>
+
+#ifdef CONFIG_FPU
+void kvm_riscv_vcpu_fp_reset(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpu_context *cntx = &vcpu->arch.guest_context;
+
+	cntx->sstatus &= ~SR_FS;
+	if (riscv_isa_extension_available(vcpu->arch.isa, f) ||
+	    riscv_isa_extension_available(vcpu->arch.isa, d))
+		cntx->sstatus |= SR_FS_INITIAL;
+	else
+		cntx->sstatus |= SR_FS_OFF;
+}
+
+static void kvm_riscv_vcpu_fp_clean(struct kvm_cpu_context *cntx)
+{
+	cntx->sstatus &= ~SR_FS;
+	cntx->sstatus |= SR_FS_CLEAN;
+}
+
+void kvm_riscv_vcpu_guest_fp_save(struct kvm_cpu_context *cntx,
+				  const unsigned long *isa)
+{
+	if ((cntx->sstatus & SR_FS) == SR_FS_DIRTY) {
+		if (riscv_isa_extension_available(isa, d))
+			__kvm_riscv_fp_d_save(cntx);
+		else if (riscv_isa_extension_available(isa, f))
+			__kvm_riscv_fp_f_save(cntx);
+		kvm_riscv_vcpu_fp_clean(cntx);
+	}
+}
+
+void kvm_riscv_vcpu_guest_fp_restore(struct kvm_cpu_context *cntx,
+				     const unsigned long *isa)
+{
+	if ((cntx->sstatus & SR_FS) != SR_FS_OFF) {
+		if (riscv_isa_extension_available(isa, d))
+			__kvm_riscv_fp_d_restore(cntx);
+		else if (riscv_isa_extension_available(isa, f))
+			__kvm_riscv_fp_f_restore(cntx);
+		kvm_riscv_vcpu_fp_clean(cntx);
+	}
+}
+
+void kvm_riscv_vcpu_host_fp_save(struct kvm_cpu_context *cntx)
+{
+	/* No need to check host sstatus as it can be modified outside */
+	if (riscv_isa_extension_available(NULL, d))
+		__kvm_riscv_fp_d_save(cntx);
+	else if (riscv_isa_extension_available(NULL, f))
+		__kvm_riscv_fp_f_save(cntx);
+}
+
+void kvm_riscv_vcpu_host_fp_restore(struct kvm_cpu_context *cntx)
+{
+	if (riscv_isa_extension_available(NULL, d))
+		__kvm_riscv_fp_d_restore(cntx);
+	else if (riscv_isa_extension_available(NULL, f))
+		__kvm_riscv_fp_f_restore(cntx);
+}
+#endif
+
+int kvm_riscv_vcpu_get_reg_fp(struct kvm_vcpu *vcpu,
+			      const struct kvm_one_reg *reg,
+			      unsigned long rtype)
+{
+	struct kvm_cpu_context *cntx = &vcpu->arch.guest_context;
+	unsigned long __user *uaddr =
+			(unsigned long __user *)(unsigned long)reg->addr;
+	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
+					    KVM_REG_SIZE_MASK |
+					    rtype);
+	void *reg_val;
+
+	if ((rtype == KVM_REG_RISCV_FP_F) &&
+	    riscv_isa_extension_available(vcpu->arch.isa, f)) {
+		if (KVM_REG_SIZE(reg->id) != sizeof(u32))
+			return -EINVAL;
+		if (reg_num == KVM_REG_RISCV_FP_F_REG(fcsr))
+			reg_val = &cntx->fp.f.fcsr;
+		else if ((KVM_REG_RISCV_FP_F_REG(f[0]) <= reg_num) &&
+			  reg_num <= KVM_REG_RISCV_FP_F_REG(f[31]))
+			reg_val = &cntx->fp.f.f[reg_num];
+		else
+			return -EINVAL;
+	} else if ((rtype == KVM_REG_RISCV_FP_D) &&
+		   riscv_isa_extension_available(vcpu->arch.isa, d)) {
+		if (reg_num == KVM_REG_RISCV_FP_D_REG(fcsr)) {
+			if (KVM_REG_SIZE(reg->id) != sizeof(u32))
+				return -EINVAL;
+			reg_val = &cntx->fp.d.fcsr;
+		} else if ((KVM_REG_RISCV_FP_D_REG(f[0]) <= reg_num) &&
+			   reg_num <= KVM_REG_RISCV_FP_D_REG(f[31])) {
+			if (KVM_REG_SIZE(reg->id) != sizeof(u64))
+				return -EINVAL;
+			reg_val = &cntx->fp.d.f[reg_num];
+		} else
+			return -EINVAL;
+	} else
+		return -EINVAL;
+
+	if (copy_to_user(uaddr, reg_val, KVM_REG_SIZE(reg->id)))
+		return -EFAULT;
+
+	return 0;
+}
+
+int kvm_riscv_vcpu_set_reg_fp(struct kvm_vcpu *vcpu,
+			      const struct kvm_one_reg *reg,
+			      unsigned long rtype)
+{
+	struct kvm_cpu_context *cntx = &vcpu->arch.guest_context;
+	unsigned long __user *uaddr =
+			(unsigned long __user *)(unsigned long)reg->addr;
+	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
+					    KVM_REG_SIZE_MASK |
+					    rtype);
+	void *reg_val;
+
+	if ((rtype == KVM_REG_RISCV_FP_F) &&
+	    riscv_isa_extension_available(vcpu->arch.isa, f)) {
+		if (KVM_REG_SIZE(reg->id) != sizeof(u32))
+			return -EINVAL;
+		if (reg_num == KVM_REG_RISCV_FP_F_REG(fcsr))
+			reg_val = &cntx->fp.f.fcsr;
+		else if ((KVM_REG_RISCV_FP_F_REG(f[0]) <= reg_num) &&
+			  reg_num <= KVM_REG_RISCV_FP_F_REG(f[31]))
+			reg_val = &cntx->fp.f.f[reg_num];
+		else
+			return -EINVAL;
+	} else if ((rtype == KVM_REG_RISCV_FP_D) &&
+		   riscv_isa_extension_available(vcpu->arch.isa, d)) {
+		if (reg_num == KVM_REG_RISCV_FP_D_REG(fcsr)) {
+			if (KVM_REG_SIZE(reg->id) != sizeof(u32))
+				return -EINVAL;
+			reg_val = &cntx->fp.d.fcsr;
+		} else if ((KVM_REG_RISCV_FP_D_REG(f[0]) <= reg_num) &&
+			   reg_num <= KVM_REG_RISCV_FP_D_REG(f[31])) {
+			if (KVM_REG_SIZE(reg->id) != sizeof(u64))
+				return -EINVAL;
+			reg_val = &cntx->fp.d.f[reg_num];
+		} else
+			return -EINVAL;
+	} else
+		return -EINVAL;
+
+	if (copy_from_user(reg_val, uaddr, KVM_REG_SIZE(reg->id)))
+		return -EFAULT;
+
+	return 0;
+}
diff --git a/arch/riscv/kvm/vcpu_insn.c b/arch/riscv/kvm/vcpu_insn.c
new file mode 100644
index 000000000..0bb52761a
--- /dev/null
+++ b/arch/riscv/kvm/vcpu_insn.c
@@ -0,0 +1,751 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 Western Digital Corporation or its affiliates.
+ * Copyright (c) 2022 Ventana Micro Systems Inc.
+ */
+
+#include <linux/bitops.h>
+#include <linux/kvm_host.h>
+
+#define INSN_OPCODE_MASK	0x007c
+#define INSN_OPCODE_SHIFT	2
+#define INSN_OPCODE_SYSTEM	28
+
+#define INSN_MASK_WFI		0xffffffff
+#define INSN_MATCH_WFI		0x10500073
+
+#define INSN_MATCH_CSRRW	0x1073
+#define INSN_MASK_CSRRW		0x707f
+#define INSN_MATCH_CSRRS	0x2073
+#define INSN_MASK_CSRRS		0x707f
+#define INSN_MATCH_CSRRC	0x3073
+#define INSN_MASK_CSRRC		0x707f
+#define INSN_MATCH_CSRRWI	0x5073
+#define INSN_MASK_CSRRWI	0x707f
+#define INSN_MATCH_CSRRSI	0x6073
+#define INSN_MASK_CSRRSI	0x707f
+#define INSN_MATCH_CSRRCI	0x7073
+#define INSN_MASK_CSRRCI	0x707f
+
+#define INSN_MATCH_LB		0x3
+#define INSN_MASK_LB		0x707f
+#define INSN_MATCH_LH		0x1003
+#define INSN_MASK_LH		0x707f
+#define INSN_MATCH_LW		0x2003
+#define INSN_MASK_LW		0x707f
+#define INSN_MATCH_LD		0x3003
+#define INSN_MASK_LD		0x707f
+#define INSN_MATCH_LBU		0x4003
+#define INSN_MASK_LBU		0x707f
+#define INSN_MATCH_LHU		0x5003
+#define INSN_MASK_LHU		0x707f
+#define INSN_MATCH_LWU		0x6003
+#define INSN_MASK_LWU		0x707f
+#define INSN_MATCH_SB		0x23
+#define INSN_MASK_SB		0x707f
+#define INSN_MATCH_SH		0x1023
+#define INSN_MASK_SH		0x707f
+#define INSN_MATCH_SW		0x2023
+#define INSN_MASK_SW		0x707f
+#define INSN_MATCH_SD		0x3023
+#define INSN_MASK_SD		0x707f
+
+#define INSN_MATCH_C_LD		0x6000
+#define INSN_MASK_C_LD		0xe003
+#define INSN_MATCH_C_SD		0xe000
+#define INSN_MASK_C_SD		0xe003
+#define INSN_MATCH_C_LW		0x4000
+#define INSN_MASK_C_LW		0xe003
+#define INSN_MATCH_C_SW		0xc000
+#define INSN_MASK_C_SW		0xe003
+#define INSN_MATCH_C_LDSP	0x6002
+#define INSN_MASK_C_LDSP	0xe003
+#define INSN_MATCH_C_SDSP	0xe002
+#define INSN_MASK_C_SDSP	0xe003
+#define INSN_MATCH_C_LWSP	0x4002
+#define INSN_MASK_C_LWSP	0xe003
+#define INSN_MATCH_C_SWSP	0xc002
+#define INSN_MASK_C_SWSP	0xe003
+
+#define INSN_16BIT_MASK		0x3
+
+#define INSN_IS_16BIT(insn)	(((insn) & INSN_16BIT_MASK) != INSN_16BIT_MASK)
+
+#define INSN_LEN(insn)		(INSN_IS_16BIT(insn) ? 2 : 4)
+
+#ifdef CONFIG_64BIT
+#define LOG_REGBYTES		3
+#else
+#define LOG_REGBYTES		2
+#endif
+#define REGBYTES		(1 << LOG_REGBYTES)
+
+#define SH_RD			7
+#define SH_RS1			15
+#define SH_RS2			20
+#define SH_RS2C			2
+#define MASK_RX			0x1f
+
+#define RV_X(x, s, n)		(((x) >> (s)) & ((1 << (n)) - 1))
+#define RVC_LW_IMM(x)		((RV_X(x, 6, 1) << 2) | \
+				 (RV_X(x, 10, 3) << 3) | \
+				 (RV_X(x, 5, 1) << 6))
+#define RVC_LD_IMM(x)		((RV_X(x, 10, 3) << 3) | \
+				 (RV_X(x, 5, 2) << 6))
+#define RVC_LWSP_IMM(x)		((RV_X(x, 4, 3) << 2) | \
+				 (RV_X(x, 12, 1) << 5) | \
+				 (RV_X(x, 2, 2) << 6))
+#define RVC_LDSP_IMM(x)		((RV_X(x, 5, 2) << 3) | \
+				 (RV_X(x, 12, 1) << 5) | \
+				 (RV_X(x, 2, 3) << 6))
+#define RVC_SWSP_IMM(x)		((RV_X(x, 9, 4) << 2) | \
+				 (RV_X(x, 7, 2) << 6))
+#define RVC_SDSP_IMM(x)		((RV_X(x, 10, 3) << 3) | \
+				 (RV_X(x, 7, 3) << 6))
+#define RVC_RS1S(insn)		(8 + RV_X(insn, SH_RD, 3))
+#define RVC_RS2S(insn)		(8 + RV_X(insn, SH_RS2C, 3))
+#define RVC_RS2(insn)		RV_X(insn, SH_RS2C, 5)
+
+#define SHIFT_RIGHT(x, y)		\
+	((y) < 0 ? ((x) << -(y)) : ((x) >> (y)))
+
+#define REG_MASK			\
+	((1 << (5 + LOG_REGBYTES)) - (1 << LOG_REGBYTES))
+
+#define REG_OFFSET(insn, pos)		\
+	(SHIFT_RIGHT((insn), (pos) - LOG_REGBYTES) & REG_MASK)
+
+#define REG_PTR(insn, pos, regs)	\
+	((ulong *)((ulong)(regs) + REG_OFFSET(insn, pos)))
+
+#define GET_FUNCT3(insn)	(((insn) >> 12) & 7)
+
+#define GET_RS1(insn, regs)	(*REG_PTR(insn, SH_RS1, regs))
+#define GET_RS2(insn, regs)	(*REG_PTR(insn, SH_RS2, regs))
+#define GET_RS1S(insn, regs)	(*REG_PTR(RVC_RS1S(insn), 0, regs))
+#define GET_RS2S(insn, regs)	(*REG_PTR(RVC_RS2S(insn), 0, regs))
+#define GET_RS2C(insn, regs)	(*REG_PTR(insn, SH_RS2C, regs))
+#define GET_SP(regs)		(*REG_PTR(2, 0, regs))
+#define SET_RD(insn, regs, val)	(*REG_PTR(insn, SH_RD, regs) = (val))
+#define IMM_I(insn)		((s32)(insn) >> 20)
+#define IMM_S(insn)		(((s32)(insn) >> 25 << 5) | \
+				 (s32)(((insn) >> 7) & 0x1f))
+
+struct insn_func {
+	unsigned long mask;
+	unsigned long match;
+	/*
+	 * Possible return values are as follows:
+	 * 1) Returns < 0 for error case
+	 * 2) Returns 0 for exit to user-space
+	 * 3) Returns 1 to continue with next sepc
+	 * 4) Returns 2 to continue with same sepc
+	 * 5) Returns 3 to inject illegal instruction trap and continue
+	 * 6) Returns 4 to inject virtual instruction trap and continue
+	 *
+	 * Use enum kvm_insn_return for return values
+	 */
+	int (*func)(struct kvm_vcpu *vcpu, struct kvm_run *run, ulong insn);
+};
+
+static int truly_illegal_insn(struct kvm_vcpu *vcpu, struct kvm_run *run,
+			      ulong insn)
+{
+	struct kvm_cpu_trap utrap = { 0 };
+
+	/* Redirect trap to Guest VCPU */
+	utrap.sepc = vcpu->arch.guest_context.sepc;
+	utrap.scause = EXC_INST_ILLEGAL;
+	utrap.stval = insn;
+	utrap.htval = 0;
+	utrap.htinst = 0;
+	kvm_riscv_vcpu_trap_redirect(vcpu, &utrap);
+
+	return 1;
+}
+
+static int truly_virtual_insn(struct kvm_vcpu *vcpu, struct kvm_run *run,
+			      ulong insn)
+{
+	struct kvm_cpu_trap utrap = { 0 };
+
+	/* Redirect trap to Guest VCPU */
+	utrap.sepc = vcpu->arch.guest_context.sepc;
+	utrap.scause = EXC_VIRTUAL_INST_FAULT;
+	utrap.stval = insn;
+	utrap.htval = 0;
+	utrap.htinst = 0;
+	kvm_riscv_vcpu_trap_redirect(vcpu, &utrap);
+
+	return 1;
+}
+
+/**
+ * kvm_riscv_vcpu_wfi -- Emulate wait for interrupt (WFI) behaviour
+ *
+ * @vcpu: The VCPU pointer
+ */
+void kvm_riscv_vcpu_wfi(struct kvm_vcpu *vcpu)
+{
+	if (!kvm_arch_vcpu_runnable(vcpu)) {
+		kvm_vcpu_srcu_read_unlock(vcpu);
+		kvm_vcpu_halt(vcpu);
+		kvm_vcpu_srcu_read_lock(vcpu);
+	}
+}
+
+static int wfi_insn(struct kvm_vcpu *vcpu, struct kvm_run *run, ulong insn)
+{
+	vcpu->stat.wfi_exit_stat++;
+	kvm_riscv_vcpu_wfi(vcpu);
+	return KVM_INSN_CONTINUE_NEXT_SEPC;
+}
+
+struct csr_func {
+	unsigned int base;
+	unsigned int count;
+	/*
+	 * Possible return values are as same as "func" callback in
+	 * "struct insn_func".
+	 */
+	int (*func)(struct kvm_vcpu *vcpu, unsigned int csr_num,
+		    unsigned long *val, unsigned long new_val,
+		    unsigned long wr_mask);
+};
+
+static const struct csr_func csr_funcs[] = { };
+
+/**
+ * kvm_riscv_vcpu_csr_return -- Handle CSR read/write after user space
+ *				emulation or in-kernel emulation
+ *
+ * @vcpu: The VCPU pointer
+ * @run:  The VCPU run struct containing the CSR data
+ *
+ * Returns > 0 upon failure and 0 upon success
+ */
+int kvm_riscv_vcpu_csr_return(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	ulong insn;
+
+	if (vcpu->arch.csr_decode.return_handled)
+		return 0;
+	vcpu->arch.csr_decode.return_handled = 1;
+
+	/* Update destination register for CSR reads */
+	insn = vcpu->arch.csr_decode.insn;
+	if ((insn >> SH_RD) & MASK_RX)
+		SET_RD(insn, &vcpu->arch.guest_context,
+		       run->riscv_csr.ret_value);
+
+	/* Move to next instruction */
+	vcpu->arch.guest_context.sepc += INSN_LEN(insn);
+
+	return 0;
+}
+
+static int csr_insn(struct kvm_vcpu *vcpu, struct kvm_run *run, ulong insn)
+{
+	int i, rc = KVM_INSN_ILLEGAL_TRAP;
+	unsigned int csr_num = insn >> SH_RS2;
+	unsigned int rs1_num = (insn >> SH_RS1) & MASK_RX;
+	ulong rs1_val = GET_RS1(insn, &vcpu->arch.guest_context);
+	const struct csr_func *tcfn, *cfn = NULL;
+	ulong val = 0, wr_mask = 0, new_val = 0;
+
+	/* Decode the CSR instruction */
+	switch (GET_FUNCT3(insn)) {
+	case GET_FUNCT3(INSN_MATCH_CSRRW):
+		wr_mask = -1UL;
+		new_val = rs1_val;
+		break;
+	case GET_FUNCT3(INSN_MATCH_CSRRS):
+		wr_mask = rs1_val;
+		new_val = -1UL;
+		break;
+	case GET_FUNCT3(INSN_MATCH_CSRRC):
+		wr_mask = rs1_val;
+		new_val = 0;
+		break;
+	case GET_FUNCT3(INSN_MATCH_CSRRWI):
+		wr_mask = -1UL;
+		new_val = rs1_num;
+		break;
+	case GET_FUNCT3(INSN_MATCH_CSRRSI):
+		wr_mask = rs1_num;
+		new_val = -1UL;
+		break;
+	case GET_FUNCT3(INSN_MATCH_CSRRCI):
+		wr_mask = rs1_num;
+		new_val = 0;
+		break;
+	default:
+		return rc;
+	}
+
+	/* Save instruction decode info */
+	vcpu->arch.csr_decode.insn = insn;
+	vcpu->arch.csr_decode.return_handled = 0;
+
+	/* Update CSR details in kvm_run struct */
+	run->riscv_csr.csr_num = csr_num;
+	run->riscv_csr.new_value = new_val;
+	run->riscv_csr.write_mask = wr_mask;
+	run->riscv_csr.ret_value = 0;
+
+	/* Find in-kernel CSR function */
+	for (i = 0; i < ARRAY_SIZE(csr_funcs); i++) {
+		tcfn = &csr_funcs[i];
+		if ((tcfn->base <= csr_num) &&
+		    (csr_num < (tcfn->base + tcfn->count))) {
+			cfn = tcfn;
+			break;
+		}
+	}
+
+	/* First try in-kernel CSR emulation */
+	if (cfn && cfn->func) {
+		rc = cfn->func(vcpu, csr_num, &val, new_val, wr_mask);
+		if (rc > KVM_INSN_EXIT_TO_USER_SPACE) {
+			if (rc == KVM_INSN_CONTINUE_NEXT_SEPC) {
+				run->riscv_csr.ret_value = val;
+				vcpu->stat.csr_exit_kernel++;
+				kvm_riscv_vcpu_csr_return(vcpu, run);
+				rc = KVM_INSN_CONTINUE_SAME_SEPC;
+			}
+			return rc;
+		}
+	}
+
+	/* Exit to user-space for CSR emulation */
+	if (rc <= KVM_INSN_EXIT_TO_USER_SPACE) {
+		vcpu->stat.csr_exit_user++;
+		run->exit_reason = KVM_EXIT_RISCV_CSR;
+	}
+
+	return rc;
+}
+
+static const struct insn_func system_opcode_funcs[] = {
+	{
+		.mask  = INSN_MASK_CSRRW,
+		.match = INSN_MATCH_CSRRW,
+		.func  = csr_insn,
+	},
+	{
+		.mask  = INSN_MASK_CSRRS,
+		.match = INSN_MATCH_CSRRS,
+		.func  = csr_insn,
+	},
+	{
+		.mask  = INSN_MASK_CSRRC,
+		.match = INSN_MATCH_CSRRC,
+		.func  = csr_insn,
+	},
+	{
+		.mask  = INSN_MASK_CSRRWI,
+		.match = INSN_MATCH_CSRRWI,
+		.func  = csr_insn,
+	},
+	{
+		.mask  = INSN_MASK_CSRRSI,
+		.match = INSN_MATCH_CSRRSI,
+		.func  = csr_insn,
+	},
+	{
+		.mask  = INSN_MASK_CSRRCI,
+		.match = INSN_MATCH_CSRRCI,
+		.func  = csr_insn,
+	},
+	{
+		.mask  = INSN_MASK_WFI,
+		.match = INSN_MATCH_WFI,
+		.func  = wfi_insn,
+	},
+};
+
+static int system_opcode_insn(struct kvm_vcpu *vcpu, struct kvm_run *run,
+			      ulong insn)
+{
+	int i, rc = KVM_INSN_ILLEGAL_TRAP;
+	const struct insn_func *ifn;
+
+	for (i = 0; i < ARRAY_SIZE(system_opcode_funcs); i++) {
+		ifn = &system_opcode_funcs[i];
+		if ((insn & ifn->mask) == ifn->match) {
+			rc = ifn->func(vcpu, run, insn);
+			break;
+		}
+	}
+
+	switch (rc) {
+	case KVM_INSN_ILLEGAL_TRAP:
+		return truly_illegal_insn(vcpu, run, insn);
+	case KVM_INSN_VIRTUAL_TRAP:
+		return truly_virtual_insn(vcpu, run, insn);
+	case KVM_INSN_CONTINUE_NEXT_SEPC:
+		vcpu->arch.guest_context.sepc += INSN_LEN(insn);
+		break;
+	default:
+		break;
+	}
+
+	return (rc <= 0) ? rc : 1;
+}
+
+/**
+ * kvm_riscv_vcpu_virtual_insn -- Handle virtual instruction trap
+ *
+ * @vcpu: The VCPU pointer
+ * @run:  The VCPU run struct containing the mmio data
+ * @trap: Trap details
+ *
+ * Returns > 0 to continue run-loop
+ * Returns   0 to exit run-loop and handle in user-space.
+ * Returns < 0 to report failure and exit run-loop
+ */
+int kvm_riscv_vcpu_virtual_insn(struct kvm_vcpu *vcpu, struct kvm_run *run,
+				struct kvm_cpu_trap *trap)
+{
+	unsigned long insn = trap->stval;
+	struct kvm_cpu_trap utrap = { 0 };
+	struct kvm_cpu_context *ct;
+
+	if (unlikely(INSN_IS_16BIT(insn))) {
+		if (insn == 0) {
+			ct = &vcpu->arch.guest_context;
+			insn = kvm_riscv_vcpu_unpriv_read(vcpu, true,
+							  ct->sepc,
+							  &utrap);
+			if (utrap.scause) {
+				utrap.sepc = ct->sepc;
+				kvm_riscv_vcpu_trap_redirect(vcpu, &utrap);
+				return 1;
+			}
+		}
+		if (INSN_IS_16BIT(insn))
+			return truly_illegal_insn(vcpu, run, insn);
+	}
+
+	switch ((insn & INSN_OPCODE_MASK) >> INSN_OPCODE_SHIFT) {
+	case INSN_OPCODE_SYSTEM:
+		return system_opcode_insn(vcpu, run, insn);
+	default:
+		return truly_illegal_insn(vcpu, run, insn);
+	}
+}
+
+/**
+ * kvm_riscv_vcpu_mmio_load -- Emulate MMIO load instruction
+ *
+ * @vcpu: The VCPU pointer
+ * @run:  The VCPU run struct containing the mmio data
+ * @fault_addr: Guest physical address to load
+ * @htinst: Transformed encoding of the load instruction
+ *
+ * Returns > 0 to continue run-loop
+ * Returns   0 to exit run-loop and handle in user-space.
+ * Returns < 0 to report failure and exit run-loop
+ */
+int kvm_riscv_vcpu_mmio_load(struct kvm_vcpu *vcpu, struct kvm_run *run,
+			     unsigned long fault_addr,
+			     unsigned long htinst)
+{
+	u8 data_buf[8];
+	unsigned long insn;
+	int shift = 0, len = 0, insn_len = 0;
+	struct kvm_cpu_trap utrap = { 0 };
+	struct kvm_cpu_context *ct = &vcpu->arch.guest_context;
+
+	/* Determine trapped instruction */
+	if (htinst & 0x1) {
+		/*
+		 * Bit[0] == 1 implies trapped instruction value is
+		 * transformed instruction or custom instruction.
+		 */
+		insn = htinst | INSN_16BIT_MASK;
+		insn_len = (htinst & BIT(1)) ? INSN_LEN(insn) : 2;
+	} else {
+		/*
+		 * Bit[0] == 0 implies trapped instruction value is
+		 * zero or special value.
+		 */
+		insn = kvm_riscv_vcpu_unpriv_read(vcpu, true, ct->sepc,
+						  &utrap);
+		if (utrap.scause) {
+			/* Redirect trap if we failed to read instruction */
+			utrap.sepc = ct->sepc;
+			kvm_riscv_vcpu_trap_redirect(vcpu, &utrap);
+			return 1;
+		}
+		insn_len = INSN_LEN(insn);
+	}
+
+	/* Decode length of MMIO and shift */
+	if ((insn & INSN_MASK_LW) == INSN_MATCH_LW) {
+		len = 4;
+		shift = 8 * (sizeof(ulong) - len);
+	} else if ((insn & INSN_MASK_LB) == INSN_MATCH_LB) {
+		len = 1;
+		shift = 8 * (sizeof(ulong) - len);
+	} else if ((insn & INSN_MASK_LBU) == INSN_MATCH_LBU) {
+		len = 1;
+		shift = 8 * (sizeof(ulong) - len);
+#ifdef CONFIG_64BIT
+	} else if ((insn & INSN_MASK_LD) == INSN_MATCH_LD) {
+		len = 8;
+		shift = 8 * (sizeof(ulong) - len);
+	} else if ((insn & INSN_MASK_LWU) == INSN_MATCH_LWU) {
+		len = 4;
+#endif
+	} else if ((insn & INSN_MASK_LH) == INSN_MATCH_LH) {
+		len = 2;
+		shift = 8 * (sizeof(ulong) - len);
+	} else if ((insn & INSN_MASK_LHU) == INSN_MATCH_LHU) {
+		len = 2;
+#ifdef CONFIG_64BIT
+	} else if ((insn & INSN_MASK_C_LD) == INSN_MATCH_C_LD) {
+		len = 8;
+		shift = 8 * (sizeof(ulong) - len);
+		insn = RVC_RS2S(insn) << SH_RD;
+	} else if ((insn & INSN_MASK_C_LDSP) == INSN_MATCH_C_LDSP &&
+		   ((insn >> SH_RD) & 0x1f)) {
+		len = 8;
+		shift = 8 * (sizeof(ulong) - len);
+#endif
+	} else if ((insn & INSN_MASK_C_LW) == INSN_MATCH_C_LW) {
+		len = 4;
+		shift = 8 * (sizeof(ulong) - len);
+		insn = RVC_RS2S(insn) << SH_RD;
+	} else if ((insn & INSN_MASK_C_LWSP) == INSN_MATCH_C_LWSP &&
+		   ((insn >> SH_RD) & 0x1f)) {
+		len = 4;
+		shift = 8 * (sizeof(ulong) - len);
+	} else {
+		return -EOPNOTSUPP;
+	}
+
+	/* Fault address should be aligned to length of MMIO */
+	if (fault_addr & (len - 1))
+		return -EIO;
+
+	/* Save instruction decode info */
+	vcpu->arch.mmio_decode.insn = insn;
+	vcpu->arch.mmio_decode.insn_len = insn_len;
+	vcpu->arch.mmio_decode.shift = shift;
+	vcpu->arch.mmio_decode.len = len;
+	vcpu->arch.mmio_decode.return_handled = 0;
+
+	/* Update MMIO details in kvm_run struct */
+	run->mmio.is_write = false;
+	run->mmio.phys_addr = fault_addr;
+	run->mmio.len = len;
+
+	/* Try to handle MMIO access in the kernel */
+	if (!kvm_io_bus_read(vcpu, KVM_MMIO_BUS, fault_addr, len, data_buf)) {
+		/* Successfully handled MMIO access in the kernel so resume */
+		memcpy(run->mmio.data, data_buf, len);
+		vcpu->stat.mmio_exit_kernel++;
+		kvm_riscv_vcpu_mmio_return(vcpu, run);
+		return 1;
+	}
+
+	/* Exit to userspace for MMIO emulation */
+	vcpu->stat.mmio_exit_user++;
+	run->exit_reason = KVM_EXIT_MMIO;
+
+	return 0;
+}
+
+/**
+ * kvm_riscv_vcpu_mmio_store -- Emulate MMIO store instruction
+ *
+ * @vcpu: The VCPU pointer
+ * @run:  The VCPU run struct containing the mmio data
+ * @fault_addr: Guest physical address to store
+ * @htinst: Transformed encoding of the store instruction
+ *
+ * Returns > 0 to continue run-loop
+ * Returns   0 to exit run-loop and handle in user-space.
+ * Returns < 0 to report failure and exit run-loop
+ */
+int kvm_riscv_vcpu_mmio_store(struct kvm_vcpu *vcpu, struct kvm_run *run,
+			      unsigned long fault_addr,
+			      unsigned long htinst)
+{
+	u8 data8;
+	u16 data16;
+	u32 data32;
+	u64 data64;
+	ulong data;
+	unsigned long insn;
+	int len = 0, insn_len = 0;
+	struct kvm_cpu_trap utrap = { 0 };
+	struct kvm_cpu_context *ct = &vcpu->arch.guest_context;
+
+	/* Determine trapped instruction */
+	if (htinst & 0x1) {
+		/*
+		 * Bit[0] == 1 implies trapped instruction value is
+		 * transformed instruction or custom instruction.
+		 */
+		insn = htinst | INSN_16BIT_MASK;
+		insn_len = (htinst & BIT(1)) ? INSN_LEN(insn) : 2;
+	} else {
+		/*
+		 * Bit[0] == 0 implies trapped instruction value is
+		 * zero or special value.
+		 */
+		insn = kvm_riscv_vcpu_unpriv_read(vcpu, true, ct->sepc,
+						  &utrap);
+		if (utrap.scause) {
+			/* Redirect trap if we failed to read instruction */
+			utrap.sepc = ct->sepc;
+			kvm_riscv_vcpu_trap_redirect(vcpu, &utrap);
+			return 1;
+		}
+		insn_len = INSN_LEN(insn);
+	}
+
+	data = GET_RS2(insn, &vcpu->arch.guest_context);
+	data8 = data16 = data32 = data64 = data;
+
+	if ((insn & INSN_MASK_SW) == INSN_MATCH_SW) {
+		len = 4;
+	} else if ((insn & INSN_MASK_SB) == INSN_MATCH_SB) {
+		len = 1;
+#ifdef CONFIG_64BIT
+	} else if ((insn & INSN_MASK_SD) == INSN_MATCH_SD) {
+		len = 8;
+#endif
+	} else if ((insn & INSN_MASK_SH) == INSN_MATCH_SH) {
+		len = 2;
+#ifdef CONFIG_64BIT
+	} else if ((insn & INSN_MASK_C_SD) == INSN_MATCH_C_SD) {
+		len = 8;
+		data64 = GET_RS2S(insn, &vcpu->arch.guest_context);
+	} else if ((insn & INSN_MASK_C_SDSP) == INSN_MATCH_C_SDSP &&
+		   ((insn >> SH_RD) & 0x1f)) {
+		len = 8;
+		data64 = GET_RS2C(insn, &vcpu->arch.guest_context);
+#endif
+	} else if ((insn & INSN_MASK_C_SW) == INSN_MATCH_C_SW) {
+		len = 4;
+		data32 = GET_RS2S(insn, &vcpu->arch.guest_context);
+	} else if ((insn & INSN_MASK_C_SWSP) == INSN_MATCH_C_SWSP &&
+		   ((insn >> SH_RD) & 0x1f)) {
+		len = 4;
+		data32 = GET_RS2C(insn, &vcpu->arch.guest_context);
+	} else {
+		return -EOPNOTSUPP;
+	}
+
+	/* Fault address should be aligned to length of MMIO */
+	if (fault_addr & (len - 1))
+		return -EIO;
+
+	/* Save instruction decode info */
+	vcpu->arch.mmio_decode.insn = insn;
+	vcpu->arch.mmio_decode.insn_len = insn_len;
+	vcpu->arch.mmio_decode.shift = 0;
+	vcpu->arch.mmio_decode.len = len;
+	vcpu->arch.mmio_decode.return_handled = 0;
+
+	/* Copy data to kvm_run instance */
+	switch (len) {
+	case 1:
+		*((u8 *)run->mmio.data) = data8;
+		break;
+	case 2:
+		*((u16 *)run->mmio.data) = data16;
+		break;
+	case 4:
+		*((u32 *)run->mmio.data) = data32;
+		break;
+	case 8:
+		*((u64 *)run->mmio.data) = data64;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	/* Update MMIO details in kvm_run struct */
+	run->mmio.is_write = true;
+	run->mmio.phys_addr = fault_addr;
+	run->mmio.len = len;
+
+	/* Try to handle MMIO access in the kernel */
+	if (!kvm_io_bus_write(vcpu, KVM_MMIO_BUS,
+			      fault_addr, len, run->mmio.data)) {
+		/* Successfully handled MMIO access in the kernel so resume */
+		vcpu->stat.mmio_exit_kernel++;
+		kvm_riscv_vcpu_mmio_return(vcpu, run);
+		return 1;
+	}
+
+	/* Exit to userspace for MMIO emulation */
+	vcpu->stat.mmio_exit_user++;
+	run->exit_reason = KVM_EXIT_MMIO;
+
+	return 0;
+}
+
+/**
+ * kvm_riscv_vcpu_mmio_return -- Handle MMIO loads after user space emulation
+ *			     or in-kernel IO emulation
+ *
+ * @vcpu: The VCPU pointer
+ * @run:  The VCPU run struct containing the mmio data
+ */
+int kvm_riscv_vcpu_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	u8 data8;
+	u16 data16;
+	u32 data32;
+	u64 data64;
+	ulong insn;
+	int len, shift;
+
+	if (vcpu->arch.mmio_decode.return_handled)
+		return 0;
+
+	vcpu->arch.mmio_decode.return_handled = 1;
+	insn = vcpu->arch.mmio_decode.insn;
+
+	if (run->mmio.is_write)
+		goto done;
+
+	len = vcpu->arch.mmio_decode.len;
+	shift = vcpu->arch.mmio_decode.shift;
+
+	switch (len) {
+	case 1:
+		data8 = *((u8 *)run->mmio.data);
+		SET_RD(insn, &vcpu->arch.guest_context,
+			(ulong)data8 << shift >> shift);
+		break;
+	case 2:
+		data16 = *((u16 *)run->mmio.data);
+		SET_RD(insn, &vcpu->arch.guest_context,
+			(ulong)data16 << shift >> shift);
+		break;
+	case 4:
+		data32 = *((u32 *)run->mmio.data);
+		SET_RD(insn, &vcpu->arch.guest_context,
+			(ulong)data32 << shift >> shift);
+		break;
+	case 8:
+		data64 = *((u64 *)run->mmio.data);
+		SET_RD(insn, &vcpu->arch.guest_context,
+			(ulong)data64 << shift >> shift);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+done:
+	/* Move to next instruction */
+	vcpu->arch.guest_context.sepc += vcpu->arch.mmio_decode.insn_len;
+
+	return 0;
+}
diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c
new file mode 100644
index 000000000..f96991d23
--- /dev/null
+++ b/arch/riscv/kvm/vcpu_sbi.c
@@ -0,0 +1,180 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2019 Western Digital Corporation or its affiliates.
+ *
+ * Authors:
+ *     Atish Patra <atish.patra@wdc.com>
+ */
+
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/kvm_host.h>
+#include <asm/sbi.h>
+#include <asm/kvm_vcpu_sbi.h>
+
+static int kvm_linux_err_map_sbi(int err)
+{
+	switch (err) {
+	case 0:
+		return SBI_SUCCESS;
+	case -EPERM:
+		return SBI_ERR_DENIED;
+	case -EINVAL:
+		return SBI_ERR_INVALID_PARAM;
+	case -EFAULT:
+		return SBI_ERR_INVALID_ADDRESS;
+	case -EOPNOTSUPP:
+		return SBI_ERR_NOT_SUPPORTED;
+	case -EALREADY:
+		return SBI_ERR_ALREADY_AVAILABLE;
+	default:
+		return SBI_ERR_FAILURE;
+	};
+}
+
+#ifndef CONFIG_RISCV_SBI_V01
+static const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_v01 = {
+	.extid_start = -1UL,
+	.extid_end = -1UL,
+	.handler = NULL,
+};
+#endif
+
+static const struct kvm_vcpu_sbi_extension *sbi_ext[] = {
+	&vcpu_sbi_ext_v01,
+	&vcpu_sbi_ext_base,
+	&vcpu_sbi_ext_time,
+	&vcpu_sbi_ext_ipi,
+	&vcpu_sbi_ext_rfence,
+	&vcpu_sbi_ext_srst,
+	&vcpu_sbi_ext_hsm,
+	&vcpu_sbi_ext_experimental,
+	&vcpu_sbi_ext_vendor,
+};
+
+void kvm_riscv_vcpu_sbi_forward(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	struct kvm_cpu_context *cp = &vcpu->arch.guest_context;
+
+	vcpu->arch.sbi_context.return_handled = 0;
+	vcpu->stat.ecall_exit_stat++;
+	run->exit_reason = KVM_EXIT_RISCV_SBI;
+	run->riscv_sbi.extension_id = cp->a7;
+	run->riscv_sbi.function_id = cp->a6;
+	run->riscv_sbi.args[0] = cp->a0;
+	run->riscv_sbi.args[1] = cp->a1;
+	run->riscv_sbi.args[2] = cp->a2;
+	run->riscv_sbi.args[3] = cp->a3;
+	run->riscv_sbi.args[4] = cp->a4;
+	run->riscv_sbi.args[5] = cp->a5;
+	run->riscv_sbi.ret[0] = cp->a0;
+	run->riscv_sbi.ret[1] = cp->a1;
+}
+
+void kvm_riscv_vcpu_sbi_system_reset(struct kvm_vcpu *vcpu,
+				     struct kvm_run *run,
+				     u32 type, u64 reason)
+{
+	unsigned long i;
+	struct kvm_vcpu *tmp;
+
+	kvm_for_each_vcpu(i, tmp, vcpu->kvm)
+		tmp->arch.power_off = true;
+	kvm_make_all_cpus_request(vcpu->kvm, KVM_REQ_SLEEP);
+
+	memset(&run->system_event, 0, sizeof(run->system_event));
+	run->system_event.type = type;
+	run->system_event.ndata = 1;
+	run->system_event.data[0] = reason;
+	run->exit_reason = KVM_EXIT_SYSTEM_EVENT;
+}
+
+int kvm_riscv_vcpu_sbi_return(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	struct kvm_cpu_context *cp = &vcpu->arch.guest_context;
+
+	/* Handle SBI return only once */
+	if (vcpu->arch.sbi_context.return_handled)
+		return 0;
+	vcpu->arch.sbi_context.return_handled = 1;
+
+	/* Update return values */
+	cp->a0 = run->riscv_sbi.ret[0];
+	cp->a1 = run->riscv_sbi.ret[1];
+
+	/* Move to next instruction */
+	vcpu->arch.guest_context.sepc += 4;
+
+	return 0;
+}
+
+const struct kvm_vcpu_sbi_extension *kvm_vcpu_sbi_find_ext(unsigned long extid)
+{
+	int i = 0;
+
+	for (i = 0; i < ARRAY_SIZE(sbi_ext); i++) {
+		if (sbi_ext[i]->extid_start <= extid &&
+		    sbi_ext[i]->extid_end >= extid)
+			return sbi_ext[i];
+	}
+
+	return NULL;
+}
+
+int kvm_riscv_vcpu_sbi_ecall(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	int ret = 1;
+	bool next_sepc = true;
+	bool userspace_exit = false;
+	struct kvm_cpu_context *cp = &vcpu->arch.guest_context;
+	const struct kvm_vcpu_sbi_extension *sbi_ext;
+	struct kvm_cpu_trap utrap = { 0 };
+	unsigned long out_val = 0;
+	bool ext_is_v01 = false;
+
+	sbi_ext = kvm_vcpu_sbi_find_ext(cp->a7);
+	if (sbi_ext && sbi_ext->handler) {
+#ifdef CONFIG_RISCV_SBI_V01
+		if (cp->a7 >= SBI_EXT_0_1_SET_TIMER &&
+		    cp->a7 <= SBI_EXT_0_1_SHUTDOWN)
+			ext_is_v01 = true;
+#endif
+		ret = sbi_ext->handler(vcpu, run, &out_val, &utrap, &userspace_exit);
+	} else {
+		/* Return error for unsupported SBI calls */
+		cp->a0 = SBI_ERR_NOT_SUPPORTED;
+		goto ecall_done;
+	}
+
+	/* Handle special error cases i.e trap, exit or userspace forward */
+	if (utrap.scause) {
+		/* No need to increment sepc or exit ioctl loop */
+		ret = 1;
+		utrap.sepc = cp->sepc;
+		kvm_riscv_vcpu_trap_redirect(vcpu, &utrap);
+		next_sepc = false;
+		goto ecall_done;
+	}
+
+	/* Exit ioctl loop or Propagate the error code the guest */
+	if (userspace_exit) {
+		next_sepc = false;
+		ret = 0;
+	} else {
+		/**
+		 * SBI extension handler always returns an Linux error code. Convert
+		 * it to the SBI specific error code that can be propagated the SBI
+		 * caller.
+		 */
+		ret = kvm_linux_err_map_sbi(ret);
+		cp->a0 = ret;
+		ret = 1;
+	}
+ecall_done:
+	if (next_sepc)
+		cp->sepc += 4;
+	if (!ext_is_v01)
+		cp->a1 = out_val;
+
+	return ret;
+}
diff --git a/arch/riscv/kvm/vcpu_sbi_base.c b/arch/riscv/kvm/vcpu_sbi_base.c
new file mode 100644
index 000000000..48f431091
--- /dev/null
+++ b/arch/riscv/kvm/vcpu_sbi_base.c
@@ -0,0 +1,100 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2021 Western Digital Corporation or its affiliates.
+ *
+ * Authors:
+ *     Atish Patra <atish.patra@wdc.com>
+ */
+
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/kvm_host.h>
+#include <linux/version.h>
+#include <asm/csr.h>
+#include <asm/sbi.h>
+#include <asm/kvm_vcpu_timer.h>
+#include <asm/kvm_vcpu_sbi.h>
+
+static int kvm_sbi_ext_base_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
+				    unsigned long *out_val,
+				    struct kvm_cpu_trap *trap, bool *exit)
+{
+	int ret = 0;
+	struct kvm_cpu_context *cp = &vcpu->arch.guest_context;
+	struct sbiret ecall_ret;
+
+	switch (cp->a6) {
+	case SBI_EXT_BASE_GET_SPEC_VERSION:
+		*out_val = (KVM_SBI_VERSION_MAJOR <<
+			    SBI_SPEC_VERSION_MAJOR_SHIFT) |
+			    KVM_SBI_VERSION_MINOR;
+		break;
+	case SBI_EXT_BASE_GET_IMP_ID:
+		*out_val = KVM_SBI_IMPID;
+		break;
+	case SBI_EXT_BASE_GET_IMP_VERSION:
+		*out_val = LINUX_VERSION_CODE;
+		break;
+	case SBI_EXT_BASE_PROBE_EXT:
+		if ((cp->a0 >= SBI_EXT_EXPERIMENTAL_START &&
+		     cp->a0 <= SBI_EXT_EXPERIMENTAL_END) ||
+		    (cp->a0 >= SBI_EXT_VENDOR_START &&
+		     cp->a0 <= SBI_EXT_VENDOR_END)) {
+			/*
+			 * For experimental/vendor extensions
+			 * forward it to the userspace
+			 */
+			kvm_riscv_vcpu_sbi_forward(vcpu, run);
+			*exit = true;
+		} else
+			*out_val = kvm_vcpu_sbi_find_ext(cp->a0) ? 1 : 0;
+		break;
+	case SBI_EXT_BASE_GET_MVENDORID:
+	case SBI_EXT_BASE_GET_MARCHID:
+	case SBI_EXT_BASE_GET_MIMPID:
+		ecall_ret = sbi_ecall(SBI_EXT_BASE, cp->a6, 0, 0, 0, 0, 0, 0);
+		if (!ecall_ret.error)
+			*out_val = ecall_ret.value;
+		/*TODO: We are unnecessarily converting the error twice */
+		ret = sbi_err_map_linux_errno(ecall_ret.error);
+		break;
+	default:
+		ret = -EOPNOTSUPP;
+		break;
+	}
+
+	return ret;
+}
+
+const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_base = {
+	.extid_start = SBI_EXT_BASE,
+	.extid_end = SBI_EXT_BASE,
+	.handler = kvm_sbi_ext_base_handler,
+};
+
+static int kvm_sbi_ext_forward_handler(struct kvm_vcpu *vcpu,
+					struct kvm_run *run,
+					unsigned long *out_val,
+					struct kvm_cpu_trap *utrap,
+					bool *exit)
+{
+	/*
+	 * Both SBI experimental and vendor extensions are
+	 * unconditionally forwarded to userspace.
+	 */
+	kvm_riscv_vcpu_sbi_forward(vcpu, run);
+	*exit = true;
+	return 0;
+}
+
+const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_experimental = {
+	.extid_start = SBI_EXT_EXPERIMENTAL_START,
+	.extid_end = SBI_EXT_EXPERIMENTAL_END,
+	.handler = kvm_sbi_ext_forward_handler,
+};
+
+const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_vendor = {
+	.extid_start = SBI_EXT_VENDOR_START,
+	.extid_end = SBI_EXT_VENDOR_END,
+	.handler = kvm_sbi_ext_forward_handler,
+};
diff --git a/arch/riscv/kvm/vcpu_sbi_hsm.c b/arch/riscv/kvm/vcpu_sbi_hsm.c
new file mode 100644
index 000000000..239dec0a6
--- /dev/null
+++ b/arch/riscv/kvm/vcpu_sbi_hsm.c
@@ -0,0 +1,119 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2021 Western Digital Corporation or its affiliates.
+ *
+ * Authors:
+ *     Atish Patra <atish.patra@wdc.com>
+ */
+
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/kvm_host.h>
+#include <asm/csr.h>
+#include <asm/sbi.h>
+#include <asm/kvm_vcpu_sbi.h>
+
+static int kvm_sbi_hsm_vcpu_start(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpu_context *reset_cntx;
+	struct kvm_cpu_context *cp = &vcpu->arch.guest_context;
+	struct kvm_vcpu *target_vcpu;
+	unsigned long target_vcpuid = cp->a0;
+
+	target_vcpu = kvm_get_vcpu_by_id(vcpu->kvm, target_vcpuid);
+	if (!target_vcpu)
+		return -EINVAL;
+	if (!target_vcpu->arch.power_off)
+		return -EALREADY;
+
+	reset_cntx = &target_vcpu->arch.guest_reset_context;
+	/* start address */
+	reset_cntx->sepc = cp->a1;
+	/* target vcpu id to start */
+	reset_cntx->a0 = target_vcpuid;
+	/* private data passed from kernel */
+	reset_cntx->a1 = cp->a2;
+	kvm_make_request(KVM_REQ_VCPU_RESET, target_vcpu);
+
+	kvm_riscv_vcpu_power_on(target_vcpu);
+
+	return 0;
+}
+
+static int kvm_sbi_hsm_vcpu_stop(struct kvm_vcpu *vcpu)
+{
+	if (vcpu->arch.power_off)
+		return -EINVAL;
+
+	kvm_riscv_vcpu_power_off(vcpu);
+
+	return 0;
+}
+
+static int kvm_sbi_hsm_vcpu_get_status(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpu_context *cp = &vcpu->arch.guest_context;
+	unsigned long target_vcpuid = cp->a0;
+	struct kvm_vcpu *target_vcpu;
+
+	target_vcpu = kvm_get_vcpu_by_id(vcpu->kvm, target_vcpuid);
+	if (!target_vcpu)
+		return -EINVAL;
+	if (!target_vcpu->arch.power_off)
+		return SBI_HSM_STATE_STARTED;
+	else if (vcpu->stat.generic.blocking)
+		return SBI_HSM_STATE_SUSPENDED;
+	else
+		return SBI_HSM_STATE_STOPPED;
+}
+
+static int kvm_sbi_ext_hsm_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
+				   unsigned long *out_val,
+				   struct kvm_cpu_trap *utrap,
+				   bool *exit)
+{
+	int ret = 0;
+	struct kvm_cpu_context *cp = &vcpu->arch.guest_context;
+	struct kvm *kvm = vcpu->kvm;
+	unsigned long funcid = cp->a6;
+
+	switch (funcid) {
+	case SBI_EXT_HSM_HART_START:
+		mutex_lock(&kvm->lock);
+		ret = kvm_sbi_hsm_vcpu_start(vcpu);
+		mutex_unlock(&kvm->lock);
+		break;
+	case SBI_EXT_HSM_HART_STOP:
+		ret = kvm_sbi_hsm_vcpu_stop(vcpu);
+		break;
+	case SBI_EXT_HSM_HART_STATUS:
+		ret = kvm_sbi_hsm_vcpu_get_status(vcpu);
+		if (ret >= 0) {
+			*out_val = ret;
+			ret = 0;
+		}
+		break;
+	case SBI_EXT_HSM_HART_SUSPEND:
+		switch (cp->a0) {
+		case SBI_HSM_SUSPEND_RET_DEFAULT:
+			kvm_riscv_vcpu_wfi(vcpu);
+			break;
+		case SBI_HSM_SUSPEND_NON_RET_DEFAULT:
+			ret = -EOPNOTSUPP;
+			break;
+		default:
+			ret = -EINVAL;
+		}
+		break;
+	default:
+		ret = -EOPNOTSUPP;
+	}
+
+	return ret;
+}
+
+const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_hsm = {
+	.extid_start = SBI_EXT_HSM,
+	.extid_end = SBI_EXT_HSM,
+	.handler = kvm_sbi_ext_hsm_handler,
+};
diff --git a/arch/riscv/kvm/vcpu_sbi_replace.c b/arch/riscv/kvm/vcpu_sbi_replace.c
new file mode 100644
index 000000000..4c034d8a6
--- /dev/null
+++ b/arch/riscv/kvm/vcpu_sbi_replace.c
@@ -0,0 +1,174 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2021 Western Digital Corporation or its affiliates.
+ *
+ * Authors:
+ *     Atish Patra <atish.patra@wdc.com>
+ */
+
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/kvm_host.h>
+#include <asm/csr.h>
+#include <asm/sbi.h>
+#include <asm/kvm_vcpu_timer.h>
+#include <asm/kvm_vcpu_sbi.h>
+
+static int kvm_sbi_ext_time_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
+				    unsigned long *out_val,
+				    struct kvm_cpu_trap *utrap, bool *exit)
+{
+	int ret = 0;
+	struct kvm_cpu_context *cp = &vcpu->arch.guest_context;
+	u64 next_cycle;
+
+	if (cp->a6 != SBI_EXT_TIME_SET_TIMER)
+		return -EINVAL;
+
+#if __riscv_xlen == 32
+	next_cycle = ((u64)cp->a1 << 32) | (u64)cp->a0;
+#else
+	next_cycle = (u64)cp->a0;
+#endif
+	kvm_riscv_vcpu_timer_next_event(vcpu, next_cycle);
+
+	return ret;
+}
+
+const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_time = {
+	.extid_start = SBI_EXT_TIME,
+	.extid_end = SBI_EXT_TIME,
+	.handler = kvm_sbi_ext_time_handler,
+};
+
+static int kvm_sbi_ext_ipi_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
+				   unsigned long *out_val,
+				   struct kvm_cpu_trap *utrap, bool *exit)
+{
+	int ret = 0;
+	unsigned long i;
+	struct kvm_vcpu *tmp;
+	struct kvm_cpu_context *cp = &vcpu->arch.guest_context;
+	unsigned long hmask = cp->a0;
+	unsigned long hbase = cp->a1;
+
+	if (cp->a6 != SBI_EXT_IPI_SEND_IPI)
+		return -EINVAL;
+
+	kvm_for_each_vcpu(i, tmp, vcpu->kvm) {
+		if (hbase != -1UL) {
+			if (tmp->vcpu_id < hbase)
+				continue;
+			if (!(hmask & (1UL << (tmp->vcpu_id - hbase))))
+				continue;
+		}
+		ret = kvm_riscv_vcpu_set_interrupt(tmp, IRQ_VS_SOFT);
+		if (ret < 0)
+			break;
+	}
+
+	return ret;
+}
+
+const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_ipi = {
+	.extid_start = SBI_EXT_IPI,
+	.extid_end = SBI_EXT_IPI,
+	.handler = kvm_sbi_ext_ipi_handler,
+};
+
+static int kvm_sbi_ext_rfence_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
+				      unsigned long *out_val,
+				      struct kvm_cpu_trap *utrap, bool *exit)
+{
+	int ret = 0;
+	struct kvm_cpu_context *cp = &vcpu->arch.guest_context;
+	unsigned long hmask = cp->a0;
+	unsigned long hbase = cp->a1;
+	unsigned long funcid = cp->a6;
+
+	switch (funcid) {
+	case SBI_EXT_RFENCE_REMOTE_FENCE_I:
+		kvm_riscv_fence_i(vcpu->kvm, hbase, hmask);
+		break;
+	case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA:
+		if (cp->a2 == 0 && cp->a3 == 0)
+			kvm_riscv_hfence_vvma_all(vcpu->kvm, hbase, hmask);
+		else
+			kvm_riscv_hfence_vvma_gva(vcpu->kvm, hbase, hmask,
+						  cp->a2, cp->a3, PAGE_SHIFT);
+		break;
+	case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID:
+		if (cp->a2 == 0 && cp->a3 == 0)
+			kvm_riscv_hfence_vvma_asid_all(vcpu->kvm,
+						       hbase, hmask, cp->a4);
+		else
+			kvm_riscv_hfence_vvma_asid_gva(vcpu->kvm,
+						       hbase, hmask,
+						       cp->a2, cp->a3,
+						       PAGE_SHIFT, cp->a4);
+		break;
+	case SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA:
+	case SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA_VMID:
+	case SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA:
+	case SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA_ASID:
+		/*
+		 * Until nested virtualization is implemented, the
+		 * SBI HFENCE calls should be treated as NOPs
+		 */
+		break;
+	default:
+		ret = -EOPNOTSUPP;
+	}
+
+	return ret;
+}
+
+const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_rfence = {
+	.extid_start = SBI_EXT_RFENCE,
+	.extid_end = SBI_EXT_RFENCE,
+	.handler = kvm_sbi_ext_rfence_handler,
+};
+
+static int kvm_sbi_ext_srst_handler(struct kvm_vcpu *vcpu,
+				    struct kvm_run *run,
+				    unsigned long *out_val,
+				    struct kvm_cpu_trap *utrap, bool *exit)
+{
+	struct kvm_cpu_context *cp = &vcpu->arch.guest_context;
+	unsigned long funcid = cp->a6;
+	u32 reason = cp->a1;
+	u32 type = cp->a0;
+	int ret = 0;
+
+	switch (funcid) {
+	case SBI_EXT_SRST_RESET:
+		switch (type) {
+		case SBI_SRST_RESET_TYPE_SHUTDOWN:
+			kvm_riscv_vcpu_sbi_system_reset(vcpu, run,
+						KVM_SYSTEM_EVENT_SHUTDOWN,
+						reason);
+			*exit = true;
+			break;
+		case SBI_SRST_RESET_TYPE_COLD_REBOOT:
+		case SBI_SRST_RESET_TYPE_WARM_REBOOT:
+			kvm_riscv_vcpu_sbi_system_reset(vcpu, run,
+						KVM_SYSTEM_EVENT_RESET,
+						reason);
+			*exit = true;
+			break;
+		default:
+			ret = -EOPNOTSUPP;
+		}
+		break;
+	default:
+		ret = -EOPNOTSUPP;
+	}
+
+	return ret;
+}
+
+const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_srst = {
+	.extid_start = SBI_EXT_SRST,
+	.extid_end = SBI_EXT_SRST,
+	.handler = kvm_sbi_ext_srst_handler,
+};
diff --git a/arch/riscv/kvm/vcpu_sbi_v01.c b/arch/riscv/kvm/vcpu_sbi_v01.c
new file mode 100644
index 000000000..8a91a14e7
--- /dev/null
+++ b/arch/riscv/kvm/vcpu_sbi_v01.c
@@ -0,0 +1,118 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2021 Western Digital Corporation or its affiliates.
+ *
+ * Authors:
+ *     Atish Patra <atish.patra@wdc.com>
+ */
+
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/kvm_host.h>
+#include <asm/csr.h>
+#include <asm/sbi.h>
+#include <asm/kvm_vcpu_timer.h>
+#include <asm/kvm_vcpu_sbi.h>
+
+static int kvm_sbi_ext_v01_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
+				      unsigned long *out_val,
+				      struct kvm_cpu_trap *utrap,
+				      bool *exit)
+{
+	ulong hmask;
+	int i, ret = 0;
+	u64 next_cycle;
+	struct kvm_vcpu *rvcpu;
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_cpu_context *cp = &vcpu->arch.guest_context;
+
+	switch (cp->a7) {
+	case SBI_EXT_0_1_CONSOLE_GETCHAR:
+	case SBI_EXT_0_1_CONSOLE_PUTCHAR:
+		/*
+		 * The CONSOLE_GETCHAR/CONSOLE_PUTCHAR SBI calls cannot be
+		 * handled in kernel so we forward these to user-space
+		 */
+		kvm_riscv_vcpu_sbi_forward(vcpu, run);
+		*exit = true;
+		break;
+	case SBI_EXT_0_1_SET_TIMER:
+#if __riscv_xlen == 32
+		next_cycle = ((u64)cp->a1 << 32) | (u64)cp->a0;
+#else
+		next_cycle = (u64)cp->a0;
+#endif
+		ret = kvm_riscv_vcpu_timer_next_event(vcpu, next_cycle);
+		break;
+	case SBI_EXT_0_1_CLEAR_IPI:
+		ret = kvm_riscv_vcpu_unset_interrupt(vcpu, IRQ_VS_SOFT);
+		break;
+	case SBI_EXT_0_1_SEND_IPI:
+		if (cp->a0)
+			hmask = kvm_riscv_vcpu_unpriv_read(vcpu, false, cp->a0,
+							   utrap);
+		else
+			hmask = (1UL << atomic_read(&kvm->online_vcpus)) - 1;
+		if (utrap->scause)
+			break;
+
+		for_each_set_bit(i, &hmask, BITS_PER_LONG) {
+			rvcpu = kvm_get_vcpu_by_id(vcpu->kvm, i);
+			ret = kvm_riscv_vcpu_set_interrupt(rvcpu, IRQ_VS_SOFT);
+			if (ret < 0)
+				break;
+		}
+		break;
+	case SBI_EXT_0_1_SHUTDOWN:
+		kvm_riscv_vcpu_sbi_system_reset(vcpu, run,
+						KVM_SYSTEM_EVENT_SHUTDOWN, 0);
+		*exit = true;
+		break;
+	case SBI_EXT_0_1_REMOTE_FENCE_I:
+	case SBI_EXT_0_1_REMOTE_SFENCE_VMA:
+	case SBI_EXT_0_1_REMOTE_SFENCE_VMA_ASID:
+		if (cp->a0)
+			hmask = kvm_riscv_vcpu_unpriv_read(vcpu, false, cp->a0,
+							   utrap);
+		else
+			hmask = (1UL << atomic_read(&kvm->online_vcpus)) - 1;
+		if (utrap->scause)
+			break;
+
+		if (cp->a7 == SBI_EXT_0_1_REMOTE_FENCE_I)
+			kvm_riscv_fence_i(vcpu->kvm, 0, hmask);
+		else if (cp->a7 == SBI_EXT_0_1_REMOTE_SFENCE_VMA) {
+			if (cp->a1 == 0 && cp->a2 == 0)
+				kvm_riscv_hfence_vvma_all(vcpu->kvm,
+							  0, hmask);
+			else
+				kvm_riscv_hfence_vvma_gva(vcpu->kvm,
+							  0, hmask,
+							  cp->a1, cp->a2,
+							  PAGE_SHIFT);
+		} else {
+			if (cp->a1 == 0 && cp->a2 == 0)
+				kvm_riscv_hfence_vvma_asid_all(vcpu->kvm,
+							       0, hmask,
+							       cp->a3);
+			else
+				kvm_riscv_hfence_vvma_asid_gva(vcpu->kvm,
+							       0, hmask,
+							       cp->a1, cp->a2,
+							       PAGE_SHIFT,
+							       cp->a3);
+		}
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
+const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_v01 = {
+	.extid_start = SBI_EXT_0_1_SET_TIMER,
+	.extid_end = SBI_EXT_0_1_SHUTDOWN,
+	.handler = kvm_sbi_ext_v01_handler,
+};
diff --git a/arch/riscv/kvm/vcpu_switch.S b/arch/riscv/kvm/vcpu_switch.S
new file mode 100644
index 000000000..d74df8eb4
--- /dev/null
+++ b/arch/riscv/kvm/vcpu_switch.S
@@ -0,0 +1,408 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2019 Western Digital Corporation or its affiliates.
+ *
+ * Authors:
+ *     Anup Patel <anup.patel@wdc.com>
+ */
+
+#include <linux/linkage.h>
+#include <asm/asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/csr.h>
+
+	.text
+	.altmacro
+	.option norelax
+
+ENTRY(__kvm_riscv_switch_to)
+	/* Save Host GPRs (except A0 and T0-T6) */
+	REG_S	ra, (KVM_ARCH_HOST_RA)(a0)
+	REG_S	sp, (KVM_ARCH_HOST_SP)(a0)
+	REG_S	gp, (KVM_ARCH_HOST_GP)(a0)
+	REG_S	tp, (KVM_ARCH_HOST_TP)(a0)
+	REG_S	s0, (KVM_ARCH_HOST_S0)(a0)
+	REG_S	s1, (KVM_ARCH_HOST_S1)(a0)
+	REG_S	a1, (KVM_ARCH_HOST_A1)(a0)
+	REG_S	a2, (KVM_ARCH_HOST_A2)(a0)
+	REG_S	a3, (KVM_ARCH_HOST_A3)(a0)
+	REG_S	a4, (KVM_ARCH_HOST_A4)(a0)
+	REG_S	a5, (KVM_ARCH_HOST_A5)(a0)
+	REG_S	a6, (KVM_ARCH_HOST_A6)(a0)
+	REG_S	a7, (KVM_ARCH_HOST_A7)(a0)
+	REG_S	s2, (KVM_ARCH_HOST_S2)(a0)
+	REG_S	s3, (KVM_ARCH_HOST_S3)(a0)
+	REG_S	s4, (KVM_ARCH_HOST_S4)(a0)
+	REG_S	s5, (KVM_ARCH_HOST_S5)(a0)
+	REG_S	s6, (KVM_ARCH_HOST_S6)(a0)
+	REG_S	s7, (KVM_ARCH_HOST_S7)(a0)
+	REG_S	s8, (KVM_ARCH_HOST_S8)(a0)
+	REG_S	s9, (KVM_ARCH_HOST_S9)(a0)
+	REG_S	s10, (KVM_ARCH_HOST_S10)(a0)
+	REG_S	s11, (KVM_ARCH_HOST_S11)(a0)
+
+	/* Load Guest CSR values */
+	REG_L	t0, (KVM_ARCH_GUEST_SSTATUS)(a0)
+	REG_L	t1, (KVM_ARCH_GUEST_HSTATUS)(a0)
+	REG_L	t2, (KVM_ARCH_GUEST_SCOUNTEREN)(a0)
+	la	t4, __kvm_switch_return
+	REG_L	t5, (KVM_ARCH_GUEST_SEPC)(a0)
+
+	/* Save Host and Restore Guest SSTATUS */
+	csrrw	t0, CSR_SSTATUS, t0
+
+	/* Save Host and Restore Guest HSTATUS */
+	csrrw	t1, CSR_HSTATUS, t1
+
+	/* Save Host and Restore Guest SCOUNTEREN */
+	csrrw	t2, CSR_SCOUNTEREN, t2
+
+	/* Save Host STVEC and change it to return path */
+	csrrw	t4, CSR_STVEC, t4
+
+	/* Save Host SSCRATCH and change it to struct kvm_vcpu_arch pointer */
+	csrrw	t3, CSR_SSCRATCH, a0
+
+	/* Restore Guest SEPC */
+	csrw	CSR_SEPC, t5
+
+	/* Store Host CSR values */
+	REG_S	t0, (KVM_ARCH_HOST_SSTATUS)(a0)
+	REG_S	t1, (KVM_ARCH_HOST_HSTATUS)(a0)
+	REG_S	t2, (KVM_ARCH_HOST_SCOUNTEREN)(a0)
+	REG_S	t3, (KVM_ARCH_HOST_SSCRATCH)(a0)
+	REG_S	t4, (KVM_ARCH_HOST_STVEC)(a0)
+
+	/* Restore Guest GPRs (except A0) */
+	REG_L	ra, (KVM_ARCH_GUEST_RA)(a0)
+	REG_L	sp, (KVM_ARCH_GUEST_SP)(a0)
+	REG_L	gp, (KVM_ARCH_GUEST_GP)(a0)
+	REG_L	tp, (KVM_ARCH_GUEST_TP)(a0)
+	REG_L	t0, (KVM_ARCH_GUEST_T0)(a0)
+	REG_L	t1, (KVM_ARCH_GUEST_T1)(a0)
+	REG_L	t2, (KVM_ARCH_GUEST_T2)(a0)
+	REG_L	s0, (KVM_ARCH_GUEST_S0)(a0)
+	REG_L	s1, (KVM_ARCH_GUEST_S1)(a0)
+	REG_L	a1, (KVM_ARCH_GUEST_A1)(a0)
+	REG_L	a2, (KVM_ARCH_GUEST_A2)(a0)
+	REG_L	a3, (KVM_ARCH_GUEST_A3)(a0)
+	REG_L	a4, (KVM_ARCH_GUEST_A4)(a0)
+	REG_L	a5, (KVM_ARCH_GUEST_A5)(a0)
+	REG_L	a6, (KVM_ARCH_GUEST_A6)(a0)
+	REG_L	a7, (KVM_ARCH_GUEST_A7)(a0)
+	REG_L	s2, (KVM_ARCH_GUEST_S2)(a0)
+	REG_L	s3, (KVM_ARCH_GUEST_S3)(a0)
+	REG_L	s4, (KVM_ARCH_GUEST_S4)(a0)
+	REG_L	s5, (KVM_ARCH_GUEST_S5)(a0)
+	REG_L	s6, (KVM_ARCH_GUEST_S6)(a0)
+	REG_L	s7, (KVM_ARCH_GUEST_S7)(a0)
+	REG_L	s8, (KVM_ARCH_GUEST_S8)(a0)
+	REG_L	s9, (KVM_ARCH_GUEST_S9)(a0)
+	REG_L	s10, (KVM_ARCH_GUEST_S10)(a0)
+	REG_L	s11, (KVM_ARCH_GUEST_S11)(a0)
+	REG_L	t3, (KVM_ARCH_GUEST_T3)(a0)
+	REG_L	t4, (KVM_ARCH_GUEST_T4)(a0)
+	REG_L	t5, (KVM_ARCH_GUEST_T5)(a0)
+	REG_L	t6, (KVM_ARCH_GUEST_T6)(a0)
+
+	/* Restore Guest A0 */
+	REG_L	a0, (KVM_ARCH_GUEST_A0)(a0)
+
+	/* Resume Guest */
+	sret
+
+	/* Back to Host */
+	.align 2
+__kvm_switch_return:
+	/* Swap Guest A0 with SSCRATCH */
+	csrrw	a0, CSR_SSCRATCH, a0
+
+	/* Save Guest GPRs (except A0) */
+	REG_S	ra, (KVM_ARCH_GUEST_RA)(a0)
+	REG_S	sp, (KVM_ARCH_GUEST_SP)(a0)
+	REG_S	gp, (KVM_ARCH_GUEST_GP)(a0)
+	REG_S	tp, (KVM_ARCH_GUEST_TP)(a0)
+	REG_S	t0, (KVM_ARCH_GUEST_T0)(a0)
+	REG_S	t1, (KVM_ARCH_GUEST_T1)(a0)
+	REG_S	t2, (KVM_ARCH_GUEST_T2)(a0)
+	REG_S	s0, (KVM_ARCH_GUEST_S0)(a0)
+	REG_S	s1, (KVM_ARCH_GUEST_S1)(a0)
+	REG_S	a1, (KVM_ARCH_GUEST_A1)(a0)
+	REG_S	a2, (KVM_ARCH_GUEST_A2)(a0)
+	REG_S	a3, (KVM_ARCH_GUEST_A3)(a0)
+	REG_S	a4, (KVM_ARCH_GUEST_A4)(a0)
+	REG_S	a5, (KVM_ARCH_GUEST_A5)(a0)
+	REG_S	a6, (KVM_ARCH_GUEST_A6)(a0)
+	REG_S	a7, (KVM_ARCH_GUEST_A7)(a0)
+	REG_S	s2, (KVM_ARCH_GUEST_S2)(a0)
+	REG_S	s3, (KVM_ARCH_GUEST_S3)(a0)
+	REG_S	s4, (KVM_ARCH_GUEST_S4)(a0)
+	REG_S	s5, (KVM_ARCH_GUEST_S5)(a0)
+	REG_S	s6, (KVM_ARCH_GUEST_S6)(a0)
+	REG_S	s7, (KVM_ARCH_GUEST_S7)(a0)
+	REG_S	s8, (KVM_ARCH_GUEST_S8)(a0)
+	REG_S	s9, (KVM_ARCH_GUEST_S9)(a0)
+	REG_S	s10, (KVM_ARCH_GUEST_S10)(a0)
+	REG_S	s11, (KVM_ARCH_GUEST_S11)(a0)
+	REG_S	t3, (KVM_ARCH_GUEST_T3)(a0)
+	REG_S	t4, (KVM_ARCH_GUEST_T4)(a0)
+	REG_S	t5, (KVM_ARCH_GUEST_T5)(a0)
+	REG_S	t6, (KVM_ARCH_GUEST_T6)(a0)
+
+	/* Load Host CSR values */
+	REG_L	t1, (KVM_ARCH_HOST_STVEC)(a0)
+	REG_L	t2, (KVM_ARCH_HOST_SSCRATCH)(a0)
+	REG_L	t3, (KVM_ARCH_HOST_SCOUNTEREN)(a0)
+	REG_L	t4, (KVM_ARCH_HOST_HSTATUS)(a0)
+	REG_L	t5, (KVM_ARCH_HOST_SSTATUS)(a0)
+
+	/* Save Guest SEPC */
+	csrr	t0, CSR_SEPC
+
+	/* Save Guest A0 and Restore Host SSCRATCH */
+	csrrw	t2, CSR_SSCRATCH, t2
+
+	/* Restore Host STVEC */
+	csrw	CSR_STVEC, t1
+
+	/* Save Guest and Restore Host SCOUNTEREN */
+	csrrw	t3, CSR_SCOUNTEREN, t3
+
+	/* Save Guest and Restore Host HSTATUS */
+	csrrw	t4, CSR_HSTATUS, t4
+
+	/* Save Guest and Restore Host SSTATUS */
+	csrrw	t5, CSR_SSTATUS, t5
+
+	/* Store Guest CSR values */
+	REG_S	t0, (KVM_ARCH_GUEST_SEPC)(a0)
+	REG_S	t2, (KVM_ARCH_GUEST_A0)(a0)
+	REG_S	t3, (KVM_ARCH_GUEST_SCOUNTEREN)(a0)
+	REG_S	t4, (KVM_ARCH_GUEST_HSTATUS)(a0)
+	REG_S	t5, (KVM_ARCH_GUEST_SSTATUS)(a0)
+
+	/* Restore Host GPRs (except A0 and T0-T6) */
+	REG_L	ra, (KVM_ARCH_HOST_RA)(a0)
+	REG_L	sp, (KVM_ARCH_HOST_SP)(a0)
+	REG_L	gp, (KVM_ARCH_HOST_GP)(a0)
+	REG_L	tp, (KVM_ARCH_HOST_TP)(a0)
+	REG_L	s0, (KVM_ARCH_HOST_S0)(a0)
+	REG_L	s1, (KVM_ARCH_HOST_S1)(a0)
+	REG_L	a1, (KVM_ARCH_HOST_A1)(a0)
+	REG_L	a2, (KVM_ARCH_HOST_A2)(a0)
+	REG_L	a3, (KVM_ARCH_HOST_A3)(a0)
+	REG_L	a4, (KVM_ARCH_HOST_A4)(a0)
+	REG_L	a5, (KVM_ARCH_HOST_A5)(a0)
+	REG_L	a6, (KVM_ARCH_HOST_A6)(a0)
+	REG_L	a7, (KVM_ARCH_HOST_A7)(a0)
+	REG_L	s2, (KVM_ARCH_HOST_S2)(a0)
+	REG_L	s3, (KVM_ARCH_HOST_S3)(a0)
+	REG_L	s4, (KVM_ARCH_HOST_S4)(a0)
+	REG_L	s5, (KVM_ARCH_HOST_S5)(a0)
+	REG_L	s6, (KVM_ARCH_HOST_S6)(a0)
+	REG_L	s7, (KVM_ARCH_HOST_S7)(a0)
+	REG_L	s8, (KVM_ARCH_HOST_S8)(a0)
+	REG_L	s9, (KVM_ARCH_HOST_S9)(a0)
+	REG_L	s10, (KVM_ARCH_HOST_S10)(a0)
+	REG_L	s11, (KVM_ARCH_HOST_S11)(a0)
+
+	/* Return to C code */
+	ret
+ENDPROC(__kvm_riscv_switch_to)
+
+ENTRY(__kvm_riscv_unpriv_trap)
+	/*
+	 * We assume that faulting unpriv load/store instruction is
+	 * 4-byte long and blindly increment SEPC by 4.
+	 *
+	 * The trap details will be saved at address pointed by 'A0'
+	 * register and we use 'A1' register as temporary.
+	 */
+	csrr	a1, CSR_SEPC
+	REG_S	a1, (KVM_ARCH_TRAP_SEPC)(a0)
+	addi	a1, a1, 4
+	csrw	CSR_SEPC, a1
+	csrr	a1, CSR_SCAUSE
+	REG_S	a1, (KVM_ARCH_TRAP_SCAUSE)(a0)
+	csrr	a1, CSR_STVAL
+	REG_S	a1, (KVM_ARCH_TRAP_STVAL)(a0)
+	csrr	a1, CSR_HTVAL
+	REG_S	a1, (KVM_ARCH_TRAP_HTVAL)(a0)
+	csrr	a1, CSR_HTINST
+	REG_S	a1, (KVM_ARCH_TRAP_HTINST)(a0)
+	sret
+ENDPROC(__kvm_riscv_unpriv_trap)
+
+#ifdef	CONFIG_FPU
+	.align 3
+	.global __kvm_riscv_fp_f_save
+__kvm_riscv_fp_f_save:
+	csrr t2, CSR_SSTATUS
+	li t1, SR_FS
+	csrs CSR_SSTATUS, t1
+	frcsr t0
+	fsw f0,  KVM_ARCH_FP_F_F0(a0)
+	fsw f1,  KVM_ARCH_FP_F_F1(a0)
+	fsw f2,  KVM_ARCH_FP_F_F2(a0)
+	fsw f3,  KVM_ARCH_FP_F_F3(a0)
+	fsw f4,  KVM_ARCH_FP_F_F4(a0)
+	fsw f5,  KVM_ARCH_FP_F_F5(a0)
+	fsw f6,  KVM_ARCH_FP_F_F6(a0)
+	fsw f7,  KVM_ARCH_FP_F_F7(a0)
+	fsw f8,  KVM_ARCH_FP_F_F8(a0)
+	fsw f9,  KVM_ARCH_FP_F_F9(a0)
+	fsw f10, KVM_ARCH_FP_F_F10(a0)
+	fsw f11, KVM_ARCH_FP_F_F11(a0)
+	fsw f12, KVM_ARCH_FP_F_F12(a0)
+	fsw f13, KVM_ARCH_FP_F_F13(a0)
+	fsw f14, KVM_ARCH_FP_F_F14(a0)
+	fsw f15, KVM_ARCH_FP_F_F15(a0)
+	fsw f16, KVM_ARCH_FP_F_F16(a0)
+	fsw f17, KVM_ARCH_FP_F_F17(a0)
+	fsw f18, KVM_ARCH_FP_F_F18(a0)
+	fsw f19, KVM_ARCH_FP_F_F19(a0)
+	fsw f20, KVM_ARCH_FP_F_F20(a0)
+	fsw f21, KVM_ARCH_FP_F_F21(a0)
+	fsw f22, KVM_ARCH_FP_F_F22(a0)
+	fsw f23, KVM_ARCH_FP_F_F23(a0)
+	fsw f24, KVM_ARCH_FP_F_F24(a0)
+	fsw f25, KVM_ARCH_FP_F_F25(a0)
+	fsw f26, KVM_ARCH_FP_F_F26(a0)
+	fsw f27, KVM_ARCH_FP_F_F27(a0)
+	fsw f28, KVM_ARCH_FP_F_F28(a0)
+	fsw f29, KVM_ARCH_FP_F_F29(a0)
+	fsw f30, KVM_ARCH_FP_F_F30(a0)
+	fsw f31, KVM_ARCH_FP_F_F31(a0)
+	sw t0, KVM_ARCH_FP_F_FCSR(a0)
+	csrw CSR_SSTATUS, t2
+	ret
+
+	.align 3
+	.global __kvm_riscv_fp_d_save
+__kvm_riscv_fp_d_save:
+	csrr t2, CSR_SSTATUS
+	li t1, SR_FS
+	csrs CSR_SSTATUS, t1
+	frcsr t0
+	fsd f0,  KVM_ARCH_FP_D_F0(a0)
+	fsd f1,  KVM_ARCH_FP_D_F1(a0)
+	fsd f2,  KVM_ARCH_FP_D_F2(a0)
+	fsd f3,  KVM_ARCH_FP_D_F3(a0)
+	fsd f4,  KVM_ARCH_FP_D_F4(a0)
+	fsd f5,  KVM_ARCH_FP_D_F5(a0)
+	fsd f6,  KVM_ARCH_FP_D_F6(a0)
+	fsd f7,  KVM_ARCH_FP_D_F7(a0)
+	fsd f8,  KVM_ARCH_FP_D_F8(a0)
+	fsd f9,  KVM_ARCH_FP_D_F9(a0)
+	fsd f10, KVM_ARCH_FP_D_F10(a0)
+	fsd f11, KVM_ARCH_FP_D_F11(a0)
+	fsd f12, KVM_ARCH_FP_D_F12(a0)
+	fsd f13, KVM_ARCH_FP_D_F13(a0)
+	fsd f14, KVM_ARCH_FP_D_F14(a0)
+	fsd f15, KVM_ARCH_FP_D_F15(a0)
+	fsd f16, KVM_ARCH_FP_D_F16(a0)
+	fsd f17, KVM_ARCH_FP_D_F17(a0)
+	fsd f18, KVM_ARCH_FP_D_F18(a0)
+	fsd f19, KVM_ARCH_FP_D_F19(a0)
+	fsd f20, KVM_ARCH_FP_D_F20(a0)
+	fsd f21, KVM_ARCH_FP_D_F21(a0)
+	fsd f22, KVM_ARCH_FP_D_F22(a0)
+	fsd f23, KVM_ARCH_FP_D_F23(a0)
+	fsd f24, KVM_ARCH_FP_D_F24(a0)
+	fsd f25, KVM_ARCH_FP_D_F25(a0)
+	fsd f26, KVM_ARCH_FP_D_F26(a0)
+	fsd f27, KVM_ARCH_FP_D_F27(a0)
+	fsd f28, KVM_ARCH_FP_D_F28(a0)
+	fsd f29, KVM_ARCH_FP_D_F29(a0)
+	fsd f30, KVM_ARCH_FP_D_F30(a0)
+	fsd f31, KVM_ARCH_FP_D_F31(a0)
+	sw t0, KVM_ARCH_FP_D_FCSR(a0)
+	csrw CSR_SSTATUS, t2
+	ret
+
+	.align 3
+	.global __kvm_riscv_fp_f_restore
+__kvm_riscv_fp_f_restore:
+	csrr t2, CSR_SSTATUS
+	li t1, SR_FS
+	lw t0, KVM_ARCH_FP_F_FCSR(a0)
+	csrs CSR_SSTATUS, t1
+	flw f0,  KVM_ARCH_FP_F_F0(a0)
+	flw f1,  KVM_ARCH_FP_F_F1(a0)
+	flw f2,  KVM_ARCH_FP_F_F2(a0)
+	flw f3,  KVM_ARCH_FP_F_F3(a0)
+	flw f4,  KVM_ARCH_FP_F_F4(a0)
+	flw f5,  KVM_ARCH_FP_F_F5(a0)
+	flw f6,  KVM_ARCH_FP_F_F6(a0)
+	flw f7,  KVM_ARCH_FP_F_F7(a0)
+	flw f8,  KVM_ARCH_FP_F_F8(a0)
+	flw f9,  KVM_ARCH_FP_F_F9(a0)
+	flw f10, KVM_ARCH_FP_F_F10(a0)
+	flw f11, KVM_ARCH_FP_F_F11(a0)
+	flw f12, KVM_ARCH_FP_F_F12(a0)
+	flw f13, KVM_ARCH_FP_F_F13(a0)
+	flw f14, KVM_ARCH_FP_F_F14(a0)
+	flw f15, KVM_ARCH_FP_F_F15(a0)
+	flw f16, KVM_ARCH_FP_F_F16(a0)
+	flw f17, KVM_ARCH_FP_F_F17(a0)
+	flw f18, KVM_ARCH_FP_F_F18(a0)
+	flw f19, KVM_ARCH_FP_F_F19(a0)
+	flw f20, KVM_ARCH_FP_F_F20(a0)
+	flw f21, KVM_ARCH_FP_F_F21(a0)
+	flw f22, KVM_ARCH_FP_F_F22(a0)
+	flw f23, KVM_ARCH_FP_F_F23(a0)
+	flw f24, KVM_ARCH_FP_F_F24(a0)
+	flw f25, KVM_ARCH_FP_F_F25(a0)
+	flw f26, KVM_ARCH_FP_F_F26(a0)
+	flw f27, KVM_ARCH_FP_F_F27(a0)
+	flw f28, KVM_ARCH_FP_F_F28(a0)
+	flw f29, KVM_ARCH_FP_F_F29(a0)
+	flw f30, KVM_ARCH_FP_F_F30(a0)
+	flw f31, KVM_ARCH_FP_F_F31(a0)
+	fscsr t0
+	csrw CSR_SSTATUS, t2
+	ret
+
+	.align 3
+	.global __kvm_riscv_fp_d_restore
+__kvm_riscv_fp_d_restore:
+	csrr t2, CSR_SSTATUS
+	li t1, SR_FS
+	lw t0, KVM_ARCH_FP_D_FCSR(a0)
+	csrs CSR_SSTATUS, t1
+	fld f0,  KVM_ARCH_FP_D_F0(a0)
+	fld f1,  KVM_ARCH_FP_D_F1(a0)
+	fld f2,  KVM_ARCH_FP_D_F2(a0)
+	fld f3,  KVM_ARCH_FP_D_F3(a0)
+	fld f4,  KVM_ARCH_FP_D_F4(a0)
+	fld f5,  KVM_ARCH_FP_D_F5(a0)
+	fld f6,  KVM_ARCH_FP_D_F6(a0)
+	fld f7,  KVM_ARCH_FP_D_F7(a0)
+	fld f8,  KVM_ARCH_FP_D_F8(a0)
+	fld f9,  KVM_ARCH_FP_D_F9(a0)
+	fld f10, KVM_ARCH_FP_D_F10(a0)
+	fld f11, KVM_ARCH_FP_D_F11(a0)
+	fld f12, KVM_ARCH_FP_D_F12(a0)
+	fld f13, KVM_ARCH_FP_D_F13(a0)
+	fld f14, KVM_ARCH_FP_D_F14(a0)
+	fld f15, KVM_ARCH_FP_D_F15(a0)
+	fld f16, KVM_ARCH_FP_D_F16(a0)
+	fld f17, KVM_ARCH_FP_D_F17(a0)
+	fld f18, KVM_ARCH_FP_D_F18(a0)
+	fld f19, KVM_ARCH_FP_D_F19(a0)
+	fld f20, KVM_ARCH_FP_D_F20(a0)
+	fld f21, KVM_ARCH_FP_D_F21(a0)
+	fld f22, KVM_ARCH_FP_D_F22(a0)
+	fld f23, KVM_ARCH_FP_D_F23(a0)
+	fld f24, KVM_ARCH_FP_D_F24(a0)
+	fld f25, KVM_ARCH_FP_D_F25(a0)
+	fld f26, KVM_ARCH_FP_D_F26(a0)
+	fld f27, KVM_ARCH_FP_D_F27(a0)
+	fld f28, KVM_ARCH_FP_D_F28(a0)
+	fld f29, KVM_ARCH_FP_D_F29(a0)
+	fld f30, KVM_ARCH_FP_D_F30(a0)
+	fld f31, KVM_ARCH_FP_D_F31(a0)
+	fscsr t0
+	csrw CSR_SSTATUS, t2
+	ret
+#endif
diff --git a/arch/riscv/kvm/vcpu_timer.c b/arch/riscv/kvm/vcpu_timer.c
new file mode 100644
index 000000000..3ac2ff6a6
--- /dev/null
+++ b/arch/riscv/kvm/vcpu_timer.c
@@ -0,0 +1,362 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 Western Digital Corporation or its affiliates.
+ *
+ * Authors:
+ *     Atish Patra <atish.patra@wdc.com>
+ */
+
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/kvm_host.h>
+#include <linux/uaccess.h>
+#include <clocksource/timer-riscv.h>
+#include <asm/csr.h>
+#include <asm/delay.h>
+#include <asm/kvm_vcpu_timer.h>
+
+static u64 kvm_riscv_current_cycles(struct kvm_guest_timer *gt)
+{
+	return get_cycles64() + gt->time_delta;
+}
+
+static u64 kvm_riscv_delta_cycles2ns(u64 cycles,
+				     struct kvm_guest_timer *gt,
+				     struct kvm_vcpu_timer *t)
+{
+	unsigned long flags;
+	u64 cycles_now, cycles_delta, delta_ns;
+
+	local_irq_save(flags);
+	cycles_now = kvm_riscv_current_cycles(gt);
+	if (cycles_now < cycles)
+		cycles_delta = cycles - cycles_now;
+	else
+		cycles_delta = 0;
+	delta_ns = (cycles_delta * gt->nsec_mult) >> gt->nsec_shift;
+	local_irq_restore(flags);
+
+	return delta_ns;
+}
+
+static enum hrtimer_restart kvm_riscv_vcpu_hrtimer_expired(struct hrtimer *h)
+{
+	u64 delta_ns;
+	struct kvm_vcpu_timer *t = container_of(h, struct kvm_vcpu_timer, hrt);
+	struct kvm_vcpu *vcpu = container_of(t, struct kvm_vcpu, arch.timer);
+	struct kvm_guest_timer *gt = &vcpu->kvm->arch.timer;
+
+	if (kvm_riscv_current_cycles(gt) < t->next_cycles) {
+		delta_ns = kvm_riscv_delta_cycles2ns(t->next_cycles, gt, t);
+		hrtimer_forward_now(&t->hrt, ktime_set(0, delta_ns));
+		return HRTIMER_RESTART;
+	}
+
+	t->next_set = false;
+	kvm_riscv_vcpu_set_interrupt(vcpu, IRQ_VS_TIMER);
+
+	return HRTIMER_NORESTART;
+}
+
+static int kvm_riscv_vcpu_timer_cancel(struct kvm_vcpu_timer *t)
+{
+	if (!t->init_done || !t->next_set)
+		return -EINVAL;
+
+	hrtimer_cancel(&t->hrt);
+	t->next_set = false;
+
+	return 0;
+}
+
+static int kvm_riscv_vcpu_update_vstimecmp(struct kvm_vcpu *vcpu, u64 ncycles)
+{
+#if defined(CONFIG_32BIT)
+		csr_write(CSR_VSTIMECMP, ncycles & 0xFFFFFFFF);
+		csr_write(CSR_VSTIMECMPH, ncycles >> 32);
+#else
+		csr_write(CSR_VSTIMECMP, ncycles);
+#endif
+		return 0;
+}
+
+static int kvm_riscv_vcpu_update_hrtimer(struct kvm_vcpu *vcpu, u64 ncycles)
+{
+	struct kvm_vcpu_timer *t = &vcpu->arch.timer;
+	struct kvm_guest_timer *gt = &vcpu->kvm->arch.timer;
+	u64 delta_ns;
+
+	if (!t->init_done)
+		return -EINVAL;
+
+	kvm_riscv_vcpu_unset_interrupt(vcpu, IRQ_VS_TIMER);
+
+	delta_ns = kvm_riscv_delta_cycles2ns(ncycles, gt, t);
+	t->next_cycles = ncycles;
+	hrtimer_start(&t->hrt, ktime_set(0, delta_ns), HRTIMER_MODE_REL);
+	t->next_set = true;
+
+	return 0;
+}
+
+int kvm_riscv_vcpu_timer_next_event(struct kvm_vcpu *vcpu, u64 ncycles)
+{
+	struct kvm_vcpu_timer *t = &vcpu->arch.timer;
+
+	return t->timer_next_event(vcpu, ncycles);
+}
+
+static enum hrtimer_restart kvm_riscv_vcpu_vstimer_expired(struct hrtimer *h)
+{
+	u64 delta_ns;
+	struct kvm_vcpu_timer *t = container_of(h, struct kvm_vcpu_timer, hrt);
+	struct kvm_vcpu *vcpu = container_of(t, struct kvm_vcpu, arch.timer);
+	struct kvm_guest_timer *gt = &vcpu->kvm->arch.timer;
+
+	if (kvm_riscv_current_cycles(gt) < t->next_cycles) {
+		delta_ns = kvm_riscv_delta_cycles2ns(t->next_cycles, gt, t);
+		hrtimer_forward_now(&t->hrt, ktime_set(0, delta_ns));
+		return HRTIMER_RESTART;
+	}
+
+	t->next_set = false;
+	kvm_vcpu_kick(vcpu);
+
+	return HRTIMER_NORESTART;
+}
+
+bool kvm_riscv_vcpu_timer_pending(struct kvm_vcpu *vcpu)
+{
+	struct kvm_vcpu_timer *t = &vcpu->arch.timer;
+	struct kvm_guest_timer *gt = &vcpu->kvm->arch.timer;
+
+	if (!kvm_riscv_delta_cycles2ns(t->next_cycles, gt, t) ||
+	    kvm_riscv_vcpu_has_interrupts(vcpu, 1UL << IRQ_VS_TIMER))
+		return true;
+	else
+		return false;
+}
+
+static void kvm_riscv_vcpu_timer_blocking(struct kvm_vcpu *vcpu)
+{
+	struct kvm_vcpu_timer *t = &vcpu->arch.timer;
+	struct kvm_guest_timer *gt = &vcpu->kvm->arch.timer;
+	u64 delta_ns;
+
+	if (!t->init_done)
+		return;
+
+	delta_ns = kvm_riscv_delta_cycles2ns(t->next_cycles, gt, t);
+	hrtimer_start(&t->hrt, ktime_set(0, delta_ns), HRTIMER_MODE_REL);
+	t->next_set = true;
+}
+
+static void kvm_riscv_vcpu_timer_unblocking(struct kvm_vcpu *vcpu)
+{
+	kvm_riscv_vcpu_timer_cancel(&vcpu->arch.timer);
+}
+
+int kvm_riscv_vcpu_get_reg_timer(struct kvm_vcpu *vcpu,
+				 const struct kvm_one_reg *reg)
+{
+	struct kvm_vcpu_timer *t = &vcpu->arch.timer;
+	struct kvm_guest_timer *gt = &vcpu->kvm->arch.timer;
+	u64 __user *uaddr = (u64 __user *)(unsigned long)reg->addr;
+	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
+					    KVM_REG_SIZE_MASK |
+					    KVM_REG_RISCV_TIMER);
+	u64 reg_val;
+
+	if (KVM_REG_SIZE(reg->id) != sizeof(u64))
+		return -EINVAL;
+	if (reg_num >= sizeof(struct kvm_riscv_timer) / sizeof(u64))
+		return -EINVAL;
+
+	switch (reg_num) {
+	case KVM_REG_RISCV_TIMER_REG(frequency):
+		reg_val = riscv_timebase;
+		break;
+	case KVM_REG_RISCV_TIMER_REG(time):
+		reg_val = kvm_riscv_current_cycles(gt);
+		break;
+	case KVM_REG_RISCV_TIMER_REG(compare):
+		reg_val = t->next_cycles;
+		break;
+	case KVM_REG_RISCV_TIMER_REG(state):
+		reg_val = (t->next_set) ? KVM_RISCV_TIMER_STATE_ON :
+					  KVM_RISCV_TIMER_STATE_OFF;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (copy_to_user(uaddr, &reg_val, KVM_REG_SIZE(reg->id)))
+		return -EFAULT;
+
+	return 0;
+}
+
+int kvm_riscv_vcpu_set_reg_timer(struct kvm_vcpu *vcpu,
+				 const struct kvm_one_reg *reg)
+{
+	struct kvm_vcpu_timer *t = &vcpu->arch.timer;
+	struct kvm_guest_timer *gt = &vcpu->kvm->arch.timer;
+	u64 __user *uaddr = (u64 __user *)(unsigned long)reg->addr;
+	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
+					    KVM_REG_SIZE_MASK |
+					    KVM_REG_RISCV_TIMER);
+	u64 reg_val;
+	int ret = 0;
+
+	if (KVM_REG_SIZE(reg->id) != sizeof(u64))
+		return -EINVAL;
+	if (reg_num >= sizeof(struct kvm_riscv_timer) / sizeof(u64))
+		return -EINVAL;
+
+	if (copy_from_user(&reg_val, uaddr, KVM_REG_SIZE(reg->id)))
+		return -EFAULT;
+
+	switch (reg_num) {
+	case KVM_REG_RISCV_TIMER_REG(frequency):
+		ret = -EOPNOTSUPP;
+		break;
+	case KVM_REG_RISCV_TIMER_REG(time):
+		gt->time_delta = reg_val - get_cycles64();
+		break;
+	case KVM_REG_RISCV_TIMER_REG(compare):
+		t->next_cycles = reg_val;
+		break;
+	case KVM_REG_RISCV_TIMER_REG(state):
+		if (reg_val == KVM_RISCV_TIMER_STATE_ON)
+			ret = kvm_riscv_vcpu_timer_next_event(vcpu, reg_val);
+		else
+			ret = kvm_riscv_vcpu_timer_cancel(t);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
+int kvm_riscv_vcpu_timer_init(struct kvm_vcpu *vcpu)
+{
+	struct kvm_vcpu_timer *t = &vcpu->arch.timer;
+
+	if (t->init_done)
+		return -EINVAL;
+
+	hrtimer_init(&t->hrt, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	t->init_done = true;
+	t->next_set = false;
+
+	/* Enable sstc for every vcpu if available in hardware */
+	if (riscv_isa_extension_available(NULL, SSTC)) {
+		t->sstc_enabled = true;
+		t->hrt.function = kvm_riscv_vcpu_vstimer_expired;
+		t->timer_next_event = kvm_riscv_vcpu_update_vstimecmp;
+	} else {
+		t->sstc_enabled = false;
+		t->hrt.function = kvm_riscv_vcpu_hrtimer_expired;
+		t->timer_next_event = kvm_riscv_vcpu_update_hrtimer;
+	}
+
+	return 0;
+}
+
+int kvm_riscv_vcpu_timer_deinit(struct kvm_vcpu *vcpu)
+{
+	int ret;
+
+	ret = kvm_riscv_vcpu_timer_cancel(&vcpu->arch.timer);
+	vcpu->arch.timer.init_done = false;
+
+	return ret;
+}
+
+int kvm_riscv_vcpu_timer_reset(struct kvm_vcpu *vcpu)
+{
+	struct kvm_vcpu_timer *t = &vcpu->arch.timer;
+
+	t->next_cycles = -1ULL;
+	return kvm_riscv_vcpu_timer_cancel(&vcpu->arch.timer);
+}
+
+static void kvm_riscv_vcpu_update_timedelta(struct kvm_vcpu *vcpu)
+{
+	struct kvm_guest_timer *gt = &vcpu->kvm->arch.timer;
+
+#if defined(CONFIG_32BIT)
+	csr_write(CSR_HTIMEDELTA, (u32)(gt->time_delta));
+	csr_write(CSR_HTIMEDELTAH, (u32)(gt->time_delta >> 32));
+#else
+	csr_write(CSR_HTIMEDELTA, gt->time_delta);
+#endif
+}
+
+void kvm_riscv_vcpu_timer_restore(struct kvm_vcpu *vcpu)
+{
+	struct kvm_vcpu_timer *t = &vcpu->arch.timer;
+
+	kvm_riscv_vcpu_update_timedelta(vcpu);
+
+	if (!t->sstc_enabled)
+		return;
+
+#if defined(CONFIG_32BIT)
+	csr_write(CSR_VSTIMECMP, (u32)t->next_cycles);
+	csr_write(CSR_VSTIMECMPH, (u32)(t->next_cycles >> 32));
+#else
+	csr_write(CSR_VSTIMECMP, t->next_cycles);
+#endif
+
+	/* timer should be enabled for the remaining operations */
+	if (unlikely(!t->init_done))
+		return;
+
+	kvm_riscv_vcpu_timer_unblocking(vcpu);
+}
+
+void kvm_riscv_vcpu_timer_sync(struct kvm_vcpu *vcpu)
+{
+	struct kvm_vcpu_timer *t = &vcpu->arch.timer;
+
+	if (!t->sstc_enabled)
+		return;
+
+#if defined(CONFIG_32BIT)
+	t->next_cycles = csr_read(CSR_VSTIMECMP);
+	t->next_cycles |= (u64)csr_read(CSR_VSTIMECMPH) << 32;
+#else
+	t->next_cycles = csr_read(CSR_VSTIMECMP);
+#endif
+}
+
+void kvm_riscv_vcpu_timer_save(struct kvm_vcpu *vcpu)
+{
+	struct kvm_vcpu_timer *t = &vcpu->arch.timer;
+
+	if (!t->sstc_enabled)
+		return;
+
+	/*
+	 * The vstimecmp CSRs are saved by kvm_riscv_vcpu_timer_sync()
+	 * upon every VM exit so no need to save here.
+	 */
+
+	/* timer should be enabled for the remaining operations */
+	if (unlikely(!t->init_done))
+		return;
+
+	if (kvm_vcpu_is_blocking(vcpu))
+		kvm_riscv_vcpu_timer_blocking(vcpu);
+}
+
+void kvm_riscv_guest_timer_init(struct kvm *kvm)
+{
+	struct kvm_guest_timer *gt = &kvm->arch.timer;
+
+	riscv_cs_get_mult_shift(&gt->nsec_mult, &gt->nsec_shift);
+	gt->time_delta = -get_cycles64();
+}
diff --git a/arch/riscv/kvm/vm.c b/arch/riscv/kvm/vm.c
new file mode 100644
index 000000000..65a964d7e
--- /dev/null
+++ b/arch/riscv/kvm/vm.c
@@ -0,0 +1,94 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 Western Digital Corporation or its affiliates.
+ *
+ * Authors:
+ *     Anup Patel <anup.patel@wdc.com>
+ */
+
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/uaccess.h>
+#include <linux/kvm_host.h>
+
+const struct _kvm_stats_desc kvm_vm_stats_desc[] = {
+	KVM_GENERIC_VM_STATS()
+};
+static_assert(ARRAY_SIZE(kvm_vm_stats_desc) ==
+		sizeof(struct kvm_vm_stat) / sizeof(u64));
+
+const struct kvm_stats_header kvm_vm_stats_header = {
+	.name_size = KVM_STATS_NAME_SIZE,
+	.num_desc = ARRAY_SIZE(kvm_vm_stats_desc),
+	.id_offset =  sizeof(struct kvm_stats_header),
+	.desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE,
+	.data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE +
+		       sizeof(kvm_vm_stats_desc),
+};
+
+int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
+{
+	int r;
+
+	r = kvm_riscv_gstage_alloc_pgd(kvm);
+	if (r)
+		return r;
+
+	r = kvm_riscv_gstage_vmid_init(kvm);
+	if (r) {
+		kvm_riscv_gstage_free_pgd(kvm);
+		return r;
+	}
+
+	kvm_riscv_guest_timer_init(kvm);
+
+	return 0;
+}
+
+void kvm_arch_destroy_vm(struct kvm *kvm)
+{
+	kvm_destroy_vcpus(kvm);
+}
+
+int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
+{
+	int r;
+
+	switch (ext) {
+	case KVM_CAP_IOEVENTFD:
+	case KVM_CAP_DEVICE_CTRL:
+	case KVM_CAP_USER_MEMORY:
+	case KVM_CAP_SYNC_MMU:
+	case KVM_CAP_DESTROY_MEMORY_REGION_WORKS:
+	case KVM_CAP_ONE_REG:
+	case KVM_CAP_READONLY_MEM:
+	case KVM_CAP_MP_STATE:
+	case KVM_CAP_IMMEDIATE_EXIT:
+		r = 1;
+		break;
+	case KVM_CAP_NR_VCPUS:
+		r = min_t(unsigned int, num_online_cpus(), KVM_MAX_VCPUS);
+		break;
+	case KVM_CAP_MAX_VCPUS:
+		r = KVM_MAX_VCPUS;
+		break;
+	case KVM_CAP_NR_MEMSLOTS:
+		r = KVM_USER_MEM_SLOTS;
+		break;
+	case KVM_CAP_VM_GPA_BITS:
+		r = kvm_riscv_gstage_gpa_bits();
+		break;
+	default:
+		r = 0;
+		break;
+	}
+
+	return r;
+}
+
+long kvm_arch_vm_ioctl(struct file *filp,
+		       unsigned int ioctl, unsigned long arg)
+{
+	return -EINVAL;
+}
diff --git a/arch/riscv/kvm/vmid.c b/arch/riscv/kvm/vmid.c
new file mode 100644
index 000000000..6cd93995f
--- /dev/null
+++ b/arch/riscv/kvm/vmid.c
@@ -0,0 +1,124 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 Western Digital Corporation or its affiliates.
+ *
+ * Authors:
+ *     Anup Patel <anup.patel@wdc.com>
+ */
+
+#include <linux/bitops.h>
+#include <linux/cpumask.h>
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/smp.h>
+#include <linux/kvm_host.h>
+#include <asm/csr.h>
+
+static unsigned long vmid_version = 1;
+static unsigned long vmid_next;
+static unsigned long vmid_bits;
+static DEFINE_SPINLOCK(vmid_lock);
+
+void kvm_riscv_gstage_vmid_detect(void)
+{
+	unsigned long old;
+
+	/* Figure-out number of VMID bits in HW */
+	old = csr_read(CSR_HGATP);
+	csr_write(CSR_HGATP, old | HGATP_VMID_MASK);
+	vmid_bits = csr_read(CSR_HGATP);
+	vmid_bits = (vmid_bits & HGATP_VMID_MASK) >> HGATP_VMID_SHIFT;
+	vmid_bits = fls_long(vmid_bits);
+	csr_write(CSR_HGATP, old);
+
+	/* We polluted local TLB so flush all guest TLB */
+	kvm_riscv_local_hfence_gvma_all();
+
+	/* We don't use VMID bits if they are not sufficient */
+	if ((1UL << vmid_bits) < num_possible_cpus())
+		vmid_bits = 0;
+}
+
+unsigned long kvm_riscv_gstage_vmid_bits(void)
+{
+	return vmid_bits;
+}
+
+int kvm_riscv_gstage_vmid_init(struct kvm *kvm)
+{
+	/* Mark the initial VMID and VMID version invalid */
+	kvm->arch.vmid.vmid_version = 0;
+	kvm->arch.vmid.vmid = 0;
+
+	return 0;
+}
+
+bool kvm_riscv_gstage_vmid_ver_changed(struct kvm_vmid *vmid)
+{
+	if (!vmid_bits)
+		return false;
+
+	return unlikely(READ_ONCE(vmid->vmid_version) !=
+			READ_ONCE(vmid_version));
+}
+
+static void __local_hfence_gvma_all(void *info)
+{
+	kvm_riscv_local_hfence_gvma_all();
+}
+
+void kvm_riscv_gstage_vmid_update(struct kvm_vcpu *vcpu)
+{
+	unsigned long i;
+	struct kvm_vcpu *v;
+	struct kvm_vmid *vmid = &vcpu->kvm->arch.vmid;
+
+	if (!kvm_riscv_gstage_vmid_ver_changed(vmid))
+		return;
+
+	spin_lock(&vmid_lock);
+
+	/*
+	 * We need to re-check the vmid_version here to ensure that if
+	 * another vcpu already allocated a valid vmid for this vm.
+	 */
+	if (!kvm_riscv_gstage_vmid_ver_changed(vmid)) {
+		spin_unlock(&vmid_lock);
+		return;
+	}
+
+	/* First user of a new VMID version? */
+	if (unlikely(vmid_next == 0)) {
+		WRITE_ONCE(vmid_version, READ_ONCE(vmid_version) + 1);
+		vmid_next = 1;
+
+		/*
+		 * We ran out of VMIDs so we increment vmid_version and
+		 * start assigning VMIDs from 1.
+		 *
+		 * This also means existing VMIDs assignment to all Guest
+		 * instances is invalid and we have force VMID re-assignement
+		 * for all Guest instances. The Guest instances that were not
+		 * running will automatically pick-up new VMIDs because will
+		 * call kvm_riscv_gstage_vmid_update() whenever they enter
+		 * in-kernel run loop. For Guest instances that are already
+		 * running, we force VM exits on all host CPUs using IPI and
+		 * flush all Guest TLBs.
+		 */
+		on_each_cpu_mask(cpu_online_mask, __local_hfence_gvma_all,
+				 NULL, 1);
+	}
+
+	vmid->vmid = vmid_next;
+	vmid_next++;
+	vmid_next &= (1 << vmid_bits) - 1;
+
+	WRITE_ONCE(vmid->vmid_version, READ_ONCE(vmid_version));
+
+	spin_unlock(&vmid_lock);
+
+	/* Request G-stage page table update for all VCPUs */
+	kvm_for_each_vcpu(i, v, vcpu->kvm)
+		kvm_make_request(KVM_REQ_UPDATE_HGATP, v);
+}
diff --git a/arch/riscv/lib/Makefile b/arch/riscv/lib/Makefile
new file mode 100644
index 000000000..25d5c9664
--- /dev/null
+++ b/arch/riscv/lib/Makefile
@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0-only
+lib-y			+= delay.o
+lib-y			+= memcpy.o
+lib-y			+= memset.o
+lib-y			+= memmove.o
+lib-$(CONFIG_MMU)	+= uaccess.o
+lib-$(CONFIG_64BIT)	+= tishift.o
+
+obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
diff --git a/arch/riscv/lib/delay.c b/arch/riscv/lib/delay.c
new file mode 100644
index 000000000..49d510ba7
--- /dev/null
+++ b/arch/riscv/lib/delay.c
@@ -0,0 +1,111 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ */
+
+#include <linux/delay.h>
+#include <linux/math.h>
+#include <linux/param.h>
+#include <linux/timex.h>
+#include <linux/types.h>
+#include <linux/export.h>
+
+#include <asm/processor.h>
+
+/*
+ * This is copies from arch/arm/include/asm/delay.h
+ *
+ * Loop (or tick) based delay:
+ *
+ * loops = loops_per_jiffy * jiffies_per_sec * delay_us / us_per_sec
+ *
+ * where:
+ *
+ * jiffies_per_sec = HZ
+ * us_per_sec = 1000000
+ *
+ * Therefore the constant part is HZ / 1000000 which is a small
+ * fractional number. To make this usable with integer math, we
+ * scale up this constant by 2^31, perform the actual multiplication,
+ * and scale the result back down by 2^31 with a simple shift:
+ *
+ * loops = (loops_per_jiffy * delay_us * UDELAY_MULT) >> 31
+ *
+ * where:
+ *
+ * UDELAY_MULT = 2^31 * HZ / 1000000
+ *             = (2^31 / 1000000) * HZ
+ *             = 2147.483648 * HZ
+ *             = 2147 * HZ + 483648 * HZ / 1000000
+ *
+ * 31 is the biggest scale shift value that won't overflow 32 bits for
+ * delay_us * UDELAY_MULT assuming HZ <= 1000 and delay_us <= 2000.
+ */
+#define MAX_UDELAY_US	2000
+#define MAX_UDELAY_HZ	1000
+#define UDELAY_MULT	(2147UL * HZ + 483648UL * HZ / 1000000UL)
+#define UDELAY_SHIFT	31
+
+#if HZ > MAX_UDELAY_HZ
+#error "HZ > MAX_UDELAY_HZ"
+#endif
+
+/*
+ * RISC-V supports both UDELAY and NDELAY.  This is largely the same as above,
+ * but with different constants.  I added 10 bits to the shift to get this, but
+ * the result is that I need a 64-bit multiply, which is slow on 32-bit
+ * platforms.
+ *
+ * NDELAY_MULT = 2^41 * HZ / 1000000000
+ *             = (2^41 / 1000000000) * HZ
+ *             = 2199.02325555 * HZ
+ *             = 2199 * HZ + 23255550 * HZ / 1000000000
+ *
+ * The maximum here is to avoid 64-bit overflow, but it isn't checked as it
+ * won't happen.
+ */
+#define MAX_NDELAY_NS   (1ULL << 42)
+#define MAX_NDELAY_HZ	MAX_UDELAY_HZ
+#define NDELAY_MULT	((unsigned long long)(2199ULL * HZ + 23255550ULL * HZ / 1000000000ULL))
+#define NDELAY_SHIFT	41
+
+#if HZ > MAX_NDELAY_HZ
+#error "HZ > MAX_NDELAY_HZ"
+#endif
+
+void __delay(unsigned long cycles)
+{
+	u64 t0 = get_cycles();
+
+	while ((unsigned long)(get_cycles() - t0) < cycles)
+		cpu_relax();
+}
+EXPORT_SYMBOL(__delay);
+
+void udelay(unsigned long usecs)
+{
+	u64 ucycles = (u64)usecs * lpj_fine * UDELAY_MULT;
+	u64 n;
+
+	if (unlikely(usecs > MAX_UDELAY_US)) {
+		n = (u64)usecs * riscv_timebase;
+		do_div(n, 1000000);
+
+		__delay(n);
+		return;
+	}
+
+	__delay(ucycles >> UDELAY_SHIFT);
+}
+EXPORT_SYMBOL(udelay);
+
+void ndelay(unsigned long nsecs)
+{
+	/*
+	 * This doesn't bother checking for overflow, as it won't happen (it's
+	 * an hour) of delay.
+	 */
+	unsigned long long ncycles = nsecs * lpj_fine * NDELAY_MULT;
+	__delay(ncycles >> NDELAY_SHIFT);
+}
+EXPORT_SYMBOL(ndelay);
diff --git a/arch/riscv/lib/error-inject.c b/arch/riscv/lib/error-inject.c
new file mode 100644
index 000000000..d667ade2b
--- /dev/null
+++ b/arch/riscv/lib/error-inject.c
@@ -0,0 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/error-injection.h>
+#include <linux/kprobes.h>
+
+void override_function_with_return(struct pt_regs *regs)
+{
+	instruction_pointer_set(regs, regs->ra);
+}
+NOKPROBE_SYMBOL(override_function_with_return);
diff --git a/arch/riscv/lib/memcpy.S b/arch/riscv/lib/memcpy.S
new file mode 100644
index 000000000..51ab71625
--- /dev/null
+++ b/arch/riscv/lib/memcpy.S
@@ -0,0 +1,108 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2013 Regents of the University of California
+ */
+
+#include <linux/linkage.h>
+#include <asm/asm.h>
+
+/* void *memcpy(void *, const void *, size_t) */
+ENTRY(__memcpy)
+WEAK(memcpy)
+	move t6, a0  /* Preserve return value */
+
+	/* Defer to byte-oriented copy for small sizes */
+	sltiu a3, a2, 128
+	bnez a3, 4f
+	/* Use word-oriented copy only if low-order bits match */
+	andi a3, t6, SZREG-1
+	andi a4, a1, SZREG-1
+	bne a3, a4, 4f
+
+	beqz a3, 2f  /* Skip if already aligned */
+	/*
+	 * Round to nearest double word-aligned address
+	 * greater than or equal to start address
+	 */
+	andi a3, a1, ~(SZREG-1)
+	addi a3, a3, SZREG
+	/* Handle initial misalignment */
+	sub a4, a3, a1
+1:
+	lb a5, 0(a1)
+	addi a1, a1, 1
+	sb a5, 0(t6)
+	addi t6, t6, 1
+	bltu a1, a3, 1b
+	sub a2, a2, a4  /* Update count */
+
+2:
+	andi a4, a2, ~((16*SZREG)-1)
+	beqz a4, 4f
+	add a3, a1, a4
+3:
+	REG_L a4,       0(a1)
+	REG_L a5,   SZREG(a1)
+	REG_L a6, 2*SZREG(a1)
+	REG_L a7, 3*SZREG(a1)
+	REG_L t0, 4*SZREG(a1)
+	REG_L t1, 5*SZREG(a1)
+	REG_L t2, 6*SZREG(a1)
+	REG_L t3, 7*SZREG(a1)
+	REG_L t4, 8*SZREG(a1)
+	REG_L t5, 9*SZREG(a1)
+	REG_S a4,       0(t6)
+	REG_S a5,   SZREG(t6)
+	REG_S a6, 2*SZREG(t6)
+	REG_S a7, 3*SZREG(t6)
+	REG_S t0, 4*SZREG(t6)
+	REG_S t1, 5*SZREG(t6)
+	REG_S t2, 6*SZREG(t6)
+	REG_S t3, 7*SZREG(t6)
+	REG_S t4, 8*SZREG(t6)
+	REG_S t5, 9*SZREG(t6)
+	REG_L a4, 10*SZREG(a1)
+	REG_L a5, 11*SZREG(a1)
+	REG_L a6, 12*SZREG(a1)
+	REG_L a7, 13*SZREG(a1)
+	REG_L t0, 14*SZREG(a1)
+	REG_L t1, 15*SZREG(a1)
+	addi a1, a1, 16*SZREG
+	REG_S a4, 10*SZREG(t6)
+	REG_S a5, 11*SZREG(t6)
+	REG_S a6, 12*SZREG(t6)
+	REG_S a7, 13*SZREG(t6)
+	REG_S t0, 14*SZREG(t6)
+	REG_S t1, 15*SZREG(t6)
+	addi t6, t6, 16*SZREG
+	bltu a1, a3, 3b
+	andi a2, a2, (16*SZREG)-1  /* Update count */
+
+4:
+	/* Handle trailing misalignment */
+	beqz a2, 6f
+	add a3, a1, a2
+
+	/* Use word-oriented copy if co-aligned to word boundary */
+	or a5, a1, t6
+	or a5, a5, a3
+	andi a5, a5, 3
+	bnez a5, 5f
+7:
+	lw a4, 0(a1)
+	addi a1, a1, 4
+	sw a4, 0(t6)
+	addi t6, t6, 4
+	bltu a1, a3, 7b
+
+	ret
+
+5:
+	lb a4, 0(a1)
+	addi a1, a1, 1
+	sb a4, 0(t6)
+	addi t6, t6, 1
+	bltu a1, a3, 5b
+6:
+	ret
+END(__memcpy)
diff --git a/arch/riscv/lib/memmove.S b/arch/riscv/lib/memmove.S
new file mode 100644
index 000000000..e0609e1f0
--- /dev/null
+++ b/arch/riscv/lib/memmove.S
@@ -0,0 +1,316 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2022 Michael T. Kloos <michael@michaelkloos.com>
+ */
+
+#include <linux/linkage.h>
+#include <asm/asm.h>
+
+SYM_FUNC_START(__memmove)
+SYM_FUNC_START_WEAK(memmove)
+	/*
+	 * Returns
+	 *   a0 - dest
+	 *
+	 * Parameters
+	 *   a0 - Inclusive first byte of dest
+	 *   a1 - Inclusive first byte of src
+	 *   a2 - Length of copy n
+	 *
+	 * Because the return matches the parameter register a0,
+	 * we will not clobber or modify that register.
+	 *
+	 * Note: This currently only works on little-endian.
+	 * To port to big-endian, reverse the direction of shifts
+	 * in the 2 misaligned fixup copy loops.
+	 */
+
+	/* Return if nothing to do */
+	beq a0, a1, return_from_memmove
+	beqz a2, return_from_memmove
+
+	/*
+	 * Register Uses
+	 *      Forward Copy: a1 - Index counter of src
+	 *      Reverse Copy: a4 - Index counter of src
+	 *      Forward Copy: t3 - Index counter of dest
+	 *      Reverse Copy: t4 - Index counter of dest
+	 *   Both Copy Modes: t5 - Inclusive first multibyte/aligned of dest
+	 *   Both Copy Modes: t6 - Non-Inclusive last multibyte/aligned of dest
+	 *   Both Copy Modes: t0 - Link / Temporary for load-store
+	 *   Both Copy Modes: t1 - Temporary for load-store
+	 *   Both Copy Modes: t2 - Temporary for load-store
+	 *   Both Copy Modes: a5 - dest to src alignment offset
+	 *   Both Copy Modes: a6 - Shift ammount
+	 *   Both Copy Modes: a7 - Inverse Shift ammount
+	 *   Both Copy Modes: a2 - Alternate breakpoint for unrolled loops
+	 */
+
+	/*
+	 * Solve for some register values now.
+	 * Byte copy does not need t5 or t6.
+	 */
+	mv   t3, a0
+	add  t4, a0, a2
+	add  a4, a1, a2
+
+	/*
+	 * Byte copy if copying less than (2 * SZREG) bytes. This can
+	 * cause problems with the bulk copy implementation and is
+	 * small enough not to bother.
+	 */
+	andi t0, a2, -(2 * SZREG)
+	beqz t0, byte_copy
+
+	/*
+	 * Now solve for t5 and t6.
+	 */
+	andi t5, t3, -SZREG
+	andi t6, t4, -SZREG
+	/*
+	 * If dest(Register t3) rounded down to the nearest naturally
+	 * aligned SZREG address, does not equal dest, then add SZREG
+	 * to find the low-bound of SZREG alignment in the dest memory
+	 * region.  Note that this could overshoot the dest memory
+	 * region if n is less than SZREG.  This is one reason why
+	 * we always byte copy if n is less than SZREG.
+	 * Otherwise, dest is already naturally aligned to SZREG.
+	 */
+	beq  t5, t3, 1f
+		addi t5, t5, SZREG
+	1:
+
+	/*
+	 * If the dest and src are co-aligned to SZREG, then there is
+	 * no need for the full rigmarole of a full misaligned fixup copy.
+	 * Instead, do a simpler co-aligned copy.
+	 */
+	xor  t0, a0, a1
+	andi t1, t0, (SZREG - 1)
+	beqz t1, coaligned_copy
+	/* Fall through to misaligned fixup copy */
+
+misaligned_fixup_copy:
+	bltu a1, a0, misaligned_fixup_copy_reverse
+
+misaligned_fixup_copy_forward:
+	jal  t0, byte_copy_until_aligned_forward
+
+	andi a5, a1, (SZREG - 1) /* Find the alignment offset of src (a1) */
+	slli a6, a5, 3 /* Multiply by 8 to convert that to bits to shift */
+	sub  a5, a1, t3 /* Find the difference between src and dest */
+	andi a1, a1, -SZREG /* Align the src pointer */
+	addi a2, t6, SZREG /* The other breakpoint for the unrolled loop*/
+
+	/*
+	 * Compute The Inverse Shift
+	 * a7 = XLEN - a6 = XLEN + -a6
+	 * 2s complement negation to find the negative: -a6 = ~a6 + 1
+	 * Add that to XLEN.  XLEN = SZREG * 8.
+	 */
+	not  a7, a6
+	addi a7, a7, (SZREG * 8 + 1)
+
+	/*
+	 * Fix Misalignment Copy Loop - Forward
+	 * load_val0 = load_ptr[0];
+	 * do {
+	 * 	load_val1 = load_ptr[1];
+	 * 	store_ptr += 2;
+	 * 	store_ptr[0 - 2] = (load_val0 >> {a6}) | (load_val1 << {a7});
+	 *
+	 * 	if (store_ptr == {a2})
+	 * 		break;
+	 *
+	 * 	load_val0 = load_ptr[2];
+	 * 	load_ptr += 2;
+	 * 	store_ptr[1 - 2] = (load_val1 >> {a6}) | (load_val0 << {a7});
+	 *
+	 * } while (store_ptr != store_ptr_end);
+	 * store_ptr = store_ptr_end;
+	 */
+
+	REG_L t0, (0 * SZREG)(a1)
+	1:
+	REG_L t1, (1 * SZREG)(a1)
+	addi  t3, t3, (2 * SZREG)
+	srl   t0, t0, a6
+	sll   t2, t1, a7
+	or    t2, t0, t2
+	REG_S t2, ((0 * SZREG) - (2 * SZREG))(t3)
+
+	beq   t3, a2, 2f
+
+	REG_L t0, (2 * SZREG)(a1)
+	addi  a1, a1, (2 * SZREG)
+	srl   t1, t1, a6
+	sll   t2, t0, a7
+	or    t2, t1, t2
+	REG_S t2, ((1 * SZREG) - (2 * SZREG))(t3)
+
+	bne   t3, t6, 1b
+	2:
+	mv    t3, t6 /* Fix the dest pointer in case the loop was broken */
+
+	add  a1, t3, a5 /* Restore the src pointer */
+	j byte_copy_forward /* Copy any remaining bytes */
+
+misaligned_fixup_copy_reverse:
+	jal  t0, byte_copy_until_aligned_reverse
+
+	andi a5, a4, (SZREG - 1) /* Find the alignment offset of src (a4) */
+	slli a6, a5, 3 /* Multiply by 8 to convert that to bits to shift */
+	sub  a5, a4, t4 /* Find the difference between src and dest */
+	andi a4, a4, -SZREG /* Align the src pointer */
+	addi a2, t5, -SZREG /* The other breakpoint for the unrolled loop*/
+
+	/*
+	 * Compute The Inverse Shift
+	 * a7 = XLEN - a6 = XLEN + -a6
+	 * 2s complement negation to find the negative: -a6 = ~a6 + 1
+	 * Add that to XLEN.  XLEN = SZREG * 8.
+	 */
+	not  a7, a6
+	addi a7, a7, (SZREG * 8 + 1)
+
+	/*
+	 * Fix Misalignment Copy Loop - Reverse
+	 * load_val1 = load_ptr[0];
+	 * do {
+	 * 	load_val0 = load_ptr[-1];
+	 * 	store_ptr -= 2;
+	 * 	store_ptr[1] = (load_val0 >> {a6}) | (load_val1 << {a7});
+	 *
+	 * 	if (store_ptr == {a2})
+	 * 		break;
+	 *
+	 * 	load_val1 = load_ptr[-2];
+	 * 	load_ptr -= 2;
+	 * 	store_ptr[0] = (load_val1 >> {a6}) | (load_val0 << {a7});
+	 *
+	 * } while (store_ptr != store_ptr_end);
+	 * store_ptr = store_ptr_end;
+	 */
+
+	REG_L t1, ( 0 * SZREG)(a4)
+	1:
+	REG_L t0, (-1 * SZREG)(a4)
+	addi  t4, t4, (-2 * SZREG)
+	sll   t1, t1, a7
+	srl   t2, t0, a6
+	or    t2, t1, t2
+	REG_S t2, ( 1 * SZREG)(t4)
+
+	beq   t4, a2, 2f
+
+	REG_L t1, (-2 * SZREG)(a4)
+	addi  a4, a4, (-2 * SZREG)
+	sll   t0, t0, a7
+	srl   t2, t1, a6
+	or    t2, t0, t2
+	REG_S t2, ( 0 * SZREG)(t4)
+
+	bne   t4, t5, 1b
+	2:
+	mv    t4, t5 /* Fix the dest pointer in case the loop was broken */
+
+	add  a4, t4, a5 /* Restore the src pointer */
+	j byte_copy_reverse /* Copy any remaining bytes */
+
+/*
+ * Simple copy loops for SZREG co-aligned memory locations.
+ * These also make calls to do byte copies for any unaligned
+ * data at their terminations.
+ */
+coaligned_copy:
+	bltu a1, a0, coaligned_copy_reverse
+
+coaligned_copy_forward:
+	jal t0, byte_copy_until_aligned_forward
+
+	1:
+	REG_L t1, ( 0 * SZREG)(a1)
+	addi  a1, a1, SZREG
+	addi  t3, t3, SZREG
+	REG_S t1, (-1 * SZREG)(t3)
+	bne   t3, t6, 1b
+
+	j byte_copy_forward /* Copy any remaining bytes */
+
+coaligned_copy_reverse:
+	jal t0, byte_copy_until_aligned_reverse
+
+	1:
+	REG_L t1, (-1 * SZREG)(a4)
+	addi  a4, a4, -SZREG
+	addi  t4, t4, -SZREG
+	REG_S t1, ( 0 * SZREG)(t4)
+	bne   t4, t5, 1b
+
+	j byte_copy_reverse /* Copy any remaining bytes */
+
+/*
+ * These are basically sub-functions within the function.  They
+ * are used to byte copy until the dest pointer is in alignment.
+ * At which point, a bulk copy method can be used by the
+ * calling code.  These work on the same registers as the bulk
+ * copy loops.  Therefore, the register values can be picked
+ * up from where they were left and we avoid code duplication
+ * without any overhead except the call in and return jumps.
+ */
+byte_copy_until_aligned_forward:
+	beq  t3, t5, 2f
+	1:
+	lb   t1,  0(a1)
+	addi a1, a1, 1
+	addi t3, t3, 1
+	sb   t1, -1(t3)
+	bne  t3, t5, 1b
+	2:
+	jalr zero, 0x0(t0) /* Return to multibyte copy loop */
+
+byte_copy_until_aligned_reverse:
+	beq  t4, t6, 2f
+	1:
+	lb   t1, -1(a4)
+	addi a4, a4, -1
+	addi t4, t4, -1
+	sb   t1,  0(t4)
+	bne  t4, t6, 1b
+	2:
+	jalr zero, 0x0(t0) /* Return to multibyte copy loop */
+
+/*
+ * Simple byte copy loops.
+ * These will byte copy until they reach the end of data to copy.
+ * At that point, they will call to return from memmove.
+ */
+byte_copy:
+	bltu a1, a0, byte_copy_reverse
+
+byte_copy_forward:
+	beq  t3, t4, 2f
+	1:
+	lb   t1,  0(a1)
+	addi a1, a1, 1
+	addi t3, t3, 1
+	sb   t1, -1(t3)
+	bne  t3, t4, 1b
+	2:
+	ret
+
+byte_copy_reverse:
+	beq  t4, t3, 2f
+	1:
+	lb   t1, -1(a4)
+	addi a4, a4, -1
+	addi t4, t4, -1
+	sb   t1,  0(t4)
+	bne  t4, t3, 1b
+	2:
+
+return_from_memmove:
+	ret
+
+SYM_FUNC_END(memmove)
+SYM_FUNC_END(__memmove)
diff --git a/arch/riscv/lib/memset.S b/arch/riscv/lib/memset.S
new file mode 100644
index 000000000..34c5360c6
--- /dev/null
+++ b/arch/riscv/lib/memset.S
@@ -0,0 +1,113 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2013 Regents of the University of California
+ */
+
+
+#include <linux/linkage.h>
+#include <asm/asm.h>
+
+/* void *memset(void *, int, size_t) */
+ENTRY(__memset)
+WEAK(memset)
+	move t0, a0  /* Preserve return value */
+
+	/* Defer to byte-oriented fill for small sizes */
+	sltiu a3, a2, 16
+	bnez a3, 4f
+
+	/*
+	 * Round to nearest XLEN-aligned address
+	 * greater than or equal to start address
+	 */
+	addi a3, t0, SZREG-1
+	andi a3, a3, ~(SZREG-1)
+	beq a3, t0, 2f  /* Skip if already aligned */
+	/* Handle initial misalignment */
+	sub a4, a3, t0
+1:
+	sb a1, 0(t0)
+	addi t0, t0, 1
+	bltu t0, a3, 1b
+	sub a2, a2, a4  /* Update count */
+
+2: /* Duff's device with 32 XLEN stores per iteration */
+	/* Broadcast value into all bytes */
+	andi a1, a1, 0xff
+	slli a3, a1, 8
+	or a1, a3, a1
+	slli a3, a1, 16
+	or a1, a3, a1
+#ifdef CONFIG_64BIT
+	slli a3, a1, 32
+	or a1, a3, a1
+#endif
+
+	/* Calculate end address */
+	andi a4, a2, ~(SZREG-1)
+	add a3, t0, a4
+
+	andi a4, a4, 31*SZREG  /* Calculate remainder */
+	beqz a4, 3f            /* Shortcut if no remainder */
+	neg a4, a4
+	addi a4, a4, 32*SZREG  /* Calculate initial offset */
+
+	/* Adjust start address with offset */
+	sub t0, t0, a4
+
+	/* Jump into loop body */
+	/* Assumes 32-bit instruction lengths */
+	la a5, 3f
+#ifdef CONFIG_64BIT
+	srli a4, a4, 1
+#endif
+	add a5, a5, a4
+	jr a5
+3:
+	REG_S a1,        0(t0)
+	REG_S a1,    SZREG(t0)
+	REG_S a1,  2*SZREG(t0)
+	REG_S a1,  3*SZREG(t0)
+	REG_S a1,  4*SZREG(t0)
+	REG_S a1,  5*SZREG(t0)
+	REG_S a1,  6*SZREG(t0)
+	REG_S a1,  7*SZREG(t0)
+	REG_S a1,  8*SZREG(t0)
+	REG_S a1,  9*SZREG(t0)
+	REG_S a1, 10*SZREG(t0)
+	REG_S a1, 11*SZREG(t0)
+	REG_S a1, 12*SZREG(t0)
+	REG_S a1, 13*SZREG(t0)
+	REG_S a1, 14*SZREG(t0)
+	REG_S a1, 15*SZREG(t0)
+	REG_S a1, 16*SZREG(t0)
+	REG_S a1, 17*SZREG(t0)
+	REG_S a1, 18*SZREG(t0)
+	REG_S a1, 19*SZREG(t0)
+	REG_S a1, 20*SZREG(t0)
+	REG_S a1, 21*SZREG(t0)
+	REG_S a1, 22*SZREG(t0)
+	REG_S a1, 23*SZREG(t0)
+	REG_S a1, 24*SZREG(t0)
+	REG_S a1, 25*SZREG(t0)
+	REG_S a1, 26*SZREG(t0)
+	REG_S a1, 27*SZREG(t0)
+	REG_S a1, 28*SZREG(t0)
+	REG_S a1, 29*SZREG(t0)
+	REG_S a1, 30*SZREG(t0)
+	REG_S a1, 31*SZREG(t0)
+	addi t0, t0, 32*SZREG
+	bltu t0, a3, 3b
+	andi a2, a2, SZREG-1  /* Update count */
+
+4:
+	/* Handle trailing misalignment */
+	beqz a2, 6f
+	add a3, t0, a2
+5:
+	sb a1, 0(t0)
+	addi t0, t0, 1
+	bltu t0, a3, 5b
+6:
+	ret
+END(__memset)
diff --git a/arch/riscv/lib/tishift.S b/arch/riscv/lib/tishift.S
new file mode 100644
index 000000000..ef90075c4
--- /dev/null
+++ b/arch/riscv/lib/tishift.S
@@ -0,0 +1,76 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2018 Free Software Foundation, Inc.
+ */
+
+#include <linux/linkage.h>
+#include <asm-generic/export.h>
+
+SYM_FUNC_START(__lshrti3)
+	beqz	a2, .L1
+	li	a5,64
+	sub	a5,a5,a2
+	sext.w	a4,a5
+	blez	a5, .L2
+	sext.w	a2,a2
+	srl	a0,a0,a2
+	sll	a4,a1,a4
+	srl	a2,a1,a2
+	or	a0,a0,a4
+	mv	a1,a2
+.L1:
+	ret
+.L2:
+	negw	a0,a4
+	li	a2,0
+	srl	a0,a1,a0
+	mv	a1,a2
+	ret
+SYM_FUNC_END(__lshrti3)
+EXPORT_SYMBOL(__lshrti3)
+
+SYM_FUNC_START(__ashrti3)
+	beqz	a2, .L3
+	li	a5,64
+	sub	a5,a5,a2
+	sext.w	a4,a5
+	blez	a5, .L4
+	sext.w	a2,a2
+	srl	a0,a0,a2
+	sll	a4,a1,a4
+	sra	a2,a1,a2
+	or	a0,a0,a4
+	mv	a1,a2
+.L3:
+	ret
+.L4:
+	negw	a0,a4
+	srai	a2,a1,0x3f
+	sra	a0,a1,a0
+	mv	a1,a2
+	ret
+SYM_FUNC_END(__ashrti3)
+EXPORT_SYMBOL(__ashrti3)
+
+SYM_FUNC_START(__ashlti3)
+	beqz	a2, .L5
+	li	a5,64
+	sub	a5,a5,a2
+	sext.w	a4,a5
+	blez	a5, .L6
+	sext.w	a2,a2
+	sll	a1,a1,a2
+	srl	a4,a0,a4
+	sll	a2,a0,a2
+	or	a1,a1,a4
+	mv	a0,a2
+.L5:
+	ret
+.L6:
+	negw	a1,a4
+	li	a2,0
+	sll	a1,a0,a1
+	mv	a0,a2
+	ret
+SYM_FUNC_END(__ashlti3)
+EXPORT_SYMBOL(__ashlti3)
diff --git a/arch/riscv/lib/uaccess.S b/arch/riscv/lib/uaccess.S
new file mode 100644
index 000000000..09b47ebac
--- /dev/null
+++ b/arch/riscv/lib/uaccess.S
@@ -0,0 +1,237 @@
+#include <linux/linkage.h>
+#include <asm-generic/export.h>
+#include <asm/asm.h>
+#include <asm/asm-extable.h>
+#include <asm/csr.h>
+
+	.macro fixup op reg addr lbl
+100:
+	\op \reg, \addr
+	_asm_extable	100b, \lbl
+	.endm
+
+ENTRY(__asm_copy_to_user)
+ENTRY(__asm_copy_from_user)
+
+	/* Enable access to user memory */
+	li t6, SR_SUM
+	csrs CSR_STATUS, t6
+
+	/*
+	 * Save the terminal address which will be used to compute the number
+	 * of bytes copied in case of a fixup exception.
+	 */
+	add	t5, a0, a2
+
+	/*
+	 * Register allocation for code below:
+	 * a0 - start of uncopied dst
+	 * a1 - start of uncopied src
+	 * a2 - size
+	 * t0 - end of uncopied dst
+	 */
+	add	t0, a0, a2
+
+	/*
+	 * Use byte copy only if too small.
+	 * SZREG holds 4 for RV32 and 8 for RV64
+	 */
+	li	a3, 9*SZREG /* size must be larger than size in word_copy */
+	bltu	a2, a3, .Lbyte_copy_tail
+
+	/*
+	 * Copy first bytes until dst is aligned to word boundary.
+	 * a0 - start of dst
+	 * t1 - start of aligned dst
+	 */
+	addi	t1, a0, SZREG-1
+	andi	t1, t1, ~(SZREG-1)
+	/* dst is already aligned, skip */
+	beq	a0, t1, .Lskip_align_dst
+1:
+	/* a5 - one byte for copying data */
+	fixup lb      a5, 0(a1), 10f
+	addi	a1, a1, 1	/* src */
+	fixup sb      a5, 0(a0), 10f
+	addi	a0, a0, 1	/* dst */
+	bltu	a0, t1, 1b	/* t1 - start of aligned dst */
+
+.Lskip_align_dst:
+	/*
+	 * Now dst is aligned.
+	 * Use shift-copy if src is misaligned.
+	 * Use word-copy if both src and dst are aligned because
+	 * can not use shift-copy which do not require shifting
+	 */
+	/* a1 - start of src */
+	andi	a3, a1, SZREG-1
+	bnez	a3, .Lshift_copy
+
+.Lword_copy:
+        /*
+	 * Both src and dst are aligned, unrolled word copy
+	 *
+	 * a0 - start of aligned dst
+	 * a1 - start of aligned src
+	 * t0 - end of aligned dst
+	 */
+	addi	t0, t0, -(8*SZREG) /* not to over run */
+2:
+	fixup REG_L   a4,        0(a1), 10f
+	fixup REG_L   a5,    SZREG(a1), 10f
+	fixup REG_L   a6,  2*SZREG(a1), 10f
+	fixup REG_L   a7,  3*SZREG(a1), 10f
+	fixup REG_L   t1,  4*SZREG(a1), 10f
+	fixup REG_L   t2,  5*SZREG(a1), 10f
+	fixup REG_L   t3,  6*SZREG(a1), 10f
+	fixup REG_L   t4,  7*SZREG(a1), 10f
+	fixup REG_S   a4,        0(a0), 10f
+	fixup REG_S   a5,    SZREG(a0), 10f
+	fixup REG_S   a6,  2*SZREG(a0), 10f
+	fixup REG_S   a7,  3*SZREG(a0), 10f
+	fixup REG_S   t1,  4*SZREG(a0), 10f
+	fixup REG_S   t2,  5*SZREG(a0), 10f
+	fixup REG_S   t3,  6*SZREG(a0), 10f
+	fixup REG_S   t4,  7*SZREG(a0), 10f
+	addi	a0, a0, 8*SZREG
+	addi	a1, a1, 8*SZREG
+	bltu	a0, t0, 2b
+
+	addi	t0, t0, 8*SZREG /* revert to original value */
+	j	.Lbyte_copy_tail
+
+.Lshift_copy:
+
+	/*
+	 * Word copy with shifting.
+	 * For misaligned copy we still perform aligned word copy, but
+	 * we need to use the value fetched from the previous iteration and
+	 * do some shifts.
+	 * This is safe because reading is less than a word size.
+	 *
+	 * a0 - start of aligned dst
+	 * a1 - start of src
+	 * a3 - a1 & mask:(SZREG-1)
+	 * t0 - end of uncopied dst
+	 * t1 - end of aligned dst
+	 */
+	/* calculating aligned word boundary for dst */
+	andi	t1, t0, ~(SZREG-1)
+	/* Converting unaligned src to aligned src */
+	andi	a1, a1, ~(SZREG-1)
+
+	/*
+	 * Calculate shifts
+	 * t3 - prev shift
+	 * t4 - current shift
+	 */
+	slli	t3, a3, 3 /* converting bytes in a3 to bits */
+	li	a5, SZREG*8
+	sub	t4, a5, t3
+
+	/* Load the first word to combine with second word */
+	fixup REG_L   a5, 0(a1), 10f
+
+3:
+	/* Main shifting copy
+	 *
+	 * a0 - start of aligned dst
+	 * a1 - start of aligned src
+	 * t1 - end of aligned dst
+	 */
+
+	/* At least one iteration will be executed */
+	srl	a4, a5, t3
+	fixup REG_L   a5, SZREG(a1), 10f
+	addi	a1, a1, SZREG
+	sll	a2, a5, t4
+	or	a2, a2, a4
+	fixup REG_S   a2, 0(a0), 10f
+	addi	a0, a0, SZREG
+	bltu	a0, t1, 3b
+
+	/* Revert src to original unaligned value  */
+	add	a1, a1, a3
+
+.Lbyte_copy_tail:
+	/*
+	 * Byte copy anything left.
+	 *
+	 * a0 - start of remaining dst
+	 * a1 - start of remaining src
+	 * t0 - end of remaining dst
+	 */
+	bgeu	a0, t0, .Lout_copy_user  /* check if end of copy */
+4:
+	fixup lb      a5, 0(a1), 10f
+	addi	a1, a1, 1	/* src */
+	fixup sb      a5, 0(a0), 10f
+	addi	a0, a0, 1	/* dst */
+	bltu	a0, t0, 4b	/* t0 - end of dst */
+
+.Lout_copy_user:
+	/* Disable access to user memory */
+	csrc CSR_STATUS, t6
+	li	a0, 0
+	ret
+
+	/* Exception fixup code */
+10:
+	/* Disable access to user memory */
+	csrc CSR_STATUS, t6
+	sub a0, t5, a0
+	ret
+ENDPROC(__asm_copy_to_user)
+ENDPROC(__asm_copy_from_user)
+EXPORT_SYMBOL(__asm_copy_to_user)
+EXPORT_SYMBOL(__asm_copy_from_user)
+
+
+ENTRY(__clear_user)
+
+	/* Enable access to user memory */
+	li t6, SR_SUM
+	csrs CSR_STATUS, t6
+
+	add a3, a0, a1
+	addi t0, a0, SZREG-1
+	andi t1, a3, ~(SZREG-1)
+	andi t0, t0, ~(SZREG-1)
+	/*
+	 * a3: terminal address of target region
+	 * t0: lowest doubleword-aligned address in target region
+	 * t1: highest doubleword-aligned address in target region
+	 */
+	bgeu t0, t1, 2f
+	bltu a0, t0, 4f
+1:
+	fixup REG_S, zero, (a0), 11f
+	addi a0, a0, SZREG
+	bltu a0, t1, 1b
+2:
+	bltu a0, a3, 5f
+
+3:
+	/* Disable access to user memory */
+	csrc CSR_STATUS, t6
+	li a0, 0
+	ret
+4: /* Edge case: unalignment */
+	fixup sb, zero, (a0), 11f
+	addi a0, a0, 1
+	bltu a0, t0, 4b
+	j 1b
+5: /* Edge case: remainder */
+	fixup sb, zero, (a0), 11f
+	addi a0, a0, 1
+	bltu a0, a3, 5b
+	j 3b
+
+	/* Exception fixup code */
+11:
+	/* Disable access to user memory */
+	csrc CSR_STATUS, t6
+	sub a0, a3, a0
+	ret
+ENDPROC(__clear_user)
+EXPORT_SYMBOL(__clear_user)
diff --git a/arch/riscv/mm/Makefile b/arch/riscv/mm/Makefile
new file mode 100644
index 000000000..d76aabf4b
--- /dev/null
+++ b/arch/riscv/mm/Makefile
@@ -0,0 +1,33 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+CFLAGS_init.o := -mcmodel=medany
+ifdef CONFIG_FTRACE
+CFLAGS_REMOVE_init.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_cacheflush.o = $(CC_FLAGS_FTRACE)
+endif
+
+KCOV_INSTRUMENT_init.o := n
+
+obj-y += init.o
+obj-y += extable.o
+obj-$(CONFIG_MMU) += fault.o pageattr.o
+obj-y += cacheflush.o
+obj-y += context.o
+
+ifeq ($(CONFIG_MMU),y)
+obj-$(CONFIG_SMP) += tlbflush.o
+endif
+obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
+obj-$(CONFIG_PTDUMP_CORE) += ptdump.o
+obj-$(CONFIG_KASAN)   += kasan_init.o
+
+ifdef CONFIG_KASAN
+KASAN_SANITIZE_kasan_init.o := n
+KASAN_SANITIZE_init.o := n
+ifdef CONFIG_DEBUG_VIRTUAL
+KASAN_SANITIZE_physaddr.o := n
+endif
+endif
+
+obj-$(CONFIG_DEBUG_VIRTUAL) += physaddr.o
+obj-$(CONFIG_RISCV_DMA_NONCOHERENT) += dma-noncoherent.o
diff --git a/arch/riscv/mm/cacheflush.c b/arch/riscv/mm/cacheflush.c
new file mode 100644
index 000000000..8a2e7040f
--- /dev/null
+++ b/arch/riscv/mm/cacheflush.c
@@ -0,0 +1,128 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2017 SiFive
+ */
+
+#include <linux/of.h>
+#include <asm/cacheflush.h>
+
+#ifdef CONFIG_SMP
+
+#include <asm/sbi.h>
+
+static void ipi_remote_fence_i(void *info)
+{
+	return local_flush_icache_all();
+}
+
+void flush_icache_all(void)
+{
+	local_flush_icache_all();
+
+	if (IS_ENABLED(CONFIG_RISCV_SBI))
+		sbi_remote_fence_i(NULL);
+	else
+		on_each_cpu(ipi_remote_fence_i, NULL, 1);
+}
+EXPORT_SYMBOL(flush_icache_all);
+
+/*
+ * Performs an icache flush for the given MM context.  RISC-V has no direct
+ * mechanism for instruction cache shoot downs, so instead we send an IPI that
+ * informs the remote harts they need to flush their local instruction caches.
+ * To avoid pathologically slow behavior in a common case (a bunch of
+ * single-hart processes on a many-hart machine, ie 'make -j') we avoid the
+ * IPIs for harts that are not currently executing a MM context and instead
+ * schedule a deferred local instruction cache flush to be performed before
+ * execution resumes on each hart.
+ */
+void flush_icache_mm(struct mm_struct *mm, bool local)
+{
+	unsigned int cpu;
+	cpumask_t others, *mask;
+
+	preempt_disable();
+
+	/* Mark every hart's icache as needing a flush for this MM. */
+	mask = &mm->context.icache_stale_mask;
+	cpumask_setall(mask);
+	/* Flush this hart's I$ now, and mark it as flushed. */
+	cpu = smp_processor_id();
+	cpumask_clear_cpu(cpu, mask);
+	local_flush_icache_all();
+
+	/*
+	 * Flush the I$ of other harts concurrently executing, and mark them as
+	 * flushed.
+	 */
+	cpumask_andnot(&others, mm_cpumask(mm), cpumask_of(cpu));
+	local |= cpumask_empty(&others);
+	if (mm == current->active_mm && local) {
+		/*
+		 * It's assumed that at least one strongly ordered operation is
+		 * performed on this hart between setting a hart's cpumask bit
+		 * and scheduling this MM context on that hart.  Sending an SBI
+		 * remote message will do this, but in the case where no
+		 * messages are sent we still need to order this hart's writes
+		 * with flush_icache_deferred().
+		 */
+		smp_mb();
+	} else if (IS_ENABLED(CONFIG_RISCV_SBI)) {
+		sbi_remote_fence_i(&others);
+	} else {
+		on_each_cpu_mask(&others, ipi_remote_fence_i, NULL, 1);
+	}
+
+	preempt_enable();
+}
+
+#endif /* CONFIG_SMP */
+
+#ifdef CONFIG_MMU
+void flush_icache_pte(pte_t pte)
+{
+	struct page *page = pte_page(pte);
+
+	if (!test_bit(PG_dcache_clean, &page->flags)) {
+		flush_icache_all();
+		set_bit(PG_dcache_clean, &page->flags);
+	}
+}
+#endif /* CONFIG_MMU */
+
+unsigned int riscv_cbom_block_size;
+EXPORT_SYMBOL_GPL(riscv_cbom_block_size);
+
+void riscv_init_cbom_blocksize(void)
+{
+	struct device_node *node;
+	unsigned long cbom_hartid;
+	u32 val, probed_block_size;
+	int ret;
+
+	probed_block_size = 0;
+	for_each_of_cpu_node(node) {
+		unsigned long hartid;
+
+		ret = riscv_of_processor_hartid(node, &hartid);
+		if (ret)
+			continue;
+
+		/* set block-size for cbom extension if available */
+		ret = of_property_read_u32(node, "riscv,cbom-block-size", &val);
+		if (ret)
+			continue;
+
+		if (!probed_block_size) {
+			probed_block_size = val;
+			cbom_hartid = hartid;
+		} else {
+			if (probed_block_size != val)
+				pr_warn("cbom-block-size mismatched between harts %lu and %lu\n",
+					cbom_hartid, hartid);
+		}
+	}
+
+	if (probed_block_size)
+		riscv_cbom_block_size = probed_block_size;
+}
diff --git a/arch/riscv/mm/context.c b/arch/riscv/mm/context.c
new file mode 100644
index 000000000..12e22e733
--- /dev/null
+++ b/arch/riscv/mm/context.c
@@ -0,0 +1,336 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ * Copyright (C) 2017 SiFive
+ * Copyright (C) 2021 Western Digital Corporation or its affiliates.
+ */
+
+#include <linux/bitops.h>
+#include <linux/cpumask.h>
+#include <linux/mm.h>
+#include <linux/percpu.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/static_key.h>
+#include <asm/tlbflush.h>
+#include <asm/cacheflush.h>
+#include <asm/mmu_context.h>
+
+#ifdef CONFIG_MMU
+
+DEFINE_STATIC_KEY_FALSE(use_asid_allocator);
+
+static unsigned long asid_bits;
+static unsigned long num_asids;
+unsigned long asid_mask;
+
+static atomic_long_t current_version;
+
+static DEFINE_RAW_SPINLOCK(context_lock);
+static cpumask_t context_tlb_flush_pending;
+static unsigned long *context_asid_map;
+
+static DEFINE_PER_CPU(atomic_long_t, active_context);
+static DEFINE_PER_CPU(unsigned long, reserved_context);
+
+static bool check_update_reserved_context(unsigned long cntx,
+					  unsigned long newcntx)
+{
+	int cpu;
+	bool hit = false;
+
+	/*
+	 * Iterate over the set of reserved CONTEXT looking for a match.
+	 * If we find one, then we can update our mm to use new CONTEXT
+	 * (i.e. the same CONTEXT in the current_version) but we can't
+	 * exit the loop early, since we need to ensure that all copies
+	 * of the old CONTEXT are updated to reflect the mm. Failure to do
+	 * so could result in us missing the reserved CONTEXT in a future
+	 * version.
+	 */
+	for_each_possible_cpu(cpu) {
+		if (per_cpu(reserved_context, cpu) == cntx) {
+			hit = true;
+			per_cpu(reserved_context, cpu) = newcntx;
+		}
+	}
+
+	return hit;
+}
+
+static void __flush_context(void)
+{
+	int i;
+	unsigned long cntx;
+
+	/* Must be called with context_lock held */
+	lockdep_assert_held(&context_lock);
+
+	/* Update the list of reserved ASIDs and the ASID bitmap. */
+	bitmap_clear(context_asid_map, 0, num_asids);
+
+	/* Mark already active ASIDs as used */
+	for_each_possible_cpu(i) {
+		cntx = atomic_long_xchg_relaxed(&per_cpu(active_context, i), 0);
+		/*
+		 * If this CPU has already been through a rollover, but
+		 * hasn't run another task in the meantime, we must preserve
+		 * its reserved CONTEXT, as this is the only trace we have of
+		 * the process it is still running.
+		 */
+		if (cntx == 0)
+			cntx = per_cpu(reserved_context, i);
+
+		__set_bit(cntx & asid_mask, context_asid_map);
+		per_cpu(reserved_context, i) = cntx;
+	}
+
+	/* Mark ASID #0 as used because it is used at boot-time */
+	__set_bit(0, context_asid_map);
+
+	/* Queue a TLB invalidation for each CPU on next context-switch */
+	cpumask_setall(&context_tlb_flush_pending);
+}
+
+static unsigned long __new_context(struct mm_struct *mm)
+{
+	static u32 cur_idx = 1;
+	unsigned long cntx = atomic_long_read(&mm->context.id);
+	unsigned long asid, ver = atomic_long_read(&current_version);
+
+	/* Must be called with context_lock held */
+	lockdep_assert_held(&context_lock);
+
+	if (cntx != 0) {
+		unsigned long newcntx = ver | (cntx & asid_mask);
+
+		/*
+		 * If our current CONTEXT was active during a rollover, we
+		 * can continue to use it and this was just a false alarm.
+		 */
+		if (check_update_reserved_context(cntx, newcntx))
+			return newcntx;
+
+		/*
+		 * We had a valid CONTEXT in a previous life, so try to
+		 * re-use it if possible.
+		 */
+		if (!__test_and_set_bit(cntx & asid_mask, context_asid_map))
+			return newcntx;
+	}
+
+	/*
+	 * Allocate a free ASID. If we can't find one then increment
+	 * current_version and flush all ASIDs.
+	 */
+	asid = find_next_zero_bit(context_asid_map, num_asids, cur_idx);
+	if (asid != num_asids)
+		goto set_asid;
+
+	/* We're out of ASIDs, so increment current_version */
+	ver = atomic_long_add_return_relaxed(num_asids, &current_version);
+
+	/* Flush everything  */
+	__flush_context();
+
+	/* We have more ASIDs than CPUs, so this will always succeed */
+	asid = find_next_zero_bit(context_asid_map, num_asids, 1);
+
+set_asid:
+	__set_bit(asid, context_asid_map);
+	cur_idx = asid;
+	return asid | ver;
+}
+
+static void set_mm_asid(struct mm_struct *mm, unsigned int cpu)
+{
+	unsigned long flags;
+	bool need_flush_tlb = false;
+	unsigned long cntx, old_active_cntx;
+
+	cntx = atomic_long_read(&mm->context.id);
+
+	/*
+	 * If our active_context is non-zero and the context matches the
+	 * current_version, then we update the active_context entry with a
+	 * relaxed cmpxchg.
+	 *
+	 * Following is how we handle racing with a concurrent rollover:
+	 *
+	 * - We get a zero back from the cmpxchg and end up waiting on the
+	 *   lock. Taking the lock synchronises with the rollover and so
+	 *   we are forced to see the updated verion.
+	 *
+	 * - We get a valid context back from the cmpxchg then we continue
+	 *   using old ASID because __flush_context() would have marked ASID
+	 *   of active_context as used and next context switch we will
+	 *   allocate new context.
+	 */
+	old_active_cntx = atomic_long_read(&per_cpu(active_context, cpu));
+	if (old_active_cntx &&
+	    ((cntx & ~asid_mask) == atomic_long_read(&current_version)) &&
+	    atomic_long_cmpxchg_relaxed(&per_cpu(active_context, cpu),
+					old_active_cntx, cntx))
+		goto switch_mm_fast;
+
+	raw_spin_lock_irqsave(&context_lock, flags);
+
+	/* Check that our ASID belongs to the current_version. */
+	cntx = atomic_long_read(&mm->context.id);
+	if ((cntx & ~asid_mask) != atomic_long_read(&current_version)) {
+		cntx = __new_context(mm);
+		atomic_long_set(&mm->context.id, cntx);
+	}
+
+	if (cpumask_test_and_clear_cpu(cpu, &context_tlb_flush_pending))
+		need_flush_tlb = true;
+
+	atomic_long_set(&per_cpu(active_context, cpu), cntx);
+
+	raw_spin_unlock_irqrestore(&context_lock, flags);
+
+switch_mm_fast:
+	csr_write(CSR_SATP, virt_to_pfn(mm->pgd) |
+		  ((cntx & asid_mask) << SATP_ASID_SHIFT) |
+		  satp_mode);
+
+	if (need_flush_tlb)
+		local_flush_tlb_all();
+}
+
+static void set_mm_noasid(struct mm_struct *mm)
+{
+	/* Switch the page table and blindly nuke entire local TLB */
+	csr_write(CSR_SATP, virt_to_pfn(mm->pgd) | satp_mode);
+	local_flush_tlb_all();
+}
+
+static inline void set_mm(struct mm_struct *prev,
+			  struct mm_struct *next, unsigned int cpu)
+{
+	/*
+	 * The mm_cpumask indicates which harts' TLBs contain the virtual
+	 * address mapping of the mm. Compared to noasid, using asid
+	 * can't guarantee that stale TLB entries are invalidated because
+	 * the asid mechanism wouldn't flush TLB for every switch_mm for
+	 * performance. So when using asid, keep all CPUs footmarks in
+	 * cpumask() until mm reset.
+	 */
+	cpumask_set_cpu(cpu, mm_cpumask(next));
+	if (static_branch_unlikely(&use_asid_allocator)) {
+		set_mm_asid(next, cpu);
+	} else {
+		cpumask_clear_cpu(cpu, mm_cpumask(prev));
+		set_mm_noasid(next);
+	}
+}
+
+static int __init asids_init(void)
+{
+	unsigned long old;
+
+	/* Figure-out number of ASID bits in HW */
+	old = csr_read(CSR_SATP);
+	asid_bits = old | (SATP_ASID_MASK << SATP_ASID_SHIFT);
+	csr_write(CSR_SATP, asid_bits);
+	asid_bits = (csr_read(CSR_SATP) >> SATP_ASID_SHIFT)  & SATP_ASID_MASK;
+	asid_bits = fls_long(asid_bits);
+	csr_write(CSR_SATP, old);
+
+	/*
+	 * In the process of determining number of ASID bits (above)
+	 * we polluted the TLB of current HART so let's do TLB flushed
+	 * to remove unwanted TLB enteries.
+	 */
+	local_flush_tlb_all();
+
+	/* Pre-compute ASID details */
+	if (asid_bits) {
+		num_asids = 1 << asid_bits;
+		asid_mask = num_asids - 1;
+	}
+
+	/*
+	 * Use ASID allocator only if number of HW ASIDs are
+	 * at-least twice more than CPUs
+	 */
+	if (num_asids > (2 * num_possible_cpus())) {
+		atomic_long_set(&current_version, num_asids);
+
+		context_asid_map = bitmap_zalloc(num_asids, GFP_KERNEL);
+		if (!context_asid_map)
+			panic("Failed to allocate bitmap for %lu ASIDs\n",
+			      num_asids);
+
+		__set_bit(0, context_asid_map);
+
+		static_branch_enable(&use_asid_allocator);
+
+		pr_info("ASID allocator using %lu bits (%lu entries)\n",
+			asid_bits, num_asids);
+	} else {
+		pr_info("ASID allocator disabled (%lu bits)\n", asid_bits);
+	}
+
+	return 0;
+}
+early_initcall(asids_init);
+#else
+static inline void set_mm(struct mm_struct *prev,
+			  struct mm_struct *next, unsigned int cpu)
+{
+	/* Nothing to do here when there is no MMU */
+}
+#endif
+
+/*
+ * When necessary, performs a deferred icache flush for the given MM context,
+ * on the local CPU.  RISC-V has no direct mechanism for instruction cache
+ * shoot downs, so instead we send an IPI that informs the remote harts they
+ * need to flush their local instruction caches.  To avoid pathologically slow
+ * behavior in a common case (a bunch of single-hart processes on a many-hart
+ * machine, ie 'make -j') we avoid the IPIs for harts that are not currently
+ * executing a MM context and instead schedule a deferred local instruction
+ * cache flush to be performed before execution resumes on each hart.  This
+ * actually performs that local instruction cache flush, which implicitly only
+ * refers to the current hart.
+ *
+ * The "cpu" argument must be the current local CPU number.
+ */
+static inline void flush_icache_deferred(struct mm_struct *mm, unsigned int cpu)
+{
+#ifdef CONFIG_SMP
+	cpumask_t *mask = &mm->context.icache_stale_mask;
+
+	if (cpumask_test_cpu(cpu, mask)) {
+		cpumask_clear_cpu(cpu, mask);
+		/*
+		 * Ensure the remote hart's writes are visible to this hart.
+		 * This pairs with a barrier in flush_icache_mm.
+		 */
+		smp_mb();
+		local_flush_icache_all();
+	}
+
+#endif
+}
+
+void switch_mm(struct mm_struct *prev, struct mm_struct *next,
+	struct task_struct *task)
+{
+	unsigned int cpu;
+
+	if (unlikely(prev == next))
+		return;
+
+	/*
+	 * Mark the current MM context as inactive, and the next as
+	 * active.  This is at least used by the icache flushing
+	 * routines in order to determine who should be flushed.
+	 */
+	cpu = smp_processor_id();
+
+	set_mm(prev, next, cpu);
+
+	flush_icache_deferred(next, cpu);
+}
diff --git a/arch/riscv/mm/dma-noncoherent.c b/arch/riscv/mm/dma-noncoherent.c
new file mode 100644
index 000000000..d919efab6
--- /dev/null
+++ b/arch/riscv/mm/dma-noncoherent.c
@@ -0,0 +1,80 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * RISC-V specific functions to support DMA for non-coherent devices
+ *
+ * Copyright (c) 2021 Western Digital Corporation or its affiliates.
+ */
+
+#include <linux/dma-direct.h>
+#include <linux/dma-map-ops.h>
+#include <linux/mm.h>
+#include <asm/cacheflush.h>
+
+static bool noncoherent_supported;
+
+void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+			      enum dma_data_direction dir)
+{
+	void *vaddr = phys_to_virt(paddr);
+
+	switch (dir) {
+	case DMA_TO_DEVICE:
+		ALT_CMO_OP(clean, vaddr, size, riscv_cbom_block_size);
+		break;
+	case DMA_FROM_DEVICE:
+		ALT_CMO_OP(clean, vaddr, size, riscv_cbom_block_size);
+		break;
+	case DMA_BIDIRECTIONAL:
+		ALT_CMO_OP(flush, vaddr, size, riscv_cbom_block_size);
+		break;
+	default:
+		break;
+	}
+}
+
+void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+			   enum dma_data_direction dir)
+{
+	void *vaddr = phys_to_virt(paddr);
+
+	switch (dir) {
+	case DMA_TO_DEVICE:
+		break;
+	case DMA_FROM_DEVICE:
+	case DMA_BIDIRECTIONAL:
+		ALT_CMO_OP(flush, vaddr, size, riscv_cbom_block_size);
+		break;
+	default:
+		break;
+	}
+}
+
+void arch_dma_prep_coherent(struct page *page, size_t size)
+{
+	void *flush_addr = page_address(page);
+
+	ALT_CMO_OP(flush, flush_addr, size, riscv_cbom_block_size);
+}
+
+void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
+		const struct iommu_ops *iommu, bool coherent)
+{
+	WARN_TAINT(!coherent && riscv_cbom_block_size > ARCH_DMA_MINALIGN,
+		   TAINT_CPU_OUT_OF_SPEC,
+		   "%s %s: ARCH_DMA_MINALIGN smaller than riscv,cbom-block-size (%d < %d)",
+		   dev_driver_string(dev), dev_name(dev),
+		   ARCH_DMA_MINALIGN, riscv_cbom_block_size);
+
+	WARN_TAINT(!coherent && !noncoherent_supported, TAINT_CPU_OUT_OF_SPEC,
+		   "%s %s: device non-coherent but no non-coherent operations supported",
+		   dev_driver_string(dev), dev_name(dev));
+
+	dev->dma_coherent = coherent;
+}
+
+void riscv_noncoherent_supported(void)
+{
+	WARN(!riscv_cbom_block_size,
+	     "Non-coherent DMA support enabled without a block size\n");
+	noncoherent_supported = true;
+}
diff --git a/arch/riscv/mm/extable.c b/arch/riscv/mm/extable.c
new file mode 100644
index 000000000..35484d830
--- /dev/null
+++ b/arch/riscv/mm/extable.c
@@ -0,0 +1,71 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2009 Sunplus Core Technology Co., Ltd.
+ *  Lennox Wu <lennox.wu@sunplusct.com>
+ *  Chen Liqin <liqin.chen@sunplusct.com>
+ * Copyright (C) 2013 Regents of the University of California
+ */
+
+
+#include <linux/bitfield.h>
+#include <linux/extable.h>
+#include <linux/module.h>
+#include <linux/uaccess.h>
+#include <asm/asm-extable.h>
+#include <asm/ptrace.h>
+
+static inline unsigned long
+get_ex_fixup(const struct exception_table_entry *ex)
+{
+	return ((unsigned long)&ex->fixup + ex->fixup);
+}
+
+static bool ex_handler_fixup(const struct exception_table_entry *ex,
+			     struct pt_regs *regs)
+{
+	regs->epc = get_ex_fixup(ex);
+	return true;
+}
+
+static inline void regs_set_gpr(struct pt_regs *regs, unsigned int offset,
+				unsigned long val)
+{
+	if (unlikely(offset > MAX_REG_OFFSET))
+		return;
+
+	if (offset)
+		*(unsigned long *)((unsigned long)regs + offset) = val;
+}
+
+static bool ex_handler_uaccess_err_zero(const struct exception_table_entry *ex,
+					struct pt_regs *regs)
+{
+	int reg_err = FIELD_GET(EX_DATA_REG_ERR, ex->data);
+	int reg_zero = FIELD_GET(EX_DATA_REG_ZERO, ex->data);
+
+	regs_set_gpr(regs, reg_err * sizeof(unsigned long), -EFAULT);
+	regs_set_gpr(regs, reg_zero * sizeof(unsigned long), 0);
+
+	regs->epc = get_ex_fixup(ex);
+	return true;
+}
+
+bool fixup_exception(struct pt_regs *regs)
+{
+	const struct exception_table_entry *ex;
+
+	ex = search_exception_tables(regs->epc);
+	if (!ex)
+		return false;
+
+	switch (ex->type) {
+	case EX_TYPE_FIXUP:
+		return ex_handler_fixup(ex, regs);
+	case EX_TYPE_BPF:
+		return ex_handler_bpf(ex, regs);
+	case EX_TYPE_UACCESS_ERR_ZERO:
+		return ex_handler_uaccess_err_zero(ex, regs);
+	}
+
+	BUG();
+}
diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c
new file mode 100644
index 000000000..274bc6dd8
--- /dev/null
+++ b/arch/riscv/mm/fault.c
@@ -0,0 +1,351 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2009 Sunplus Core Technology Co., Ltd.
+ *  Lennox Wu <lennox.wu@sunplusct.com>
+ *  Chen Liqin <liqin.chen@sunplusct.com>
+ * Copyright (C) 2012 Regents of the University of California
+ */
+
+
+#include <linux/mm.h>
+#include <linux/kernel.h>
+#include <linux/interrupt.h>
+#include <linux/perf_event.h>
+#include <linux/signal.h>
+#include <linux/uaccess.h>
+#include <linux/kprobes.h>
+#include <linux/kfence.h>
+
+#include <asm/ptrace.h>
+#include <asm/tlbflush.h>
+
+#include "../kernel/head.h"
+
+static void die_kernel_fault(const char *msg, unsigned long addr,
+		struct pt_regs *regs)
+{
+	bust_spinlocks(1);
+
+	pr_alert("Unable to handle kernel %s at virtual address " REG_FMT "\n", msg,
+		addr);
+
+	bust_spinlocks(0);
+	die(regs, "Oops");
+	make_task_dead(SIGKILL);
+}
+
+static inline void no_context(struct pt_regs *regs, unsigned long addr)
+{
+	const char *msg;
+
+	/* Are we prepared to handle this kernel fault? */
+	if (fixup_exception(regs))
+		return;
+
+	/*
+	 * Oops. The kernel tried to access some bad page. We'll have to
+	 * terminate things with extreme prejudice.
+	 */
+	if (addr < PAGE_SIZE)
+		msg = "NULL pointer dereference";
+	else {
+		if (kfence_handle_page_fault(addr, regs->cause == EXC_STORE_PAGE_FAULT, regs))
+			return;
+
+		msg = "paging request";
+	}
+
+	die_kernel_fault(msg, addr, regs);
+}
+
+static inline void mm_fault_error(struct pt_regs *regs, unsigned long addr, vm_fault_t fault)
+{
+	if (fault & VM_FAULT_OOM) {
+		/*
+		 * We ran out of memory, call the OOM killer, and return the userspace
+		 * (which will retry the fault, or kill us if we got oom-killed).
+		 */
+		if (!user_mode(regs)) {
+			no_context(regs, addr);
+			return;
+		}
+		pagefault_out_of_memory();
+		return;
+	} else if (fault & VM_FAULT_SIGBUS) {
+		/* Kernel mode? Handle exceptions or die */
+		if (!user_mode(regs)) {
+			no_context(regs, addr);
+			return;
+		}
+		do_trap(regs, SIGBUS, BUS_ADRERR, addr);
+		return;
+	}
+	BUG();
+}
+
+static inline void
+bad_area_nosemaphore(struct pt_regs *regs, int code, unsigned long addr)
+{
+	/*
+	 * Something tried to access memory that isn't in our memory map.
+	 * Fix it, but check if it's kernel or user first.
+	 */
+	/* User mode accesses just cause a SIGSEGV */
+	if (user_mode(regs)) {
+		do_trap(regs, SIGSEGV, code, addr);
+		return;
+	}
+
+	no_context(regs, addr);
+}
+
+static inline void
+bad_area(struct pt_regs *regs, struct mm_struct *mm, int code,
+	 unsigned long addr)
+{
+	mmap_read_unlock(mm);
+
+	bad_area_nosemaphore(regs, code, addr);
+}
+
+static inline void vmalloc_fault(struct pt_regs *regs, int code, unsigned long addr)
+{
+	pgd_t *pgd, *pgd_k;
+	pud_t *pud_k;
+	p4d_t *p4d_k;
+	pmd_t *pmd_k;
+	pte_t *pte_k;
+	int index;
+	unsigned long pfn;
+
+	/* User mode accesses just cause a SIGSEGV */
+	if (user_mode(regs))
+		return do_trap(regs, SIGSEGV, code, addr);
+
+	/*
+	 * Synchronize this task's top level page-table
+	 * with the 'reference' page table.
+	 *
+	 * Do _not_ use "tsk->active_mm->pgd" here.
+	 * We might be inside an interrupt in the middle
+	 * of a task switch.
+	 */
+	index = pgd_index(addr);
+	pfn = csr_read(CSR_SATP) & SATP_PPN;
+	pgd = (pgd_t *)pfn_to_virt(pfn) + index;
+	pgd_k = init_mm.pgd + index;
+
+	if (!pgd_present(*pgd_k)) {
+		no_context(regs, addr);
+		return;
+	}
+	set_pgd(pgd, *pgd_k);
+
+	p4d_k = p4d_offset(pgd_k, addr);
+	if (!p4d_present(*p4d_k)) {
+		no_context(regs, addr);
+		return;
+	}
+
+	pud_k = pud_offset(p4d_k, addr);
+	if (!pud_present(*pud_k)) {
+		no_context(regs, addr);
+		return;
+	}
+
+	/*
+	 * Since the vmalloc area is global, it is unnecessary
+	 * to copy individual PTEs
+	 */
+	pmd_k = pmd_offset(pud_k, addr);
+	if (!pmd_present(*pmd_k)) {
+		no_context(regs, addr);
+		return;
+	}
+
+	/*
+	 * Make sure the actual PTE exists as well to
+	 * catch kernel vmalloc-area accesses to non-mapped
+	 * addresses. If we don't do this, this will just
+	 * silently loop forever.
+	 */
+	pte_k = pte_offset_kernel(pmd_k, addr);
+	if (!pte_present(*pte_k)) {
+		no_context(regs, addr);
+		return;
+	}
+
+	/*
+	 * The kernel assumes that TLBs don't cache invalid
+	 * entries, but in RISC-V, SFENCE.VMA specifies an
+	 * ordering constraint, not a cache flush; it is
+	 * necessary even after writing invalid entries.
+	 */
+	local_flush_tlb_page(addr);
+}
+
+static inline bool access_error(unsigned long cause, struct vm_area_struct *vma)
+{
+	switch (cause) {
+	case EXC_INST_PAGE_FAULT:
+		if (!(vma->vm_flags & VM_EXEC)) {
+			return true;
+		}
+		break;
+	case EXC_LOAD_PAGE_FAULT:
+		/* Write implies read */
+		if (!(vma->vm_flags & (VM_READ | VM_WRITE))) {
+			return true;
+		}
+		break;
+	case EXC_STORE_PAGE_FAULT:
+		if (!(vma->vm_flags & VM_WRITE)) {
+			return true;
+		}
+		break;
+	default:
+		panic("%s: unhandled cause %lu", __func__, cause);
+	}
+	return false;
+}
+
+/*
+ * This routine handles page faults.  It determines the address and the
+ * problem, and then passes it off to one of the appropriate routines.
+ */
+asmlinkage void do_page_fault(struct pt_regs *regs)
+{
+	struct task_struct *tsk;
+	struct vm_area_struct *vma;
+	struct mm_struct *mm;
+	unsigned long addr, cause;
+	unsigned int flags = FAULT_FLAG_DEFAULT;
+	int code = SEGV_MAPERR;
+	vm_fault_t fault;
+
+	cause = regs->cause;
+	addr = regs->badaddr;
+
+	tsk = current;
+	mm = tsk->mm;
+
+	if (kprobe_page_fault(regs, cause))
+		return;
+
+	/*
+	 * Fault-in kernel-space virtual memory on-demand.
+	 * The 'reference' page table is init_mm.pgd.
+	 *
+	 * NOTE! We MUST NOT take any locks for this case. We may
+	 * be in an interrupt or a critical region, and should
+	 * only copy the information from the master page table,
+	 * nothing more.
+	 */
+	if (unlikely((addr >= VMALLOC_START) && (addr < VMALLOC_END))) {
+		vmalloc_fault(regs, code, addr);
+		return;
+	}
+
+#ifdef CONFIG_64BIT
+	/*
+	 * Modules in 64bit kernels lie in their own virtual region which is not
+	 * in the vmalloc region, but dealing with page faults in this region
+	 * or the vmalloc region amounts to doing the same thing: checking that
+	 * the mapping exists in init_mm.pgd and updating user page table, so
+	 * just use vmalloc_fault.
+	 */
+	if (unlikely(addr >= MODULES_VADDR && addr < MODULES_END)) {
+		vmalloc_fault(regs, code, addr);
+		return;
+	}
+#endif
+	/* Enable interrupts if they were enabled in the parent context. */
+	if (likely(regs->status & SR_PIE))
+		local_irq_enable();
+
+	/*
+	 * If we're in an interrupt, have no user context, or are running
+	 * in an atomic region, then we must not take the fault.
+	 */
+	if (unlikely(faulthandler_disabled() || !mm)) {
+		tsk->thread.bad_cause = cause;
+		no_context(regs, addr);
+		return;
+	}
+
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
+
+	if (!user_mode(regs) && addr < TASK_SIZE && unlikely(!(regs->status & SR_SUM))) {
+		if (fixup_exception(regs))
+			return;
+
+		die_kernel_fault("access to user memory without uaccess routines", addr, regs);
+	}
+
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
+
+	if (cause == EXC_STORE_PAGE_FAULT)
+		flags |= FAULT_FLAG_WRITE;
+	else if (cause == EXC_INST_PAGE_FAULT)
+		flags |= FAULT_FLAG_INSTRUCTION;
+retry:
+	vma = lock_mm_and_find_vma(mm, addr, regs);
+	if (unlikely(!vma)) {
+		tsk->thread.bad_cause = cause;
+		bad_area_nosemaphore(regs, code, addr);
+		return;
+	}
+
+	/*
+	 * Ok, we have a good vm_area for this memory access, so
+	 * we can handle it.
+	 */
+	code = SEGV_ACCERR;
+
+	if (unlikely(access_error(cause, vma))) {
+		tsk->thread.bad_cause = cause;
+		bad_area(regs, mm, code, addr);
+		return;
+	}
+
+	/*
+	 * If for any reason at all we could not handle the fault,
+	 * make sure we exit gracefully rather than endlessly redo
+	 * the fault.
+	 */
+	fault = handle_mm_fault(vma, addr, flags, regs);
+
+	/*
+	 * If we need to retry but a fatal signal is pending, handle the
+	 * signal first. We do not need to release the mmap_lock because it
+	 * would already be released in __lock_page_or_retry in mm/filemap.c.
+	 */
+	if (fault_signal_pending(fault, regs))
+		return;
+
+	/* The fault is fully completed (including releasing mmap lock) */
+	if (fault & VM_FAULT_COMPLETED)
+		return;
+
+	if (unlikely(fault & VM_FAULT_RETRY)) {
+		flags |= FAULT_FLAG_TRIED;
+
+		/*
+		 * No need to mmap_read_unlock(mm) as we would
+		 * have already released it in __lock_page_or_retry
+		 * in mm/filemap.c.
+		 */
+		goto retry;
+	}
+
+	mmap_read_unlock(mm);
+
+	if (unlikely(fault & VM_FAULT_ERROR)) {
+		tsk->thread.bad_cause = cause;
+		mm_fault_error(regs, addr, fault);
+		return;
+	}
+	return;
+}
+NOKPROBE_SYMBOL(do_page_fault);
diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c
new file mode 100644
index 000000000..932dadfdc
--- /dev/null
+++ b/arch/riscv/mm/hugetlbpage.c
@@ -0,0 +1,34 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/hugetlb.h>
+#include <linux/err.h>
+
+int pud_huge(pud_t pud)
+{
+	return pud_leaf(pud);
+}
+
+int pmd_huge(pmd_t pmd)
+{
+	return pmd_leaf(pmd);
+}
+
+bool __init arch_hugetlb_valid_size(unsigned long size)
+{
+	if (size == HPAGE_SIZE)
+		return true;
+	else if (IS_ENABLED(CONFIG_64BIT) && size == PUD_SIZE)
+		return true;
+	else
+		return false;
+}
+
+#ifdef CONFIG_CONTIG_ALLOC
+static __init int gigantic_pages_init(void)
+{
+	/* With CONTIG_ALLOC, we can allocate gigantic pages at runtime */
+	if (IS_ENABLED(CONFIG_64BIT))
+		hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
+	return 0;
+}
+arch_initcall(gigantic_pages_init);
+#endif
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
new file mode 100644
index 000000000..7c4852af9
--- /dev/null
+++ b/arch/riscv/mm/init.c
@@ -0,0 +1,1234 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ * Copyright (C) 2019 Western Digital Corporation or its affiliates.
+ * Copyright (C) 2020 FORTH-ICS/CARV
+ *  Nick Kossifidis <mick@ics.forth.gr>
+ */
+
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/memblock.h>
+#include <linux/initrd.h>
+#include <linux/swap.h>
+#include <linux/swiotlb.h>
+#include <linux/sizes.h>
+#include <linux/of_fdt.h>
+#include <linux/of_reserved_mem.h>
+#include <linux/libfdt.h>
+#include <linux/set_memory.h>
+#include <linux/dma-map-ops.h>
+#include <linux/crash_dump.h>
+#include <linux/hugetlb.h>
+
+#include <asm/fixmap.h>
+#include <asm/tlbflush.h>
+#include <asm/sections.h>
+#include <asm/soc.h>
+#include <asm/io.h>
+#include <asm/ptdump.h>
+#include <asm/numa.h>
+
+#include "../kernel/head.h"
+
+struct kernel_mapping kernel_map __ro_after_init;
+EXPORT_SYMBOL(kernel_map);
+#ifdef CONFIG_XIP_KERNEL
+#define kernel_map	(*(struct kernel_mapping *)XIP_FIXUP(&kernel_map))
+#endif
+
+#ifdef CONFIG_64BIT
+u64 satp_mode __ro_after_init = !IS_ENABLED(CONFIG_XIP_KERNEL) ? SATP_MODE_57 : SATP_MODE_39;
+#else
+u64 satp_mode __ro_after_init = SATP_MODE_32;
+#endif
+EXPORT_SYMBOL(satp_mode);
+
+bool pgtable_l4_enabled = IS_ENABLED(CONFIG_64BIT) && !IS_ENABLED(CONFIG_XIP_KERNEL);
+bool pgtable_l5_enabled = IS_ENABLED(CONFIG_64BIT) && !IS_ENABLED(CONFIG_XIP_KERNEL);
+EXPORT_SYMBOL(pgtable_l4_enabled);
+EXPORT_SYMBOL(pgtable_l5_enabled);
+
+phys_addr_t phys_ram_base __ro_after_init;
+EXPORT_SYMBOL(phys_ram_base);
+
+unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]
+							__page_aligned_bss;
+EXPORT_SYMBOL(empty_zero_page);
+
+extern char _start[];
+void *_dtb_early_va __initdata;
+uintptr_t _dtb_early_pa __initdata;
+
+static phys_addr_t dma32_phys_limit __initdata;
+
+static void __init zone_sizes_init(void)
+{
+	unsigned long max_zone_pfns[MAX_NR_ZONES] = { 0, };
+
+#ifdef CONFIG_ZONE_DMA32
+	max_zone_pfns[ZONE_DMA32] = PFN_DOWN(dma32_phys_limit);
+#endif
+	max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
+
+	free_area_init(max_zone_pfns);
+}
+
+#if defined(CONFIG_MMU) && defined(CONFIG_DEBUG_VM)
+
+#define LOG2_SZ_1K  ilog2(SZ_1K)
+#define LOG2_SZ_1M  ilog2(SZ_1M)
+#define LOG2_SZ_1G  ilog2(SZ_1G)
+#define LOG2_SZ_1T  ilog2(SZ_1T)
+
+static inline void print_mlk(char *name, unsigned long b, unsigned long t)
+{
+	pr_notice("%12s : 0x%08lx - 0x%08lx   (%4ld kB)\n", name, b, t,
+		  (((t) - (b)) >> LOG2_SZ_1K));
+}
+
+static inline void print_mlm(char *name, unsigned long b, unsigned long t)
+{
+	pr_notice("%12s : 0x%08lx - 0x%08lx   (%4ld MB)\n", name, b, t,
+		  (((t) - (b)) >> LOG2_SZ_1M));
+}
+
+static inline void print_mlg(char *name, unsigned long b, unsigned long t)
+{
+	pr_notice("%12s : 0x%08lx - 0x%08lx   (%4ld GB)\n", name, b, t,
+		   (((t) - (b)) >> LOG2_SZ_1G));
+}
+
+#ifdef CONFIG_64BIT
+static inline void print_mlt(char *name, unsigned long b, unsigned long t)
+{
+	pr_notice("%12s : 0x%08lx - 0x%08lx   (%4ld TB)\n", name, b, t,
+		   (((t) - (b)) >> LOG2_SZ_1T));
+}
+#else
+#define print_mlt(n, b, t) do {} while (0)
+#endif
+
+static inline void print_ml(char *name, unsigned long b, unsigned long t)
+{
+	unsigned long diff = t - b;
+
+	if (IS_ENABLED(CONFIG_64BIT) && (diff >> LOG2_SZ_1T) >= 10)
+		print_mlt(name, b, t);
+	else if ((diff >> LOG2_SZ_1G) >= 10)
+		print_mlg(name, b, t);
+	else if ((diff >> LOG2_SZ_1M) >= 10)
+		print_mlm(name, b, t);
+	else
+		print_mlk(name, b, t);
+}
+
+static void __init print_vm_layout(void)
+{
+	pr_notice("Virtual kernel memory layout:\n");
+	print_ml("fixmap", (unsigned long)FIXADDR_START,
+		(unsigned long)FIXADDR_TOP);
+	print_ml("pci io", (unsigned long)PCI_IO_START,
+		(unsigned long)PCI_IO_END);
+	print_ml("vmemmap", (unsigned long)VMEMMAP_START,
+		(unsigned long)VMEMMAP_END);
+	print_ml("vmalloc", (unsigned long)VMALLOC_START,
+		(unsigned long)VMALLOC_END);
+#ifdef CONFIG_64BIT
+	print_ml("modules", (unsigned long)MODULES_VADDR,
+		(unsigned long)MODULES_END);
+#endif
+	print_ml("lowmem", (unsigned long)PAGE_OFFSET,
+		(unsigned long)high_memory);
+	if (IS_ENABLED(CONFIG_64BIT)) {
+#ifdef CONFIG_KASAN
+		print_ml("kasan", KASAN_SHADOW_START, KASAN_SHADOW_END);
+#endif
+
+		print_ml("kernel", (unsigned long)KERNEL_LINK_ADDR,
+			 (unsigned long)ADDRESS_SPACE_END);
+	}
+}
+#else
+static void print_vm_layout(void) { }
+#endif /* CONFIG_DEBUG_VM */
+
+void __init mem_init(void)
+{
+#ifdef CONFIG_FLATMEM
+	BUG_ON(!mem_map);
+#endif /* CONFIG_FLATMEM */
+
+	swiotlb_init(max_pfn > PFN_DOWN(dma32_phys_limit), SWIOTLB_VERBOSE);
+	memblock_free_all();
+
+	print_vm_layout();
+}
+
+/* Limit the memory size via mem. */
+static phys_addr_t memory_limit;
+
+static int __init early_mem(char *p)
+{
+	u64 size;
+
+	if (!p)
+		return 1;
+
+	size = memparse(p, &p) & PAGE_MASK;
+	memory_limit = min_t(u64, size, memory_limit);
+
+	pr_notice("Memory limited to %lldMB\n", (u64)memory_limit >> 20);
+
+	return 0;
+}
+early_param("mem", early_mem);
+
+static void __init setup_bootmem(void)
+{
+	phys_addr_t vmlinux_end = __pa_symbol(&_end);
+	phys_addr_t max_mapped_addr;
+	phys_addr_t phys_ram_end, vmlinux_start;
+
+	if (IS_ENABLED(CONFIG_XIP_KERNEL))
+		vmlinux_start = __pa_symbol(&_sdata);
+	else
+		vmlinux_start = __pa_symbol(&_start);
+
+	memblock_enforce_memory_limit(memory_limit);
+
+	/*
+	 * Make sure we align the reservation on PMD_SIZE since we will
+	 * map the kernel in the linear mapping as read-only: we do not want
+	 * any allocation to happen between _end and the next pmd aligned page.
+	 */
+	if (IS_ENABLED(CONFIG_64BIT) && IS_ENABLED(CONFIG_STRICT_KERNEL_RWX))
+		vmlinux_end = (vmlinux_end + PMD_SIZE - 1) & PMD_MASK;
+	/*
+	 * Reserve from the start of the kernel to the end of the kernel
+	 */
+	memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start);
+
+	phys_ram_end = memblock_end_of_DRAM();
+	if (!IS_ENABLED(CONFIG_XIP_KERNEL))
+		phys_ram_base = memblock_start_of_DRAM();
+	/*
+	 * memblock allocator is not aware of the fact that last 4K bytes of
+	 * the addressable memory can not be mapped because of IS_ERR_VALUE
+	 * macro. Make sure that last 4k bytes are not usable by memblock
+	 * if end of dram is equal to maximum addressable memory.  For 64-bit
+	 * kernel, this problem can't happen here as the end of the virtual
+	 * address space is occupied by the kernel mapping then this check must
+	 * be done as soon as the kernel mapping base address is determined.
+	 */
+	if (!IS_ENABLED(CONFIG_64BIT)) {
+		max_mapped_addr = __pa(~(ulong)0);
+		if (max_mapped_addr == (phys_ram_end - 1))
+			memblock_set_current_limit(max_mapped_addr - 4096);
+	}
+
+	min_low_pfn = PFN_UP(phys_ram_base);
+	max_low_pfn = max_pfn = PFN_DOWN(phys_ram_end);
+	high_memory = (void *)(__va(PFN_PHYS(max_low_pfn)));
+
+	dma32_phys_limit = min(4UL * SZ_1G, (unsigned long)PFN_PHYS(max_low_pfn));
+	set_max_mapnr(max_low_pfn - ARCH_PFN_OFFSET);
+
+	reserve_initrd_mem();
+
+	/*
+	 * No allocation should be done before reserving the memory as defined
+	 * in the device tree, otherwise the allocation could end up in a
+	 * reserved region.
+	 */
+	early_init_fdt_scan_reserved_mem();
+
+	/*
+	 * If DTB is built in, no need to reserve its memblock.
+	 * Otherwise, do reserve it but avoid using
+	 * early_init_fdt_reserve_self() since __pa() does
+	 * not work for DTB pointers that are fixmap addresses
+	 */
+	if (!IS_ENABLED(CONFIG_BUILTIN_DTB))
+		memblock_reserve(dtb_early_pa, fdt_totalsize(dtb_early_va));
+
+	dma_contiguous_reserve(dma32_phys_limit);
+	if (IS_ENABLED(CONFIG_64BIT))
+		hugetlb_cma_reserve(PUD_SHIFT - PAGE_SHIFT);
+}
+
+#ifdef CONFIG_MMU
+struct pt_alloc_ops pt_ops __initdata;
+
+unsigned long riscv_pfn_base __ro_after_init;
+EXPORT_SYMBOL(riscv_pfn_base);
+
+pgd_t swapper_pg_dir[PTRS_PER_PGD] __page_aligned_bss;
+pgd_t trampoline_pg_dir[PTRS_PER_PGD] __page_aligned_bss;
+static pte_t fixmap_pte[PTRS_PER_PTE] __page_aligned_bss;
+
+pgd_t early_pg_dir[PTRS_PER_PGD] __initdata __aligned(PAGE_SIZE);
+
+#ifdef CONFIG_XIP_KERNEL
+#define pt_ops			(*(struct pt_alloc_ops *)XIP_FIXUP(&pt_ops))
+#define riscv_pfn_base         (*(unsigned long  *)XIP_FIXUP(&riscv_pfn_base))
+#define trampoline_pg_dir      ((pgd_t *)XIP_FIXUP(trampoline_pg_dir))
+#define fixmap_pte             ((pte_t *)XIP_FIXUP(fixmap_pte))
+#define early_pg_dir           ((pgd_t *)XIP_FIXUP(early_pg_dir))
+#endif /* CONFIG_XIP_KERNEL */
+
+static const pgprot_t protection_map[16] = {
+	[VM_NONE]					= PAGE_NONE,
+	[VM_READ]					= PAGE_READ,
+	[VM_WRITE]					= PAGE_COPY,
+	[VM_WRITE | VM_READ]				= PAGE_COPY,
+	[VM_EXEC]					= PAGE_EXEC,
+	[VM_EXEC | VM_READ]				= PAGE_READ_EXEC,
+	[VM_EXEC | VM_WRITE]				= PAGE_COPY_EXEC,
+	[VM_EXEC | VM_WRITE | VM_READ]			= PAGE_COPY_EXEC,
+	[VM_SHARED]					= PAGE_NONE,
+	[VM_SHARED | VM_READ]				= PAGE_READ,
+	[VM_SHARED | VM_WRITE]				= PAGE_SHARED,
+	[VM_SHARED | VM_WRITE | VM_READ]		= PAGE_SHARED,
+	[VM_SHARED | VM_EXEC]				= PAGE_EXEC,
+	[VM_SHARED | VM_EXEC | VM_READ]			= PAGE_READ_EXEC,
+	[VM_SHARED | VM_EXEC | VM_WRITE]		= PAGE_SHARED_EXEC,
+	[VM_SHARED | VM_EXEC | VM_WRITE | VM_READ]	= PAGE_SHARED_EXEC
+};
+DECLARE_VM_GET_PAGE_PROT
+
+void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t prot)
+{
+	unsigned long addr = __fix_to_virt(idx);
+	pte_t *ptep;
+
+	BUG_ON(idx <= FIX_HOLE || idx >= __end_of_fixed_addresses);
+
+	ptep = &fixmap_pte[pte_index(addr)];
+
+	if (pgprot_val(prot))
+		set_pte(ptep, pfn_pte(phys >> PAGE_SHIFT, prot));
+	else
+		pte_clear(&init_mm, addr, ptep);
+	local_flush_tlb_page(addr);
+}
+
+static inline pte_t *__init get_pte_virt_early(phys_addr_t pa)
+{
+	return (pte_t *)((uintptr_t)pa);
+}
+
+static inline pte_t *__init get_pte_virt_fixmap(phys_addr_t pa)
+{
+	clear_fixmap(FIX_PTE);
+	return (pte_t *)set_fixmap_offset(FIX_PTE, pa);
+}
+
+static inline pte_t *__init get_pte_virt_late(phys_addr_t pa)
+{
+	return (pte_t *) __va(pa);
+}
+
+static inline phys_addr_t __init alloc_pte_early(uintptr_t va)
+{
+	/*
+	 * We only create PMD or PGD early mappings so we
+	 * should never reach here with MMU disabled.
+	 */
+	BUG();
+}
+
+static inline phys_addr_t __init alloc_pte_fixmap(uintptr_t va)
+{
+	return memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE);
+}
+
+static phys_addr_t __init alloc_pte_late(uintptr_t va)
+{
+	unsigned long vaddr;
+
+	vaddr = __get_free_page(GFP_KERNEL);
+	BUG_ON(!vaddr || !pgtable_pte_page_ctor(virt_to_page(vaddr)));
+
+	return __pa(vaddr);
+}
+
+static void __init create_pte_mapping(pte_t *ptep,
+				      uintptr_t va, phys_addr_t pa,
+				      phys_addr_t sz, pgprot_t prot)
+{
+	uintptr_t pte_idx = pte_index(va);
+
+	BUG_ON(sz != PAGE_SIZE);
+
+	if (pte_none(ptep[pte_idx]))
+		ptep[pte_idx] = pfn_pte(PFN_DOWN(pa), prot);
+}
+
+#ifndef __PAGETABLE_PMD_FOLDED
+
+static pmd_t trampoline_pmd[PTRS_PER_PMD] __page_aligned_bss;
+static pmd_t fixmap_pmd[PTRS_PER_PMD] __page_aligned_bss;
+static pmd_t early_pmd[PTRS_PER_PMD] __initdata __aligned(PAGE_SIZE);
+
+#ifdef CONFIG_XIP_KERNEL
+#define trampoline_pmd ((pmd_t *)XIP_FIXUP(trampoline_pmd))
+#define fixmap_pmd     ((pmd_t *)XIP_FIXUP(fixmap_pmd))
+#define early_pmd      ((pmd_t *)XIP_FIXUP(early_pmd))
+#endif /* CONFIG_XIP_KERNEL */
+
+static p4d_t trampoline_p4d[PTRS_PER_P4D] __page_aligned_bss;
+static p4d_t fixmap_p4d[PTRS_PER_P4D] __page_aligned_bss;
+static p4d_t early_p4d[PTRS_PER_P4D] __initdata __aligned(PAGE_SIZE);
+
+#ifdef CONFIG_XIP_KERNEL
+#define trampoline_p4d ((p4d_t *)XIP_FIXUP(trampoline_p4d))
+#define fixmap_p4d     ((p4d_t *)XIP_FIXUP(fixmap_p4d))
+#define early_p4d      ((p4d_t *)XIP_FIXUP(early_p4d))
+#endif /* CONFIG_XIP_KERNEL */
+
+static pud_t trampoline_pud[PTRS_PER_PUD] __page_aligned_bss;
+static pud_t fixmap_pud[PTRS_PER_PUD] __page_aligned_bss;
+static pud_t early_pud[PTRS_PER_PUD] __initdata __aligned(PAGE_SIZE);
+
+#ifdef CONFIG_XIP_KERNEL
+#define trampoline_pud ((pud_t *)XIP_FIXUP(trampoline_pud))
+#define fixmap_pud     ((pud_t *)XIP_FIXUP(fixmap_pud))
+#define early_pud      ((pud_t *)XIP_FIXUP(early_pud))
+#endif /* CONFIG_XIP_KERNEL */
+
+static pmd_t *__init get_pmd_virt_early(phys_addr_t pa)
+{
+	/* Before MMU is enabled */
+	return (pmd_t *)((uintptr_t)pa);
+}
+
+static pmd_t *__init get_pmd_virt_fixmap(phys_addr_t pa)
+{
+	clear_fixmap(FIX_PMD);
+	return (pmd_t *)set_fixmap_offset(FIX_PMD, pa);
+}
+
+static pmd_t *__init get_pmd_virt_late(phys_addr_t pa)
+{
+	return (pmd_t *) __va(pa);
+}
+
+static phys_addr_t __init alloc_pmd_early(uintptr_t va)
+{
+	BUG_ON((va - kernel_map.virt_addr) >> PUD_SHIFT);
+
+	return (uintptr_t)early_pmd;
+}
+
+static phys_addr_t __init alloc_pmd_fixmap(uintptr_t va)
+{
+	return memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE);
+}
+
+static phys_addr_t __init alloc_pmd_late(uintptr_t va)
+{
+	unsigned long vaddr;
+
+	vaddr = __get_free_page(GFP_KERNEL);
+	BUG_ON(!vaddr || !pgtable_pmd_page_ctor(virt_to_page(vaddr)));
+
+	return __pa(vaddr);
+}
+
+static void __init create_pmd_mapping(pmd_t *pmdp,
+				      uintptr_t va, phys_addr_t pa,
+				      phys_addr_t sz, pgprot_t prot)
+{
+	pte_t *ptep;
+	phys_addr_t pte_phys;
+	uintptr_t pmd_idx = pmd_index(va);
+
+	if (sz == PMD_SIZE) {
+		if (pmd_none(pmdp[pmd_idx]))
+			pmdp[pmd_idx] = pfn_pmd(PFN_DOWN(pa), prot);
+		return;
+	}
+
+	if (pmd_none(pmdp[pmd_idx])) {
+		pte_phys = pt_ops.alloc_pte(va);
+		pmdp[pmd_idx] = pfn_pmd(PFN_DOWN(pte_phys), PAGE_TABLE);
+		ptep = pt_ops.get_pte_virt(pte_phys);
+		memset(ptep, 0, PAGE_SIZE);
+	} else {
+		pte_phys = PFN_PHYS(_pmd_pfn(pmdp[pmd_idx]));
+		ptep = pt_ops.get_pte_virt(pte_phys);
+	}
+
+	create_pte_mapping(ptep, va, pa, sz, prot);
+}
+
+static pud_t *__init get_pud_virt_early(phys_addr_t pa)
+{
+	return (pud_t *)((uintptr_t)pa);
+}
+
+static pud_t *__init get_pud_virt_fixmap(phys_addr_t pa)
+{
+	clear_fixmap(FIX_PUD);
+	return (pud_t *)set_fixmap_offset(FIX_PUD, pa);
+}
+
+static pud_t *__init get_pud_virt_late(phys_addr_t pa)
+{
+	return (pud_t *)__va(pa);
+}
+
+static phys_addr_t __init alloc_pud_early(uintptr_t va)
+{
+	/* Only one PUD is available for early mapping */
+	BUG_ON((va - kernel_map.virt_addr) >> PGDIR_SHIFT);
+
+	return (uintptr_t)early_pud;
+}
+
+static phys_addr_t __init alloc_pud_fixmap(uintptr_t va)
+{
+	return memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE);
+}
+
+static phys_addr_t alloc_pud_late(uintptr_t va)
+{
+	unsigned long vaddr;
+
+	vaddr = __get_free_page(GFP_KERNEL);
+	BUG_ON(!vaddr);
+	return __pa(vaddr);
+}
+
+static p4d_t *__init get_p4d_virt_early(phys_addr_t pa)
+{
+	return (p4d_t *)((uintptr_t)pa);
+}
+
+static p4d_t *__init get_p4d_virt_fixmap(phys_addr_t pa)
+{
+	clear_fixmap(FIX_P4D);
+	return (p4d_t *)set_fixmap_offset(FIX_P4D, pa);
+}
+
+static p4d_t *__init get_p4d_virt_late(phys_addr_t pa)
+{
+	return (p4d_t *)__va(pa);
+}
+
+static phys_addr_t __init alloc_p4d_early(uintptr_t va)
+{
+	/* Only one P4D is available for early mapping */
+	BUG_ON((va - kernel_map.virt_addr) >> PGDIR_SHIFT);
+
+	return (uintptr_t)early_p4d;
+}
+
+static phys_addr_t __init alloc_p4d_fixmap(uintptr_t va)
+{
+	return memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE);
+}
+
+static phys_addr_t alloc_p4d_late(uintptr_t va)
+{
+	unsigned long vaddr;
+
+	vaddr = __get_free_page(GFP_KERNEL);
+	BUG_ON(!vaddr);
+	return __pa(vaddr);
+}
+
+static void __init create_pud_mapping(pud_t *pudp,
+				      uintptr_t va, phys_addr_t pa,
+				      phys_addr_t sz, pgprot_t prot)
+{
+	pmd_t *nextp;
+	phys_addr_t next_phys;
+	uintptr_t pud_index = pud_index(va);
+
+	if (sz == PUD_SIZE) {
+		if (pud_val(pudp[pud_index]) == 0)
+			pudp[pud_index] = pfn_pud(PFN_DOWN(pa), prot);
+		return;
+	}
+
+	if (pud_val(pudp[pud_index]) == 0) {
+		next_phys = pt_ops.alloc_pmd(va);
+		pudp[pud_index] = pfn_pud(PFN_DOWN(next_phys), PAGE_TABLE);
+		nextp = pt_ops.get_pmd_virt(next_phys);
+		memset(nextp, 0, PAGE_SIZE);
+	} else {
+		next_phys = PFN_PHYS(_pud_pfn(pudp[pud_index]));
+		nextp = pt_ops.get_pmd_virt(next_phys);
+	}
+
+	create_pmd_mapping(nextp, va, pa, sz, prot);
+}
+
+static void __init create_p4d_mapping(p4d_t *p4dp,
+				      uintptr_t va, phys_addr_t pa,
+				      phys_addr_t sz, pgprot_t prot)
+{
+	pud_t *nextp;
+	phys_addr_t next_phys;
+	uintptr_t p4d_index = p4d_index(va);
+
+	if (sz == P4D_SIZE) {
+		if (p4d_val(p4dp[p4d_index]) == 0)
+			p4dp[p4d_index] = pfn_p4d(PFN_DOWN(pa), prot);
+		return;
+	}
+
+	if (p4d_val(p4dp[p4d_index]) == 0) {
+		next_phys = pt_ops.alloc_pud(va);
+		p4dp[p4d_index] = pfn_p4d(PFN_DOWN(next_phys), PAGE_TABLE);
+		nextp = pt_ops.get_pud_virt(next_phys);
+		memset(nextp, 0, PAGE_SIZE);
+	} else {
+		next_phys = PFN_PHYS(_p4d_pfn(p4dp[p4d_index]));
+		nextp = pt_ops.get_pud_virt(next_phys);
+	}
+
+	create_pud_mapping(nextp, va, pa, sz, prot);
+}
+
+#define pgd_next_t		p4d_t
+#define alloc_pgd_next(__va)	(pgtable_l5_enabled ?			\
+		pt_ops.alloc_p4d(__va) : (pgtable_l4_enabled ?		\
+		pt_ops.alloc_pud(__va) : pt_ops.alloc_pmd(__va)))
+#define get_pgd_next_virt(__pa)	(pgtable_l5_enabled ?			\
+		pt_ops.get_p4d_virt(__pa) : (pgd_next_t *)(pgtable_l4_enabled ?	\
+		pt_ops.get_pud_virt(__pa) : (pud_t *)pt_ops.get_pmd_virt(__pa)))
+#define create_pgd_next_mapping(__nextp, __va, __pa, __sz, __prot)	\
+				(pgtable_l5_enabled ?			\
+		create_p4d_mapping(__nextp, __va, __pa, __sz, __prot) : \
+				(pgtable_l4_enabled ?			\
+		create_pud_mapping((pud_t *)__nextp, __va, __pa, __sz, __prot) :	\
+		create_pmd_mapping((pmd_t *)__nextp, __va, __pa, __sz, __prot)))
+#define fixmap_pgd_next		(pgtable_l5_enabled ?			\
+		(uintptr_t)fixmap_p4d : (pgtable_l4_enabled ?		\
+		(uintptr_t)fixmap_pud : (uintptr_t)fixmap_pmd))
+#define trampoline_pgd_next	(pgtable_l5_enabled ?			\
+		(uintptr_t)trampoline_p4d : (pgtable_l4_enabled ?	\
+		(uintptr_t)trampoline_pud : (uintptr_t)trampoline_pmd))
+#else
+#define pgd_next_t		pte_t
+#define alloc_pgd_next(__va)	pt_ops.alloc_pte(__va)
+#define get_pgd_next_virt(__pa)	pt_ops.get_pte_virt(__pa)
+#define create_pgd_next_mapping(__nextp, __va, __pa, __sz, __prot)	\
+	create_pte_mapping(__nextp, __va, __pa, __sz, __prot)
+#define fixmap_pgd_next		((uintptr_t)fixmap_pte)
+#define create_p4d_mapping(__pmdp, __va, __pa, __sz, __prot) do {} while(0)
+#define create_pud_mapping(__pmdp, __va, __pa, __sz, __prot) do {} while(0)
+#define create_pmd_mapping(__pmdp, __va, __pa, __sz, __prot) do {} while(0)
+#endif /* __PAGETABLE_PMD_FOLDED */
+
+void __init create_pgd_mapping(pgd_t *pgdp,
+				      uintptr_t va, phys_addr_t pa,
+				      phys_addr_t sz, pgprot_t prot)
+{
+	pgd_next_t *nextp;
+	phys_addr_t next_phys;
+	uintptr_t pgd_idx = pgd_index(va);
+
+	if (sz == PGDIR_SIZE) {
+		if (pgd_val(pgdp[pgd_idx]) == 0)
+			pgdp[pgd_idx] = pfn_pgd(PFN_DOWN(pa), prot);
+		return;
+	}
+
+	if (pgd_val(pgdp[pgd_idx]) == 0) {
+		next_phys = alloc_pgd_next(va);
+		pgdp[pgd_idx] = pfn_pgd(PFN_DOWN(next_phys), PAGE_TABLE);
+		nextp = get_pgd_next_virt(next_phys);
+		memset(nextp, 0, PAGE_SIZE);
+	} else {
+		next_phys = PFN_PHYS(_pgd_pfn(pgdp[pgd_idx]));
+		nextp = get_pgd_next_virt(next_phys);
+	}
+
+	create_pgd_next_mapping(nextp, va, pa, sz, prot);
+}
+
+static uintptr_t __init best_map_size(phys_addr_t base, phys_addr_t size)
+{
+	/* Upgrade to PMD_SIZE mappings whenever possible */
+	if ((base & (PMD_SIZE - 1)) || (size & (PMD_SIZE - 1)))
+		return PAGE_SIZE;
+
+	return PMD_SIZE;
+}
+
+#ifdef CONFIG_XIP_KERNEL
+#define phys_ram_base  (*(phys_addr_t *)XIP_FIXUP(&phys_ram_base))
+extern char _xiprom[], _exiprom[], __data_loc;
+
+/* called from head.S with MMU off */
+asmlinkage void __init __copy_data(void)
+{
+	void *from = (void *)(&__data_loc);
+	void *to = (void *)CONFIG_PHYS_RAM_BASE;
+	size_t sz = (size_t)((uintptr_t)(&_end) - (uintptr_t)(&_sdata));
+
+	memcpy(to, from, sz);
+}
+#endif
+
+#ifdef CONFIG_STRICT_KERNEL_RWX
+static __init pgprot_t pgprot_from_va(uintptr_t va)
+{
+	if (is_va_kernel_text(va))
+		return PAGE_KERNEL_READ_EXEC;
+
+	/*
+	 * In 64-bit kernel, the kernel mapping is outside the linear mapping so
+	 * we must protect its linear mapping alias from being executed and
+	 * written.
+	 * And rodata section is marked readonly in mark_rodata_ro.
+	 */
+	if (IS_ENABLED(CONFIG_64BIT) && is_va_kernel_lm_alias_text(va))
+		return PAGE_KERNEL_READ;
+
+	return PAGE_KERNEL;
+}
+
+void mark_rodata_ro(void)
+{
+	set_kernel_memory(__start_rodata, _data, set_memory_ro);
+	if (IS_ENABLED(CONFIG_64BIT))
+		set_kernel_memory(lm_alias(__start_rodata), lm_alias(_data),
+				  set_memory_ro);
+
+	debug_checkwx();
+}
+#else
+static __init pgprot_t pgprot_from_va(uintptr_t va)
+{
+	if (IS_ENABLED(CONFIG_64BIT) && !is_kernel_mapping(va))
+		return PAGE_KERNEL;
+
+	return PAGE_KERNEL_EXEC;
+}
+#endif /* CONFIG_STRICT_KERNEL_RWX */
+
+#if defined(CONFIG_64BIT) && !defined(CONFIG_XIP_KERNEL)
+static void __init disable_pgtable_l5(void)
+{
+	pgtable_l5_enabled = false;
+	kernel_map.page_offset = PAGE_OFFSET_L4;
+	satp_mode = SATP_MODE_48;
+}
+
+static void __init disable_pgtable_l4(void)
+{
+	pgtable_l4_enabled = false;
+	kernel_map.page_offset = PAGE_OFFSET_L3;
+	satp_mode = SATP_MODE_39;
+}
+
+/*
+ * There is a simple way to determine if 4-level is supported by the
+ * underlying hardware: establish 1:1 mapping in 4-level page table mode
+ * then read SATP to see if the configuration was taken into account
+ * meaning sv48 is supported.
+ */
+static __init void set_satp_mode(void)
+{
+	u64 identity_satp, hw_satp;
+	uintptr_t set_satp_mode_pmd = ((unsigned long)set_satp_mode) & PMD_MASK;
+	bool check_l4 = false;
+
+	create_p4d_mapping(early_p4d,
+			set_satp_mode_pmd, (uintptr_t)early_pud,
+			P4D_SIZE, PAGE_TABLE);
+	create_pud_mapping(early_pud,
+			   set_satp_mode_pmd, (uintptr_t)early_pmd,
+			   PUD_SIZE, PAGE_TABLE);
+	/* Handle the case where set_satp_mode straddles 2 PMDs */
+	create_pmd_mapping(early_pmd,
+			   set_satp_mode_pmd, set_satp_mode_pmd,
+			   PMD_SIZE, PAGE_KERNEL_EXEC);
+	create_pmd_mapping(early_pmd,
+			   set_satp_mode_pmd + PMD_SIZE,
+			   set_satp_mode_pmd + PMD_SIZE,
+			   PMD_SIZE, PAGE_KERNEL_EXEC);
+retry:
+	create_pgd_mapping(early_pg_dir,
+			   set_satp_mode_pmd,
+			   check_l4 ? (uintptr_t)early_pud : (uintptr_t)early_p4d,
+			   PGDIR_SIZE, PAGE_TABLE);
+
+	identity_satp = PFN_DOWN((uintptr_t)&early_pg_dir) | satp_mode;
+
+	local_flush_tlb_all();
+	csr_write(CSR_SATP, identity_satp);
+	hw_satp = csr_swap(CSR_SATP, 0ULL);
+	local_flush_tlb_all();
+
+	if (hw_satp != identity_satp) {
+		if (!check_l4) {
+			disable_pgtable_l5();
+			check_l4 = true;
+			memset(early_pg_dir, 0, PAGE_SIZE);
+			goto retry;
+		}
+		disable_pgtable_l4();
+	}
+
+	memset(early_pg_dir, 0, PAGE_SIZE);
+	memset(early_p4d, 0, PAGE_SIZE);
+	memset(early_pud, 0, PAGE_SIZE);
+	memset(early_pmd, 0, PAGE_SIZE);
+}
+#endif
+
+/*
+ * setup_vm() is called from head.S with MMU-off.
+ *
+ * Following requirements should be honoured for setup_vm() to work
+ * correctly:
+ * 1) It should use PC-relative addressing for accessing kernel symbols.
+ *    To achieve this we always use GCC cmodel=medany.
+ * 2) The compiler instrumentation for FTRACE will not work for setup_vm()
+ *    so disable compiler instrumentation when FTRACE is enabled.
+ *
+ * Currently, the above requirements are honoured by using custom CFLAGS
+ * for init.o in mm/Makefile.
+ */
+
+#ifndef __riscv_cmodel_medany
+#error "setup_vm() is called from head.S before relocate so it should not use absolute addressing."
+#endif
+
+#ifdef CONFIG_XIP_KERNEL
+static void __init create_kernel_page_table(pgd_t *pgdir,
+					    __always_unused bool early)
+{
+	uintptr_t va, end_va;
+
+	/* Map the flash resident part */
+	end_va = kernel_map.virt_addr + kernel_map.xiprom_sz;
+	for (va = kernel_map.virt_addr; va < end_va; va += PMD_SIZE)
+		create_pgd_mapping(pgdir, va,
+				   kernel_map.xiprom + (va - kernel_map.virt_addr),
+				   PMD_SIZE, PAGE_KERNEL_EXEC);
+
+	/* Map the data in RAM */
+	end_va = kernel_map.virt_addr + XIP_OFFSET + kernel_map.size;
+	for (va = kernel_map.virt_addr + XIP_OFFSET; va < end_va; va += PMD_SIZE)
+		create_pgd_mapping(pgdir, va,
+				   kernel_map.phys_addr + (va - (kernel_map.virt_addr + XIP_OFFSET)),
+				   PMD_SIZE, PAGE_KERNEL);
+}
+#else
+static void __init create_kernel_page_table(pgd_t *pgdir, bool early)
+{
+	uintptr_t va, end_va;
+
+	end_va = kernel_map.virt_addr + kernel_map.size;
+	for (va = kernel_map.virt_addr; va < end_va; va += PMD_SIZE)
+		create_pgd_mapping(pgdir, va,
+				   kernel_map.phys_addr + (va - kernel_map.virt_addr),
+				   PMD_SIZE,
+				   early ?
+					PAGE_KERNEL_EXEC : pgprot_from_va(va));
+}
+#endif
+
+/*
+ * Setup a 4MB mapping that encompasses the device tree: for 64-bit kernel,
+ * this means 2 PMD entries whereas for 32-bit kernel, this is only 1 PGDIR
+ * entry.
+ */
+static void __init create_fdt_early_page_table(uintptr_t fix_fdt_va,
+					       uintptr_t dtb_pa)
+{
+#ifndef CONFIG_BUILTIN_DTB
+	uintptr_t pa = dtb_pa & ~(PMD_SIZE - 1);
+
+	/* Make sure the fdt fixmap address is always aligned on PMD size */
+	BUILD_BUG_ON(FIX_FDT % (PMD_SIZE / PAGE_SIZE));
+
+	/* In 32-bit only, the fdt lies in its own PGD */
+	if (!IS_ENABLED(CONFIG_64BIT)) {
+		create_pgd_mapping(early_pg_dir, fix_fdt_va,
+				   pa, MAX_FDT_SIZE, PAGE_KERNEL);
+	} else {
+		create_pmd_mapping(fixmap_pmd, fix_fdt_va,
+				   pa, PMD_SIZE, PAGE_KERNEL);
+		create_pmd_mapping(fixmap_pmd, fix_fdt_va + PMD_SIZE,
+				   pa + PMD_SIZE, PMD_SIZE, PAGE_KERNEL);
+	}
+
+	dtb_early_va = (void *)fix_fdt_va + (dtb_pa & (PMD_SIZE - 1));
+#else
+	/*
+	 * For 64-bit kernel, __va can't be used since it would return a linear
+	 * mapping address whereas dtb_early_va will be used before
+	 * setup_vm_final installs the linear mapping. For 32-bit kernel, as the
+	 * kernel is mapped in the linear mapping, that makes no difference.
+	 */
+	dtb_early_va = kernel_mapping_pa_to_va(XIP_FIXUP(dtb_pa));
+#endif
+
+	dtb_early_pa = dtb_pa;
+}
+
+/*
+ * MMU is not enabled, the page tables are allocated directly using
+ * early_pmd/pud/p4d and the address returned is the physical one.
+ */
+static void __init pt_ops_set_early(void)
+{
+	pt_ops.alloc_pte = alloc_pte_early;
+	pt_ops.get_pte_virt = get_pte_virt_early;
+#ifndef __PAGETABLE_PMD_FOLDED
+	pt_ops.alloc_pmd = alloc_pmd_early;
+	pt_ops.get_pmd_virt = get_pmd_virt_early;
+	pt_ops.alloc_pud = alloc_pud_early;
+	pt_ops.get_pud_virt = get_pud_virt_early;
+	pt_ops.alloc_p4d = alloc_p4d_early;
+	pt_ops.get_p4d_virt = get_p4d_virt_early;
+#endif
+}
+
+/*
+ * MMU is enabled but page table setup is not complete yet.
+ * fixmap page table alloc functions must be used as a means to temporarily
+ * map the allocated physical pages since the linear mapping does not exist yet.
+ *
+ * Note that this is called with MMU disabled, hence kernel_mapping_pa_to_va,
+ * but it will be used as described above.
+ */
+static void __init pt_ops_set_fixmap(void)
+{
+	pt_ops.alloc_pte = kernel_mapping_pa_to_va((uintptr_t)alloc_pte_fixmap);
+	pt_ops.get_pte_virt = kernel_mapping_pa_to_va((uintptr_t)get_pte_virt_fixmap);
+#ifndef __PAGETABLE_PMD_FOLDED
+	pt_ops.alloc_pmd = kernel_mapping_pa_to_va((uintptr_t)alloc_pmd_fixmap);
+	pt_ops.get_pmd_virt = kernel_mapping_pa_to_va((uintptr_t)get_pmd_virt_fixmap);
+	pt_ops.alloc_pud = kernel_mapping_pa_to_va((uintptr_t)alloc_pud_fixmap);
+	pt_ops.get_pud_virt = kernel_mapping_pa_to_va((uintptr_t)get_pud_virt_fixmap);
+	pt_ops.alloc_p4d = kernel_mapping_pa_to_va((uintptr_t)alloc_p4d_fixmap);
+	pt_ops.get_p4d_virt = kernel_mapping_pa_to_va((uintptr_t)get_p4d_virt_fixmap);
+#endif
+}
+
+/*
+ * MMU is enabled and page table setup is complete, so from now, we can use
+ * generic page allocation functions to setup page table.
+ */
+static void __init pt_ops_set_late(void)
+{
+	pt_ops.alloc_pte = alloc_pte_late;
+	pt_ops.get_pte_virt = get_pte_virt_late;
+#ifndef __PAGETABLE_PMD_FOLDED
+	pt_ops.alloc_pmd = alloc_pmd_late;
+	pt_ops.get_pmd_virt = get_pmd_virt_late;
+	pt_ops.alloc_pud = alloc_pud_late;
+	pt_ops.get_pud_virt = get_pud_virt_late;
+	pt_ops.alloc_p4d = alloc_p4d_late;
+	pt_ops.get_p4d_virt = get_p4d_virt_late;
+#endif
+}
+
+asmlinkage void __init setup_vm(uintptr_t dtb_pa)
+{
+	pmd_t __maybe_unused fix_bmap_spmd, fix_bmap_epmd;
+
+	kernel_map.virt_addr = KERNEL_LINK_ADDR;
+	kernel_map.page_offset = _AC(CONFIG_PAGE_OFFSET, UL);
+
+#ifdef CONFIG_XIP_KERNEL
+	kernel_map.xiprom = (uintptr_t)CONFIG_XIP_PHYS_ADDR;
+	kernel_map.xiprom_sz = (uintptr_t)(&_exiprom) - (uintptr_t)(&_xiprom);
+
+	phys_ram_base = CONFIG_PHYS_RAM_BASE;
+	kernel_map.phys_addr = (uintptr_t)CONFIG_PHYS_RAM_BASE;
+	kernel_map.size = (uintptr_t)(&_end) - (uintptr_t)(&_sdata);
+
+	kernel_map.va_kernel_xip_pa_offset = kernel_map.virt_addr - kernel_map.xiprom;
+#else
+	kernel_map.phys_addr = (uintptr_t)(&_start);
+	kernel_map.size = (uintptr_t)(&_end) - kernel_map.phys_addr;
+#endif
+
+#if defined(CONFIG_64BIT) && !defined(CONFIG_XIP_KERNEL)
+	set_satp_mode();
+#endif
+
+	kernel_map.va_pa_offset = PAGE_OFFSET - kernel_map.phys_addr;
+	kernel_map.va_kernel_pa_offset = kernel_map.virt_addr - kernel_map.phys_addr;
+
+	riscv_pfn_base = PFN_DOWN(kernel_map.phys_addr);
+
+	/*
+	 * The default maximal physical memory size is KERN_VIRT_SIZE for 32-bit
+	 * kernel, whereas for 64-bit kernel, the end of the virtual address
+	 * space is occupied by the modules/BPF/kernel mappings which reduces
+	 * the available size of the linear mapping.
+	 */
+	memory_limit = KERN_VIRT_SIZE - (IS_ENABLED(CONFIG_64BIT) ? SZ_4G : 0);
+
+	/* Sanity check alignment and size */
+	BUG_ON((PAGE_OFFSET % PGDIR_SIZE) != 0);
+	BUG_ON((kernel_map.phys_addr % PMD_SIZE) != 0);
+
+#ifdef CONFIG_64BIT
+	/*
+	 * The last 4K bytes of the addressable memory can not be mapped because
+	 * of IS_ERR_VALUE macro.
+	 */
+	BUG_ON((kernel_map.virt_addr + kernel_map.size) > ADDRESS_SPACE_END - SZ_4K);
+#endif
+
+	apply_early_boot_alternatives();
+	pt_ops_set_early();
+
+	/* Setup early PGD for fixmap */
+	create_pgd_mapping(early_pg_dir, FIXADDR_START,
+			   fixmap_pgd_next, PGDIR_SIZE, PAGE_TABLE);
+
+#ifndef __PAGETABLE_PMD_FOLDED
+	/* Setup fixmap P4D and PUD */
+	if (pgtable_l5_enabled)
+		create_p4d_mapping(fixmap_p4d, FIXADDR_START,
+				   (uintptr_t)fixmap_pud, P4D_SIZE, PAGE_TABLE);
+	/* Setup fixmap PUD and PMD */
+	if (pgtable_l4_enabled)
+		create_pud_mapping(fixmap_pud, FIXADDR_START,
+				   (uintptr_t)fixmap_pmd, PUD_SIZE, PAGE_TABLE);
+	create_pmd_mapping(fixmap_pmd, FIXADDR_START,
+			   (uintptr_t)fixmap_pte, PMD_SIZE, PAGE_TABLE);
+	/* Setup trampoline PGD and PMD */
+	create_pgd_mapping(trampoline_pg_dir, kernel_map.virt_addr,
+			   trampoline_pgd_next, PGDIR_SIZE, PAGE_TABLE);
+	if (pgtable_l5_enabled)
+		create_p4d_mapping(trampoline_p4d, kernel_map.virt_addr,
+				   (uintptr_t)trampoline_pud, P4D_SIZE, PAGE_TABLE);
+	if (pgtable_l4_enabled)
+		create_pud_mapping(trampoline_pud, kernel_map.virt_addr,
+				   (uintptr_t)trampoline_pmd, PUD_SIZE, PAGE_TABLE);
+#ifdef CONFIG_XIP_KERNEL
+	create_pmd_mapping(trampoline_pmd, kernel_map.virt_addr,
+			   kernel_map.xiprom, PMD_SIZE, PAGE_KERNEL_EXEC);
+#else
+	create_pmd_mapping(trampoline_pmd, kernel_map.virt_addr,
+			   kernel_map.phys_addr, PMD_SIZE, PAGE_KERNEL_EXEC);
+#endif
+#else
+	/* Setup trampoline PGD */
+	create_pgd_mapping(trampoline_pg_dir, kernel_map.virt_addr,
+			   kernel_map.phys_addr, PGDIR_SIZE, PAGE_KERNEL_EXEC);
+#endif
+
+	/*
+	 * Setup early PGD covering entire kernel which will allow
+	 * us to reach paging_init(). We map all memory banks later
+	 * in setup_vm_final() below.
+	 */
+	create_kernel_page_table(early_pg_dir, true);
+
+	/* Setup early mapping for FDT early scan */
+	create_fdt_early_page_table(__fix_to_virt(FIX_FDT), dtb_pa);
+
+	/*
+	 * Bootime fixmap only can handle PMD_SIZE mapping. Thus, boot-ioremap
+	 * range can not span multiple pmds.
+	 */
+	BUG_ON((__fix_to_virt(FIX_BTMAP_BEGIN) >> PMD_SHIFT)
+		     != (__fix_to_virt(FIX_BTMAP_END) >> PMD_SHIFT));
+
+#ifndef __PAGETABLE_PMD_FOLDED
+	/*
+	 * Early ioremap fixmap is already created as it lies within first 2MB
+	 * of fixmap region. We always map PMD_SIZE. Thus, both FIX_BTMAP_END
+	 * FIX_BTMAP_BEGIN should lie in the same pmd. Verify that and warn
+	 * the user if not.
+	 */
+	fix_bmap_spmd = fixmap_pmd[pmd_index(__fix_to_virt(FIX_BTMAP_BEGIN))];
+	fix_bmap_epmd = fixmap_pmd[pmd_index(__fix_to_virt(FIX_BTMAP_END))];
+	if (pmd_val(fix_bmap_spmd) != pmd_val(fix_bmap_epmd)) {
+		WARN_ON(1);
+		pr_warn("fixmap btmap start [%08lx] != end [%08lx]\n",
+			pmd_val(fix_bmap_spmd), pmd_val(fix_bmap_epmd));
+		pr_warn("fix_to_virt(FIX_BTMAP_BEGIN): %08lx\n",
+			fix_to_virt(FIX_BTMAP_BEGIN));
+		pr_warn("fix_to_virt(FIX_BTMAP_END):   %08lx\n",
+			fix_to_virt(FIX_BTMAP_END));
+
+		pr_warn("FIX_BTMAP_END:       %d\n", FIX_BTMAP_END);
+		pr_warn("FIX_BTMAP_BEGIN:     %d\n", FIX_BTMAP_BEGIN);
+	}
+#endif
+
+	pt_ops_set_fixmap();
+}
+
+static void __init setup_vm_final(void)
+{
+	uintptr_t va, map_size;
+	phys_addr_t pa, start, end;
+	u64 i;
+
+	/* Setup swapper PGD for fixmap */
+#if !defined(CONFIG_64BIT)
+	/*
+	 * In 32-bit, the device tree lies in a pgd entry, so it must be copied
+	 * directly in swapper_pg_dir in addition to the pgd entry that points
+	 * to fixmap_pte.
+	 */
+	unsigned long idx = pgd_index(__fix_to_virt(FIX_FDT));
+
+	set_pgd(&swapper_pg_dir[idx], early_pg_dir[idx]);
+#endif
+	create_pgd_mapping(swapper_pg_dir, FIXADDR_START,
+			   __pa_symbol(fixmap_pgd_next),
+			   PGDIR_SIZE, PAGE_TABLE);
+
+	/* Map all memory banks in the linear mapping */
+	for_each_mem_range(i, &start, &end) {
+		if (start >= end)
+			break;
+		if (start <= __pa(PAGE_OFFSET) &&
+		    __pa(PAGE_OFFSET) < end)
+			start = __pa(PAGE_OFFSET);
+		if (end >= __pa(PAGE_OFFSET) + memory_limit)
+			end = __pa(PAGE_OFFSET) + memory_limit;
+
+		map_size = best_map_size(start, end - start);
+		for (pa = start; pa < end; pa += map_size) {
+			va = (uintptr_t)__va(pa);
+
+			create_pgd_mapping(swapper_pg_dir, va, pa, map_size,
+					   pgprot_from_va(va));
+		}
+	}
+
+	/* Map the kernel */
+	if (IS_ENABLED(CONFIG_64BIT))
+		create_kernel_page_table(swapper_pg_dir, false);
+
+#ifdef CONFIG_KASAN
+	kasan_swapper_init();
+#endif
+
+	/* Clear fixmap PTE and PMD mappings */
+	clear_fixmap(FIX_PTE);
+	clear_fixmap(FIX_PMD);
+	clear_fixmap(FIX_PUD);
+	clear_fixmap(FIX_P4D);
+
+	/* Move to swapper page table */
+	csr_write(CSR_SATP, PFN_DOWN(__pa_symbol(swapper_pg_dir)) | satp_mode);
+	local_flush_tlb_all();
+
+	pt_ops_set_late();
+}
+#else
+asmlinkage void __init setup_vm(uintptr_t dtb_pa)
+{
+	dtb_early_va = (void *)dtb_pa;
+	dtb_early_pa = dtb_pa;
+}
+
+static inline void setup_vm_final(void)
+{
+}
+#endif /* CONFIG_MMU */
+
+/*
+ * reserve_crashkernel() - reserves memory for crash kernel
+ *
+ * This function reserves memory area given in "crashkernel=" kernel command
+ * line parameter. The memory reserved is used by dump capture kernel when
+ * primary kernel is crashing.
+ */
+static void __init reserve_crashkernel(void)
+{
+	unsigned long long crash_base = 0;
+	unsigned long long crash_size = 0;
+	unsigned long search_start = memblock_start_of_DRAM();
+	unsigned long search_end = memblock_end_of_DRAM();
+
+	int ret = 0;
+
+	if (!IS_ENABLED(CONFIG_KEXEC_CORE))
+		return;
+	/*
+	 * Don't reserve a region for a crash kernel on a crash kernel
+	 * since it doesn't make much sense and we have limited memory
+	 * resources.
+	 */
+	if (is_kdump_kernel()) {
+		pr_info("crashkernel: ignoring reservation request\n");
+		return;
+	}
+
+	ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
+				&crash_size, &crash_base);
+	if (ret || !crash_size)
+		return;
+
+	crash_size = PAGE_ALIGN(crash_size);
+
+	if (crash_base) {
+		search_start = crash_base;
+		search_end = crash_base + crash_size;
+	}
+
+	/*
+	 * Current riscv boot protocol requires 2MB alignment for
+	 * RV64 and 4MB alignment for RV32 (hugepage size)
+	 *
+	 * Try to alloc from 32bit addressible physical memory so that
+	 * swiotlb can work on the crash kernel.
+	 */
+	crash_base = memblock_phys_alloc_range(crash_size, PMD_SIZE,
+					       search_start,
+					       min(search_end, (unsigned long)(SZ_4G - 1)));
+	if (crash_base == 0) {
+		/* Try again without restricting region to 32bit addressible memory */
+		crash_base = memblock_phys_alloc_range(crash_size, PMD_SIZE,
+						search_start, search_end);
+		if (crash_base == 0) {
+			pr_warn("crashkernel: couldn't allocate %lldKB\n",
+				crash_size >> 10);
+			return;
+		}
+	}
+
+	pr_info("crashkernel: reserved 0x%016llx - 0x%016llx (%lld MB)\n",
+		crash_base, crash_base + crash_size, crash_size >> 20);
+
+	crashk_res.start = crash_base;
+	crashk_res.end = crash_base + crash_size - 1;
+}
+
+void __init paging_init(void)
+{
+	setup_bootmem();
+	setup_vm_final();
+
+	/* Depend on that Linear Mapping is ready */
+	memblock_allow_resize();
+}
+
+void __init misc_mem_init(void)
+{
+	early_memtest(min_low_pfn << PAGE_SHIFT, max_low_pfn << PAGE_SHIFT);
+	arch_numa_init();
+	sparse_init();
+	zone_sizes_init();
+	reserve_crashkernel();
+	memblock_dump_all();
+}
+
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
+			       struct vmem_altmap *altmap)
+{
+	return vmemmap_populate_basepages(start, end, node, NULL);
+}
+#endif
diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c
new file mode 100644
index 000000000..e12267094
--- /dev/null
+++ b/arch/riscv/mm/kasan_init.c
@@ -0,0 +1,474 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2019 Andes Technology Corporation
+
+#include <linux/pfn.h>
+#include <linux/init_task.h>
+#include <linux/kasan.h>
+#include <linux/kernel.h>
+#include <linux/memblock.h>
+#include <linux/pgtable.h>
+#include <asm/tlbflush.h>
+#include <asm/fixmap.h>
+#include <asm/pgalloc.h>
+
+/*
+ * Kasan shadow region must lie at a fixed address across sv39, sv48 and sv57
+ * which is right before the kernel.
+ *
+ * For sv39, the region is aligned on PGDIR_SIZE so we only need to populate
+ * the page global directory with kasan_early_shadow_pmd.
+ *
+ * For sv48 and sv57, the region is not aligned on PGDIR_SIZE so the mapping
+ * must be divided as follows:
+ * - the first PGD entry, although incomplete, is populated with
+ *   kasan_early_shadow_pud/p4d
+ * - the PGD entries in the middle are populated with kasan_early_shadow_pud/p4d
+ * - the last PGD entry is shared with the kernel mapping so populated at the
+ *   lower levels pud/p4d
+ *
+ * In addition, when shallow populating a kasan region (for example vmalloc),
+ * this region may also not be aligned on PGDIR size, so we must go down to the
+ * pud level too.
+ */
+
+extern pgd_t early_pg_dir[PTRS_PER_PGD];
+
+static void __init kasan_populate_pte(pmd_t *pmd, unsigned long vaddr, unsigned long end)
+{
+	phys_addr_t phys_addr;
+	pte_t *ptep, *base_pte;
+
+	if (pmd_none(*pmd))
+		base_pte = memblock_alloc(PTRS_PER_PTE * sizeof(pte_t), PAGE_SIZE);
+	else
+		base_pte = (pte_t *)pmd_page_vaddr(*pmd);
+
+	ptep = base_pte + pte_index(vaddr);
+
+	do {
+		if (pte_none(*ptep)) {
+			phys_addr = memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE);
+			set_pte(ptep, pfn_pte(PFN_DOWN(phys_addr), PAGE_KERNEL));
+		}
+	} while (ptep++, vaddr += PAGE_SIZE, vaddr != end);
+
+	set_pmd(pmd, pfn_pmd(PFN_DOWN(__pa(base_pte)), PAGE_TABLE));
+}
+
+static void __init kasan_populate_pmd(pud_t *pud, unsigned long vaddr, unsigned long end)
+{
+	phys_addr_t phys_addr;
+	pmd_t *pmdp, *base_pmd;
+	unsigned long next;
+
+	if (pud_none(*pud)) {
+		base_pmd = memblock_alloc(PTRS_PER_PMD * sizeof(pmd_t), PAGE_SIZE);
+	} else {
+		base_pmd = (pmd_t *)pud_pgtable(*pud);
+		if (base_pmd == lm_alias(kasan_early_shadow_pmd))
+			base_pmd = memblock_alloc(PTRS_PER_PMD * sizeof(pmd_t), PAGE_SIZE);
+	}
+
+	pmdp = base_pmd + pmd_index(vaddr);
+
+	do {
+		next = pmd_addr_end(vaddr, end);
+
+		if (pmd_none(*pmdp) && IS_ALIGNED(vaddr, PMD_SIZE) && (next - vaddr) >= PMD_SIZE) {
+			phys_addr = memblock_phys_alloc(PMD_SIZE, PMD_SIZE);
+			if (phys_addr) {
+				set_pmd(pmdp, pfn_pmd(PFN_DOWN(phys_addr), PAGE_KERNEL));
+				continue;
+			}
+		}
+
+		kasan_populate_pte(pmdp, vaddr, next);
+	} while (pmdp++, vaddr = next, vaddr != end);
+
+	/*
+	 * Wait for the whole PGD to be populated before setting the PGD in
+	 * the page table, otherwise, if we did set the PGD before populating
+	 * it entirely, memblock could allocate a page at a physical address
+	 * where KASAN is not populated yet and then we'd get a page fault.
+	 */
+	set_pud(pud, pfn_pud(PFN_DOWN(__pa(base_pmd)), PAGE_TABLE));
+}
+
+static void __init kasan_populate_pud(pgd_t *pgd,
+				      unsigned long vaddr, unsigned long end,
+				      bool early)
+{
+	phys_addr_t phys_addr;
+	pud_t *pudp, *base_pud;
+	unsigned long next;
+
+	if (early) {
+		/*
+		 * We can't use pgd_page_vaddr here as it would return a linear
+		 * mapping address but it is not mapped yet, but when populating
+		 * early_pg_dir, we need the physical address and when populating
+		 * swapper_pg_dir, we need the kernel virtual address so use
+		 * pt_ops facility.
+		 */
+		base_pud = pt_ops.get_pud_virt(pfn_to_phys(_pgd_pfn(*pgd)));
+	} else if (pgd_none(*pgd)) {
+		base_pud = memblock_alloc(PTRS_PER_PUD * sizeof(pud_t), PAGE_SIZE);
+		memcpy(base_pud, (void *)kasan_early_shadow_pud,
+			sizeof(pud_t) * PTRS_PER_PUD);
+	} else {
+		base_pud = (pud_t *)pgd_page_vaddr(*pgd);
+		if (base_pud == lm_alias(kasan_early_shadow_pud)) {
+			base_pud = memblock_alloc(PTRS_PER_PUD * sizeof(pud_t), PAGE_SIZE);
+			memcpy(base_pud, (void *)kasan_early_shadow_pud,
+			       sizeof(pud_t) * PTRS_PER_PUD);
+		}
+	}
+
+	pudp = base_pud + pud_index(vaddr);
+
+	do {
+		next = pud_addr_end(vaddr, end);
+
+		if (pud_none(*pudp) && IS_ALIGNED(vaddr, PUD_SIZE) && (next - vaddr) >= PUD_SIZE) {
+			if (early) {
+				phys_addr = __pa(((uintptr_t)kasan_early_shadow_pmd));
+				set_pud(pudp, pfn_pud(PFN_DOWN(phys_addr), PAGE_TABLE));
+				continue;
+			} else {
+				phys_addr = memblock_phys_alloc(PUD_SIZE, PUD_SIZE);
+				if (phys_addr) {
+					set_pud(pudp, pfn_pud(PFN_DOWN(phys_addr), PAGE_KERNEL));
+					continue;
+				}
+			}
+		}
+
+		kasan_populate_pmd(pudp, vaddr, next);
+	} while (pudp++, vaddr = next, vaddr != end);
+
+	/*
+	 * Wait for the whole PGD to be populated before setting the PGD in
+	 * the page table, otherwise, if we did set the PGD before populating
+	 * it entirely, memblock could allocate a page at a physical address
+	 * where KASAN is not populated yet and then we'd get a page fault.
+	 */
+	if (!early)
+		set_pgd(pgd, pfn_pgd(PFN_DOWN(__pa(base_pud)), PAGE_TABLE));
+}
+
+static void __init kasan_populate_p4d(pgd_t *pgd,
+				      unsigned long vaddr, unsigned long end,
+				      bool early)
+{
+	phys_addr_t phys_addr;
+	p4d_t *p4dp, *base_p4d;
+	unsigned long next;
+
+	if (early) {
+		/*
+		 * We can't use pgd_page_vaddr here as it would return a linear
+		 * mapping address but it is not mapped yet, but when populating
+		 * early_pg_dir, we need the physical address and when populating
+		 * swapper_pg_dir, we need the kernel virtual address so use
+		 * pt_ops facility.
+		 */
+		base_p4d = pt_ops.get_p4d_virt(pfn_to_phys(_pgd_pfn(*pgd)));
+	} else {
+		base_p4d = (p4d_t *)pgd_page_vaddr(*pgd);
+		if (base_p4d == lm_alias(kasan_early_shadow_p4d)) {
+			base_p4d = memblock_alloc(PTRS_PER_PUD * sizeof(p4d_t), PAGE_SIZE);
+			memcpy(base_p4d, (void *)kasan_early_shadow_p4d,
+				sizeof(p4d_t) * PTRS_PER_P4D);
+		}
+	}
+
+	p4dp = base_p4d + p4d_index(vaddr);
+
+	do {
+		next = p4d_addr_end(vaddr, end);
+
+		if (p4d_none(*p4dp) && IS_ALIGNED(vaddr, P4D_SIZE) && (next - vaddr) >= P4D_SIZE) {
+			if (early) {
+				phys_addr = __pa(((uintptr_t)kasan_early_shadow_pud));
+				set_p4d(p4dp, pfn_p4d(PFN_DOWN(phys_addr), PAGE_TABLE));
+				continue;
+			} else {
+				phys_addr = memblock_phys_alloc(P4D_SIZE, P4D_SIZE);
+				if (phys_addr) {
+					set_p4d(p4dp, pfn_p4d(PFN_DOWN(phys_addr), PAGE_KERNEL));
+					continue;
+				}
+			}
+		}
+
+		kasan_populate_pud((pgd_t *)p4dp, vaddr, next, early);
+	} while (p4dp++, vaddr = next, vaddr != end);
+
+	/*
+	 * Wait for the whole P4D to be populated before setting the P4D in
+	 * the page table, otherwise, if we did set the P4D before populating
+	 * it entirely, memblock could allocate a page at a physical address
+	 * where KASAN is not populated yet and then we'd get a page fault.
+	 */
+	if (!early)
+		set_pgd(pgd, pfn_pgd(PFN_DOWN(__pa(base_p4d)), PAGE_TABLE));
+}
+
+#define kasan_early_shadow_pgd_next			(pgtable_l5_enabled ?	\
+				(uintptr_t)kasan_early_shadow_p4d :		\
+							(pgtable_l4_enabled ?	\
+				(uintptr_t)kasan_early_shadow_pud :		\
+				(uintptr_t)kasan_early_shadow_pmd))
+#define kasan_populate_pgd_next(pgdp, vaddr, next, early)			\
+		(pgtable_l5_enabled ?						\
+		kasan_populate_p4d(pgdp, vaddr, next, early) :			\
+		(pgtable_l4_enabled ?						\
+			kasan_populate_pud(pgdp, vaddr, next, early) :		\
+			kasan_populate_pmd((pud_t *)pgdp, vaddr, next)))
+
+static void __init kasan_populate_pgd(pgd_t *pgdp,
+				      unsigned long vaddr, unsigned long end,
+				      bool early)
+{
+	phys_addr_t phys_addr;
+	unsigned long next;
+
+	do {
+		next = pgd_addr_end(vaddr, end);
+
+		if (IS_ALIGNED(vaddr, PGDIR_SIZE) && (next - vaddr) >= PGDIR_SIZE) {
+			if (early) {
+				phys_addr = __pa((uintptr_t)kasan_early_shadow_pgd_next);
+				set_pgd(pgdp, pfn_pgd(PFN_DOWN(phys_addr), PAGE_TABLE));
+				continue;
+			} else if (pgd_page_vaddr(*pgdp) ==
+				   (unsigned long)lm_alias(kasan_early_shadow_pgd_next)) {
+				/*
+				 * pgdp can't be none since kasan_early_init
+				 * initialized all KASAN shadow region with
+				 * kasan_early_shadow_pud: if this is still the
+				 * case, that means we can try to allocate a
+				 * hugepage as a replacement.
+				 */
+				phys_addr = memblock_phys_alloc(PGDIR_SIZE, PGDIR_SIZE);
+				if (phys_addr) {
+					set_pgd(pgdp, pfn_pgd(PFN_DOWN(phys_addr), PAGE_KERNEL));
+					continue;
+				}
+			}
+		}
+
+		kasan_populate_pgd_next(pgdp, vaddr, next, early);
+	} while (pgdp++, vaddr = next, vaddr != end);
+}
+
+asmlinkage void __init kasan_early_init(void)
+{
+	uintptr_t i;
+
+	BUILD_BUG_ON(KASAN_SHADOW_OFFSET !=
+		KASAN_SHADOW_END - (1UL << (64 - KASAN_SHADOW_SCALE_SHIFT)));
+
+	for (i = 0; i < PTRS_PER_PTE; ++i)
+		set_pte(kasan_early_shadow_pte + i,
+			pfn_pte(virt_to_pfn(kasan_early_shadow_page), PAGE_KERNEL));
+
+	for (i = 0; i < PTRS_PER_PMD; ++i)
+		set_pmd(kasan_early_shadow_pmd + i,
+			pfn_pmd(PFN_DOWN
+				(__pa((uintptr_t)kasan_early_shadow_pte)),
+				PAGE_TABLE));
+
+	if (pgtable_l4_enabled) {
+		for (i = 0; i < PTRS_PER_PUD; ++i)
+			set_pud(kasan_early_shadow_pud + i,
+				pfn_pud(PFN_DOWN
+					(__pa(((uintptr_t)kasan_early_shadow_pmd))),
+					PAGE_TABLE));
+	}
+
+	if (pgtable_l5_enabled) {
+		for (i = 0; i < PTRS_PER_P4D; ++i)
+			set_p4d(kasan_early_shadow_p4d + i,
+				pfn_p4d(PFN_DOWN
+					(__pa(((uintptr_t)kasan_early_shadow_pud))),
+					PAGE_TABLE));
+	}
+
+	kasan_populate_pgd(early_pg_dir + pgd_index(KASAN_SHADOW_START),
+			   KASAN_SHADOW_START, KASAN_SHADOW_END, true);
+
+	local_flush_tlb_all();
+}
+
+void __init kasan_swapper_init(void)
+{
+	kasan_populate_pgd(pgd_offset_k(KASAN_SHADOW_START),
+			   KASAN_SHADOW_START, KASAN_SHADOW_END, true);
+
+	local_flush_tlb_all();
+}
+
+static void __init kasan_populate(void *start, void *end)
+{
+	unsigned long vaddr = (unsigned long)start & PAGE_MASK;
+	unsigned long vend = PAGE_ALIGN((unsigned long)end);
+
+	kasan_populate_pgd(pgd_offset_k(vaddr), vaddr, vend, false);
+
+	local_flush_tlb_all();
+	memset(start, KASAN_SHADOW_INIT, end - start);
+}
+
+static void __init kasan_shallow_populate_pmd(pgd_t *pgdp,
+					      unsigned long vaddr, unsigned long end)
+{
+	unsigned long next;
+	pmd_t *pmdp, *base_pmd;
+	bool is_kasan_pte;
+
+	base_pmd = (pmd_t *)pgd_page_vaddr(*pgdp);
+	pmdp = base_pmd + pmd_index(vaddr);
+
+	do {
+		next = pmd_addr_end(vaddr, end);
+		is_kasan_pte = (pmd_pgtable(*pmdp) == lm_alias(kasan_early_shadow_pte));
+
+		if (is_kasan_pte)
+			pmd_clear(pmdp);
+	} while (pmdp++, vaddr = next, vaddr != end);
+}
+
+static void __init kasan_shallow_populate_pud(pgd_t *pgdp,
+					      unsigned long vaddr, unsigned long end)
+{
+	unsigned long next;
+	pud_t *pudp, *base_pud;
+	pmd_t *base_pmd;
+	bool is_kasan_pmd;
+
+	base_pud = (pud_t *)pgd_page_vaddr(*pgdp);
+	pudp = base_pud + pud_index(vaddr);
+
+	do {
+		next = pud_addr_end(vaddr, end);
+		is_kasan_pmd = (pud_pgtable(*pudp) == lm_alias(kasan_early_shadow_pmd));
+
+		if (!is_kasan_pmd)
+			continue;
+
+		base_pmd = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
+		set_pud(pudp, pfn_pud(PFN_DOWN(__pa(base_pmd)), PAGE_TABLE));
+
+		if (IS_ALIGNED(vaddr, PUD_SIZE) && (next - vaddr) >= PUD_SIZE)
+			continue;
+
+		memcpy(base_pmd, (void *)kasan_early_shadow_pmd, PAGE_SIZE);
+		kasan_shallow_populate_pmd((pgd_t *)pudp, vaddr, next);
+	} while (pudp++, vaddr = next, vaddr != end);
+}
+
+static void __init kasan_shallow_populate_p4d(pgd_t *pgdp,
+					      unsigned long vaddr, unsigned long end)
+{
+	unsigned long next;
+	p4d_t *p4dp, *base_p4d;
+	pud_t *base_pud;
+	bool is_kasan_pud;
+
+	base_p4d = (p4d_t *)pgd_page_vaddr(*pgdp);
+	p4dp = base_p4d + p4d_index(vaddr);
+
+	do {
+		next = p4d_addr_end(vaddr, end);
+		is_kasan_pud = (p4d_pgtable(*p4dp) == lm_alias(kasan_early_shadow_pud));
+
+		if (!is_kasan_pud)
+			continue;
+
+		base_pud = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
+		set_p4d(p4dp, pfn_p4d(PFN_DOWN(__pa(base_pud)), PAGE_TABLE));
+
+		if (IS_ALIGNED(vaddr, P4D_SIZE) && (next - vaddr) >= P4D_SIZE)
+			continue;
+
+		memcpy(base_pud, (void *)kasan_early_shadow_pud, PAGE_SIZE);
+		kasan_shallow_populate_pud((pgd_t *)p4dp, vaddr, next);
+	} while (p4dp++, vaddr = next, vaddr != end);
+}
+
+#define kasan_shallow_populate_pgd_next(pgdp, vaddr, next)			\
+		(pgtable_l5_enabled ?						\
+		kasan_shallow_populate_p4d(pgdp, vaddr, next) :			\
+		(pgtable_l4_enabled ?						\
+		kasan_shallow_populate_pud(pgdp, vaddr, next) :			\
+		kasan_shallow_populate_pmd(pgdp, vaddr, next)))
+
+static void __init kasan_shallow_populate_pgd(unsigned long vaddr, unsigned long end)
+{
+	unsigned long next;
+	void *p;
+	pgd_t *pgd_k = pgd_offset_k(vaddr);
+	bool is_kasan_pgd_next;
+
+	do {
+		next = pgd_addr_end(vaddr, end);
+		is_kasan_pgd_next = (pgd_page_vaddr(*pgd_k) ==
+				     (unsigned long)lm_alias(kasan_early_shadow_pgd_next));
+
+		if (is_kasan_pgd_next) {
+			p = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
+			set_pgd(pgd_k, pfn_pgd(PFN_DOWN(__pa(p)), PAGE_TABLE));
+		}
+
+		if (IS_ALIGNED(vaddr, PGDIR_SIZE) && (next - vaddr) >= PGDIR_SIZE)
+			continue;
+
+		memcpy(p, (void *)kasan_early_shadow_pgd_next, PAGE_SIZE);
+		kasan_shallow_populate_pgd_next(pgd_k, vaddr, next);
+	} while (pgd_k++, vaddr = next, vaddr != end);
+}
+
+static void __init kasan_shallow_populate(void *start, void *end)
+{
+	unsigned long vaddr = (unsigned long)start & PAGE_MASK;
+	unsigned long vend = PAGE_ALIGN((unsigned long)end);
+
+	kasan_shallow_populate_pgd(vaddr, vend);
+	local_flush_tlb_all();
+}
+
+void __init kasan_init(void)
+{
+	phys_addr_t p_start, p_end;
+	u64 i;
+
+	if (IS_ENABLED(CONFIG_KASAN_VMALLOC))
+		kasan_shallow_populate(
+			(void *)kasan_mem_to_shadow((void *)VMALLOC_START),
+			(void *)kasan_mem_to_shadow((void *)VMALLOC_END));
+
+	/* Populate the linear mapping */
+	for_each_mem_range(i, &p_start, &p_end) {
+		void *start = (void *)__va(p_start);
+		void *end = (void *)__va(p_end);
+
+		if (start >= end)
+			break;
+
+		kasan_populate(kasan_mem_to_shadow(start), kasan_mem_to_shadow(end));
+	}
+
+	/* Populate kernel, BPF, modules mapping */
+	kasan_populate(kasan_mem_to_shadow((const void *)MODULES_VADDR),
+		       kasan_mem_to_shadow((const void *)MODULES_VADDR + SZ_2G));
+
+	for (i = 0; i < PTRS_PER_PTE; i++)
+		set_pte(&kasan_early_shadow_pte[i],
+			mk_pte(virt_to_page(kasan_early_shadow_page),
+			       __pgprot(_PAGE_PRESENT | _PAGE_READ |
+					_PAGE_ACCESSED)));
+
+	memset(kasan_early_shadow_page, KASAN_SHADOW_INIT, PAGE_SIZE);
+	init_task.kasan_depth = 0;
+}
diff --git a/arch/riscv/mm/pageattr.c b/arch/riscv/mm/pageattr.c
new file mode 100644
index 000000000..9587e4487
--- /dev/null
+++ b/arch/riscv/mm/pageattr.c
@@ -0,0 +1,438 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2019 SiFive
+ */
+
+#include <linux/pagewalk.h>
+#include <linux/pgtable.h>
+#include <linux/vmalloc.h>
+#include <asm/tlbflush.h>
+#include <asm/bitops.h>
+#include <asm/set_memory.h>
+
+struct pageattr_masks {
+	pgprot_t set_mask;
+	pgprot_t clear_mask;
+};
+
+static unsigned long set_pageattr_masks(unsigned long val, struct mm_walk *walk)
+{
+	struct pageattr_masks *masks = walk->private;
+	unsigned long new_val = val;
+
+	new_val &= ~(pgprot_val(masks->clear_mask));
+	new_val |= (pgprot_val(masks->set_mask));
+
+	return new_val;
+}
+
+static int pageattr_p4d_entry(p4d_t *p4d, unsigned long addr,
+			      unsigned long next, struct mm_walk *walk)
+{
+	p4d_t val = READ_ONCE(*p4d);
+
+	if (p4d_leaf(val)) {
+		val = __p4d(set_pageattr_masks(p4d_val(val), walk));
+		set_p4d(p4d, val);
+	}
+
+	return 0;
+}
+
+static int pageattr_pud_entry(pud_t *pud, unsigned long addr,
+			      unsigned long next, struct mm_walk *walk)
+{
+	pud_t val = READ_ONCE(*pud);
+
+	if (pud_leaf(val)) {
+		val = __pud(set_pageattr_masks(pud_val(val), walk));
+		set_pud(pud, val);
+	}
+
+	return 0;
+}
+
+static int pageattr_pmd_entry(pmd_t *pmd, unsigned long addr,
+			      unsigned long next, struct mm_walk *walk)
+{
+	pmd_t val = READ_ONCE(*pmd);
+
+	if (pmd_leaf(val)) {
+		val = __pmd(set_pageattr_masks(pmd_val(val), walk));
+		set_pmd(pmd, val);
+	}
+
+	return 0;
+}
+
+static int pageattr_pte_entry(pte_t *pte, unsigned long addr,
+			      unsigned long next, struct mm_walk *walk)
+{
+	pte_t val = READ_ONCE(*pte);
+
+	val = __pte(set_pageattr_masks(pte_val(val), walk));
+	set_pte(pte, val);
+
+	return 0;
+}
+
+static int pageattr_pte_hole(unsigned long addr, unsigned long next,
+			     int depth, struct mm_walk *walk)
+{
+	/* Nothing to do here */
+	return 0;
+}
+
+static const struct mm_walk_ops pageattr_ops = {
+	.p4d_entry = pageattr_p4d_entry,
+	.pud_entry = pageattr_pud_entry,
+	.pmd_entry = pageattr_pmd_entry,
+	.pte_entry = pageattr_pte_entry,
+	.pte_hole = pageattr_pte_hole,
+};
+
+#ifdef CONFIG_64BIT
+static int __split_linear_mapping_pmd(pud_t *pudp,
+				      unsigned long vaddr, unsigned long end)
+{
+	pmd_t *pmdp;
+	unsigned long next;
+
+	pmdp = pmd_offset(pudp, vaddr);
+
+	do {
+		next = pmd_addr_end(vaddr, end);
+
+		if (next - vaddr >= PMD_SIZE &&
+		    vaddr <= (vaddr & PMD_MASK) && end >= next)
+			continue;
+
+		if (pmd_leaf(*pmdp)) {
+			struct page *pte_page;
+			unsigned long pfn = _pmd_pfn(*pmdp);
+			pgprot_t prot = __pgprot(pmd_val(*pmdp) & ~_PAGE_PFN_MASK);
+			pte_t *ptep_new;
+			int i;
+
+			pte_page = alloc_page(GFP_KERNEL);
+			if (!pte_page)
+				return -ENOMEM;
+
+			ptep_new = (pte_t *)page_address(pte_page);
+			for (i = 0; i < PTRS_PER_PTE; ++i, ++ptep_new)
+				set_pte(ptep_new, pfn_pte(pfn + i, prot));
+
+			smp_wmb();
+
+			set_pmd(pmdp, pfn_pmd(page_to_pfn(pte_page), PAGE_TABLE));
+		}
+	} while (pmdp++, vaddr = next, vaddr != end);
+
+	return 0;
+}
+
+static int __split_linear_mapping_pud(p4d_t *p4dp,
+				      unsigned long vaddr, unsigned long end)
+{
+	pud_t *pudp;
+	unsigned long next;
+	int ret;
+
+	pudp = pud_offset(p4dp, vaddr);
+
+	do {
+		next = pud_addr_end(vaddr, end);
+
+		if (next - vaddr >= PUD_SIZE &&
+		    vaddr <= (vaddr & PUD_MASK) && end >= next)
+			continue;
+
+		if (pud_leaf(*pudp)) {
+			struct page *pmd_page;
+			unsigned long pfn = _pud_pfn(*pudp);
+			pgprot_t prot = __pgprot(pud_val(*pudp) & ~_PAGE_PFN_MASK);
+			pmd_t *pmdp_new;
+			int i;
+
+			pmd_page = alloc_page(GFP_KERNEL);
+			if (!pmd_page)
+				return -ENOMEM;
+
+			pmdp_new = (pmd_t *)page_address(pmd_page);
+			for (i = 0; i < PTRS_PER_PMD; ++i, ++pmdp_new)
+				set_pmd(pmdp_new,
+					pfn_pmd(pfn + ((i * PMD_SIZE) >> PAGE_SHIFT), prot));
+
+			smp_wmb();
+
+			set_pud(pudp, pfn_pud(page_to_pfn(pmd_page), PAGE_TABLE));
+		}
+
+		ret = __split_linear_mapping_pmd(pudp, vaddr, next);
+		if (ret)
+			return ret;
+	} while (pudp++, vaddr = next, vaddr != end);
+
+	return 0;
+}
+
+static int __split_linear_mapping_p4d(pgd_t *pgdp,
+				      unsigned long vaddr, unsigned long end)
+{
+	p4d_t *p4dp;
+	unsigned long next;
+	int ret;
+
+	p4dp = p4d_offset(pgdp, vaddr);
+
+	do {
+		next = p4d_addr_end(vaddr, end);
+
+		/*
+		 * If [vaddr; end] contains [vaddr & P4D_MASK; next], we don't
+		 * need to split, we'll change the protections on the whole P4D.
+		 */
+		if (next - vaddr >= P4D_SIZE &&
+		    vaddr <= (vaddr & P4D_MASK) && end >= next)
+			continue;
+
+		if (p4d_leaf(*p4dp)) {
+			struct page *pud_page;
+			unsigned long pfn = _p4d_pfn(*p4dp);
+			pgprot_t prot = __pgprot(p4d_val(*p4dp) & ~_PAGE_PFN_MASK);
+			pud_t *pudp_new;
+			int i;
+
+			pud_page = alloc_page(GFP_KERNEL);
+			if (!pud_page)
+				return -ENOMEM;
+
+			/*
+			 * Fill the pud level with leaf puds that have the same
+			 * protections as the leaf p4d.
+			 */
+			pudp_new = (pud_t *)page_address(pud_page);
+			for (i = 0; i < PTRS_PER_PUD; ++i, ++pudp_new)
+				set_pud(pudp_new,
+					pfn_pud(pfn + ((i * PUD_SIZE) >> PAGE_SHIFT), prot));
+
+			/*
+			 * Make sure the pud filling is not reordered with the
+			 * p4d store which could result in seeing a partially
+			 * filled pud level.
+			 */
+			smp_wmb();
+
+			set_p4d(p4dp, pfn_p4d(page_to_pfn(pud_page), PAGE_TABLE));
+		}
+
+		ret = __split_linear_mapping_pud(p4dp, vaddr, next);
+		if (ret)
+			return ret;
+	} while (p4dp++, vaddr = next, vaddr != end);
+
+	return 0;
+}
+
+static int __split_linear_mapping_pgd(pgd_t *pgdp,
+				      unsigned long vaddr,
+				      unsigned long end)
+{
+	unsigned long next;
+	int ret;
+
+	do {
+		next = pgd_addr_end(vaddr, end);
+		/* We never use PGD mappings for the linear mapping */
+		ret = __split_linear_mapping_p4d(pgdp, vaddr, next);
+		if (ret)
+			return ret;
+	} while (pgdp++, vaddr = next, vaddr != end);
+
+	return 0;
+}
+
+static int split_linear_mapping(unsigned long start, unsigned long end)
+{
+	return __split_linear_mapping_pgd(pgd_offset_k(start), start, end);
+}
+#endif	/* CONFIG_64BIT */
+
+static int __set_memory(unsigned long addr, int numpages, pgprot_t set_mask,
+			pgprot_t clear_mask)
+{
+	int ret;
+	unsigned long start = addr;
+	unsigned long end = start + PAGE_SIZE * numpages;
+	unsigned long __maybe_unused lm_start;
+	unsigned long __maybe_unused lm_end;
+	struct pageattr_masks masks = {
+		.set_mask = set_mask,
+		.clear_mask = clear_mask
+	};
+
+	if (!numpages)
+		return 0;
+
+	mmap_write_lock(&init_mm);
+
+#ifdef CONFIG_64BIT
+	/*
+	 * We are about to change the permissions of a kernel mapping, we must
+	 * apply the same changes to its linear mapping alias, which may imply
+	 * splitting a huge mapping.
+	 */
+
+	if (is_vmalloc_or_module_addr((void *)start)) {
+		struct vm_struct *area = NULL;
+		int i, page_start;
+
+		area = find_vm_area((void *)start);
+		page_start = (start - (unsigned long)area->addr) >> PAGE_SHIFT;
+
+		for (i = page_start; i < page_start + numpages; ++i) {
+			lm_start = (unsigned long)page_address(area->pages[i]);
+			lm_end = lm_start + PAGE_SIZE;
+
+			ret = split_linear_mapping(lm_start, lm_end);
+			if (ret)
+				goto unlock;
+
+			ret = walk_page_range_novma(&init_mm, lm_start, lm_end,
+						    &pageattr_ops, NULL, &masks);
+			if (ret)
+				goto unlock;
+		}
+	} else if (is_kernel_mapping(start) || is_linear_mapping(start)) {
+		if (is_kernel_mapping(start)) {
+			lm_start = (unsigned long)lm_alias(start);
+			lm_end = (unsigned long)lm_alias(end);
+		} else {
+			lm_start = start;
+			lm_end = end;
+		}
+
+		ret = split_linear_mapping(lm_start, lm_end);
+		if (ret)
+			goto unlock;
+
+		ret = walk_page_range_novma(&init_mm, lm_start, lm_end,
+					    &pageattr_ops, NULL, &masks);
+		if (ret)
+			goto unlock;
+	}
+
+	ret =  walk_page_range_novma(&init_mm, start, end, &pageattr_ops, NULL,
+				     &masks);
+
+unlock:
+	mmap_write_unlock(&init_mm);
+
+	/*
+	 * We can't use flush_tlb_kernel_range() here as we may have split a
+	 * hugepage that is larger than that, so let's flush everything.
+	 */
+	flush_tlb_all();
+#else
+	ret =  walk_page_range_novma(&init_mm, start, end, &pageattr_ops, NULL,
+				     &masks);
+
+	mmap_write_unlock(&init_mm);
+
+	flush_tlb_kernel_range(start, end);
+#endif
+
+	return ret;
+}
+
+int set_memory_rw_nx(unsigned long addr, int numpages)
+{
+	return __set_memory(addr, numpages, __pgprot(_PAGE_READ | _PAGE_WRITE),
+			    __pgprot(_PAGE_EXEC));
+}
+
+int set_memory_ro(unsigned long addr, int numpages)
+{
+	return __set_memory(addr, numpages, __pgprot(_PAGE_READ),
+			    __pgprot(_PAGE_WRITE));
+}
+
+int set_memory_rw(unsigned long addr, int numpages)
+{
+	return __set_memory(addr, numpages, __pgprot(_PAGE_READ | _PAGE_WRITE),
+			    __pgprot(0));
+}
+
+int set_memory_x(unsigned long addr, int numpages)
+{
+	return __set_memory(addr, numpages, __pgprot(_PAGE_EXEC), __pgprot(0));
+}
+
+int set_memory_nx(unsigned long addr, int numpages)
+{
+	return __set_memory(addr, numpages, __pgprot(0), __pgprot(_PAGE_EXEC));
+}
+
+int set_direct_map_invalid_noflush(struct page *page)
+{
+	return __set_memory((unsigned long)page_address(page), 1,
+			    __pgprot(0), __pgprot(_PAGE_PRESENT));
+}
+
+int set_direct_map_default_noflush(struct page *page)
+{
+	return __set_memory((unsigned long)page_address(page), 1,
+			    PAGE_KERNEL, __pgprot(_PAGE_EXEC));
+}
+
+#ifdef CONFIG_DEBUG_PAGEALLOC
+void __kernel_map_pages(struct page *page, int numpages, int enable)
+{
+	if (!debug_pagealloc_enabled())
+		return;
+
+	if (enable)
+		__set_memory((unsigned long)page_address(page), numpages,
+			     __pgprot(_PAGE_PRESENT), __pgprot(0));
+	else
+		__set_memory((unsigned long)page_address(page), numpages,
+			     __pgprot(0), __pgprot(_PAGE_PRESENT));
+}
+#endif
+
+bool kernel_page_present(struct page *page)
+{
+	unsigned long addr = (unsigned long)page_address(page);
+	pgd_t *pgd;
+	pud_t *pud;
+	p4d_t *p4d;
+	pmd_t *pmd;
+	pte_t *pte;
+
+	pgd = pgd_offset_k(addr);
+	if (!pgd_present(*pgd))
+		return false;
+	if (pgd_leaf(*pgd))
+		return true;
+
+	p4d = p4d_offset(pgd, addr);
+	if (!p4d_present(*p4d))
+		return false;
+	if (p4d_leaf(*p4d))
+		return true;
+
+	pud = pud_offset(p4d, addr);
+	if (!pud_present(*pud))
+		return false;
+	if (pud_leaf(*pud))
+		return true;
+
+	pmd = pmd_offset(pud, addr);
+	if (!pmd_present(*pmd))
+		return false;
+	if (pmd_leaf(*pmd))
+		return true;
+
+	pte = pte_offset_kernel(pmd, addr);
+	return pte_present(*pte);
+}
diff --git a/arch/riscv/mm/physaddr.c b/arch/riscv/mm/physaddr.c
new file mode 100644
index 000000000..9b18bda74
--- /dev/null
+++ b/arch/riscv/mm/physaddr.c
@@ -0,0 +1,35 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/types.h>
+#include <linux/mmdebug.h>
+#include <linux/mm.h>
+#include <asm/page.h>
+#include <asm/sections.h>
+
+phys_addr_t __virt_to_phys(unsigned long x)
+{
+	/*
+	 * Boundary checking aginst the kernel linear mapping space.
+	 */
+	WARN(!is_linear_mapping(x) && !is_kernel_mapping(x),
+	     "virt_to_phys used for non-linear address: %pK (%pS)\n",
+	     (void *)x, (void *)x);
+
+	return __va_to_pa_nodebug(x);
+}
+EXPORT_SYMBOL(__virt_to_phys);
+
+phys_addr_t __phys_addr_symbol(unsigned long x)
+{
+	unsigned long kernel_start = kernel_map.virt_addr;
+	unsigned long kernel_end = kernel_start + kernel_map.size;
+
+	/*
+	 * Boundary checking aginst the kernel image mapping.
+	 * __pa_symbol should only be used on kernel symbol addresses.
+	 */
+	VIRTUAL_BUG_ON(x < kernel_start || x > kernel_end);
+
+	return __va_to_pa_nodebug(x);
+}
+EXPORT_SYMBOL(__phys_addr_symbol);
diff --git a/arch/riscv/mm/ptdump.c b/arch/riscv/mm/ptdump.c
new file mode 100644
index 000000000..e9090b38f
--- /dev/null
+++ b/arch/riscv/mm/ptdump.c
@@ -0,0 +1,405 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2019 SiFive
+ */
+
+#include <linux/efi.h>
+#include <linux/init.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+#include <linux/ptdump.h>
+
+#include <asm/ptdump.h>
+#include <linux/pgtable.h>
+#include <asm/kasan.h>
+
+#define pt_dump_seq_printf(m, fmt, args...)	\
+({						\
+	if (m)					\
+		seq_printf(m, fmt, ##args);	\
+})
+
+#define pt_dump_seq_puts(m, fmt)	\
+({					\
+	if (m)				\
+		seq_printf(m, fmt);	\
+})
+
+/*
+ * The page dumper groups page table entries of the same type into a single
+ * description. It uses pg_state to track the range information while
+ * iterating over the pte entries. When the continuity is broken it then
+ * dumps out a description of the range.
+ */
+struct pg_state {
+	struct ptdump_state ptdump;
+	struct seq_file *seq;
+	const struct addr_marker *marker;
+	unsigned long start_address;
+	unsigned long start_pa;
+	unsigned long last_pa;
+	int level;
+	u64 current_prot;
+	bool check_wx;
+	unsigned long wx_pages;
+};
+
+/* Address marker */
+struct addr_marker {
+	unsigned long start_address;
+	const char *name;
+};
+
+/* Private information for debugfs */
+struct ptd_mm_info {
+	struct mm_struct		*mm;
+	const struct addr_marker	*markers;
+	unsigned long base_addr;
+	unsigned long end;
+};
+
+enum address_markers_idx {
+	FIXMAP_START_NR,
+	FIXMAP_END_NR,
+	PCI_IO_START_NR,
+	PCI_IO_END_NR,
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+	VMEMMAP_START_NR,
+	VMEMMAP_END_NR,
+#endif
+	VMALLOC_START_NR,
+	VMALLOC_END_NR,
+	PAGE_OFFSET_NR,
+#ifdef CONFIG_KASAN
+	KASAN_SHADOW_START_NR,
+	KASAN_SHADOW_END_NR,
+#endif
+#ifdef CONFIG_64BIT
+	MODULES_MAPPING_NR,
+	KERNEL_MAPPING_NR,
+#endif
+	END_OF_SPACE_NR
+};
+
+static struct addr_marker address_markers[] = {
+	{0, "Fixmap start"},
+	{0, "Fixmap end"},
+	{0, "PCI I/O start"},
+	{0, "PCI I/O end"},
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+	{0, "vmemmap start"},
+	{0, "vmemmap end"},
+#endif
+	{0, "vmalloc() area"},
+	{0, "vmalloc() end"},
+	{0, "Linear mapping"},
+#ifdef CONFIG_KASAN
+	{0, "Kasan shadow start"},
+	{0, "Kasan shadow end"},
+#endif
+#ifdef CONFIG_64BIT
+	{0, "Modules/BPF mapping"},
+	{0, "Kernel mapping"},
+#endif
+	{-1, NULL},
+};
+
+static struct ptd_mm_info kernel_ptd_info = {
+	.mm		= &init_mm,
+	.markers	= address_markers,
+	.base_addr	= 0,
+	.end		= ULONG_MAX,
+};
+
+#ifdef CONFIG_EFI
+static struct addr_marker efi_addr_markers[] = {
+		{ 0,		"UEFI runtime start" },
+		{ SZ_1G,	"UEFI runtime end" },
+		{ -1,		NULL }
+};
+
+static struct ptd_mm_info efi_ptd_info = {
+	.mm		= &efi_mm,
+	.markers	= efi_addr_markers,
+	.base_addr	= 0,
+	.end		= SZ_2G,
+};
+#endif
+
+/* Page Table Entry */
+struct prot_bits {
+	u64 mask;
+	u64 val;
+	const char *set;
+	const char *clear;
+};
+
+static const struct prot_bits pte_bits[] = {
+	{
+		.mask = _PAGE_SOFT,
+		.val = _PAGE_SOFT,
+		.set = "RSW",
+		.clear = "   ",
+	}, {
+		.mask = _PAGE_DIRTY,
+		.val = _PAGE_DIRTY,
+		.set = "D",
+		.clear = ".",
+	}, {
+		.mask = _PAGE_ACCESSED,
+		.val = _PAGE_ACCESSED,
+		.set = "A",
+		.clear = ".",
+	}, {
+		.mask = _PAGE_GLOBAL,
+		.val = _PAGE_GLOBAL,
+		.set = "G",
+		.clear = ".",
+	}, {
+		.mask = _PAGE_USER,
+		.val = _PAGE_USER,
+		.set = "U",
+		.clear = ".",
+	}, {
+		.mask = _PAGE_EXEC,
+		.val = _PAGE_EXEC,
+		.set = "X",
+		.clear = ".",
+	}, {
+		.mask = _PAGE_WRITE,
+		.val = _PAGE_WRITE,
+		.set = "W",
+		.clear = ".",
+	}, {
+		.mask = _PAGE_READ,
+		.val = _PAGE_READ,
+		.set = "R",
+		.clear = ".",
+	}, {
+		.mask = _PAGE_PRESENT,
+		.val = _PAGE_PRESENT,
+		.set = "V",
+		.clear = ".",
+	}
+};
+
+/* Page Level */
+struct pg_level {
+	const char *name;
+	u64 mask;
+};
+
+static struct pg_level pg_level[] = {
+	{ /* pgd */
+		.name = "PGD",
+	}, { /* p4d */
+		.name = (CONFIG_PGTABLE_LEVELS > 4) ? "P4D" : "PGD",
+	}, { /* pud */
+		.name = (CONFIG_PGTABLE_LEVELS > 3) ? "PUD" : "PGD",
+	}, { /* pmd */
+		.name = (CONFIG_PGTABLE_LEVELS > 2) ? "PMD" : "PGD",
+	}, { /* pte */
+		.name = "PTE",
+	},
+};
+
+static void dump_prot(struct pg_state *st)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(pte_bits); i++) {
+		const char *s;
+
+		if ((st->current_prot & pte_bits[i].mask) == pte_bits[i].val)
+			s = pte_bits[i].set;
+		else
+			s = pte_bits[i].clear;
+
+		if (s)
+			pt_dump_seq_printf(st->seq, " %s", s);
+	}
+}
+
+#ifdef CONFIG_64BIT
+#define ADDR_FORMAT	"0x%016lx"
+#else
+#define ADDR_FORMAT	"0x%08lx"
+#endif
+static void dump_addr(struct pg_state *st, unsigned long addr)
+{
+	static const char units[] = "KMGTPE";
+	const char *unit = units;
+	unsigned long delta;
+
+	pt_dump_seq_printf(st->seq, ADDR_FORMAT "-" ADDR_FORMAT "   ",
+			   st->start_address, addr);
+
+	pt_dump_seq_printf(st->seq, " " ADDR_FORMAT " ", st->start_pa);
+	delta = (addr - st->start_address) >> 10;
+
+	while (!(delta & 1023) && unit[1]) {
+		delta >>= 10;
+		unit++;
+	}
+
+	pt_dump_seq_printf(st->seq, "%9lu%c %s", delta, *unit,
+			   pg_level[st->level].name);
+}
+
+static void note_prot_wx(struct pg_state *st, unsigned long addr)
+{
+	if (!st->check_wx)
+		return;
+
+	if ((st->current_prot & (_PAGE_WRITE | _PAGE_EXEC)) !=
+	    (_PAGE_WRITE | _PAGE_EXEC))
+		return;
+
+	WARN_ONCE(1, "riscv/mm: Found insecure W+X mapping at address %p/%pS\n",
+		  (void *)st->start_address, (void *)st->start_address);
+
+	st->wx_pages += (addr - st->start_address) / PAGE_SIZE;
+}
+
+static void note_page(struct ptdump_state *pt_st, unsigned long addr,
+		      int level, u64 val)
+{
+	struct pg_state *st = container_of(pt_st, struct pg_state, ptdump);
+	u64 pa = PFN_PHYS(pte_pfn(__pte(val)));
+	u64 prot = 0;
+
+	if (level >= 0)
+		prot = val & pg_level[level].mask;
+
+	if (st->level == -1) {
+		st->level = level;
+		st->current_prot = prot;
+		st->start_address = addr;
+		st->start_pa = pa;
+		st->last_pa = pa;
+		pt_dump_seq_printf(st->seq, "---[ %s ]---\n", st->marker->name);
+	} else if (prot != st->current_prot ||
+		   level != st->level || addr >= st->marker[1].start_address) {
+		if (st->current_prot) {
+			note_prot_wx(st, addr);
+			dump_addr(st, addr);
+			dump_prot(st);
+			pt_dump_seq_puts(st->seq, "\n");
+		}
+
+		while (addr >= st->marker[1].start_address) {
+			st->marker++;
+			pt_dump_seq_printf(st->seq, "---[ %s ]---\n",
+					   st->marker->name);
+		}
+
+		st->start_address = addr;
+		st->start_pa = pa;
+		st->last_pa = pa;
+		st->current_prot = prot;
+		st->level = level;
+	} else {
+		st->last_pa = pa;
+	}
+}
+
+static void ptdump_walk(struct seq_file *s, struct ptd_mm_info *pinfo)
+{
+	struct pg_state st = {
+		.seq = s,
+		.marker = pinfo->markers,
+		.level = -1,
+		.ptdump = {
+			.note_page = note_page,
+			.range = (struct ptdump_range[]) {
+				{pinfo->base_addr, pinfo->end},
+				{0, 0}
+			}
+		}
+	};
+
+	ptdump_walk_pgd(&st.ptdump, pinfo->mm, NULL);
+}
+
+void ptdump_check_wx(void)
+{
+	struct pg_state st = {
+		.seq = NULL,
+		.marker = (struct addr_marker[]) {
+			{0, NULL},
+			{-1, NULL},
+		},
+		.level = -1,
+		.check_wx = true,
+		.ptdump = {
+			.note_page = note_page,
+			.range = (struct ptdump_range[]) {
+				{KERN_VIRT_START, ULONG_MAX},
+				{0, 0}
+			}
+		}
+	};
+
+	ptdump_walk_pgd(&st.ptdump, &init_mm, NULL);
+
+	if (st.wx_pages)
+		pr_warn("Checked W+X mappings: failed, %lu W+X pages found\n",
+			st.wx_pages);
+	else
+		pr_info("Checked W+X mappings: passed, no W+X pages found\n");
+}
+
+static int ptdump_show(struct seq_file *m, void *v)
+{
+	ptdump_walk(m, m->private);
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(ptdump);
+
+static int __init ptdump_init(void)
+{
+	unsigned int i, j;
+
+	address_markers[FIXMAP_START_NR].start_address = FIXADDR_START;
+	address_markers[FIXMAP_END_NR].start_address = FIXADDR_TOP;
+	address_markers[PCI_IO_START_NR].start_address = PCI_IO_START;
+	address_markers[PCI_IO_END_NR].start_address = PCI_IO_END;
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+	address_markers[VMEMMAP_START_NR].start_address = VMEMMAP_START;
+	address_markers[VMEMMAP_END_NR].start_address = VMEMMAP_END;
+#endif
+	address_markers[VMALLOC_START_NR].start_address = VMALLOC_START;
+	address_markers[VMALLOC_END_NR].start_address = VMALLOC_END;
+	address_markers[PAGE_OFFSET_NR].start_address = PAGE_OFFSET;
+#ifdef CONFIG_KASAN
+	address_markers[KASAN_SHADOW_START_NR].start_address = KASAN_SHADOW_START;
+	address_markers[KASAN_SHADOW_END_NR].start_address = KASAN_SHADOW_END;
+#endif
+#ifdef CONFIG_64BIT
+	address_markers[MODULES_MAPPING_NR].start_address = MODULES_VADDR;
+	address_markers[KERNEL_MAPPING_NR].start_address = kernel_map.virt_addr;
+#endif
+
+	kernel_ptd_info.base_addr = KERN_VIRT_START;
+
+	pg_level[1].name = pgtable_l5_enabled ? "P4D" : "PGD";
+	pg_level[2].name = pgtable_l4_enabled ? "PUD" : "PGD";
+
+	for (i = 0; i < ARRAY_SIZE(pg_level); i++)
+		for (j = 0; j < ARRAY_SIZE(pte_bits); j++)
+			pg_level[i].mask |= pte_bits[j].mask;
+
+	debugfs_create_file("kernel_page_tables", 0400, NULL, &kernel_ptd_info,
+			    &ptdump_fops);
+#ifdef CONFIG_EFI
+	if (efi_enabled(EFI_RUNTIME_SERVICES))
+		debugfs_create_file("efi_page_tables", 0400, NULL, &efi_ptd_info,
+				    &ptdump_fops);
+#endif
+
+	return 0;
+}
+
+device_initcall(ptdump_init);
diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c
new file mode 100644
index 000000000..ef701fa83
--- /dev/null
+++ b/arch/riscv/mm/tlbflush.c
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/sched.h>
+#include <asm/sbi.h>
+#include <asm/mmu_context.h>
+
+static inline void local_flush_tlb_all_asid(unsigned long asid)
+{
+	__asm__ __volatile__ ("sfence.vma x0, %0"
+			:
+			: "r" (asid)
+			: "memory");
+}
+
+static inline void local_flush_tlb_page_asid(unsigned long addr,
+		unsigned long asid)
+{
+	__asm__ __volatile__ ("sfence.vma %0, %1"
+			:
+			: "r" (addr), "r" (asid)
+			: "memory");
+}
+
+void flush_tlb_all(void)
+{
+	sbi_remote_sfence_vma(NULL, 0, -1);
+}
+
+static void __sbi_tlb_flush_range(struct mm_struct *mm, unsigned long start,
+				  unsigned long size, unsigned long stride)
+{
+	struct cpumask *cmask = mm_cpumask(mm);
+	unsigned int cpuid;
+	bool broadcast;
+
+	if (cpumask_empty(cmask))
+		return;
+
+	cpuid = get_cpu();
+	/* check if the tlbflush needs to be sent to other CPUs */
+	broadcast = cpumask_any_but(cmask, cpuid) < nr_cpu_ids;
+	if (static_branch_unlikely(&use_asid_allocator)) {
+		unsigned long asid = atomic_long_read(&mm->context.id) & asid_mask;
+
+		if (broadcast) {
+			sbi_remote_sfence_vma_asid(cmask, start, size, asid);
+		} else if (size <= stride) {
+			local_flush_tlb_page_asid(start, asid);
+		} else {
+			local_flush_tlb_all_asid(asid);
+		}
+	} else {
+		if (broadcast) {
+			sbi_remote_sfence_vma(cmask, start, size);
+		} else if (size <= stride) {
+			local_flush_tlb_page(start);
+		} else {
+			local_flush_tlb_all();
+		}
+	}
+
+	put_cpu();
+}
+
+void flush_tlb_mm(struct mm_struct *mm)
+{
+	__sbi_tlb_flush_range(mm, 0, -1, PAGE_SIZE);
+}
+
+void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr)
+{
+	__sbi_tlb_flush_range(vma->vm_mm, addr, PAGE_SIZE, PAGE_SIZE);
+}
+
+void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
+		     unsigned long end)
+{
+	__sbi_tlb_flush_range(vma->vm_mm, start, end - start, PAGE_SIZE);
+}
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
+			unsigned long end)
+{
+	__sbi_tlb_flush_range(vma->vm_mm, start, end - start, PMD_SIZE);
+}
+#endif
diff --git a/arch/riscv/net/Makefile b/arch/riscv/net/Makefile
new file mode 100644
index 000000000..9a1e5f0a9
--- /dev/null
+++ b/arch/riscv/net/Makefile
@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+obj-$(CONFIG_BPF_JIT) += bpf_jit_core.o
+
+ifeq ($(CONFIG_ARCH_RV64I),y)
+	obj-$(CONFIG_BPF_JIT) += bpf_jit_comp64.o
+else
+	obj-$(CONFIG_BPF_JIT) += bpf_jit_comp32.o
+endif
diff --git a/arch/riscv/net/bpf_jit.h b/arch/riscv/net/bpf_jit.h
new file mode 100644
index 000000000..5ee21a199
--- /dev/null
+++ b/arch/riscv/net/bpf_jit.h
@@ -0,0 +1,1060 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Common functionality for RV32 and RV64 BPF JIT compilers
+ *
+ * Copyright (c) 2019 Björn Töpel <bjorn.topel@gmail.com>
+ *
+ */
+
+#ifndef _BPF_JIT_H
+#define _BPF_JIT_H
+
+#include <linux/bpf.h>
+#include <linux/filter.h>
+#include <asm/cacheflush.h>
+
+static inline bool rvc_enabled(void)
+{
+	return IS_ENABLED(CONFIG_RISCV_ISA_C);
+}
+
+enum {
+	RV_REG_ZERO =	0,	/* The constant value 0 */
+	RV_REG_RA =	1,	/* Return address */
+	RV_REG_SP =	2,	/* Stack pointer */
+	RV_REG_GP =	3,	/* Global pointer */
+	RV_REG_TP =	4,	/* Thread pointer */
+	RV_REG_T0 =	5,	/* Temporaries */
+	RV_REG_T1 =	6,
+	RV_REG_T2 =	7,
+	RV_REG_FP =	8,	/* Saved register/frame pointer */
+	RV_REG_S1 =	9,	/* Saved register */
+	RV_REG_A0 =	10,	/* Function argument/return values */
+	RV_REG_A1 =	11,	/* Function arguments */
+	RV_REG_A2 =	12,
+	RV_REG_A3 =	13,
+	RV_REG_A4 =	14,
+	RV_REG_A5 =	15,
+	RV_REG_A6 =	16,
+	RV_REG_A7 =	17,
+	RV_REG_S2 =	18,	/* Saved registers */
+	RV_REG_S3 =	19,
+	RV_REG_S4 =	20,
+	RV_REG_S5 =	21,
+	RV_REG_S6 =	22,
+	RV_REG_S7 =	23,
+	RV_REG_S8 =	24,
+	RV_REG_S9 =	25,
+	RV_REG_S10 =	26,
+	RV_REG_S11 =	27,
+	RV_REG_T3 =	28,	/* Temporaries */
+	RV_REG_T4 =	29,
+	RV_REG_T5 =	30,
+	RV_REG_T6 =	31,
+};
+
+static inline bool is_creg(u8 reg)
+{
+	return (1 << reg) & (BIT(RV_REG_FP) |
+			     BIT(RV_REG_S1) |
+			     BIT(RV_REG_A0) |
+			     BIT(RV_REG_A1) |
+			     BIT(RV_REG_A2) |
+			     BIT(RV_REG_A3) |
+			     BIT(RV_REG_A4) |
+			     BIT(RV_REG_A5));
+}
+
+struct rv_jit_context {
+	struct bpf_prog *prog;
+	u16 *insns;		/* RV insns */
+	int ninsns;
+	int prologue_len;
+	int epilogue_offset;
+	int *offset;		/* BPF to RV */
+	int nexentries;
+	unsigned long flags;
+	int stack_size;
+};
+
+/* Convert from ninsns to bytes. */
+static inline int ninsns_rvoff(int ninsns)
+{
+	return ninsns << 1;
+}
+
+struct rv_jit_data {
+	struct bpf_binary_header *header;
+	u8 *image;
+	struct rv_jit_context ctx;
+};
+
+static inline void bpf_fill_ill_insns(void *area, unsigned int size)
+{
+	memset(area, 0, size);
+}
+
+static inline void bpf_flush_icache(void *start, void *end)
+{
+	flush_icache_range((unsigned long)start, (unsigned long)end);
+}
+
+/* Emit a 4-byte riscv instruction. */
+static inline void emit(const u32 insn, struct rv_jit_context *ctx)
+{
+	if (ctx->insns) {
+		ctx->insns[ctx->ninsns] = insn;
+		ctx->insns[ctx->ninsns + 1] = (insn >> 16);
+	}
+
+	ctx->ninsns += 2;
+}
+
+/* Emit a 2-byte riscv compressed instruction. */
+static inline void emitc(const u16 insn, struct rv_jit_context *ctx)
+{
+	BUILD_BUG_ON(!rvc_enabled());
+
+	if (ctx->insns)
+		ctx->insns[ctx->ninsns] = insn;
+
+	ctx->ninsns++;
+}
+
+static inline int epilogue_offset(struct rv_jit_context *ctx)
+{
+	int to = ctx->epilogue_offset, from = ctx->ninsns;
+
+	return ninsns_rvoff(to - from);
+}
+
+/* Return -1 or inverted cond. */
+static inline int invert_bpf_cond(u8 cond)
+{
+	switch (cond) {
+	case BPF_JEQ:
+		return BPF_JNE;
+	case BPF_JGT:
+		return BPF_JLE;
+	case BPF_JLT:
+		return BPF_JGE;
+	case BPF_JGE:
+		return BPF_JLT;
+	case BPF_JLE:
+		return BPF_JGT;
+	case BPF_JNE:
+		return BPF_JEQ;
+	case BPF_JSGT:
+		return BPF_JSLE;
+	case BPF_JSLT:
+		return BPF_JSGE;
+	case BPF_JSGE:
+		return BPF_JSLT;
+	case BPF_JSLE:
+		return BPF_JSGT;
+	}
+	return -1;
+}
+
+static inline bool is_6b_int(long val)
+{
+	return -(1L << 5) <= val && val < (1L << 5);
+}
+
+static inline bool is_7b_uint(unsigned long val)
+{
+	return val < (1UL << 7);
+}
+
+static inline bool is_8b_uint(unsigned long val)
+{
+	return val < (1UL << 8);
+}
+
+static inline bool is_9b_uint(unsigned long val)
+{
+	return val < (1UL << 9);
+}
+
+static inline bool is_10b_int(long val)
+{
+	return -(1L << 9) <= val && val < (1L << 9);
+}
+
+static inline bool is_10b_uint(unsigned long val)
+{
+	return val < (1UL << 10);
+}
+
+static inline bool is_12b_int(long val)
+{
+	return -(1L << 11) <= val && val < (1L << 11);
+}
+
+static inline int is_12b_check(int off, int insn)
+{
+	if (!is_12b_int(off)) {
+		pr_err("bpf-jit: insn=%d 12b < offset=%d not supported yet!\n",
+		       insn, (int)off);
+		return -1;
+	}
+	return 0;
+}
+
+static inline bool is_13b_int(long val)
+{
+	return -(1L << 12) <= val && val < (1L << 12);
+}
+
+static inline bool is_21b_int(long val)
+{
+	return -(1L << 20) <= val && val < (1L << 20);
+}
+
+static inline int rv_offset(int insn, int off, struct rv_jit_context *ctx)
+{
+	int from, to;
+
+	off++; /* BPF branch is from PC+1, RV is from PC */
+	from = (insn > 0) ? ctx->offset[insn - 1] : ctx->prologue_len;
+	to = (insn + off > 0) ? ctx->offset[insn + off - 1] : ctx->prologue_len;
+	return ninsns_rvoff(to - from);
+}
+
+/* Instruction formats. */
+
+static inline u32 rv_r_insn(u8 funct7, u8 rs2, u8 rs1, u8 funct3, u8 rd,
+			    u8 opcode)
+{
+	return (funct7 << 25) | (rs2 << 20) | (rs1 << 15) | (funct3 << 12) |
+		(rd << 7) | opcode;
+}
+
+static inline u32 rv_i_insn(u16 imm11_0, u8 rs1, u8 funct3, u8 rd, u8 opcode)
+{
+	return (imm11_0 << 20) | (rs1 << 15) | (funct3 << 12) | (rd << 7) |
+		opcode;
+}
+
+static inline u32 rv_s_insn(u16 imm11_0, u8 rs2, u8 rs1, u8 funct3, u8 opcode)
+{
+	u8 imm11_5 = imm11_0 >> 5, imm4_0 = imm11_0 & 0x1f;
+
+	return (imm11_5 << 25) | (rs2 << 20) | (rs1 << 15) | (funct3 << 12) |
+		(imm4_0 << 7) | opcode;
+}
+
+static inline u32 rv_b_insn(u16 imm12_1, u8 rs2, u8 rs1, u8 funct3, u8 opcode)
+{
+	u8 imm12 = ((imm12_1 & 0x800) >> 5) | ((imm12_1 & 0x3f0) >> 4);
+	u8 imm4_1 = ((imm12_1 & 0xf) << 1) | ((imm12_1 & 0x400) >> 10);
+
+	return (imm12 << 25) | (rs2 << 20) | (rs1 << 15) | (funct3 << 12) |
+		(imm4_1 << 7) | opcode;
+}
+
+static inline u32 rv_u_insn(u32 imm31_12, u8 rd, u8 opcode)
+{
+	return (imm31_12 << 12) | (rd << 7) | opcode;
+}
+
+static inline u32 rv_j_insn(u32 imm20_1, u8 rd, u8 opcode)
+{
+	u32 imm;
+
+	imm = (imm20_1 & 0x80000) | ((imm20_1 & 0x3ff) << 9) |
+		((imm20_1 & 0x400) >> 2) | ((imm20_1 & 0x7f800) >> 11);
+
+	return (imm << 12) | (rd << 7) | opcode;
+}
+
+static inline u32 rv_amo_insn(u8 funct5, u8 aq, u8 rl, u8 rs2, u8 rs1,
+			      u8 funct3, u8 rd, u8 opcode)
+{
+	u8 funct7 = (funct5 << 2) | (aq << 1) | rl;
+
+	return rv_r_insn(funct7, rs2, rs1, funct3, rd, opcode);
+}
+
+/* RISC-V compressed instruction formats. */
+
+static inline u16 rv_cr_insn(u8 funct4, u8 rd, u8 rs2, u8 op)
+{
+	return (funct4 << 12) | (rd << 7) | (rs2 << 2) | op;
+}
+
+static inline u16 rv_ci_insn(u8 funct3, u32 imm6, u8 rd, u8 op)
+{
+	u32 imm;
+
+	imm = ((imm6 & 0x20) << 7) | ((imm6 & 0x1f) << 2);
+	return (funct3 << 13) | (rd << 7) | op | imm;
+}
+
+static inline u16 rv_css_insn(u8 funct3, u32 uimm, u8 rs2, u8 op)
+{
+	return (funct3 << 13) | (uimm << 7) | (rs2 << 2) | op;
+}
+
+static inline u16 rv_ciw_insn(u8 funct3, u32 uimm, u8 rd, u8 op)
+{
+	return (funct3 << 13) | (uimm << 5) | ((rd & 0x7) << 2) | op;
+}
+
+static inline u16 rv_cl_insn(u8 funct3, u32 imm_hi, u8 rs1, u32 imm_lo, u8 rd,
+			     u8 op)
+{
+	return (funct3 << 13) | (imm_hi << 10) | ((rs1 & 0x7) << 7) |
+		(imm_lo << 5) | ((rd & 0x7) << 2) | op;
+}
+
+static inline u16 rv_cs_insn(u8 funct3, u32 imm_hi, u8 rs1, u32 imm_lo, u8 rs2,
+			     u8 op)
+{
+	return (funct3 << 13) | (imm_hi << 10) | ((rs1 & 0x7) << 7) |
+		(imm_lo << 5) | ((rs2 & 0x7) << 2) | op;
+}
+
+static inline u16 rv_ca_insn(u8 funct6, u8 rd, u8 funct2, u8 rs2, u8 op)
+{
+	return (funct6 << 10) | ((rd & 0x7) << 7) | (funct2 << 5) |
+		((rs2 & 0x7) << 2) | op;
+}
+
+static inline u16 rv_cb_insn(u8 funct3, u32 imm6, u8 funct2, u8 rd, u8 op)
+{
+	u32 imm;
+
+	imm = ((imm6 & 0x20) << 7) | ((imm6 & 0x1f) << 2);
+	return (funct3 << 13) | (funct2 << 10) | ((rd & 0x7) << 7) | op | imm;
+}
+
+/* Instructions shared by both RV32 and RV64. */
+
+static inline u32 rv_addi(u8 rd, u8 rs1, u16 imm11_0)
+{
+	return rv_i_insn(imm11_0, rs1, 0, rd, 0x13);
+}
+
+static inline u32 rv_andi(u8 rd, u8 rs1, u16 imm11_0)
+{
+	return rv_i_insn(imm11_0, rs1, 7, rd, 0x13);
+}
+
+static inline u32 rv_ori(u8 rd, u8 rs1, u16 imm11_0)
+{
+	return rv_i_insn(imm11_0, rs1, 6, rd, 0x13);
+}
+
+static inline u32 rv_xori(u8 rd, u8 rs1, u16 imm11_0)
+{
+	return rv_i_insn(imm11_0, rs1, 4, rd, 0x13);
+}
+
+static inline u32 rv_slli(u8 rd, u8 rs1, u16 imm11_0)
+{
+	return rv_i_insn(imm11_0, rs1, 1, rd, 0x13);
+}
+
+static inline u32 rv_srli(u8 rd, u8 rs1, u16 imm11_0)
+{
+	return rv_i_insn(imm11_0, rs1, 5, rd, 0x13);
+}
+
+static inline u32 rv_srai(u8 rd, u8 rs1, u16 imm11_0)
+{
+	return rv_i_insn(0x400 | imm11_0, rs1, 5, rd, 0x13);
+}
+
+static inline u32 rv_lui(u8 rd, u32 imm31_12)
+{
+	return rv_u_insn(imm31_12, rd, 0x37);
+}
+
+static inline u32 rv_auipc(u8 rd, u32 imm31_12)
+{
+	return rv_u_insn(imm31_12, rd, 0x17);
+}
+
+static inline u32 rv_add(u8 rd, u8 rs1, u8 rs2)
+{
+	return rv_r_insn(0, rs2, rs1, 0, rd, 0x33);
+}
+
+static inline u32 rv_sub(u8 rd, u8 rs1, u8 rs2)
+{
+	return rv_r_insn(0x20, rs2, rs1, 0, rd, 0x33);
+}
+
+static inline u32 rv_sltu(u8 rd, u8 rs1, u8 rs2)
+{
+	return rv_r_insn(0, rs2, rs1, 3, rd, 0x33);
+}
+
+static inline u32 rv_and(u8 rd, u8 rs1, u8 rs2)
+{
+	return rv_r_insn(0, rs2, rs1, 7, rd, 0x33);
+}
+
+static inline u32 rv_or(u8 rd, u8 rs1, u8 rs2)
+{
+	return rv_r_insn(0, rs2, rs1, 6, rd, 0x33);
+}
+
+static inline u32 rv_xor(u8 rd, u8 rs1, u8 rs2)
+{
+	return rv_r_insn(0, rs2, rs1, 4, rd, 0x33);
+}
+
+static inline u32 rv_sll(u8 rd, u8 rs1, u8 rs2)
+{
+	return rv_r_insn(0, rs2, rs1, 1, rd, 0x33);
+}
+
+static inline u32 rv_srl(u8 rd, u8 rs1, u8 rs2)
+{
+	return rv_r_insn(0, rs2, rs1, 5, rd, 0x33);
+}
+
+static inline u32 rv_sra(u8 rd, u8 rs1, u8 rs2)
+{
+	return rv_r_insn(0x20, rs2, rs1, 5, rd, 0x33);
+}
+
+static inline u32 rv_mul(u8 rd, u8 rs1, u8 rs2)
+{
+	return rv_r_insn(1, rs2, rs1, 0, rd, 0x33);
+}
+
+static inline u32 rv_mulhu(u8 rd, u8 rs1, u8 rs2)
+{
+	return rv_r_insn(1, rs2, rs1, 3, rd, 0x33);
+}
+
+static inline u32 rv_divu(u8 rd, u8 rs1, u8 rs2)
+{
+	return rv_r_insn(1, rs2, rs1, 5, rd, 0x33);
+}
+
+static inline u32 rv_remu(u8 rd, u8 rs1, u8 rs2)
+{
+	return rv_r_insn(1, rs2, rs1, 7, rd, 0x33);
+}
+
+static inline u32 rv_jal(u8 rd, u32 imm20_1)
+{
+	return rv_j_insn(imm20_1, rd, 0x6f);
+}
+
+static inline u32 rv_jalr(u8 rd, u8 rs1, u16 imm11_0)
+{
+	return rv_i_insn(imm11_0, rs1, 0, rd, 0x67);
+}
+
+static inline u32 rv_beq(u8 rs1, u8 rs2, u16 imm12_1)
+{
+	return rv_b_insn(imm12_1, rs2, rs1, 0, 0x63);
+}
+
+static inline u32 rv_bne(u8 rs1, u8 rs2, u16 imm12_1)
+{
+	return rv_b_insn(imm12_1, rs2, rs1, 1, 0x63);
+}
+
+static inline u32 rv_bltu(u8 rs1, u8 rs2, u16 imm12_1)
+{
+	return rv_b_insn(imm12_1, rs2, rs1, 6, 0x63);
+}
+
+static inline u32 rv_bgtu(u8 rs1, u8 rs2, u16 imm12_1)
+{
+	return rv_bltu(rs2, rs1, imm12_1);
+}
+
+static inline u32 rv_bgeu(u8 rs1, u8 rs2, u16 imm12_1)
+{
+	return rv_b_insn(imm12_1, rs2, rs1, 7, 0x63);
+}
+
+static inline u32 rv_bleu(u8 rs1, u8 rs2, u16 imm12_1)
+{
+	return rv_bgeu(rs2, rs1, imm12_1);
+}
+
+static inline u32 rv_blt(u8 rs1, u8 rs2, u16 imm12_1)
+{
+	return rv_b_insn(imm12_1, rs2, rs1, 4, 0x63);
+}
+
+static inline u32 rv_bgt(u8 rs1, u8 rs2, u16 imm12_1)
+{
+	return rv_blt(rs2, rs1, imm12_1);
+}
+
+static inline u32 rv_bge(u8 rs1, u8 rs2, u16 imm12_1)
+{
+	return rv_b_insn(imm12_1, rs2, rs1, 5, 0x63);
+}
+
+static inline u32 rv_ble(u8 rs1, u8 rs2, u16 imm12_1)
+{
+	return rv_bge(rs2, rs1, imm12_1);
+}
+
+static inline u32 rv_lw(u8 rd, u16 imm11_0, u8 rs1)
+{
+	return rv_i_insn(imm11_0, rs1, 2, rd, 0x03);
+}
+
+static inline u32 rv_lbu(u8 rd, u16 imm11_0, u8 rs1)
+{
+	return rv_i_insn(imm11_0, rs1, 4, rd, 0x03);
+}
+
+static inline u32 rv_lhu(u8 rd, u16 imm11_0, u8 rs1)
+{
+	return rv_i_insn(imm11_0, rs1, 5, rd, 0x03);
+}
+
+static inline u32 rv_sb(u8 rs1, u16 imm11_0, u8 rs2)
+{
+	return rv_s_insn(imm11_0, rs2, rs1, 0, 0x23);
+}
+
+static inline u32 rv_sh(u8 rs1, u16 imm11_0, u8 rs2)
+{
+	return rv_s_insn(imm11_0, rs2, rs1, 1, 0x23);
+}
+
+static inline u32 rv_sw(u8 rs1, u16 imm11_0, u8 rs2)
+{
+	return rv_s_insn(imm11_0, rs2, rs1, 2, 0x23);
+}
+
+static inline u32 rv_amoadd_w(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl)
+{
+	return rv_amo_insn(0, aq, rl, rs2, rs1, 2, rd, 0x2f);
+}
+
+static inline u32 rv_amoand_w(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl)
+{
+	return rv_amo_insn(0xc, aq, rl, rs2, rs1, 2, rd, 0x2f);
+}
+
+static inline u32 rv_amoor_w(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl)
+{
+	return rv_amo_insn(0x8, aq, rl, rs2, rs1, 2, rd, 0x2f);
+}
+
+static inline u32 rv_amoxor_w(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl)
+{
+	return rv_amo_insn(0x4, aq, rl, rs2, rs1, 2, rd, 0x2f);
+}
+
+static inline u32 rv_amoswap_w(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl)
+{
+	return rv_amo_insn(0x1, aq, rl, rs2, rs1, 2, rd, 0x2f);
+}
+
+static inline u32 rv_lr_w(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl)
+{
+	return rv_amo_insn(0x2, aq, rl, rs2, rs1, 2, rd, 0x2f);
+}
+
+static inline u32 rv_sc_w(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl)
+{
+	return rv_amo_insn(0x3, aq, rl, rs2, rs1, 2, rd, 0x2f);
+}
+
+static inline u32 rv_fence(u8 pred, u8 succ)
+{
+	u16 imm11_0 = pred << 4 | succ;
+
+	return rv_i_insn(imm11_0, 0, 0, 0, 0xf);
+}
+
+/* RVC instrutions. */
+
+static inline u16 rvc_addi4spn(u8 rd, u32 imm10)
+{
+	u32 imm;
+
+	imm = ((imm10 & 0x30) << 2) | ((imm10 & 0x3c0) >> 4) |
+		((imm10 & 0x4) >> 1) | ((imm10 & 0x8) >> 3);
+	return rv_ciw_insn(0x0, imm, rd, 0x0);
+}
+
+static inline u16 rvc_lw(u8 rd, u32 imm7, u8 rs1)
+{
+	u32 imm_hi, imm_lo;
+
+	imm_hi = (imm7 & 0x38) >> 3;
+	imm_lo = ((imm7 & 0x4) >> 1) | ((imm7 & 0x40) >> 6);
+	return rv_cl_insn(0x2, imm_hi, rs1, imm_lo, rd, 0x0);
+}
+
+static inline u16 rvc_sw(u8 rs1, u32 imm7, u8 rs2)
+{
+	u32 imm_hi, imm_lo;
+
+	imm_hi = (imm7 & 0x38) >> 3;
+	imm_lo = ((imm7 & 0x4) >> 1) | ((imm7 & 0x40) >> 6);
+	return rv_cs_insn(0x6, imm_hi, rs1, imm_lo, rs2, 0x0);
+}
+
+static inline u16 rvc_addi(u8 rd, u32 imm6)
+{
+	return rv_ci_insn(0, imm6, rd, 0x1);
+}
+
+static inline u16 rvc_li(u8 rd, u32 imm6)
+{
+	return rv_ci_insn(0x2, imm6, rd, 0x1);
+}
+
+static inline u16 rvc_addi16sp(u32 imm10)
+{
+	u32 imm;
+
+	imm = ((imm10 & 0x200) >> 4) | (imm10 & 0x10) | ((imm10 & 0x40) >> 3) |
+		((imm10 & 0x180) >> 6) | ((imm10 & 0x20) >> 5);
+	return rv_ci_insn(0x3, imm, RV_REG_SP, 0x1);
+}
+
+static inline u16 rvc_lui(u8 rd, u32 imm6)
+{
+	return rv_ci_insn(0x3, imm6, rd, 0x1);
+}
+
+static inline u16 rvc_srli(u8 rd, u32 imm6)
+{
+	return rv_cb_insn(0x4, imm6, 0, rd, 0x1);
+}
+
+static inline u16 rvc_srai(u8 rd, u32 imm6)
+{
+	return rv_cb_insn(0x4, imm6, 0x1, rd, 0x1);
+}
+
+static inline u16 rvc_andi(u8 rd, u32 imm6)
+{
+	return rv_cb_insn(0x4, imm6, 0x2, rd, 0x1);
+}
+
+static inline u16 rvc_sub(u8 rd, u8 rs)
+{
+	return rv_ca_insn(0x23, rd, 0, rs, 0x1);
+}
+
+static inline u16 rvc_xor(u8 rd, u8 rs)
+{
+	return rv_ca_insn(0x23, rd, 0x1, rs, 0x1);
+}
+
+static inline u16 rvc_or(u8 rd, u8 rs)
+{
+	return rv_ca_insn(0x23, rd, 0x2, rs, 0x1);
+}
+
+static inline u16 rvc_and(u8 rd, u8 rs)
+{
+	return rv_ca_insn(0x23, rd, 0x3, rs, 0x1);
+}
+
+static inline u16 rvc_slli(u8 rd, u32 imm6)
+{
+	return rv_ci_insn(0, imm6, rd, 0x2);
+}
+
+static inline u16 rvc_lwsp(u8 rd, u32 imm8)
+{
+	u32 imm;
+
+	imm = ((imm8 & 0xc0) >> 6) | (imm8 & 0x3c);
+	return rv_ci_insn(0x2, imm, rd, 0x2);
+}
+
+static inline u16 rvc_jr(u8 rs1)
+{
+	return rv_cr_insn(0x8, rs1, RV_REG_ZERO, 0x2);
+}
+
+static inline u16 rvc_mv(u8 rd, u8 rs)
+{
+	return rv_cr_insn(0x8, rd, rs, 0x2);
+}
+
+static inline u16 rvc_jalr(u8 rs1)
+{
+	return rv_cr_insn(0x9, rs1, RV_REG_ZERO, 0x2);
+}
+
+static inline u16 rvc_add(u8 rd, u8 rs)
+{
+	return rv_cr_insn(0x9, rd, rs, 0x2);
+}
+
+static inline u16 rvc_swsp(u32 imm8, u8 rs2)
+{
+	u32 imm;
+
+	imm = (imm8 & 0x3c) | ((imm8 & 0xc0) >> 6);
+	return rv_css_insn(0x6, imm, rs2, 0x2);
+}
+
+/*
+ * RV64-only instructions.
+ *
+ * These instructions are not available on RV32.  Wrap them below a #if to
+ * ensure that the RV32 JIT doesn't emit any of these instructions.
+ */
+
+#if __riscv_xlen == 64
+
+static inline u32 rv_addiw(u8 rd, u8 rs1, u16 imm11_0)
+{
+	return rv_i_insn(imm11_0, rs1, 0, rd, 0x1b);
+}
+
+static inline u32 rv_slliw(u8 rd, u8 rs1, u16 imm11_0)
+{
+	return rv_i_insn(imm11_0, rs1, 1, rd, 0x1b);
+}
+
+static inline u32 rv_srliw(u8 rd, u8 rs1, u16 imm11_0)
+{
+	return rv_i_insn(imm11_0, rs1, 5, rd, 0x1b);
+}
+
+static inline u32 rv_sraiw(u8 rd, u8 rs1, u16 imm11_0)
+{
+	return rv_i_insn(0x400 | imm11_0, rs1, 5, rd, 0x1b);
+}
+
+static inline u32 rv_addw(u8 rd, u8 rs1, u8 rs2)
+{
+	return rv_r_insn(0, rs2, rs1, 0, rd, 0x3b);
+}
+
+static inline u32 rv_subw(u8 rd, u8 rs1, u8 rs2)
+{
+	return rv_r_insn(0x20, rs2, rs1, 0, rd, 0x3b);
+}
+
+static inline u32 rv_sllw(u8 rd, u8 rs1, u8 rs2)
+{
+	return rv_r_insn(0, rs2, rs1, 1, rd, 0x3b);
+}
+
+static inline u32 rv_srlw(u8 rd, u8 rs1, u8 rs2)
+{
+	return rv_r_insn(0, rs2, rs1, 5, rd, 0x3b);
+}
+
+static inline u32 rv_sraw(u8 rd, u8 rs1, u8 rs2)
+{
+	return rv_r_insn(0x20, rs2, rs1, 5, rd, 0x3b);
+}
+
+static inline u32 rv_mulw(u8 rd, u8 rs1, u8 rs2)
+{
+	return rv_r_insn(1, rs2, rs1, 0, rd, 0x3b);
+}
+
+static inline u32 rv_divuw(u8 rd, u8 rs1, u8 rs2)
+{
+	return rv_r_insn(1, rs2, rs1, 5, rd, 0x3b);
+}
+
+static inline u32 rv_remuw(u8 rd, u8 rs1, u8 rs2)
+{
+	return rv_r_insn(1, rs2, rs1, 7, rd, 0x3b);
+}
+
+static inline u32 rv_ld(u8 rd, u16 imm11_0, u8 rs1)
+{
+	return rv_i_insn(imm11_0, rs1, 3, rd, 0x03);
+}
+
+static inline u32 rv_lwu(u8 rd, u16 imm11_0, u8 rs1)
+{
+	return rv_i_insn(imm11_0, rs1, 6, rd, 0x03);
+}
+
+static inline u32 rv_sd(u8 rs1, u16 imm11_0, u8 rs2)
+{
+	return rv_s_insn(imm11_0, rs2, rs1, 3, 0x23);
+}
+
+static inline u32 rv_amoadd_d(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl)
+{
+	return rv_amo_insn(0, aq, rl, rs2, rs1, 3, rd, 0x2f);
+}
+
+static inline u32 rv_amoand_d(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl)
+{
+	return rv_amo_insn(0xc, aq, rl, rs2, rs1, 3, rd, 0x2f);
+}
+
+static inline u32 rv_amoor_d(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl)
+{
+	return rv_amo_insn(0x8, aq, rl, rs2, rs1, 3, rd, 0x2f);
+}
+
+static inline u32 rv_amoxor_d(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl)
+{
+	return rv_amo_insn(0x4, aq, rl, rs2, rs1, 3, rd, 0x2f);
+}
+
+static inline u32 rv_amoswap_d(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl)
+{
+	return rv_amo_insn(0x1, aq, rl, rs2, rs1, 3, rd, 0x2f);
+}
+
+static inline u32 rv_lr_d(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl)
+{
+	return rv_amo_insn(0x2, aq, rl, rs2, rs1, 3, rd, 0x2f);
+}
+
+static inline u32 rv_sc_d(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl)
+{
+	return rv_amo_insn(0x3, aq, rl, rs2, rs1, 3, rd, 0x2f);
+}
+
+/* RV64-only RVC instructions. */
+
+static inline u16 rvc_ld(u8 rd, u32 imm8, u8 rs1)
+{
+	u32 imm_hi, imm_lo;
+
+	imm_hi = (imm8 & 0x38) >> 3;
+	imm_lo = (imm8 & 0xc0) >> 6;
+	return rv_cl_insn(0x3, imm_hi, rs1, imm_lo, rd, 0x0);
+}
+
+static inline u16 rvc_sd(u8 rs1, u32 imm8, u8 rs2)
+{
+	u32 imm_hi, imm_lo;
+
+	imm_hi = (imm8 & 0x38) >> 3;
+	imm_lo = (imm8 & 0xc0) >> 6;
+	return rv_cs_insn(0x7, imm_hi, rs1, imm_lo, rs2, 0x0);
+}
+
+static inline u16 rvc_subw(u8 rd, u8 rs)
+{
+	return rv_ca_insn(0x27, rd, 0, rs, 0x1);
+}
+
+static inline u16 rvc_addiw(u8 rd, u32 imm6)
+{
+	return rv_ci_insn(0x1, imm6, rd, 0x1);
+}
+
+static inline u16 rvc_ldsp(u8 rd, u32 imm9)
+{
+	u32 imm;
+
+	imm = ((imm9 & 0x1c0) >> 6) | (imm9 & 0x38);
+	return rv_ci_insn(0x3, imm, rd, 0x2);
+}
+
+static inline u16 rvc_sdsp(u32 imm9, u8 rs2)
+{
+	u32 imm;
+
+	imm = (imm9 & 0x38) | ((imm9 & 0x1c0) >> 6);
+	return rv_css_insn(0x7, imm, rs2, 0x2);
+}
+
+#endif /* __riscv_xlen == 64 */
+
+/* Helper functions that emit RVC instructions when possible. */
+
+static inline void emit_jalr(u8 rd, u8 rs, s32 imm, struct rv_jit_context *ctx)
+{
+	if (rvc_enabled() && rd == RV_REG_RA && rs && !imm)
+		emitc(rvc_jalr(rs), ctx);
+	else if (rvc_enabled() && !rd && rs && !imm)
+		emitc(rvc_jr(rs), ctx);
+	else
+		emit(rv_jalr(rd, rs, imm), ctx);
+}
+
+static inline void emit_mv(u8 rd, u8 rs, struct rv_jit_context *ctx)
+{
+	if (rvc_enabled() && rd && rs)
+		emitc(rvc_mv(rd, rs), ctx);
+	else
+		emit(rv_addi(rd, rs, 0), ctx);
+}
+
+static inline void emit_add(u8 rd, u8 rs1, u8 rs2, struct rv_jit_context *ctx)
+{
+	if (rvc_enabled() && rd && rd == rs1 && rs2)
+		emitc(rvc_add(rd, rs2), ctx);
+	else
+		emit(rv_add(rd, rs1, rs2), ctx);
+}
+
+static inline void emit_addi(u8 rd, u8 rs, s32 imm, struct rv_jit_context *ctx)
+{
+	if (rvc_enabled() && rd == RV_REG_SP && rd == rs && is_10b_int(imm) && imm && !(imm & 0xf))
+		emitc(rvc_addi16sp(imm), ctx);
+	else if (rvc_enabled() && is_creg(rd) && rs == RV_REG_SP && is_10b_uint(imm) &&
+		 !(imm & 0x3) && imm)
+		emitc(rvc_addi4spn(rd, imm), ctx);
+	else if (rvc_enabled() && rd && rd == rs && imm && is_6b_int(imm))
+		emitc(rvc_addi(rd, imm), ctx);
+	else
+		emit(rv_addi(rd, rs, imm), ctx);
+}
+
+static inline void emit_li(u8 rd, s32 imm, struct rv_jit_context *ctx)
+{
+	if (rvc_enabled() && rd && is_6b_int(imm))
+		emitc(rvc_li(rd, imm), ctx);
+	else
+		emit(rv_addi(rd, RV_REG_ZERO, imm), ctx);
+}
+
+static inline void emit_lui(u8 rd, s32 imm, struct rv_jit_context *ctx)
+{
+	if (rvc_enabled() && rd && rd != RV_REG_SP && is_6b_int(imm) && imm)
+		emitc(rvc_lui(rd, imm), ctx);
+	else
+		emit(rv_lui(rd, imm), ctx);
+}
+
+static inline void emit_slli(u8 rd, u8 rs, s32 imm, struct rv_jit_context *ctx)
+{
+	if (rvc_enabled() && rd && rd == rs && imm && (u32)imm < __riscv_xlen)
+		emitc(rvc_slli(rd, imm), ctx);
+	else
+		emit(rv_slli(rd, rs, imm), ctx);
+}
+
+static inline void emit_andi(u8 rd, u8 rs, s32 imm, struct rv_jit_context *ctx)
+{
+	if (rvc_enabled() && is_creg(rd) && rd == rs && is_6b_int(imm))
+		emitc(rvc_andi(rd, imm), ctx);
+	else
+		emit(rv_andi(rd, rs, imm), ctx);
+}
+
+static inline void emit_srli(u8 rd, u8 rs, s32 imm, struct rv_jit_context *ctx)
+{
+	if (rvc_enabled() && is_creg(rd) && rd == rs && imm && (u32)imm < __riscv_xlen)
+		emitc(rvc_srli(rd, imm), ctx);
+	else
+		emit(rv_srli(rd, rs, imm), ctx);
+}
+
+static inline void emit_srai(u8 rd, u8 rs, s32 imm, struct rv_jit_context *ctx)
+{
+	if (rvc_enabled() && is_creg(rd) && rd == rs && imm && (u32)imm < __riscv_xlen)
+		emitc(rvc_srai(rd, imm), ctx);
+	else
+		emit(rv_srai(rd, rs, imm), ctx);
+}
+
+static inline void emit_sub(u8 rd, u8 rs1, u8 rs2, struct rv_jit_context *ctx)
+{
+	if (rvc_enabled() && is_creg(rd) && rd == rs1 && is_creg(rs2))
+		emitc(rvc_sub(rd, rs2), ctx);
+	else
+		emit(rv_sub(rd, rs1, rs2), ctx);
+}
+
+static inline void emit_or(u8 rd, u8 rs1, u8 rs2, struct rv_jit_context *ctx)
+{
+	if (rvc_enabled() && is_creg(rd) && rd == rs1 && is_creg(rs2))
+		emitc(rvc_or(rd, rs2), ctx);
+	else
+		emit(rv_or(rd, rs1, rs2), ctx);
+}
+
+static inline void emit_and(u8 rd, u8 rs1, u8 rs2, struct rv_jit_context *ctx)
+{
+	if (rvc_enabled() && is_creg(rd) && rd == rs1 && is_creg(rs2))
+		emitc(rvc_and(rd, rs2), ctx);
+	else
+		emit(rv_and(rd, rs1, rs2), ctx);
+}
+
+static inline void emit_xor(u8 rd, u8 rs1, u8 rs2, struct rv_jit_context *ctx)
+{
+	if (rvc_enabled() && is_creg(rd) && rd == rs1 && is_creg(rs2))
+		emitc(rvc_xor(rd, rs2), ctx);
+	else
+		emit(rv_xor(rd, rs1, rs2), ctx);
+}
+
+static inline void emit_lw(u8 rd, s32 off, u8 rs1, struct rv_jit_context *ctx)
+{
+	if (rvc_enabled() && rs1 == RV_REG_SP && rd && is_8b_uint(off) && !(off & 0x3))
+		emitc(rvc_lwsp(rd, off), ctx);
+	else if (rvc_enabled() && is_creg(rd) && is_creg(rs1) && is_7b_uint(off) && !(off & 0x3))
+		emitc(rvc_lw(rd, off, rs1), ctx);
+	else
+		emit(rv_lw(rd, off, rs1), ctx);
+}
+
+static inline void emit_sw(u8 rs1, s32 off, u8 rs2, struct rv_jit_context *ctx)
+{
+	if (rvc_enabled() && rs1 == RV_REG_SP && is_8b_uint(off) && !(off & 0x3))
+		emitc(rvc_swsp(off, rs2), ctx);
+	else if (rvc_enabled() && is_creg(rs1) && is_creg(rs2) && is_7b_uint(off) && !(off & 0x3))
+		emitc(rvc_sw(rs1, off, rs2), ctx);
+	else
+		emit(rv_sw(rs1, off, rs2), ctx);
+}
+
+/* RV64-only helper functions. */
+#if __riscv_xlen == 64
+
+static inline void emit_addiw(u8 rd, u8 rs, s32 imm, struct rv_jit_context *ctx)
+{
+	if (rvc_enabled() && rd && rd == rs && is_6b_int(imm))
+		emitc(rvc_addiw(rd, imm), ctx);
+	else
+		emit(rv_addiw(rd, rs, imm), ctx);
+}
+
+static inline void emit_ld(u8 rd, s32 off, u8 rs1, struct rv_jit_context *ctx)
+{
+	if (rvc_enabled() && rs1 == RV_REG_SP && rd && is_9b_uint(off) && !(off & 0x7))
+		emitc(rvc_ldsp(rd, off), ctx);
+	else if (rvc_enabled() && is_creg(rd) && is_creg(rs1) && is_8b_uint(off) && !(off & 0x7))
+		emitc(rvc_ld(rd, off, rs1), ctx);
+	else
+		emit(rv_ld(rd, off, rs1), ctx);
+}
+
+static inline void emit_sd(u8 rs1, s32 off, u8 rs2, struct rv_jit_context *ctx)
+{
+	if (rvc_enabled() && rs1 == RV_REG_SP && is_9b_uint(off) && !(off & 0x7))
+		emitc(rvc_sdsp(off, rs2), ctx);
+	else if (rvc_enabled() && is_creg(rs1) && is_creg(rs2) && is_8b_uint(off) && !(off & 0x7))
+		emitc(rvc_sd(rs1, off, rs2), ctx);
+	else
+		emit(rv_sd(rs1, off, rs2), ctx);
+}
+
+static inline void emit_subw(u8 rd, u8 rs1, u8 rs2, struct rv_jit_context *ctx)
+{
+	if (rvc_enabled() && is_creg(rd) && rd == rs1 && is_creg(rs2))
+		emitc(rvc_subw(rd, rs2), ctx);
+	else
+		emit(rv_subw(rd, rs1, rs2), ctx);
+}
+
+#endif /* __riscv_xlen == 64 */
+
+void bpf_jit_build_prologue(struct rv_jit_context *ctx);
+void bpf_jit_build_epilogue(struct rv_jit_context *ctx);
+
+int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
+		      bool extra_pass);
+
+#endif /* _BPF_JIT_H */
diff --git a/arch/riscv/net/bpf_jit_comp32.c b/arch/riscv/net/bpf_jit_comp32.c
new file mode 100644
index 000000000..529a83b85
--- /dev/null
+++ b/arch/riscv/net/bpf_jit_comp32.c
@@ -0,0 +1,1357 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * BPF JIT compiler for RV32G
+ *
+ * Copyright (c) 2020 Luke Nelson <luke.r.nels@gmail.com>
+ * Copyright (c) 2020 Xi Wang <xi.wang@gmail.com>
+ *
+ * The code is based on the BPF JIT compiler for RV64G by Björn Töpel and
+ * the BPF JIT compiler for 32-bit ARM by Shubham Bansal and Mircea Gherzan.
+ */
+
+#include <linux/bpf.h>
+#include <linux/filter.h>
+#include "bpf_jit.h"
+
+/*
+ * Stack layout during BPF program execution:
+ *
+ *                     high
+ *     RV32 fp =>  +----------+
+ *                 | saved ra |
+ *                 | saved fp | RV32 callee-saved registers
+ *                 |   ...    |
+ *                 +----------+ <= (fp - 4 * NR_SAVED_REGISTERS)
+ *                 |  hi(R6)  |
+ *                 |  lo(R6)  |
+ *                 |  hi(R7)  | JIT scratch space for BPF registers
+ *                 |  lo(R7)  |
+ *                 |   ...    |
+ *  BPF_REG_FP =>  +----------+ <= (fp - 4 * NR_SAVED_REGISTERS
+ *                 |          |        - 4 * BPF_JIT_SCRATCH_REGS)
+ *                 |          |
+ *                 |   ...    | BPF program stack
+ *                 |          |
+ *     RV32 sp =>  +----------+
+ *                 |          |
+ *                 |   ...    | Function call stack
+ *                 |          |
+ *                 +----------+
+ *                     low
+ */
+
+enum {
+	/* Stack layout - these are offsets from top of JIT scratch space. */
+	BPF_R6_HI,
+	BPF_R6_LO,
+	BPF_R7_HI,
+	BPF_R7_LO,
+	BPF_R8_HI,
+	BPF_R8_LO,
+	BPF_R9_HI,
+	BPF_R9_LO,
+	BPF_AX_HI,
+	BPF_AX_LO,
+	/* Stack space for BPF_REG_6 through BPF_REG_9 and BPF_REG_AX. */
+	BPF_JIT_SCRATCH_REGS,
+};
+
+/* Number of callee-saved registers stored to stack: ra, fp, s1--s7. */
+#define NR_SAVED_REGISTERS	9
+
+/* Offset from fp for BPF registers stored on stack. */
+#define STACK_OFFSET(k)	(-4 - (4 * NR_SAVED_REGISTERS) - (4 * (k)))
+
+#define TMP_REG_1	(MAX_BPF_JIT_REG + 0)
+#define TMP_REG_2	(MAX_BPF_JIT_REG + 1)
+
+#define RV_REG_TCC		RV_REG_T6
+#define RV_REG_TCC_SAVED	RV_REG_S7
+
+static const s8 bpf2rv32[][2] = {
+	/* Return value from in-kernel function, and exit value from eBPF. */
+	[BPF_REG_0] = {RV_REG_S2, RV_REG_S1},
+	/* Arguments from eBPF program to in-kernel function. */
+	[BPF_REG_1] = {RV_REG_A1, RV_REG_A0},
+	[BPF_REG_2] = {RV_REG_A3, RV_REG_A2},
+	[BPF_REG_3] = {RV_REG_A5, RV_REG_A4},
+	[BPF_REG_4] = {RV_REG_A7, RV_REG_A6},
+	[BPF_REG_5] = {RV_REG_S4, RV_REG_S3},
+	/*
+	 * Callee-saved registers that in-kernel function will preserve.
+	 * Stored on the stack.
+	 */
+	[BPF_REG_6] = {STACK_OFFSET(BPF_R6_HI), STACK_OFFSET(BPF_R6_LO)},
+	[BPF_REG_7] = {STACK_OFFSET(BPF_R7_HI), STACK_OFFSET(BPF_R7_LO)},
+	[BPF_REG_8] = {STACK_OFFSET(BPF_R8_HI), STACK_OFFSET(BPF_R8_LO)},
+	[BPF_REG_9] = {STACK_OFFSET(BPF_R9_HI), STACK_OFFSET(BPF_R9_LO)},
+	/* Read-only frame pointer to access BPF stack. */
+	[BPF_REG_FP] = {RV_REG_S6, RV_REG_S5},
+	/* Temporary register for blinding constants. Stored on the stack. */
+	[BPF_REG_AX] = {STACK_OFFSET(BPF_AX_HI), STACK_OFFSET(BPF_AX_LO)},
+	/*
+	 * Temporary registers used by the JIT to operate on registers stored
+	 * on the stack. Save t0 and t1 to be used as temporaries in generated
+	 * code.
+	 */
+	[TMP_REG_1] = {RV_REG_T3, RV_REG_T2},
+	[TMP_REG_2] = {RV_REG_T5, RV_REG_T4},
+};
+
+static s8 hi(const s8 *r)
+{
+	return r[0];
+}
+
+static s8 lo(const s8 *r)
+{
+	return r[1];
+}
+
+static void emit_imm(const s8 rd, s32 imm, struct rv_jit_context *ctx)
+{
+	u32 upper = (imm + (1 << 11)) >> 12;
+	u32 lower = imm & 0xfff;
+
+	if (upper) {
+		emit(rv_lui(rd, upper), ctx);
+		emit(rv_addi(rd, rd, lower), ctx);
+	} else {
+		emit(rv_addi(rd, RV_REG_ZERO, lower), ctx);
+	}
+}
+
+static void emit_imm32(const s8 *rd, s32 imm, struct rv_jit_context *ctx)
+{
+	/* Emit immediate into lower bits. */
+	emit_imm(lo(rd), imm, ctx);
+
+	/* Sign-extend into upper bits. */
+	if (imm >= 0)
+		emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx);
+	else
+		emit(rv_addi(hi(rd), RV_REG_ZERO, -1), ctx);
+}
+
+static void emit_imm64(const s8 *rd, s32 imm_hi, s32 imm_lo,
+		       struct rv_jit_context *ctx)
+{
+	emit_imm(lo(rd), imm_lo, ctx);
+	emit_imm(hi(rd), imm_hi, ctx);
+}
+
+static void __build_epilogue(bool is_tail_call, struct rv_jit_context *ctx)
+{
+	int stack_adjust = ctx->stack_size;
+	const s8 *r0 = bpf2rv32[BPF_REG_0];
+
+	/* Set return value if not tail call. */
+	if (!is_tail_call) {
+		emit(rv_addi(RV_REG_A0, lo(r0), 0), ctx);
+		emit(rv_addi(RV_REG_A1, hi(r0), 0), ctx);
+	}
+
+	/* Restore callee-saved registers. */
+	emit(rv_lw(RV_REG_RA, stack_adjust - 4, RV_REG_SP), ctx);
+	emit(rv_lw(RV_REG_FP, stack_adjust - 8, RV_REG_SP), ctx);
+	emit(rv_lw(RV_REG_S1, stack_adjust - 12, RV_REG_SP), ctx);
+	emit(rv_lw(RV_REG_S2, stack_adjust - 16, RV_REG_SP), ctx);
+	emit(rv_lw(RV_REG_S3, stack_adjust - 20, RV_REG_SP), ctx);
+	emit(rv_lw(RV_REG_S4, stack_adjust - 24, RV_REG_SP), ctx);
+	emit(rv_lw(RV_REG_S5, stack_adjust - 28, RV_REG_SP), ctx);
+	emit(rv_lw(RV_REG_S6, stack_adjust - 32, RV_REG_SP), ctx);
+	emit(rv_lw(RV_REG_S7, stack_adjust - 36, RV_REG_SP), ctx);
+
+	emit(rv_addi(RV_REG_SP, RV_REG_SP, stack_adjust), ctx);
+
+	if (is_tail_call) {
+		/*
+		 * goto *(t0 + 4);
+		 * Skips first instruction of prologue which initializes tail
+		 * call counter. Assumes t0 contains address of target program,
+		 * see emit_bpf_tail_call.
+		 */
+		emit(rv_jalr(RV_REG_ZERO, RV_REG_T0, 4), ctx);
+	} else {
+		emit(rv_jalr(RV_REG_ZERO, RV_REG_RA, 0), ctx);
+	}
+}
+
+static bool is_stacked(s8 reg)
+{
+	return reg < 0;
+}
+
+static const s8 *bpf_get_reg64(const s8 *reg, const s8 *tmp,
+			       struct rv_jit_context *ctx)
+{
+	if (is_stacked(hi(reg))) {
+		emit(rv_lw(hi(tmp), hi(reg), RV_REG_FP), ctx);
+		emit(rv_lw(lo(tmp), lo(reg), RV_REG_FP), ctx);
+		reg = tmp;
+	}
+	return reg;
+}
+
+static void bpf_put_reg64(const s8 *reg, const s8 *src,
+			  struct rv_jit_context *ctx)
+{
+	if (is_stacked(hi(reg))) {
+		emit(rv_sw(RV_REG_FP, hi(reg), hi(src)), ctx);
+		emit(rv_sw(RV_REG_FP, lo(reg), lo(src)), ctx);
+	}
+}
+
+static const s8 *bpf_get_reg32(const s8 *reg, const s8 *tmp,
+			       struct rv_jit_context *ctx)
+{
+	if (is_stacked(lo(reg))) {
+		emit(rv_lw(lo(tmp), lo(reg), RV_REG_FP), ctx);
+		reg = tmp;
+	}
+	return reg;
+}
+
+static void bpf_put_reg32(const s8 *reg, const s8 *src,
+			  struct rv_jit_context *ctx)
+{
+	if (is_stacked(lo(reg))) {
+		emit(rv_sw(RV_REG_FP, lo(reg), lo(src)), ctx);
+		if (!ctx->prog->aux->verifier_zext)
+			emit(rv_sw(RV_REG_FP, hi(reg), RV_REG_ZERO), ctx);
+	} else if (!ctx->prog->aux->verifier_zext) {
+		emit(rv_addi(hi(reg), RV_REG_ZERO, 0), ctx);
+	}
+}
+
+static void emit_jump_and_link(u8 rd, s32 rvoff, bool force_jalr,
+			       struct rv_jit_context *ctx)
+{
+	s32 upper, lower;
+
+	if (rvoff && is_21b_int(rvoff) && !force_jalr) {
+		emit(rv_jal(rd, rvoff >> 1), ctx);
+		return;
+	}
+
+	upper = (rvoff + (1 << 11)) >> 12;
+	lower = rvoff & 0xfff;
+	emit(rv_auipc(RV_REG_T1, upper), ctx);
+	emit(rv_jalr(rd, RV_REG_T1, lower), ctx);
+}
+
+static void emit_alu_i64(const s8 *dst, s32 imm,
+			 struct rv_jit_context *ctx, const u8 op)
+{
+	const s8 *tmp1 = bpf2rv32[TMP_REG_1];
+	const s8 *rd = bpf_get_reg64(dst, tmp1, ctx);
+
+	switch (op) {
+	case BPF_MOV:
+		emit_imm32(rd, imm, ctx);
+		break;
+	case BPF_AND:
+		if (is_12b_int(imm)) {
+			emit(rv_andi(lo(rd), lo(rd), imm), ctx);
+		} else {
+			emit_imm(RV_REG_T0, imm, ctx);
+			emit(rv_and(lo(rd), lo(rd), RV_REG_T0), ctx);
+		}
+		if (imm >= 0)
+			emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx);
+		break;
+	case BPF_OR:
+		if (is_12b_int(imm)) {
+			emit(rv_ori(lo(rd), lo(rd), imm), ctx);
+		} else {
+			emit_imm(RV_REG_T0, imm, ctx);
+			emit(rv_or(lo(rd), lo(rd), RV_REG_T0), ctx);
+		}
+		if (imm < 0)
+			emit(rv_ori(hi(rd), RV_REG_ZERO, -1), ctx);
+		break;
+	case BPF_XOR:
+		if (is_12b_int(imm)) {
+			emit(rv_xori(lo(rd), lo(rd), imm), ctx);
+		} else {
+			emit_imm(RV_REG_T0, imm, ctx);
+			emit(rv_xor(lo(rd), lo(rd), RV_REG_T0), ctx);
+		}
+		if (imm < 0)
+			emit(rv_xori(hi(rd), hi(rd), -1), ctx);
+		break;
+	case BPF_LSH:
+		if (imm >= 32) {
+			emit(rv_slli(hi(rd), lo(rd), imm - 32), ctx);
+			emit(rv_addi(lo(rd), RV_REG_ZERO, 0), ctx);
+		} else if (imm == 0) {
+			/* Do nothing. */
+		} else {
+			emit(rv_srli(RV_REG_T0, lo(rd), 32 - imm), ctx);
+			emit(rv_slli(hi(rd), hi(rd), imm), ctx);
+			emit(rv_or(hi(rd), RV_REG_T0, hi(rd)), ctx);
+			emit(rv_slli(lo(rd), lo(rd), imm), ctx);
+		}
+		break;
+	case BPF_RSH:
+		if (imm >= 32) {
+			emit(rv_srli(lo(rd), hi(rd), imm - 32), ctx);
+			emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx);
+		} else if (imm == 0) {
+			/* Do nothing. */
+		} else {
+			emit(rv_slli(RV_REG_T0, hi(rd), 32 - imm), ctx);
+			emit(rv_srli(lo(rd), lo(rd), imm), ctx);
+			emit(rv_or(lo(rd), RV_REG_T0, lo(rd)), ctx);
+			emit(rv_srli(hi(rd), hi(rd), imm), ctx);
+		}
+		break;
+	case BPF_ARSH:
+		if (imm >= 32) {
+			emit(rv_srai(lo(rd), hi(rd), imm - 32), ctx);
+			emit(rv_srai(hi(rd), hi(rd), 31), ctx);
+		} else if (imm == 0) {
+			/* Do nothing. */
+		} else {
+			emit(rv_slli(RV_REG_T0, hi(rd), 32 - imm), ctx);
+			emit(rv_srli(lo(rd), lo(rd), imm), ctx);
+			emit(rv_or(lo(rd), RV_REG_T0, lo(rd)), ctx);
+			emit(rv_srai(hi(rd), hi(rd), imm), ctx);
+		}
+		break;
+	}
+
+	bpf_put_reg64(dst, rd, ctx);
+}
+
+static void emit_alu_i32(const s8 *dst, s32 imm,
+			 struct rv_jit_context *ctx, const u8 op)
+{
+	const s8 *tmp1 = bpf2rv32[TMP_REG_1];
+	const s8 *rd = bpf_get_reg32(dst, tmp1, ctx);
+
+	switch (op) {
+	case BPF_MOV:
+		emit_imm(lo(rd), imm, ctx);
+		break;
+	case BPF_ADD:
+		if (is_12b_int(imm)) {
+			emit(rv_addi(lo(rd), lo(rd), imm), ctx);
+		} else {
+			emit_imm(RV_REG_T0, imm, ctx);
+			emit(rv_add(lo(rd), lo(rd), RV_REG_T0), ctx);
+		}
+		break;
+	case BPF_SUB:
+		if (is_12b_int(-imm)) {
+			emit(rv_addi(lo(rd), lo(rd), -imm), ctx);
+		} else {
+			emit_imm(RV_REG_T0, imm, ctx);
+			emit(rv_sub(lo(rd), lo(rd), RV_REG_T0), ctx);
+		}
+		break;
+	case BPF_AND:
+		if (is_12b_int(imm)) {
+			emit(rv_andi(lo(rd), lo(rd), imm), ctx);
+		} else {
+			emit_imm(RV_REG_T0, imm, ctx);
+			emit(rv_and(lo(rd), lo(rd), RV_REG_T0), ctx);
+		}
+		break;
+	case BPF_OR:
+		if (is_12b_int(imm)) {
+			emit(rv_ori(lo(rd), lo(rd), imm), ctx);
+		} else {
+			emit_imm(RV_REG_T0, imm, ctx);
+			emit(rv_or(lo(rd), lo(rd), RV_REG_T0), ctx);
+		}
+		break;
+	case BPF_XOR:
+		if (is_12b_int(imm)) {
+			emit(rv_xori(lo(rd), lo(rd), imm), ctx);
+		} else {
+			emit_imm(RV_REG_T0, imm, ctx);
+			emit(rv_xor(lo(rd), lo(rd), RV_REG_T0), ctx);
+		}
+		break;
+	case BPF_LSH:
+		if (is_12b_int(imm)) {
+			emit(rv_slli(lo(rd), lo(rd), imm), ctx);
+		} else {
+			emit_imm(RV_REG_T0, imm, ctx);
+			emit(rv_sll(lo(rd), lo(rd), RV_REG_T0), ctx);
+		}
+		break;
+	case BPF_RSH:
+		if (is_12b_int(imm)) {
+			emit(rv_srli(lo(rd), lo(rd), imm), ctx);
+		} else {
+			emit_imm(RV_REG_T0, imm, ctx);
+			emit(rv_srl(lo(rd), lo(rd), RV_REG_T0), ctx);
+		}
+		break;
+	case BPF_ARSH:
+		if (is_12b_int(imm)) {
+			emit(rv_srai(lo(rd), lo(rd), imm), ctx);
+		} else {
+			emit_imm(RV_REG_T0, imm, ctx);
+			emit(rv_sra(lo(rd), lo(rd), RV_REG_T0), ctx);
+		}
+		break;
+	}
+
+	bpf_put_reg32(dst, rd, ctx);
+}
+
+static void emit_alu_r64(const s8 *dst, const s8 *src,
+			 struct rv_jit_context *ctx, const u8 op)
+{
+	const s8 *tmp1 = bpf2rv32[TMP_REG_1];
+	const s8 *tmp2 = bpf2rv32[TMP_REG_2];
+	const s8 *rd = bpf_get_reg64(dst, tmp1, ctx);
+	const s8 *rs = bpf_get_reg64(src, tmp2, ctx);
+
+	switch (op) {
+	case BPF_MOV:
+		emit(rv_addi(lo(rd), lo(rs), 0), ctx);
+		emit(rv_addi(hi(rd), hi(rs), 0), ctx);
+		break;
+	case BPF_ADD:
+		if (rd == rs) {
+			emit(rv_srli(RV_REG_T0, lo(rd), 31), ctx);
+			emit(rv_slli(hi(rd), hi(rd), 1), ctx);
+			emit(rv_or(hi(rd), RV_REG_T0, hi(rd)), ctx);
+			emit(rv_slli(lo(rd), lo(rd), 1), ctx);
+		} else {
+			emit(rv_add(lo(rd), lo(rd), lo(rs)), ctx);
+			emit(rv_sltu(RV_REG_T0, lo(rd), lo(rs)), ctx);
+			emit(rv_add(hi(rd), hi(rd), hi(rs)), ctx);
+			emit(rv_add(hi(rd), hi(rd), RV_REG_T0), ctx);
+		}
+		break;
+	case BPF_SUB:
+		emit(rv_sub(RV_REG_T1, hi(rd), hi(rs)), ctx);
+		emit(rv_sltu(RV_REG_T0, lo(rd), lo(rs)), ctx);
+		emit(rv_sub(hi(rd), RV_REG_T1, RV_REG_T0), ctx);
+		emit(rv_sub(lo(rd), lo(rd), lo(rs)), ctx);
+		break;
+	case BPF_AND:
+		emit(rv_and(lo(rd), lo(rd), lo(rs)), ctx);
+		emit(rv_and(hi(rd), hi(rd), hi(rs)), ctx);
+		break;
+	case BPF_OR:
+		emit(rv_or(lo(rd), lo(rd), lo(rs)), ctx);
+		emit(rv_or(hi(rd), hi(rd), hi(rs)), ctx);
+		break;
+	case BPF_XOR:
+		emit(rv_xor(lo(rd), lo(rd), lo(rs)), ctx);
+		emit(rv_xor(hi(rd), hi(rd), hi(rs)), ctx);
+		break;
+	case BPF_MUL:
+		emit(rv_mul(RV_REG_T0, hi(rs), lo(rd)), ctx);
+		emit(rv_mul(hi(rd), hi(rd), lo(rs)), ctx);
+		emit(rv_mulhu(RV_REG_T1, lo(rd), lo(rs)), ctx);
+		emit(rv_add(hi(rd), hi(rd), RV_REG_T0), ctx);
+		emit(rv_mul(lo(rd), lo(rd), lo(rs)), ctx);
+		emit(rv_add(hi(rd), hi(rd), RV_REG_T1), ctx);
+		break;
+	case BPF_LSH:
+		emit(rv_addi(RV_REG_T0, lo(rs), -32), ctx);
+		emit(rv_blt(RV_REG_T0, RV_REG_ZERO, 8), ctx);
+		emit(rv_sll(hi(rd), lo(rd), RV_REG_T0), ctx);
+		emit(rv_addi(lo(rd), RV_REG_ZERO, 0), ctx);
+		emit(rv_jal(RV_REG_ZERO, 16), ctx);
+		emit(rv_addi(RV_REG_T1, RV_REG_ZERO, 31), ctx);
+		emit(rv_srli(RV_REG_T0, lo(rd), 1), ctx);
+		emit(rv_sub(RV_REG_T1, RV_REG_T1, lo(rs)), ctx);
+		emit(rv_srl(RV_REG_T0, RV_REG_T0, RV_REG_T1), ctx);
+		emit(rv_sll(hi(rd), hi(rd), lo(rs)), ctx);
+		emit(rv_or(hi(rd), RV_REG_T0, hi(rd)), ctx);
+		emit(rv_sll(lo(rd), lo(rd), lo(rs)), ctx);
+		break;
+	case BPF_RSH:
+		emit(rv_addi(RV_REG_T0, lo(rs), -32), ctx);
+		emit(rv_blt(RV_REG_T0, RV_REG_ZERO, 8), ctx);
+		emit(rv_srl(lo(rd), hi(rd), RV_REG_T0), ctx);
+		emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx);
+		emit(rv_jal(RV_REG_ZERO, 16), ctx);
+		emit(rv_addi(RV_REG_T1, RV_REG_ZERO, 31), ctx);
+		emit(rv_slli(RV_REG_T0, hi(rd), 1), ctx);
+		emit(rv_sub(RV_REG_T1, RV_REG_T1, lo(rs)), ctx);
+		emit(rv_sll(RV_REG_T0, RV_REG_T0, RV_REG_T1), ctx);
+		emit(rv_srl(lo(rd), lo(rd), lo(rs)), ctx);
+		emit(rv_or(lo(rd), RV_REG_T0, lo(rd)), ctx);
+		emit(rv_srl(hi(rd), hi(rd), lo(rs)), ctx);
+		break;
+	case BPF_ARSH:
+		emit(rv_addi(RV_REG_T0, lo(rs), -32), ctx);
+		emit(rv_blt(RV_REG_T0, RV_REG_ZERO, 8), ctx);
+		emit(rv_sra(lo(rd), hi(rd), RV_REG_T0), ctx);
+		emit(rv_srai(hi(rd), hi(rd), 31), ctx);
+		emit(rv_jal(RV_REG_ZERO, 16), ctx);
+		emit(rv_addi(RV_REG_T1, RV_REG_ZERO, 31), ctx);
+		emit(rv_slli(RV_REG_T0, hi(rd), 1), ctx);
+		emit(rv_sub(RV_REG_T1, RV_REG_T1, lo(rs)), ctx);
+		emit(rv_sll(RV_REG_T0, RV_REG_T0, RV_REG_T1), ctx);
+		emit(rv_srl(lo(rd), lo(rd), lo(rs)), ctx);
+		emit(rv_or(lo(rd), RV_REG_T0, lo(rd)), ctx);
+		emit(rv_sra(hi(rd), hi(rd), lo(rs)), ctx);
+		break;
+	case BPF_NEG:
+		emit(rv_sub(lo(rd), RV_REG_ZERO, lo(rd)), ctx);
+		emit(rv_sltu(RV_REG_T0, RV_REG_ZERO, lo(rd)), ctx);
+		emit(rv_sub(hi(rd), RV_REG_ZERO, hi(rd)), ctx);
+		emit(rv_sub(hi(rd), hi(rd), RV_REG_T0), ctx);
+		break;
+	}
+
+	bpf_put_reg64(dst, rd, ctx);
+}
+
+static void emit_alu_r32(const s8 *dst, const s8 *src,
+			 struct rv_jit_context *ctx, const u8 op)
+{
+	const s8 *tmp1 = bpf2rv32[TMP_REG_1];
+	const s8 *tmp2 = bpf2rv32[TMP_REG_2];
+	const s8 *rd = bpf_get_reg32(dst, tmp1, ctx);
+	const s8 *rs = bpf_get_reg32(src, tmp2, ctx);
+
+	switch (op) {
+	case BPF_MOV:
+		emit(rv_addi(lo(rd), lo(rs), 0), ctx);
+		break;
+	case BPF_ADD:
+		emit(rv_add(lo(rd), lo(rd), lo(rs)), ctx);
+		break;
+	case BPF_SUB:
+		emit(rv_sub(lo(rd), lo(rd), lo(rs)), ctx);
+		break;
+	case BPF_AND:
+		emit(rv_and(lo(rd), lo(rd), lo(rs)), ctx);
+		break;
+	case BPF_OR:
+		emit(rv_or(lo(rd), lo(rd), lo(rs)), ctx);
+		break;
+	case BPF_XOR:
+		emit(rv_xor(lo(rd), lo(rd), lo(rs)), ctx);
+		break;
+	case BPF_MUL:
+		emit(rv_mul(lo(rd), lo(rd), lo(rs)), ctx);
+		break;
+	case BPF_DIV:
+		emit(rv_divu(lo(rd), lo(rd), lo(rs)), ctx);
+		break;
+	case BPF_MOD:
+		emit(rv_remu(lo(rd), lo(rd), lo(rs)), ctx);
+		break;
+	case BPF_LSH:
+		emit(rv_sll(lo(rd), lo(rd), lo(rs)), ctx);
+		break;
+	case BPF_RSH:
+		emit(rv_srl(lo(rd), lo(rd), lo(rs)), ctx);
+		break;
+	case BPF_ARSH:
+		emit(rv_sra(lo(rd), lo(rd), lo(rs)), ctx);
+		break;
+	case BPF_NEG:
+		emit(rv_sub(lo(rd), RV_REG_ZERO, lo(rd)), ctx);
+		break;
+	}
+
+	bpf_put_reg32(dst, rd, ctx);
+}
+
+static int emit_branch_r64(const s8 *src1, const s8 *src2, s32 rvoff,
+			   struct rv_jit_context *ctx, const u8 op)
+{
+	int e, s = ctx->ninsns;
+	const s8 *tmp1 = bpf2rv32[TMP_REG_1];
+	const s8 *tmp2 = bpf2rv32[TMP_REG_2];
+
+	const s8 *rs1 = bpf_get_reg64(src1, tmp1, ctx);
+	const s8 *rs2 = bpf_get_reg64(src2, tmp2, ctx);
+
+	/*
+	 * NO_JUMP skips over the rest of the instructions and the
+	 * emit_jump_and_link, meaning the BPF branch is not taken.
+	 * JUMP skips directly to the emit_jump_and_link, meaning
+	 * the BPF branch is taken.
+	 *
+	 * The fallthrough case results in the BPF branch being taken.
+	 */
+#define NO_JUMP(idx) (6 + (2 * (idx)))
+#define JUMP(idx) (2 + (2 * (idx)))
+
+	switch (op) {
+	case BPF_JEQ:
+		emit(rv_bne(hi(rs1), hi(rs2), NO_JUMP(1)), ctx);
+		emit(rv_bne(lo(rs1), lo(rs2), NO_JUMP(0)), ctx);
+		break;
+	case BPF_JGT:
+		emit(rv_bgtu(hi(rs1), hi(rs2), JUMP(2)), ctx);
+		emit(rv_bltu(hi(rs1), hi(rs2), NO_JUMP(1)), ctx);
+		emit(rv_bleu(lo(rs1), lo(rs2), NO_JUMP(0)), ctx);
+		break;
+	case BPF_JLT:
+		emit(rv_bltu(hi(rs1), hi(rs2), JUMP(2)), ctx);
+		emit(rv_bgtu(hi(rs1), hi(rs2), NO_JUMP(1)), ctx);
+		emit(rv_bgeu(lo(rs1), lo(rs2), NO_JUMP(0)), ctx);
+		break;
+	case BPF_JGE:
+		emit(rv_bgtu(hi(rs1), hi(rs2), JUMP(2)), ctx);
+		emit(rv_bltu(hi(rs1), hi(rs2), NO_JUMP(1)), ctx);
+		emit(rv_bltu(lo(rs1), lo(rs2), NO_JUMP(0)), ctx);
+		break;
+	case BPF_JLE:
+		emit(rv_bltu(hi(rs1), hi(rs2), JUMP(2)), ctx);
+		emit(rv_bgtu(hi(rs1), hi(rs2), NO_JUMP(1)), ctx);
+		emit(rv_bgtu(lo(rs1), lo(rs2), NO_JUMP(0)), ctx);
+		break;
+	case BPF_JNE:
+		emit(rv_bne(hi(rs1), hi(rs2), JUMP(1)), ctx);
+		emit(rv_beq(lo(rs1), lo(rs2), NO_JUMP(0)), ctx);
+		break;
+	case BPF_JSGT:
+		emit(rv_bgt(hi(rs1), hi(rs2), JUMP(2)), ctx);
+		emit(rv_blt(hi(rs1), hi(rs2), NO_JUMP(1)), ctx);
+		emit(rv_bleu(lo(rs1), lo(rs2), NO_JUMP(0)), ctx);
+		break;
+	case BPF_JSLT:
+		emit(rv_blt(hi(rs1), hi(rs2), JUMP(2)), ctx);
+		emit(rv_bgt(hi(rs1), hi(rs2), NO_JUMP(1)), ctx);
+		emit(rv_bgeu(lo(rs1), lo(rs2), NO_JUMP(0)), ctx);
+		break;
+	case BPF_JSGE:
+		emit(rv_bgt(hi(rs1), hi(rs2), JUMP(2)), ctx);
+		emit(rv_blt(hi(rs1), hi(rs2), NO_JUMP(1)), ctx);
+		emit(rv_bltu(lo(rs1), lo(rs2), NO_JUMP(0)), ctx);
+		break;
+	case BPF_JSLE:
+		emit(rv_blt(hi(rs1), hi(rs2), JUMP(2)), ctx);
+		emit(rv_bgt(hi(rs1), hi(rs2), NO_JUMP(1)), ctx);
+		emit(rv_bgtu(lo(rs1), lo(rs2), NO_JUMP(0)), ctx);
+		break;
+	case BPF_JSET:
+		emit(rv_and(RV_REG_T0, hi(rs1), hi(rs2)), ctx);
+		emit(rv_bne(RV_REG_T0, RV_REG_ZERO, JUMP(2)), ctx);
+		emit(rv_and(RV_REG_T0, lo(rs1), lo(rs2)), ctx);
+		emit(rv_beq(RV_REG_T0, RV_REG_ZERO, NO_JUMP(0)), ctx);
+		break;
+	}
+
+#undef NO_JUMP
+#undef JUMP
+
+	e = ctx->ninsns;
+	/* Adjust for extra insns. */
+	rvoff -= ninsns_rvoff(e - s);
+	emit_jump_and_link(RV_REG_ZERO, rvoff, true, ctx);
+	return 0;
+}
+
+static int emit_bcc(u8 op, u8 rd, u8 rs, int rvoff, struct rv_jit_context *ctx)
+{
+	int e, s = ctx->ninsns;
+	bool far = false;
+	int off;
+
+	if (op == BPF_JSET) {
+		/*
+		 * BPF_JSET is a special case: it has no inverse so we always
+		 * treat it as a far branch.
+		 */
+		far = true;
+	} else if (!is_13b_int(rvoff)) {
+		op = invert_bpf_cond(op);
+		far = true;
+	}
+
+	/*
+	 * For a far branch, the condition is negated and we jump over the
+	 * branch itself, and the two instructions from emit_jump_and_link.
+	 * For a near branch, just use rvoff.
+	 */
+	off = far ? 6 : (rvoff >> 1);
+
+	switch (op) {
+	case BPF_JEQ:
+		emit(rv_beq(rd, rs, off), ctx);
+		break;
+	case BPF_JGT:
+		emit(rv_bgtu(rd, rs, off), ctx);
+		break;
+	case BPF_JLT:
+		emit(rv_bltu(rd, rs, off), ctx);
+		break;
+	case BPF_JGE:
+		emit(rv_bgeu(rd, rs, off), ctx);
+		break;
+	case BPF_JLE:
+		emit(rv_bleu(rd, rs, off), ctx);
+		break;
+	case BPF_JNE:
+		emit(rv_bne(rd, rs, off), ctx);
+		break;
+	case BPF_JSGT:
+		emit(rv_bgt(rd, rs, off), ctx);
+		break;
+	case BPF_JSLT:
+		emit(rv_blt(rd, rs, off), ctx);
+		break;
+	case BPF_JSGE:
+		emit(rv_bge(rd, rs, off), ctx);
+		break;
+	case BPF_JSLE:
+		emit(rv_ble(rd, rs, off), ctx);
+		break;
+	case BPF_JSET:
+		emit(rv_and(RV_REG_T0, rd, rs), ctx);
+		emit(rv_beq(RV_REG_T0, RV_REG_ZERO, off), ctx);
+		break;
+	}
+
+	if (far) {
+		e = ctx->ninsns;
+		/* Adjust for extra insns. */
+		rvoff -= ninsns_rvoff(e - s);
+		emit_jump_and_link(RV_REG_ZERO, rvoff, true, ctx);
+	}
+	return 0;
+}
+
+static int emit_branch_r32(const s8 *src1, const s8 *src2, s32 rvoff,
+			   struct rv_jit_context *ctx, const u8 op)
+{
+	int e, s = ctx->ninsns;
+	const s8 *tmp1 = bpf2rv32[TMP_REG_1];
+	const s8 *tmp2 = bpf2rv32[TMP_REG_2];
+
+	const s8 *rs1 = bpf_get_reg32(src1, tmp1, ctx);
+	const s8 *rs2 = bpf_get_reg32(src2, tmp2, ctx);
+
+	e = ctx->ninsns;
+	/* Adjust for extra insns. */
+	rvoff -= ninsns_rvoff(e - s);
+
+	if (emit_bcc(op, lo(rs1), lo(rs2), rvoff, ctx))
+		return -1;
+
+	return 0;
+}
+
+static void emit_call(bool fixed, u64 addr, struct rv_jit_context *ctx)
+{
+	const s8 *r0 = bpf2rv32[BPF_REG_0];
+	const s8 *r5 = bpf2rv32[BPF_REG_5];
+	u32 upper = ((u32)addr + (1 << 11)) >> 12;
+	u32 lower = addr & 0xfff;
+
+	/* R1-R4 already in correct registers---need to push R5 to stack. */
+	emit(rv_addi(RV_REG_SP, RV_REG_SP, -16), ctx);
+	emit(rv_sw(RV_REG_SP, 0, lo(r5)), ctx);
+	emit(rv_sw(RV_REG_SP, 4, hi(r5)), ctx);
+
+	/* Backup TCC. */
+	emit(rv_addi(RV_REG_TCC_SAVED, RV_REG_TCC, 0), ctx);
+
+	/*
+	 * Use lui/jalr pair to jump to absolute address. Don't use emit_imm as
+	 * the number of emitted instructions should not depend on the value of
+	 * addr.
+	 */
+	emit(rv_lui(RV_REG_T1, upper), ctx);
+	emit(rv_jalr(RV_REG_RA, RV_REG_T1, lower), ctx);
+
+	/* Restore TCC. */
+	emit(rv_addi(RV_REG_TCC, RV_REG_TCC_SAVED, 0), ctx);
+
+	/* Set return value and restore stack. */
+	emit(rv_addi(lo(r0), RV_REG_A0, 0), ctx);
+	emit(rv_addi(hi(r0), RV_REG_A1, 0), ctx);
+	emit(rv_addi(RV_REG_SP, RV_REG_SP, 16), ctx);
+}
+
+static int emit_bpf_tail_call(int insn, struct rv_jit_context *ctx)
+{
+	/*
+	 * R1 -> &ctx
+	 * R2 -> &array
+	 * R3 -> index
+	 */
+	int tc_ninsn, off, start_insn = ctx->ninsns;
+	const s8 *arr_reg = bpf2rv32[BPF_REG_2];
+	const s8 *idx_reg = bpf2rv32[BPF_REG_3];
+
+	tc_ninsn = insn ? ctx->offset[insn] - ctx->offset[insn - 1] :
+		ctx->offset[0];
+
+	/* max_entries = array->map.max_entries; */
+	off = offsetof(struct bpf_array, map.max_entries);
+	if (is_12b_check(off, insn))
+		return -1;
+	emit(rv_lw(RV_REG_T1, off, lo(arr_reg)), ctx);
+
+	/*
+	 * if (index >= max_entries)
+	 *   goto out;
+	 */
+	off = ninsns_rvoff(tc_ninsn - (ctx->ninsns - start_insn));
+	emit_bcc(BPF_JGE, lo(idx_reg), RV_REG_T1, off, ctx);
+
+	/*
+	 * if (--tcc < 0)
+	 *   goto out;
+	 */
+	emit(rv_addi(RV_REG_TCC, RV_REG_TCC, -1), ctx);
+	off = ninsns_rvoff(tc_ninsn - (ctx->ninsns - start_insn));
+	emit_bcc(BPF_JSLT, RV_REG_TCC, RV_REG_ZERO, off, ctx);
+
+	/*
+	 * prog = array->ptrs[index];
+	 * if (!prog)
+	 *   goto out;
+	 */
+	emit(rv_slli(RV_REG_T0, lo(idx_reg), 2), ctx);
+	emit(rv_add(RV_REG_T0, RV_REG_T0, lo(arr_reg)), ctx);
+	off = offsetof(struct bpf_array, ptrs);
+	if (is_12b_check(off, insn))
+		return -1;
+	emit(rv_lw(RV_REG_T0, off, RV_REG_T0), ctx);
+	off = ninsns_rvoff(tc_ninsn - (ctx->ninsns - start_insn));
+	emit_bcc(BPF_JEQ, RV_REG_T0, RV_REG_ZERO, off, ctx);
+
+	/*
+	 * tcc = temp_tcc;
+	 * goto *(prog->bpf_func + 4);
+	 */
+	off = offsetof(struct bpf_prog, bpf_func);
+	if (is_12b_check(off, insn))
+		return -1;
+	emit(rv_lw(RV_REG_T0, off, RV_REG_T0), ctx);
+	/* Epilogue jumps to *(t0 + 4). */
+	__build_epilogue(true, ctx);
+	return 0;
+}
+
+static int emit_load_r64(const s8 *dst, const s8 *src, s16 off,
+			 struct rv_jit_context *ctx, const u8 size)
+{
+	const s8 *tmp1 = bpf2rv32[TMP_REG_1];
+	const s8 *tmp2 = bpf2rv32[TMP_REG_2];
+	const s8 *rd = bpf_get_reg64(dst, tmp1, ctx);
+	const s8 *rs = bpf_get_reg64(src, tmp2, ctx);
+
+	emit_imm(RV_REG_T0, off, ctx);
+	emit(rv_add(RV_REG_T0, RV_REG_T0, lo(rs)), ctx);
+
+	switch (size) {
+	case BPF_B:
+		emit(rv_lbu(lo(rd), 0, RV_REG_T0), ctx);
+		if (!ctx->prog->aux->verifier_zext)
+			emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx);
+		break;
+	case BPF_H:
+		emit(rv_lhu(lo(rd), 0, RV_REG_T0), ctx);
+		if (!ctx->prog->aux->verifier_zext)
+			emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx);
+		break;
+	case BPF_W:
+		emit(rv_lw(lo(rd), 0, RV_REG_T0), ctx);
+		if (!ctx->prog->aux->verifier_zext)
+			emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx);
+		break;
+	case BPF_DW:
+		emit(rv_lw(lo(rd), 0, RV_REG_T0), ctx);
+		emit(rv_lw(hi(rd), 4, RV_REG_T0), ctx);
+		break;
+	}
+
+	bpf_put_reg64(dst, rd, ctx);
+	return 0;
+}
+
+static int emit_store_r64(const s8 *dst, const s8 *src, s16 off,
+			  struct rv_jit_context *ctx, const u8 size,
+			  const u8 mode)
+{
+	const s8 *tmp1 = bpf2rv32[TMP_REG_1];
+	const s8 *tmp2 = bpf2rv32[TMP_REG_2];
+	const s8 *rd = bpf_get_reg64(dst, tmp1, ctx);
+	const s8 *rs = bpf_get_reg64(src, tmp2, ctx);
+
+	if (mode == BPF_ATOMIC && size != BPF_W)
+		return -1;
+
+	emit_imm(RV_REG_T0, off, ctx);
+	emit(rv_add(RV_REG_T0, RV_REG_T0, lo(rd)), ctx);
+
+	switch (size) {
+	case BPF_B:
+		emit(rv_sb(RV_REG_T0, 0, lo(rs)), ctx);
+		break;
+	case BPF_H:
+		emit(rv_sh(RV_REG_T0, 0, lo(rs)), ctx);
+		break;
+	case BPF_W:
+		switch (mode) {
+		case BPF_MEM:
+			emit(rv_sw(RV_REG_T0, 0, lo(rs)), ctx);
+			break;
+		case BPF_ATOMIC: /* Only BPF_ADD supported */
+			emit(rv_amoadd_w(RV_REG_ZERO, lo(rs), RV_REG_T0, 0, 0),
+			     ctx);
+			break;
+		}
+		break;
+	case BPF_DW:
+		emit(rv_sw(RV_REG_T0, 0, lo(rs)), ctx);
+		emit(rv_sw(RV_REG_T0, 4, hi(rs)), ctx);
+		break;
+	}
+
+	return 0;
+}
+
+static void emit_rev16(const s8 rd, struct rv_jit_context *ctx)
+{
+	emit(rv_slli(rd, rd, 16), ctx);
+	emit(rv_slli(RV_REG_T1, rd, 8), ctx);
+	emit(rv_srli(rd, rd, 8), ctx);
+	emit(rv_add(RV_REG_T1, rd, RV_REG_T1), ctx);
+	emit(rv_srli(rd, RV_REG_T1, 16), ctx);
+}
+
+static void emit_rev32(const s8 rd, struct rv_jit_context *ctx)
+{
+	emit(rv_addi(RV_REG_T1, RV_REG_ZERO, 0), ctx);
+	emit(rv_andi(RV_REG_T0, rd, 255), ctx);
+	emit(rv_add(RV_REG_T1, RV_REG_T1, RV_REG_T0), ctx);
+	emit(rv_slli(RV_REG_T1, RV_REG_T1, 8), ctx);
+	emit(rv_srli(rd, rd, 8), ctx);
+	emit(rv_andi(RV_REG_T0, rd, 255), ctx);
+	emit(rv_add(RV_REG_T1, RV_REG_T1, RV_REG_T0), ctx);
+	emit(rv_slli(RV_REG_T1, RV_REG_T1, 8), ctx);
+	emit(rv_srli(rd, rd, 8), ctx);
+	emit(rv_andi(RV_REG_T0, rd, 255), ctx);
+	emit(rv_add(RV_REG_T1, RV_REG_T1, RV_REG_T0), ctx);
+	emit(rv_slli(RV_REG_T1, RV_REG_T1, 8), ctx);
+	emit(rv_srli(rd, rd, 8), ctx);
+	emit(rv_andi(RV_REG_T0, rd, 255), ctx);
+	emit(rv_add(RV_REG_T1, RV_REG_T1, RV_REG_T0), ctx);
+	emit(rv_addi(rd, RV_REG_T1, 0), ctx);
+}
+
+static void emit_zext64(const s8 *dst, struct rv_jit_context *ctx)
+{
+	const s8 *rd;
+	const s8 *tmp1 = bpf2rv32[TMP_REG_1];
+
+	rd = bpf_get_reg64(dst, tmp1, ctx);
+	emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx);
+	bpf_put_reg64(dst, rd, ctx);
+}
+
+int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
+		      bool extra_pass)
+{
+	bool is64 = BPF_CLASS(insn->code) == BPF_ALU64 ||
+		BPF_CLASS(insn->code) == BPF_JMP;
+	int s, e, rvoff, i = insn - ctx->prog->insnsi;
+	u8 code = insn->code;
+	s16 off = insn->off;
+	s32 imm = insn->imm;
+
+	const s8 *dst = bpf2rv32[insn->dst_reg];
+	const s8 *src = bpf2rv32[insn->src_reg];
+	const s8 *tmp1 = bpf2rv32[TMP_REG_1];
+	const s8 *tmp2 = bpf2rv32[TMP_REG_2];
+
+	switch (code) {
+	case BPF_ALU64 | BPF_MOV | BPF_X:
+
+	case BPF_ALU64 | BPF_ADD | BPF_X:
+	case BPF_ALU64 | BPF_ADD | BPF_K:
+
+	case BPF_ALU64 | BPF_SUB | BPF_X:
+	case BPF_ALU64 | BPF_SUB | BPF_K:
+
+	case BPF_ALU64 | BPF_AND | BPF_X:
+	case BPF_ALU64 | BPF_OR | BPF_X:
+	case BPF_ALU64 | BPF_XOR | BPF_X:
+
+	case BPF_ALU64 | BPF_MUL | BPF_X:
+	case BPF_ALU64 | BPF_MUL | BPF_K:
+
+	case BPF_ALU64 | BPF_LSH | BPF_X:
+	case BPF_ALU64 | BPF_RSH | BPF_X:
+	case BPF_ALU64 | BPF_ARSH | BPF_X:
+		if (BPF_SRC(code) == BPF_K) {
+			emit_imm32(tmp2, imm, ctx);
+			src = tmp2;
+		}
+		emit_alu_r64(dst, src, ctx, BPF_OP(code));
+		break;
+
+	case BPF_ALU64 | BPF_NEG:
+		emit_alu_r64(dst, tmp2, ctx, BPF_OP(code));
+		break;
+
+	case BPF_ALU64 | BPF_DIV | BPF_X:
+	case BPF_ALU64 | BPF_DIV | BPF_K:
+	case BPF_ALU64 | BPF_MOD | BPF_X:
+	case BPF_ALU64 | BPF_MOD | BPF_K:
+		goto notsupported;
+
+	case BPF_ALU64 | BPF_MOV | BPF_K:
+	case BPF_ALU64 | BPF_AND | BPF_K:
+	case BPF_ALU64 | BPF_OR | BPF_K:
+	case BPF_ALU64 | BPF_XOR | BPF_K:
+	case BPF_ALU64 | BPF_LSH | BPF_K:
+	case BPF_ALU64 | BPF_RSH | BPF_K:
+	case BPF_ALU64 | BPF_ARSH | BPF_K:
+		emit_alu_i64(dst, imm, ctx, BPF_OP(code));
+		break;
+
+	case BPF_ALU | BPF_MOV | BPF_X:
+		if (imm == 1) {
+			/* Special mov32 for zext. */
+			emit_zext64(dst, ctx);
+			break;
+		}
+		fallthrough;
+
+	case BPF_ALU | BPF_ADD | BPF_X:
+	case BPF_ALU | BPF_SUB | BPF_X:
+	case BPF_ALU | BPF_AND | BPF_X:
+	case BPF_ALU | BPF_OR | BPF_X:
+	case BPF_ALU | BPF_XOR | BPF_X:
+
+	case BPF_ALU | BPF_MUL | BPF_X:
+	case BPF_ALU | BPF_MUL | BPF_K:
+
+	case BPF_ALU | BPF_DIV | BPF_X:
+	case BPF_ALU | BPF_DIV | BPF_K:
+
+	case BPF_ALU | BPF_MOD | BPF_X:
+	case BPF_ALU | BPF_MOD | BPF_K:
+
+	case BPF_ALU | BPF_LSH | BPF_X:
+	case BPF_ALU | BPF_RSH | BPF_X:
+	case BPF_ALU | BPF_ARSH | BPF_X:
+		if (BPF_SRC(code) == BPF_K) {
+			emit_imm32(tmp2, imm, ctx);
+			src = tmp2;
+		}
+		emit_alu_r32(dst, src, ctx, BPF_OP(code));
+		break;
+
+	case BPF_ALU | BPF_MOV | BPF_K:
+	case BPF_ALU | BPF_ADD | BPF_K:
+	case BPF_ALU | BPF_SUB | BPF_K:
+	case BPF_ALU | BPF_AND | BPF_K:
+	case BPF_ALU | BPF_OR | BPF_K:
+	case BPF_ALU | BPF_XOR | BPF_K:
+	case BPF_ALU | BPF_LSH | BPF_K:
+	case BPF_ALU | BPF_RSH | BPF_K:
+	case BPF_ALU | BPF_ARSH | BPF_K:
+		/*
+		 * mul,div,mod are handled in the BPF_X case since there are
+		 * no RISC-V I-type equivalents.
+		 */
+		emit_alu_i32(dst, imm, ctx, BPF_OP(code));
+		break;
+
+	case BPF_ALU | BPF_NEG:
+		/*
+		 * src is ignored---choose tmp2 as a dummy register since it
+		 * is not on the stack.
+		 */
+		emit_alu_r32(dst, tmp2, ctx, BPF_OP(code));
+		break;
+
+	case BPF_ALU | BPF_END | BPF_FROM_LE:
+	{
+		const s8 *rd = bpf_get_reg64(dst, tmp1, ctx);
+
+		switch (imm) {
+		case 16:
+			emit(rv_slli(lo(rd), lo(rd), 16), ctx);
+			emit(rv_srli(lo(rd), lo(rd), 16), ctx);
+			fallthrough;
+		case 32:
+			if (!ctx->prog->aux->verifier_zext)
+				emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx);
+			break;
+		case 64:
+			/* Do nothing. */
+			break;
+		default:
+			pr_err("bpf-jit: BPF_END imm %d invalid\n", imm);
+			return -1;
+		}
+
+		bpf_put_reg64(dst, rd, ctx);
+		break;
+	}
+
+	case BPF_ALU | BPF_END | BPF_FROM_BE:
+	{
+		const s8 *rd = bpf_get_reg64(dst, tmp1, ctx);
+
+		switch (imm) {
+		case 16:
+			emit_rev16(lo(rd), ctx);
+			if (!ctx->prog->aux->verifier_zext)
+				emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx);
+			break;
+		case 32:
+			emit_rev32(lo(rd), ctx);
+			if (!ctx->prog->aux->verifier_zext)
+				emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx);
+			break;
+		case 64:
+			/* Swap upper and lower halves. */
+			emit(rv_addi(RV_REG_T0, lo(rd), 0), ctx);
+			emit(rv_addi(lo(rd), hi(rd), 0), ctx);
+			emit(rv_addi(hi(rd), RV_REG_T0, 0), ctx);
+
+			/* Swap each half. */
+			emit_rev32(lo(rd), ctx);
+			emit_rev32(hi(rd), ctx);
+			break;
+		default:
+			pr_err("bpf-jit: BPF_END imm %d invalid\n", imm);
+			return -1;
+		}
+
+		bpf_put_reg64(dst, rd, ctx);
+		break;
+	}
+
+	case BPF_JMP | BPF_JA:
+		rvoff = rv_offset(i, off, ctx);
+		emit_jump_and_link(RV_REG_ZERO, rvoff, false, ctx);
+		break;
+
+	case BPF_JMP | BPF_CALL:
+	{
+		bool fixed;
+		int ret;
+		u64 addr;
+
+		ret = bpf_jit_get_func_addr(ctx->prog, insn, extra_pass, &addr,
+					    &fixed);
+		if (ret < 0)
+			return ret;
+		emit_call(fixed, addr, ctx);
+		break;
+	}
+
+	case BPF_JMP | BPF_TAIL_CALL:
+		if (emit_bpf_tail_call(i, ctx))
+			return -1;
+		break;
+
+	case BPF_JMP | BPF_JEQ | BPF_X:
+	case BPF_JMP | BPF_JEQ | BPF_K:
+	case BPF_JMP32 | BPF_JEQ | BPF_X:
+	case BPF_JMP32 | BPF_JEQ | BPF_K:
+
+	case BPF_JMP | BPF_JNE | BPF_X:
+	case BPF_JMP | BPF_JNE | BPF_K:
+	case BPF_JMP32 | BPF_JNE | BPF_X:
+	case BPF_JMP32 | BPF_JNE | BPF_K:
+
+	case BPF_JMP | BPF_JLE | BPF_X:
+	case BPF_JMP | BPF_JLE | BPF_K:
+	case BPF_JMP32 | BPF_JLE | BPF_X:
+	case BPF_JMP32 | BPF_JLE | BPF_K:
+
+	case BPF_JMP | BPF_JLT | BPF_X:
+	case BPF_JMP | BPF_JLT | BPF_K:
+	case BPF_JMP32 | BPF_JLT | BPF_X:
+	case BPF_JMP32 | BPF_JLT | BPF_K:
+
+	case BPF_JMP | BPF_JGE | BPF_X:
+	case BPF_JMP | BPF_JGE | BPF_K:
+	case BPF_JMP32 | BPF_JGE | BPF_X:
+	case BPF_JMP32 | BPF_JGE | BPF_K:
+
+	case BPF_JMP | BPF_JGT | BPF_X:
+	case BPF_JMP | BPF_JGT | BPF_K:
+	case BPF_JMP32 | BPF_JGT | BPF_X:
+	case BPF_JMP32 | BPF_JGT | BPF_K:
+
+	case BPF_JMP | BPF_JSLE | BPF_X:
+	case BPF_JMP | BPF_JSLE | BPF_K:
+	case BPF_JMP32 | BPF_JSLE | BPF_X:
+	case BPF_JMP32 | BPF_JSLE | BPF_K:
+
+	case BPF_JMP | BPF_JSLT | BPF_X:
+	case BPF_JMP | BPF_JSLT | BPF_K:
+	case BPF_JMP32 | BPF_JSLT | BPF_X:
+	case BPF_JMP32 | BPF_JSLT | BPF_K:
+
+	case BPF_JMP | BPF_JSGE | BPF_X:
+	case BPF_JMP | BPF_JSGE | BPF_K:
+	case BPF_JMP32 | BPF_JSGE | BPF_X:
+	case BPF_JMP32 | BPF_JSGE | BPF_K:
+
+	case BPF_JMP | BPF_JSGT | BPF_X:
+	case BPF_JMP | BPF_JSGT | BPF_K:
+	case BPF_JMP32 | BPF_JSGT | BPF_X:
+	case BPF_JMP32 | BPF_JSGT | BPF_K:
+
+	case BPF_JMP | BPF_JSET | BPF_X:
+	case BPF_JMP | BPF_JSET | BPF_K:
+	case BPF_JMP32 | BPF_JSET | BPF_X:
+	case BPF_JMP32 | BPF_JSET | BPF_K:
+		rvoff = rv_offset(i, off, ctx);
+		if (BPF_SRC(code) == BPF_K) {
+			s = ctx->ninsns;
+			emit_imm32(tmp2, imm, ctx);
+			src = tmp2;
+			e = ctx->ninsns;
+			rvoff -= ninsns_rvoff(e - s);
+		}
+
+		if (is64)
+			emit_branch_r64(dst, src, rvoff, ctx, BPF_OP(code));
+		else
+			emit_branch_r32(dst, src, rvoff, ctx, BPF_OP(code));
+		break;
+
+	case BPF_JMP | BPF_EXIT:
+		if (i == ctx->prog->len - 1)
+			break;
+
+		rvoff = epilogue_offset(ctx);
+		emit_jump_and_link(RV_REG_ZERO, rvoff, false, ctx);
+		break;
+
+	case BPF_LD | BPF_IMM | BPF_DW:
+	{
+		struct bpf_insn insn1 = insn[1];
+		s32 imm_lo = imm;
+		s32 imm_hi = insn1.imm;
+		const s8 *rd = bpf_get_reg64(dst, tmp1, ctx);
+
+		emit_imm64(rd, imm_hi, imm_lo, ctx);
+		bpf_put_reg64(dst, rd, ctx);
+		return 1;
+	}
+
+	case BPF_LDX | BPF_MEM | BPF_B:
+	case BPF_LDX | BPF_MEM | BPF_H:
+	case BPF_LDX | BPF_MEM | BPF_W:
+	case BPF_LDX | BPF_MEM | BPF_DW:
+		if (emit_load_r64(dst, src, off, ctx, BPF_SIZE(code)))
+			return -1;
+		break;
+
+	/* speculation barrier */
+	case BPF_ST | BPF_NOSPEC:
+		break;
+
+	case BPF_ST | BPF_MEM | BPF_B:
+	case BPF_ST | BPF_MEM | BPF_H:
+	case BPF_ST | BPF_MEM | BPF_W:
+	case BPF_ST | BPF_MEM | BPF_DW:
+
+	case BPF_STX | BPF_MEM | BPF_B:
+	case BPF_STX | BPF_MEM | BPF_H:
+	case BPF_STX | BPF_MEM | BPF_W:
+	case BPF_STX | BPF_MEM | BPF_DW:
+		if (BPF_CLASS(code) == BPF_ST) {
+			emit_imm32(tmp2, imm, ctx);
+			src = tmp2;
+		}
+
+		if (emit_store_r64(dst, src, off, ctx, BPF_SIZE(code),
+				   BPF_MODE(code)))
+			return -1;
+		break;
+
+	case BPF_STX | BPF_ATOMIC | BPF_W:
+		if (insn->imm != BPF_ADD) {
+			pr_info_once(
+				"bpf-jit: not supported: atomic operation %02x ***\n",
+				insn->imm);
+			return -EFAULT;
+		}
+
+		if (emit_store_r64(dst, src, off, ctx, BPF_SIZE(code),
+				   BPF_MODE(code)))
+			return -1;
+		break;
+
+	/* No hardware support for 8-byte atomics in RV32. */
+	case BPF_STX | BPF_ATOMIC | BPF_DW:
+		/* Fallthrough. */
+
+notsupported:
+		pr_info_once("bpf-jit: not supported: opcode %02x ***\n", code);
+		return -EFAULT;
+
+	default:
+		pr_err("bpf-jit: unknown opcode %02x\n", code);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+void bpf_jit_build_prologue(struct rv_jit_context *ctx)
+{
+	const s8 *fp = bpf2rv32[BPF_REG_FP];
+	const s8 *r1 = bpf2rv32[BPF_REG_1];
+	int stack_adjust = 0;
+	int bpf_stack_adjust =
+		round_up(ctx->prog->aux->stack_depth, STACK_ALIGN);
+
+	/* Make space for callee-saved registers. */
+	stack_adjust += NR_SAVED_REGISTERS * sizeof(u32);
+	/* Make space for BPF registers on stack. */
+	stack_adjust += BPF_JIT_SCRATCH_REGS * sizeof(u32);
+	/* Make space for BPF stack. */
+	stack_adjust += bpf_stack_adjust;
+	/* Round up for stack alignment. */
+	stack_adjust = round_up(stack_adjust, STACK_ALIGN);
+
+	/*
+	 * The first instruction sets the tail-call-counter (TCC) register.
+	 * This instruction is skipped by tail calls.
+	 */
+	emit(rv_addi(RV_REG_TCC, RV_REG_ZERO, MAX_TAIL_CALL_CNT), ctx);
+
+	emit(rv_addi(RV_REG_SP, RV_REG_SP, -stack_adjust), ctx);
+
+	/* Save callee-save registers. */
+	emit(rv_sw(RV_REG_SP, stack_adjust - 4, RV_REG_RA), ctx);
+	emit(rv_sw(RV_REG_SP, stack_adjust - 8, RV_REG_FP), ctx);
+	emit(rv_sw(RV_REG_SP, stack_adjust - 12, RV_REG_S1), ctx);
+	emit(rv_sw(RV_REG_SP, stack_adjust - 16, RV_REG_S2), ctx);
+	emit(rv_sw(RV_REG_SP, stack_adjust - 20, RV_REG_S3), ctx);
+	emit(rv_sw(RV_REG_SP, stack_adjust - 24, RV_REG_S4), ctx);
+	emit(rv_sw(RV_REG_SP, stack_adjust - 28, RV_REG_S5), ctx);
+	emit(rv_sw(RV_REG_SP, stack_adjust - 32, RV_REG_S6), ctx);
+	emit(rv_sw(RV_REG_SP, stack_adjust - 36, RV_REG_S7), ctx);
+
+	/* Set fp: used as the base address for stacked BPF registers. */
+	emit(rv_addi(RV_REG_FP, RV_REG_SP, stack_adjust), ctx);
+
+	/* Set up BPF frame pointer. */
+	emit(rv_addi(lo(fp), RV_REG_SP, bpf_stack_adjust), ctx);
+	emit(rv_addi(hi(fp), RV_REG_ZERO, 0), ctx);
+
+	/* Set up BPF context pointer. */
+	emit(rv_addi(lo(r1), RV_REG_A0, 0), ctx);
+	emit(rv_addi(hi(r1), RV_REG_ZERO, 0), ctx);
+
+	ctx->stack_size = stack_adjust;
+}
+
+void bpf_jit_build_epilogue(struct rv_jit_context *ctx)
+{
+	__build_epilogue(false, ctx);
+}
diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
new file mode 100644
index 000000000..8f5d3c57d
--- /dev/null
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -0,0 +1,1353 @@
+// SPDX-License-Identifier: GPL-2.0
+/* BPF JIT compiler for RV64G
+ *
+ * Copyright(c) 2019 Björn Töpel <bjorn.topel@gmail.com>
+ *
+ */
+
+#include <linux/bitfield.h>
+#include <linux/bpf.h>
+#include <linux/filter.h>
+#include "bpf_jit.h"
+
+#define RV_REG_TCC RV_REG_A6
+#define RV_REG_TCC_SAVED RV_REG_S6 /* Store A6 in S6 if program do calls */
+
+static const int regmap[] = {
+	[BPF_REG_0] =	RV_REG_A5,
+	[BPF_REG_1] =	RV_REG_A0,
+	[BPF_REG_2] =	RV_REG_A1,
+	[BPF_REG_3] =	RV_REG_A2,
+	[BPF_REG_4] =	RV_REG_A3,
+	[BPF_REG_5] =	RV_REG_A4,
+	[BPF_REG_6] =	RV_REG_S1,
+	[BPF_REG_7] =	RV_REG_S2,
+	[BPF_REG_8] =	RV_REG_S3,
+	[BPF_REG_9] =	RV_REG_S4,
+	[BPF_REG_FP] =	RV_REG_S5,
+	[BPF_REG_AX] =	RV_REG_T0,
+};
+
+static const int pt_regmap[] = {
+	[RV_REG_A0] = offsetof(struct pt_regs, a0),
+	[RV_REG_A1] = offsetof(struct pt_regs, a1),
+	[RV_REG_A2] = offsetof(struct pt_regs, a2),
+	[RV_REG_A3] = offsetof(struct pt_regs, a3),
+	[RV_REG_A4] = offsetof(struct pt_regs, a4),
+	[RV_REG_A5] = offsetof(struct pt_regs, a5),
+	[RV_REG_S1] = offsetof(struct pt_regs, s1),
+	[RV_REG_S2] = offsetof(struct pt_regs, s2),
+	[RV_REG_S3] = offsetof(struct pt_regs, s3),
+	[RV_REG_S4] = offsetof(struct pt_regs, s4),
+	[RV_REG_S5] = offsetof(struct pt_regs, s5),
+	[RV_REG_T0] = offsetof(struct pt_regs, t0),
+};
+
+enum {
+	RV_CTX_F_SEEN_TAIL_CALL =	0,
+	RV_CTX_F_SEEN_CALL =		RV_REG_RA,
+	RV_CTX_F_SEEN_S1 =		RV_REG_S1,
+	RV_CTX_F_SEEN_S2 =		RV_REG_S2,
+	RV_CTX_F_SEEN_S3 =		RV_REG_S3,
+	RV_CTX_F_SEEN_S4 =		RV_REG_S4,
+	RV_CTX_F_SEEN_S5 =		RV_REG_S5,
+	RV_CTX_F_SEEN_S6 =		RV_REG_S6,
+};
+
+static u8 bpf_to_rv_reg(int bpf_reg, struct rv_jit_context *ctx)
+{
+	u8 reg = regmap[bpf_reg];
+
+	switch (reg) {
+	case RV_CTX_F_SEEN_S1:
+	case RV_CTX_F_SEEN_S2:
+	case RV_CTX_F_SEEN_S3:
+	case RV_CTX_F_SEEN_S4:
+	case RV_CTX_F_SEEN_S5:
+	case RV_CTX_F_SEEN_S6:
+		__set_bit(reg, &ctx->flags);
+	}
+	return reg;
+};
+
+static bool seen_reg(int reg, struct rv_jit_context *ctx)
+{
+	switch (reg) {
+	case RV_CTX_F_SEEN_CALL:
+	case RV_CTX_F_SEEN_S1:
+	case RV_CTX_F_SEEN_S2:
+	case RV_CTX_F_SEEN_S3:
+	case RV_CTX_F_SEEN_S4:
+	case RV_CTX_F_SEEN_S5:
+	case RV_CTX_F_SEEN_S6:
+		return test_bit(reg, &ctx->flags);
+	}
+	return false;
+}
+
+static void mark_fp(struct rv_jit_context *ctx)
+{
+	__set_bit(RV_CTX_F_SEEN_S5, &ctx->flags);
+}
+
+static void mark_call(struct rv_jit_context *ctx)
+{
+	__set_bit(RV_CTX_F_SEEN_CALL, &ctx->flags);
+}
+
+static bool seen_call(struct rv_jit_context *ctx)
+{
+	return test_bit(RV_CTX_F_SEEN_CALL, &ctx->flags);
+}
+
+static void mark_tail_call(struct rv_jit_context *ctx)
+{
+	__set_bit(RV_CTX_F_SEEN_TAIL_CALL, &ctx->flags);
+}
+
+static bool seen_tail_call(struct rv_jit_context *ctx)
+{
+	return test_bit(RV_CTX_F_SEEN_TAIL_CALL, &ctx->flags);
+}
+
+static u8 rv_tail_call_reg(struct rv_jit_context *ctx)
+{
+	mark_tail_call(ctx);
+
+	if (seen_call(ctx)) {
+		__set_bit(RV_CTX_F_SEEN_S6, &ctx->flags);
+		return RV_REG_S6;
+	}
+	return RV_REG_A6;
+}
+
+static bool is_32b_int(s64 val)
+{
+	return -(1L << 31) <= val && val < (1L << 31);
+}
+
+static bool in_auipc_jalr_range(s64 val)
+{
+	/*
+	 * auipc+jalr can reach any signed PC-relative offset in the range
+	 * [-2^31 - 2^11, 2^31 - 2^11).
+	 */
+	return (-(1L << 31) - (1L << 11)) <= val &&
+		val < ((1L << 31) - (1L << 11));
+}
+
+/* Emit fixed-length instructions for address */
+static int emit_addr(u8 rd, u64 addr, bool extra_pass, struct rv_jit_context *ctx)
+{
+	u64 ip = (u64)(ctx->insns + ctx->ninsns);
+	s64 off = addr - ip;
+	s64 upper = (off + (1 << 11)) >> 12;
+	s64 lower = off & 0xfff;
+
+	if (extra_pass && !in_auipc_jalr_range(off)) {
+		pr_err("bpf-jit: target offset 0x%llx is out of range\n", off);
+		return -ERANGE;
+	}
+
+	emit(rv_auipc(rd, upper), ctx);
+	emit(rv_addi(rd, rd, lower), ctx);
+	return 0;
+}
+
+/* Emit variable-length instructions for 32-bit and 64-bit imm */
+static void emit_imm(u8 rd, s64 val, struct rv_jit_context *ctx)
+{
+	/* Note that the immediate from the add is sign-extended,
+	 * which means that we need to compensate this by adding 2^12,
+	 * when the 12th bit is set. A simpler way of doing this, and
+	 * getting rid of the check, is to just add 2**11 before the
+	 * shift. The "Loading a 32-Bit constant" example from the
+	 * "Computer Organization and Design, RISC-V edition" book by
+	 * Patterson/Hennessy highlights this fact.
+	 *
+	 * This also means that we need to process LSB to MSB.
+	 */
+	s64 upper = (val + (1 << 11)) >> 12;
+	/* Sign-extend lower 12 bits to 64 bits since immediates for li, addiw,
+	 * and addi are signed and RVC checks will perform signed comparisons.
+	 */
+	s64 lower = ((val & 0xfff) << 52) >> 52;
+	int shift;
+
+	if (is_32b_int(val)) {
+		if (upper)
+			emit_lui(rd, upper, ctx);
+
+		if (!upper) {
+			emit_li(rd, lower, ctx);
+			return;
+		}
+
+		emit_addiw(rd, rd, lower, ctx);
+		return;
+	}
+
+	shift = __ffs(upper);
+	upper >>= shift;
+	shift += 12;
+
+	emit_imm(rd, upper, ctx);
+
+	emit_slli(rd, rd, shift, ctx);
+	if (lower)
+		emit_addi(rd, rd, lower, ctx);
+}
+
+static void __build_epilogue(bool is_tail_call, struct rv_jit_context *ctx)
+{
+	int stack_adjust = ctx->stack_size, store_offset = stack_adjust - 8;
+
+	if (seen_reg(RV_REG_RA, ctx)) {
+		emit_ld(RV_REG_RA, store_offset, RV_REG_SP, ctx);
+		store_offset -= 8;
+	}
+	emit_ld(RV_REG_FP, store_offset, RV_REG_SP, ctx);
+	store_offset -= 8;
+	if (seen_reg(RV_REG_S1, ctx)) {
+		emit_ld(RV_REG_S1, store_offset, RV_REG_SP, ctx);
+		store_offset -= 8;
+	}
+	if (seen_reg(RV_REG_S2, ctx)) {
+		emit_ld(RV_REG_S2, store_offset, RV_REG_SP, ctx);
+		store_offset -= 8;
+	}
+	if (seen_reg(RV_REG_S3, ctx)) {
+		emit_ld(RV_REG_S3, store_offset, RV_REG_SP, ctx);
+		store_offset -= 8;
+	}
+	if (seen_reg(RV_REG_S4, ctx)) {
+		emit_ld(RV_REG_S4, store_offset, RV_REG_SP, ctx);
+		store_offset -= 8;
+	}
+	if (seen_reg(RV_REG_S5, ctx)) {
+		emit_ld(RV_REG_S5, store_offset, RV_REG_SP, ctx);
+		store_offset -= 8;
+	}
+	if (seen_reg(RV_REG_S6, ctx)) {
+		emit_ld(RV_REG_S6, store_offset, RV_REG_SP, ctx);
+		store_offset -= 8;
+	}
+
+	emit_addi(RV_REG_SP, RV_REG_SP, stack_adjust, ctx);
+	/* Set return value. */
+	if (!is_tail_call)
+		emit_addiw(RV_REG_A0, RV_REG_A5, 0, ctx);
+	emit_jalr(RV_REG_ZERO, is_tail_call ? RV_REG_T3 : RV_REG_RA,
+		  is_tail_call ? 4 : 0, /* skip TCC init */
+		  ctx);
+}
+
+static void emit_bcc(u8 cond, u8 rd, u8 rs, int rvoff,
+		     struct rv_jit_context *ctx)
+{
+	switch (cond) {
+	case BPF_JEQ:
+		emit(rv_beq(rd, rs, rvoff >> 1), ctx);
+		return;
+	case BPF_JGT:
+		emit(rv_bltu(rs, rd, rvoff >> 1), ctx);
+		return;
+	case BPF_JLT:
+		emit(rv_bltu(rd, rs, rvoff >> 1), ctx);
+		return;
+	case BPF_JGE:
+		emit(rv_bgeu(rd, rs, rvoff >> 1), ctx);
+		return;
+	case BPF_JLE:
+		emit(rv_bgeu(rs, rd, rvoff >> 1), ctx);
+		return;
+	case BPF_JNE:
+		emit(rv_bne(rd, rs, rvoff >> 1), ctx);
+		return;
+	case BPF_JSGT:
+		emit(rv_blt(rs, rd, rvoff >> 1), ctx);
+		return;
+	case BPF_JSLT:
+		emit(rv_blt(rd, rs, rvoff >> 1), ctx);
+		return;
+	case BPF_JSGE:
+		emit(rv_bge(rd, rs, rvoff >> 1), ctx);
+		return;
+	case BPF_JSLE:
+		emit(rv_bge(rs, rd, rvoff >> 1), ctx);
+	}
+}
+
+static void emit_branch(u8 cond, u8 rd, u8 rs, int rvoff,
+			struct rv_jit_context *ctx)
+{
+	s64 upper, lower;
+
+	if (is_13b_int(rvoff)) {
+		emit_bcc(cond, rd, rs, rvoff, ctx);
+		return;
+	}
+
+	/* Adjust for jal */
+	rvoff -= 4;
+
+	/* Transform, e.g.:
+	 *   bne rd,rs,foo
+	 * to
+	 *   beq rd,rs,<.L1>
+	 *   (auipc foo)
+	 *   jal(r) foo
+	 * .L1
+	 */
+	cond = invert_bpf_cond(cond);
+	if (is_21b_int(rvoff)) {
+		emit_bcc(cond, rd, rs, 8, ctx);
+		emit(rv_jal(RV_REG_ZERO, rvoff >> 1), ctx);
+		return;
+	}
+
+	/* 32b No need for an additional rvoff adjustment, since we
+	 * get that from the auipc at PC', where PC = PC' + 4.
+	 */
+	upper = (rvoff + (1 << 11)) >> 12;
+	lower = rvoff & 0xfff;
+
+	emit_bcc(cond, rd, rs, 12, ctx);
+	emit(rv_auipc(RV_REG_T1, upper), ctx);
+	emit(rv_jalr(RV_REG_ZERO, RV_REG_T1, lower), ctx);
+}
+
+static void emit_zext_32(u8 reg, struct rv_jit_context *ctx)
+{
+	emit_slli(reg, reg, 32, ctx);
+	emit_srli(reg, reg, 32, ctx);
+}
+
+static int emit_bpf_tail_call(int insn, struct rv_jit_context *ctx)
+{
+	int tc_ninsn, off, start_insn = ctx->ninsns;
+	u8 tcc = rv_tail_call_reg(ctx);
+
+	/* a0: &ctx
+	 * a1: &array
+	 * a2: index
+	 *
+	 * if (index >= array->map.max_entries)
+	 *	goto out;
+	 */
+	tc_ninsn = insn ? ctx->offset[insn] - ctx->offset[insn - 1] :
+		   ctx->offset[0];
+	emit_zext_32(RV_REG_A2, ctx);
+
+	off = offsetof(struct bpf_array, map.max_entries);
+	if (is_12b_check(off, insn))
+		return -1;
+	emit(rv_lwu(RV_REG_T1, off, RV_REG_A1), ctx);
+	off = ninsns_rvoff(tc_ninsn - (ctx->ninsns - start_insn));
+	emit_branch(BPF_JGE, RV_REG_A2, RV_REG_T1, off, ctx);
+
+	/* if (--TCC < 0)
+	 *     goto out;
+	 */
+	emit_addi(RV_REG_TCC, tcc, -1, ctx);
+	off = ninsns_rvoff(tc_ninsn - (ctx->ninsns - start_insn));
+	emit_branch(BPF_JSLT, RV_REG_TCC, RV_REG_ZERO, off, ctx);
+
+	/* prog = array->ptrs[index];
+	 * if (!prog)
+	 *     goto out;
+	 */
+	emit_slli(RV_REG_T2, RV_REG_A2, 3, ctx);
+	emit_add(RV_REG_T2, RV_REG_T2, RV_REG_A1, ctx);
+	off = offsetof(struct bpf_array, ptrs);
+	if (is_12b_check(off, insn))
+		return -1;
+	emit_ld(RV_REG_T2, off, RV_REG_T2, ctx);
+	off = ninsns_rvoff(tc_ninsn - (ctx->ninsns - start_insn));
+	emit_branch(BPF_JEQ, RV_REG_T2, RV_REG_ZERO, off, ctx);
+
+	/* goto *(prog->bpf_func + 4); */
+	off = offsetof(struct bpf_prog, bpf_func);
+	if (is_12b_check(off, insn))
+		return -1;
+	emit_ld(RV_REG_T3, off, RV_REG_T2, ctx);
+	__build_epilogue(true, ctx);
+	return 0;
+}
+
+static void init_regs(u8 *rd, u8 *rs, const struct bpf_insn *insn,
+		      struct rv_jit_context *ctx)
+{
+	u8 code = insn->code;
+
+	switch (code) {
+	case BPF_JMP | BPF_JA:
+	case BPF_JMP | BPF_CALL:
+	case BPF_JMP | BPF_EXIT:
+	case BPF_JMP | BPF_TAIL_CALL:
+		break;
+	default:
+		*rd = bpf_to_rv_reg(insn->dst_reg, ctx);
+	}
+
+	if (code & (BPF_ALU | BPF_X) || code & (BPF_ALU64 | BPF_X) ||
+	    code & (BPF_JMP | BPF_X) || code & (BPF_JMP32 | BPF_X) ||
+	    code & BPF_LDX || code & BPF_STX)
+		*rs = bpf_to_rv_reg(insn->src_reg, ctx);
+}
+
+static void emit_zext_32_rd_rs(u8 *rd, u8 *rs, struct rv_jit_context *ctx)
+{
+	emit_mv(RV_REG_T2, *rd, ctx);
+	emit_zext_32(RV_REG_T2, ctx);
+	emit_mv(RV_REG_T1, *rs, ctx);
+	emit_zext_32(RV_REG_T1, ctx);
+	*rd = RV_REG_T2;
+	*rs = RV_REG_T1;
+}
+
+static void emit_sext_32_rd_rs(u8 *rd, u8 *rs, struct rv_jit_context *ctx)
+{
+	emit_addiw(RV_REG_T2, *rd, 0, ctx);
+	emit_addiw(RV_REG_T1, *rs, 0, ctx);
+	*rd = RV_REG_T2;
+	*rs = RV_REG_T1;
+}
+
+static void emit_zext_32_rd_t1(u8 *rd, struct rv_jit_context *ctx)
+{
+	emit_mv(RV_REG_T2, *rd, ctx);
+	emit_zext_32(RV_REG_T2, ctx);
+	emit_zext_32(RV_REG_T1, ctx);
+	*rd = RV_REG_T2;
+}
+
+static void emit_sext_32_rd(u8 *rd, struct rv_jit_context *ctx)
+{
+	emit_addiw(RV_REG_T2, *rd, 0, ctx);
+	*rd = RV_REG_T2;
+}
+
+static int emit_jump_and_link(u8 rd, s64 rvoff, bool fixed_addr,
+			      struct rv_jit_context *ctx)
+{
+	s64 upper, lower;
+
+	if (rvoff && fixed_addr && is_21b_int(rvoff)) {
+		emit(rv_jal(rd, rvoff >> 1), ctx);
+		return 0;
+	} else if (in_auipc_jalr_range(rvoff)) {
+		upper = (rvoff + (1 << 11)) >> 12;
+		lower = rvoff & 0xfff;
+		emit(rv_auipc(RV_REG_T1, upper), ctx);
+		emit(rv_jalr(rd, RV_REG_T1, lower), ctx);
+		return 0;
+	}
+
+	pr_err("bpf-jit: target offset 0x%llx is out of range\n", rvoff);
+	return -ERANGE;
+}
+
+static bool is_signed_bpf_cond(u8 cond)
+{
+	return cond == BPF_JSGT || cond == BPF_JSLT ||
+		cond == BPF_JSGE || cond == BPF_JSLE;
+}
+
+static int emit_call(u64 addr, bool fixed_addr, struct rv_jit_context *ctx)
+{
+	s64 off = 0;
+	u64 ip;
+
+	if (addr && ctx->insns) {
+		ip = (u64)(long)(ctx->insns + ctx->ninsns);
+		off = addr - ip;
+	}
+
+	return emit_jump_and_link(RV_REG_RA, off, fixed_addr, ctx);
+}
+
+static void emit_atomic(u8 rd, u8 rs, s16 off, s32 imm, bool is64,
+			struct rv_jit_context *ctx)
+{
+	u8 r0;
+	int jmp_offset;
+
+	if (off) {
+		if (is_12b_int(off)) {
+			emit_addi(RV_REG_T1, rd, off, ctx);
+		} else {
+			emit_imm(RV_REG_T1, off, ctx);
+			emit_add(RV_REG_T1, RV_REG_T1, rd, ctx);
+		}
+		rd = RV_REG_T1;
+	}
+
+	switch (imm) {
+	/* lock *(u32/u64 *)(dst_reg + off16) <op>= src_reg */
+	case BPF_ADD:
+		emit(is64 ? rv_amoadd_d(RV_REG_ZERO, rs, rd, 0, 0) :
+		     rv_amoadd_w(RV_REG_ZERO, rs, rd, 0, 0), ctx);
+		break;
+	case BPF_AND:
+		emit(is64 ? rv_amoand_d(RV_REG_ZERO, rs, rd, 0, 0) :
+		     rv_amoand_w(RV_REG_ZERO, rs, rd, 0, 0), ctx);
+		break;
+	case BPF_OR:
+		emit(is64 ? rv_amoor_d(RV_REG_ZERO, rs, rd, 0, 0) :
+		     rv_amoor_w(RV_REG_ZERO, rs, rd, 0, 0), ctx);
+		break;
+	case BPF_XOR:
+		emit(is64 ? rv_amoxor_d(RV_REG_ZERO, rs, rd, 0, 0) :
+		     rv_amoxor_w(RV_REG_ZERO, rs, rd, 0, 0), ctx);
+		break;
+	/* src_reg = atomic_fetch_<op>(dst_reg + off16, src_reg) */
+	case BPF_ADD | BPF_FETCH:
+		emit(is64 ? rv_amoadd_d(rs, rs, rd, 0, 0) :
+		     rv_amoadd_w(rs, rs, rd, 0, 0), ctx);
+		if (!is64)
+			emit_zext_32(rs, ctx);
+		break;
+	case BPF_AND | BPF_FETCH:
+		emit(is64 ? rv_amoand_d(rs, rs, rd, 0, 0) :
+		     rv_amoand_w(rs, rs, rd, 0, 0), ctx);
+		if (!is64)
+			emit_zext_32(rs, ctx);
+		break;
+	case BPF_OR | BPF_FETCH:
+		emit(is64 ? rv_amoor_d(rs, rs, rd, 0, 0) :
+		     rv_amoor_w(rs, rs, rd, 0, 0), ctx);
+		if (!is64)
+			emit_zext_32(rs, ctx);
+		break;
+	case BPF_XOR | BPF_FETCH:
+		emit(is64 ? rv_amoxor_d(rs, rs, rd, 0, 0) :
+		     rv_amoxor_w(rs, rs, rd, 0, 0), ctx);
+		if (!is64)
+			emit_zext_32(rs, ctx);
+		break;
+	/* src_reg = atomic_xchg(dst_reg + off16, src_reg); */
+	case BPF_XCHG:
+		emit(is64 ? rv_amoswap_d(rs, rs, rd, 0, 0) :
+		     rv_amoswap_w(rs, rs, rd, 0, 0), ctx);
+		if (!is64)
+			emit_zext_32(rs, ctx);
+		break;
+	/* r0 = atomic_cmpxchg(dst_reg + off16, r0, src_reg); */
+	case BPF_CMPXCHG:
+		r0 = bpf_to_rv_reg(BPF_REG_0, ctx);
+		emit(is64 ? rv_addi(RV_REG_T2, r0, 0) :
+		     rv_addiw(RV_REG_T2, r0, 0), ctx);
+		emit(is64 ? rv_lr_d(r0, 0, rd, 0, 0) :
+		     rv_lr_w(r0, 0, rd, 0, 0), ctx);
+		jmp_offset = ninsns_rvoff(8);
+		emit(rv_bne(RV_REG_T2, r0, jmp_offset >> 1), ctx);
+		emit(is64 ? rv_sc_d(RV_REG_T3, rs, rd, 0, 0) :
+		     rv_sc_w(RV_REG_T3, rs, rd, 0, 0), ctx);
+		jmp_offset = ninsns_rvoff(-6);
+		emit(rv_bne(RV_REG_T3, 0, jmp_offset >> 1), ctx);
+		emit(rv_fence(0x3, 0x3), ctx);
+		break;
+	}
+}
+
+#define BPF_FIXUP_OFFSET_MASK   GENMASK(26, 0)
+#define BPF_FIXUP_REG_MASK      GENMASK(31, 27)
+
+bool ex_handler_bpf(const struct exception_table_entry *ex,
+		    struct pt_regs *regs)
+{
+	off_t offset = FIELD_GET(BPF_FIXUP_OFFSET_MASK, ex->fixup);
+	int regs_offset = FIELD_GET(BPF_FIXUP_REG_MASK, ex->fixup);
+
+	*(unsigned long *)((void *)regs + pt_regmap[regs_offset]) = 0;
+	regs->epc = (unsigned long)&ex->fixup - offset;
+
+	return true;
+}
+
+/* For accesses to BTF pointers, add an entry to the exception table */
+static int add_exception_handler(const struct bpf_insn *insn,
+				 struct rv_jit_context *ctx,
+				 int dst_reg, int insn_len)
+{
+	struct exception_table_entry *ex;
+	unsigned long pc;
+	off_t offset;
+
+	if (!ctx->insns || !ctx->prog->aux->extable || BPF_MODE(insn->code) != BPF_PROBE_MEM)
+		return 0;
+
+	if (WARN_ON_ONCE(ctx->nexentries >= ctx->prog->aux->num_exentries))
+		return -EINVAL;
+
+	if (WARN_ON_ONCE(insn_len > ctx->ninsns))
+		return -EINVAL;
+
+	if (WARN_ON_ONCE(!rvc_enabled() && insn_len == 1))
+		return -EINVAL;
+
+	ex = &ctx->prog->aux->extable[ctx->nexentries];
+	pc = (unsigned long)&ctx->insns[ctx->ninsns - insn_len];
+
+	offset = pc - (long)&ex->insn;
+	if (WARN_ON_ONCE(offset >= 0 || offset < INT_MIN))
+		return -ERANGE;
+	ex->insn = offset;
+
+	/*
+	 * Since the extable follows the program, the fixup offset is always
+	 * negative and limited to BPF_JIT_REGION_SIZE. Store a positive value
+	 * to keep things simple, and put the destination register in the upper
+	 * bits. We don't need to worry about buildtime or runtime sort
+	 * modifying the upper bits because the table is already sorted, and
+	 * isn't part of the main exception table.
+	 */
+	offset = (long)&ex->fixup - (pc + insn_len * sizeof(u16));
+	if (!FIELD_FIT(BPF_FIXUP_OFFSET_MASK, offset))
+		return -ERANGE;
+
+	ex->fixup = FIELD_PREP(BPF_FIXUP_OFFSET_MASK, offset) |
+		FIELD_PREP(BPF_FIXUP_REG_MASK, dst_reg);
+	ex->type = EX_TYPE_BPF;
+
+	ctx->nexentries++;
+	return 0;
+}
+
+int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
+		      bool extra_pass)
+{
+	bool is64 = BPF_CLASS(insn->code) == BPF_ALU64 ||
+		    BPF_CLASS(insn->code) == BPF_JMP;
+	int s, e, rvoff, ret, i = insn - ctx->prog->insnsi;
+	struct bpf_prog_aux *aux = ctx->prog->aux;
+	u8 rd = -1, rs = -1, code = insn->code;
+	s16 off = insn->off;
+	s32 imm = insn->imm;
+
+	init_regs(&rd, &rs, insn, ctx);
+
+	switch (code) {
+	/* dst = src */
+	case BPF_ALU | BPF_MOV | BPF_X:
+	case BPF_ALU64 | BPF_MOV | BPF_X:
+		if (imm == 1) {
+			/* Special mov32 for zext */
+			emit_zext_32(rd, ctx);
+			break;
+		}
+		emit_mv(rd, rs, ctx);
+		if (!is64 && !aux->verifier_zext)
+			emit_zext_32(rd, ctx);
+		break;
+
+	/* dst = dst OP src */
+	case BPF_ALU | BPF_ADD | BPF_X:
+	case BPF_ALU64 | BPF_ADD | BPF_X:
+		emit_add(rd, rd, rs, ctx);
+		if (!is64 && !aux->verifier_zext)
+			emit_zext_32(rd, ctx);
+		break;
+	case BPF_ALU | BPF_SUB | BPF_X:
+	case BPF_ALU64 | BPF_SUB | BPF_X:
+		if (is64)
+			emit_sub(rd, rd, rs, ctx);
+		else
+			emit_subw(rd, rd, rs, ctx);
+
+		if (!is64 && !aux->verifier_zext)
+			emit_zext_32(rd, ctx);
+		break;
+	case BPF_ALU | BPF_AND | BPF_X:
+	case BPF_ALU64 | BPF_AND | BPF_X:
+		emit_and(rd, rd, rs, ctx);
+		if (!is64 && !aux->verifier_zext)
+			emit_zext_32(rd, ctx);
+		break;
+	case BPF_ALU | BPF_OR | BPF_X:
+	case BPF_ALU64 | BPF_OR | BPF_X:
+		emit_or(rd, rd, rs, ctx);
+		if (!is64 && !aux->verifier_zext)
+			emit_zext_32(rd, ctx);
+		break;
+	case BPF_ALU | BPF_XOR | BPF_X:
+	case BPF_ALU64 | BPF_XOR | BPF_X:
+		emit_xor(rd, rd, rs, ctx);
+		if (!is64 && !aux->verifier_zext)
+			emit_zext_32(rd, ctx);
+		break;
+	case BPF_ALU | BPF_MUL | BPF_X:
+	case BPF_ALU64 | BPF_MUL | BPF_X:
+		emit(is64 ? rv_mul(rd, rd, rs) : rv_mulw(rd, rd, rs), ctx);
+		if (!is64 && !aux->verifier_zext)
+			emit_zext_32(rd, ctx);
+		break;
+	case BPF_ALU | BPF_DIV | BPF_X:
+	case BPF_ALU64 | BPF_DIV | BPF_X:
+		emit(is64 ? rv_divu(rd, rd, rs) : rv_divuw(rd, rd, rs), ctx);
+		if (!is64 && !aux->verifier_zext)
+			emit_zext_32(rd, ctx);
+		break;
+	case BPF_ALU | BPF_MOD | BPF_X:
+	case BPF_ALU64 | BPF_MOD | BPF_X:
+		emit(is64 ? rv_remu(rd, rd, rs) : rv_remuw(rd, rd, rs), ctx);
+		if (!is64 && !aux->verifier_zext)
+			emit_zext_32(rd, ctx);
+		break;
+	case BPF_ALU | BPF_LSH | BPF_X:
+	case BPF_ALU64 | BPF_LSH | BPF_X:
+		emit(is64 ? rv_sll(rd, rd, rs) : rv_sllw(rd, rd, rs), ctx);
+		if (!is64 && !aux->verifier_zext)
+			emit_zext_32(rd, ctx);
+		break;
+	case BPF_ALU | BPF_RSH | BPF_X:
+	case BPF_ALU64 | BPF_RSH | BPF_X:
+		emit(is64 ? rv_srl(rd, rd, rs) : rv_srlw(rd, rd, rs), ctx);
+		if (!is64 && !aux->verifier_zext)
+			emit_zext_32(rd, ctx);
+		break;
+	case BPF_ALU | BPF_ARSH | BPF_X:
+	case BPF_ALU64 | BPF_ARSH | BPF_X:
+		emit(is64 ? rv_sra(rd, rd, rs) : rv_sraw(rd, rd, rs), ctx);
+		if (!is64 && !aux->verifier_zext)
+			emit_zext_32(rd, ctx);
+		break;
+
+	/* dst = -dst */
+	case BPF_ALU | BPF_NEG:
+	case BPF_ALU64 | BPF_NEG:
+		emit_sub(rd, RV_REG_ZERO, rd, ctx);
+		if (!is64 && !aux->verifier_zext)
+			emit_zext_32(rd, ctx);
+		break;
+
+	/* dst = BSWAP##imm(dst) */
+	case BPF_ALU | BPF_END | BPF_FROM_LE:
+		switch (imm) {
+		case 16:
+			emit_slli(rd, rd, 48, ctx);
+			emit_srli(rd, rd, 48, ctx);
+			break;
+		case 32:
+			if (!aux->verifier_zext)
+				emit_zext_32(rd, ctx);
+			break;
+		case 64:
+			/* Do nothing */
+			break;
+		}
+		break;
+
+	case BPF_ALU | BPF_END | BPF_FROM_BE:
+		emit_li(RV_REG_T2, 0, ctx);
+
+		emit_andi(RV_REG_T1, rd, 0xff, ctx);
+		emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx);
+		emit_slli(RV_REG_T2, RV_REG_T2, 8, ctx);
+		emit_srli(rd, rd, 8, ctx);
+		if (imm == 16)
+			goto out_be;
+
+		emit_andi(RV_REG_T1, rd, 0xff, ctx);
+		emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx);
+		emit_slli(RV_REG_T2, RV_REG_T2, 8, ctx);
+		emit_srli(rd, rd, 8, ctx);
+
+		emit_andi(RV_REG_T1, rd, 0xff, ctx);
+		emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx);
+		emit_slli(RV_REG_T2, RV_REG_T2, 8, ctx);
+		emit_srli(rd, rd, 8, ctx);
+		if (imm == 32)
+			goto out_be;
+
+		emit_andi(RV_REG_T1, rd, 0xff, ctx);
+		emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx);
+		emit_slli(RV_REG_T2, RV_REG_T2, 8, ctx);
+		emit_srli(rd, rd, 8, ctx);
+
+		emit_andi(RV_REG_T1, rd, 0xff, ctx);
+		emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx);
+		emit_slli(RV_REG_T2, RV_REG_T2, 8, ctx);
+		emit_srli(rd, rd, 8, ctx);
+
+		emit_andi(RV_REG_T1, rd, 0xff, ctx);
+		emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx);
+		emit_slli(RV_REG_T2, RV_REG_T2, 8, ctx);
+		emit_srli(rd, rd, 8, ctx);
+
+		emit_andi(RV_REG_T1, rd, 0xff, ctx);
+		emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx);
+		emit_slli(RV_REG_T2, RV_REG_T2, 8, ctx);
+		emit_srli(rd, rd, 8, ctx);
+out_be:
+		emit_andi(RV_REG_T1, rd, 0xff, ctx);
+		emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx);
+
+		emit_mv(rd, RV_REG_T2, ctx);
+		break;
+
+	/* dst = imm */
+	case BPF_ALU | BPF_MOV | BPF_K:
+	case BPF_ALU64 | BPF_MOV | BPF_K:
+		emit_imm(rd, imm, ctx);
+		if (!is64 && !aux->verifier_zext)
+			emit_zext_32(rd, ctx);
+		break;
+
+	/* dst = dst OP imm */
+	case BPF_ALU | BPF_ADD | BPF_K:
+	case BPF_ALU64 | BPF_ADD | BPF_K:
+		if (is_12b_int(imm)) {
+			emit_addi(rd, rd, imm, ctx);
+		} else {
+			emit_imm(RV_REG_T1, imm, ctx);
+			emit_add(rd, rd, RV_REG_T1, ctx);
+		}
+		if (!is64 && !aux->verifier_zext)
+			emit_zext_32(rd, ctx);
+		break;
+	case BPF_ALU | BPF_SUB | BPF_K:
+	case BPF_ALU64 | BPF_SUB | BPF_K:
+		if (is_12b_int(-imm)) {
+			emit_addi(rd, rd, -imm, ctx);
+		} else {
+			emit_imm(RV_REG_T1, imm, ctx);
+			emit_sub(rd, rd, RV_REG_T1, ctx);
+		}
+		if (!is64 && !aux->verifier_zext)
+			emit_zext_32(rd, ctx);
+		break;
+	case BPF_ALU | BPF_AND | BPF_K:
+	case BPF_ALU64 | BPF_AND | BPF_K:
+		if (is_12b_int(imm)) {
+			emit_andi(rd, rd, imm, ctx);
+		} else {
+			emit_imm(RV_REG_T1, imm, ctx);
+			emit_and(rd, rd, RV_REG_T1, ctx);
+		}
+		if (!is64 && !aux->verifier_zext)
+			emit_zext_32(rd, ctx);
+		break;
+	case BPF_ALU | BPF_OR | BPF_K:
+	case BPF_ALU64 | BPF_OR | BPF_K:
+		if (is_12b_int(imm)) {
+			emit(rv_ori(rd, rd, imm), ctx);
+		} else {
+			emit_imm(RV_REG_T1, imm, ctx);
+			emit_or(rd, rd, RV_REG_T1, ctx);
+		}
+		if (!is64 && !aux->verifier_zext)
+			emit_zext_32(rd, ctx);
+		break;
+	case BPF_ALU | BPF_XOR | BPF_K:
+	case BPF_ALU64 | BPF_XOR | BPF_K:
+		if (is_12b_int(imm)) {
+			emit(rv_xori(rd, rd, imm), ctx);
+		} else {
+			emit_imm(RV_REG_T1, imm, ctx);
+			emit_xor(rd, rd, RV_REG_T1, ctx);
+		}
+		if (!is64 && !aux->verifier_zext)
+			emit_zext_32(rd, ctx);
+		break;
+	case BPF_ALU | BPF_MUL | BPF_K:
+	case BPF_ALU64 | BPF_MUL | BPF_K:
+		emit_imm(RV_REG_T1, imm, ctx);
+		emit(is64 ? rv_mul(rd, rd, RV_REG_T1) :
+		     rv_mulw(rd, rd, RV_REG_T1), ctx);
+		if (!is64 && !aux->verifier_zext)
+			emit_zext_32(rd, ctx);
+		break;
+	case BPF_ALU | BPF_DIV | BPF_K:
+	case BPF_ALU64 | BPF_DIV | BPF_K:
+		emit_imm(RV_REG_T1, imm, ctx);
+		emit(is64 ? rv_divu(rd, rd, RV_REG_T1) :
+		     rv_divuw(rd, rd, RV_REG_T1), ctx);
+		if (!is64 && !aux->verifier_zext)
+			emit_zext_32(rd, ctx);
+		break;
+	case BPF_ALU | BPF_MOD | BPF_K:
+	case BPF_ALU64 | BPF_MOD | BPF_K:
+		emit_imm(RV_REG_T1, imm, ctx);
+		emit(is64 ? rv_remu(rd, rd, RV_REG_T1) :
+		     rv_remuw(rd, rd, RV_REG_T1), ctx);
+		if (!is64 && !aux->verifier_zext)
+			emit_zext_32(rd, ctx);
+		break;
+	case BPF_ALU | BPF_LSH | BPF_K:
+	case BPF_ALU64 | BPF_LSH | BPF_K:
+		emit_slli(rd, rd, imm, ctx);
+
+		if (!is64 && !aux->verifier_zext)
+			emit_zext_32(rd, ctx);
+		break;
+	case BPF_ALU | BPF_RSH | BPF_K:
+	case BPF_ALU64 | BPF_RSH | BPF_K:
+		if (is64)
+			emit_srli(rd, rd, imm, ctx);
+		else
+			emit(rv_srliw(rd, rd, imm), ctx);
+
+		if (!is64 && !aux->verifier_zext)
+			emit_zext_32(rd, ctx);
+		break;
+	case BPF_ALU | BPF_ARSH | BPF_K:
+	case BPF_ALU64 | BPF_ARSH | BPF_K:
+		if (is64)
+			emit_srai(rd, rd, imm, ctx);
+		else
+			emit(rv_sraiw(rd, rd, imm), ctx);
+
+		if (!is64 && !aux->verifier_zext)
+			emit_zext_32(rd, ctx);
+		break;
+
+	/* JUMP off */
+	case BPF_JMP | BPF_JA:
+		rvoff = rv_offset(i, off, ctx);
+		ret = emit_jump_and_link(RV_REG_ZERO, rvoff, true, ctx);
+		if (ret)
+			return ret;
+		break;
+
+	/* IF (dst COND src) JUMP off */
+	case BPF_JMP | BPF_JEQ | BPF_X:
+	case BPF_JMP32 | BPF_JEQ | BPF_X:
+	case BPF_JMP | BPF_JGT | BPF_X:
+	case BPF_JMP32 | BPF_JGT | BPF_X:
+	case BPF_JMP | BPF_JLT | BPF_X:
+	case BPF_JMP32 | BPF_JLT | BPF_X:
+	case BPF_JMP | BPF_JGE | BPF_X:
+	case BPF_JMP32 | BPF_JGE | BPF_X:
+	case BPF_JMP | BPF_JLE | BPF_X:
+	case BPF_JMP32 | BPF_JLE | BPF_X:
+	case BPF_JMP | BPF_JNE | BPF_X:
+	case BPF_JMP32 | BPF_JNE | BPF_X:
+	case BPF_JMP | BPF_JSGT | BPF_X:
+	case BPF_JMP32 | BPF_JSGT | BPF_X:
+	case BPF_JMP | BPF_JSLT | BPF_X:
+	case BPF_JMP32 | BPF_JSLT | BPF_X:
+	case BPF_JMP | BPF_JSGE | BPF_X:
+	case BPF_JMP32 | BPF_JSGE | BPF_X:
+	case BPF_JMP | BPF_JSLE | BPF_X:
+	case BPF_JMP32 | BPF_JSLE | BPF_X:
+	case BPF_JMP | BPF_JSET | BPF_X:
+	case BPF_JMP32 | BPF_JSET | BPF_X:
+		rvoff = rv_offset(i, off, ctx);
+		if (!is64) {
+			s = ctx->ninsns;
+			if (is_signed_bpf_cond(BPF_OP(code)))
+				emit_sext_32_rd_rs(&rd, &rs, ctx);
+			else
+				emit_zext_32_rd_rs(&rd, &rs, ctx);
+			e = ctx->ninsns;
+
+			/* Adjust for extra insns */
+			rvoff -= ninsns_rvoff(e - s);
+		}
+
+		if (BPF_OP(code) == BPF_JSET) {
+			/* Adjust for and */
+			rvoff -= 4;
+			emit_and(RV_REG_T1, rd, rs, ctx);
+			emit_branch(BPF_JNE, RV_REG_T1, RV_REG_ZERO, rvoff,
+				    ctx);
+		} else {
+			emit_branch(BPF_OP(code), rd, rs, rvoff, ctx);
+		}
+		break;
+
+	/* IF (dst COND imm) JUMP off */
+	case BPF_JMP | BPF_JEQ | BPF_K:
+	case BPF_JMP32 | BPF_JEQ | BPF_K:
+	case BPF_JMP | BPF_JGT | BPF_K:
+	case BPF_JMP32 | BPF_JGT | BPF_K:
+	case BPF_JMP | BPF_JLT | BPF_K:
+	case BPF_JMP32 | BPF_JLT | BPF_K:
+	case BPF_JMP | BPF_JGE | BPF_K:
+	case BPF_JMP32 | BPF_JGE | BPF_K:
+	case BPF_JMP | BPF_JLE | BPF_K:
+	case BPF_JMP32 | BPF_JLE | BPF_K:
+	case BPF_JMP | BPF_JNE | BPF_K:
+	case BPF_JMP32 | BPF_JNE | BPF_K:
+	case BPF_JMP | BPF_JSGT | BPF_K:
+	case BPF_JMP32 | BPF_JSGT | BPF_K:
+	case BPF_JMP | BPF_JSLT | BPF_K:
+	case BPF_JMP32 | BPF_JSLT | BPF_K:
+	case BPF_JMP | BPF_JSGE | BPF_K:
+	case BPF_JMP32 | BPF_JSGE | BPF_K:
+	case BPF_JMP | BPF_JSLE | BPF_K:
+	case BPF_JMP32 | BPF_JSLE | BPF_K:
+		rvoff = rv_offset(i, off, ctx);
+		s = ctx->ninsns;
+		if (imm) {
+			emit_imm(RV_REG_T1, imm, ctx);
+			rs = RV_REG_T1;
+		} else {
+			/* If imm is 0, simply use zero register. */
+			rs = RV_REG_ZERO;
+		}
+		if (!is64) {
+			if (is_signed_bpf_cond(BPF_OP(code)))
+				emit_sext_32_rd(&rd, ctx);
+			else
+				emit_zext_32_rd_t1(&rd, ctx);
+		}
+		e = ctx->ninsns;
+
+		/* Adjust for extra insns */
+		rvoff -= ninsns_rvoff(e - s);
+		emit_branch(BPF_OP(code), rd, rs, rvoff, ctx);
+		break;
+
+	case BPF_JMP | BPF_JSET | BPF_K:
+	case BPF_JMP32 | BPF_JSET | BPF_K:
+		rvoff = rv_offset(i, off, ctx);
+		s = ctx->ninsns;
+		if (is_12b_int(imm)) {
+			emit_andi(RV_REG_T1, rd, imm, ctx);
+		} else {
+			emit_imm(RV_REG_T1, imm, ctx);
+			emit_and(RV_REG_T1, rd, RV_REG_T1, ctx);
+		}
+		/* For jset32, we should clear the upper 32 bits of t1, but
+		 * sign-extension is sufficient here and saves one instruction,
+		 * as t1 is used only in comparison against zero.
+		 */
+		if (!is64 && imm < 0)
+			emit_addiw(RV_REG_T1, RV_REG_T1, 0, ctx);
+		e = ctx->ninsns;
+		rvoff -= ninsns_rvoff(e - s);
+		emit_branch(BPF_JNE, RV_REG_T1, RV_REG_ZERO, rvoff, ctx);
+		break;
+
+	/* function call */
+	case BPF_JMP | BPF_CALL:
+	{
+		bool fixed_addr;
+		u64 addr;
+
+		mark_call(ctx);
+		ret = bpf_jit_get_func_addr(ctx->prog, insn, extra_pass,
+					    &addr, &fixed_addr);
+		if (ret < 0)
+			return ret;
+
+		ret = emit_call(addr, fixed_addr, ctx);
+		if (ret)
+			return ret;
+
+		if (insn->src_reg != BPF_PSEUDO_CALL)
+			emit_mv(bpf_to_rv_reg(BPF_REG_0, ctx), RV_REG_A0, ctx);
+		break;
+	}
+	/* tail call */
+	case BPF_JMP | BPF_TAIL_CALL:
+		if (emit_bpf_tail_call(i, ctx))
+			return -1;
+		break;
+
+	/* function return */
+	case BPF_JMP | BPF_EXIT:
+		if (i == ctx->prog->len - 1)
+			break;
+
+		rvoff = epilogue_offset(ctx);
+		ret = emit_jump_and_link(RV_REG_ZERO, rvoff, true, ctx);
+		if (ret)
+			return ret;
+		break;
+
+	/* dst = imm64 */
+	case BPF_LD | BPF_IMM | BPF_DW:
+	{
+		struct bpf_insn insn1 = insn[1];
+		u64 imm64;
+
+		imm64 = (u64)insn1.imm << 32 | (u32)imm;
+		if (bpf_pseudo_func(insn)) {
+			/* fixed-length insns for extra jit pass */
+			ret = emit_addr(rd, imm64, extra_pass, ctx);
+			if (ret)
+				return ret;
+		} else {
+			emit_imm(rd, imm64, ctx);
+		}
+
+		return 1;
+	}
+
+	/* LDX: dst = *(size *)(src + off) */
+	case BPF_LDX | BPF_MEM | BPF_B:
+	case BPF_LDX | BPF_MEM | BPF_H:
+	case BPF_LDX | BPF_MEM | BPF_W:
+	case BPF_LDX | BPF_MEM | BPF_DW:
+	case BPF_LDX | BPF_PROBE_MEM | BPF_B:
+	case BPF_LDX | BPF_PROBE_MEM | BPF_H:
+	case BPF_LDX | BPF_PROBE_MEM | BPF_W:
+	case BPF_LDX | BPF_PROBE_MEM | BPF_DW:
+	{
+		int insn_len, insns_start;
+
+		switch (BPF_SIZE(code)) {
+		case BPF_B:
+			if (is_12b_int(off)) {
+				insns_start = ctx->ninsns;
+				emit(rv_lbu(rd, off, rs), ctx);
+				insn_len = ctx->ninsns - insns_start;
+				break;
+			}
+
+			emit_imm(RV_REG_T1, off, ctx);
+			emit_add(RV_REG_T1, RV_REG_T1, rs, ctx);
+			insns_start = ctx->ninsns;
+			emit(rv_lbu(rd, 0, RV_REG_T1), ctx);
+			insn_len = ctx->ninsns - insns_start;
+			if (insn_is_zext(&insn[1]))
+				return 1;
+			break;
+		case BPF_H:
+			if (is_12b_int(off)) {
+				insns_start = ctx->ninsns;
+				emit(rv_lhu(rd, off, rs), ctx);
+				insn_len = ctx->ninsns - insns_start;
+				break;
+			}
+
+			emit_imm(RV_REG_T1, off, ctx);
+			emit_add(RV_REG_T1, RV_REG_T1, rs, ctx);
+			insns_start = ctx->ninsns;
+			emit(rv_lhu(rd, 0, RV_REG_T1), ctx);
+			insn_len = ctx->ninsns - insns_start;
+			if (insn_is_zext(&insn[1]))
+				return 1;
+			break;
+		case BPF_W:
+			if (is_12b_int(off)) {
+				insns_start = ctx->ninsns;
+				emit(rv_lwu(rd, off, rs), ctx);
+				insn_len = ctx->ninsns - insns_start;
+				break;
+			}
+
+			emit_imm(RV_REG_T1, off, ctx);
+			emit_add(RV_REG_T1, RV_REG_T1, rs, ctx);
+			insns_start = ctx->ninsns;
+			emit(rv_lwu(rd, 0, RV_REG_T1), ctx);
+			insn_len = ctx->ninsns - insns_start;
+			if (insn_is_zext(&insn[1]))
+				return 1;
+			break;
+		case BPF_DW:
+			if (is_12b_int(off)) {
+				insns_start = ctx->ninsns;
+				emit_ld(rd, off, rs, ctx);
+				insn_len = ctx->ninsns - insns_start;
+				break;
+			}
+
+			emit_imm(RV_REG_T1, off, ctx);
+			emit_add(RV_REG_T1, RV_REG_T1, rs, ctx);
+			insns_start = ctx->ninsns;
+			emit_ld(rd, 0, RV_REG_T1, ctx);
+			insn_len = ctx->ninsns - insns_start;
+			break;
+		}
+
+		ret = add_exception_handler(insn, ctx, rd, insn_len);
+		if (ret)
+			return ret;
+		break;
+	}
+	/* speculation barrier */
+	case BPF_ST | BPF_NOSPEC:
+		break;
+
+	/* ST: *(size *)(dst + off) = imm */
+	case BPF_ST | BPF_MEM | BPF_B:
+		emit_imm(RV_REG_T1, imm, ctx);
+		if (is_12b_int(off)) {
+			emit(rv_sb(rd, off, RV_REG_T1), ctx);
+			break;
+		}
+
+		emit_imm(RV_REG_T2, off, ctx);
+		emit_add(RV_REG_T2, RV_REG_T2, rd, ctx);
+		emit(rv_sb(RV_REG_T2, 0, RV_REG_T1), ctx);
+		break;
+
+	case BPF_ST | BPF_MEM | BPF_H:
+		emit_imm(RV_REG_T1, imm, ctx);
+		if (is_12b_int(off)) {
+			emit(rv_sh(rd, off, RV_REG_T1), ctx);
+			break;
+		}
+
+		emit_imm(RV_REG_T2, off, ctx);
+		emit_add(RV_REG_T2, RV_REG_T2, rd, ctx);
+		emit(rv_sh(RV_REG_T2, 0, RV_REG_T1), ctx);
+		break;
+	case BPF_ST | BPF_MEM | BPF_W:
+		emit_imm(RV_REG_T1, imm, ctx);
+		if (is_12b_int(off)) {
+			emit_sw(rd, off, RV_REG_T1, ctx);
+			break;
+		}
+
+		emit_imm(RV_REG_T2, off, ctx);
+		emit_add(RV_REG_T2, RV_REG_T2, rd, ctx);
+		emit_sw(RV_REG_T2, 0, RV_REG_T1, ctx);
+		break;
+	case BPF_ST | BPF_MEM | BPF_DW:
+		emit_imm(RV_REG_T1, imm, ctx);
+		if (is_12b_int(off)) {
+			emit_sd(rd, off, RV_REG_T1, ctx);
+			break;
+		}
+
+		emit_imm(RV_REG_T2, off, ctx);
+		emit_add(RV_REG_T2, RV_REG_T2, rd, ctx);
+		emit_sd(RV_REG_T2, 0, RV_REG_T1, ctx);
+		break;
+
+	/* STX: *(size *)(dst + off) = src */
+	case BPF_STX | BPF_MEM | BPF_B:
+		if (is_12b_int(off)) {
+			emit(rv_sb(rd, off, rs), ctx);
+			break;
+		}
+
+		emit_imm(RV_REG_T1, off, ctx);
+		emit_add(RV_REG_T1, RV_REG_T1, rd, ctx);
+		emit(rv_sb(RV_REG_T1, 0, rs), ctx);
+		break;
+	case BPF_STX | BPF_MEM | BPF_H:
+		if (is_12b_int(off)) {
+			emit(rv_sh(rd, off, rs), ctx);
+			break;
+		}
+
+		emit_imm(RV_REG_T1, off, ctx);
+		emit_add(RV_REG_T1, RV_REG_T1, rd, ctx);
+		emit(rv_sh(RV_REG_T1, 0, rs), ctx);
+		break;
+	case BPF_STX | BPF_MEM | BPF_W:
+		if (is_12b_int(off)) {
+			emit_sw(rd, off, rs, ctx);
+			break;
+		}
+
+		emit_imm(RV_REG_T1, off, ctx);
+		emit_add(RV_REG_T1, RV_REG_T1, rd, ctx);
+		emit_sw(RV_REG_T1, 0, rs, ctx);
+		break;
+	case BPF_STX | BPF_MEM | BPF_DW:
+		if (is_12b_int(off)) {
+			emit_sd(rd, off, rs, ctx);
+			break;
+		}
+
+		emit_imm(RV_REG_T1, off, ctx);
+		emit_add(RV_REG_T1, RV_REG_T1, rd, ctx);
+		emit_sd(RV_REG_T1, 0, rs, ctx);
+		break;
+	case BPF_STX | BPF_ATOMIC | BPF_W:
+	case BPF_STX | BPF_ATOMIC | BPF_DW:
+		emit_atomic(rd, rs, off, imm,
+			    BPF_SIZE(code) == BPF_DW, ctx);
+		break;
+	default:
+		pr_err("bpf-jit: unknown opcode %02x\n", code);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+void bpf_jit_build_prologue(struct rv_jit_context *ctx)
+{
+	int stack_adjust = 0, store_offset, bpf_stack_adjust;
+
+	bpf_stack_adjust = round_up(ctx->prog->aux->stack_depth, 16);
+	if (bpf_stack_adjust)
+		mark_fp(ctx);
+
+	if (seen_reg(RV_REG_RA, ctx))
+		stack_adjust += 8;
+	stack_adjust += 8; /* RV_REG_FP */
+	if (seen_reg(RV_REG_S1, ctx))
+		stack_adjust += 8;
+	if (seen_reg(RV_REG_S2, ctx))
+		stack_adjust += 8;
+	if (seen_reg(RV_REG_S3, ctx))
+		stack_adjust += 8;
+	if (seen_reg(RV_REG_S4, ctx))
+		stack_adjust += 8;
+	if (seen_reg(RV_REG_S5, ctx))
+		stack_adjust += 8;
+	if (seen_reg(RV_REG_S6, ctx))
+		stack_adjust += 8;
+
+	stack_adjust = round_up(stack_adjust, 16);
+	stack_adjust += bpf_stack_adjust;
+
+	store_offset = stack_adjust - 8;
+
+	/* First instruction is always setting the tail-call-counter
+	 * (TCC) register. This instruction is skipped for tail calls.
+	 * Force using a 4-byte (non-compressed) instruction.
+	 */
+	emit(rv_addi(RV_REG_TCC, RV_REG_ZERO, MAX_TAIL_CALL_CNT), ctx);
+
+	emit_addi(RV_REG_SP, RV_REG_SP, -stack_adjust, ctx);
+
+	if (seen_reg(RV_REG_RA, ctx)) {
+		emit_sd(RV_REG_SP, store_offset, RV_REG_RA, ctx);
+		store_offset -= 8;
+	}
+	emit_sd(RV_REG_SP, store_offset, RV_REG_FP, ctx);
+	store_offset -= 8;
+	if (seen_reg(RV_REG_S1, ctx)) {
+		emit_sd(RV_REG_SP, store_offset, RV_REG_S1, ctx);
+		store_offset -= 8;
+	}
+	if (seen_reg(RV_REG_S2, ctx)) {
+		emit_sd(RV_REG_SP, store_offset, RV_REG_S2, ctx);
+		store_offset -= 8;
+	}
+	if (seen_reg(RV_REG_S3, ctx)) {
+		emit_sd(RV_REG_SP, store_offset, RV_REG_S3, ctx);
+		store_offset -= 8;
+	}
+	if (seen_reg(RV_REG_S4, ctx)) {
+		emit_sd(RV_REG_SP, store_offset, RV_REG_S4, ctx);
+		store_offset -= 8;
+	}
+	if (seen_reg(RV_REG_S5, ctx)) {
+		emit_sd(RV_REG_SP, store_offset, RV_REG_S5, ctx);
+		store_offset -= 8;
+	}
+	if (seen_reg(RV_REG_S6, ctx)) {
+		emit_sd(RV_REG_SP, store_offset, RV_REG_S6, ctx);
+		store_offset -= 8;
+	}
+
+	emit_addi(RV_REG_FP, RV_REG_SP, stack_adjust, ctx);
+
+	if (bpf_stack_adjust)
+		emit_addi(RV_REG_S5, RV_REG_SP, bpf_stack_adjust, ctx);
+
+	/* Program contains calls and tail calls, so RV_REG_TCC need
+	 * to be saved across calls.
+	 */
+	if (seen_tail_call(ctx) && seen_call(ctx))
+		emit_mv(RV_REG_TCC_SAVED, RV_REG_TCC, ctx);
+
+	ctx->stack_size = stack_adjust;
+}
+
+void bpf_jit_build_epilogue(struct rv_jit_context *ctx)
+{
+	__build_epilogue(false, ctx);
+}
diff --git a/arch/riscv/net/bpf_jit_core.c b/arch/riscv/net/bpf_jit_core.c
new file mode 100644
index 000000000..7a26a3e1c
--- /dev/null
+++ b/arch/riscv/net/bpf_jit_core.c
@@ -0,0 +1,206 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Common functionality for RV32 and RV64 BPF JIT compilers
+ *
+ * Copyright (c) 2019 Björn Töpel <bjorn.topel@gmail.com>
+ *
+ */
+
+#include <linux/bpf.h>
+#include <linux/filter.h>
+#include "bpf_jit.h"
+
+/* Number of iterations to try until offsets converge. */
+#define NR_JIT_ITERATIONS	32
+
+static int build_body(struct rv_jit_context *ctx, bool extra_pass, int *offset)
+{
+	const struct bpf_prog *prog = ctx->prog;
+	int i;
+
+	for (i = 0; i < prog->len; i++) {
+		const struct bpf_insn *insn = &prog->insnsi[i];
+		int ret;
+
+		ret = bpf_jit_emit_insn(insn, ctx, extra_pass);
+		/* BPF_LD | BPF_IMM | BPF_DW: skip the next instruction. */
+		if (ret > 0)
+			i++;
+		if (offset)
+			offset[i] = ctx->ninsns;
+		if (ret < 0)
+			return ret;
+	}
+	return 0;
+}
+
+bool bpf_jit_needs_zext(void)
+{
+	return true;
+}
+
+struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
+{
+	unsigned int prog_size = 0, extable_size = 0;
+	bool tmp_blinded = false, extra_pass = false;
+	struct bpf_prog *tmp, *orig_prog = prog;
+	int pass = 0, prev_ninsns = 0, i;
+	struct rv_jit_data *jit_data;
+	struct rv_jit_context *ctx;
+
+	if (!prog->jit_requested)
+		return orig_prog;
+
+	tmp = bpf_jit_blind_constants(prog);
+	if (IS_ERR(tmp))
+		return orig_prog;
+	if (tmp != prog) {
+		tmp_blinded = true;
+		prog = tmp;
+	}
+
+	jit_data = prog->aux->jit_data;
+	if (!jit_data) {
+		jit_data = kzalloc(sizeof(*jit_data), GFP_KERNEL);
+		if (!jit_data) {
+			prog = orig_prog;
+			goto out;
+		}
+		prog->aux->jit_data = jit_data;
+	}
+
+	ctx = &jit_data->ctx;
+
+	if (ctx->offset) {
+		extra_pass = true;
+		prog_size = sizeof(*ctx->insns) * ctx->ninsns;
+		goto skip_init_ctx;
+	}
+
+	ctx->prog = prog;
+	ctx->offset = kcalloc(prog->len, sizeof(int), GFP_KERNEL);
+	if (!ctx->offset) {
+		prog = orig_prog;
+		goto out_offset;
+	}
+
+	if (build_body(ctx, extra_pass, NULL)) {
+		prog = orig_prog;
+		goto out_offset;
+	}
+
+	for (i = 0; i < prog->len; i++) {
+		prev_ninsns += 32;
+		ctx->offset[i] = prev_ninsns;
+	}
+
+	for (i = 0; i < NR_JIT_ITERATIONS; i++) {
+		pass++;
+		ctx->ninsns = 0;
+
+		bpf_jit_build_prologue(ctx);
+		ctx->prologue_len = ctx->ninsns;
+
+		if (build_body(ctx, extra_pass, ctx->offset)) {
+			prog = orig_prog;
+			goto out_offset;
+		}
+
+		ctx->epilogue_offset = ctx->ninsns;
+		bpf_jit_build_epilogue(ctx);
+
+		if (ctx->ninsns == prev_ninsns) {
+			if (jit_data->header)
+				break;
+			/* obtain the actual image size */
+			extable_size = prog->aux->num_exentries *
+				sizeof(struct exception_table_entry);
+			prog_size = sizeof(*ctx->insns) * ctx->ninsns;
+
+			jit_data->header =
+				bpf_jit_binary_alloc(prog_size + extable_size,
+						     &jit_data->image,
+						     sizeof(u32),
+						     bpf_fill_ill_insns);
+			if (!jit_data->header) {
+				prog = orig_prog;
+				goto out_offset;
+			}
+
+			ctx->insns = (u16 *)jit_data->image;
+			/*
+			 * Now, when the image is allocated, the image can
+			 * potentially shrink more (auipc/jalr -> jal).
+			 */
+		}
+		prev_ninsns = ctx->ninsns;
+	}
+
+	if (i == NR_JIT_ITERATIONS) {
+		pr_err("bpf-jit: image did not converge in <%d passes!\n", i);
+		if (jit_data->header)
+			bpf_jit_binary_free(jit_data->header);
+		prog = orig_prog;
+		goto out_offset;
+	}
+
+	if (extable_size)
+		prog->aux->extable = (void *)ctx->insns + prog_size;
+
+skip_init_ctx:
+	pass++;
+	ctx->ninsns = 0;
+	ctx->nexentries = 0;
+
+	bpf_jit_build_prologue(ctx);
+	if (build_body(ctx, extra_pass, NULL)) {
+		bpf_jit_binary_free(jit_data->header);
+		prog = orig_prog;
+		goto out_offset;
+	}
+	bpf_jit_build_epilogue(ctx);
+
+	if (bpf_jit_enable > 1)
+		bpf_jit_dump(prog->len, prog_size, pass, ctx->insns);
+
+	prog->bpf_func = (void *)ctx->insns;
+	prog->jited = 1;
+	prog->jited_len = prog_size;
+
+	bpf_flush_icache(jit_data->header, ctx->insns + ctx->ninsns);
+
+	if (!prog->is_func || extra_pass) {
+		bpf_jit_binary_lock_ro(jit_data->header);
+		for (i = 0; i < prog->len; i++)
+			ctx->offset[i] = ninsns_rvoff(ctx->offset[i]);
+		bpf_prog_fill_jited_linfo(prog, ctx->offset);
+out_offset:
+		kfree(ctx->offset);
+		kfree(jit_data);
+		prog->aux->jit_data = NULL;
+	}
+out:
+
+	if (tmp_blinded)
+		bpf_jit_prog_release_other(prog, prog == orig_prog ?
+					   tmp : orig_prog);
+	return prog;
+}
+
+u64 bpf_jit_alloc_exec_limit(void)
+{
+	return BPF_JIT_REGION_SIZE;
+}
+
+void *bpf_jit_alloc_exec(unsigned long size)
+{
+	return __vmalloc_node_range(size, PAGE_SIZE, BPF_JIT_REGION_START,
+				    BPF_JIT_REGION_END, GFP_KERNEL,
+				    PAGE_KERNEL, 0, NUMA_NO_NODE,
+				    __builtin_return_address(0));
+}
+
+void bpf_jit_free_exec(void *addr)
+{
+	return vfree(addr);
+}
diff --git a/arch/riscv/purgatory/.gitignore b/arch/riscv/purgatory/.gitignore
new file mode 100644
index 000000000..6e4dfb024
--- /dev/null
+++ b/arch/riscv/purgatory/.gitignore
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
+purgatory.chk
+purgatory.ro
diff --git a/arch/riscv/purgatory/Makefile b/arch/riscv/purgatory/Makefile
new file mode 100644
index 000000000..6574c91c9
--- /dev/null
+++ b/arch/riscv/purgatory/Makefile
@@ -0,0 +1,92 @@
+# SPDX-License-Identifier: GPL-2.0
+OBJECT_FILES_NON_STANDARD := y
+
+purgatory-y := purgatory.o sha256.o entry.o string.o ctype.o memcpy.o memset.o
+
+targets += $(purgatory-y)
+PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y))
+
+$(obj)/string.o: $(srctree)/lib/string.c FORCE
+	$(call if_changed_rule,cc_o_c)
+
+$(obj)/ctype.o: $(srctree)/lib/ctype.c FORCE
+	$(call if_changed_rule,cc_o_c)
+
+$(obj)/memcpy.o: $(srctree)/arch/riscv/lib/memcpy.S FORCE
+	$(call if_changed_rule,as_o_S)
+
+$(obj)/memset.o: $(srctree)/arch/riscv/lib/memset.S FORCE
+	$(call if_changed_rule,as_o_S)
+
+$(obj)/sha256.o: $(srctree)/lib/crypto/sha256.c FORCE
+	$(call if_changed_rule,cc_o_c)
+
+CFLAGS_sha256.o := -D__DISABLE_EXPORTS
+CFLAGS_string.o := -D__DISABLE_EXPORTS
+CFLAGS_ctype.o := -D__DISABLE_EXPORTS
+
+# When profile-guided optimization is enabled, llvm emits two different
+# overlapping text sections, which is not supported by kexec. Remove profile
+# optimization flags.
+KBUILD_CFLAGS := $(filter-out -fprofile-sample-use=% -fprofile-use=%,$(KBUILD_CFLAGS))
+
+# When linking purgatory.ro with -r unresolved symbols are not checked,
+# also link a purgatory.chk binary without -r to check for unresolved symbols.
+PURGATORY_LDFLAGS := -e purgatory_start -z nodefaultlib
+LDFLAGS_purgatory.ro := -r $(PURGATORY_LDFLAGS)
+LDFLAGS_purgatory.chk := $(PURGATORY_LDFLAGS)
+targets += purgatory.ro purgatory.chk
+
+# Sanitizer, etc. runtimes are unavailable and cannot be linked here.
+GCOV_PROFILE	:= n
+KASAN_SANITIZE	:= n
+UBSAN_SANITIZE	:= n
+KCSAN_SANITIZE	:= n
+KCOV_INSTRUMENT := n
+
+# These are adjustments to the compiler flags used for objects that
+# make up the standalone purgatory.ro
+
+PURGATORY_CFLAGS_REMOVE := -mcmodel=kernel
+PURGATORY_CFLAGS := -mcmodel=medany -ffreestanding -fno-zero-initialized-in-bss
+PURGATORY_CFLAGS += $(DISABLE_STACKLEAK_PLUGIN) -DDISABLE_BRANCH_PROFILING
+PURGATORY_CFLAGS += -fno-stack-protector -g0
+
+# Default KBUILD_CFLAGS can have -pg option set when FTRACE is enabled. That
+# in turn leaves some undefined symbols like __fentry__ in purgatory and not
+# sure how to relocate those.
+ifdef CONFIG_FUNCTION_TRACER
+PURGATORY_CFLAGS_REMOVE		+= $(CC_FLAGS_FTRACE)
+endif
+
+ifdef CONFIG_STACKPROTECTOR
+PURGATORY_CFLAGS_REMOVE		+= -fstack-protector
+endif
+
+ifdef CONFIG_STACKPROTECTOR_STRONG
+PURGATORY_CFLAGS_REMOVE		+= -fstack-protector-strong
+endif
+
+CFLAGS_REMOVE_purgatory.o	+= $(PURGATORY_CFLAGS_REMOVE)
+CFLAGS_purgatory.o		+= $(PURGATORY_CFLAGS)
+
+CFLAGS_REMOVE_sha256.o		+= $(PURGATORY_CFLAGS_REMOVE)
+CFLAGS_sha256.o			+= $(PURGATORY_CFLAGS)
+
+CFLAGS_REMOVE_string.o		+= $(PURGATORY_CFLAGS_REMOVE)
+CFLAGS_string.o			+= $(PURGATORY_CFLAGS)
+
+CFLAGS_REMOVE_ctype.o		+= $(PURGATORY_CFLAGS_REMOVE)
+CFLAGS_ctype.o			+= $(PURGATORY_CFLAGS)
+
+asflags-remove-y		+= $(foreach x, -g -gdwarf-4 -gdwarf-5, $(x) -Wa,$(x))
+
+$(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE
+		$(call if_changed,ld)
+
+$(obj)/purgatory.chk: $(obj)/purgatory.ro FORCE
+		$(call if_changed,ld)
+
+$(obj)/kexec-purgatory.o: $(obj)/purgatory.ro $(obj)/purgatory.chk
+
+obj-y += kexec-purgatory.o
diff --git a/arch/riscv/purgatory/entry.S b/arch/riscv/purgatory/entry.S
new file mode 100644
index 000000000..0194f4554
--- /dev/null
+++ b/arch/riscv/purgatory/entry.S
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * purgatory: Runs between two kernels
+ *
+ * Copyright (C) 2022 Huawei Technologies Co, Ltd.
+ *
+ * Author: Li Zhengyu (lizhengyu3@huawei.com)
+ *
+ */
+
+.macro	size, sym:req
+	.size \sym, . - \sym
+.endm
+
+.text
+
+.globl purgatory_start
+purgatory_start:
+
+	lla	sp, .Lstack
+	mv	s0, a0	/* The hartid of the current hart */
+	mv	s1, a1	/* Phys address of the FDT image */
+
+	jal	purgatory
+
+	/* Start new image. */
+	mv	a0, s0
+	mv	a1, s1
+	ld	a2, riscv_kernel_entry
+	jr	a2
+
+size purgatory_start
+
+.align 4
+	.rept	256
+	.quad	0
+	.endr
+.Lstack:
+
+.data
+
+.globl riscv_kernel_entry
+riscv_kernel_entry:
+	.quad	0
+size riscv_kernel_entry
+
+.end
diff --git a/arch/riscv/purgatory/kexec-purgatory.S b/arch/riscv/purgatory/kexec-purgatory.S
new file mode 100644
index 000000000..0e9188815
--- /dev/null
+++ b/arch/riscv/purgatory/kexec-purgatory.S
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+	.section .rodata, "a"
+
+	.align	8
+kexec_purgatory:
+	.globl	kexec_purgatory
+	.incbin	"arch/riscv/purgatory/purgatory.ro"
+.Lkexec_purgatroy_end:
+
+	.align	8
+kexec_purgatory_size:
+	.globl	kexec_purgatory_size
+	.quad	.Lkexec_purgatroy_end - kexec_purgatory
diff --git a/arch/riscv/purgatory/purgatory.c b/arch/riscv/purgatory/purgatory.c
new file mode 100644
index 000000000..80596ab5f
--- /dev/null
+++ b/arch/riscv/purgatory/purgatory.c
@@ -0,0 +1,45 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * purgatory: Runs between two kernels
+ *
+ * Copyright (C) 2022 Huawei Technologies Co, Ltd.
+ *
+ * Author: Li Zhengyu (lizhengyu3@huawei.com)
+ *
+ */
+
+#include <linux/purgatory.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <asm/string.h>
+
+u8 purgatory_sha256_digest[SHA256_DIGEST_SIZE] __section(".kexec-purgatory");
+
+struct kexec_sha_region purgatory_sha_regions[KEXEC_SEGMENT_MAX] __section(".kexec-purgatory");
+
+static int verify_sha256_digest(void)
+{
+	struct kexec_sha_region *ptr, *end;
+	struct sha256_state ss;
+	u8 digest[SHA256_DIGEST_SIZE];
+
+	sha256_init(&ss);
+	end = purgatory_sha_regions + ARRAY_SIZE(purgatory_sha_regions);
+	for (ptr = purgatory_sha_regions; ptr < end; ptr++)
+		sha256_update(&ss, (uint8_t *)(ptr->start), ptr->len);
+	sha256_final(&ss, digest);
+	if (memcmp(digest, purgatory_sha256_digest, sizeof(digest)) != 0)
+		return 1;
+	return 0;
+}
+
+/* workaround for a warning with -Wmissing-prototypes */
+void purgatory(void);
+
+void purgatory(void)
+{
+	if (verify_sha256_digest())
+		for (;;)
+			/* loop forever */
+			;
+}